* [PATCH 00/31] Move LRU page reclaim from zones to nodes v8
@ 2016-07-01 20:01 Mel Gorman
2016-07-01 20:01 ` [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats Mel Gorman
` (31 more replies)
0 siblings, 32 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
(Sorry for the resend, I accidentally sent the branch that still had the
Signed-off-by's from mmotm still applied which is incorrect.)
Previous releases double accounted LRU stats on the zone and the node
because it was required by should_reclaim_retry. The last patch in the
series removes the double accounting. It's not integrated with the series
as reviewers may not like the solution. If not, it can be safely dropped
without a major impact to the results.
Changelog since v7
o Rebase onto current mmots
o Avoid double accounting of stats in node and zone
o Kswapd will avoid more reclaim if an eligible zone is available
o Remove some duplications of sc->reclaim_idx and classzone_idx
o Print per-node stats in zoneinfo
Changelog since v6
o Correct reclaim_idx when direct reclaiming for memcg
o Also account LRU pages per zone for compaction/reclaim
o Add page_pgdat helper with more efficient lookup
o Init pgdat LRU lock only once
o Slight optimisation to wake_all_kswapds
o Always wake kcompactd when kswapd is going to sleep
o Rebase to mmotm as of June 15th, 2016
Changelog since v5
o Rebase and adjust to changes
Changelog since v4
o Rebase on top of v3 of page allocator optimisation series
Changelog since v3
o Rebase on top of the page allocator optimisation series
o Remove RFC tag
This is the latest version of a series that moves LRUs from the zones to
the node that is based upon 4.7-rc4 with Andrew's tree applied. While this
is a current rebase, the test results were based on mmotm as of June 23rd.
Conceptually, this series is simple but there are a lot of details. Some
of the broad motivations for this are;
1. The residency of a page partially depends on what zone the page was
allocated from. This is partially combatted by the fair zone allocation
policy but that is a partial solution that introduces overhead in the
page allocator paths.
2. Currently, reclaim on node 0 behaves slightly different to node 1. For
example, direct reclaim scans in zonelist order and reclaims even if
the zone is over the high watermark regardless of the age of pages
in that LRU. Kswapd on the other hand starts reclaim on the highest
unbalanced zone. A difference in distribution of file/anon pages due
to when they were allocated results can result in a difference in
again. While the fair zone allocation policy mitigates some of the
problems here, the page reclaim results on a multi-zone node will
always be different to a single-zone node.
it was scheduled on as a result.
3. kswapd and the page allocator scan zones in the opposite order to
avoid interfering with each other but it's sensitive to timing. This
mitigates the page allocator using pages that were allocated very recently
in the ideal case but it's sensitive to timing. When kswapd is allocating
from lower zones then it's great but during the rebalancing of the highest
zone, the page allocator and kswapd interfere with each other. It's worse
if the highest zone is small and difficult to balance.
4. slab shrinkers are node-based which makes it harder to identify the exact
relationship between slab reclaim and LRU reclaim.
The reason we have zone-based reclaim is that we used to have
large highmem zones in common configurations and it was necessary
to quickly find ZONE_NORMAL pages for reclaim. Today, this is much
less of a concern as machines with lots of memory will (or should) use
64-bit kernels. Combinations of 32-bit hardware and 64-bit hardware are
rare. Machines that do use highmem should have relatively low highmem:lowmem
ratios than we worried about in the past.
Conceptually, moving to node LRUs should be easier to understand. The
page allocator plays fewer tricks to game reclaim and reclaim behaves
similarly on all nodes.
The series has been tested on a 16 core UMA machine and a 2-socket 48
core NUMA machine. The UMA results are presented in most cases as the NUMA
machine behaved similarly.
pagealloc
---------
This is a microbenchmark that shows the benefit of removing the fair zone
allocation policy. It was tested uip to order-4 but only orders 0 and 1 are
shown as the other orders were comparable.
4.7.0-rc4 4.7.0-rc4
mmotm-20160623 nodelru-v8
Min total-odr0-1 490.00 ( 0.00%) 463.00 ( 5.51%)
Min total-odr0-2 349.00 ( 0.00%) 325.00 ( 6.88%)
Min total-odr0-4 288.00 ( 0.00%) 272.00 ( 5.56%)
Min total-odr0-8 250.00 ( 0.00%) 235.00 ( 6.00%)
Min total-odr0-16 234.00 ( 0.00%) 222.00 ( 5.13%)
Min total-odr0-32 223.00 ( 0.00%) 205.00 ( 8.07%)
Min total-odr0-64 217.00 ( 0.00%) 202.00 ( 6.91%)
Min total-odr0-128 214.00 ( 0.00%) 207.00 ( 3.27%)
Min total-odr0-256 242.00 ( 0.00%) 242.00 ( 0.00%)
Min total-odr0-512 272.00 ( 0.00%) 265.00 ( 2.57%)
Min total-odr0-1024 290.00 ( 0.00%) 283.00 ( 2.41%)
Min total-odr0-2048 302.00 ( 0.00%) 296.00 ( 1.99%)
Min total-odr0-4096 311.00 ( 0.00%) 306.00 ( 1.61%)
Min total-odr0-8192 314.00 ( 0.00%) 309.00 ( 1.59%)
Min total-odr0-16384 315.00 ( 0.00%) 309.00 ( 1.90%)
Min total-odr1-1 741.00 ( 0.00%) 716.00 ( 3.37%)
Min total-odr1-2 565.00 ( 0.00%) 524.00 ( 7.26%)
Min total-odr1-4 457.00 ( 0.00%) 427.00 ( 6.56%)
Min total-odr1-8 408.00 ( 0.00%) 371.00 ( 9.07%)
Min total-odr1-16 383.00 ( 0.00%) 344.00 ( 10.18%)
Min total-odr1-32 378.00 ( 0.00%) 334.00 ( 11.64%)
Min total-odr1-64 383.00 ( 0.00%) 334.00 ( 12.79%)
Min total-odr1-128 376.00 ( 0.00%) 342.00 ( 9.04%)
Min total-odr1-256 381.00 ( 0.00%) 343.00 ( 9.97%)
Min total-odr1-512 388.00 ( 0.00%) 349.00 ( 10.05%)
Min total-odr1-1024 386.00 ( 0.00%) 356.00 ( 7.77%)
Min total-odr1-2048 389.00 ( 0.00%) 362.00 ( 6.94%)
Min total-odr1-4096 389.00 ( 0.00%) 362.00 ( 6.94%)
Min total-odr1-8192 389.00 ( 0.00%) 362.00 ( 6.94%)
This shows a steady improvement throughout. The primary benefit is from
reduced system CPU usage which is obvious from the overall times;
4.7.0-rc4 4.7.0-rc4
mmotm-20160623nodelru-v8
User 191.39 191.61
System 2651.24 2504.48
Elapsed 2904.40 2757.01
The vmstats also showed that the fair zone allocation policy was definitely
removed as can be seen here;
4.7.0-rc3 4.7.0-rc3
mmotm-20160623 nodelru-v8
DMA32 allocs 28794771816 0
Normal allocs 48432582848 77227356392
Movable allocs 0 0
tiobench on ext4
----------------
tiobench is a benchmark that artifically benefits if old pages remain resident
while new pages get reclaimed. The fair zone allocation policy mitigates this
problem so pages age fairly. While the benchmark has problems, it is important
that tiobench performance remains constant as it implies that page aging
problems that the fair zone allocation policy fixes are not re-introduced.
4.7.0-rc4 4.7.0-rc4
mmotm-20160623 nodelru-v8
Min PotentialReadSpeed 89.65 ( 0.00%) 90.34 ( 0.77%)
Min SeqRead-MB/sec-1 82.68 ( 0.00%) 83.13 ( 0.54%)
Min SeqRead-MB/sec-2 72.76 ( 0.00%) 72.15 ( -0.84%)
Min SeqRead-MB/sec-4 75.13 ( 0.00%) 74.23 ( -1.20%)
Min SeqRead-MB/sec-8 64.91 ( 0.00%) 65.25 ( 0.52%)
Min SeqRead-MB/sec-16 62.24 ( 0.00%) 62.76 ( 0.84%)
Min RandRead-MB/sec-1 0.88 ( 0.00%) 0.95 ( 7.95%)
Min RandRead-MB/sec-2 0.95 ( 0.00%) 0.94 ( -1.05%)
Min RandRead-MB/sec-4 1.43 ( 0.00%) 1.46 ( 2.10%)
Min RandRead-MB/sec-8 1.61 ( 0.00%) 1.58 ( -1.86%)
Min RandRead-MB/sec-16 1.80 ( 0.00%) 1.93 ( 7.22%)
Min SeqWrite-MB/sec-1 76.41 ( 0.00%) 78.84 ( 3.18%)
Min SeqWrite-MB/sec-2 74.11 ( 0.00%) 73.35 ( -1.03%)
Min SeqWrite-MB/sec-4 80.05 ( 0.00%) 78.69 ( -1.70%)
Min SeqWrite-MB/sec-8 72.88 ( 0.00%) 71.38 ( -2.06%)
Min SeqWrite-MB/sec-16 75.91 ( 0.00%) 75.81 ( -0.13%)
Min RandWrite-MB/sec-1 1.18 ( 0.00%) 1.12 ( -5.08%)
Min RandWrite-MB/sec-2 1.02 ( 0.00%) 1.02 ( 0.00%)
Min RandWrite-MB/sec-4 1.05 ( 0.00%) 0.99 ( -5.71%)
Min RandWrite-MB/sec-8 0.89 ( 0.00%) 0.92 ( 3.37%)
Min RandWrite-MB/sec-16 0.92 ( 0.00%) 0.89 ( -3.26%)
This shows that the series has little or not impact on tiobench which is
desirable. It indicates that the fair zone allocation policy was removed
in a manner that didn't reintroduce one class of page aging bug. There
were only minor differences in overall reclaim activity
4.7.0-rc4 4.7.0-rc4
mmotm-20160623nodelru-v8
Minor Faults 645838 644036
Major Faults 573 593
Swap Ins 0 0
Swap Outs 0 0
Allocation stalls 24 0
DMA allocs 0 0
DMA32 allocs 46041453 44154171
Normal allocs 78053072 79865782
Movable allocs 0 0
Direct pages scanned 10969 54504
Kswapd pages scanned 93375144 93250583
Kswapd pages reclaimed 93372243 93247714
Direct pages reclaimed 10969 54504
Kswapd efficiency 99% 99%
Kswapd velocity 13741.015 13711.950
Direct efficiency 100% 100%
Direct velocity 1.614 8.014
Percentage direct scans 0% 0%
Zone normal velocity 8641.875 13719.964
Zone dma32 velocity 5100.754 0.000
Zone dma velocity 0.000 0.000
Page writes by reclaim 0.000 0.000
Page writes file 0 0
Page writes anon 0 0
Page reclaim immediate 37 54
kswapd activity was roughly comparable. There were differences in direct
reclaim activity but negligible in the context of the overall workload
(velocity of 8 pages per second with the patches applied, 1.6 pages per
second in the baseline kernel).
pgbench read-only large configuration on ext4
---------------------------------------------
pgbench is a database benchmark that can be sensitive to page reclaim
decisions. This also checks if removing the fair zone allocation policy
is safe
pgbench Transactions
4.7.0-rc4 4.7.0-rc4
mmotm-20160623 nodelru-v8
Hmean 1 188.26 ( 0.00%) 189.78 ( 0.81%)
Hmean 5 330.66 ( 0.00%) 328.69 ( -0.59%)
Hmean 12 370.32 ( 0.00%) 380.72 ( 2.81%)
Hmean 21 368.89 ( 0.00%) 369.00 ( 0.03%)
Hmean 30 382.14 ( 0.00%) 360.89 ( -5.56%)
Hmean 32 428.87 ( 0.00%) 432.96 ( 0.95%)
Negligible differences again. As with tiobench, overall reclaim activity
was comparable.
bonnie++ on ext4
----------------
No interesting performance difference, negligible differences on reclaim
stats.
paralleldd on ext4
------------------
This workload uses varying numbers of dd instances to read large amounts of
data from disk.
4.7.0-rc3 4.7.0-rc3
mmotm-20160615 nodelru-v7r17
Amean Elapsd-1 181.57 ( 0.00%) 179.63 ( 1.07%)
Amean Elapsd-3 188.29 ( 0.00%) 183.68 ( 2.45%)
Amean Elapsd-5 188.02 ( 0.00%) 181.73 ( 3.35%)
Amean Elapsd-7 186.07 ( 0.00%) 184.11 ( 1.05%)
Amean Elapsd-12 188.16 ( 0.00%) 183.51 ( 2.47%)
Amean Elapsd-16 189.03 ( 0.00%) 181.27 ( 4.10%)
4.7.0-rc3 4.7.0-rc3
mmotm-20160615nodelru-v7r17
User 1439.23 1433.37
System 8332.31 8216.01
Elapsed 3619.80 3532.69
There is a slight gain in performance, some of which is from the reduced system
CPU usage. There areminor differences in reclaim activity but nothing significant
4.7.0-rc3 4.7.0-rc3
mmotm-20160615nodelru-v7r17
Minor Faults 362486 358215
Major Faults 1143 1113
Swap Ins 26 0
Swap Outs 2920 482
DMA allocs 0 0
DMA32 allocs 31568814 28598887
Normal allocs 46539922 49514444
Movable allocs 0 0
Allocation stalls 0 0
Direct pages scanned 0 0
Kswapd pages scanned 40886878 40849710
Kswapd pages reclaimed 40869923 40835207
Direct pages reclaimed 0 0
Kswapd efficiency 99% 99%
Kswapd velocity 11295.342 11563.344
Direct efficiency 100% 100%
Direct velocity 0.000 0.000
Slabs scanned 131673 126099
Direct inode steals 57 60
Kswapd inode steals 762 18
It basically shows that kswapd was active at roughly the same rate in
both kernels. There was also comparable slab scanning activity and direct
reclaim was avoided in both cases. There appears to be a large difference
in numbers of inodes reclaimed but the workload has few active inodes and
is likely a timing artifact. It's interesting to note that the node-lru
did not swap in any pages but given the low swap activity, it's unlikely
to be significant.
stutter
-------
stutter simulates a simple workload. One part uses a lot of anonymous
memory, a second measures mmap latency and a third copies a large file.
The primary metric is checking for mmap latency.
stutter
4.7.0-rc4 4.7.0-rc4
mmotm-20160623 nodelru-v8
Min mmap 16.6283 ( 0.00%) 16.1394 ( 2.94%)
1st-qrtle mmap 54.7570 ( 0.00%) 55.2975 ( -0.99%)
2nd-qrtle mmap 57.3163 ( 0.00%) 57.5230 ( -0.36%)
3rd-qrtle mmap 58.9976 ( 0.00%) 58.0537 ( 1.60%)
Max-90% mmap 59.7433 ( 0.00%) 58.3910 ( 2.26%)
Max-93% mmap 60.1298 ( 0.00%) 58.4801 ( 2.74%)
Max-95% mmap 73.4112 ( 0.00%) 58.5537 ( 20.24%)
Max-99% mmap 92.8542 ( 0.00%) 58.9673 ( 36.49%)
Max mmap 1440.6569 ( 0.00%) 137.6875 ( 90.44%)
Mean mmap 59.3493 ( 0.00%) 55.5153 ( 6.46%)
Best99%Mean mmap 57.2121 ( 0.00%) 55.4194 ( 3.13%)
Best95%Mean mmap 55.9113 ( 0.00%) 55.2813 ( 1.13%)
Best90%Mean mmap 55.6199 ( 0.00%) 55.1044 ( 0.93%)
Best50%Mean mmap 53.2183 ( 0.00%) 52.8330 ( 0.72%)
Best10%Mean mmap 45.9842 ( 0.00%) 42.3740 ( 7.85%)
Best5%Mean mmap 43.2256 ( 0.00%) 38.8660 ( 10.09%)
Best1%Mean mmap 32.9388 ( 0.00%) 27.7577 ( 15.73%)
This shows a number of improvements with the worst-case outlier greatly
improved.
Some of the vmstats are interesting
4.7.0-rc4 4.7.0-rc4
mmotm-20160623nodelru-v8
Swap Ins 163 239
Swap Outs 0 0
Allocation stalls 2603 0
DMA allocs 0 0
DMA32 allocs 618719206 1303037965
Normal allocs 891235743 229914091
Movable allocs 0 0
Direct pages scanned 216787 3173
Kswapd pages scanned 50719775 41732250
Kswapd pages reclaimed 41541765 41731168
Direct pages reclaimed 209159 3173
Kswapd efficiency 81% 99%
Kswapd velocity 16859.554 14231.043
Direct efficiency 96% 100%
Direct velocity 72.061 1.082
Percentage direct scans 0% 0%
Zone normal velocity 8431.777 14232.125
Zone dma32 velocity 8499.838 0.000
Zone dma velocity 0.000 0.000
Page writes by reclaim 6215049.000 0.000
Page writes file 6215049 0
Page writes anon 0 0
Page reclaim immediate 70673 143
Sector Reads 81940800 81489388
Sector Writes 100158984 99161860
Page rescued immediate 0 0
Slabs scanned 1366954 21196
While this is not guaranteed in all cases, this particular test showed
a large reduction in direct reclaim activity. It's also worth noting
that no page writes were issued from reclaim context.
This series is not without its hazards. There are at least three areas
that I'm concerned with even though I could not reproduce any problems in
that area.
1. Reclaim/compaction is going to be affected because the amount of reclaim is
no longer targetted at a specific zone. Compaction works on a per-zone basis
so there is no guarantee that reclaiming a few THP's worth page pages will
have a positive impact on compaction success rates.
2. The Slab/LRU reclaim ratio is affected because the frequency the shrinkers
are called is now different. This may or may not be a problem but if it
is, it'll be because shrinkers are not called enough and some balancing
is required.
3. The anon/file reclaim ratio may be affected. Pages about to be dirtied are
distributed between zones and the fair zone allocation policy used to do
something very similar for anon. The distribution is now different but not
necessarily in any way that matters but it's still worth bearing in mind.
Documentation/cgroup-v1/memcg_test.txt | 4 +-
Documentation/cgroup-v1/memory.txt | 4 +-
arch/s390/appldata/appldata_mem.c | 2 +-
arch/tile/mm/pgtable.c | 18 +-
drivers/base/node.c | 77 ++-
drivers/staging/android/lowmemorykiller.c | 12 +-
drivers/staging/lustre/lustre/osc/osc_cache.c | 6 +-
fs/fs-writeback.c | 4 +-
fs/fuse/file.c | 8 +-
fs/nfs/internal.h | 2 +-
fs/nfs/write.c | 2 +-
fs/proc/meminfo.c | 20 +-
include/linux/backing-dev.h | 2 +-
include/linux/memcontrol.h | 61 +-
include/linux/mm.h | 5 +
include/linux/mm_inline.h | 35 +-
include/linux/mm_types.h | 2 +-
include/linux/mmzone.h | 155 +++--
include/linux/swap.h | 24 +-
include/linux/topology.h | 2 +-
include/linux/vm_event_item.h | 14 +-
include/linux/vmstat.h | 111 +++-
include/linux/writeback.h | 2 +-
include/trace/events/vmscan.h | 63 +-
include/trace/events/writeback.h | 10 +-
kernel/power/snapshot.c | 10 +-
kernel/sysctl.c | 4 +-
mm/backing-dev.c | 15 +-
mm/compaction.c | 50 +-
mm/filemap.c | 16 +-
mm/huge_memory.c | 12 +-
mm/internal.h | 11 +-
mm/khugepaged.c | 14 +-
mm/memcontrol.c | 215 +++----
mm/memory-failure.c | 4 +-
mm/memory_hotplug.c | 7 +-
mm/mempolicy.c | 2 +-
mm/migrate.c | 35 +-
mm/mlock.c | 12 +-
mm/page-writeback.c | 123 ++--
mm/page_alloc.c | 371 +++++------
mm/page_idle.c | 4 +-
mm/rmap.c | 26 +-
mm/shmem.c | 14 +-
mm/swap.c | 64 +-
mm/swap_state.c | 4 +-
mm/util.c | 4 +-
mm/vmscan.c | 879 +++++++++++++-------------
mm/vmstat.c | 398 +++++++++---
mm/workingset.c | 54 +-
50 files changed, 1674 insertions(+), 1319 deletions(-)
--
2.6.4
Mel Gorman (31):
mm, vmstat: add infrastructure for per-node vmstats
mm, vmscan: move lru_lock to the node
mm, vmscan: move LRU lists to node
mm, vmscan: begin reclaiming pages on a per-node basis
mm, vmscan: have kswapd only scan based on the highest requested zone
mm, vmscan: make kswapd reclaim in terms of nodes
mm, vmscan: remove balance gap
mm, vmscan: simplify the logic deciding whether kswapd sleeps
mm, vmscan: by default have direct reclaim only shrink once per node
mm, vmscan: remove duplicate logic clearing node congestion and dirty
state
mm: vmscan: do not reclaim from kswapd if there is any eligible zone
mm, vmscan: make shrink_node decisions more node-centric
mm, memcg: move memcg limit enforcement from zones to nodes
mm, workingset: make working set detection node-aware
mm, page_alloc: consider dirtyable memory in terms of nodes
mm: move page mapped accounting to the node
mm: rename NR_ANON_PAGES to NR_ANON_MAPPED
mm: move most file-based accounting to the node
mm: move vmscan writes and file write accounting to the node
mm, vmscan: only wakeup kswapd once per node for the requested
classzone
mm, page_alloc: Wake kswapd based on the highest eligible zone
mm: convert zone_reclaim to node_reclaim
mm, vmscan: Avoid passing in classzone_idx unnecessarily to
shrink_node
mm, vmscan: Avoid passing in classzone_idx unnecessarily to
compaction_ready
mm, vmscan: add classzone information to tracepoints
mm, page_alloc: remove fair zone allocation policy
mm: page_alloc: cache the last node whose dirty limit is reached
mm: vmstat: replace __count_zone_vm_events with a zone id equivalent
mm: vmstat: account per-zone stalls and pages skipped during reclaim
mm, vmstat: print node-based stats in zoneinfo file
mm, vmstat: Remove zone and node double accounting by approximating
retries
Documentation/cgroup-v1/memcg_test.txt | 4 +-
Documentation/cgroup-v1/memory.txt | 4 +-
arch/s390/appldata/appldata_mem.c | 2 +-
arch/tile/mm/pgtable.c | 18 +-
drivers/base/node.c | 77 ++-
drivers/staging/android/lowmemorykiller.c | 12 +-
drivers/staging/lustre/lustre/osc/osc_cache.c | 6 +-
fs/fs-writeback.c | 4 +-
fs/fuse/file.c | 8 +-
fs/nfs/internal.h | 2 +-
fs/nfs/write.c | 2 +-
fs/proc/meminfo.c | 20 +-
include/linux/backing-dev.h | 2 +-
include/linux/memcontrol.h | 61 +-
include/linux/mm.h | 5 +
include/linux/mm_inline.h | 35 +-
include/linux/mm_types.h | 2 +-
include/linux/mmzone.h | 155 +++--
include/linux/swap.h | 24 +-
include/linux/topology.h | 2 +-
include/linux/vm_event_item.h | 14 +-
include/linux/vmstat.h | 111 +++-
include/linux/writeback.h | 2 +-
include/trace/events/vmscan.h | 63 +-
include/trace/events/writeback.h | 10 +-
kernel/power/snapshot.c | 10 +-
kernel/sysctl.c | 4 +-
mm/backing-dev.c | 15 +-
mm/compaction.c | 50 +-
mm/filemap.c | 16 +-
mm/huge_memory.c | 12 +-
mm/internal.h | 11 +-
mm/khugepaged.c | 14 +-
mm/memcontrol.c | 215 +++----
mm/memory-failure.c | 4 +-
mm/memory_hotplug.c | 7 +-
mm/mempolicy.c | 2 +-
mm/migrate.c | 35 +-
mm/mlock.c | 12 +-
mm/page-writeback.c | 123 ++--
mm/page_alloc.c | 371 +++++------
mm/page_idle.c | 4 +-
mm/rmap.c | 26 +-
mm/shmem.c | 14 +-
mm/swap.c | 64 +-
mm/swap_state.c | 4 +-
mm/util.c | 4 +-
mm/vmscan.c | 879 +++++++++++++-------------
mm/vmstat.c | 398 +++++++++---
mm/workingset.c | 54 +-
50 files changed, 1674 insertions(+), 1319 deletions(-)
--
2.6.4
^ permalink raw reply [flat|nested] 90+ messages in thread
* [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-04 23:50 ` Minchan Kim
2016-07-01 20:01 ` [PATCH 02/31] mm, vmscan: move lru_lock to the node Mel Gorman
` (30 subsequent siblings)
31 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
VM statistic counters for reclaim decisions are zone-based. If the kernel
is to reclaim on a per-node basis then we need to track per-node
statistics but there is no infrastructure for that. The most notable
change is that the old node_page_state is renamed to
sum_zone_node_page_state. The new node_page_state takes a pglist_data and
uses per-node stats but none exist yet. There is some renaming such as
vm_stat to vm_zone_stat and the addition of vm_node_stat and the renaming
of mod_state to mod_zone_state. Otherwise, this is mostly a mechanical
patch with no functional change. There is a lot of similarity between the
node and zone helpers which is unfortunate but there was no obvious way of
reusing the code and maintaining type safety.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
drivers/base/node.c | 76 +++++++------
include/linux/mm.h | 5 +
include/linux/mmzone.h | 13 +++
include/linux/vmstat.h | 92 +++++++++++++---
mm/page_alloc.c | 10 +-
mm/vmstat.c | 282 +++++++++++++++++++++++++++++++++++++++++++++----
mm/workingset.c | 9 +-
7 files changed, 411 insertions(+), 76 deletions(-)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index ed0ef0f69489..92d8e090c5b3 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -74,16 +74,16 @@ static ssize_t node_read_meminfo(struct device *dev,
nid, K(i.totalram),
nid, K(i.freeram),
nid, K(i.totalram - i.freeram),
- nid, K(node_page_state(nid, NR_ACTIVE_ANON) +
- node_page_state(nid, NR_ACTIVE_FILE)),
- nid, K(node_page_state(nid, NR_INACTIVE_ANON) +
- node_page_state(nid, NR_INACTIVE_FILE)),
- nid, K(node_page_state(nid, NR_ACTIVE_ANON)),
- nid, K(node_page_state(nid, NR_INACTIVE_ANON)),
- nid, K(node_page_state(nid, NR_ACTIVE_FILE)),
- nid, K(node_page_state(nid, NR_INACTIVE_FILE)),
- nid, K(node_page_state(nid, NR_UNEVICTABLE)),
- nid, K(node_page_state(nid, NR_MLOCK)));
+ nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_ANON) +
+ sum_zone_node_page_state(nid, NR_ACTIVE_FILE)),
+ nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_ANON) +
+ sum_zone_node_page_state(nid, NR_INACTIVE_FILE)),
+ nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_ANON)),
+ nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_ANON)),
+ nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_FILE)),
+ nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_FILE)),
+ nid, K(sum_zone_node_page_state(nid, NR_UNEVICTABLE)),
+ nid, K(sum_zone_node_page_state(nid, NR_MLOCK)));
#ifdef CONFIG_HIGHMEM
n += sprintf(buf + n,
@@ -117,31 +117,31 @@ static ssize_t node_read_meminfo(struct device *dev,
"Node %d ShmemPmdMapped: %8lu kB\n"
#endif
,
- nid, K(node_page_state(nid, NR_FILE_DIRTY)),
- nid, K(node_page_state(nid, NR_WRITEBACK)),
- nid, K(node_page_state(nid, NR_FILE_PAGES)),
- nid, K(node_page_state(nid, NR_FILE_MAPPED)),
- nid, K(node_page_state(nid, NR_ANON_PAGES)),
+ nid, K(sum_zone_node_page_state(nid, NR_FILE_DIRTY)),
+ nid, K(sum_zone_node_page_state(nid, NR_WRITEBACK)),
+ nid, K(sum_zone_node_page_state(nid, NR_FILE_PAGES)),
+ nid, K(sum_zone_node_page_state(nid, NR_FILE_MAPPED)),
+ nid, K(sum_zone_node_page_state(nid, NR_ANON_PAGES)),
nid, K(i.sharedram),
- nid, node_page_state(nid, NR_KERNEL_STACK) *
+ nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK) *
THREAD_SIZE / 1024,
- nid, K(node_page_state(nid, NR_PAGETABLE)),
- nid, K(node_page_state(nid, NR_UNSTABLE_NFS)),
- nid, K(node_page_state(nid, NR_BOUNCE)),
- nid, K(node_page_state(nid, NR_WRITEBACK_TEMP)),
- nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE) +
- node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
- nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE)),
+ nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)),
+ nid, K(sum_zone_node_page_state(nid, NR_UNSTABLE_NFS)),
+ nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
+ nid, K(sum_zone_node_page_state(nid, NR_WRITEBACK_TEMP)),
+ nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE) +
+ sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
+ nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE)),
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
- nid, K(node_page_state(nid, NR_ANON_THPS) *
+ nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
+ nid, K(sum_zone_node_page_state(nid, NR_ANON_THPS) *
HPAGE_PMD_NR),
- nid, K(node_page_state(nid, NR_SHMEM_THPS) *
+ nid, K(sum_zone_node_page_state(nid, NR_SHMEM_THPS) *
HPAGE_PMD_NR),
- nid, K(node_page_state(nid, NR_SHMEM_PMDMAPPED) *
+ nid, K(sum_zone_node_page_state(nid, NR_SHMEM_PMDMAPPED) *
HPAGE_PMD_NR));
#else
- nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
+ nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
#endif
n += hugetlb_report_node_meminfo(nid, buf + n);
return n;
@@ -160,12 +160,12 @@ static ssize_t node_read_numastat(struct device *dev,
"interleave_hit %lu\n"
"local_node %lu\n"
"other_node %lu\n",
- node_page_state(dev->id, NUMA_HIT),
- node_page_state(dev->id, NUMA_MISS),
- node_page_state(dev->id, NUMA_FOREIGN),
- node_page_state(dev->id, NUMA_INTERLEAVE_HIT),
- node_page_state(dev->id, NUMA_LOCAL),
- node_page_state(dev->id, NUMA_OTHER));
+ sum_zone_node_page_state(dev->id, NUMA_HIT),
+ sum_zone_node_page_state(dev->id, NUMA_MISS),
+ sum_zone_node_page_state(dev->id, NUMA_FOREIGN),
+ sum_zone_node_page_state(dev->id, NUMA_INTERLEAVE_HIT),
+ sum_zone_node_page_state(dev->id, NUMA_LOCAL),
+ sum_zone_node_page_state(dev->id, NUMA_OTHER));
}
static DEVICE_ATTR(numastat, S_IRUGO, node_read_numastat, NULL);
@@ -173,12 +173,18 @@ static ssize_t node_read_vmstat(struct device *dev,
struct device_attribute *attr, char *buf)
{
int nid = dev->id;
+ struct pglist_data *pgdat = NODE_DATA(nid);
int i;
int n = 0;
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
n += sprintf(buf+n, "%s %lu\n", vmstat_text[i],
- node_page_state(nid, i));
+ sum_zone_node_page_state(nid, i));
+
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+ n += sprintf(buf+n, "%s %lu\n",
+ vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
+ node_page_state(pgdat, i));
return n;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b21e5f30378e..dd79aa2800a3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -933,6 +933,11 @@ static inline struct zone *page_zone(const struct page *page)
return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
}
+static inline pg_data_t *page_pgdat(const struct page *page)
+{
+ return NODE_DATA(page_to_nid(page));
+}
+
#ifdef SECTION_IN_PAGE_FLAGS
static inline void set_page_section(struct page *page, unsigned long section)
{
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 19425e988bdc..078ecb81e209 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -160,6 +160,10 @@ enum zone_stat_item {
NR_FREE_CMA_PAGES,
NR_VM_ZONE_STAT_ITEMS };
+enum node_stat_item {
+ NR_VM_NODE_STAT_ITEMS
+};
+
/*
* We do arithmetic on the LRU lists in various places in the code,
* so it is important to keep the active lists LRU_ACTIVE higher in
@@ -267,6 +271,11 @@ struct per_cpu_pageset {
#endif
};
+struct per_cpu_nodestat {
+ s8 stat_threshold;
+ s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
+};
+
#endif /* !__GENERATING_BOUNDS.H */
enum zone_type {
@@ -695,6 +704,10 @@ typedef struct pglist_data {
struct list_head split_queue;
unsigned long split_queue_len;
#endif
+
+ /* Per-node vmstats */
+ struct per_cpu_nodestat __percpu *per_cpu_nodestats;
+ atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS];
} pg_data_t;
#define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages)
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index d2da8e053210..d1744aa3ab9c 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -106,20 +106,38 @@ static inline void vm_events_fold_cpu(int cpu)
zone_idx(zone), delta)
/*
- * Zone based page accounting with per cpu differentials.
+ * Zone and node-based page accounting with per cpu differentials.
*/
-extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS];
+extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS];
static inline void zone_page_state_add(long x, struct zone *zone,
enum zone_stat_item item)
{
atomic_long_add(x, &zone->vm_stat[item]);
- atomic_long_add(x, &vm_stat[item]);
+ atomic_long_add(x, &vm_zone_stat[item]);
+}
+
+static inline void node_page_state_add(long x, struct pglist_data *pgdat,
+ enum node_stat_item item)
+{
+ atomic_long_add(x, &pgdat->vm_stat[item]);
+ atomic_long_add(x, &vm_node_stat[item]);
}
static inline unsigned long global_page_state(enum zone_stat_item item)
{
- long x = atomic_long_read(&vm_stat[item]);
+ long x = atomic_long_read(&vm_zone_stat[item]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
+}
+
+static inline unsigned long global_node_page_state(enum node_stat_item item)
+{
+ long x = atomic_long_read(&vm_node_stat[item]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
@@ -161,31 +179,44 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
}
#ifdef CONFIG_NUMA
-
-extern unsigned long node_page_state(int node, enum zone_stat_item item);
-
+extern unsigned long sum_zone_node_page_state(int node,
+ enum zone_stat_item item);
+extern unsigned long node_page_state(struct pglist_data *pgdat,
+ enum node_stat_item item);
#else
-
-#define node_page_state(node, item) global_page_state(item)
-
+#define sum_zone_node_page_state(node, item) global_page_state(item)
+#define node_page_state(node, item) global_node_page_state(item)
#endif /* CONFIG_NUMA */
#define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
#define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
+#define add_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, __d)
+#define sub_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, -(__d))
#ifdef CONFIG_SMP
void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long);
void __inc_zone_page_state(struct page *, enum zone_stat_item);
void __dec_zone_page_state(struct page *, enum zone_stat_item);
+void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long);
+void __inc_node_page_state(struct page *, enum node_stat_item);
+void __dec_node_page_state(struct page *, enum node_stat_item);
+
void mod_zone_page_state(struct zone *, enum zone_stat_item, long);
void inc_zone_page_state(struct page *, enum zone_stat_item);
void dec_zone_page_state(struct page *, enum zone_stat_item);
+void mod_node_page_state(struct pglist_data *, enum node_stat_item, long);
+void inc_node_page_state(struct page *, enum node_stat_item);
+void dec_node_page_state(struct page *, enum node_stat_item);
+
extern void inc_zone_state(struct zone *, enum zone_stat_item);
+extern void inc_node_state(struct pglist_data *, enum node_stat_item);
extern void __inc_zone_state(struct zone *, enum zone_stat_item);
+extern void __inc_node_state(struct pglist_data *, enum node_stat_item);
extern void dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
+extern void __dec_node_state(struct pglist_data *, enum node_stat_item);
void quiet_vmstat(void);
void cpu_vm_stats_fold(int cpu);
@@ -213,16 +244,34 @@ static inline void __mod_zone_page_state(struct zone *zone,
zone_page_state_add(delta, zone, item);
}
+static inline void __mod_node_page_state(struct pglist_data *pgdat,
+ enum node_stat_item item, int delta)
+{
+ node_page_state_add(delta, pgdat, item);
+}
+
static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
{
atomic_long_inc(&zone->vm_stat[item]);
- atomic_long_inc(&vm_stat[item]);
+ atomic_long_inc(&vm_zone_stat[item]);
+}
+
+static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ atomic_long_inc(&pgdat->vm_stat[item]);
+ atomic_long_inc(&vm_node_stat[item]);
}
static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
{
atomic_long_dec(&zone->vm_stat[item]);
- atomic_long_dec(&vm_stat[item]);
+ atomic_long_dec(&vm_zone_stat[item]);
+}
+
+static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ atomic_long_dec(&pgdat->vm_stat[item]);
+ atomic_long_dec(&vm_node_stat[item]);
}
static inline void __inc_zone_page_state(struct page *page,
@@ -231,12 +280,26 @@ static inline void __inc_zone_page_state(struct page *page,
__inc_zone_state(page_zone(page), item);
}
+static inline void __inc_node_page_state(struct page *page,
+ enum node_stat_item item)
+{
+ __inc_node_state(page_pgdat(page), item);
+}
+
+
static inline void __dec_zone_page_state(struct page *page,
enum zone_stat_item item)
{
__dec_zone_state(page_zone(page), item);
}
+static inline void __dec_node_page_state(struct page *page,
+ enum node_stat_item item)
+{
+ __dec_node_state(page_pgdat(page), item);
+}
+
+
/*
* We only use atomic operations to update counters. So there is no need to
* disable interrupts.
@@ -245,7 +308,12 @@ static inline void __dec_zone_page_state(struct page *page,
#define dec_zone_page_state __dec_zone_page_state
#define mod_zone_page_state __mod_zone_page_state
+#define inc_node_page_state __inc_node_page_state
+#define dec_node_page_state __dec_node_page_state
+#define mod_node_page_state __mod_node_page_state
+
#define inc_zone_state __inc_zone_state
+#define inc_node_state __inc_node_state
#define dec_zone_state __dec_zone_state
#define set_pgdat_percpu_threshold(pgdat, callback) { }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 403c5dcd24da..34e46c02a406 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4247,8 +4247,8 @@ void si_meminfo_node(struct sysinfo *val, int nid)
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
managed_pages += pgdat->node_zones[zone_type].managed_pages;
val->totalram = managed_pages;
- val->sharedram = node_page_state(nid, NR_SHMEM);
- val->freeram = node_page_state(nid, NR_FREE_PAGES);
+ val->sharedram = sum_zone_node_page_state(nid, NR_SHMEM);
+ val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES);
#ifdef CONFIG_HIGHMEM
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
struct zone *zone = &pgdat->node_zones[zone_type];
@@ -5373,6 +5373,11 @@ static void __meminit setup_zone_pageset(struct zone *zone)
zone->pageset = alloc_percpu(struct per_cpu_pageset);
for_each_possible_cpu(cpu)
zone_pageset_init(zone, cpu);
+
+ if (!zone->zone_pgdat->per_cpu_nodestats) {
+ zone->zone_pgdat->per_cpu_nodestats =
+ alloc_percpu(struct per_cpu_nodestat);
+ }
}
/*
@@ -6078,6 +6083,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
reset_deferred_meminit(pgdat);
pgdat->node_id = nid;
pgdat->node_start_pfn = node_start_pfn;
+ pgdat->per_cpu_nodestats = NULL;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7997f52935c9..90b0737ee4be 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -86,8 +86,10 @@ void vm_events_fold_cpu(int cpu)
*
* vm_stat contains the global counters
*/
-atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
-EXPORT_SYMBOL(vm_stat);
+atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
+atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp;
+EXPORT_SYMBOL(vm_zone_stat);
+EXPORT_SYMBOL(vm_node_stat);
#ifdef CONFIG_SMP
@@ -172,13 +174,17 @@ void refresh_zone_stat_thresholds(void)
int threshold;
for_each_populated_zone(zone) {
+ struct pglist_data *pgdat = zone->zone_pgdat;
unsigned long max_drift, tolerate_drift;
threshold = calculate_normal_threshold(zone);
- for_each_online_cpu(cpu)
+ for_each_online_cpu(cpu) {
per_cpu_ptr(zone->pageset, cpu)->stat_threshold
= threshold;
+ per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
+ = threshold;
+ }
/*
* Only set percpu_drift_mark if there is a danger that
@@ -238,6 +244,26 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
}
EXPORT_SYMBOL(__mod_zone_page_state);
+void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
+ long delta)
+{
+ struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+ s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ long x;
+ long t;
+
+ x = delta + __this_cpu_read(*p);
+
+ t = __this_cpu_read(pcp->stat_threshold);
+
+ if (unlikely(x > t || x < -t)) {
+ node_page_state_add(x, pgdat, item);
+ x = 0;
+ }
+ __this_cpu_write(*p, x);
+}
+EXPORT_SYMBOL(__mod_node_page_state);
+
/*
* Optimized increment and decrement functions.
*
@@ -277,12 +303,34 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
}
}
+void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+ s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ s8 v, t;
+
+ v = __this_cpu_inc_return(*p);
+ t = __this_cpu_read(pcp->stat_threshold);
+ if (unlikely(v > t)) {
+ s8 overstep = t >> 1;
+
+ node_page_state_add(v + overstep, pgdat, item);
+ __this_cpu_write(*p, -overstep);
+ }
+}
+
void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
__inc_zone_state(page_zone(page), item);
}
EXPORT_SYMBOL(__inc_zone_page_state);
+void __inc_node_page_state(struct page *page, enum node_stat_item item)
+{
+ __inc_node_state(page_pgdat(page), item);
+}
+EXPORT_SYMBOL(__inc_node_page_state);
+
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
{
struct per_cpu_pageset __percpu *pcp = zone->pageset;
@@ -299,12 +347,34 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
}
}
+void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+ s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ s8 v, t;
+
+ v = __this_cpu_dec_return(*p);
+ t = __this_cpu_read(pcp->stat_threshold);
+ if (unlikely(v < - t)) {
+ s8 overstep = t >> 1;
+
+ node_page_state_add(v - overstep, pgdat, item);
+ __this_cpu_write(*p, overstep);
+ }
+}
+
void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
__dec_zone_state(page_zone(page), item);
}
EXPORT_SYMBOL(__dec_zone_page_state);
+void __dec_node_page_state(struct page *page, enum node_stat_item item)
+{
+ __dec_node_state(page_pgdat(page), item);
+}
+EXPORT_SYMBOL(__dec_node_page_state);
+
#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
/*
* If we have cmpxchg_local support then we do not need to incur the overhead
@@ -318,8 +388,8 @@ EXPORT_SYMBOL(__dec_zone_page_state);
* 1 Overstepping half of threshold
* -1 Overstepping minus half of threshold
*/
-static inline void mod_state(struct zone *zone, enum zone_stat_item item,
- long delta, int overstep_mode)
+static inline void mod_zone_state(struct zone *zone,
+ enum zone_stat_item item, long delta, int overstep_mode)
{
struct per_cpu_pageset __percpu *pcp = zone->pageset;
s8 __percpu *p = pcp->vm_stat_diff + item;
@@ -359,26 +429,88 @@ static inline void mod_state(struct zone *zone, enum zone_stat_item item,
void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
long delta)
{
- mod_state(zone, item, delta, 0);
+ mod_zone_state(zone, item, delta, 0);
}
EXPORT_SYMBOL(mod_zone_page_state);
void inc_zone_state(struct zone *zone, enum zone_stat_item item)
{
- mod_state(zone, item, 1, 1);
+ mod_zone_state(zone, item, 1, 1);
}
void inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
- mod_state(page_zone(page), item, 1, 1);
+ mod_zone_state(page_zone(page), item, 1, 1);
}
EXPORT_SYMBOL(inc_zone_page_state);
void dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
- mod_state(page_zone(page), item, -1, -1);
+ mod_zone_state(page_zone(page), item, -1, -1);
}
EXPORT_SYMBOL(dec_zone_page_state);
+
+static inline void mod_node_state(struct pglist_data *pgdat,
+ enum node_stat_item item, int delta, int overstep_mode)
+{
+ struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+ s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ long o, n, t, z;
+
+ do {
+ z = 0; /* overflow to node counters */
+
+ /*
+ * The fetching of the stat_threshold is racy. We may apply
+ * a counter threshold to the wrong the cpu if we get
+ * rescheduled while executing here. However, the next
+ * counter update will apply the threshold again and
+ * therefore bring the counter under the threshold again.
+ *
+ * Most of the time the thresholds are the same anyways
+ * for all cpus in a node.
+ */
+ t = this_cpu_read(pcp->stat_threshold);
+
+ o = this_cpu_read(*p);
+ n = delta + o;
+
+ if (n > t || n < -t) {
+ int os = overstep_mode * (t >> 1) ;
+
+ /* Overflow must be added to node counters */
+ z = n + os;
+ n = -os;
+ }
+ } while (this_cpu_cmpxchg(*p, o, n) != o);
+
+ if (z)
+ node_page_state_add(z, pgdat, item);
+}
+
+void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
+ long delta)
+{
+ mod_node_state(pgdat, item, delta, 0);
+}
+EXPORT_SYMBOL(mod_node_page_state);
+
+void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ mod_node_state(pgdat, item, 1, 1);
+}
+
+void inc_node_page_state(struct page *page, enum node_stat_item item)
+{
+ mod_node_state(page_pgdat(page), item, 1, 1);
+}
+EXPORT_SYMBOL(inc_node_page_state);
+
+void dec_node_page_state(struct page *page, enum node_stat_item item)
+{
+ mod_node_state(page_pgdat(page), item, -1, -1);
+}
+EXPORT_SYMBOL(dec_node_page_state);
#else
/*
* Use interrupt disable to serialize counter updates
@@ -424,21 +556,69 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item)
local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);
-#endif
+void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __inc_node_state(pgdat, item);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(inc_node_state);
+
+void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
+ long delta)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __mod_node_page_state(pgdat, item, delta);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_node_page_state);
+
+void inc_node_page_state(struct page *page, enum node_stat_item item)
+{
+ unsigned long flags;
+ struct pglist_data *pgdat;
+
+ pgdat = page_pgdat(page);
+ local_irq_save(flags);
+ __inc_node_state(pgdat, item);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(inc_node_page_state);
+
+void dec_node_page_state(struct page *page, enum node_stat_item item)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __dec_node_page_state(page, item);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(dec_node_page_state);
+#endif
/*
* Fold a differential into the global counters.
* Returns the number of counters updated.
*/
-static int fold_diff(int *diff)
+static int fold_diff(int *zone_diff, int *node_diff)
{
int i;
int changes = 0;
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
- if (diff[i]) {
- atomic_long_add(diff[i], &vm_stat[i]);
+ if (zone_diff[i]) {
+ atomic_long_add(zone_diff[i], &vm_zone_stat[i]);
+ changes++;
+ }
+
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+ if (node_diff[i]) {
+ atomic_long_add(node_diff[i], &vm_node_stat[i]);
changes++;
}
return changes;
@@ -462,9 +642,11 @@ static int fold_diff(int *diff)
*/
static int refresh_cpu_vm_stats(bool do_pagesets)
{
+ struct pglist_data *pgdat;
struct zone *zone;
int i;
- int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+ int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+ int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
int changes = 0;
for_each_populated_zone(zone) {
@@ -477,7 +659,7 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
if (v) {
atomic_long_add(v, &zone->vm_stat[i]);
- global_diff[i] += v;
+ global_zone_diff[i] += v;
#ifdef CONFIG_NUMA
/* 3 seconds idle till flush */
__this_cpu_write(p->expire, 3);
@@ -516,7 +698,22 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
}
#endif
}
- changes += fold_diff(global_diff);
+
+ for_each_online_pgdat(pgdat) {
+ struct per_cpu_nodestat __percpu *p = pgdat->per_cpu_nodestats;
+
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+ int v;
+
+ v = this_cpu_xchg(p->vm_node_stat_diff[i], 0);
+ if (v) {
+ atomic_long_add(v, &pgdat->vm_stat[i]);
+ global_node_diff[i] += v;
+ }
+ }
+ }
+
+ changes += fold_diff(global_zone_diff, global_node_diff);
return changes;
}
@@ -527,9 +724,11 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
*/
void cpu_vm_stats_fold(int cpu)
{
+ struct pglist_data *pgdat;
struct zone *zone;
int i;
- int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+ int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+ int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
for_each_populated_zone(zone) {
struct per_cpu_pageset *p;
@@ -543,11 +742,27 @@ void cpu_vm_stats_fold(int cpu)
v = p->vm_stat_diff[i];
p->vm_stat_diff[i] = 0;
atomic_long_add(v, &zone->vm_stat[i]);
- global_diff[i] += v;
+ global_zone_diff[i] += v;
}
}
- fold_diff(global_diff);
+ for_each_online_pgdat(pgdat) {
+ struct per_cpu_nodestat *p;
+
+ p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu);
+
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+ if (p->vm_node_stat_diff[i]) {
+ int v;
+
+ v = p->vm_node_stat_diff[i];
+ p->vm_node_stat_diff[i] = 0;
+ atomic_long_add(v, &pgdat->vm_stat[i]);
+ global_node_diff[i] += v;
+ }
+ }
+
+ fold_diff(global_zone_diff, global_node_diff);
}
/*
@@ -563,16 +778,19 @@ void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset)
int v = pset->vm_stat_diff[i];
pset->vm_stat_diff[i] = 0;
atomic_long_add(v, &zone->vm_stat[i]);
- atomic_long_add(v, &vm_stat[i]);
+ atomic_long_add(v, &vm_zone_stat[i]);
}
}
#endif
#ifdef CONFIG_NUMA
/*
- * Determine the per node value of a stat item.
+ * Determine the per node value of a stat item. This function
+ * is called frequently in a NUMA machine, so try to be as
+ * frugal as possible.
*/
-unsigned long node_page_state(int node, enum zone_stat_item item)
+unsigned long sum_zone_node_page_state(int node,
+ enum zone_stat_item item)
{
struct zone *zones = NODE_DATA(node)->node_zones;
int i;
@@ -584,6 +802,19 @@ unsigned long node_page_state(int node, enum zone_stat_item item)
return count;
}
+/*
+ * Determine the per node value of a stat item.
+ */
+unsigned long node_page_state(struct pglist_data *pgdat,
+ enum node_stat_item item)
+{
+ long x = atomic_long_read(&pgdat->vm_stat[item]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
+}
#endif
#ifdef CONFIG_COMPACTION
@@ -1287,6 +1518,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
if (*pos >= ARRAY_SIZE(vmstat_text))
return NULL;
stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
+ NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) +
NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);
#ifdef CONFIG_VM_EVENT_COUNTERS
@@ -1301,6 +1533,10 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
v[i] = global_page_state(i);
v += NR_VM_ZONE_STAT_ITEMS;
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+ v[i] = global_node_page_state(i);
+ v += NR_VM_NODE_STAT_ITEMS;
+
global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
v + NR_DIRTY_THRESHOLD);
v += NR_VM_WRITEBACK_STAT_ITEMS;
@@ -1390,7 +1626,7 @@ int vmstat_refresh(struct ctl_table *table, int write,
if (err)
return err;
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
- val = atomic_long_read(&vm_stat[i]);
+ val = atomic_long_read(&vm_zone_stat[i]);
if (val < 0) {
switch (i) {
case NR_ALLOC_BATCH:
diff --git a/mm/workingset.c b/mm/workingset.c
index 8252de4566e9..ba972ac2dfdd 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -351,12 +351,13 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc);
local_irq_enable();
- if (memcg_kmem_enabled())
+ if (memcg_kmem_enabled()) {
pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid,
LRU_ALL_FILE);
- else
- pages = node_page_state(sc->nid, NR_ACTIVE_FILE) +
- node_page_state(sc->nid, NR_INACTIVE_FILE);
+ } else {
+ pages = sum_zone_node_page_state(sc->nid, NR_ACTIVE_FILE) +
+ sum_zone_node_page_state(sc->nid, NR_INACTIVE_FILE);
+ }
/*
* Active cache pages are limited to 50% of memory, and shadow
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 02/31] mm, vmscan: move lru_lock to the node
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
2016-07-01 20:01 ` [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-05 0:03 ` Minchan Kim
2016-07-01 20:01 ` [PATCH 03/31] mm, vmscan: move LRU lists to node Mel Gorman
` (29 subsequent siblings)
31 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
Node-based reclaim requires node-based LRUs and locking. This is a
preparation patch that just moves the lru_lock to the node so later
patches are easier to review. It is a mechanical change but note this
patch makes contention worse because the LRU lock is hotter and direct
reclaim and kswapd can contend on the same lock even when reclaiming from
different zones.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
Documentation/cgroup-v1/memcg_test.txt | 4 +--
Documentation/cgroup-v1/memory.txt | 4 +--
include/linux/mm_types.h | 2 +-
include/linux/mmzone.h | 10 +++++--
mm/compaction.c | 10 +++----
mm/filemap.c | 4 +--
mm/huge_memory.c | 6 ++---
mm/memcontrol.c | 6 ++---
mm/mlock.c | 10 +++----
mm/page_alloc.c | 4 +--
mm/page_idle.c | 4 +--
mm/rmap.c | 2 +-
mm/swap.c | 30 ++++++++++-----------
mm/vmscan.c | 48 +++++++++++++++++-----------------
14 files changed, 75 insertions(+), 69 deletions(-)
diff --git a/Documentation/cgroup-v1/memcg_test.txt b/Documentation/cgroup-v1/memcg_test.txt
index 8870b0212150..78a8c2963b38 100644
--- a/Documentation/cgroup-v1/memcg_test.txt
+++ b/Documentation/cgroup-v1/memcg_test.txt
@@ -107,9 +107,9 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
8. LRU
Each memcg has its own private LRU. Now, its handling is under global
- VM's control (means that it's handled under global zone->lru_lock).
+ VM's control (means that it's handled under global zone_lru_lock).
Almost all routines around memcg's LRU is called by global LRU's
- list management functions under zone->lru_lock().
+ list management functions under zone_lru_lock().
A special function is mem_cgroup_isolate_pages(). This scans
memcg's private LRU and call __isolate_lru_page() to extract a page
diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt
index b14abf217239..946e69103cdd 100644
--- a/Documentation/cgroup-v1/memory.txt
+++ b/Documentation/cgroup-v1/memory.txt
@@ -267,11 +267,11 @@ When oom event notifier is registered, event will be delivered.
Other lock order is following:
PG_locked.
mm->page_table_lock
- zone->lru_lock
+ zone_lru_lock
lock_page_cgroup.
In many cases, just lock_page_cgroup() is called.
per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
- zone->lru_lock, it has no lock of its own.
+ zone_lru_lock, it has no lock of its own.
2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e093e1d3285b..ca2ed9a6c8d8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -118,7 +118,7 @@ struct page {
*/
union {
struct list_head lru; /* Pageout list, eg. active_list
- * protected by zone->lru_lock !
+ * protected by zone_lru_lock !
* Can be used as a generic list
* by the page owner.
*/
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 078ecb81e209..2d5087e3c034 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -93,7 +93,7 @@ struct free_area {
struct pglist_data;
/*
- * zone->lock and zone->lru_lock are two of the hottest locks in the kernel.
+ * zone->lock and the zone lru_lock are two of the hottest locks in the kernel.
* So add a wild amount of padding here to ensure that they fall into separate
* cachelines. There are very few zone structures in the machine, so space
* consumption is not a concern here.
@@ -496,7 +496,6 @@ struct zone {
/* Write-intensive fields used by page reclaim */
/* Fields commonly accessed by the page reclaim scanner */
- spinlock_t lru_lock;
struct lruvec lruvec;
/*
@@ -690,6 +689,9 @@ typedef struct pglist_data {
/* Number of pages migrated during the rate limiting time interval */
unsigned long numabalancing_migrate_nr_pages;
#endif
+ /* Write-intensive fields used from the page allocator */
+ ZONE_PADDING(_pad1_)
+ spinlock_t lru_lock;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
@@ -721,6 +723,10 @@ typedef struct pglist_data {
#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn)
#define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
+static inline spinlock_t *zone_lru_lock(struct zone *zone)
+{
+ return &zone->zone_pgdat->lru_lock;
+}
static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
{
diff --git a/mm/compaction.c b/mm/compaction.c
index 0bd53fb05162..7607efb7bee2 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -752,7 +752,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
* if contended.
*/
if (!(low_pfn % SWAP_CLUSTER_MAX)
- && compact_unlock_should_abort(&zone->lru_lock, flags,
+ && compact_unlock_should_abort(zone_lru_lock(zone), flags,
&locked, cc))
break;
@@ -813,7 +813,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
if (unlikely(__PageMovable(page)) &&
!PageIsolated(page)) {
if (locked) {
- spin_unlock_irqrestore(&zone->lru_lock,
+ spin_unlock_irqrestore(zone_lru_lock(zone),
flags);
locked = false;
}
@@ -836,7 +836,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
/* If we already hold the lock, we can skip some rechecking */
if (!locked) {
- locked = compact_trylock_irqsave(&zone->lru_lock,
+ locked = compact_trylock_irqsave(zone_lru_lock(zone),
&flags, cc);
if (!locked)
break;
@@ -899,7 +899,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
*/
if (nr_isolated) {
if (locked) {
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(zone), flags);
locked = false;
}
acct_isolated(zone, cc);
@@ -927,7 +927,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
low_pfn = end_pfn;
if (locked)
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(zone), flags);
/*
* Update the pageblock-skip information and cached scanner pfn,
diff --git a/mm/filemap.c b/mm/filemap.c
index e90c1543ec2d..7ec50bd6f88c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -95,8 +95,8 @@
* ->swap_lock (try_to_unmap_one)
* ->private_lock (try_to_unmap_one)
* ->tree_lock (try_to_unmap_one)
- * ->zone.lru_lock (follow_page->mark_page_accessed)
- * ->zone.lru_lock (check_pte_range->isolate_lru_page)
+ * ->zone_lru_lock(zone) (follow_page->mark_page_accessed)
+ * ->zone_lru_lock(zone) (check_pte_range->isolate_lru_page)
* ->private_lock (page_remove_rmap->set_page_dirty)
* ->tree_lock (page_remove_rmap->set_page_dirty)
* bdi.wb->list_lock (page_remove_rmap->set_page_dirty)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 848c16caf8f8..2f997328ae64 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1860,7 +1860,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
spin_unlock(&head->mapping->tree_lock);
}
- spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
unfreeze_page(head);
@@ -2046,7 +2046,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
lru_add_drain();
/* prevent PageLRU to go away from under us, and freeze lru stats */
- spin_lock_irqsave(&page_zone(head)->lru_lock, flags);
+ spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags);
if (mapping) {
void **pslot;
@@ -2089,7 +2089,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
spin_unlock(&pgdata->split_queue_lock);
fail: if (mapping)
spin_unlock(&mapping->tree_lock);
- spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
unfreeze_page(head);
ret = -EBUSY;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 40dfca3ef4bb..9b70f9ca8ddf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2065,7 +2065,7 @@ static void lock_page_lru(struct page *page, int *isolated)
{
struct zone *zone = page_zone(page);
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
if (PageLRU(page)) {
struct lruvec *lruvec;
@@ -2089,7 +2089,7 @@ static void unlock_page_lru(struct page *page, int isolated)
SetPageLRU(page);
add_page_to_lru_list(page, lruvec, page_lru(page));
}
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
}
static void commit_charge(struct page *page, struct mem_cgroup *memcg,
@@ -2389,7 +2389,7 @@ void memcg_kmem_uncharge(struct page *page, int order)
/*
* Because tail pages are not marked as "used", set it. We're under
- * zone->lru_lock and migration entries setup in all page mappings.
+ * zone_lru_lock and migration entries setup in all page mappings.
*/
void mem_cgroup_split_huge_fixup(struct page *head)
{
diff --git a/mm/mlock.c b/mm/mlock.c
index ef8dc9f395c4..997f63082ff5 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -188,7 +188,7 @@ unsigned int munlock_vma_page(struct page *page)
* might otherwise copy PageMlocked to part of the tail pages before
* we clear it in the head page. It also stabilizes hpage_nr_pages().
*/
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
nr_pages = hpage_nr_pages(page);
if (!TestClearPageMlocked(page))
@@ -197,14 +197,14 @@ unsigned int munlock_vma_page(struct page *page)
__mod_zone_page_state(zone, NR_MLOCK, -nr_pages);
if (__munlock_isolate_lru_page(page, true)) {
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
__munlock_isolated_page(page);
goto out;
}
__munlock_isolation_failed(page);
unlock_out:
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
out:
return nr_pages - 1;
@@ -289,7 +289,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
pagevec_init(&pvec_putback, 0);
/* Phase 1: page isolation */
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
@@ -315,7 +315,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
}
delta_munlocked = -nr + pagevec_count(&pvec_putback);
__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
/* Now we can release pins of pages that we are not munlocking */
pagevec_release(&pvec_putback);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 34e46c02a406..48b5414009ac 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5947,6 +5947,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
init_waitqueue_head(&pgdat->kcompactd_wait);
#endif
pgdat_page_ext_init(pgdat);
+ spin_lock_init(&pgdat->lru_lock);
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
@@ -6001,10 +6002,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100;
#endif
zone->name = zone_names[j];
+ zone->zone_pgdat = pgdat;
spin_lock_init(&zone->lock);
- spin_lock_init(&zone->lru_lock);
zone_seqlock_init(zone);
- zone->zone_pgdat = pgdat;
zone_pcp_init(zone);
/* For bootup, initialized properly in watermark setup */
diff --git a/mm/page_idle.c b/mm/page_idle.c
index 4ea9c4ef5146..ae11aa914e55 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -41,12 +41,12 @@ static struct page *page_idle_get_page(unsigned long pfn)
return NULL;
zone = page_zone(page);
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
if (unlikely(!PageLRU(page))) {
put_page(page);
page = NULL;
}
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
return page;
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 256e585c67ef..573253efb645 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -27,7 +27,7 @@
* mapping->i_mmap_rwsem
* anon_vma->rwsem
* mm->page_table_lock or pte_lock
- * zone->lru_lock (in mark_page_accessed, isolate_lru_page)
+ * zone_lru_lock (in mark_page_accessed, isolate_lru_page)
* swap_lock (in swap_duplicate, swap_info_get)
* mmlist_lock (in mmput, drain_mmlist and others)
* mapping->private_lock (in __set_page_dirty_buffers)
diff --git a/mm/swap.c b/mm/swap.c
index 616df4ddd870..bf37e5cfae81 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -62,12 +62,12 @@ static void __page_cache_release(struct page *page)
struct lruvec *lruvec;
unsigned long flags;
- spin_lock_irqsave(&zone->lru_lock, flags);
+ spin_lock_irqsave(zone_lru_lock(zone), flags);
lruvec = mem_cgroup_page_lruvec(page, zone);
VM_BUG_ON_PAGE(!PageLRU(page), page);
__ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, page_off_lru(page));
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(zone), flags);
}
mem_cgroup_uncharge(page);
}
@@ -189,16 +189,16 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
if (pagezone != zone) {
if (zone)
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(zone), flags);
zone = pagezone;
- spin_lock_irqsave(&zone->lru_lock, flags);
+ spin_lock_irqsave(zone_lru_lock(zone), flags);
}
lruvec = mem_cgroup_page_lruvec(page, zone);
(*move_fn)(page, lruvec, arg);
}
if (zone)
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(zone), flags);
release_pages(pvec->pages, pvec->nr, pvec->cold);
pagevec_reinit(pvec);
}
@@ -318,9 +318,9 @@ void activate_page(struct page *page)
struct zone *zone = page_zone(page);
page = compound_head(page);
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
__activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL);
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
}
#endif
@@ -448,13 +448,13 @@ void add_page_to_unevictable_list(struct page *page)
struct zone *zone = page_zone(page);
struct lruvec *lruvec;
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
lruvec = mem_cgroup_page_lruvec(page, zone);
ClearPageActive(page);
SetPageUnevictable(page);
SetPageLRU(page);
add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
}
/**
@@ -744,7 +744,7 @@ void release_pages(struct page **pages, int nr, bool cold)
* same zone. The lock is held only if zone != NULL.
*/
if (zone && ++lock_batch == SWAP_CLUSTER_MAX) {
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(zone), flags);
zone = NULL;
}
@@ -759,7 +759,7 @@ void release_pages(struct page **pages, int nr, bool cold)
if (PageCompound(page)) {
if (zone) {
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(zone), flags);
zone = NULL;
}
__put_compound_page(page);
@@ -771,11 +771,11 @@ void release_pages(struct page **pages, int nr, bool cold)
if (pagezone != zone) {
if (zone)
- spin_unlock_irqrestore(&zone->lru_lock,
+ spin_unlock_irqrestore(zone_lru_lock(zone),
flags);
lock_batch = 0;
zone = pagezone;
- spin_lock_irqsave(&zone->lru_lock, flags);
+ spin_lock_irqsave(zone_lru_lock(zone), flags);
}
lruvec = mem_cgroup_page_lruvec(page, zone);
@@ -790,7 +790,7 @@ void release_pages(struct page **pages, int nr, bool cold)
list_add(&page->lru, &pages_to_free);
}
if (zone)
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ spin_unlock_irqrestore(zone_lru_lock(zone), flags);
mem_cgroup_uncharge_list(&pages_to_free);
free_hot_cold_page_list(&pages_to_free, cold);
@@ -826,7 +826,7 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
VM_BUG_ON_PAGE(PageCompound(page_tail), page);
VM_BUG_ON_PAGE(PageLRU(page_tail), page);
VM_BUG_ON(NR_CPUS != 1 &&
- !spin_is_locked(&lruvec_zone(lruvec)->lru_lock));
+ !spin_is_locked(zone_lru_lock(lruvec_zone(lruvec))));
if (!list)
SetPageLRU(page_tail);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 21d417ccff69..e7ffcd259cc4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1349,7 +1349,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
}
/*
- * zone->lru_lock is heavily contended. Some of the functions that
+ * zone_lru_lock is heavily contended. Some of the functions that
* shrink the lists perform better by taking out a batch of pages
* and working on them outside the LRU lock.
*
@@ -1444,7 +1444,7 @@ int isolate_lru_page(struct page *page)
struct zone *zone = page_zone(page);
struct lruvec *lruvec;
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
lruvec = mem_cgroup_page_lruvec(page, zone);
if (PageLRU(page)) {
int lru = page_lru(page);
@@ -1453,7 +1453,7 @@ int isolate_lru_page(struct page *page)
del_page_from_lru_list(page, lruvec, lru);
ret = 0;
}
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
}
return ret;
}
@@ -1512,9 +1512,9 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
VM_BUG_ON_PAGE(PageLRU(page), page);
list_del(&page->lru);
if (unlikely(!page_evictable(page))) {
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
putback_lru_page(page);
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
continue;
}
@@ -1535,10 +1535,10 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
del_page_from_lru_list(page, lruvec, lru);
if (unlikely(PageCompound(page))) {
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
mem_cgroup_uncharge(page);
(*get_compound_page_dtor(page))(page);
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
} else
list_add(&page->lru, &pages_to_free);
}
@@ -1600,7 +1600,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
if (!sc->may_writepage)
isolate_mode |= ISOLATE_CLEAN;
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
&nr_scanned, sc, isolate_mode, lru);
@@ -1616,7 +1616,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
else
__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned);
}
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
if (nr_taken == 0)
return 0;
@@ -1626,7 +1626,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
&nr_writeback, &nr_immediate,
false);
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
if (global_reclaim(sc)) {
if (current_is_kswapd())
@@ -1641,7 +1641,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
mem_cgroup_uncharge_list(&page_list);
free_hot_cold_page_list(&page_list, true);
@@ -1715,9 +1715,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
* processes, from rmap.
*
* If the pages are mostly unmapped, the processing is fast and it is
- * appropriate to hold zone->lru_lock across the whole operation. But if
+ * appropriate to hold zone_lru_lock across the whole operation. But if
* the pages are mapped, the processing is slow (page_referenced()) so we
- * should drop zone->lru_lock around each page. It's impossible to balance
+ * should drop zone_lru_lock around each page. It's impossible to balance
* this, so instead we remove the pages from the LRU while processing them.
* It is safe to rely on PG_active against the non-LRU pages in here because
* nobody will play with that bit on a non-LRU page.
@@ -1754,10 +1754,10 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
del_page_from_lru_list(page, lruvec, lru);
if (unlikely(PageCompound(page))) {
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
mem_cgroup_uncharge(page);
(*get_compound_page_dtor(page))(page);
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
} else
list_add(&page->lru, pages_to_free);
}
@@ -1792,7 +1792,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
if (!sc->may_writepage)
isolate_mode |= ISOLATE_CLEAN;
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
&nr_scanned, sc, isolate_mode, lru);
@@ -1805,7 +1805,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
__mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
__count_zone_vm_events(PGREFILL, zone, nr_scanned);
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
while (!list_empty(&l_hold)) {
cond_resched();
@@ -1850,7 +1850,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
/*
* Move pages back to the lru list.
*/
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
/*
* Count referenced pages from currently used mappings as rotated,
* even though only some of them are actually re-activated. This
@@ -1862,7 +1862,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
mem_cgroup_uncharge_list(&l_hold);
free_hot_cold_page_list(&l_hold, true);
@@ -2077,7 +2077,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
reclaim_stat->recent_scanned[0] /= 2;
reclaim_stat->recent_rotated[0] /= 2;
@@ -2098,7 +2098,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
fp /= reclaim_stat->recent_rotated[1] + 1;
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
fraction[0] = ap;
fraction[1] = fp;
@@ -3791,9 +3791,9 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages)
pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
zone = pagezone;
- spin_lock_irq(&zone->lru_lock);
+ spin_lock_irq(zone_lru_lock(zone));
}
lruvec = mem_cgroup_page_lruvec(page, zone);
@@ -3814,7 +3814,7 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages)
if (zone) {
__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irq(zone_lru_lock(zone));
}
}
#endif /* CONFIG_SHMEM */
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 03/31] mm, vmscan: move LRU lists to node
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
2016-07-01 20:01 ` [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats Mel Gorman
2016-07-01 20:01 ` [PATCH 02/31] mm, vmscan: move lru_lock to the node Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-05 1:19 ` Minchan Kim
2016-07-01 20:01 ` [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis Mel Gorman
` (28 subsequent siblings)
31 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
This moves the LRU lists from the zone to the node and related data such
as counters, tracing, congestion tracking and writeback tracking.
Unfortunately, due to reclaim and compaction retry logic, it is necessary
to account for the number of LRU pages on both zone and node logic. Most
reclaim logic is based on the node counters but the retry logic uses the
zone counters which do not distinguish inactive and inactive sizes. It
would be possible to leave the LRU counters on a per-zone basis but it's a
heavier calculation across multiple cache lines that is much more frequent
than the retry checks.
Other than the LRU counters, this is mostly a mechanical patch but note
that it introduces a number of anomalies. For example, the scans are
per-zone but using per-node counters. We also mark a node as congested
when a zone is congested. This causes weird problems that are fixed later
but is easier to review.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
arch/tile/mm/pgtable.c | 8 +-
drivers/base/node.c | 19 +--
drivers/staging/android/lowmemorykiller.c | 8 +-
include/linux/backing-dev.h | 2 +-
include/linux/memcontrol.h | 16 +--
include/linux/mm_inline.h | 21 ++-
include/linux/mmzone.h | 69 +++++----
include/linux/swap.h | 1 +
include/linux/vm_event_item.h | 10 +-
include/linux/vmstat.h | 17 +++
include/trace/events/vmscan.h | 12 +-
kernel/power/snapshot.c | 10 +-
mm/backing-dev.c | 15 +-
mm/compaction.c | 18 +--
mm/huge_memory.c | 2 +-
mm/internal.h | 2 +-
mm/khugepaged.c | 4 +-
mm/memcontrol.c | 17 +--
mm/memory-failure.c | 4 +-
mm/memory_hotplug.c | 2 +-
mm/mempolicy.c | 2 +-
mm/migrate.c | 21 +--
mm/mlock.c | 2 +-
mm/page-writeback.c | 8 +-
mm/page_alloc.c | 70 ++++-----
mm/swap.c | 50 +++----
mm/vmscan.c | 226 +++++++++++++++++-------------
mm/vmstat.c | 47 ++++---
mm/workingset.c | 4 +-
29 files changed, 387 insertions(+), 300 deletions(-)
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index c4d5bf841a7f..9e389213580d 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -45,10 +45,10 @@ void show_mem(unsigned int filter)
struct zone *zone;
pr_err("Active:%lu inactive:%lu dirty:%lu writeback:%lu unstable:%lu free:%lu\n slab:%lu mapped:%lu pagetables:%lu bounce:%lu pagecache:%lu swap:%lu\n",
- (global_page_state(NR_ACTIVE_ANON) +
- global_page_state(NR_ACTIVE_FILE)),
- (global_page_state(NR_INACTIVE_ANON) +
- global_page_state(NR_INACTIVE_FILE)),
+ (global_node_page_state(NR_ACTIVE_ANON) +
+ global_node_page_state(NR_ACTIVE_FILE)),
+ (global_node_page_state(NR_INACTIVE_ANON) +
+ global_node_page_state(NR_INACTIVE_FILE)),
global_page_state(NR_FILE_DIRTY),
global_page_state(NR_WRITEBACK),
global_page_state(NR_UNSTABLE_NFS),
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 92d8e090c5b3..b7f01a4a642d 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -56,6 +56,7 @@ static ssize_t node_read_meminfo(struct device *dev,
{
int n;
int nid = dev->id;
+ struct pglist_data *pgdat = NODE_DATA(nid);
struct sysinfo i;
si_meminfo_node(&i, nid);
@@ -74,15 +75,15 @@ static ssize_t node_read_meminfo(struct device *dev,
nid, K(i.totalram),
nid, K(i.freeram),
nid, K(i.totalram - i.freeram),
- nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_ANON) +
- sum_zone_node_page_state(nid, NR_ACTIVE_FILE)),
- nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_ANON) +
- sum_zone_node_page_state(nid, NR_INACTIVE_FILE)),
- nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_ANON)),
- nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_ANON)),
- nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_FILE)),
- nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_FILE)),
- nid, K(sum_zone_node_page_state(nid, NR_UNEVICTABLE)),
+ nid, K(node_page_state(pgdat, NR_ACTIVE_ANON) +
+ node_page_state(pgdat, NR_ACTIVE_FILE)),
+ nid, K(node_page_state(pgdat, NR_INACTIVE_ANON) +
+ node_page_state(pgdat, NR_INACTIVE_FILE)),
+ nid, K(node_page_state(pgdat, NR_ACTIVE_ANON)),
+ nid, K(node_page_state(pgdat, NR_INACTIVE_ANON)),
+ nid, K(node_page_state(pgdat, NR_ACTIVE_FILE)),
+ nid, K(node_page_state(pgdat, NR_INACTIVE_FILE)),
+ nid, K(node_page_state(pgdat, NR_UNEVICTABLE)),
nid, K(sum_zone_node_page_state(nid, NR_MLOCK)));
#ifdef CONFIG_HIGHMEM
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index 24d2745e9437..93dbcc38eb0f 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -72,10 +72,10 @@ static unsigned long lowmem_deathpending_timeout;
static unsigned long lowmem_count(struct shrinker *s,
struct shrink_control *sc)
{
- return global_page_state(NR_ACTIVE_ANON) +
- global_page_state(NR_ACTIVE_FILE) +
- global_page_state(NR_INACTIVE_ANON) +
- global_page_state(NR_INACTIVE_FILE);
+ return global_node_page_state(NR_ACTIVE_ANON) +
+ global_node_page_state(NR_ACTIVE_FILE) +
+ global_node_page_state(NR_INACTIVE_ANON) +
+ global_node_page_state(NR_INACTIVE_FILE);
}
static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c82794f20110..491a91717788 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -197,7 +197,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
}
long congestion_wait(int sync, long timeout);
-long wait_iff_congested(struct zone *zone, int sync, long timeout);
+long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout);
int pdflush_proc_obsolete(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 104efa6874db..1927dcb6921e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -340,7 +340,7 @@ static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
struct lruvec *lruvec;
if (mem_cgroup_disabled()) {
- lruvec = &zone->lruvec;
+ lruvec = zone_lruvec(zone);
goto out;
}
@@ -352,12 +352,12 @@ static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
* we have to be prepared to initialize lruvec->zone here;
* and if offlined then reonlined, we need to reinitialize it.
*/
- if (unlikely(lruvec->zone != zone))
- lruvec->zone = zone;
+ if (unlikely(lruvec->pgdat != zone->zone_pgdat))
+ lruvec->pgdat = zone->zone_pgdat;
return lruvec;
}
-struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
+struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
@@ -438,7 +438,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
- int nr_pages);
+ enum zone_type zid, int nr_pages);
unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
int nid, unsigned int lru_mask);
@@ -613,13 +613,13 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
struct mem_cgroup *memcg)
{
- return &zone->lruvec;
+ return zone_lruvec(zone);
}
static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
- struct zone *zone)
+ struct pglist_data *pgdat)
{
- return &zone->lruvec;
+ return &pgdat->lruvec;
}
static inline bool mm_match_cgroup(struct mm_struct *mm,
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 5bd29ba4f174..9aadcc781857 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -23,25 +23,32 @@ static inline int page_is_file_cache(struct page *page)
}
static __always_inline void __update_lru_size(struct lruvec *lruvec,
- enum lru_list lru, int nr_pages)
+ enum lru_list lru, enum zone_type zid,
+ int nr_pages)
{
- __mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, nr_pages);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
+ __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
+ __mod_zone_page_state(&pgdat->node_zones[zid],
+ NR_ZONE_LRU_BASE + !!is_file_lru(lru),
+ nr_pages);
}
static __always_inline void update_lru_size(struct lruvec *lruvec,
- enum lru_list lru, int nr_pages)
+ enum lru_list lru, enum zone_type zid,
+ int nr_pages)
{
#ifdef CONFIG_MEMCG
- mem_cgroup_update_lru_size(lruvec, lru, nr_pages);
+ mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages);
#else
- __update_lru_size(lruvec, lru, nr_pages);
+ __update_lru_size(lruvec, lru, zid, nr_pages);
#endif
}
static __always_inline void add_page_to_lru_list(struct page *page,
struct lruvec *lruvec, enum lru_list lru)
{
- update_lru_size(lruvec, lru, hpage_nr_pages(page));
+ update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page));
list_add(&page->lru, &lruvec->lists[lru]);
}
@@ -49,7 +56,7 @@ static __always_inline void del_page_from_lru_list(struct page *page,
struct lruvec *lruvec, enum lru_list lru)
{
list_del(&page->lru);
- update_lru_size(lruvec, lru, -hpage_nr_pages(page));
+ update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page));
}
/**
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 2d5087e3c034..258c20758e80 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -111,12 +111,9 @@ enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
NR_ALLOC_BATCH,
- NR_LRU_BASE,
- NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
- NR_ACTIVE_ANON, /* " " " " " */
- NR_INACTIVE_FILE, /* " " " " " */
- NR_ACTIVE_FILE, /* " " " " " */
- NR_UNEVICTABLE, /* " " " " " */
+ NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
+ NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
+ NR_ZONE_LRU_FILE,
NR_MLOCK, /* mlock()ed pages found and moved off LRU */
NR_ANON_PAGES, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
@@ -134,12 +131,9 @@ enum zone_stat_item {
NR_VMSCAN_WRITE,
NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */
NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */
- NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
- NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */
NR_DIRTIED, /* page dirtyings since bootup */
NR_WRITTEN, /* page writings since bootup */
- NR_PAGES_SCANNED, /* pages scanned since last reclaim */
#if IS_ENABLED(CONFIG_ZSMALLOC)
NR_ZSPAGES, /* allocated in zsmalloc */
#endif
@@ -161,6 +155,15 @@ enum zone_stat_item {
NR_VM_ZONE_STAT_ITEMS };
enum node_stat_item {
+ NR_LRU_BASE,
+ NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
+ NR_ACTIVE_ANON, /* " " " " " */
+ NR_INACTIVE_FILE, /* " " " " " */
+ NR_ACTIVE_FILE, /* " " " " " */
+ NR_UNEVICTABLE, /* " " " " " */
+ NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
+ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
+ NR_PAGES_SCANNED, /* pages scanned since last reclaim */
NR_VM_NODE_STAT_ITEMS
};
@@ -219,7 +222,7 @@ struct lruvec {
/* Evictions & activations on the inactive file list */
atomic_long_t inactive_age;
#ifdef CONFIG_MEMCG
- struct zone *zone;
+ struct pglist_data *pgdat;
#endif
};
@@ -357,13 +360,6 @@ struct zone {
#ifdef CONFIG_NUMA
int node;
#endif
-
- /*
- * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
- * this zone's LRU. Maintained by the pageout code.
- */
- unsigned int inactive_ratio;
-
struct pglist_data *zone_pgdat;
struct per_cpu_pageset __percpu *pageset;
@@ -495,9 +491,6 @@ struct zone {
/* Write-intensive fields used by page reclaim */
- /* Fields commonly accessed by the page reclaim scanner */
- struct lruvec lruvec;
-
/*
* When free pages are below this point, additional steps are taken
* when reading the number of free pages to avoid per-cpu counter
@@ -537,17 +530,20 @@ struct zone {
enum zone_flags {
ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */
- ZONE_CONGESTED, /* zone has many dirty pages backed by
+ ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
+};
+
+enum pgdat_flags {
+ PGDAT_CONGESTED, /* zone has many dirty pages backed by
* a congested BDI
*/
- ZONE_DIRTY, /* reclaim scanning has recently found
+ PGDAT_DIRTY, /* reclaim scanning has recently found
* many dirty file pages at the tail
* of the LRU.
*/
- ZONE_WRITEBACK, /* reclaim scanning has recently found
+ PGDAT_WRITEBACK, /* reclaim scanning has recently found
* many pages under writeback
*/
- ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
};
static inline unsigned long zone_end_pfn(const struct zone *zone)
@@ -701,12 +697,26 @@ typedef struct pglist_data {
unsigned long first_deferred_pfn;
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
spinlock_t split_queue_lock;
struct list_head split_queue;
unsigned long split_queue_len;
#endif
+ /* Fields commonly accessed by the page reclaim scanner */
+ struct lruvec lruvec;
+
+ /*
+ * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
+ * this node's LRU. Maintained by the pageout code.
+ */
+ unsigned int inactive_ratio;
+
+ unsigned long flags;
+
+ ZONE_PADDING(_pad2_)
+
/* Per-node vmstats */
struct per_cpu_nodestat __percpu *per_cpu_nodestats;
atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS];
@@ -728,6 +738,11 @@ static inline spinlock_t *zone_lru_lock(struct zone *zone)
return &zone->zone_pgdat->lru_lock;
}
+static inline struct lruvec *zone_lruvec(struct zone *zone)
+{
+ return &zone->zone_pgdat->lruvec;
+}
+
static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
{
return pgdat->node_start_pfn + pgdat->node_spanned_pages;
@@ -779,12 +794,12 @@ extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
extern void lruvec_init(struct lruvec *lruvec);
-static inline struct zone *lruvec_zone(struct lruvec *lruvec)
+static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
{
#ifdef CONFIG_MEMCG
- return lruvec->zone;
+ return lruvec->pgdat;
#else
- return container_of(lruvec, struct zone, lruvec);
+ return container_of(lruvec, struct pglist_data, lruvec);
#endif
}
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 0af2bb2028fd..c82f916008b7 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -317,6 +317,7 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
/* linux/mm/vmscan.c */
extern unsigned long zone_reclaimable_pages(struct zone *zone);
+extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 42604173f122..1798ff542517 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -26,11 +26,11 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
PGFREE, PGACTIVATE, PGDEACTIVATE,
PGFAULT, PGMAJFAULT,
PGLAZYFREED,
- FOR_ALL_ZONES(PGREFILL),
- FOR_ALL_ZONES(PGSTEAL_KSWAPD),
- FOR_ALL_ZONES(PGSTEAL_DIRECT),
- FOR_ALL_ZONES(PGSCAN_KSWAPD),
- FOR_ALL_ZONES(PGSCAN_DIRECT),
+ PGREFILL,
+ PGSTEAL_KSWAPD,
+ PGSTEAL_DIRECT,
+ PGSCAN_KSWAPD,
+ PGSCAN_DIRECT,
PGSCAN_DIRECT_THROTTLE,
#ifdef CONFIG_NUMA
PGSCAN_ZONE_RECLAIM_FAILED,
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index d1744aa3ab9c..ced0c3e9da88 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -178,6 +178,23 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
return x;
}
+static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat,
+ enum zone_stat_item item)
+{
+ long x = atomic_long_read(&pgdat->vm_stat[item]);
+
+#ifdef CONFIG_SMP
+ int cpu;
+ for_each_online_cpu(cpu)
+ x += per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->vm_node_stat_diff[item];
+
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
+}
+
+
#ifdef CONFIG_NUMA
extern unsigned long sum_zone_node_page_state(int node,
enum zone_stat_item item);
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 0101ef37f1ee..897f1aa1ee5f 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -352,15 +352,14 @@ TRACE_EVENT(mm_vmscan_writepage,
TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
- TP_PROTO(struct zone *zone,
+ TP_PROTO(int nid,
unsigned long nr_scanned, unsigned long nr_reclaimed,
int priority, int file),
- TP_ARGS(zone, nr_scanned, nr_reclaimed, priority, file),
+ TP_ARGS(nid, nr_scanned, nr_reclaimed, priority, file),
TP_STRUCT__entry(
__field(int, nid)
- __field(int, zid)
__field(unsigned long, nr_scanned)
__field(unsigned long, nr_reclaimed)
__field(int, priority)
@@ -368,16 +367,15 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
),
TP_fast_assign(
- __entry->nid = zone_to_nid(zone);
- __entry->zid = zone_idx(zone);
+ __entry->nid = nid;
__entry->nr_scanned = nr_scanned;
__entry->nr_reclaimed = nr_reclaimed;
__entry->priority = priority;
__entry->reclaim_flags = trace_shrink_flags(file);
),
- TP_printk("nid=%d zid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s",
- __entry->nid, __entry->zid,
+ TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s",
+ __entry->nid,
__entry->nr_scanned, __entry->nr_reclaimed,
__entry->priority,
show_reclaim_flags(__entry->reclaim_flags))
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 3a970604308f..24a06bc23f85 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1525,11 +1525,11 @@ static unsigned long minimum_image_size(unsigned long saveable)
unsigned long size;
size = global_page_state(NR_SLAB_RECLAIMABLE)
- + global_page_state(NR_ACTIVE_ANON)
- + global_page_state(NR_INACTIVE_ANON)
- + global_page_state(NR_ACTIVE_FILE)
- + global_page_state(NR_INACTIVE_FILE)
- - global_page_state(NR_FILE_MAPPED);
+ + global_node_page_state(NR_ACTIVE_ANON)
+ + global_node_page_state(NR_INACTIVE_ANON)
+ + global_node_page_state(NR_ACTIVE_FILE)
+ + global_node_page_state(NR_INACTIVE_FILE)
+ - global_node_page_state(NR_FILE_MAPPED);
return saveable <= size ? 0 : saveable - size;
}
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f53b23ab7ed7..a8c3af46bd3d 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -982,24 +982,24 @@ long congestion_wait(int sync, long timeout)
EXPORT_SYMBOL(congestion_wait);
/**
- * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
- * @zone: A zone to check if it is heavily congested
+ * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes
+ * @pgdat: A pgdat to check if it is heavily congested
* @sync: SYNC or ASYNC IO
* @timeout: timeout in jiffies
*
* In the event of a congested backing_dev (any backing_dev) and the given
- * @zone has experienced recent congestion, this waits for up to @timeout
+ * @pgdat has experienced recent congestion, this waits for up to @timeout
* jiffies for either a BDI to exit congestion of the given @sync queue
* or a write to complete.
*
- * In the absence of zone congestion, cond_resched() is called to yield
+ * In the absence of pgdat congestion, cond_resched() is called to yield
* the processor if necessary but otherwise does not sleep.
*
* The return value is 0 if the sleep is for the full timeout. Otherwise,
* it is the number of jiffies that were still remaining when the function
* returned. return_value == timeout implies the function did not sleep.
*/
-long wait_iff_congested(struct zone *zone, int sync, long timeout)
+long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout)
{
long ret;
unsigned long start = jiffies;
@@ -1008,12 +1008,13 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
/*
* If there is no congestion, or heavy congestion is not being
- * encountered in the current zone, yield if necessary instead
+ * encountered in the current pgdat, yield if necessary instead
* of sleeping on the congestion queue
*/
if (atomic_read(&nr_wb_congested[sync]) == 0 ||
- !test_bit(ZONE_CONGESTED, &zone->flags)) {
+ !test_bit(PGDAT_CONGESTED, &pgdat->flags)) {
cond_resched();
+
/* In case we scheduled, work out time remaining */
ret = timeout - (jiffies - start);
if (ret < 0)
diff --git a/mm/compaction.c b/mm/compaction.c
index 7607efb7bee2..a0bd85712516 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -646,8 +646,8 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc)
list_for_each_entry(page, &cc->migratepages, lru)
count[!!page_is_file_cache(page)]++;
- mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
- mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, count[0]);
+ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, count[1]);
}
/* Similar to reclaim, but different enough that they don't share logic */
@@ -655,12 +655,12 @@ static bool too_many_isolated(struct zone *zone)
{
unsigned long active, inactive, isolated;
- inactive = zone_page_state(zone, NR_INACTIVE_FILE) +
- zone_page_state(zone, NR_INACTIVE_ANON);
- active = zone_page_state(zone, NR_ACTIVE_FILE) +
- zone_page_state(zone, NR_ACTIVE_ANON);
- isolated = zone_page_state(zone, NR_ISOLATED_FILE) +
- zone_page_state(zone, NR_ISOLATED_ANON);
+ inactive = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) +
+ node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON);
+ active = node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE) +
+ node_page_state(zone->zone_pgdat, NR_ACTIVE_ANON);
+ isolated = node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE) +
+ node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON);
return isolated > (inactive + active) / 2;
}
@@ -856,7 +856,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
}
}
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
/* Try isolate the page */
if (__isolate_lru_page(page, isolate_mode) != 0)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2f997328ae64..5d5b2207cfd2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1830,7 +1830,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
pgoff_t end = -1;
int i;
- lruvec = mem_cgroup_page_lruvec(head, zone);
+ lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);
/* complete memcg works before add pages to LRU */
mem_cgroup_split_huge_fixup(head);
diff --git a/mm/internal.h b/mm/internal.h
index 9b6a6c43ac39..2f80d0343c56 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -78,7 +78,7 @@ extern unsigned long highest_memmap_pfn;
*/
extern int isolate_lru_page(struct page *page);
extern void putback_lru_page(struct page *page);
-extern bool zone_reclaimable(struct zone *zone);
+extern bool pgdat_reclaimable(struct pglist_data *pgdat);
/*
* in mm/rmap.c:
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 93d5f87c00d5..d7a49f665f04 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -480,7 +480,7 @@ void __khugepaged_exit(struct mm_struct *mm)
static void release_pte_page(struct page *page)
{
/* 0 stands for page_is_file_cache(page) == false */
- dec_zone_page_state(page, NR_ISOLATED_ANON + 0);
+ dec_node_page_state(page, NR_ISOLATED_ANON + 0);
unlock_page(page);
putback_lru_page(page);
}
@@ -576,7 +576,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
goto out;
}
/* 0 stands for page_is_file_cache(page) == false */
- inc_zone_page_state(page, NR_ISOLATED_ANON + 0);
+ inc_node_page_state(page, NR_ISOLATED_ANON + 0);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageLRU(page), page);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9b70f9ca8ddf..50c86ad121bc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -943,14 +943,14 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
* and putback protocol: the LRU lock must be held, and the page must
* either be PageLRU() or the caller must have isolated/allocated it.
*/
-struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
+struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat)
{
struct mem_cgroup_per_zone *mz;
struct mem_cgroup *memcg;
struct lruvec *lruvec;
if (mem_cgroup_disabled()) {
- lruvec = &zone->lruvec;
+ lruvec = &pgdat->lruvec;
goto out;
}
@@ -970,8 +970,8 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
* we have to be prepared to initialize lruvec->zone here;
* and if offlined then reonlined, we need to reinitialize it.
*/
- if (unlikely(lruvec->zone != zone))
- lruvec->zone = zone;
+ if (unlikely(lruvec->pgdat != pgdat))
+ lruvec->pgdat = pgdat;
return lruvec;
}
@@ -979,6 +979,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
* mem_cgroup_update_lru_size - account for adding or removing an lru page
* @lruvec: mem_cgroup per zone lru vector
* @lru: index of lru list the page is sitting on
+ * @zid: Zone ID of the zone pages have been added to
* @nr_pages: positive when adding or negative when removing
*
* This function must be called under lru_lock, just before a page is added
@@ -986,14 +987,14 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
* so as to allow it to check that lru_size 0 is consistent with list_empty).
*/
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
- int nr_pages)
+ enum zone_type zid, int nr_pages)
{
struct mem_cgroup_per_zone *mz;
unsigned long *lru_size;
long size;
bool empty;
- __update_lru_size(lruvec, lru, nr_pages);
+ __update_lru_size(lruvec, lru, zid, nr_pages);
if (mem_cgroup_disabled())
return;
@@ -2069,7 +2070,7 @@ static void lock_page_lru(struct page *page, int *isolated)
if (PageLRU(page)) {
struct lruvec *lruvec;
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, page_lru(page));
*isolated = 1;
@@ -2084,7 +2085,7 @@ static void unlock_page_lru(struct page *page, int isolated)
if (isolated) {
struct lruvec *lruvec;
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
VM_BUG_ON_PAGE(PageLRU(page), page);
SetPageLRU(page);
add_page_to_lru_list(page, lruvec, page_lru(page));
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2fcca6b0e005..11de752ccaf5 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1663,7 +1663,7 @@ static int __soft_offline_page(struct page *page, int flags)
put_hwpoison_page(page);
if (!ret) {
LIST_HEAD(pagelist);
- inc_zone_page_state(page, NR_ISOLATED_ANON +
+ inc_node_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
list_add(&page->lru, &pagelist);
ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
@@ -1671,7 +1671,7 @@ static int __soft_offline_page(struct page *page, int flags)
if (ret) {
if (!list_empty(&pagelist)) {
list_del(&page->lru);
- dec_zone_page_state(page, NR_ISOLATED_ANON +
+ dec_node_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
putback_lru_page(page);
}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 82d0b98d27f8..c5278360ca66 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1586,7 +1586,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
put_page(page);
list_add_tail(&page->lru, &source);
move_pages--;
- inc_zone_page_state(page, NR_ISOLATED_ANON +
+ inc_node_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
} else {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 53e40d3f3933..d8c4e38fb5f4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -962,7 +962,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
if (!isolate_lru_page(page)) {
list_add_tail(&page->lru, pagelist);
- inc_zone_page_state(page, NR_ISOLATED_ANON +
+ inc_node_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
}
}
diff --git a/mm/migrate.c b/mm/migrate.c
index 2232f6923cc7..3033dae33a0a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -168,7 +168,7 @@ void putback_movable_pages(struct list_head *l)
continue;
}
list_del(&page->lru);
- dec_zone_page_state(page, NR_ISOLATED_ANON +
+ dec_node_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
/*
* We isolated non-lru movable page so here we can use
@@ -1119,7 +1119,7 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page,
* restored.
*/
list_del(&page->lru);
- dec_zone_page_state(page, NR_ISOLATED_ANON +
+ dec_node_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
}
@@ -1460,7 +1460,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
err = isolate_lru_page(page);
if (!err) {
list_add_tail(&page->lru, &pagelist);
- inc_zone_page_state(page, NR_ISOLATED_ANON +
+ inc_node_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
}
put_and_set:
@@ -1726,15 +1726,16 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
unsigned long nr_migrate_pages)
{
int z;
+
+ if (!pgdat_reclaimable(pgdat))
+ return false;
+
for (z = pgdat->nr_zones - 1; z >= 0; z--) {
struct zone *zone = pgdat->node_zones + z;
if (!populated_zone(zone))
continue;
- if (!zone_reclaimable(zone))
- continue;
-
/* Avoid waking kswapd by allocating pages_to_migrate pages. */
if (!zone_watermark_ok(zone, 0,
high_wmark_pages(zone) +
@@ -1828,7 +1829,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
}
page_lru = page_is_file_cache(page);
- mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru,
+ mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru,
hpage_nr_pages(page));
/*
@@ -1886,7 +1887,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
if (nr_remaining) {
if (!list_empty(&migratepages)) {
list_del(&page->lru);
- dec_zone_page_state(page, NR_ISOLATED_ANON +
+ dec_node_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
putback_lru_page(page);
}
@@ -1979,7 +1980,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
/* Retake the callers reference and putback on LRU */
get_page(page);
putback_lru_page(page);
- mod_zone_page_state(page_zone(page),
+ mod_node_page_state(page_pgdat(page),
NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
goto out_unlock;
@@ -2030,7 +2031,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
- mod_zone_page_state(page_zone(page),
+ mod_node_page_state(page_pgdat(page),
NR_ISOLATED_ANON + page_lru,
-HPAGE_PMD_NR);
return isolated;
diff --git a/mm/mlock.c b/mm/mlock.c
index 997f63082ff5..14645be06e30 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -103,7 +103,7 @@ static bool __munlock_isolate_lru_page(struct page *page, bool getpage)
if (PageLRU(page)) {
struct lruvec *lruvec;
- lruvec = mem_cgroup_page_lruvec(page, page_zone(page));
+ lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
if (getpage)
get_page(page);
ClearPageLRU(page);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d578d2a56b19..0ada2b2954b0 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -285,8 +285,8 @@ static unsigned long zone_dirtyable_memory(struct zone *zone)
*/
nr_pages -= min(nr_pages, zone->totalreserve_pages);
- nr_pages += zone_page_state(zone, NR_INACTIVE_FILE);
- nr_pages += zone_page_state(zone, NR_ACTIVE_FILE);
+ nr_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE);
+ nr_pages += node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE);
return nr_pages;
}
@@ -348,8 +348,8 @@ static unsigned long global_dirtyable_memory(void)
*/
x -= min(x, totalreserve_pages);
- x += global_page_state(NR_INACTIVE_FILE);
- x += global_page_state(NR_ACTIVE_FILE);
+ x += global_node_page_state(NR_INACTIVE_FILE);
+ x += global_node_page_state(NR_ACTIVE_FILE);
if (!vm_highmem_is_dirtyable)
x -= highmem_dirtyable_memory(x);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 48b5414009ac..59e4463e5dce 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1090,9 +1090,9 @@ static void free_pcppages_bulk(struct zone *zone, int count,
spin_lock(&zone->lock);
isolated_pageblocks = has_isolate_pageblock(zone);
- nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+ nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
if (nr_scanned)
- __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
+ __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
while (count) {
struct page *page;
@@ -1147,9 +1147,9 @@ static void free_one_page(struct zone *zone,
{
unsigned long nr_scanned;
spin_lock(&zone->lock);
- nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+ nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
if (nr_scanned)
- __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
+ __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
if (unlikely(has_isolate_pageblock(zone) ||
is_migrate_isolate(migratetype))) {
@@ -3526,7 +3526,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
available = reclaimable = zone_reclaimable_pages(zone);
available -= DIV_ROUND_UP(no_progress_loops * available,
- MAX_RECLAIM_RETRIES);
+ MAX_RECLAIM_RETRIES);
available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
/*
@@ -4331,6 +4331,7 @@ void show_free_areas(unsigned int filter)
unsigned long free_pcp = 0;
int cpu;
struct zone *zone;
+ pg_data_t *pgdat;
for_each_populated_zone(zone) {
if (skip_free_areas_node(filter, zone_to_nid(zone)))
@@ -4349,13 +4350,13 @@ void show_free_areas(unsigned int filter)
" anon_thp: %lu shmem_thp: %lu shmem_pmdmapped: %lu\n"
#endif
" free:%lu free_pcp:%lu free_cma:%lu\n",
- global_page_state(NR_ACTIVE_ANON),
- global_page_state(NR_INACTIVE_ANON),
- global_page_state(NR_ISOLATED_ANON),
- global_page_state(NR_ACTIVE_FILE),
- global_page_state(NR_INACTIVE_FILE),
- global_page_state(NR_ISOLATED_FILE),
- global_page_state(NR_UNEVICTABLE),
+ global_node_page_state(NR_ACTIVE_ANON),
+ global_node_page_state(NR_INACTIVE_ANON),
+ global_node_page_state(NR_ISOLATED_ANON),
+ global_node_page_state(NR_ACTIVE_FILE),
+ global_node_page_state(NR_INACTIVE_FILE),
+ global_node_page_state(NR_ISOLATED_FILE),
+ global_node_page_state(NR_UNEVICTABLE),
global_page_state(NR_FILE_DIRTY),
global_page_state(NR_WRITEBACK),
global_page_state(NR_UNSTABLE_NFS),
@@ -4374,6 +4375,28 @@ void show_free_areas(unsigned int filter)
free_pcp,
global_page_state(NR_FREE_CMA_PAGES));
+ for_each_online_pgdat(pgdat) {
+ printk("Node %d"
+ " active_anon:%lukB"
+ " inactive_anon:%lukB"
+ " active_file:%lukB"
+ " inactive_file:%lukB"
+ " unevictable:%lukB"
+ " isolated(anon):%lukB"
+ " isolated(file):%lukB"
+ " all_unreclaimable? %s"
+ "\n",
+ pgdat->node_id,
+ K(node_page_state(pgdat, NR_ACTIVE_ANON)),
+ K(node_page_state(pgdat, NR_INACTIVE_ANON)),
+ K(node_page_state(pgdat, NR_ACTIVE_FILE)),
+ K(node_page_state(pgdat, NR_INACTIVE_FILE)),
+ K(node_page_state(pgdat, NR_UNEVICTABLE)),
+ K(node_page_state(pgdat, NR_ISOLATED_ANON)),
+ K(node_page_state(pgdat, NR_ISOLATED_FILE)),
+ !pgdat_reclaimable(pgdat) ? "yes" : "no");
+ }
+
for_each_populated_zone(zone) {
int i;
@@ -4390,13 +4413,6 @@ void show_free_areas(unsigned int filter)
" min:%lukB"
" low:%lukB"
" high:%lukB"
- " active_anon:%lukB"
- " inactive_anon:%lukB"
- " active_file:%lukB"
- " inactive_file:%lukB"
- " unevictable:%lukB"
- " isolated(anon):%lukB"
- " isolated(file):%lukB"
" present:%lukB"
" managed:%lukB"
" mlocked:%lukB"
@@ -4419,21 +4435,13 @@ void show_free_areas(unsigned int filter)
" local_pcp:%ukB"
" free_cma:%lukB"
" writeback_tmp:%lukB"
- " pages_scanned:%lu"
- " all_unreclaimable? %s"
+ " node_pages_scanned:%lu"
"\n",
zone->name,
K(zone_page_state(zone, NR_FREE_PAGES)),
K(min_wmark_pages(zone)),
K(low_wmark_pages(zone)),
K(high_wmark_pages(zone)),
- K(zone_page_state(zone, NR_ACTIVE_ANON)),
- K(zone_page_state(zone, NR_INACTIVE_ANON)),
- K(zone_page_state(zone, NR_ACTIVE_FILE)),
- K(zone_page_state(zone, NR_INACTIVE_FILE)),
- K(zone_page_state(zone, NR_UNEVICTABLE)),
- K(zone_page_state(zone, NR_ISOLATED_ANON)),
- K(zone_page_state(zone, NR_ISOLATED_FILE)),
K(zone->present_pages),
K(zone->managed_pages),
K(zone_page_state(zone, NR_MLOCK)),
@@ -4458,9 +4466,7 @@ void show_free_areas(unsigned int filter)
K(this_cpu_read(zone->pageset->pcp.count)),
K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
- K(zone_page_state(zone, NR_PAGES_SCANNED)),
- (!zone_reclaimable(zone) ? "yes" : "no")
- );
+ K(node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED)));
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
printk(" %ld", zone->lowmem_reserve[i]);
@@ -6010,7 +6016,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
/* For bootup, initialized properly in watermark setup */
mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
- lruvec_init(&zone->lruvec);
+ lruvec_init(zone_lruvec(zone));
if (!size)
continue;
diff --git a/mm/swap.c b/mm/swap.c
index bf37e5cfae81..77af473635fe 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -63,7 +63,7 @@ static void __page_cache_release(struct page *page)
unsigned long flags;
spin_lock_irqsave(zone_lru_lock(zone), flags);
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
VM_BUG_ON_PAGE(!PageLRU(page), page);
__ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, page_off_lru(page));
@@ -194,7 +194,7 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
spin_lock_irqsave(zone_lru_lock(zone), flags);
}
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
(*move_fn)(page, lruvec, arg);
}
if (zone)
@@ -319,7 +319,7 @@ void activate_page(struct page *page)
page = compound_head(page);
spin_lock_irq(zone_lru_lock(zone));
- __activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL);
+ __activate_page(page, mem_cgroup_page_lruvec(page, zone->zone_pgdat), NULL);
spin_unlock_irq(zone_lru_lock(zone));
}
#endif
@@ -445,16 +445,16 @@ void lru_cache_add(struct page *page)
*/
void add_page_to_unevictable_list(struct page *page)
{
- struct zone *zone = page_zone(page);
+ struct pglist_data *pgdat = page_pgdat(page);
struct lruvec *lruvec;
- spin_lock_irq(zone_lru_lock(zone));
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ spin_lock_irq(&pgdat->lru_lock);
+ lruvec = mem_cgroup_page_lruvec(page, pgdat);
ClearPageActive(page);
SetPageUnevictable(page);
SetPageLRU(page);
add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
- spin_unlock_irq(zone_lru_lock(zone));
+ spin_unlock_irq(&pgdat->lru_lock);
}
/**
@@ -730,7 +730,7 @@ void release_pages(struct page **pages, int nr, bool cold)
{
int i;
LIST_HEAD(pages_to_free);
- struct zone *zone = NULL;
+ struct pglist_data *locked_pgdat = NULL;
struct lruvec *lruvec;
unsigned long uninitialized_var(flags);
unsigned int uninitialized_var(lock_batch);
@@ -741,11 +741,11 @@ void release_pages(struct page **pages, int nr, bool cold)
/*
* Make sure the IRQ-safe lock-holding time does not get
* excessive with a continuous string of pages from the
- * same zone. The lock is held only if zone != NULL.
+ * same pgdat. The lock is held only if pgdat != NULL.
*/
- if (zone && ++lock_batch == SWAP_CLUSTER_MAX) {
- spin_unlock_irqrestore(zone_lru_lock(zone), flags);
- zone = NULL;
+ if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) {
+ spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
+ locked_pgdat = NULL;
}
if (is_huge_zero_page(page)) {
@@ -758,27 +758,27 @@ void release_pages(struct page **pages, int nr, bool cold)
continue;
if (PageCompound(page)) {
- if (zone) {
- spin_unlock_irqrestore(zone_lru_lock(zone), flags);
- zone = NULL;
+ if (locked_pgdat) {
+ spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
+ locked_pgdat = NULL;
}
__put_compound_page(page);
continue;
}
if (PageLRU(page)) {
- struct zone *pagezone = page_zone(page);
+ struct pglist_data *pgdat = page_pgdat(page);
- if (pagezone != zone) {
- if (zone)
- spin_unlock_irqrestore(zone_lru_lock(zone),
+ if (pgdat != locked_pgdat) {
+ if (locked_pgdat)
+ spin_unlock_irqrestore(&locked_pgdat->lru_lock,
flags);
lock_batch = 0;
- zone = pagezone;
- spin_lock_irqsave(zone_lru_lock(zone), flags);
+ locked_pgdat = pgdat;
+ spin_lock_irqsave(&locked_pgdat->lru_lock, flags);
}
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, locked_pgdat);
VM_BUG_ON_PAGE(!PageLRU(page), page);
__ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, page_off_lru(page));
@@ -789,8 +789,8 @@ void release_pages(struct page **pages, int nr, bool cold)
list_add(&page->lru, &pages_to_free);
}
- if (zone)
- spin_unlock_irqrestore(zone_lru_lock(zone), flags);
+ if (locked_pgdat)
+ spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
mem_cgroup_uncharge_list(&pages_to_free);
free_hot_cold_page_list(&pages_to_free, cold);
@@ -826,7 +826,7 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
VM_BUG_ON_PAGE(PageCompound(page_tail), page);
VM_BUG_ON_PAGE(PageLRU(page_tail), page);
VM_BUG_ON(NR_CPUS != 1 &&
- !spin_is_locked(zone_lru_lock(lruvec_zone(lruvec))));
+ !spin_is_locked(&lruvec_pgdat(lruvec)->lru_lock));
if (!list)
SetPageLRU(page_tail);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e7ffcd259cc4..86a523a761c9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -191,26 +191,42 @@ static bool sane_reclaim(struct scan_control *sc)
}
#endif
+/*
+ * This misses isolated pages which are not accounted for to save counters.
+ * As the data only determines if reclaim or compaction continues, it is
+ * not expected that isolated pages will be a dominating factor.
+ */
unsigned long zone_reclaimable_pages(struct zone *zone)
{
unsigned long nr;
- nr = zone_page_state_snapshot(zone, NR_ACTIVE_FILE) +
- zone_page_state_snapshot(zone, NR_INACTIVE_FILE) +
- zone_page_state_snapshot(zone, NR_ISOLATED_FILE);
+ nr = zone_page_state_snapshot(zone, NR_ZONE_LRU_FILE);
+ if (get_nr_swap_pages() > 0)
+ nr += zone_page_state_snapshot(zone, NR_ZONE_LRU_ANON);
+
+ return nr;
+}
+
+unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat)
+{
+ unsigned long nr;
+
+ nr = node_page_state_snapshot(pgdat, NR_ACTIVE_FILE) +
+ node_page_state_snapshot(pgdat, NR_INACTIVE_FILE) +
+ node_page_state_snapshot(pgdat, NR_ISOLATED_FILE);
if (get_nr_swap_pages() > 0)
- nr += zone_page_state_snapshot(zone, NR_ACTIVE_ANON) +
- zone_page_state_snapshot(zone, NR_INACTIVE_ANON) +
- zone_page_state_snapshot(zone, NR_ISOLATED_ANON);
+ nr += node_page_state_snapshot(pgdat, NR_ACTIVE_ANON) +
+ node_page_state_snapshot(pgdat, NR_INACTIVE_ANON) +
+ node_page_state_snapshot(pgdat, NR_ISOLATED_ANON);
return nr;
}
-bool zone_reclaimable(struct zone *zone)
+bool pgdat_reclaimable(struct pglist_data *pgdat)
{
- return zone_page_state_snapshot(zone, NR_PAGES_SCANNED) <
- zone_reclaimable_pages(zone) * 6;
+ return node_page_state_snapshot(pgdat, NR_PAGES_SCANNED) <
+ pgdat_reclaimable_pages(pgdat) * 6;
}
unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
@@ -218,7 +234,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
if (!mem_cgroup_disabled())
return mem_cgroup_get_lru_size(lruvec, lru);
- return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru);
+ return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
}
/*
@@ -877,7 +893,7 @@ static void page_check_dirty_writeback(struct page *page,
* shrink_page_list() returns the number of reclaimed pages
*/
static unsigned long shrink_page_list(struct list_head *page_list,
- struct zone *zone,
+ struct pglist_data *pgdat,
struct scan_control *sc,
enum ttu_flags ttu_flags,
unsigned long *ret_nr_dirty,
@@ -917,7 +933,6 @@ static unsigned long shrink_page_list(struct list_head *page_list,
goto keep;
VM_BUG_ON_PAGE(PageActive(page), page);
- VM_BUG_ON_PAGE(page_zone(page) != zone, page);
sc->nr_scanned++;
@@ -996,7 +1011,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
/* Case 1 above */
if (current_is_kswapd() &&
PageReclaim(page) &&
- test_bit(ZONE_WRITEBACK, &zone->flags)) {
+ test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
nr_immediate++;
goto keep_locked;
@@ -1092,7 +1107,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
*/
if (page_is_file_cache(page) &&
(!current_is_kswapd() ||
- !test_bit(ZONE_DIRTY, &zone->flags))) {
+ !test_bit(PGDAT_DIRTY, &pgdat->flags))) {
/*
* Immediately reclaim when written back.
* Similar in principal to deactivate_page()
@@ -1266,11 +1281,11 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
}
}
- ret = shrink_page_list(&clean_pages, zone, &sc,
+ ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
TTU_UNMAP|TTU_IGNORE_ACCESS,
&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
list_splice(&clean_pages, page_list);
- mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
+ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret);
return ret;
}
@@ -1375,7 +1390,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
{
struct list_head *src = &lruvec->lists[lru];
unsigned long nr_taken = 0;
- unsigned long scan;
+ unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
+ unsigned long scan, nr_pages;
for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
!list_empty(src); scan++) {
@@ -1388,7 +1404,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
switch (__isolate_lru_page(page, mode)) {
case 0:
- nr_taken += hpage_nr_pages(page);
+ nr_pages = hpage_nr_pages(page);
+ nr_taken += nr_pages;
+ nr_zone_taken[page_zonenum(page)] += nr_pages;
list_move(&page->lru, dst);
break;
@@ -1405,6 +1423,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
*nr_scanned = scan;
trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
nr_taken, mode, is_file_lru(lru));
+ for (scan = 0; scan < MAX_NR_ZONES; scan++) {
+ nr_pages = nr_zone_taken[scan];
+ if (!nr_pages)
+ continue;
+
+ update_lru_size(lruvec, lru, scan, -nr_pages);
+ }
return nr_taken;
}
@@ -1445,7 +1470,7 @@ int isolate_lru_page(struct page *page)
struct lruvec *lruvec;
spin_lock_irq(zone_lru_lock(zone));
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
if (PageLRU(page)) {
int lru = page_lru(page);
get_page(page);
@@ -1465,7 +1490,7 @@ int isolate_lru_page(struct page *page)
* the LRU list will go small and be scanned faster than necessary, leading to
* unnecessary swapping, thrashing and OOM.
*/
-static int too_many_isolated(struct zone *zone, int file,
+static int too_many_isolated(struct pglist_data *pgdat, int file,
struct scan_control *sc)
{
unsigned long inactive, isolated;
@@ -1477,11 +1502,11 @@ static int too_many_isolated(struct zone *zone, int file,
return 0;
if (file) {
- inactive = zone_page_state(zone, NR_INACTIVE_FILE);
- isolated = zone_page_state(zone, NR_ISOLATED_FILE);
+ inactive = node_page_state(pgdat, NR_INACTIVE_FILE);
+ isolated = node_page_state(pgdat, NR_ISOLATED_FILE);
} else {
- inactive = zone_page_state(zone, NR_INACTIVE_ANON);
- isolated = zone_page_state(zone, NR_ISOLATED_ANON);
+ inactive = node_page_state(pgdat, NR_INACTIVE_ANON);
+ isolated = node_page_state(pgdat, NR_ISOLATED_ANON);
}
/*
@@ -1499,7 +1524,7 @@ static noinline_for_stack void
putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
{
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
- struct zone *zone = lruvec_zone(lruvec);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
LIST_HEAD(pages_to_free);
/*
@@ -1512,13 +1537,13 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
VM_BUG_ON_PAGE(PageLRU(page), page);
list_del(&page->lru);
if (unlikely(!page_evictable(page))) {
- spin_unlock_irq(zone_lru_lock(zone));
+ spin_unlock_irq(&pgdat->lru_lock);
putback_lru_page(page);
- spin_lock_irq(zone_lru_lock(zone));
+ spin_lock_irq(&pgdat->lru_lock);
continue;
}
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, pgdat);
SetPageLRU(page);
lru = page_lru(page);
@@ -1535,10 +1560,10 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
del_page_from_lru_list(page, lruvec, lru);
if (unlikely(PageCompound(page))) {
- spin_unlock_irq(zone_lru_lock(zone));
+ spin_unlock_irq(&pgdat->lru_lock);
mem_cgroup_uncharge(page);
(*get_compound_page_dtor(page))(page);
- spin_lock_irq(zone_lru_lock(zone));
+ spin_lock_irq(&pgdat->lru_lock);
} else
list_add(&page->lru, &pages_to_free);
}
@@ -1582,10 +1607,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
unsigned long nr_immediate = 0;
isolate_mode_t isolate_mode = 0;
int file = is_file_lru(lru);
- struct zone *zone = lruvec_zone(lruvec);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
- while (unlikely(too_many_isolated(zone, file, sc))) {
+ while (unlikely(too_many_isolated(pgdat, file, sc))) {
congestion_wait(BLK_RW_ASYNC, HZ/10);
/* We are about to die and free our memory. Return now. */
@@ -1600,48 +1625,45 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
if (!sc->may_writepage)
isolate_mode |= ISOLATE_CLEAN;
- spin_lock_irq(zone_lru_lock(zone));
+ spin_lock_irq(&pgdat->lru_lock);
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
&nr_scanned, sc, isolate_mode, lru);
- update_lru_size(lruvec, lru, -nr_taken);
- __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
+ __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
reclaim_stat->recent_scanned[file] += nr_taken;
if (global_reclaim(sc)) {
- __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
+ __mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned);
if (current_is_kswapd())
- __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned);
+ __count_vm_events(PGSCAN_KSWAPD, nr_scanned);
else
- __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned);
+ __count_vm_events(PGSCAN_DIRECT, nr_scanned);
}
- spin_unlock_irq(zone_lru_lock(zone));
+ spin_unlock_irq(&pgdat->lru_lock);
if (nr_taken == 0)
return 0;
- nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP,
+ nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, TTU_UNMAP,
&nr_dirty, &nr_unqueued_dirty, &nr_congested,
&nr_writeback, &nr_immediate,
false);
- spin_lock_irq(zone_lru_lock(zone));
+ spin_lock_irq(&pgdat->lru_lock);
if (global_reclaim(sc)) {
if (current_is_kswapd())
- __count_zone_vm_events(PGSTEAL_KSWAPD, zone,
- nr_reclaimed);
+ __count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed);
else
- __count_zone_vm_events(PGSTEAL_DIRECT, zone,
- nr_reclaimed);
+ __count_vm_events(PGSTEAL_DIRECT, nr_reclaimed);
}
putback_inactive_pages(lruvec, &page_list);
- __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
+ __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
- spin_unlock_irq(zone_lru_lock(zone));
+ spin_unlock_irq(&pgdat->lru_lock);
mem_cgroup_uncharge_list(&page_list);
free_hot_cold_page_list(&page_list, true);
@@ -1661,7 +1683,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
* are encountered in the nr_immediate check below.
*/
if (nr_writeback && nr_writeback == nr_taken)
- set_bit(ZONE_WRITEBACK, &zone->flags);
+ set_bit(PGDAT_WRITEBACK, &pgdat->flags);
/*
* Legacy memcg will stall in page writeback so avoid forcibly
@@ -1673,16 +1695,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
* backed by a congested BDI and wait_iff_congested will stall.
*/
if (nr_dirty && nr_dirty == nr_congested)
- set_bit(ZONE_CONGESTED, &zone->flags);
+ set_bit(PGDAT_CONGESTED, &pgdat->flags);
/*
* If dirty pages are scanned that are not queued for IO, it
* implies that flushers are not keeping up. In this case, flag
- * the zone ZONE_DIRTY and kswapd will start writing pages from
+ * the pgdat PGDAT_DIRTY and kswapd will start writing pages from
* reclaim context.
*/
if (nr_unqueued_dirty == nr_taken)
- set_bit(ZONE_DIRTY, &zone->flags);
+ set_bit(PGDAT_DIRTY, &pgdat->flags);
/*
* If kswapd scans pages marked marked for immediate
@@ -1701,9 +1723,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
*/
if (!sc->hibernation_mode && !current_is_kswapd() &&
current_may_throttle())
- wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);
+ wait_iff_congested(pgdat, BLK_RW_ASYNC, HZ/10);
- trace_mm_vmscan_lru_shrink_inactive(zone, nr_scanned, nr_reclaimed,
+ trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
+ nr_scanned, nr_reclaimed,
sc->priority, file);
return nr_reclaimed;
}
@@ -1731,20 +1754,20 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
struct list_head *pages_to_free,
enum lru_list lru)
{
- struct zone *zone = lruvec_zone(lruvec);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
unsigned long pgmoved = 0;
struct page *page;
int nr_pages;
while (!list_empty(list)) {
page = lru_to_page(list);
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, pgdat);
VM_BUG_ON_PAGE(PageLRU(page), page);
SetPageLRU(page);
nr_pages = hpage_nr_pages(page);
- update_lru_size(lruvec, lru, nr_pages);
+ update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
list_move(&page->lru, &lruvec->lists[lru]);
pgmoved += nr_pages;
@@ -1754,10 +1777,10 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
del_page_from_lru_list(page, lruvec, lru);
if (unlikely(PageCompound(page))) {
- spin_unlock_irq(zone_lru_lock(zone));
+ spin_unlock_irq(&pgdat->lru_lock);
mem_cgroup_uncharge(page);
(*get_compound_page_dtor(page))(page);
- spin_lock_irq(zone_lru_lock(zone));
+ spin_lock_irq(&pgdat->lru_lock);
} else
list_add(&page->lru, pages_to_free);
}
@@ -1783,7 +1806,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
unsigned long nr_rotated = 0;
isolate_mode_t isolate_mode = 0;
int file = is_file_lru(lru);
- struct zone *zone = lruvec_zone(lruvec);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
lru_add_drain();
@@ -1792,20 +1815,19 @@ static void shrink_active_list(unsigned long nr_to_scan,
if (!sc->may_writepage)
isolate_mode |= ISOLATE_CLEAN;
- spin_lock_irq(zone_lru_lock(zone));
+ spin_lock_irq(&pgdat->lru_lock);
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
&nr_scanned, sc, isolate_mode, lru);
- update_lru_size(lruvec, lru, -nr_taken);
- __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
+ __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
reclaim_stat->recent_scanned[file] += nr_taken;
if (global_reclaim(sc))
- __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
- __count_zone_vm_events(PGREFILL, zone, nr_scanned);
+ __mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned);
+ __count_vm_events(PGREFILL, nr_scanned);
- spin_unlock_irq(zone_lru_lock(zone));
+ spin_unlock_irq(&pgdat->lru_lock);
while (!list_empty(&l_hold)) {
cond_resched();
@@ -1850,7 +1872,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
/*
* Move pages back to the lru list.
*/
- spin_lock_irq(zone_lru_lock(zone));
+ spin_lock_irq(&pgdat->lru_lock);
/*
* Count referenced pages from currently used mappings as rotated,
* even though only some of them are actually re-activated. This
@@ -1861,8 +1883,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
- __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
- spin_unlock_irq(zone_lru_lock(zone));
+ __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
+ spin_unlock_irq(&pgdat->lru_lock);
mem_cgroup_uncharge_list(&l_hold);
free_hot_cold_page_list(&l_hold, true);
@@ -1956,7 +1978,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
u64 fraction[2];
u64 denominator = 0; /* gcc */
- struct zone *zone = lruvec_zone(lruvec);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
unsigned long anon_prio, file_prio;
enum scan_balance scan_balance;
unsigned long anon, file;
@@ -1977,7 +1999,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
* well.
*/
if (current_is_kswapd()) {
- if (!zone_reclaimable(zone))
+ if (!pgdat_reclaimable(pgdat))
force_scan = true;
if (!mem_cgroup_online(memcg))
force_scan = true;
@@ -2023,14 +2045,24 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
* anon pages. Try to detect this based on file LRU size.
*/
if (global_reclaim(sc)) {
- unsigned long zonefile;
- unsigned long zonefree;
+ unsigned long pgdatfile;
+ unsigned long pgdatfree;
+ int z;
+ unsigned long total_high_wmark = 0;
- zonefree = zone_page_state(zone, NR_FREE_PAGES);
- zonefile = zone_page_state(zone, NR_ACTIVE_FILE) +
- zone_page_state(zone, NR_INACTIVE_FILE);
+ pgdatfree = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
+ pgdatfile = node_page_state(pgdat, NR_ACTIVE_FILE) +
+ node_page_state(pgdat, NR_INACTIVE_FILE);
+
+ for (z = 0; z < MAX_NR_ZONES; z++) {
+ struct zone *zone = &pgdat->node_zones[z];
+ if (!populated_zone(zone))
+ continue;
+
+ total_high_wmark += high_wmark_pages(zone);
+ }
- if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) {
+ if (unlikely(pgdatfile + pgdatfree <= total_high_wmark)) {
scan_balance = SCAN_ANON;
goto out;
}
@@ -2077,7 +2109,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
- spin_lock_irq(zone_lru_lock(zone));
+ spin_lock_irq(&pgdat->lru_lock);
if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
reclaim_stat->recent_scanned[0] /= 2;
reclaim_stat->recent_rotated[0] /= 2;
@@ -2098,7 +2130,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
fp /= reclaim_stat->recent_rotated[1] + 1;
- spin_unlock_irq(zone_lru_lock(zone));
+ spin_unlock_irq(&pgdat->lru_lock);
fraction[0] = ap;
fraction[1] = fp;
@@ -2352,9 +2384,9 @@ static inline bool should_continue_reclaim(struct zone *zone,
* inactive lists are large enough, continue reclaiming
*/
pages_for_compaction = (2UL << sc->order);
- inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE);
+ inactive_lru_pages = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE);
if (get_nr_swap_pages() > 0)
- inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON);
+ inactive_lru_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON);
if (sc->nr_reclaimed < pages_for_compaction &&
inactive_lru_pages > pages_for_compaction)
return true;
@@ -2554,7 +2586,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
continue;
if (sc->priority != DEF_PRIORITY &&
- !zone_reclaimable(zone))
+ !pgdat_reclaimable(zone->zone_pgdat))
continue; /* Let kswapd poll it */
/*
@@ -2692,7 +2724,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
if (!populated_zone(zone) ||
- zone_reclaimable_pages(zone) == 0)
+ pgdat_reclaimable_pages(pgdat) == 0)
continue;
pfmemalloc_reserve += min_wmark_pages(zone);
@@ -3000,7 +3032,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
* DEF_PRIORITY. Effectively, it considers them balanced so
* they must be considered balanced here as well!
*/
- if (!zone_reclaimable(zone)) {
+ if (!pgdat_reclaimable(zone->zone_pgdat)) {
balanced_pages += zone->managed_pages;
continue;
}
@@ -3063,6 +3095,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
{
unsigned long balance_gap;
bool lowmem_pressure;
+ struct pglist_data *pgdat = zone->zone_pgdat;
/* Reclaim above the high watermark. */
sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone));
@@ -3087,7 +3120,8 @@ static bool kswapd_shrink_zone(struct zone *zone,
shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
- clear_bit(ZONE_WRITEBACK, &zone->flags);
+ /* TODO: ANOMALY */
+ clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
/*
* If a zone reaches its high watermark, consider it to be no longer
@@ -3095,10 +3129,10 @@ static bool kswapd_shrink_zone(struct zone *zone,
* BDIs but as pressure is relieved, speculatively avoid congestion
* waits.
*/
- if (zone_reclaimable(zone) &&
+ if (pgdat_reclaimable(zone->zone_pgdat) &&
zone_balanced(zone, sc->order, false, 0, classzone_idx)) {
- clear_bit(ZONE_CONGESTED, &zone->flags);
- clear_bit(ZONE_DIRTY, &zone->flags);
+ clear_bit(PGDAT_CONGESTED, &pgdat->flags);
+ clear_bit(PGDAT_DIRTY, &pgdat->flags);
}
return sc->nr_scanned >= sc->nr_to_reclaim;
@@ -3157,7 +3191,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
continue;
if (sc.priority != DEF_PRIORITY &&
- !zone_reclaimable(zone))
+ !pgdat_reclaimable(zone->zone_pgdat))
continue;
/*
@@ -3184,9 +3218,11 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
/*
* If balanced, clear the dirty and congested
* flags
+ *
+ * TODO: ANOMALY
*/
- clear_bit(ZONE_CONGESTED, &zone->flags);
- clear_bit(ZONE_DIRTY, &zone->flags);
+ clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
+ clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);
}
}
@@ -3216,7 +3252,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
continue;
if (sc.priority != DEF_PRIORITY &&
- !zone_reclaimable(zone))
+ !pgdat_reclaimable(zone->zone_pgdat))
continue;
sc.nr_scanned = 0;
@@ -3612,8 +3648,8 @@ int sysctl_min_slab_ratio = 5;
static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
{
unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
- unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) +
- zone_page_state(zone, NR_ACTIVE_FILE);
+ unsigned long file_lru = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) +
+ node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE);
/*
* It's possible for there to be more file mapped pages than
@@ -3716,7 +3752,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
return ZONE_RECLAIM_FULL;
- if (!zone_reclaimable(zone))
+ if (!pgdat_reclaimable(zone->zone_pgdat))
return ZONE_RECLAIM_FULL;
/*
@@ -3795,7 +3831,7 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages)
zone = pagezone;
spin_lock_irq(zone_lru_lock(zone));
}
- lruvec = mem_cgroup_page_lruvec(page, zone);
+ lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
if (!PageLRU(page) || !PageUnevictable(page))
continue;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 90b0737ee4be..2eab7903c5c2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -923,11 +923,8 @@ const char * const vmstat_text[] = {
/* enum zone_stat_item countes */
"nr_free_pages",
"nr_alloc_batch",
- "nr_inactive_anon",
- "nr_active_anon",
- "nr_inactive_file",
- "nr_active_file",
- "nr_unevictable",
+ "nr_zone_anon_lru",
+ "nr_zone_file_lru",
"nr_mlock",
"nr_anon_pages",
"nr_mapped",
@@ -943,12 +940,9 @@ const char * const vmstat_text[] = {
"nr_vmscan_write",
"nr_vmscan_immediate_reclaim",
"nr_writeback_temp",
- "nr_isolated_anon",
- "nr_isolated_file",
"nr_shmem",
"nr_dirtied",
"nr_written",
- "nr_pages_scanned",
#if IS_ENABLED(CONFIG_ZSMALLOC)
"nr_zspages",
#endif
@@ -968,6 +962,16 @@ const char * const vmstat_text[] = {
"nr_shmem_pmdmapped",
"nr_free_cma",
+ /* Node-based counters */
+ "nr_inactive_anon",
+ "nr_active_anon",
+ "nr_inactive_file",
+ "nr_active_file",
+ "nr_unevictable",
+ "nr_isolated_anon",
+ "nr_isolated_file",
+ "nr_pages_scanned",
+
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
"nr_dirty_background_threshold",
@@ -989,11 +993,11 @@ const char * const vmstat_text[] = {
"pgmajfault",
"pglazyfreed",
- TEXTS_FOR_ZONES("pgrefill")
- TEXTS_FOR_ZONES("pgsteal_kswapd")
- TEXTS_FOR_ZONES("pgsteal_direct")
- TEXTS_FOR_ZONES("pgscan_kswapd")
- TEXTS_FOR_ZONES("pgscan_direct")
+ "pgrefill",
+ "pgsteal_kswapd",
+ "pgsteal_direct",
+ "pgscan_kswapd",
+ "pgscan_direct",
"pgscan_direct_throttle",
#ifdef CONFIG_NUMA
@@ -1421,7 +1425,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
"\n min %lu"
"\n low %lu"
"\n high %lu"
- "\n scanned %lu"
+ "\n node_scanned %lu"
"\n spanned %lu"
"\n present %lu"
"\n managed %lu",
@@ -1429,13 +1433,13 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
min_wmark_pages(zone),
low_wmark_pages(zone),
high_wmark_pages(zone),
- zone_page_state(zone, NR_PAGES_SCANNED),
+ node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED),
zone->spanned_pages,
zone->present_pages,
zone->managed_pages);
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
- seq_printf(m, "\n %-12s %lu", vmstat_text[i],
+ seq_printf(m, "\n %-12s %lu", vmstat_text[i],
zone_page_state(zone, i));
seq_printf(m,
@@ -1465,12 +1469,12 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
#endif
}
seq_printf(m,
- "\n all_unreclaimable: %u"
- "\n start_pfn: %lu"
- "\n inactive_ratio: %u",
- !zone_reclaimable(zone),
+ "\n node_unreclaimable: %u"
+ "\n start_pfn: %lu"
+ "\n node_inactive_ratio: %u",
+ !pgdat_reclaimable(zone->zone_pgdat),
zone->zone_start_pfn,
- zone->inactive_ratio);
+ zone->zone_pgdat->inactive_ratio);
seq_putc(m, '\n');
}
@@ -1561,7 +1565,6 @@ static int vmstat_show(struct seq_file *m, void *arg)
{
unsigned long *l = arg;
unsigned long off = l - (unsigned long *)m->private;
-
seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
return 0;
}
diff --git a/mm/workingset.c b/mm/workingset.c
index ba972ac2dfdd..ebe14445809a 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -355,8 +355,8 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid,
LRU_ALL_FILE);
} else {
- pages = sum_zone_node_page_state(sc->nid, NR_ACTIVE_FILE) +
- sum_zone_node_page_state(sc->nid, NR_INACTIVE_FILE);
+ pages = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) +
+ node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE);
}
/*
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (2 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 03/31] mm, vmscan: move LRU lists to node Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-07 1:12 ` Joonsoo Kim
2016-07-01 20:01 ` [PATCH 05/31] mm, vmscan: have kswapd only scan based on the highest requested zone Mel Gorman
` (27 subsequent siblings)
31 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
This patch makes reclaim decisions on a per-node basis. A reclaimer knows
what zone is required by the allocation request and skips pages from
higher zones. In many cases this will be ok because it's a GFP_HIGHMEM
request of some description. On 64-bit, ZONE_DMA32 requests will cause
some problems but 32-bit devices on 64-bit platforms are increasingly
rare. Historically it would have been a major problem on 32-bit with big
Highmem:Lowmem ratios but such configurations are also now rare and even
where they exist, they are not encouraged. If it really becomes a
problem, it'll manifest as very low reclaim efficiencies.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
mm/vmscan.c | 79 ++++++++++++++++++++++++++++++++++++++++++-------------------
1 file changed, 55 insertions(+), 24 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 86a523a761c9..766b36bec829 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -84,6 +84,9 @@ struct scan_control {
/* Scan (total_size >> priority) pages at once */
int priority;
+ /* The highest zone to isolate pages for reclaim from */
+ enum zone_type reclaim_idx;
+
unsigned int may_writepage:1;
/* Can mapped pages be reclaimed? */
@@ -1392,6 +1395,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
unsigned long nr_taken = 0;
unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
unsigned long scan, nr_pages;
+ LIST_HEAD(pages_skipped);
for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
!list_empty(src); scan++) {
@@ -1402,6 +1406,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
VM_BUG_ON_PAGE(!PageLRU(page), page);
+ if (page_zonenum(page) > sc->reclaim_idx) {
+ list_move(&page->lru, &pages_skipped);
+ continue;
+ }
+
switch (__isolate_lru_page(page, mode)) {
case 0:
nr_pages = hpage_nr_pages(page);
@@ -1420,6 +1429,15 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
}
}
+ /*
+ * Splice any skipped pages to the start of the LRU list. Note that
+ * this disrupts the LRU order when reclaiming for lower zones but
+ * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX
+ * scanning would soon rescan the same pages to skip and put the
+ * system at risk of premature OOM.
+ */
+ if (!list_empty(&pages_skipped))
+ list_splice(&pages_skipped, src);
*nr_scanned = scan;
trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
nr_taken, mode, is_file_lru(lru));
@@ -1589,7 +1607,7 @@ static int current_may_throttle(void)
}
/*
- * shrink_inactive_list() is a helper for shrink_zone(). It returns the number
+ * shrink_inactive_list() is a helper for shrink_node(). It returns the number
* of reclaimed pages
*/
static noinline_for_stack unsigned long
@@ -2401,12 +2419,13 @@ static inline bool should_continue_reclaim(struct zone *zone,
}
}
-static bool shrink_zone(struct zone *zone, struct scan_control *sc,
- bool is_classzone)
+static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
+ enum zone_type classzone_idx)
{
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
bool reclaimable = false;
+ struct zone *zone = &pgdat->node_zones[classzone_idx];
do {
struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2438,7 +2457,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
shrink_zone_memcg(zone, memcg, sc, &lru_pages);
zone_lru_pages += lru_pages;
- if (memcg && is_classzone)
+ if (!global_reclaim(sc))
shrink_slab(sc->gfp_mask, zone_to_nid(zone),
memcg, sc->nr_scanned - scanned,
lru_pages);
@@ -2469,7 +2488,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
* Shrink the slab caches in the same proportion that
* the eligible LRU pages were scanned.
*/
- if (global_reclaim(sc) && is_classzone)
+ if (global_reclaim(sc))
shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
sc->nr_scanned - nr_scanned,
zone_lru_pages);
@@ -2553,7 +2572,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
gfp_t orig_mask;
- enum zone_type requested_highidx = gfp_zone(sc->gfp_mask);
+ enum zone_type classzone_idx;
/*
* If the number of buffer_heads in the machine exceeds the maximum
@@ -2561,17 +2580,23 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
* highmem pages could be pinning lowmem pages storing buffer_heads
*/
orig_mask = sc->gfp_mask;
- if (buffer_heads_over_limit)
+ if (buffer_heads_over_limit) {
sc->gfp_mask |= __GFP_HIGHMEM;
+ sc->reclaim_idx = classzone_idx = gfp_zone(sc->gfp_mask);
+ }
for_each_zone_zonelist_nodemask(zone, z, zonelist,
- gfp_zone(sc->gfp_mask), sc->nodemask) {
- enum zone_type classzone_idx;
-
+ sc->reclaim_idx, sc->nodemask) {
if (!populated_zone(zone))
continue;
- classzone_idx = requested_highidx;
+ /*
+ * Note that reclaim_idx does not change as it is the highest
+ * zone reclaimed from which for empty zones is a no-op but
+ * classzone_idx is used by shrink_node to test if the slabs
+ * should be shrunk on a given node.
+ */
+ classzone_idx = sc->reclaim_idx;
while (!populated_zone(zone->zone_pgdat->node_zones +
classzone_idx))
classzone_idx--;
@@ -2600,8 +2625,8 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
*/
if (IS_ENABLED(CONFIG_COMPACTION) &&
sc->order > PAGE_ALLOC_COSTLY_ORDER &&
- zonelist_zone_idx(z) <= requested_highidx &&
- compaction_ready(zone, sc->order, requested_highidx)) {
+ zonelist_zone_idx(z) <= classzone_idx &&
+ compaction_ready(zone, sc->order, classzone_idx)) {
sc->compaction_ready = true;
continue;
}
@@ -2621,7 +2646,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
/* need some check for avoid more shrink_zone() */
}
- shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
+ shrink_node(zone->zone_pgdat, sc, classzone_idx);
}
/*
@@ -2847,6 +2872,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
struct scan_control sc = {
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
+ .reclaim_idx = gfp_zone(gfp_mask),
.order = order,
.nodemask = nodemask,
.priority = DEF_PRIORITY,
@@ -2886,6 +2912,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
.target_mem_cgroup = memcg,
.may_writepage = !laptop_mode,
.may_unmap = 1,
+ .reclaim_idx = MAX_NR_ZONES - 1,
.may_swap = !noswap,
};
unsigned long lru_pages;
@@ -2924,6 +2951,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
+ .reclaim_idx = MAX_NR_ZONES - 1,
.target_mem_cgroup = memcg,
.priority = DEF_PRIORITY,
.may_writepage = !laptop_mode,
@@ -3118,7 +3146,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
balance_gap, classzone_idx))
return true;
- shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
+ shrink_node(zone->zone_pgdat, sc, classzone_idx);
/* TODO: ANOMALY */
clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
@@ -3167,6 +3195,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
unsigned long nr_soft_scanned;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
+ .reclaim_idx = MAX_NR_ZONES - 1,
.order = order,
.priority = DEF_PRIORITY,
.may_writepage = !laptop_mode,
@@ -3237,15 +3266,14 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
sc.may_writepage = 1;
/*
- * Now scan the zone in the dma->highmem direction, stopping
- * at the last zone which needs scanning.
- *
- * We do this because the page allocator works in the opposite
- * direction. This prevents the page allocator from allocating
- * pages behind kswapd's direction of progress, which would
- * cause too much scanning of the lower zones.
+ * Continue scanning in the highmem->dma direction stopping at
+ * the last zone which needs scanning. This may reclaim lowmem
+ * pages that are not necessary for zone balancing but it
+ * preserves LRU ordering. It is assumed that the bulk of
+ * allocation requests can use arbitrary zones with the
+ * possible exception of big highmem:lowmem configurations.
*/
- for (i = 0; i <= end_zone; i++) {
+ for (i = end_zone; i >= 0; i--) {
struct zone *zone = pgdat->node_zones + i;
if (!populated_zone(zone))
@@ -3256,6 +3284,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
continue;
sc.nr_scanned = 0;
+ sc.reclaim_idx = i;
nr_soft_scanned = 0;
/*
@@ -3513,6 +3542,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
struct scan_control sc = {
.nr_to_reclaim = nr_to_reclaim,
.gfp_mask = GFP_HIGHUSER_MOVABLE,
+ .reclaim_idx = MAX_NR_ZONES - 1,
.priority = DEF_PRIORITY,
.may_writepage = 1,
.may_unmap = 1,
@@ -3704,6 +3734,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
.may_unmap = !!(zone_reclaim_mode & RECLAIM_UNMAP),
.may_swap = 1,
+ .reclaim_idx = zone_idx(zone),
};
cond_resched();
@@ -3723,7 +3754,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
* priorities until we have enough memory freed.
*/
do {
- shrink_zone(zone, &sc, true);
+ shrink_node(zone->zone_pgdat, &sc, zone_idx(zone));
} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
}
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 05/31] mm, vmscan: have kswapd only scan based on the highest requested zone
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (3 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 06/31] mm, vmscan: make kswapd reclaim in terms of nodes Mel Gorman
` (26 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
kswapd checks all eligible zones to see if they need balancing even if it
was woken for a lower zone. This made sense when we reclaimed on a
per-zone basis because we wanted to shrink zones fairly so avoid
age-inversion problems. Ideally this is completely unnecessary when
reclaiming on a per-node basis. In theory, there may still be anomalies
when all requests are for lower zones and very old pages are preserved in
higher zones but this should be the exceptional case.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
mm/vmscan.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 766b36bec829..c6e61dae382b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3209,11 +3209,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
sc.nr_reclaimed = 0;
- /*
- * Scan in the highmem->dma direction for the highest
- * zone which needs scanning
- */
- for (i = pgdat->nr_zones - 1; i >= 0; i--) {
+ /* Scan from the highest requested zone to dma */
+ for (i = classzone_idx; i >= 0; i--) {
struct zone *zone = pgdat->node_zones + i;
if (!populated_zone(zone))
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 06/31] mm, vmscan: make kswapd reclaim in terms of nodes
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (4 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 05/31] mm, vmscan: have kswapd only scan based on the highest requested zone Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 07/31] mm, vmscan: remove balance gap Mel Gorman
` (25 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
Patch "mm: vmscan: Begin reclaiming pages on a per-node basis" started
thinking of reclaim in terms of nodes but kswapd is still zone-centric. This
patch gets rid of many of the node-based versus zone-based decisions.
o A node is considered balanced when any eligible lower zone is balanced.
This eliminates one class of age-inversion problem because we avoid
reclaiming a newer page just because it's in the wrong zone
o pgdat_balanced disappears because we now only care about one zone being
balanced.
o Some anomalies related to writeback and congestion tracking being based on
zones disappear.
o kswapd no longer has to take care to reclaim zones in the reverse order
that the page allocator uses.
o Most importantly of all, reclaim from node 0 with multiple zones will
have similar aging and reclaiming characteristics as every
other node.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
mm/vmscan.c | 292 +++++++++++++++++++++---------------------------------------
1 file changed, 101 insertions(+), 191 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c6e61dae382b..7b382b90b145 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2980,7 +2980,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
}
#endif
-static void age_active_anon(struct zone *zone, struct scan_control *sc)
+static void age_active_anon(struct pglist_data *pgdat,
+ struct zone *zone, struct scan_control *sc)
{
struct mem_cgroup *memcg;
@@ -2999,85 +3000,15 @@ static void age_active_anon(struct zone *zone, struct scan_control *sc)
} while (memcg);
}
-static bool zone_balanced(struct zone *zone, int order, bool highorder,
+static bool zone_balanced(struct zone *zone, int order,
unsigned long balance_gap, int classzone_idx)
{
unsigned long mark = high_wmark_pages(zone) + balance_gap;
- /*
- * When checking from pgdat_balanced(), kswapd should stop and sleep
- * when it reaches the high order-0 watermark and let kcompactd take
- * over. Other callers such as wakeup_kswapd() want to determine the
- * true high-order watermark.
- */
- if (IS_ENABLED(CONFIG_COMPACTION) && !highorder) {
- mark += (1UL << order);
- order = 0;
- }
-
return zone_watermark_ok_safe(zone, order, mark, classzone_idx);
}
/*
- * pgdat_balanced() is used when checking if a node is balanced.
- *
- * For order-0, all zones must be balanced!
- *
- * For high-order allocations only zones that meet watermarks and are in a
- * zone allowed by the callers classzone_idx are added to balanced_pages. The
- * total of balanced pages must be at least 25% of the zones allowed by
- * classzone_idx for the node to be considered balanced. Forcing all zones to
- * be balanced for high orders can cause excessive reclaim when there are
- * imbalanced zones.
- * The choice of 25% is due to
- * o a 16M DMA zone that is balanced will not balance a zone on any
- * reasonable sized machine
- * o On all other machines, the top zone must be at least a reasonable
- * percentage of the middle zones. For example, on 32-bit x86, highmem
- * would need to be at least 256M for it to be balance a whole node.
- * Similarly, on x86-64 the Normal zone would need to be at least 1G
- * to balance a node on its own. These seemed like reasonable ratios.
- */
-static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
-{
- unsigned long managed_pages = 0;
- unsigned long balanced_pages = 0;
- int i;
-
- /* Check the watermark levels */
- for (i = 0; i <= classzone_idx; i++) {
- struct zone *zone = pgdat->node_zones + i;
-
- if (!populated_zone(zone))
- continue;
-
- managed_pages += zone->managed_pages;
-
- /*
- * A special case here:
- *
- * balance_pgdat() skips over all_unreclaimable after
- * DEF_PRIORITY. Effectively, it considers them balanced so
- * they must be considered balanced here as well!
- */
- if (!pgdat_reclaimable(zone->zone_pgdat)) {
- balanced_pages += zone->managed_pages;
- continue;
- }
-
- if (zone_balanced(zone, order, false, 0, i))
- balanced_pages += zone->managed_pages;
- else if (!order)
- return false;
- }
-
- if (order)
- return balanced_pages >= (managed_pages >> 2);
- else
- return true;
-}
-
-/*
* Prepare kswapd for sleeping. This verifies that there are no processes
* waiting in throttle_direct_reclaim() and that watermarks have been met.
*
@@ -3086,6 +3017,8 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
int classzone_idx)
{
+ int i;
+
/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
if (remaining)
return false;
@@ -3106,101 +3039,90 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
if (waitqueue_active(&pgdat->pfmemalloc_wait))
wake_up_all(&pgdat->pfmemalloc_wait);
- return pgdat_balanced(pgdat, order, classzone_idx);
+ for (i = 0; i <= classzone_idx; i++) {
+ struct zone *zone = pgdat->node_zones + i;
+
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone_balanced(zone, order, 0, classzone_idx))
+ return true;
+ }
+
+ return false;
}
/*
- * kswapd shrinks the zone by the number of pages required to reach
- * the high watermark.
+ * kswapd shrinks a node of pages that are at or below the highest usable
+ * zone that is currently unbalanced.
*
* Returns true if kswapd scanned at least the requested number of pages to
* reclaim or if the lack of progress was due to pages under writeback.
* This is used to determine if the scanning priority needs to be raised.
*/
-static bool kswapd_shrink_zone(struct zone *zone,
+static bool kswapd_shrink_node(pg_data_t *pgdat,
int classzone_idx,
struct scan_control *sc)
{
- unsigned long balance_gap;
- bool lowmem_pressure;
- struct pglist_data *pgdat = zone->zone_pgdat;
+ struct zone *zone;
+ int z;
- /* Reclaim above the high watermark. */
- sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone));
+ /* Reclaim a number of pages proportional to the number of zones */
+ sc->nr_to_reclaim = 0;
+ for (z = 0; z <= classzone_idx; z++) {
+ zone = pgdat->node_zones + z;
+ if (!populated_zone(zone))
+ continue;
- /*
- * We put equal pressure on every zone, unless one zone has way too
- * many pages free already. The "too many pages" is defined as the
- * high wmark plus a "gap" where the gap is either the low
- * watermark or 1% of the zone, whichever is smaller.
- */
- balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP(
- zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO));
+ sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
+ }
/*
- * If there is no low memory pressure or the zone is balanced then no
- * reclaim is necessary
+ * Historically care was taken to put equal pressure on all zones but
+ * now pressure is applied based on node LRU order.
*/
- lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone));
- if (!lowmem_pressure && zone_balanced(zone, sc->order, false,
- balance_gap, classzone_idx))
- return true;
-
- shrink_node(zone->zone_pgdat, sc, classzone_idx);
-
- /* TODO: ANOMALY */
- clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
+ shrink_node(pgdat, sc, classzone_idx);
/*
- * If a zone reaches its high watermark, consider it to be no longer
- * congested. It's possible there are dirty pages backed by congested
- * BDIs but as pressure is relieved, speculatively avoid congestion
- * waits.
+ * Fragmentation may mean that the system cannot be rebalanced for
+ * high-order allocations. If twice the allocation size has been
+ * reclaimed then recheck watermarks only at order-0 to prevent
+ * excessive reclaim. Assume that a process requested a high-order
+ * can direct reclaim/compact.
*/
- if (pgdat_reclaimable(zone->zone_pgdat) &&
- zone_balanced(zone, sc->order, false, 0, classzone_idx)) {
- clear_bit(PGDAT_CONGESTED, &pgdat->flags);
- clear_bit(PGDAT_DIRTY, &pgdat->flags);
- }
+ if (sc->order && sc->nr_reclaimed >= 2UL << sc->order)
+ sc->order = 0;
return sc->nr_scanned >= sc->nr_to_reclaim;
}
/*
- * For kswapd, balance_pgdat() will work across all this node's zones until
- * they are all at high_wmark_pages(zone).
- *
- * Returns the highest zone idx kswapd was reclaiming at
+ * For kswapd, balance_pgdat() will reclaim pages across a node from zones
+ * that are eligible for use by the caller until at least one zone is
+ * balanced.
*
- * There is special handling here for zones which are full of pinned pages.
- * This can happen if the pages are all mlocked, or if they are all used by
- * device drivers (say, ZONE_DMA). Or if they are all in use by hugetlb.
- * What we do is to detect the case where all pages in the zone have been
- * scanned twice and there has been zero successful reclaim. Mark the zone as
- * dead and from now on, only perform a short scan. Basically we're polling
- * the zone for when the problem goes away.
+ * Returns the order kswapd finished reclaiming at.
*
* kswapd scans the zones in the highmem->normal->dma direction. It skips
* zones which have free_pages > high_wmark_pages(zone), but once a zone is
- * found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
- * lower zones regardless of the number of free pages in the lower zones. This
- * interoperates with the page allocator fallback scheme to ensure that aging
- * of pages is balanced across the zones.
+ * found to have free_pages <= high_wmark_pages(zone), any page is that zone
+ * or lower is eligible for reclaim until at least one usable zone is
+ * balanced.
*/
static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
{
int i;
- int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
+ struct zone *zone;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
- .reclaim_idx = MAX_NR_ZONES - 1,
.order = order,
.priority = DEF_PRIORITY,
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = 1,
+ .reclaim_idx = classzone_idx,
};
count_vm_event(PAGEOUTRUN);
@@ -3211,21 +3133,10 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
/* Scan from the highest requested zone to dma */
for (i = classzone_idx; i >= 0; i--) {
- struct zone *zone = pgdat->node_zones + i;
-
+ zone = pgdat->node_zones + i;
if (!populated_zone(zone))
continue;
- if (sc.priority != DEF_PRIORITY &&
- !pgdat_reclaimable(zone->zone_pgdat))
- continue;
-
- /*
- * Do some background aging of the anon list, to give
- * pages a chance to be referenced before reclaiming.
- */
- age_active_anon(zone, &sc);
-
/*
* If the number of buffer_heads in the machine
* exceeds the maximum allowed level and this node
@@ -3233,19 +3144,17 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
* it to relieve lowmem pressure.
*/
if (buffer_heads_over_limit && is_highmem_idx(i)) {
- end_zone = i;
+ classzone_idx = i;
break;
}
- if (!zone_balanced(zone, order, false, 0, 0)) {
- end_zone = i;
+ if (!zone_balanced(zone, order, 0, 0)) {
+ classzone_idx = i;
break;
} else {
/*
- * If balanced, clear the dirty and congested
- * flags
- *
- * TODO: ANOMALY
+ * If any eligible zone is balanced then the
+ * node is not considered congested or dirty.
*/
clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);
@@ -3256,51 +3165,34 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
goto out;
/*
+ * Do some background aging of the anon list, to give
+ * pages a chance to be referenced before reclaiming. All
+ * pages are rotated regardless of classzone as this is
+ * about consistent aging.
+ */
+ age_active_anon(pgdat, &pgdat->node_zones[MAX_NR_ZONES - 1], &sc);
+
+ /*
* If we're getting trouble reclaiming, start doing writepage
* even in laptop mode.
*/
- if (sc.priority < DEF_PRIORITY - 2)
+ if (sc.priority < DEF_PRIORITY - 2 || !pgdat_reclaimable(pgdat))
sc.may_writepage = 1;
+ /* Call soft limit reclaim before calling shrink_node. */
+ sc.nr_scanned = 0;
+ nr_soft_scanned = 0;
+ nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, sc.order,
+ sc.gfp_mask, &nr_soft_scanned);
+ sc.nr_reclaimed += nr_soft_reclaimed;
+
/*
- * Continue scanning in the highmem->dma direction stopping at
- * the last zone which needs scanning. This may reclaim lowmem
- * pages that are not necessary for zone balancing but it
- * preserves LRU ordering. It is assumed that the bulk of
- * allocation requests can use arbitrary zones with the
- * possible exception of big highmem:lowmem configurations.
+ * There should be no need to raise the scanning priority if
+ * enough pages are already being scanned that that high
+ * watermark would be met at 100% efficiency.
*/
- for (i = end_zone; i >= 0; i--) {
- struct zone *zone = pgdat->node_zones + i;
-
- if (!populated_zone(zone))
- continue;
-
- if (sc.priority != DEF_PRIORITY &&
- !pgdat_reclaimable(zone->zone_pgdat))
- continue;
-
- sc.nr_scanned = 0;
- sc.reclaim_idx = i;
-
- nr_soft_scanned = 0;
- /*
- * Call soft limit reclaim before calling shrink_zone.
- */
- nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
- order, sc.gfp_mask,
- &nr_soft_scanned);
- sc.nr_reclaimed += nr_soft_reclaimed;
-
- /*
- * There should be no need to raise the scanning
- * priority if enough pages are already being scanned
- * that that high watermark would be met at 100%
- * efficiency.
- */
- if (kswapd_shrink_zone(zone, end_zone, &sc))
- raise_priority = false;
- }
+ if (kswapd_shrink_node(pgdat, classzone_idx, &sc))
+ raise_priority = false;
/*
* If the low watermark is met there is no need for processes
@@ -3316,20 +3208,37 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
break;
/*
+ * Stop reclaiming if any eligible zone is balanced and clear
+ * node writeback or congested.
+ */
+ for (i = 0; i <= classzone_idx; i++) {
+ zone = pgdat->node_zones + i;
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone_balanced(zone, sc.order, 0, classzone_idx)) {
+ clear_bit(PGDAT_CONGESTED, &pgdat->flags);
+ clear_bit(PGDAT_DIRTY, &pgdat->flags);
+ goto out;
+ }
+ }
+
+ /*
* Raise priority if scanning rate is too low or there was no
* progress in reclaiming pages
*/
if (raise_priority || !sc.nr_reclaimed)
sc.priority--;
- } while (sc.priority >= 1 &&
- !pgdat_balanced(pgdat, order, classzone_idx));
+ } while (sc.priority >= 1);
out:
/*
- * Return the highest zone idx we were reclaiming at so
- * prepare_kswapd_sleep() makes the same decisions as here.
+ * Return the order kswapd stopped reclaiming at as
+ * prepare_kswapd_sleep() takes it into account. If another caller
+ * entered the allocator slow path while kswapd was awake, order will
+ * remain at the higher level.
*/
- return end_zone;
+ return sc.order;
}
static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
@@ -3486,8 +3395,9 @@ static int kswapd(void *p)
*/
if (!ret) {
trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
- balanced_classzone_idx = balance_pgdat(pgdat, order,
- classzone_idx);
+
+ /* return value ignored until next patch */
+ balance_pgdat(pgdat, order, classzone_idx);
}
}
@@ -3517,7 +3427,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
}
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
- if (zone_balanced(zone, order, true, 0, 0))
+ if (zone_balanced(zone, order, 0, 0))
return;
trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 07/31] mm, vmscan: remove balance gap
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (5 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 06/31] mm, vmscan: make kswapd reclaim in terms of nodes Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman
` (24 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
The balance gap was introduced to apply equal pressure to all zones when
reclaiming for a higher zone. With node-based LRU, the need for the
balance gap is removed and the code is dead so remove it.
[vbabka@suse.cz: Also remove KSWAPD_ZONE_BALANCE_GAP_RATIO]
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/swap.h | 9 ---------
mm/vmscan.c | 19 ++++++++-----------
2 files changed, 8 insertions(+), 20 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c82f916008b7..916e2eddecd6 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -157,15 +157,6 @@ enum {
#define SWAP_CLUSTER_MAX 32UL
#define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
-/*
- * Ratio between zone->managed_pages and the "gap" that above the per-zone
- * "high_wmark". While balancing nodes, We allow kswapd to shrink zones that
- * do not meet the (high_wmark + gap) watermark, even which already met the
- * high_wmark, in order to provide better per-zone lru behavior. We are ok to
- * spend not more than 1% of the memory for this zone balancing "gap".
- */
-#define KSWAPD_ZONE_BALANCE_GAP_RATIO 100
-
#define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */
#define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */
#define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7b382b90b145..a52167eabc96 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2518,7 +2518,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
*/
static inline bool compaction_ready(struct zone *zone, int order, int classzone_idx)
{
- unsigned long balance_gap, watermark;
+ unsigned long watermark;
bool watermark_ok;
/*
@@ -2527,9 +2527,7 @@ static inline bool compaction_ready(struct zone *zone, int order, int classzone_
* there is a buffer of free pages available to give compaction
* a reasonable chance of completing and allocating the page
*/
- balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP(
- zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO));
- watermark = high_wmark_pages(zone) + balance_gap + (2UL << order);
+ watermark = high_wmark_pages(zone) + (2UL << order);
watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, classzone_idx);
/*
@@ -3000,10 +2998,9 @@ static void age_active_anon(struct pglist_data *pgdat,
} while (memcg);
}
-static bool zone_balanced(struct zone *zone, int order,
- unsigned long balance_gap, int classzone_idx)
+static bool zone_balanced(struct zone *zone, int order, int classzone_idx)
{
- unsigned long mark = high_wmark_pages(zone) + balance_gap;
+ unsigned long mark = high_wmark_pages(zone);
return zone_watermark_ok_safe(zone, order, mark, classzone_idx);
}
@@ -3045,7 +3042,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
if (!populated_zone(zone))
continue;
- if (zone_balanced(zone, order, 0, classzone_idx))
+ if (zone_balanced(zone, order, classzone_idx))
return true;
}
@@ -3148,7 +3145,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
break;
}
- if (!zone_balanced(zone, order, 0, 0)) {
+ if (!zone_balanced(zone, order, 0)) {
classzone_idx = i;
break;
} else {
@@ -3216,7 +3213,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
if (!populated_zone(zone))
continue;
- if (zone_balanced(zone, sc.order, 0, classzone_idx)) {
+ if (zone_balanced(zone, sc.order, classzone_idx)) {
clear_bit(PGDAT_CONGESTED, &pgdat->flags);
clear_bit(PGDAT_DIRTY, &pgdat->flags);
goto out;
@@ -3427,7 +3424,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
}
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
- if (zone_balanced(zone, order, 0, 0))
+ if (zone_balanced(zone, order, 0))
return;
trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (6 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 07/31] mm, vmscan: remove balance gap Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-05 5:59 ` Minchan Kim
2016-07-07 1:20 ` Joonsoo Kim
2016-07-01 20:01 ` [PATCH 09/31] mm, vmscan: by default have direct reclaim only shrink once per node Mel Gorman
` (23 subsequent siblings)
31 siblings, 2 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
kswapd goes through some complex steps trying to figure out if it should
stay awake based on the classzone_idx and the requested order. It is
unnecessarily complex and passes in an invalid classzone_idx to
balance_pgdat(). What matters most of all is whether a larger order has
been requsted and whether kswapd successfully reclaimed at the previous
order. This patch irons out the logic to check just that and the end
result is less headache inducing.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/mmzone.h | 5 ++-
mm/memory_hotplug.c | 5 ++-
mm/page_alloc.c | 2 +-
mm/vmscan.c | 102 ++++++++++++++++++++++++++-----------------------
4 files changed, 62 insertions(+), 52 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 258c20758e80..eb74e63df5cf 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -667,8 +667,9 @@ typedef struct pglist_data {
wait_queue_head_t pfmemalloc_wait;
struct task_struct *kswapd; /* Protected by
mem_hotplug_begin/end() */
- int kswapd_max_order;
- enum zone_type classzone_idx;
+ int kswapd_order;
+ enum zone_type kswapd_classzone_idx;
+
#ifdef CONFIG_COMPACTION
int kcompactd_max_order;
enum zone_type kcompactd_classzone_idx;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c5278360ca66..065140ecd081 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1209,9 +1209,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
arch_refresh_nodedata(nid, pgdat);
} else {
- /* Reset the nr_zones and classzone_idx to 0 before reuse */
+ /* Reset the nr_zones, order and classzone_idx before reuse */
pgdat->nr_zones = 0;
- pgdat->classzone_idx = 0;
+ pgdat->kswapd_order = 0;
+ pgdat->kswapd_classzone_idx = 0;
}
/* we can use NODE_DATA(nid) from here */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 59e4463e5dce..f58548139bf2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6084,7 +6084,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
unsigned long end_pfn = 0;
/* pg_data_t should be reset to zero when it's allocated */
- WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
+ WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
reset_deferred_meminit(pgdat);
pgdat->node_id = nid;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a52167eabc96..b524d3b72527 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2762,7 +2762,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
/* kswapd must be awake if processes are being throttled */
if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
- pgdat->classzone_idx = min(pgdat->classzone_idx,
+ pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
(enum zone_type)ZONE_NORMAL);
wake_up_interruptible(&pgdat->kswapd_wait);
}
@@ -3238,8 +3238,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
return sc.order;
}
-static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
- int classzone_idx, int balanced_classzone_idx)
+static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
+ int classzone_idx)
{
long remaining = 0;
DEFINE_WAIT(wait);
@@ -3249,9 +3249,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
+ /*
+ * If kswapd has not been woken recently, then kswapd goes fully
+ * to sleep. kcompactd may still need to wake if the original
+ * request was high-order.
+ */
+ if (classzone_idx == -1) {
+ wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
+ classzone_idx = MAX_NR_ZONES - 1;
+ goto full_sleep;
+ }
+
/* Try to sleep for a short interval */
- if (prepare_kswapd_sleep(pgdat, order, remaining,
- balanced_classzone_idx)) {
+ if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
/*
* Compaction records what page blocks it recently failed to
* isolate pages from and skips them in the future scanning.
@@ -3264,19 +3274,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
* We have freed the memory, now we should compact it to make
* allocation of the requested order possible.
*/
- wakeup_kcompactd(pgdat, order, classzone_idx);
+ wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
remaining = schedule_timeout(HZ/10);
finish_wait(&pgdat->kswapd_wait, &wait);
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
}
+full_sleep:
/*
* After a short sleep, check if it was a premature sleep. If not, then
* go fully to sleep until explicitly woken up.
*/
- if (prepare_kswapd_sleep(pgdat, order, remaining,
- balanced_classzone_idx)) {
+ if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
/*
@@ -3317,9 +3327,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
*/
static int kswapd(void *p)
{
- unsigned long order, new_order;
- int classzone_idx, new_classzone_idx;
- int balanced_classzone_idx;
+ unsigned int alloc_order, reclaim_order, classzone_idx;
pg_data_t *pgdat = (pg_data_t*)p;
struct task_struct *tsk = current;
@@ -3349,38 +3357,26 @@ static int kswapd(void *p)
tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
set_freezable();
- order = new_order = 0;
- classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
- balanced_classzone_idx = classzone_idx;
+ pgdat->kswapd_order = alloc_order = reclaim_order = 0;
+ pgdat->kswapd_classzone_idx = classzone_idx = -1;
for ( ; ; ) {
bool ret;
+kswapd_try_sleep:
+ kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
+ classzone_idx);
+
/*
- * While we were reclaiming, there might have been another
- * wakeup, so check the values.
+ * Read the new order and classzone_idx which may be -1 if
+ * kswapd_try_to_sleep() woke up after a short timeout instead
+ * of being woken by the page allocator.
*/
- new_order = pgdat->kswapd_max_order;
- new_classzone_idx = pgdat->classzone_idx;
- pgdat->kswapd_max_order = 0;
- pgdat->classzone_idx = pgdat->nr_zones - 1;
-
- if (order < new_order || classzone_idx > new_classzone_idx) {
- /*
- * Don't sleep if someone wants a larger 'order'
- * allocation or has tigher zone constraints
- */
- order = new_order;
- classzone_idx = new_classzone_idx;
- } else {
- kswapd_try_to_sleep(pgdat, order, classzone_idx,
- balanced_classzone_idx);
- order = pgdat->kswapd_max_order;
- classzone_idx = pgdat->classzone_idx;
- new_order = order;
- new_classzone_idx = classzone_idx;
- pgdat->kswapd_max_order = 0;
- pgdat->classzone_idx = pgdat->nr_zones - 1;
- }
+ alloc_order = reclaim_order = pgdat->kswapd_order;
+ classzone_idx = pgdat->kswapd_classzone_idx;
+ if (classzone_idx == -1)
+ classzone_idx = MAX_NR_ZONES - 1;
+ pgdat->kswapd_order = 0;
+ pgdat->kswapd_classzone_idx = -1;
ret = try_to_freeze();
if (kthread_should_stop())
@@ -3390,12 +3386,24 @@ static int kswapd(void *p)
* We can speed up thawing tasks if we don't call balance_pgdat
* after returning from the refrigerator
*/
- if (!ret) {
- trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
+ if (ret)
+ continue;
- /* return value ignored until next patch */
- balance_pgdat(pgdat, order, classzone_idx);
- }
+ /*
+ * Reclaim begins at the requested order but if a high-order
+ * reclaim fails then kswapd falls back to reclaiming for
+ * order-0. If that happens, kswapd will consider sleeping
+ * for the order it finished reclaiming at (reclaim_order)
+ * but kcompactd is woken to compact for the original
+ * request (alloc_order).
+ */
+ trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order);
+ reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
+ if (reclaim_order < alloc_order)
+ goto kswapd_try_sleep;
+
+ alloc_order = reclaim_order = pgdat->kswapd_order;
+ classzone_idx = pgdat->kswapd_classzone_idx;
}
tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
@@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
return;
pgdat = zone->zone_pgdat;
- if (pgdat->kswapd_max_order < order) {
- pgdat->kswapd_max_order = order;
- pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
- }
+ if (pgdat->kswapd_classzone_idx == -1)
+ pgdat->kswapd_classzone_idx = classzone_idx;
+ pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+ pgdat->kswapd_order = max(pgdat->kswapd_order, order);
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
if (zone_balanced(zone, order, 0))
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 09/31] mm, vmscan: by default have direct reclaim only shrink once per node
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (7 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-07 1:43 ` Joonsoo Kim
2016-07-01 20:01 ` [PATCH 10/31] mm, vmscan: remove duplicate logic clearing node congestion and dirty state Mel Gorman
` (22 subsequent siblings)
31 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
Direct reclaim iterates over all zones in the zonelist and shrinking them
but this is in conflict with node-based reclaim. In the default case,
only shrink once per node.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
mm/vmscan.c | 19 +++++++++++--------
1 file changed, 11 insertions(+), 8 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b524d3b72527..34656173a670 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2552,14 +2552,6 @@ static inline bool compaction_ready(struct zone *zone, int order, int classzone_
* try to reclaim pages from zones which will satisfy the caller's allocation
* request.
*
- * We reclaim from a zone even if that zone is over high_wmark_pages(zone).
- * Because:
- * a) The caller may be trying to free *extra* pages to satisfy a higher-order
- * allocation or
- * b) The target zone may be at high_wmark_pages(zone) but the lower zones
- * must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
- * zone defense algorithm.
- *
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*/
@@ -2571,6 +2563,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
unsigned long nr_soft_scanned;
gfp_t orig_mask;
enum zone_type classzone_idx;
+ pg_data_t *last_pgdat = NULL;
/*
* If the number of buffer_heads in the machine exceeds the maximum
@@ -2600,6 +2593,16 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
classzone_idx--;
/*
+ * Shrink each node in the zonelist once. If the zonelist is
+ * ordered by zone (not the default) then a node may be
+ * shrunk multiple times but in that case the user prefers
+ * lower zones being preserved
+ */
+ if (zone->zone_pgdat == last_pgdat)
+ continue;
+ last_pgdat = zone->zone_pgdat;
+
+ /*
* Take care memory controller reclaiming has small influence
* to global LRU.
*/
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 10/31] mm, vmscan: remove duplicate logic clearing node congestion and dirty state
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (8 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 09/31] mm, vmscan: by default have direct reclaim only shrink once per node Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone Mel Gorman
` (21 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
Reclaim may stall if there is too much dirty or congested data on a node.
This was previously based on zone flags and the logic for clearing the
flags is in two places. As congestion/dirty tracking is now tracked on a
per-node basis, we can remove some duplicate logic.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
mm/vmscan.c | 24 ++++++++++++------------
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 34656173a670..911142d25de2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3005,7 +3005,17 @@ static bool zone_balanced(struct zone *zone, int order, int classzone_idx)
{
unsigned long mark = high_wmark_pages(zone);
- return zone_watermark_ok_safe(zone, order, mark, classzone_idx);
+ if (!zone_watermark_ok_safe(zone, order, mark, classzone_idx))
+ return false;
+
+ /*
+ * If any eligible zone is balanced then the node is not considered
+ * to be congested or dirty
+ */
+ clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
+ clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);
+
+ return true;
}
/*
@@ -3151,13 +3161,6 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
if (!zone_balanced(zone, order, 0)) {
classzone_idx = i;
break;
- } else {
- /*
- * If any eligible zone is balanced then the
- * node is not considered congested or dirty.
- */
- clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
- clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);
}
}
@@ -3216,11 +3219,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
if (!populated_zone(zone))
continue;
- if (zone_balanced(zone, sc.order, classzone_idx)) {
- clear_bit(PGDAT_CONGESTED, &pgdat->flags);
- clear_bit(PGDAT_DIRTY, &pgdat->flags);
+ if (zone_balanced(zone, sc.order, classzone_idx))
goto out;
- }
}
/*
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (9 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 10/31] mm, vmscan: remove duplicate logic clearing node congestion and dirty state Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-05 6:11 ` Minchan Kim
2016-07-01 20:01 ` [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric Mel Gorman
` (20 subsequent siblings)
31 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
kswapd scans from highest to lowest for a zone that requires balancing.
This was necessary when reclaim was per-zone to fairly age pages on lower
zones. Now that we are reclaiming on a per-node basis, any eligible zone
can be used and pages will still be aged fairly. This patch avoids
reclaiming excessively unless buffer_heads are over the limit and it's
necessary to reclaim from a higher zone than requested by the waker of
kswapd to relieve low memory pressure.
[hillf.zj@alibaba-inc.com: Force kswapd reclaim no more than needed]
Link: http://lkml.kernel.org/r/1466518566-30034-12-git-send-email-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
mm/vmscan.c | 56 ++++++++++++++++++++++++--------------------------------
1 file changed, 24 insertions(+), 32 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 911142d25de2..2f898ba2ee2e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3141,31 +3141,36 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
sc.nr_reclaimed = 0;
- /* Scan from the highest requested zone to dma */
- for (i = classzone_idx; i >= 0; i--) {
- zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
- continue;
-
- /*
- * If the number of buffer_heads in the machine
- * exceeds the maximum allowed level and this node
- * has a highmem zone, force kswapd to reclaim from
- * it to relieve lowmem pressure.
- */
- if (buffer_heads_over_limit && is_highmem_idx(i)) {
- classzone_idx = i;
- break;
- }
+ /*
+ * If the number of buffer_heads in the machine exceeds the
+ * maximum allowed level then reclaim from all zones. This is
+ * not specific to highmem as highmem may not exist but it is
+ * it is expected that buffer_heads are stripped in writeback.
+ */
+ if (buffer_heads_over_limit) {
+ for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
+ zone = pgdat->node_zones + i;
+ if (!populated_zone(zone))
+ continue;
- if (!zone_balanced(zone, order, 0)) {
classzone_idx = i;
break;
}
}
- if (i < 0)
- goto out;
+ /*
+ * Only reclaim if there are no eligible zones. Check from
+ * high to low zone to avoid prematurely clearing pgdat
+ * congested state.
+ */
+ for (i = classzone_idx; i >= 0; i--) {
+ zone = pgdat->node_zones + i;
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone_balanced(zone, sc.order, classzone_idx))
+ goto out;
+ }
/*
* Do some background aging of the anon list, to give
@@ -3211,19 +3216,6 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
break;
/*
- * Stop reclaiming if any eligible zone is balanced and clear
- * node writeback or congested.
- */
- for (i = 0; i <= classzone_idx; i++) {
- zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
- continue;
-
- if (zone_balanced(zone, sc.order, classzone_idx))
- goto out;
- }
-
- /*
* Raise priority if scanning rate is too low or there was no
* progress in reclaiming pages
*/
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (10 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-05 6:24 ` Minchan Kim
2016-07-01 20:01 ` [PATCH 13/31] mm, memcg: move memcg limit enforcement from zones to nodes Mel Gorman
` (19 subsequent siblings)
31 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
Earlier patches focused on having direct reclaim and kswapd use data that
is node-centric for reclaiming but shrink_node() itself still uses too
much zone information. This patch removes unnecessary zone-based
information with the most important decision being whether to continue
reclaim or not. Some memcg APIs are adjusted as a result even though
memcg itself still uses some zone information.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/memcontrol.h | 19 ++++++++--------
include/linux/mmzone.h | 4 ++--
include/linux/swap.h | 2 +-
mm/memcontrol.c | 4 ++--
mm/page_alloc.c | 2 +-
mm/vmscan.c | 57 ++++++++++++++++++++++++++--------------------
mm/workingset.c | 6 ++---
7 files changed, 51 insertions(+), 43 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1927dcb6921e..48b43c709ed7 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -325,22 +325,23 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
}
/**
- * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
+ * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
+ * @node: node of the wanted lruvec
* @zone: zone of the wanted lruvec
* @memcg: memcg of the wanted lruvec
*
- * Returns the lru list vector holding pages for the given @zone and
- * @mem. This can be the global zone lruvec, if the memory controller
+ * Returns the lru list vector holding pages for a given @node or a given
+ * @memcg and @zone. This can be the node lruvec, if the memory controller
* is disabled.
*/
-static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
- struct mem_cgroup *memcg)
+static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+ struct zone *zone, struct mem_cgroup *memcg)
{
struct mem_cgroup_per_zone *mz;
struct lruvec *lruvec;
if (mem_cgroup_disabled()) {
- lruvec = zone_lruvec(zone);
+ lruvec = node_lruvec(pgdat);
goto out;
}
@@ -610,10 +611,10 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
{
}
-static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
- struct mem_cgroup *memcg)
+static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+ struct zone *zone, struct mem_cgroup *memcg)
{
- return zone_lruvec(zone);
+ return node_lruvec(pgdat);
}
static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index eb74e63df5cf..f88cbbb476c8 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -739,9 +739,9 @@ static inline spinlock_t *zone_lru_lock(struct zone *zone)
return &zone->zone_pgdat->lru_lock;
}
-static inline struct lruvec *zone_lruvec(struct zone *zone)
+static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
{
- return &zone->zone_pgdat->lruvec;
+ return &pgdat->lruvec;
}
static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 916e2eddecd6..0ad616d7c381 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -316,7 +316,7 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
bool may_swap);
-extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
struct zone *zone,
unsigned long *nr_scanned);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 50c86ad121bc..c9ebec98e92a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1432,8 +1432,8 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
}
continue;
}
- total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
- zone, &nr_scanned);
+ total += mem_cgroup_shrink_node(victim, gfp_mask, false,
+ zone, &nr_scanned);
*total_scanned += nr_scanned;
if (!soft_limit_excess(root_memcg))
break;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f58548139bf2..b76ea2527c09 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5954,6 +5954,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
#endif
pgdat_page_ext_init(pgdat);
spin_lock_init(&pgdat->lru_lock);
+ lruvec_init(node_lruvec(pgdat));
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
@@ -6016,7 +6017,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
/* For bootup, initialized properly in watermark setup */
mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
- lruvec_init(zone_lruvec(zone));
if (!size)
continue;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2f898ba2ee2e..b8e0f76b6e00 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2226,10 +2226,11 @@ static inline void init_tlb_ubc(void)
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
-static void shrink_zone_memcg(struct zone *zone, struct mem_cgroup *memcg,
+static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg,
struct scan_control *sc, unsigned long *lru_pages)
{
- struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+ struct zone *zone = &pgdat->node_zones[sc->reclaim_idx];
+ struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, zone, memcg);
unsigned long nr[NR_LRU_LISTS];
unsigned long targets[NR_LRU_LISTS];
unsigned long nr_to_scan;
@@ -2362,13 +2363,14 @@ static bool in_reclaim_compaction(struct scan_control *sc)
* calls try_to_compact_zone() that it will have enough free pages to succeed.
* It will give up earlier than that if there is difficulty reclaiming pages.
*/
-static inline bool should_continue_reclaim(struct zone *zone,
+static inline bool should_continue_reclaim(struct pglist_data *pgdat,
unsigned long nr_reclaimed,
unsigned long nr_scanned,
struct scan_control *sc)
{
unsigned long pages_for_compaction;
unsigned long inactive_lru_pages;
+ int z;
/* If not in reclaim/compaction mode, stop */
if (!in_reclaim_compaction(sc))
@@ -2402,21 +2404,27 @@ static inline bool should_continue_reclaim(struct zone *zone,
* inactive lists are large enough, continue reclaiming
*/
pages_for_compaction = (2UL << sc->order);
- inactive_lru_pages = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE);
+ inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
if (get_nr_swap_pages() > 0)
- inactive_lru_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON);
+ inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
if (sc->nr_reclaimed < pages_for_compaction &&
inactive_lru_pages > pages_for_compaction)
return true;
/* If compaction would go ahead or the allocation would succeed, stop */
- switch (compaction_suitable(zone, sc->order, 0, 0)) {
- case COMPACT_PARTIAL:
- case COMPACT_CONTINUE:
- return false;
- default:
- return true;
+ for (z = 0; z <= sc->reclaim_idx; z++) {
+ struct zone *zone = &pgdat->node_zones[z];
+
+ switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
+ case COMPACT_PARTIAL:
+ case COMPACT_CONTINUE:
+ return false;
+ default:
+ /* check next zone */
+ ;
+ }
}
+ return true;
}
static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
@@ -2425,15 +2433,14 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
bool reclaimable = false;
- struct zone *zone = &pgdat->node_zones[classzone_idx];
do {
struct mem_cgroup *root = sc->target_mem_cgroup;
struct mem_cgroup_reclaim_cookie reclaim = {
- .zone = zone,
+ .zone = &pgdat->node_zones[classzone_idx],
.priority = sc->priority,
};
- unsigned long zone_lru_pages = 0;
+ unsigned long node_lru_pages = 0;
struct mem_cgroup *memcg;
nr_reclaimed = sc->nr_reclaimed;
@@ -2454,11 +2461,11 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
reclaimed = sc->nr_reclaimed;
scanned = sc->nr_scanned;
- shrink_zone_memcg(zone, memcg, sc, &lru_pages);
- zone_lru_pages += lru_pages;
+ shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
+ node_lru_pages += lru_pages;
if (!global_reclaim(sc))
- shrink_slab(sc->gfp_mask, zone_to_nid(zone),
+ shrink_slab(sc->gfp_mask, pgdat->node_id,
memcg, sc->nr_scanned - scanned,
lru_pages);
@@ -2470,7 +2477,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
/*
* Direct reclaim and kswapd have to scan all memory
* cgroups to fulfill the overall scan target for the
- * zone.
+ * node.
*
* Limit reclaim, on the other hand, only cares about
* nr_to_reclaim pages to be reclaimed and it will
@@ -2489,9 +2496,9 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
* the eligible LRU pages were scanned.
*/
if (global_reclaim(sc))
- shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
+ shrink_slab(sc->gfp_mask, pgdat->node_id, NULL,
sc->nr_scanned - nr_scanned,
- zone_lru_pages);
+ node_lru_pages);
if (reclaim_state) {
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
@@ -2506,7 +2513,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
if (sc->nr_reclaimed - nr_reclaimed)
reclaimable = true;
- } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
+ } while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
sc->nr_scanned - nr_scanned, sc));
return reclaimable;
@@ -2903,7 +2910,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
#ifdef CONFIG_MEMCG
-unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
+unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
gfp_t gfp_mask, bool noswap,
struct zone *zone,
unsigned long *nr_scanned)
@@ -2928,11 +2935,11 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
/*
* NOTE: Although we can get the priority field, using it
* here is not a good idea, since it limits the pages we can scan.
- * if we don't reclaim here, the shrink_zone from balance_pgdat
+ * if we don't reclaim here, the shrink_node from balance_pgdat
* will pick up pages from other mem cgroup's as well. We hack
* the priority and make it zero.
*/
- shrink_zone_memcg(zone, memcg, &sc, &lru_pages);
+ shrink_node_memcg(zone->zone_pgdat, memcg, &sc, &lru_pages);
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
@@ -2991,7 +2998,7 @@ static void age_active_anon(struct pglist_data *pgdat,
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
- struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+ struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, zone, memcg);
if (inactive_list_is_low(lruvec, false))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
diff --git a/mm/workingset.c b/mm/workingset.c
index ebe14445809a..de68ad681585 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -218,7 +218,7 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)
VM_BUG_ON_PAGE(page_count(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
- lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+ lruvec = mem_cgroup_lruvec(zone->zone_pgdat, zone, memcg);
eviction = atomic_long_inc_return(&lruvec->inactive_age);
return pack_shadow(memcgid, zone, eviction);
}
@@ -267,7 +267,7 @@ bool workingset_refault(void *shadow)
rcu_read_unlock();
return false;
}
- lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+ lruvec = mem_cgroup_lruvec(zone->zone_pgdat, zone, memcg);
refault = atomic_long_read(&lruvec->inactive_age);
active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
rcu_read_unlock();
@@ -319,7 +319,7 @@ void workingset_activation(struct page *page)
memcg = page_memcg_rcu(page);
if (!mem_cgroup_disabled() && !memcg)
goto out;
- lruvec = mem_cgroup_zone_lruvec(page_zone(page), memcg);
+ lruvec = mem_cgroup_lruvec(page_pgdat(page), page_zone(page), memcg);
atomic_long_inc(&lruvec->inactive_age);
out:
rcu_read_unlock();
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 13/31] mm, memcg: move memcg limit enforcement from zones to nodes
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (11 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 14/31] mm, workingset: make working set detection node-aware Mel Gorman
` (18 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
Memcg needs adjustment after moving LRUs to the node. Limits are tracked
per memcg but the soft-limit excess is tracked per zone. As global page
reclaim is based on the node, it is easy to imagine a situation where
a zone soft limit is exceeded even though the memcg limit is fine.
This patch moves the soft limit tree the node. Technically, all the variable
names should also change but people are already familiar by the meaning of
"mz" even if "mn" would be a more appropriate name now.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Michal Hocko <mhocko@suse.com>
---
include/linux/memcontrol.h | 38 ++++-----
include/linux/swap.h | 2 +-
mm/memcontrol.c | 190 ++++++++++++++++++++-------------------------
mm/vmscan.c | 19 +++--
mm/workingset.c | 6 +-
5 files changed, 111 insertions(+), 144 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 48b43c709ed7..65e472f48f6c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -61,7 +61,7 @@ enum mem_cgroup_stat_index {
};
struct mem_cgroup_reclaim_cookie {
- struct zone *zone;
+ pg_data_t *pgdat;
int priority;
unsigned int generation;
};
@@ -119,7 +119,7 @@ struct mem_cgroup_reclaim_iter {
/*
* per-zone information in memory controller.
*/
-struct mem_cgroup_per_zone {
+struct mem_cgroup_per_node {
struct lruvec lruvec;
unsigned long lru_size[NR_LRU_LISTS];
@@ -133,10 +133,6 @@ struct mem_cgroup_per_zone {
/* use container_of */
};
-struct mem_cgroup_per_node {
- struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
-};
-
struct mem_cgroup_threshold {
struct eventfd_ctx *eventfd;
unsigned long threshold;
@@ -315,19 +311,15 @@ void mem_cgroup_uncharge_list(struct list_head *page_list);
void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
-static inline struct mem_cgroup_per_zone *
-mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
+static struct mem_cgroup_per_node *
+mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
{
- int nid = zone_to_nid(zone);
- int zid = zone_idx(zone);
-
- return &memcg->nodeinfo[nid]->zoneinfo[zid];
+ return memcg->nodeinfo[nid];
}
/**
* mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
* @node: node of the wanted lruvec
- * @zone: zone of the wanted lruvec
* @memcg: memcg of the wanted lruvec
*
* Returns the lru list vector holding pages for a given @node or a given
@@ -335,9 +327,9 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
* is disabled.
*/
static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
- struct zone *zone, struct mem_cgroup *memcg)
+ struct mem_cgroup *memcg)
{
- struct mem_cgroup_per_zone *mz;
+ struct mem_cgroup_per_node *mz;
struct lruvec *lruvec;
if (mem_cgroup_disabled()) {
@@ -345,7 +337,7 @@ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
goto out;
}
- mz = mem_cgroup_zone_zoneinfo(memcg, zone);
+ mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
lruvec = &mz->lruvec;
out:
/*
@@ -353,8 +345,8 @@ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
* we have to be prepared to initialize lruvec->zone here;
* and if offlined then reonlined, we need to reinitialize it.
*/
- if (unlikely(lruvec->pgdat != zone->zone_pgdat))
- lruvec->pgdat = zone->zone_pgdat;
+ if (unlikely(lruvec->pgdat != pgdat))
+ lruvec->pgdat = pgdat;
return lruvec;
}
@@ -447,9 +439,9 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
static inline
unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
- struct mem_cgroup_per_zone *mz;
+ struct mem_cgroup_per_node *mz;
- mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+ mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
return mz->lru_size[lru];
}
@@ -520,7 +512,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
mem_cgroup_update_page_stat(page, idx, -1);
}
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
gfp_t gfp_mask,
unsigned long *total_scanned);
@@ -612,7 +604,7 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
}
static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
- struct zone *zone, struct mem_cgroup *memcg)
+ struct mem_cgroup *memcg)
{
return node_lruvec(pgdat);
}
@@ -724,7 +716,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
}
static inline
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
gfp_t gfp_mask,
unsigned long *total_scanned)
{
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 0ad616d7c381..2a23ddc96edd 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -318,7 +318,7 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
bool may_swap);
extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
- struct zone *zone,
+ pg_data_t *pgdat,
unsigned long *nr_scanned);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c9ebec98e92a..9cbd40ebccd1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -132,15 +132,11 @@ static const char * const mem_cgroup_lru_names[] = {
* their hierarchy representation
*/
-struct mem_cgroup_tree_per_zone {
+struct mem_cgroup_tree_per_node {
struct rb_root rb_root;
spinlock_t lock;
};
-struct mem_cgroup_tree_per_node {
- struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
-};
-
struct mem_cgroup_tree {
struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
};
@@ -374,37 +370,35 @@ ino_t page_cgroup_ino(struct page *page)
return ino;
}
-static struct mem_cgroup_per_zone *
-mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
+static struct mem_cgroup_per_node *
+mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page)
{
int nid = page_to_nid(page);
- int zid = page_zonenum(page);
- return &memcg->nodeinfo[nid]->zoneinfo[zid];
+ return memcg->nodeinfo[nid];
}
-static struct mem_cgroup_tree_per_zone *
-soft_limit_tree_node_zone(int nid, int zid)
+static struct mem_cgroup_tree_per_node *
+soft_limit_tree_node(int nid)
{
- return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+ return soft_limit_tree.rb_tree_per_node[nid];
}
-static struct mem_cgroup_tree_per_zone *
+static struct mem_cgroup_tree_per_node *
soft_limit_tree_from_page(struct page *page)
{
int nid = page_to_nid(page);
- int zid = page_zonenum(page);
- return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+ return soft_limit_tree.rb_tree_per_node[nid];
}
-static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
- struct mem_cgroup_tree_per_zone *mctz,
+static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
+ struct mem_cgroup_tree_per_node *mctz,
unsigned long new_usage_in_excess)
{
struct rb_node **p = &mctz->rb_root.rb_node;
struct rb_node *parent = NULL;
- struct mem_cgroup_per_zone *mz_node;
+ struct mem_cgroup_per_node *mz_node;
if (mz->on_tree)
return;
@@ -414,7 +408,7 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
return;
while (*p) {
parent = *p;
- mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
+ mz_node = rb_entry(parent, struct mem_cgroup_per_node,
tree_node);
if (mz->usage_in_excess < mz_node->usage_in_excess)
p = &(*p)->rb_left;
@@ -430,8 +424,8 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
mz->on_tree = true;
}
-static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
- struct mem_cgroup_tree_per_zone *mctz)
+static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+ struct mem_cgroup_tree_per_node *mctz)
{
if (!mz->on_tree)
return;
@@ -439,8 +433,8 @@ static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
mz->on_tree = false;
}
-static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
- struct mem_cgroup_tree_per_zone *mctz)
+static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+ struct mem_cgroup_tree_per_node *mctz)
{
unsigned long flags;
@@ -464,8 +458,8 @@ static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
{
unsigned long excess;
- struct mem_cgroup_per_zone *mz;
- struct mem_cgroup_tree_per_zone *mctz;
+ struct mem_cgroup_per_node *mz;
+ struct mem_cgroup_tree_per_node *mctz;
mctz = soft_limit_tree_from_page(page);
/*
@@ -473,7 +467,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
* because their event counter is not touched.
*/
for (; memcg; memcg = parent_mem_cgroup(memcg)) {
- mz = mem_cgroup_page_zoneinfo(memcg, page);
+ mz = mem_cgroup_page_nodeinfo(memcg, page);
excess = soft_limit_excess(memcg);
/*
* We have to update the tree if mz is on RB-tree or
@@ -498,24 +492,22 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
{
- struct mem_cgroup_tree_per_zone *mctz;
- struct mem_cgroup_per_zone *mz;
- int nid, zid;
+ struct mem_cgroup_tree_per_node *mctz;
+ struct mem_cgroup_per_node *mz;
+ int nid;
for_each_node(nid) {
- for (zid = 0; zid < MAX_NR_ZONES; zid++) {
- mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
- mctz = soft_limit_tree_node_zone(nid, zid);
- mem_cgroup_remove_exceeded(mz, mctz);
- }
+ mz = mem_cgroup_nodeinfo(memcg, nid);
+ mctz = soft_limit_tree_node(nid);
+ mem_cgroup_remove_exceeded(mz, mctz);
}
}
-static struct mem_cgroup_per_zone *
-__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+static struct mem_cgroup_per_node *
+__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
{
struct rb_node *rightmost = NULL;
- struct mem_cgroup_per_zone *mz;
+ struct mem_cgroup_per_node *mz;
retry:
mz = NULL;
@@ -523,7 +515,7 @@ __mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
if (!rightmost)
goto done; /* Nothing to reclaim from */
- mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node);
+ mz = rb_entry(rightmost, struct mem_cgroup_per_node, tree_node);
/*
* Remove the node now but someone else can add it back,
* we will to add it back at the end of reclaim to its correct
@@ -537,10 +529,10 @@ __mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
return mz;
}
-static struct mem_cgroup_per_zone *
-mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+static struct mem_cgroup_per_node *
+mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
{
- struct mem_cgroup_per_zone *mz;
+ struct mem_cgroup_per_node *mz;
spin_lock_irq(&mctz->lock);
mz = __mem_cgroup_largest_soft_limit_node(mctz);
@@ -634,20 +626,16 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
int nid, unsigned int lru_mask)
{
unsigned long nr = 0;
- int zid;
+ struct mem_cgroup_per_node *mz;
+ enum lru_list lru;
VM_BUG_ON((unsigned)nid >= nr_node_ids);
- for (zid = 0; zid < MAX_NR_ZONES; zid++) {
- struct mem_cgroup_per_zone *mz;
- enum lru_list lru;
-
- for_each_lru(lru) {
- if (!(BIT(lru) & lru_mask))
- continue;
- mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
- nr += mz->lru_size[lru];
- }
+ for_each_lru(lru) {
+ if (!(BIT(lru) & lru_mask))
+ continue;
+ mz = mem_cgroup_nodeinfo(memcg, nid);
+ nr += mz->lru_size[lru];
}
return nr;
}
@@ -800,9 +788,9 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
rcu_read_lock();
if (reclaim) {
- struct mem_cgroup_per_zone *mz;
+ struct mem_cgroup_per_node *mz;
- mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone);
+ mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id);
iter = &mz->iter[reclaim->priority];
if (prev && reclaim->generation != iter->generation)
@@ -901,19 +889,17 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
{
struct mem_cgroup *memcg = dead_memcg;
struct mem_cgroup_reclaim_iter *iter;
- struct mem_cgroup_per_zone *mz;
- int nid, zid;
+ struct mem_cgroup_per_node *mz;
+ int nid;
int i;
while ((memcg = parent_mem_cgroup(memcg))) {
for_each_node(nid) {
- for (zid = 0; zid < MAX_NR_ZONES; zid++) {
- mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
- for (i = 0; i <= DEF_PRIORITY; i++) {
- iter = &mz->iter[i];
- cmpxchg(&iter->position,
- dead_memcg, NULL);
- }
+ mz = mem_cgroup_nodeinfo(memcg, nid);
+ for (i = 0; i <= DEF_PRIORITY; i++) {
+ iter = &mz->iter[i];
+ cmpxchg(&iter->position,
+ dead_memcg, NULL);
}
}
}
@@ -945,7 +931,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
*/
struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat)
{
- struct mem_cgroup_per_zone *mz;
+ struct mem_cgroup_per_node *mz;
struct mem_cgroup *memcg;
struct lruvec *lruvec;
@@ -962,7 +948,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd
if (!memcg)
memcg = root_mem_cgroup;
- mz = mem_cgroup_page_zoneinfo(memcg, page);
+ mz = mem_cgroup_page_nodeinfo(memcg, page);
lruvec = &mz->lruvec;
out:
/*
@@ -989,7 +975,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
enum zone_type zid, int nr_pages)
{
- struct mem_cgroup_per_zone *mz;
+ struct mem_cgroup_per_node *mz;
unsigned long *lru_size;
long size;
bool empty;
@@ -999,7 +985,7 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
if (mem_cgroup_disabled())
return;
- mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+ mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
lru_size = mz->lru_size + lru;
empty = list_empty(lruvec->lists + lru);
@@ -1392,7 +1378,7 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
#endif
static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
- struct zone *zone,
+ pg_data_t *pgdat,
gfp_t gfp_mask,
unsigned long *total_scanned)
{
@@ -1402,7 +1388,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
unsigned long excess;
unsigned long nr_scanned;
struct mem_cgroup_reclaim_cookie reclaim = {
- .zone = zone,
+ .pgdat = pgdat,
.priority = 0,
};
@@ -1433,7 +1419,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
continue;
}
total += mem_cgroup_shrink_node(victim, gfp_mask, false,
- zone, &nr_scanned);
+ pgdat, &nr_scanned);
*total_scanned += nr_scanned;
if (!soft_limit_excess(root_memcg))
break;
@@ -2560,22 +2546,22 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
return ret;
}
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
gfp_t gfp_mask,
unsigned long *total_scanned)
{
unsigned long nr_reclaimed = 0;
- struct mem_cgroup_per_zone *mz, *next_mz = NULL;
+ struct mem_cgroup_per_node *mz, *next_mz = NULL;
unsigned long reclaimed;
int loop = 0;
- struct mem_cgroup_tree_per_zone *mctz;
+ struct mem_cgroup_tree_per_node *mctz;
unsigned long excess;
unsigned long nr_scanned;
if (order > 0)
return 0;
- mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
+ mctz = soft_limit_tree_node(pgdat->node_id);
/*
* This loop can run a while, specially if mem_cgroup's continuously
* keep exceeding their soft limit and putting the system under
@@ -2590,7 +2576,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
break;
nr_scanned = 0;
- reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
+ reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat,
gfp_mask, &nr_scanned);
nr_reclaimed += reclaimed;
*total_scanned += nr_scanned;
@@ -3211,22 +3197,21 @@ static int memcg_stat_show(struct seq_file *m, void *v)
#ifdef CONFIG_DEBUG_VM
{
- int nid, zid;
- struct mem_cgroup_per_zone *mz;
+ pg_data_t *pgdat;
+ struct mem_cgroup_per_node *mz;
struct zone_reclaim_stat *rstat;
unsigned long recent_rotated[2] = {0, 0};
unsigned long recent_scanned[2] = {0, 0};
- for_each_online_node(nid)
- for (zid = 0; zid < MAX_NR_ZONES; zid++) {
- mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
- rstat = &mz->lruvec.reclaim_stat;
+ for_each_online_pgdat(pgdat) {
+ mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
+ rstat = &mz->lruvec.reclaim_stat;
- recent_rotated[0] += rstat->recent_rotated[0];
- recent_rotated[1] += rstat->recent_rotated[1];
- recent_scanned[0] += rstat->recent_scanned[0];
- recent_scanned[1] += rstat->recent_scanned[1];
- }
+ recent_rotated[0] += rstat->recent_rotated[0];
+ recent_rotated[1] += rstat->recent_rotated[1];
+ recent_scanned[0] += rstat->recent_scanned[0];
+ recent_scanned[1] += rstat->recent_scanned[1];
+ }
seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]);
seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]);
seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]);
@@ -4106,11 +4091,10 @@ struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
return idr_find(&mem_cgroup_idr, id);
}
-static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
+static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
{
struct mem_cgroup_per_node *pn;
- struct mem_cgroup_per_zone *mz;
- int zone, tmp = node;
+ int tmp = node;
/*
* This routine is called against possible nodes.
* But it's BUG to call kmalloc() against offline node.
@@ -4125,18 +4109,16 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
if (!pn)
return 1;
- for (zone = 0; zone < MAX_NR_ZONES; zone++) {
- mz = &pn->zoneinfo[zone];
- lruvec_init(&mz->lruvec);
- mz->usage_in_excess = 0;
- mz->on_tree = false;
- mz->memcg = memcg;
- }
+ lruvec_init(&pn->lruvec);
+ pn->usage_in_excess = 0;
+ pn->on_tree = false;
+ pn->memcg = memcg;
+
memcg->nodeinfo[node] = pn;
return 0;
}
-static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
+static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
{
kfree(memcg->nodeinfo[node]);
}
@@ -4147,7 +4129,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
memcg_wb_domain_exit(memcg);
for_each_node(node)
- free_mem_cgroup_per_zone_info(memcg, node);
+ free_mem_cgroup_per_node_info(memcg, node);
free_percpu(memcg->stat);
kfree(memcg);
}
@@ -4176,7 +4158,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
goto fail;
for_each_node(node)
- if (alloc_mem_cgroup_per_zone_info(memcg, node))
+ if (alloc_mem_cgroup_per_node_info(memcg, node))
goto fail;
if (memcg_wb_domain_init(memcg, GFP_KERNEL))
@@ -5779,18 +5761,12 @@ static int __init mem_cgroup_init(void)
for_each_node(node) {
struct mem_cgroup_tree_per_node *rtpn;
- int zone;
rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL,
node_online(node) ? node : NUMA_NO_NODE);
- for (zone = 0; zone < MAX_NR_ZONES; zone++) {
- struct mem_cgroup_tree_per_zone *rtpz;
-
- rtpz = &rtpn->rb_tree_per_zone[zone];
- rtpz->rb_root = RB_ROOT;
- spin_lock_init(&rtpz->lock);
- }
+ rtpn->rb_root = RB_ROOT;
+ spin_lock_init(&rtpn->lock);
soft_limit_tree.rb_tree_per_node[node] = rtpn;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b8e0f76b6e00..82b59b63b481 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2229,8 +2229,7 @@ static inline void init_tlb_ubc(void)
static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg,
struct scan_control *sc, unsigned long *lru_pages)
{
- struct zone *zone = &pgdat->node_zones[sc->reclaim_idx];
- struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, zone, memcg);
+ struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
unsigned long nr[NR_LRU_LISTS];
unsigned long targets[NR_LRU_LISTS];
unsigned long nr_to_scan;
@@ -2437,7 +2436,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
do {
struct mem_cgroup *root = sc->target_mem_cgroup;
struct mem_cgroup_reclaim_cookie reclaim = {
- .zone = &pgdat->node_zones[classzone_idx],
+ .pgdat = pgdat,
.priority = sc->priority,
};
unsigned long node_lru_pages = 0;
@@ -2646,7 +2645,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
* and balancing, not for a memcg's limit.
*/
nr_soft_scanned = 0;
- nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+ nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat,
sc->order, sc->gfp_mask,
&nr_soft_scanned);
sc->nr_reclaimed += nr_soft_reclaimed;
@@ -2912,7 +2911,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
gfp_t gfp_mask, bool noswap,
- struct zone *zone,
+ pg_data_t *pgdat,
unsigned long *nr_scanned)
{
struct scan_control sc = {
@@ -2939,7 +2938,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
* will pick up pages from other mem cgroup's as well. We hack
* the priority and make it zero.
*/
- shrink_node_memcg(zone->zone_pgdat, memcg, &sc, &lru_pages);
+ shrink_node_memcg(pgdat, memcg, &sc, &lru_pages);
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
@@ -2989,7 +2988,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
#endif
static void age_active_anon(struct pglist_data *pgdat,
- struct zone *zone, struct scan_control *sc)
+ struct scan_control *sc)
{
struct mem_cgroup *memcg;
@@ -2998,7 +2997,7 @@ static void age_active_anon(struct pglist_data *pgdat,
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
- struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, zone, memcg);
+ struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
if (inactive_list_is_low(lruvec, false))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
@@ -3185,7 +3184,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
* pages are rotated regardless of classzone as this is
* about consistent aging.
*/
- age_active_anon(pgdat, &pgdat->node_zones[MAX_NR_ZONES - 1], &sc);
+ age_active_anon(pgdat, &sc);
/*
* If we're getting trouble reclaiming, start doing writepage
@@ -3197,7 +3196,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
/* Call soft limit reclaim before calling shrink_node. */
sc.nr_scanned = 0;
nr_soft_scanned = 0;
- nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, sc.order,
+ nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order,
sc.gfp_mask, &nr_soft_scanned);
sc.nr_reclaimed += nr_soft_reclaimed;
diff --git a/mm/workingset.c b/mm/workingset.c
index de68ad681585..9a1016f5d500 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -218,7 +218,7 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)
VM_BUG_ON_PAGE(page_count(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
- lruvec = mem_cgroup_lruvec(zone->zone_pgdat, zone, memcg);
+ lruvec = mem_cgroup_lruvec(zone->zone_pgdat, memcg);
eviction = atomic_long_inc_return(&lruvec->inactive_age);
return pack_shadow(memcgid, zone, eviction);
}
@@ -267,7 +267,7 @@ bool workingset_refault(void *shadow)
rcu_read_unlock();
return false;
}
- lruvec = mem_cgroup_lruvec(zone->zone_pgdat, zone, memcg);
+ lruvec = mem_cgroup_lruvec(zone->zone_pgdat, memcg);
refault = atomic_long_read(&lruvec->inactive_age);
active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
rcu_read_unlock();
@@ -319,7 +319,7 @@ void workingset_activation(struct page *page)
memcg = page_memcg_rcu(page);
if (!mem_cgroup_disabled() && !memcg)
goto out;
- lruvec = mem_cgroup_lruvec(page_pgdat(page), page_zone(page), memcg);
+ lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
atomic_long_inc(&lruvec->inactive_age);
out:
rcu_read_unlock();
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 14/31] mm, workingset: make working set detection node-aware
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (12 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 13/31] mm, memcg: move memcg limit enforcement from zones to nodes Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 15/31] mm, page_alloc: consider dirtyable memory in terms of nodes Mel Gorman
` (17 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
Working set and refault detection is still zone-based, fix it.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/mmzone.h | 6 +++---
include/linux/vmstat.h | 1 -
mm/vmstat.c | 20 +++-----------------
mm/workingset.c | 43 ++++++++++++++++++++-----------------------
4 files changed, 26 insertions(+), 44 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f88cbbb476c8..08e0dc9cd7cd 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -145,9 +145,6 @@ enum zone_stat_item {
NUMA_LOCAL, /* allocation from local node */
NUMA_OTHER, /* allocation from other node */
#endif
- WORKINGSET_REFAULT,
- WORKINGSET_ACTIVATE,
- WORKINGSET_NODERECLAIM,
NR_ANON_THPS,
NR_SHMEM_THPS,
NR_SHMEM_PMDMAPPED,
@@ -164,6 +161,9 @@ enum node_stat_item {
NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
NR_PAGES_SCANNED, /* pages scanned since last reclaim */
+ WORKINGSET_REFAULT,
+ WORKINGSET_ACTIVATE,
+ WORKINGSET_NODERECLAIM,
NR_VM_NODE_STAT_ITEMS
};
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index ced0c3e9da88..552d0db4fca2 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -227,7 +227,6 @@ void mod_node_page_state(struct pglist_data *, enum node_stat_item, long);
void inc_node_page_state(struct page *, enum node_stat_item);
void dec_node_page_state(struct page *, enum node_stat_item);
-extern void inc_zone_state(struct zone *, enum zone_stat_item);
extern void inc_node_state(struct pglist_data *, enum node_stat_item);
extern void __inc_zone_state(struct zone *, enum zone_stat_item);
extern void __inc_node_state(struct pglist_data *, enum node_stat_item);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 2eab7903c5c2..89426c250a9a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -433,11 +433,6 @@ void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
}
EXPORT_SYMBOL(mod_zone_page_state);
-void inc_zone_state(struct zone *zone, enum zone_stat_item item)
-{
- mod_zone_state(zone, item, 1, 1);
-}
-
void inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
mod_zone_state(page_zone(page), item, 1, 1);
@@ -526,15 +521,6 @@ void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
}
EXPORT_SYMBOL(mod_zone_page_state);
-void inc_zone_state(struct zone *zone, enum zone_stat_item item)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __inc_zone_state(zone, item);
- local_irq_restore(flags);
-}
-
void inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
unsigned long flags;
@@ -954,9 +940,6 @@ const char * const vmstat_text[] = {
"numa_local",
"numa_other",
#endif
- "workingset_refault",
- "workingset_activate",
- "workingset_nodereclaim",
"nr_anon_transparent_hugepages",
"nr_shmem_hugepages",
"nr_shmem_pmdmapped",
@@ -971,6 +954,9 @@ const char * const vmstat_text[] = {
"nr_isolated_anon",
"nr_isolated_file",
"nr_pages_scanned",
+ "workingset_refault",
+ "workingset_activate",
+ "workingset_nodereclaim",
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
diff --git a/mm/workingset.c b/mm/workingset.c
index 9a1016f5d500..56334e7d6924 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -16,7 +16,7 @@
/*
* Double CLOCK lists
*
- * Per zone, two clock lists are maintained for file pages: the
+ * Per node, two clock lists are maintained for file pages: the
* inactive and the active list. Freshly faulted pages start out at
* the head of the inactive list and page reclaim scans pages from the
* tail. Pages that are accessed multiple times on the inactive list
@@ -141,11 +141,11 @@
*
* Implementation
*
- * For each zone's file LRU lists, a counter for inactive evictions
- * and activations is maintained (zone->inactive_age).
+ * For each node's file LRU lists, a counter for inactive evictions
+ * and activations is maintained (node->inactive_age).
*
* On eviction, a snapshot of this counter (along with some bits to
- * identify the zone) is stored in the now empty page cache radix tree
+ * identify the node) is stored in the now empty page cache radix tree
* slot of the evicted page. This is called a shadow entry.
*
* On cache misses for which there are shadow entries, an eligible
@@ -153,7 +153,7 @@
*/
#define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \
- ZONES_SHIFT + NODES_SHIFT + \
+ NODES_SHIFT + \
MEM_CGROUP_ID_SHIFT)
#define EVICTION_MASK (~0UL >> EVICTION_SHIFT)
@@ -167,33 +167,30 @@
*/
static unsigned int bucket_order __read_mostly;
-static void *pack_shadow(int memcgid, struct zone *zone, unsigned long eviction)
+static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction)
{
eviction >>= bucket_order;
eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
- eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone);
- eviction = (eviction << ZONES_SHIFT) | zone_idx(zone);
+ eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
}
-static void unpack_shadow(void *shadow, int *memcgidp, struct zone **zonep,
+static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
unsigned long *evictionp)
{
unsigned long entry = (unsigned long)shadow;
- int memcgid, nid, zid;
+ int memcgid, nid;
entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
- zid = entry & ((1UL << ZONES_SHIFT) - 1);
- entry >>= ZONES_SHIFT;
nid = entry & ((1UL << NODES_SHIFT) - 1);
entry >>= NODES_SHIFT;
memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
entry >>= MEM_CGROUP_ID_SHIFT;
*memcgidp = memcgid;
- *zonep = NODE_DATA(nid)->node_zones + zid;
+ *pgdat = NODE_DATA(nid);
*evictionp = entry << bucket_order;
}
@@ -208,7 +205,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, struct zone **zonep,
void *workingset_eviction(struct address_space *mapping, struct page *page)
{
struct mem_cgroup *memcg = page_memcg(page);
- struct zone *zone = page_zone(page);
+ struct pglist_data *pgdat = page_pgdat(page);
int memcgid = mem_cgroup_id(memcg);
unsigned long eviction;
struct lruvec *lruvec;
@@ -218,9 +215,9 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)
VM_BUG_ON_PAGE(page_count(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
- lruvec = mem_cgroup_lruvec(zone->zone_pgdat, memcg);
+ lruvec = mem_cgroup_lruvec(pgdat, memcg);
eviction = atomic_long_inc_return(&lruvec->inactive_age);
- return pack_shadow(memcgid, zone, eviction);
+ return pack_shadow(memcgid, pgdat, eviction);
}
/**
@@ -228,7 +225,7 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)
* @shadow: shadow entry of the evicted page
*
* Calculates and evaluates the refault distance of the previously
- * evicted page in the context of the zone it was allocated in.
+ * evicted page in the context of the node it was allocated in.
*
* Returns %true if the page should be activated, %false otherwise.
*/
@@ -240,10 +237,10 @@ bool workingset_refault(void *shadow)
unsigned long eviction;
struct lruvec *lruvec;
unsigned long refault;
- struct zone *zone;
+ struct pglist_data *pgdat;
int memcgid;
- unpack_shadow(shadow, &memcgid, &zone, &eviction);
+ unpack_shadow(shadow, &memcgid, &pgdat, &eviction);
rcu_read_lock();
/*
@@ -267,7 +264,7 @@ bool workingset_refault(void *shadow)
rcu_read_unlock();
return false;
}
- lruvec = mem_cgroup_lruvec(zone->zone_pgdat, memcg);
+ lruvec = mem_cgroup_lruvec(pgdat, memcg);
refault = atomic_long_read(&lruvec->inactive_age);
active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
rcu_read_unlock();
@@ -290,10 +287,10 @@ bool workingset_refault(void *shadow)
*/
refault_distance = (refault - eviction) & EVICTION_MASK;
- inc_zone_state(zone, WORKINGSET_REFAULT);
+ inc_node_state(pgdat, WORKINGSET_REFAULT);
if (refault_distance <= active_file) {
- inc_zone_state(zone, WORKINGSET_ACTIVATE);
+ inc_node_state(pgdat, WORKINGSET_ACTIVATE);
return true;
}
return false;
@@ -436,7 +433,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
}
}
BUG_ON(node->count);
- inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM);
+ inc_node_state(page_pgdat(virt_to_page(node)), WORKINGSET_NODERECLAIM);
if (!__radix_tree_delete_node(&mapping->page_tree, node))
BUG();
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 15/31] mm, page_alloc: consider dirtyable memory in terms of nodes
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (13 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 14/31] mm, workingset: make working set detection node-aware Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 16/31] mm: move page mapped accounting to the node Mel Gorman
` (16 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
Historically dirty pages were spread among zones but now that LRUs are
per-node it is more appropriate to consider dirty pages in a node.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
---
include/linux/mmzone.h | 12 +++----
include/linux/writeback.h | 2 +-
mm/page-writeback.c | 91 +++++++++++++++++++++++++++++++----------------
mm/page_alloc.c | 26 ++++++--------
4 files changed, 79 insertions(+), 52 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 08e0dc9cd7cd..0e18e87cb965 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -363,12 +363,6 @@ struct zone {
struct pglist_data *zone_pgdat;
struct per_cpu_pageset __percpu *pageset;
- /*
- * This is a per-zone reserve of pages that are not available
- * to userspace allocations.
- */
- unsigned long totalreserve_pages;
-
#ifndef CONFIG_SPARSEMEM
/*
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
@@ -686,6 +680,12 @@ typedef struct pglist_data {
/* Number of pages migrated during the rate limiting time interval */
unsigned long numabalancing_migrate_nr_pages;
#endif
+ /*
+ * This is a per-node reserve of pages that are not available
+ * to userspace allocations.
+ */
+ unsigned long totalreserve_pages;
+
/* Write-intensive fields used from the page allocator */
ZONE_PADDING(_pad1_)
spinlock_t lru_lock;
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 717e6149e753..fc1e16c25a29 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -320,7 +320,7 @@ void laptop_mode_timer_fn(unsigned long data);
static inline void laptop_sync_completion(void) { }
#endif
void throttle_vm_writeout(gfp_t gfp_mask);
-bool zone_dirty_ok(struct zone *zone);
+bool node_dirty_ok(struct pglist_data *pgdat);
int wb_domain_init(struct wb_domain *dom, gfp_t gfp);
#ifdef CONFIG_CGROUP_WRITEBACK
void wb_domain_exit(struct wb_domain *dom);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0ada2b2954b0..f7c0fb993fb9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -267,26 +267,35 @@ static void wb_min_max_ratio(struct bdi_writeback *wb,
*/
/**
- * zone_dirtyable_memory - number of dirtyable pages in a zone
- * @zone: the zone
+ * node_dirtyable_memory - number of dirtyable pages in a node
+ * @pgdat: the node
*
- * Returns the zone's number of pages potentially available for dirty
- * page cache. This is the base value for the per-zone dirty limits.
+ * Returns the node's number of pages potentially available for dirty
+ * page cache. This is the base value for the per-node dirty limits.
*/
-static unsigned long zone_dirtyable_memory(struct zone *zone)
+static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
{
- unsigned long nr_pages;
+ unsigned long nr_pages = 0;
+ int z;
+
+ for (z = 0; z < MAX_NR_ZONES; z++) {
+ struct zone *zone = pgdat->node_zones + z;
+
+ if (!populated_zone(zone))
+ continue;
+
+ nr_pages += zone_page_state(zone, NR_FREE_PAGES);
+ }
- nr_pages = zone_page_state(zone, NR_FREE_PAGES);
/*
* Pages reserved for the kernel should not be considered
* dirtyable, to prevent a situation where reclaim has to
* clean pages in order to balance the zones.
*/
- nr_pages -= min(nr_pages, zone->totalreserve_pages);
+ nr_pages -= min(nr_pages, pgdat->totalreserve_pages);
- nr_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE);
- nr_pages += node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE);
+ nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE);
+ nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE);
return nr_pages;
}
@@ -299,13 +308,24 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
int i;
for_each_node_state(node, N_HIGH_MEMORY) {
- for (i = 0; i < MAX_NR_ZONES; i++) {
- struct zone *z = &NODE_DATA(node)->node_zones[i];
+ for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) {
+ struct zone *z;
+ unsigned long dirtyable;
+
+ if (!is_highmem_idx(i))
+ continue;
+
+ z = &NODE_DATA(node)->node_zones[i];
+ dirtyable = zone_page_state(z, NR_FREE_PAGES) +
+ zone_page_state(z, NR_ZONE_LRU_FILE);
- if (is_highmem(z))
- x += zone_dirtyable_memory(z);
+ /* watch for underflows */
+ dirtyable -= min(dirtyable, high_wmark_pages(z));
+
+ x += dirtyable;
}
}
+
/*
* Unreclaimable memory (kernel memory or anonymous memory
* without swap) can bring down the dirtyable pages below
@@ -445,23 +465,23 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
}
/**
- * zone_dirty_limit - maximum number of dirty pages allowed in a zone
- * @zone: the zone
+ * node_dirty_limit - maximum number of dirty pages allowed in a node
+ * @pgdat: the node
*
- * Returns the maximum number of dirty pages allowed in a zone, based
- * on the zone's dirtyable memory.
+ * Returns the maximum number of dirty pages allowed in a node, based
+ * on the node's dirtyable memory.
*/
-static unsigned long zone_dirty_limit(struct zone *zone)
+static unsigned long node_dirty_limit(struct pglist_data *pgdat)
{
- unsigned long zone_memory = zone_dirtyable_memory(zone);
+ unsigned long node_memory = node_dirtyable_memory(pgdat);
struct task_struct *tsk = current;
unsigned long dirty;
if (vm_dirty_bytes)
dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
- zone_memory / global_dirtyable_memory();
+ node_memory / global_dirtyable_memory();
else
- dirty = vm_dirty_ratio * zone_memory / 100;
+ dirty = vm_dirty_ratio * node_memory / 100;
if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
dirty += dirty / 4;
@@ -470,19 +490,30 @@ static unsigned long zone_dirty_limit(struct zone *zone)
}
/**
- * zone_dirty_ok - tells whether a zone is within its dirty limits
- * @zone: the zone to check
+ * node_dirty_ok - tells whether a node is within its dirty limits
+ * @pgdat: the node to check
*
- * Returns %true when the dirty pages in @zone are within the zone's
+ * Returns %true when the dirty pages in @pgdat are within the node's
* dirty limit, %false if the limit is exceeded.
*/
-bool zone_dirty_ok(struct zone *zone)
+bool node_dirty_ok(struct pglist_data *pgdat)
{
- unsigned long limit = zone_dirty_limit(zone);
+ int z;
+ unsigned long limit = node_dirty_limit(pgdat);
+ unsigned long nr_pages = 0;
+
+ for (z = 0; z < MAX_NR_ZONES; z++) {
+ struct zone *zone = pgdat->node_zones + z;
+
+ if (!populated_zone(zone))
+ continue;
+
+ nr_pages += zone_page_state(zone, NR_FILE_DIRTY);
+ nr_pages += zone_page_state(zone, NR_UNSTABLE_NFS);
+ nr_pages += zone_page_state(zone, NR_WRITEBACK);
+ }
- return zone_page_state(zone, NR_FILE_DIRTY) +
- zone_page_state(zone, NR_UNSTABLE_NFS) +
- zone_page_state(zone, NR_WRITEBACK) <= limit;
+ return nr_pages <= limit;
}
int dirty_background_ratio_handler(struct ctl_table *table, int write,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b76ea2527c09..d87a5e930bef 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2955,31 +2955,24 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
}
/*
* When allocating a page cache page for writing, we
- * want to get it from a zone that is within its dirty
- * limit, such that no single zone holds more than its
+ * want to get it from a node that is within its dirty
+ * limit, such that no single node holds more than its
* proportional share of globally allowed dirty pages.
- * The dirty limits take into account the zone's
+ * The dirty limits take into account the node's
* lowmem reserves and high watermark so that kswapd
* should be able to balance it without having to
* write pages from its LRU list.
*
- * This may look like it could increase pressure on
- * lower zones by failing allocations in higher zones
- * before they are full. But the pages that do spill
- * over are limited as the lower zones are protected
- * by this very same mechanism. It should not become
- * a practical burden to them.
- *
* XXX: For now, allow allocations to potentially
- * exceed the per-zone dirty limit in the slowpath
+ * exceed the per-node dirty limit in the slowpath
* (spread_dirty_pages unset) before going into reclaim,
* which is important when on a NUMA setup the allowed
- * zones are together not big enough to reach the
+ * nodes are together not big enough to reach the
* global limit. The proper fix for these situations
- * will require awareness of zones in the
+ * will require awareness of nodes in the
* dirty-throttling and the flusher threads.
*/
- if (ac->spread_dirty_pages && !zone_dirty_ok(zone))
+ if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat))
continue;
mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
@@ -6749,6 +6742,9 @@ static void calculate_totalreserve_pages(void)
enum zone_type i, j;
for_each_online_pgdat(pgdat) {
+
+ pgdat->totalreserve_pages = 0;
+
for (i = 0; i < MAX_NR_ZONES; i++) {
struct zone *zone = pgdat->node_zones + i;
long max = 0;
@@ -6765,7 +6761,7 @@ static void calculate_totalreserve_pages(void)
if (max > zone->managed_pages)
max = zone->managed_pages;
- zone->totalreserve_pages = max;
+ pgdat->totalreserve_pages += max;
reserve_pages += max;
}
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 16/31] mm: move page mapped accounting to the node
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (14 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 15/31] mm, page_alloc: consider dirtyable memory in terms of nodes Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 17/31] mm: rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
` (15 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
Reclaim makes decisions based on the number of pages that are mapped but
it's mixing node and zone information. Account NR_FILE_MAPPED and
NR_ANON_PAGES pages on the node.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
---
arch/tile/mm/pgtable.c | 2 +-
drivers/base/node.c | 4 ++--
fs/proc/meminfo.c | 4 ++--
include/linux/mmzone.h | 6 +++---
mm/page_alloc.c | 6 +++---
mm/rmap.c | 14 +++++++-------
mm/vmscan.c | 2 +-
mm/vmstat.c | 4 ++--
8 files changed, 21 insertions(+), 21 deletions(-)
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index 9e389213580d..c606b0ef2f7e 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -55,7 +55,7 @@ void show_mem(unsigned int filter)
global_page_state(NR_FREE_PAGES),
(global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE)),
- global_page_state(NR_FILE_MAPPED),
+ global_node_page_state(NR_FILE_MAPPED),
global_page_state(NR_PAGETABLE),
global_page_state(NR_BOUNCE),
global_page_state(NR_FILE_PAGES),
diff --git a/drivers/base/node.c b/drivers/base/node.c
index b7f01a4a642d..acca09536ad9 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -121,8 +121,8 @@ static ssize_t node_read_meminfo(struct device *dev,
nid, K(sum_zone_node_page_state(nid, NR_FILE_DIRTY)),
nid, K(sum_zone_node_page_state(nid, NR_WRITEBACK)),
nid, K(sum_zone_node_page_state(nid, NR_FILE_PAGES)),
- nid, K(sum_zone_node_page_state(nid, NR_FILE_MAPPED)),
- nid, K(sum_zone_node_page_state(nid, NR_ANON_PAGES)),
+ nid, K(node_page_state(pgdat, NR_FILE_MAPPED)),
+ nid, K(node_page_state(pgdat, NR_ANON_PAGES)),
nid, K(i.sharedram),
nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK) *
THREAD_SIZE / 1024,
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index cf301a9ef512..b8d52aa2f19a 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -140,8 +140,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
K(i.freeswap),
K(global_page_state(NR_FILE_DIRTY)),
K(global_page_state(NR_WRITEBACK)),
- K(global_page_state(NR_ANON_PAGES)),
- K(global_page_state(NR_FILE_MAPPED)),
+ K(global_node_page_state(NR_ANON_PAGES)),
+ K(global_node_page_state(NR_FILE_MAPPED)),
K(i.sharedram),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE)),
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 0e18e87cb965..3f87306b3a37 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -115,9 +115,6 @@ enum zone_stat_item {
NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
NR_ZONE_LRU_FILE,
NR_MLOCK, /* mlock()ed pages found and moved off LRU */
- NR_ANON_PAGES, /* Mapped anonymous pages */
- NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
- only modified from process context */
NR_FILE_PAGES,
NR_FILE_DIRTY,
NR_WRITEBACK,
@@ -164,6 +161,9 @@ enum node_stat_item {
WORKINGSET_REFAULT,
WORKINGSET_ACTIVATE,
WORKINGSET_NODERECLAIM,
+ NR_ANON_PAGES, /* Mapped anonymous pages */
+ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
+ only modified from process context */
NR_VM_NODE_STAT_ITEMS
};
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d87a5e930bef..77977188543d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4355,7 +4355,7 @@ void show_free_areas(unsigned int filter)
global_page_state(NR_UNSTABLE_NFS),
global_page_state(NR_SLAB_RECLAIMABLE),
global_page_state(NR_SLAB_UNRECLAIMABLE),
- global_page_state(NR_FILE_MAPPED),
+ global_node_page_state(NR_FILE_MAPPED),
global_page_state(NR_SHMEM),
global_page_state(NR_PAGETABLE),
global_page_state(NR_BOUNCE),
@@ -4377,6 +4377,7 @@ void show_free_areas(unsigned int filter)
" unevictable:%lukB"
" isolated(anon):%lukB"
" isolated(file):%lukB"
+ " mapped:%lukB"
" all_unreclaimable? %s"
"\n",
pgdat->node_id,
@@ -4387,6 +4388,7 @@ void show_free_areas(unsigned int filter)
K(node_page_state(pgdat, NR_UNEVICTABLE)),
K(node_page_state(pgdat, NR_ISOLATED_ANON)),
K(node_page_state(pgdat, NR_ISOLATED_FILE)),
+ K(node_page_state(pgdat, NR_FILE_MAPPED)),
!pgdat_reclaimable(pgdat) ? "yes" : "no");
}
@@ -4411,7 +4413,6 @@ void show_free_areas(unsigned int filter)
" mlocked:%lukB"
" dirty:%lukB"
" writeback:%lukB"
- " mapped:%lukB"
" shmem:%lukB"
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
" shmem_thp: %lukB"
@@ -4440,7 +4441,6 @@ void show_free_areas(unsigned int filter)
K(zone_page_state(zone, NR_MLOCK)),
K(zone_page_state(zone, NR_FILE_DIRTY)),
K(zone_page_state(zone, NR_WRITEBACK)),
- K(zone_page_state(zone, NR_FILE_MAPPED)),
K(zone_page_state(zone, NR_SHMEM)),
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
K(zone_page_state(zone, NR_SHMEM_THPS) * HPAGE_PMD_NR),
diff --git a/mm/rmap.c b/mm/rmap.c
index 573253efb645..17876517f5fa 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1217,7 +1217,7 @@ void do_page_add_anon_rmap(struct page *page,
*/
if (compound)
__inc_zone_page_state(page, NR_ANON_THPS);
- __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr);
+ __mod_node_page_state(page_pgdat(page), NR_ANON_PAGES, nr);
}
if (unlikely(PageKsm(page)))
return;
@@ -1261,7 +1261,7 @@ void page_add_new_anon_rmap(struct page *page,
/* increment count (starts at -1) */
atomic_set(&page->_mapcount, 0);
}
- __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr);
+ __mod_node_page_state(page_pgdat(page), NR_ANON_PAGES, nr);
__page_set_anon_rmap(page, vma, address, 1);
}
@@ -1296,7 +1296,7 @@ void page_add_file_rmap(struct page *page, bool compound)
if (!atomic_inc_and_test(&page->_mapcount))
goto out;
}
- __mod_zone_page_state(page_zone(page), NR_FILE_MAPPED, nr);
+ __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, nr);
mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
out:
unlock_page_memcg(page);
@@ -1332,11 +1332,11 @@ static void page_remove_file_rmap(struct page *page, bool compound)
}
/*
- * We use the irq-unsafe __{inc|mod}_zone_page_stat because
+ * We use the irq-unsafe __{inc|mod}_zone_page_state because
* these counters are not modified in interrupt context, and
* pte lock(a spinlock) is held, which implies preemption disabled.
*/
- __mod_zone_page_state(page_zone(page), NR_FILE_MAPPED, -nr);
+ __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, -nr);
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
if (unlikely(PageMlocked(page)))
@@ -1378,7 +1378,7 @@ static void page_remove_anon_compound_rmap(struct page *page)
clear_page_mlock(page);
if (nr) {
- __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, -nr);
+ __mod_node_page_state(page_pgdat(page), NR_ANON_PAGES, -nr);
deferred_split_huge_page(page);
}
}
@@ -1407,7 +1407,7 @@ void page_remove_rmap(struct page *page, bool compound)
* these counters are not modified in interrupt context, and
* pte lock(a spinlock) is held, which implies preemption disabled.
*/
- __dec_zone_page_state(page, NR_ANON_PAGES);
+ __dec_node_page_state(page, NR_ANON_PAGES);
if (unlikely(PageMlocked(page)))
clear_page_mlock(page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 82b59b63b481..bc06a77d53fa 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3590,7 +3590,7 @@ int sysctl_min_slab_ratio = 5;
static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
{
- unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
+ unsigned long file_mapped = node_page_state(zone->zone_pgdat, NR_FILE_MAPPED);
unsigned long file_lru = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) +
node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 89426c250a9a..226370ee771c 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -912,8 +912,6 @@ const char * const vmstat_text[] = {
"nr_zone_anon_lru",
"nr_zone_file_lru",
"nr_mlock",
- "nr_anon_pages",
- "nr_mapped",
"nr_file_pages",
"nr_dirty",
"nr_writeback",
@@ -957,6 +955,8 @@ const char * const vmstat_text[] = {
"workingset_refault",
"workingset_activate",
"workingset_nodereclaim",
+ "nr_anon_pages",
+ "nr_mapped",
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 17/31] mm: rename NR_ANON_PAGES to NR_ANON_MAPPED
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (15 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 16/31] mm: move page mapped accounting to the node Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 18/31] mm: move most file-based accounting to the node Mel Gorman
` (14 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
NR_FILE_PAGES is the number of file pages.
NR_FILE_MAPPED is the number of mapped file pages.
NR_ANON_PAGES is the number of mapped anon pages.
This is unhelpful naming as it's easy to confuse NR_FILE_MAPPED and
NR_ANON_PAGES for mapped pages. This patch renames NR_ANON_PAGES so we
have
NR_FILE_PAGES is the number of file pages.
NR_FILE_MAPPED is the number of mapped file pages.
NR_ANON_MAPPED is the number of mapped anon pages.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
drivers/base/node.c | 2 +-
fs/proc/meminfo.c | 2 +-
include/linux/mmzone.h | 2 +-
mm/migrate.c | 2 +-
mm/rmap.c | 8 ++++----
5 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index acca09536ad9..ac69a7215bcc 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -122,7 +122,7 @@ static ssize_t node_read_meminfo(struct device *dev,
nid, K(sum_zone_node_page_state(nid, NR_WRITEBACK)),
nid, K(sum_zone_node_page_state(nid, NR_FILE_PAGES)),
nid, K(node_page_state(pgdat, NR_FILE_MAPPED)),
- nid, K(node_page_state(pgdat, NR_ANON_PAGES)),
+ nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
nid, K(i.sharedram),
nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK) *
THREAD_SIZE / 1024,
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index b8d52aa2f19a..40f108783d59 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -140,7 +140,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
K(i.freeswap),
K(global_page_state(NR_FILE_DIRTY)),
K(global_page_state(NR_WRITEBACK)),
- K(global_node_page_state(NR_ANON_PAGES)),
+ K(global_node_page_state(NR_ANON_MAPPED)),
K(global_node_page_state(NR_FILE_MAPPED)),
K(i.sharedram),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3f87306b3a37..21aaafcee7de 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -161,7 +161,7 @@ enum node_stat_item {
WORKINGSET_REFAULT,
WORKINGSET_ACTIVATE,
WORKINGSET_NODERECLAIM,
- NR_ANON_PAGES, /* Mapped anonymous pages */
+ NR_ANON_MAPPED, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
only modified from process context */
NR_VM_NODE_STAT_ITEMS
diff --git a/mm/migrate.c b/mm/migrate.c
index 3033dae33a0a..fba770c54d84 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -501,7 +501,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
* new page and drop references to the old page.
*
* Note that anonymous pages are accounted for
- * via NR_FILE_PAGES and NR_ANON_PAGES if they
+ * via NR_FILE_PAGES and NR_ANON_MAPPED if they
* are mapped to swap space.
*/
if (newzone != oldzone) {
diff --git a/mm/rmap.c b/mm/rmap.c
index 17876517f5fa..a66f80bc8703 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1217,7 +1217,7 @@ void do_page_add_anon_rmap(struct page *page,
*/
if (compound)
__inc_zone_page_state(page, NR_ANON_THPS);
- __mod_node_page_state(page_pgdat(page), NR_ANON_PAGES, nr);
+ __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr);
}
if (unlikely(PageKsm(page)))
return;
@@ -1261,7 +1261,7 @@ void page_add_new_anon_rmap(struct page *page,
/* increment count (starts at -1) */
atomic_set(&page->_mapcount, 0);
}
- __mod_node_page_state(page_pgdat(page), NR_ANON_PAGES, nr);
+ __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr);
__page_set_anon_rmap(page, vma, address, 1);
}
@@ -1378,7 +1378,7 @@ static void page_remove_anon_compound_rmap(struct page *page)
clear_page_mlock(page);
if (nr) {
- __mod_node_page_state(page_pgdat(page), NR_ANON_PAGES, -nr);
+ __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, -nr);
deferred_split_huge_page(page);
}
}
@@ -1407,7 +1407,7 @@ void page_remove_rmap(struct page *page, bool compound)
* these counters are not modified in interrupt context, and
* pte lock(a spinlock) is held, which implies preemption disabled.
*/
- __dec_node_page_state(page, NR_ANON_PAGES);
+ __dec_node_page_state(page, NR_ANON_MAPPED);
if (unlikely(PageMlocked(page)))
clear_page_mlock(page);
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 18/31] mm: move most file-based accounting to the node
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (16 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 17/31] mm: rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 19/31] mm: move vmscan writes and file write " Mel Gorman
` (13 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
There are now a number of accounting oddities such as mapped file pages
being accounted for on the node while the total number of file pages are
accounted on the zone. This can be coped with to some extent but it's
confusing so this patch moves the relevant file-based accounted. Due to
throttling logic in the page allocator for reliable OOM detection, it is
still necessary to track dirty and writeback pages on a per-zone basis.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
---
arch/s390/appldata/appldata_mem.c | 2 +-
arch/tile/mm/pgtable.c | 8 +--
drivers/base/node.c | 16 +++---
drivers/staging/android/lowmemorykiller.c | 4 +-
drivers/staging/lustre/lustre/osc/osc_cache.c | 6 ++-
fs/fs-writeback.c | 4 +-
fs/fuse/file.c | 8 +--
fs/nfs/internal.h | 2 +-
fs/nfs/write.c | 2 +-
fs/proc/meminfo.c | 16 +++---
include/linux/mmzone.h | 19 +++----
include/trace/events/writeback.h | 6 +--
mm/filemap.c | 12 ++---
mm/huge_memory.c | 4 +-
mm/khugepaged.c | 6 +--
mm/migrate.c | 14 ++---
mm/page-writeback.c | 47 ++++++++---------
mm/page_alloc.c | 74 ++++++++++++---------------
mm/rmap.c | 10 ++--
mm/shmem.c | 14 ++---
mm/swap_state.c | 4 +-
mm/util.c | 4 +-
mm/vmscan.c | 16 +++---
mm/vmstat.c | 19 +++----
24 files changed, 155 insertions(+), 162 deletions(-)
diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c
index edcf2a706942..598df5708501 100644
--- a/arch/s390/appldata/appldata_mem.c
+++ b/arch/s390/appldata/appldata_mem.c
@@ -102,7 +102,7 @@ static void appldata_get_mem_data(void *data)
mem_data->totalhigh = P2K(val.totalhigh);
mem_data->freehigh = P2K(val.freehigh);
mem_data->bufferram = P2K(val.bufferram);
- mem_data->cached = P2K(global_page_state(NR_FILE_PAGES)
+ mem_data->cached = P2K(global_node_page_state(NR_FILE_PAGES)
- val.bufferram);
si_swapinfo(&val);
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index c606b0ef2f7e..7cc6ee7f1a58 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -49,16 +49,16 @@ void show_mem(unsigned int filter)
global_node_page_state(NR_ACTIVE_FILE)),
(global_node_page_state(NR_INACTIVE_ANON) +
global_node_page_state(NR_INACTIVE_FILE)),
- global_page_state(NR_FILE_DIRTY),
- global_page_state(NR_WRITEBACK),
- global_page_state(NR_UNSTABLE_NFS),
+ global_node_page_state(NR_FILE_DIRTY),
+ global_node_page_state(NR_WRITEBACK),
+ global_node_page_state(NR_UNSTABLE_NFS),
global_page_state(NR_FREE_PAGES),
(global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE)),
global_node_page_state(NR_FILE_MAPPED),
global_page_state(NR_PAGETABLE),
global_page_state(NR_BOUNCE),
- global_page_state(NR_FILE_PAGES),
+ global_node_page_state(NR_FILE_PAGES),
get_nr_swap_pages());
for_each_zone(zone) {
diff --git a/drivers/base/node.c b/drivers/base/node.c
index ac69a7215bcc..89e4f96e0834 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -118,28 +118,28 @@ static ssize_t node_read_meminfo(struct device *dev,
"Node %d ShmemPmdMapped: %8lu kB\n"
#endif
,
- nid, K(sum_zone_node_page_state(nid, NR_FILE_DIRTY)),
- nid, K(sum_zone_node_page_state(nid, NR_WRITEBACK)),
- nid, K(sum_zone_node_page_state(nid, NR_FILE_PAGES)),
+ nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
+ nid, K(node_page_state(pgdat, NR_WRITEBACK)),
+ nid, K(node_page_state(pgdat, NR_FILE_PAGES)),
nid, K(node_page_state(pgdat, NR_FILE_MAPPED)),
nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
nid, K(i.sharedram),
nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK) *
THREAD_SIZE / 1024,
nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)),
- nid, K(sum_zone_node_page_state(nid, NR_UNSTABLE_NFS)),
+ nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
- nid, K(sum_zone_node_page_state(nid, NR_WRITEBACK_TEMP)),
+ nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE) +
sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE)),
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
- nid, K(sum_zone_node_page_state(nid, NR_ANON_THPS) *
+ nid, K(node_page_state(pgdat, NR_ANON_THPS) *
HPAGE_PMD_NR),
- nid, K(sum_zone_node_page_state(nid, NR_SHMEM_THPS) *
+ nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
HPAGE_PMD_NR),
- nid, K(sum_zone_node_page_state(nid, NR_SHMEM_PMDMAPPED) *
+ nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
HPAGE_PMD_NR));
#else
nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index 93dbcc38eb0f..45a1b4ec4ca3 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -91,8 +91,8 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
short selected_oom_score_adj;
int array_size = ARRAY_SIZE(lowmem_adj);
int other_free = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
- int other_file = global_page_state(NR_FILE_PAGES) -
- global_page_state(NR_SHMEM) -
+ int other_file = global_node_page_state(NR_FILE_PAGES) -
+ global_node_page_state(NR_SHMEM) -
total_swapcache_pages();
if (lowmem_adj_size < array_size)
diff --git a/drivers/staging/lustre/lustre/osc/osc_cache.c b/drivers/staging/lustre/lustre/osc/osc_cache.c
index d1a7d6beee60..d011135802d5 100644
--- a/drivers/staging/lustre/lustre/osc/osc_cache.c
+++ b/drivers/staging/lustre/lustre/osc/osc_cache.c
@@ -1864,7 +1864,8 @@ void osc_dec_unstable_pages(struct ptlrpc_request *req)
LASSERT(page_count >= 0);
for (i = 0; i < page_count; i++)
- dec_zone_page_state(desc->bd_iov[i].kiov_page, NR_UNSTABLE_NFS);
+ dec_node_page_state(desc->bd_iov[i].kiov_page,
+ NR_UNSTABLE_NFS);
atomic_sub(page_count, &cli->cl_cache->ccc_unstable_nr);
LASSERT(atomic_read(&cli->cl_cache->ccc_unstable_nr) >= 0);
@@ -1898,7 +1899,8 @@ void osc_inc_unstable_pages(struct ptlrpc_request *req)
LASSERT(page_count >= 0);
for (i = 0; i < page_count; i++)
- inc_zone_page_state(desc->bd_iov[i].kiov_page, NR_UNSTABLE_NFS);
+ inc_node_page_state(desc->bd_iov[i].kiov_page,
+ NR_UNSTABLE_NFS);
LASSERT(atomic_read(&cli->cl_cache->ccc_unstable_nr) >= 0);
atomic_add(page_count, &cli->cl_cache->ccc_unstable_nr);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e21d20bc8a54..a6ca1cb2831b 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1807,8 +1807,8 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
*/
static unsigned long get_nr_dirty_pages(void)
{
- return global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) +
+ return global_node_page_state(NR_FILE_DIRTY) +
+ global_node_page_state(NR_UNSTABLE_NFS) +
get_nr_dirty_inodes();
}
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 7270e89880b5..1b96fa4a966f 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1451,7 +1451,7 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
list_del(&req->writepages_entry);
for (i = 0; i < req->num_pages; i++) {
dec_wb_stat(&bdi->wb, WB_WRITEBACK);
- dec_zone_page_state(req->pages[i], NR_WRITEBACK_TEMP);
+ dec_node_page_state(req->pages[i], NR_WRITEBACK_TEMP);
wb_writeout_inc(&bdi->wb);
}
wake_up(&fi->page_waitq);
@@ -1641,7 +1641,7 @@ static int fuse_writepage_locked(struct page *page)
req->inode = inode;
inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
- inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
+ inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
spin_lock(&fc->lock);
list_add(&req->writepages_entry, &fi->writepages);
@@ -1755,7 +1755,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
spin_unlock(&fc->lock);
dec_wb_stat(&bdi->wb, WB_WRITEBACK);
- dec_zone_page_state(page, NR_WRITEBACK_TEMP);
+ dec_node_page_state(page, NR_WRITEBACK_TEMP);
wb_writeout_inc(&bdi->wb);
fuse_writepage_free(fc, new_req);
fuse_request_free(new_req);
@@ -1854,7 +1854,7 @@ static int fuse_writepages_fill(struct page *page,
req->page_descs[req->num_pages].length = PAGE_SIZE;
inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
- inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
+ inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
err = 0;
if (is_writeback && fuse_writepage_in_flight(req, page)) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 898e66cc5089..514f096b3bdb 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -655,7 +655,7 @@ void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo)
if (!cinfo->dreq) {
struct inode *inode = page_file_mapping(page)->host;
- inc_zone_page_state(page, NR_UNSTABLE_NFS);
+ inc_node_page_state(page, NR_UNSTABLE_NFS);
inc_wb_stat(&inode_to_bdi(inode)->wb, WB_RECLAIMABLE);
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 3087fb6f1983..4715549be0c3 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -887,7 +887,7 @@ nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
static void
nfs_clear_page_commit(struct page *page)
{
- dec_zone_page_state(page, NR_UNSTABLE_NFS);
+ dec_node_page_state(page, NR_UNSTABLE_NFS);
dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb,
WB_RECLAIMABLE);
}
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 40f108783d59..c1fdcc1a907a 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -40,7 +40,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
si_swapinfo(&i);
committed = percpu_counter_read_positive(&vm_committed_as);
- cached = global_page_state(NR_FILE_PAGES) -
+ cached = global_node_page_state(NR_FILE_PAGES) -
total_swapcache_pages() - i.bufferram;
if (cached < 0)
cached = 0;
@@ -138,8 +138,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
#endif
K(i.totalswap),
K(i.freeswap),
- K(global_page_state(NR_FILE_DIRTY)),
- K(global_page_state(NR_WRITEBACK)),
+ K(global_node_page_state(NR_FILE_DIRTY)),
+ K(global_node_page_state(NR_WRITEBACK)),
K(global_node_page_state(NR_ANON_MAPPED)),
K(global_node_page_state(NR_FILE_MAPPED)),
K(i.sharedram),
@@ -152,9 +152,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
#ifdef CONFIG_QUICKLIST
K(quicklist_total_size()),
#endif
- K(global_page_state(NR_UNSTABLE_NFS)),
+ K(global_node_page_state(NR_UNSTABLE_NFS)),
K(global_page_state(NR_BOUNCE)),
- K(global_page_state(NR_WRITEBACK_TEMP)),
+ K(global_node_page_state(NR_WRITEBACK_TEMP)),
K(vm_commit_limit()),
K(committed),
(unsigned long)VMALLOC_TOTAL >> 10,
@@ -164,9 +164,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- , K(global_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
- , K(global_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
- , K(global_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
+ , K(global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
+ , K(global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
+ , K(global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
#endif
#ifdef CONFIG_CMA
, K(totalcma_pages)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 21aaafcee7de..db2a4d986f44 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -114,21 +114,16 @@ enum zone_stat_item {
NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
NR_ZONE_LRU_FILE,
+ NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */
NR_MLOCK, /* mlock()ed pages found and moved off LRU */
- NR_FILE_PAGES,
- NR_FILE_DIRTY,
- NR_WRITEBACK,
NR_SLAB_RECLAIMABLE,
NR_SLAB_UNRECLAIMABLE,
NR_PAGETABLE, /* used for pagetables */
NR_KERNEL_STACK,
/* Second 128 byte cacheline */
- NR_UNSTABLE_NFS, /* NFS unstable pages */
NR_BOUNCE,
NR_VMSCAN_WRITE,
NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */
- NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */
- NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */
NR_DIRTIED, /* page dirtyings since bootup */
NR_WRITTEN, /* page writings since bootup */
#if IS_ENABLED(CONFIG_ZSMALLOC)
@@ -142,9 +137,6 @@ enum zone_stat_item {
NUMA_LOCAL, /* allocation from local node */
NUMA_OTHER, /* allocation from other node */
#endif
- NR_ANON_THPS,
- NR_SHMEM_THPS,
- NR_SHMEM_PMDMAPPED,
NR_FREE_CMA_PAGES,
NR_VM_ZONE_STAT_ITEMS };
@@ -164,6 +156,15 @@ enum node_stat_item {
NR_ANON_MAPPED, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
only modified from process context */
+ NR_FILE_PAGES,
+ NR_FILE_DIRTY,
+ NR_WRITEBACK,
+ NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */
+ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */
+ NR_SHMEM_THPS,
+ NR_SHMEM_PMDMAPPED,
+ NR_ANON_THPS,
+ NR_UNSTABLE_NFS, /* NFS unstable pages */
NR_VM_NODE_STAT_ITEMS
};
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 531f5811ff6b..ad20f2d2b1f9 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -412,9 +412,9 @@ TRACE_EVENT(global_dirty_state,
),
TP_fast_assign(
- __entry->nr_dirty = global_page_state(NR_FILE_DIRTY);
- __entry->nr_writeback = global_page_state(NR_WRITEBACK);
- __entry->nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+ __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY);
+ __entry->nr_writeback = global_node_page_state(NR_WRITEBACK);
+ __entry->nr_unstable = global_node_page_state(NR_UNSTABLE_NFS);
__entry->nr_dirtied = global_page_state(NR_DIRTIED);
__entry->nr_written = global_page_state(NR_WRITTEN);
__entry->background_thresh = background_thresh;
diff --git a/mm/filemap.c b/mm/filemap.c
index 7ec50bd6f88c..c5f5e46c6f7f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -218,11 +218,11 @@ void __delete_from_page_cache(struct page *page, void *shadow)
/* hugetlb pages do not participate in page cache accounting. */
if (!PageHuge(page))
- __mod_zone_page_state(page_zone(page), NR_FILE_PAGES, -nr);
+ __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
if (PageSwapBacked(page)) {
- __mod_zone_page_state(page_zone(page), NR_SHMEM, -nr);
+ __mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);
if (PageTransHuge(page))
- __dec_zone_page_state(page, NR_SHMEM_THPS);
+ __dec_node_page_state(page, NR_SHMEM_THPS);
} else {
VM_BUG_ON_PAGE(PageTransHuge(page) && !PageHuge(page), page);
}
@@ -568,9 +568,9 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
* hugetlb pages do not participate in page cache accounting.
*/
if (!PageHuge(new))
- __inc_zone_page_state(new, NR_FILE_PAGES);
+ __inc_node_page_state(new, NR_FILE_PAGES);
if (PageSwapBacked(new))
- __inc_zone_page_state(new, NR_SHMEM);
+ __inc_node_page_state(new, NR_SHMEM);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
mem_cgroup_migrate(old, new);
radix_tree_preload_end();
@@ -677,7 +677,7 @@ static int __add_to_page_cache_locked(struct page *page,
/* hugetlb pages do not participate in page cache accounting. */
if (!huge)
- __inc_zone_page_state(page, NR_FILE_PAGES);
+ __inc_node_page_state(page, NR_FILE_PAGES);
spin_unlock_irq(&mapping->tree_lock);
if (!huge)
mem_cgroup_commit_charge(page, memcg, false, false);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5d5b2207cfd2..8ec69736de18 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1591,7 +1591,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
/* Last compound_mapcount is gone. */
- __dec_zone_page_state(page, NR_ANON_THPS);
+ __dec_node_page_state(page, NR_ANON_THPS);
if (TestClearPageDoubleMap(page)) {
/* No need in mapcount reference anymore */
for (i = 0; i < HPAGE_PMD_NR; i++)
@@ -2073,7 +2073,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
list_del(page_deferred_list(head));
}
if (mapping)
- __dec_zone_page_state(page, NR_SHMEM_THPS);
+ __dec_node_page_state(page, NR_SHMEM_THPS);
spin_unlock(&pgdata->split_queue_lock);
__split_huge_page(page, list, flags);
ret = 0;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index d7a49f665f04..d907cdc3dc28 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1474,10 +1474,10 @@ static void collapse_shmem(struct mm_struct *mm,
}
local_irq_save(flags);
- __inc_zone_page_state(new_page, NR_SHMEM_THPS);
+ __inc_node_page_state(new_page, NR_SHMEM_THPS);
if (nr_none) {
- __mod_zone_page_state(zone, NR_FILE_PAGES, nr_none);
- __mod_zone_page_state(zone, NR_SHMEM, nr_none);
+ __mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
+ __mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
}
local_irq_restore(flags);
diff --git a/mm/migrate.c b/mm/migrate.c
index fba770c54d84..c77997dc6ed7 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -505,15 +505,17 @@ int migrate_page_move_mapping(struct address_space *mapping,
* are mapped to swap space.
*/
if (newzone != oldzone) {
- __dec_zone_state(oldzone, NR_FILE_PAGES);
- __inc_zone_state(newzone, NR_FILE_PAGES);
+ __dec_node_state(oldzone->zone_pgdat, NR_FILE_PAGES);
+ __inc_node_state(newzone->zone_pgdat, NR_FILE_PAGES);
if (PageSwapBacked(page) && !PageSwapCache(page)) {
- __dec_zone_state(oldzone, NR_SHMEM);
- __inc_zone_state(newzone, NR_SHMEM);
+ __dec_node_state(oldzone->zone_pgdat, NR_SHMEM);
+ __inc_node_state(newzone->zone_pgdat, NR_SHMEM);
}
if (dirty && mapping_cap_account_dirty(mapping)) {
- __dec_zone_state(oldzone, NR_FILE_DIRTY);
- __inc_zone_state(newzone, NR_FILE_DIRTY);
+ __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
+ __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
+ __inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
+ __dec_zone_state(newzone, NR_ZONE_WRITE_PENDING);
}
}
local_irq_enable();
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f7c0fb993fb9..f97591d9fa00 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -498,20 +498,12 @@ static unsigned long node_dirty_limit(struct pglist_data *pgdat)
*/
bool node_dirty_ok(struct pglist_data *pgdat)
{
- int z;
unsigned long limit = node_dirty_limit(pgdat);
unsigned long nr_pages = 0;
- for (z = 0; z < MAX_NR_ZONES; z++) {
- struct zone *zone = pgdat->node_zones + z;
-
- if (!populated_zone(zone))
- continue;
-
- nr_pages += zone_page_state(zone, NR_FILE_DIRTY);
- nr_pages += zone_page_state(zone, NR_UNSTABLE_NFS);
- nr_pages += zone_page_state(zone, NR_WRITEBACK);
- }
+ nr_pages += node_page_state(pgdat, NR_FILE_DIRTY);
+ nr_pages += node_page_state(pgdat, NR_UNSTABLE_NFS);
+ nr_pages += node_page_state(pgdat, NR_WRITEBACK);
return nr_pages <= limit;
}
@@ -1601,10 +1593,10 @@ static void balance_dirty_pages(struct address_space *mapping,
* written to the server's write cache, but has not yet
* been flushed to permanent storage.
*/
- nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
+ nr_reclaimable = global_node_page_state(NR_FILE_DIRTY) +
+ global_node_page_state(NR_UNSTABLE_NFS);
gdtc->avail = global_dirtyable_memory();
- gdtc->dirty = nr_reclaimable + global_page_state(NR_WRITEBACK);
+ gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK);
domain_dirty_limits(gdtc);
@@ -1941,8 +1933,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
* as we're trying to decide whether to put more under writeback.
*/
gdtc->avail = global_dirtyable_memory();
- gdtc->dirty = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
+ gdtc->dirty = global_node_page_state(NR_FILE_DIRTY) +
+ global_node_page_state(NR_UNSTABLE_NFS);
domain_dirty_limits(gdtc);
if (gdtc->dirty > gdtc->bg_thresh)
@@ -1986,8 +1978,8 @@ void throttle_vm_writeout(gfp_t gfp_mask)
*/
dirty_thresh += dirty_thresh / 10; /* wheeee... */
- if (global_page_state(NR_UNSTABLE_NFS) +
- global_page_state(NR_WRITEBACK) <= dirty_thresh)
+ if (global_node_page_state(NR_UNSTABLE_NFS) +
+ global_node_page_state(NR_WRITEBACK) <= dirty_thresh)
break;
congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -2015,8 +2007,8 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
void laptop_mode_timer_fn(unsigned long data)
{
struct request_queue *q = (struct request_queue *)data;
- int nr_pages = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
+ int nr_pages = global_node_page_state(NR_FILE_DIRTY) +
+ global_node_page_state(NR_UNSTABLE_NFS);
struct bdi_writeback *wb;
/*
@@ -2467,7 +2459,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
wb = inode_to_wb(inode);
mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY);
- __inc_zone_page_state(page, NR_FILE_DIRTY);
+ __inc_node_page_state(page, NR_FILE_DIRTY);
+ __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
__inc_zone_page_state(page, NR_DIRTIED);
__inc_wb_stat(wb, WB_RECLAIMABLE);
__inc_wb_stat(wb, WB_DIRTIED);
@@ -2488,7 +2481,8 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
{
if (mapping_cap_account_dirty(mapping)) {
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
- dec_zone_page_state(page, NR_FILE_DIRTY);
+ dec_node_page_state(page, NR_FILE_DIRTY);
+ dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
dec_wb_stat(wb, WB_RECLAIMABLE);
task_io_account_cancelled_write(PAGE_SIZE);
}
@@ -2744,7 +2738,8 @@ int clear_page_dirty_for_io(struct page *page)
wb = unlocked_inode_to_wb_begin(inode, &locked);
if (TestClearPageDirty(page)) {
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
- dec_zone_page_state(page, NR_FILE_DIRTY);
+ dec_node_page_state(page, NR_FILE_DIRTY);
+ dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
dec_wb_stat(wb, WB_RECLAIMABLE);
ret = 1;
}
@@ -2790,7 +2785,8 @@ int test_clear_page_writeback(struct page *page)
}
if (ret) {
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
- dec_zone_page_state(page, NR_WRITEBACK);
+ dec_node_page_state(page, NR_WRITEBACK);
+ dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
inc_zone_page_state(page, NR_WRITTEN);
}
unlock_page_memcg(page);
@@ -2844,7 +2840,8 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
}
if (!ret) {
mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
- inc_zone_page_state(page, NR_WRITEBACK);
+ inc_node_page_state(page, NR_WRITEBACK);
+ inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
}
unlock_page_memcg(page);
return ret;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 77977188543d..441f482bf9a2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3535,14 +3535,12 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
* prevent from pre mature OOM
*/
if (!did_some_progress) {
- unsigned long writeback;
- unsigned long dirty;
+ unsigned long write_pending;
- writeback = zone_page_state_snapshot(zone,
- NR_WRITEBACK);
- dirty = zone_page_state_snapshot(zone, NR_FILE_DIRTY);
+ write_pending = zone_page_state_snapshot(zone,
+ NR_ZONE_WRITE_PENDING);
- if (2*(writeback + dirty) > reclaimable) {
+ if (2 * write_pending > reclaimable) {
congestion_wait(BLK_RW_ASYNC, HZ/10);
return true;
}
@@ -4218,7 +4216,7 @@ EXPORT_SYMBOL_GPL(si_mem_available);
void si_meminfo(struct sysinfo *val)
{
val->totalram = totalram_pages;
- val->sharedram = global_page_state(NR_SHMEM);
+ val->sharedram = global_node_page_state(NR_SHMEM);
val->freeram = global_page_state(NR_FREE_PAGES);
val->bufferram = nr_blockdev_pages();
val->totalhigh = totalhigh_pages;
@@ -4240,7 +4238,7 @@ void si_meminfo_node(struct sysinfo *val, int nid)
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
managed_pages += pgdat->node_zones[zone_type].managed_pages;
val->totalram = managed_pages;
- val->sharedram = sum_zone_node_page_state(nid, NR_SHMEM);
+ val->sharedram = node_page_state(pgdat, NR_SHMEM);
val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES);
#ifdef CONFIG_HIGHMEM
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
@@ -4339,9 +4337,6 @@ void show_free_areas(unsigned int filter)
" unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n"
" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- " anon_thp: %lu shmem_thp: %lu shmem_pmdmapped: %lu\n"
-#endif
" free:%lu free_pcp:%lu free_cma:%lu\n",
global_node_page_state(NR_ACTIVE_ANON),
global_node_page_state(NR_INACTIVE_ANON),
@@ -4350,20 +4345,15 @@ void show_free_areas(unsigned int filter)
global_node_page_state(NR_INACTIVE_FILE),
global_node_page_state(NR_ISOLATED_FILE),
global_node_page_state(NR_UNEVICTABLE),
- global_page_state(NR_FILE_DIRTY),
- global_page_state(NR_WRITEBACK),
- global_page_state(NR_UNSTABLE_NFS),
+ global_node_page_state(NR_FILE_DIRTY),
+ global_node_page_state(NR_WRITEBACK),
+ global_node_page_state(NR_UNSTABLE_NFS),
global_page_state(NR_SLAB_RECLAIMABLE),
global_page_state(NR_SLAB_UNRECLAIMABLE),
global_node_page_state(NR_FILE_MAPPED),
- global_page_state(NR_SHMEM),
+ global_node_page_state(NR_SHMEM),
global_page_state(NR_PAGETABLE),
global_page_state(NR_BOUNCE),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- global_page_state(NR_ANON_THPS) * HPAGE_PMD_NR,
- global_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR,
- global_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR,
-#endif
global_page_state(NR_FREE_PAGES),
free_pcp,
global_page_state(NR_FREE_CMA_PAGES));
@@ -4378,6 +4368,16 @@ void show_free_areas(unsigned int filter)
" isolated(anon):%lukB"
" isolated(file):%lukB"
" mapped:%lukB"
+ " dirty:%lukB"
+ " writeback:%lukB"
+ " shmem:%lukB"
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ " shmem_thp: %lukB"
+ " shmem_pmdmapped: %lukB"
+ " anon_thp: %lukB"
+#endif
+ " writeback_tmp:%lukB"
+ " unstable:%lukB"
" all_unreclaimable? %s"
"\n",
pgdat->node_id,
@@ -4389,6 +4389,17 @@ void show_free_areas(unsigned int filter)
K(node_page_state(pgdat, NR_ISOLATED_ANON)),
K(node_page_state(pgdat, NR_ISOLATED_FILE)),
K(node_page_state(pgdat, NR_FILE_MAPPED)),
+ K(node_page_state(pgdat, NR_FILE_DIRTY)),
+ K(node_page_state(pgdat, NR_WRITEBACK)),
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
+ K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
+ * HPAGE_PMD_NR),
+ K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
+#endif
+ K(node_page_state(pgdat, NR_SHMEM)),
+ K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
+ K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
!pgdat_reclaimable(pgdat) ? "yes" : "no");
}
@@ -4411,24 +4422,14 @@ void show_free_areas(unsigned int filter)
" present:%lukB"
" managed:%lukB"
" mlocked:%lukB"
- " dirty:%lukB"
- " writeback:%lukB"
- " shmem:%lukB"
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- " shmem_thp: %lukB"
- " shmem_pmdmapped: %lukB"
- " anon_thp: %lukB"
-#endif
" slab_reclaimable:%lukB"
" slab_unreclaimable:%lukB"
" kernel_stack:%lukB"
" pagetables:%lukB"
- " unstable:%lukB"
" bounce:%lukB"
" free_pcp:%lukB"
" local_pcp:%ukB"
" free_cma:%lukB"
- " writeback_tmp:%lukB"
" node_pages_scanned:%lu"
"\n",
zone->name,
@@ -4439,26 +4440,15 @@ void show_free_areas(unsigned int filter)
K(zone->present_pages),
K(zone->managed_pages),
K(zone_page_state(zone, NR_MLOCK)),
- K(zone_page_state(zone, NR_FILE_DIRTY)),
- K(zone_page_state(zone, NR_WRITEBACK)),
- K(zone_page_state(zone, NR_SHMEM)),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- K(zone_page_state(zone, NR_SHMEM_THPS) * HPAGE_PMD_NR),
- K(zone_page_state(zone, NR_SHMEM_PMDMAPPED)
- * HPAGE_PMD_NR),
- K(zone_page_state(zone, NR_ANON_THPS) * HPAGE_PMD_NR),
-#endif
K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
zone_page_state(zone, NR_KERNEL_STACK) *
THREAD_SIZE / 1024,
K(zone_page_state(zone, NR_PAGETABLE)),
- K(zone_page_state(zone, NR_UNSTABLE_NFS)),
K(zone_page_state(zone, NR_BOUNCE)),
K(free_pcp),
K(this_cpu_read(zone->pageset->pcp.count)),
K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
- K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
K(node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED)));
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
@@ -4501,7 +4491,7 @@ void show_free_areas(unsigned int filter)
hugetlb_show_meminfo();
- printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES));
+ printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES));
show_swap_cache_info();
}
diff --git a/mm/rmap.c b/mm/rmap.c
index a66f80bc8703..5b6dc9e33f7b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1216,7 +1216,7 @@ void do_page_add_anon_rmap(struct page *page,
* disabled.
*/
if (compound)
- __inc_zone_page_state(page, NR_ANON_THPS);
+ __inc_node_page_state(page, NR_ANON_THPS);
__mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr);
}
if (unlikely(PageKsm(page)))
@@ -1254,7 +1254,7 @@ void page_add_new_anon_rmap(struct page *page,
VM_BUG_ON_PAGE(!PageTransHuge(page), page);
/* increment count (starts at -1) */
atomic_set(compound_mapcount_ptr(page), 0);
- __inc_zone_page_state(page, NR_ANON_THPS);
+ __inc_node_page_state(page, NR_ANON_THPS);
} else {
/* Anon THP always mapped first with PMD */
VM_BUG_ON_PAGE(PageTransCompound(page), page);
@@ -1285,7 +1285,7 @@ void page_add_file_rmap(struct page *page, bool compound)
if (!atomic_inc_and_test(compound_mapcount_ptr(page)))
goto out;
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
- __inc_zone_page_state(page, NR_SHMEM_PMDMAPPED);
+ __inc_node_page_state(page, NR_SHMEM_PMDMAPPED);
} else {
if (PageTransCompound(page)) {
VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -1325,7 +1325,7 @@ static void page_remove_file_rmap(struct page *page, bool compound)
if (!atomic_add_negative(-1, compound_mapcount_ptr(page)))
goto out;
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
- __dec_zone_page_state(page, NR_SHMEM_PMDMAPPED);
+ __dec_node_page_state(page, NR_SHMEM_PMDMAPPED);
} else {
if (!atomic_add_negative(-1, &page->_mapcount))
goto out;
@@ -1359,7 +1359,7 @@ static void page_remove_anon_compound_rmap(struct page *page)
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
return;
- __dec_zone_page_state(page, NR_ANON_THPS);
+ __dec_node_page_state(page, NR_ANON_THPS);
if (TestClearPageDoubleMap(page)) {
/*
diff --git a/mm/shmem.c b/mm/shmem.c
index bfaa007ccb58..8975df09ec26 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -575,9 +575,9 @@ static int shmem_add_to_page_cache(struct page *page,
if (!error) {
mapping->nrpages += nr;
if (PageTransHuge(page))
- __inc_zone_page_state(page, NR_SHMEM_THPS);
- __mod_zone_page_state(page_zone(page), NR_FILE_PAGES, nr);
- __mod_zone_page_state(page_zone(page), NR_SHMEM, nr);
+ __inc_node_page_state(page, NR_SHMEM_THPS);
+ __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
+ __mod_node_page_state(page_pgdat(page), NR_SHMEM, nr);
spin_unlock_irq(&mapping->tree_lock);
} else {
page->mapping = NULL;
@@ -601,8 +601,8 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap)
error = shmem_radix_tree_replace(mapping, page->index, page, radswap);
page->mapping = NULL;
mapping->nrpages--;
- __dec_zone_page_state(page, NR_FILE_PAGES);
- __dec_zone_page_state(page, NR_SHMEM);
+ __dec_node_page_state(page, NR_FILE_PAGES);
+ __dec_node_page_state(page, NR_SHMEM);
spin_unlock_irq(&mapping->tree_lock);
put_page(page);
BUG_ON(error);
@@ -1493,8 +1493,8 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
newpage);
if (!error) {
- __inc_zone_page_state(newpage, NR_FILE_PAGES);
- __dec_zone_page_state(oldpage, NR_FILE_PAGES);
+ __inc_node_page_state(newpage, NR_FILE_PAGES);
+ __dec_node_page_state(oldpage, NR_FILE_PAGES);
}
spin_unlock_irq(&swap_mapping->tree_lock);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index c99463ac02fb..c8310a37be3a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -95,7 +95,7 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry)
entry.val, page);
if (likely(!error)) {
address_space->nrpages++;
- __inc_zone_page_state(page, NR_FILE_PAGES);
+ __inc_node_page_state(page, NR_FILE_PAGES);
INC_CACHE_INFO(add_total);
}
spin_unlock_irq(&address_space->tree_lock);
@@ -147,7 +147,7 @@ void __delete_from_swap_cache(struct page *page)
set_page_private(page, 0);
ClearPageSwapCache(page);
address_space->nrpages--;
- __dec_zone_page_state(page, NR_FILE_PAGES);
+ __dec_node_page_state(page, NR_FILE_PAGES);
INC_CACHE_INFO(del_total);
}
diff --git a/mm/util.c b/mm/util.c
index 8d010ef2ce1c..662cddf914af 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -528,7 +528,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
free = global_page_state(NR_FREE_PAGES);
- free += global_page_state(NR_FILE_PAGES);
+ free += global_node_page_state(NR_FILE_PAGES);
/*
* shmem pages shouldn't be counted as free in this
@@ -536,7 +536,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
* that won't affect the overall amount of available
* memory in the system.
*/
- free -= global_page_state(NR_SHMEM);
+ free -= global_node_page_state(NR_SHMEM);
free += get_nr_swap_pages();
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bc06a77d53fa..ff1c2ad70871 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3588,11 +3588,11 @@ int sysctl_min_unmapped_ratio = 1;
*/
int sysctl_min_slab_ratio = 5;
-static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
+static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat)
{
- unsigned long file_mapped = node_page_state(zone->zone_pgdat, NR_FILE_MAPPED);
- unsigned long file_lru = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) +
- node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE);
+ unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED);
+ unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) +
+ node_page_state(pgdat, NR_ACTIVE_FILE);
/*
* It's possible for there to be more file mapped pages than
@@ -3611,17 +3611,17 @@ static unsigned long zone_pagecache_reclaimable(struct zone *zone)
/*
* If RECLAIM_UNMAP is set, then all file pages are considered
* potentially reclaimable. Otherwise, we have to worry about
- * pages like swapcache and zone_unmapped_file_pages() provides
+ * pages like swapcache and node_unmapped_file_pages() provides
* a better estimate
*/
if (zone_reclaim_mode & RECLAIM_UNMAP)
- nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
+ nr_pagecache_reclaimable = node_page_state(zone->zone_pgdat, NR_FILE_PAGES);
else
- nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);
+ nr_pagecache_reclaimable = node_unmapped_file_pages(zone->zone_pgdat);
/* If we can't clean pages, remove dirty pages from consideration */
if (!(zone_reclaim_mode & RECLAIM_WRITE))
- delta += zone_page_state(zone, NR_FILE_DIRTY);
+ delta += node_page_state(zone->zone_pgdat, NR_FILE_DIRTY);
/* Watch for any possible underflows due to delta */
if (unlikely(delta > nr_pagecache_reclaimable))
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 226370ee771c..d2e50b4b4b44 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -911,20 +911,15 @@ const char * const vmstat_text[] = {
"nr_alloc_batch",
"nr_zone_anon_lru",
"nr_zone_file_lru",
+ "nr_zone_write_pending",
"nr_mlock",
- "nr_file_pages",
- "nr_dirty",
- "nr_writeback",
"nr_slab_reclaimable",
"nr_slab_unreclaimable",
"nr_page_table_pages",
"nr_kernel_stack",
- "nr_unstable",
"nr_bounce",
"nr_vmscan_write",
"nr_vmscan_immediate_reclaim",
- "nr_writeback_temp",
- "nr_shmem",
"nr_dirtied",
"nr_written",
#if IS_ENABLED(CONFIG_ZSMALLOC)
@@ -938,9 +933,6 @@ const char * const vmstat_text[] = {
"numa_local",
"numa_other",
#endif
- "nr_anon_transparent_hugepages",
- "nr_shmem_hugepages",
- "nr_shmem_pmdmapped",
"nr_free_cma",
/* Node-based counters */
@@ -957,6 +949,15 @@ const char * const vmstat_text[] = {
"workingset_nodereclaim",
"nr_anon_pages",
"nr_mapped",
+ "nr_file_pages",
+ "nr_dirty",
+ "nr_writeback",
+ "nr_writeback_temp",
+ "nr_shmem",
+ "nr_shmem_hugepages",
+ "nr_shmem_pmdmapped",
+ "nr_anon_transparent_hugepages",
+ "nr_unstable",
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 19/31] mm: move vmscan writes and file write accounting to the node
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (17 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 18/31] mm: move most file-based accounting to the node Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 20/31] mm, vmscan: only wakeup kswapd once per node for the requested classzone Mel Gorman
` (12 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
As reclaim is now node-based, it follows that page write activity due to
page reclaim should also be accounted for on the node. For consistency,
also account page writes and page dirtying on a per-node basis.
After this patch, there are a few remaining zone counters that may appear
strange but are fine. NUMA stats are still per-zone as this is a
user-space interface that tools consume. NR_MLOCK, NR_SLAB_*,
NR_PAGETABLE, NR_KERNEL_STACK and NR_BOUNCE are all allocations that
potentially pin low memory and cannot trivially be reclaimed on demand.
This information is still useful for debugging a page allocation failure
warning.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
---
include/linux/mmzone.h | 8 ++++----
include/trace/events/writeback.h | 4 ++--
mm/page-writeback.c | 6 +++---
mm/vmscan.c | 4 ++--
mm/vmstat.c | 8 ++++----
5 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index db2a4d986f44..c1dc3267db49 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -122,10 +122,6 @@ enum zone_stat_item {
NR_KERNEL_STACK,
/* Second 128 byte cacheline */
NR_BOUNCE,
- NR_VMSCAN_WRITE,
- NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */
- NR_DIRTIED, /* page dirtyings since bootup */
- NR_WRITTEN, /* page writings since bootup */
#if IS_ENABLED(CONFIG_ZSMALLOC)
NR_ZSPAGES, /* allocated in zsmalloc */
#endif
@@ -165,6 +161,10 @@ enum node_stat_item {
NR_SHMEM_PMDMAPPED,
NR_ANON_THPS,
NR_UNSTABLE_NFS, /* NFS unstable pages */
+ NR_VMSCAN_WRITE,
+ NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */
+ NR_DIRTIED, /* page dirtyings since bootup */
+ NR_WRITTEN, /* page writings since bootup */
NR_VM_NODE_STAT_ITEMS
};
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index ad20f2d2b1f9..2ccd9ccbf9ef 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -415,8 +415,8 @@ TRACE_EVENT(global_dirty_state,
__entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY);
__entry->nr_writeback = global_node_page_state(NR_WRITEBACK);
__entry->nr_unstable = global_node_page_state(NR_UNSTABLE_NFS);
- __entry->nr_dirtied = global_page_state(NR_DIRTIED);
- __entry->nr_written = global_page_state(NR_WRITTEN);
+ __entry->nr_dirtied = global_node_page_state(NR_DIRTIED);
+ __entry->nr_written = global_node_page_state(NR_WRITTEN);
__entry->background_thresh = background_thresh;
__entry->dirty_thresh = dirty_thresh;
__entry->dirty_limit = global_wb_domain.dirty_limit;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f97591d9fa00..3c02aa603f5a 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2461,7 +2461,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY);
__inc_node_page_state(page, NR_FILE_DIRTY);
__inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- __inc_zone_page_state(page, NR_DIRTIED);
+ __inc_node_page_state(page, NR_DIRTIED);
__inc_wb_stat(wb, WB_RECLAIMABLE);
__inc_wb_stat(wb, WB_DIRTIED);
task_io_account_write(PAGE_SIZE);
@@ -2550,7 +2550,7 @@ void account_page_redirty(struct page *page)
wb = unlocked_inode_to_wb_begin(inode, &locked);
current->nr_dirtied--;
- dec_zone_page_state(page, NR_DIRTIED);
+ dec_node_page_state(page, NR_DIRTIED);
dec_wb_stat(wb, WB_DIRTIED);
unlocked_inode_to_wb_end(inode, locked);
}
@@ -2787,7 +2787,7 @@ int test_clear_page_writeback(struct page *page)
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
dec_node_page_state(page, NR_WRITEBACK);
dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- inc_zone_page_state(page, NR_WRITTEN);
+ inc_node_page_state(page, NR_WRITTEN);
}
unlock_page_memcg(page);
return ret;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ff1c2ad70871..c1c8b77d8cb4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -612,7 +612,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
ClearPageReclaim(page);
}
trace_mm_vmscan_writepage(page);
- inc_zone_page_state(page, NR_VMSCAN_WRITE);
+ inc_node_page_state(page, NR_VMSCAN_WRITE);
return PAGE_SUCCESS;
}
@@ -1117,7 +1117,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
* except we already have the page isolated
* and know it's dirty
*/
- inc_zone_page_state(page, NR_VMSCAN_IMMEDIATE);
+ inc_node_page_state(page, NR_VMSCAN_IMMEDIATE);
SetPageReclaim(page);
goto keep_locked;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index d2e50b4b4b44..e544d7e7d8f0 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -918,10 +918,6 @@ const char * const vmstat_text[] = {
"nr_page_table_pages",
"nr_kernel_stack",
"nr_bounce",
- "nr_vmscan_write",
- "nr_vmscan_immediate_reclaim",
- "nr_dirtied",
- "nr_written",
#if IS_ENABLED(CONFIG_ZSMALLOC)
"nr_zspages",
#endif
@@ -958,6 +954,10 @@ const char * const vmstat_text[] = {
"nr_shmem_pmdmapped",
"nr_anon_transparent_hugepages",
"nr_unstable",
+ "nr_vmscan_write",
+ "nr_vmscan_immediate_reclaim",
+ "nr_dirtied",
+ "nr_written",
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 20/31] mm, vmscan: only wakeup kswapd once per node for the requested classzone
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (18 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 19/31] mm: move vmscan writes and file write " Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-07 1:24 ` Joonsoo Kim
2016-07-01 20:01 ` [PATCH 21/31] mm, page_alloc: Wake kswapd based on the highest eligible zone Mel Gorman
` (11 subsequent siblings)
31 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
kswapd is woken when zones are below the low watermark but the wakeup
decision is not taking the classzone into account. Now that reclaim is
node-based, it is only required to wake kswapd once per node and only if
all zones are unbalanced for the requested classzone.
Note that one node might be checked multiple times if the zonelist is
ordered by node because there is no cheap way of tracking what nodes have
already been visited. For zone-ordering, each node should be checked only
once.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
mm/page_alloc.c | 8 ++++++--
mm/vmscan.c | 13 +++++++++++--
2 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 441f482bf9a2..2fe2fbb4f2ad 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3410,10 +3410,14 @@ static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
{
struct zoneref *z;
struct zone *zone;
+ pg_data_t *last_pgdat = NULL;
for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
- ac->high_zoneidx, ac->nodemask)
- wakeup_kswapd(zone, order, ac_classzone_idx(ac));
+ ac->high_zoneidx, ac->nodemask) {
+ if (last_pgdat != zone->zone_pgdat)
+ wakeup_kswapd(zone, order, ac_classzone_idx(ac));
+ last_pgdat = zone->zone_pgdat;
+ }
}
static inline unsigned int
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c1c8b77d8cb4..e02091be0e12 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3420,6 +3420,7 @@ static int kswapd(void *p)
void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
{
pg_data_t *pgdat;
+ int z;
if (!populated_zone(zone))
return;
@@ -3433,8 +3434,16 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
pgdat->kswapd_order = max(pgdat->kswapd_order, order);
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
- if (zone_balanced(zone, order, 0))
- return;
+
+ /* Only wake kswapd if all zones are unbalanced */
+ for (z = 0; z <= classzone_idx; z++) {
+ zone = pgdat->node_zones + z;
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone_balanced(zone, order, classzone_idx))
+ return;
+ }
trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
wake_up_interruptible(&pgdat->kswapd_wait);
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 21/31] mm, page_alloc: Wake kswapd based on the highest eligible zone
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (19 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 20/31] mm, vmscan: only wakeup kswapd once per node for the requested classzone Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 22/31] mm: convert zone_reclaim to node_reclaim Mel Gorman
` (10 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
The ac_classzone_idx is used as the basis for waking kswapd and that is based
on the preferred zoneref. If the preferred zoneref's highest zone is lower
than what is available on other nodes, it's possible that kswapd is woken
on a zone with only higher, but still eligible, zones. As classzone_idx
is strictly adhered to now, it causes a problem because eligible pages
are skipped.
For example, node 0 has only DMA32 and node 1 has only NORMAL. An allocating
context running on node 0 may wake kswapd on node 1 telling it to skip
all NORMAL pages.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
mm/page_alloc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2fe2fbb4f2ad..b10bee2e5968 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3415,7 +3415,7 @@ static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
ac->high_zoneidx, ac->nodemask) {
if (last_pgdat != zone->zone_pgdat)
- wakeup_kswapd(zone, order, ac_classzone_idx(ac));
+ wakeup_kswapd(zone, order, ac->high_zoneidx);
last_pgdat = zone->zone_pgdat;
}
}
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 22/31] mm: convert zone_reclaim to node_reclaim
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (20 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 21/31] mm, page_alloc: Wake kswapd based on the highest eligible zone Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 23/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to shrink_node Mel Gorman
` (9 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
As reclaim is now per-node based, convert zone_reclaim to be node_reclaim.
It is possible that a node will be reclaimed multiple times if it has
multiple zones but this is unavoidable without caching all nodes traversed
so far. The documentation and interface to userspace is the same from a
configuration perspective and will will be similar in behaviour unless the
node-local allocation requests were also limited to lower zones.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/mmzone.h | 18 +++++------
include/linux/swap.h | 9 +++---
include/linux/topology.h | 2 +-
kernel/sysctl.c | 4 +--
mm/internal.h | 8 ++---
mm/khugepaged.c | 4 +--
mm/page_alloc.c | 24 ++++++++++-----
mm/vmscan.c | 77 ++++++++++++++++++++++++------------------------
8 files changed, 77 insertions(+), 69 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c1dc3267db49..bb6902b73d16 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -372,14 +372,6 @@ struct zone {
unsigned long *pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
-#ifdef CONFIG_NUMA
- /*
- * zone reclaim becomes active if more unmapped pages exist.
- */
- unsigned long min_unmapped_pages;
- unsigned long min_slab_pages;
-#endif /* CONFIG_NUMA */
-
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn;
@@ -524,7 +516,6 @@ struct zone {
} ____cacheline_internodealigned_in_smp;
enum zone_flags {
- ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */
ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
};
@@ -539,6 +530,7 @@ enum pgdat_flags {
PGDAT_WRITEBACK, /* reclaim scanning has recently found
* many pages under writeback
*/
+ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */
};
static inline unsigned long zone_end_pfn(const struct zone *zone)
@@ -687,6 +679,14 @@ typedef struct pglist_data {
*/
unsigned long totalreserve_pages;
+#ifdef CONFIG_NUMA
+ /*
+ * zone reclaim becomes active if more unmapped pages exist.
+ */
+ unsigned long min_unmapped_pages;
+ unsigned long min_slab_pages;
+#endif /* CONFIG_NUMA */
+
/* Write-intensive fields used from the page allocator */
ZONE_PADDING(_pad1_)
spinlock_t lru_lock;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2a23ddc96edd..b17cc4830fa6 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -326,13 +326,14 @@ extern int remove_mapping(struct address_space *mapping, struct page *page);
extern unsigned long vm_total_pages;
#ifdef CONFIG_NUMA
-extern int zone_reclaim_mode;
+extern int node_reclaim_mode;
extern int sysctl_min_unmapped_ratio;
extern int sysctl_min_slab_ratio;
-extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
+extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
#else
-#define zone_reclaim_mode 0
-static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
+#define node_reclaim_mode 0
+static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
+ unsigned int order)
{
return 0;
}
diff --git a/include/linux/topology.h b/include/linux/topology.h
index afce69296ac0..cb0775e1ee4b 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -54,7 +54,7 @@ int arch_update_cpu_topology(void);
/*
* If the distance between nodes in a system is larger than RECLAIM_DISTANCE
* (in whatever arch specific measurement units returned by node_distance())
- * and zone_reclaim_mode is enabled then the VM will only call zone_reclaim()
+ * and node_reclaim_mode is enabled then the VM will only call node_reclaim()
* on nodes within this distance.
*/
#define RECLAIM_DISTANCE 30
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index de331c3858e5..6e47ebe5384e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1498,8 +1498,8 @@ static struct ctl_table vm_table[] = {
#ifdef CONFIG_NUMA
{
.procname = "zone_reclaim_mode",
- .data = &zone_reclaim_mode,
- .maxlen = sizeof(zone_reclaim_mode),
+ .data = &node_reclaim_mode,
+ .maxlen = sizeof(node_reclaim_mode),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = &zero,
diff --git a/mm/internal.h b/mm/internal.h
index 2f80d0343c56..1e21b2d3838d 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -433,10 +433,10 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
}
#endif /* CONFIG_SPARSEMEM */
-#define ZONE_RECLAIM_NOSCAN -2
-#define ZONE_RECLAIM_FULL -1
-#define ZONE_RECLAIM_SOME 0
-#define ZONE_RECLAIM_SUCCESS 1
+#define NODE_RECLAIM_NOSCAN -2
+#define NODE_RECLAIM_FULL -1
+#define NODE_RECLAIM_SOME 0
+#define NODE_RECLAIM_SUCCESS 1
extern int hwpoison_filter(struct page *p);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index d907cdc3dc28..bb49bd1d2d9f 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -672,10 +672,10 @@ static bool khugepaged_scan_abort(int nid)
int i;
/*
- * If zone_reclaim_mode is disabled, then no extra effort is made to
+ * If node_reclaim_mode is disabled, then no extra effort is made to
* allocate memory locally.
*/
- if (!zone_reclaim_mode)
+ if (!node_reclaim_mode)
return false;
/* If there is a count for this node already, it must be acceptable */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b10bee2e5968..eb31f114d0d8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2985,16 +2985,16 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
if (alloc_flags & ALLOC_NO_WATERMARKS)
goto try_this_zone;
- if (zone_reclaim_mode == 0 ||
+ if (node_reclaim_mode == 0 ||
!zone_allows_reclaim(ac->preferred_zoneref->zone, zone))
continue;
- ret = zone_reclaim(zone, gfp_mask, order);
+ ret = node_reclaim(zone->zone_pgdat, gfp_mask, order);
switch (ret) {
- case ZONE_RECLAIM_NOSCAN:
+ case NODE_RECLAIM_NOSCAN:
/* did not scan */
continue;
- case ZONE_RECLAIM_FULL:
+ case NODE_RECLAIM_FULL:
/* scanned but unreclaimable */
continue;
default:
@@ -5991,9 +5991,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
#ifdef CONFIG_NUMA
zone->node = nid;
- zone->min_unmapped_pages = (freesize*sysctl_min_unmapped_ratio)
+ pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio)
/ 100;
- zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100;
+ pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100;
#endif
zone->name = zone_names[j];
zone->zone_pgdat = pgdat;
@@ -6970,6 +6970,7 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
+ struct pglist_data *pgdat;
struct zone *zone;
int rc;
@@ -6977,8 +6978,11 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
if (rc)
return rc;
+ for_each_online_pgdat(pgdat)
+ pgdat->min_slab_pages = 0;
+
for_each_zone(zone)
- zone->min_unmapped_pages = (zone->managed_pages *
+ zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
sysctl_min_unmapped_ratio) / 100;
return 0;
}
@@ -6986,6 +6990,7 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
+ struct pglist_data *pgdat;
struct zone *zone;
int rc;
@@ -6993,8 +6998,11 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
if (rc)
return rc;
+ for_each_online_pgdat(pgdat)
+ pgdat->min_slab_pages = 0;
+
for_each_zone(zone)
- zone->min_slab_pages = (zone->managed_pages *
+ zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
sysctl_min_slab_ratio) / 100;
return 0;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e02091be0e12..a6b30fe1de89 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3566,12 +3566,12 @@ module_init(kswapd_init)
#ifdef CONFIG_NUMA
/*
- * Zone reclaim mode
+ * Node reclaim mode
*
- * If non-zero call zone_reclaim when the number of free pages falls below
+ * If non-zero call node_reclaim when the number of free pages falls below
* the watermarks.
*/
-int zone_reclaim_mode __read_mostly;
+int node_reclaim_mode __read_mostly;
#define RECLAIM_OFF 0
#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
@@ -3579,14 +3579,14 @@ int zone_reclaim_mode __read_mostly;
#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */
/*
- * Priority for ZONE_RECLAIM. This determines the fraction of pages
+ * Priority for NODE_RECLAIM. This determines the fraction of pages
* of a node considered for each zone_reclaim. 4 scans 1/16th of
* a zone.
*/
-#define ZONE_RECLAIM_PRIORITY 4
+#define NODE_RECLAIM_PRIORITY 4
/*
- * Percentage of pages in a zone that must be unmapped for zone_reclaim to
+ * Percentage of pages in a zone that must be unmapped for node_reclaim to
* occur.
*/
int sysctl_min_unmapped_ratio = 1;
@@ -3612,7 +3612,7 @@ static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat)
}
/* Work out how many page cache pages we can reclaim in this reclaim_mode */
-static unsigned long zone_pagecache_reclaimable(struct zone *zone)
+static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat)
{
unsigned long nr_pagecache_reclaimable;
unsigned long delta = 0;
@@ -3623,14 +3623,14 @@ static unsigned long zone_pagecache_reclaimable(struct zone *zone)
* pages like swapcache and node_unmapped_file_pages() provides
* a better estimate
*/
- if (zone_reclaim_mode & RECLAIM_UNMAP)
- nr_pagecache_reclaimable = node_page_state(zone->zone_pgdat, NR_FILE_PAGES);
+ if (node_reclaim_mode & RECLAIM_UNMAP)
+ nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES);
else
- nr_pagecache_reclaimable = node_unmapped_file_pages(zone->zone_pgdat);
+ nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat);
/* If we can't clean pages, remove dirty pages from consideration */
- if (!(zone_reclaim_mode & RECLAIM_WRITE))
- delta += node_page_state(zone->zone_pgdat, NR_FILE_DIRTY);
+ if (!(node_reclaim_mode & RECLAIM_WRITE))
+ delta += node_page_state(pgdat, NR_FILE_DIRTY);
/* Watch for any possible underflows due to delta */
if (unlikely(delta > nr_pagecache_reclaimable))
@@ -3640,23 +3640,24 @@ static unsigned long zone_pagecache_reclaimable(struct zone *zone)
}
/*
- * Try to free up some pages from this zone through reclaim.
+ * Try to free up some pages from this node through reclaim.
*/
-static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
{
/* Minimum pages needed in order to stay on node */
const unsigned long nr_pages = 1 << order;
struct task_struct *p = current;
struct reclaim_state reclaim_state;
+ int classzone_idx = gfp_zone(gfp_mask);
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
.order = order,
- .priority = ZONE_RECLAIM_PRIORITY,
- .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
- .may_unmap = !!(zone_reclaim_mode & RECLAIM_UNMAP),
+ .priority = NODE_RECLAIM_PRIORITY,
+ .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
+ .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
.may_swap = 1,
- .reclaim_idx = zone_idx(zone),
+ .reclaim_idx = classzone_idx,
};
cond_resched();
@@ -3670,13 +3671,13 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) {
+ if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
/*
* Free memory by calling shrink zone with increasing
* priorities until we have enough memory freed.
*/
do {
- shrink_node(zone->zone_pgdat, &sc, zone_idx(zone));
+ shrink_node(pgdat, &sc, classzone_idx);
} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
}
@@ -3686,49 +3687,47 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
return sc.nr_reclaimed >= nr_pages;
}
-int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
{
- int node_id;
int ret;
/*
- * Zone reclaim reclaims unmapped file backed pages and
+ * Node reclaim reclaims unmapped file backed pages and
* slab pages if we are over the defined limits.
*
* A small portion of unmapped file backed pages is needed for
* file I/O otherwise pages read by file I/O will be immediately
- * thrown out if the zone is overallocated. So we do not reclaim
- * if less than a specified percentage of the zone is used by
+ * thrown out if the node is overallocated. So we do not reclaim
+ * if less than a specified percentage of the node is used by
* unmapped file backed pages.
*/
- if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
- zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
- return ZONE_RECLAIM_FULL;
+ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
+ sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+ return NODE_RECLAIM_FULL;
- if (!pgdat_reclaimable(zone->zone_pgdat))
- return ZONE_RECLAIM_FULL;
+ if (!pgdat_reclaimable(pgdat))
+ return NODE_RECLAIM_FULL;
/*
* Do not scan if the allocation should not be delayed.
*/
if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
- return ZONE_RECLAIM_NOSCAN;
+ return NODE_RECLAIM_NOSCAN;
/*
- * Only run zone reclaim on the local zone or on zones that do not
+ * Only run node reclaim on the local node or on nodes that do not
* have associated processors. This will favor the local processor
* over remote processors and spread off node memory allocations
* as wide as possible.
*/
- node_id = zone_to_nid(zone);
- if (node_state(node_id, N_CPU) && node_id != numa_node_id())
- return ZONE_RECLAIM_NOSCAN;
+ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id())
+ return NODE_RECLAIM_NOSCAN;
- if (test_and_set_bit(ZONE_RECLAIM_LOCKED, &zone->flags))
- return ZONE_RECLAIM_NOSCAN;
+ if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags))
+ return NODE_RECLAIM_NOSCAN;
- ret = __zone_reclaim(zone, gfp_mask, order);
- clear_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
+ ret = __node_reclaim(pgdat, gfp_mask, order);
+ clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags);
if (!ret)
count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 23/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to shrink_node
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (21 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 22/31] mm: convert zone_reclaim to node_reclaim Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 24/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to compaction_ready Mel Gorman
` (8 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
shrink_node receives all information it needs about classzone_idx
from sc->reclaim_idx so remove the aliases.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
mm/vmscan.c | 20 +++++++++-----------
1 file changed, 9 insertions(+), 11 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a6b30fe1de89..6534fbe1b96f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2426,8 +2426,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
return true;
}
-static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
- enum zone_type classzone_idx)
+static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
{
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
@@ -2653,7 +2652,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
/* need some check for avoid more shrink_zone() */
}
- shrink_node(zone->zone_pgdat, sc, classzone_idx);
+ shrink_node(zone->zone_pgdat, sc);
}
/*
@@ -3077,7 +3076,6 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
* This is used to determine if the scanning priority needs to be raised.
*/
static bool kswapd_shrink_node(pg_data_t *pgdat,
- int classzone_idx,
struct scan_control *sc)
{
struct zone *zone;
@@ -3085,7 +3083,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
/* Reclaim a number of pages proportional to the number of zones */
sc->nr_to_reclaim = 0;
- for (z = 0; z <= classzone_idx; z++) {
+ for (z = 0; z <= sc->reclaim_idx; z++) {
zone = pgdat->node_zones + z;
if (!populated_zone(zone))
continue;
@@ -3097,7 +3095,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
* Historically care was taken to put equal pressure on all zones but
* now pressure is applied based on node LRU order.
*/
- shrink_node(pgdat, sc, classzone_idx);
+ shrink_node(pgdat, sc);
/*
* Fragmentation may mean that the system cannot be rebalanced for
@@ -3159,7 +3157,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
if (!populated_zone(zone))
continue;
- classzone_idx = i;
+ sc.reclaim_idx = i;
break;
}
}
@@ -3169,12 +3167,12 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
* high to low zone to avoid prematurely clearing pgdat
* congested state.
*/
- for (i = classzone_idx; i >= 0; i--) {
+ for (i = sc.reclaim_idx; i >= 0; i--) {
zone = pgdat->node_zones + i;
if (!populated_zone(zone))
continue;
- if (zone_balanced(zone, sc.order, classzone_idx))
+ if (zone_balanced(zone, sc.order, sc.reclaim_idx))
goto out;
}
@@ -3205,7 +3203,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
* enough pages are already being scanned that that high
* watermark would be met at 100% efficiency.
*/
- if (kswapd_shrink_node(pgdat, classzone_idx, &sc))
+ if (kswapd_shrink_node(pgdat, &sc))
raise_priority = false;
/*
@@ -3677,7 +3675,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
* priorities until we have enough memory freed.
*/
do {
- shrink_node(pgdat, &sc, classzone_idx);
+ shrink_node(pgdat, &sc);
} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
}
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 24/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to compaction_ready
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (22 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 23/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to shrink_node Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 25/31] mm, vmscan: add classzone information to tracepoints Mel Gorman
` (7 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
The scan_control structure has enough information available for
compaction_ready() to make a decision. The classzone_idx manipulations in
shrink_zones() are no longer necessary as the highest populated zone is
no longer used to determine if shrink_slab should be called or not.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
mm/vmscan.c | 28 ++++++++--------------------
1 file changed, 8 insertions(+), 20 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6534fbe1b96f..c4094d7771a7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2521,7 +2521,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
* Returns true if compaction should go ahead for a high-order request, or
* the high-order allocation would succeed without compaction.
*/
-static inline bool compaction_ready(struct zone *zone, int order, int classzone_idx)
+static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
{
unsigned long watermark;
bool watermark_ok;
@@ -2532,21 +2532,21 @@ static inline bool compaction_ready(struct zone *zone, int order, int classzone_
* there is a buffer of free pages available to give compaction
* a reasonable chance of completing and allocating the page
*/
- watermark = high_wmark_pages(zone) + (2UL << order);
- watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, classzone_idx);
+ watermark = high_wmark_pages(zone) + (2UL << sc->order);
+ watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx);
/*
* If compaction is deferred, reclaim up to a point where
* compaction will have a chance of success when re-enabled
*/
- if (compaction_deferred(zone, order))
+ if (compaction_deferred(zone, sc->order))
return watermark_ok;
/*
* If compaction is not ready to start and allocation is not likely
* to succeed without it, then keep reclaiming.
*/
- if (compaction_suitable(zone, order, 0, classzone_idx) == COMPACT_SKIPPED)
+ if (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx) == COMPACT_SKIPPED)
return false;
return watermark_ok;
@@ -2567,7 +2567,6 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
gfp_t orig_mask;
- enum zone_type classzone_idx;
pg_data_t *last_pgdat = NULL;
/*
@@ -2578,7 +2577,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
orig_mask = sc->gfp_mask;
if (buffer_heads_over_limit) {
sc->gfp_mask |= __GFP_HIGHMEM;
- sc->reclaim_idx = classzone_idx = gfp_zone(sc->gfp_mask);
+ sc->reclaim_idx = gfp_zone(sc->gfp_mask);
}
for_each_zone_zonelist_nodemask(zone, z, zonelist,
@@ -2587,17 +2586,6 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
continue;
/*
- * Note that reclaim_idx does not change as it is the highest
- * zone reclaimed from which for empty zones is a no-op but
- * classzone_idx is used by shrink_node to test if the slabs
- * should be shrunk on a given node.
- */
- classzone_idx = sc->reclaim_idx;
- while (!populated_zone(zone->zone_pgdat->node_zones +
- classzone_idx))
- classzone_idx--;
-
- /*
* Shrink each node in the zonelist once. If the zonelist is
* ordered by zone (not the default) then a node may be
* shrunk multiple times but in that case the user prefers
@@ -2631,8 +2619,8 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
*/
if (IS_ENABLED(CONFIG_COMPACTION) &&
sc->order > PAGE_ALLOC_COSTLY_ORDER &&
- zonelist_zone_idx(z) <= classzone_idx &&
- compaction_ready(zone, sc->order, classzone_idx)) {
+ zonelist_zone_idx(z) <= sc->reclaim_idx &&
+ compaction_ready(zone, sc)) {
sc->compaction_ready = true;
continue;
}
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 25/31] mm, vmscan: add classzone information to tracepoints
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (23 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 24/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to compaction_ready Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 26/31] mm, page_alloc: remove fair zone allocation policy Mel Gorman
` (6 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
This is convenient when tracking down why the skip count is high because
it'll show what classzone kswapd woke up at and what zones are being
isolated.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/trace/events/vmscan.h | 51 ++++++++++++++++++++++++++-----------------
mm/vmscan.c | 14 +++++++-----
2 files changed, 40 insertions(+), 25 deletions(-)
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 897f1aa1ee5f..c88fd0934e7e 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -55,21 +55,23 @@ TRACE_EVENT(mm_vmscan_kswapd_sleep,
TRACE_EVENT(mm_vmscan_kswapd_wake,
- TP_PROTO(int nid, int order),
+ TP_PROTO(int nid, int zid, int order),
- TP_ARGS(nid, order),
+ TP_ARGS(nid, zid, order),
TP_STRUCT__entry(
__field( int, nid )
+ __field( int, zid )
__field( int, order )
),
TP_fast_assign(
__entry->nid = nid;
+ __entry->zid = zid;
__entry->order = order;
),
- TP_printk("nid=%d order=%d", __entry->nid, __entry->order)
+ TP_printk("nid=%d zid=%d order=%d", __entry->nid, __entry->zid, __entry->order)
);
TRACE_EVENT(mm_vmscan_wakeup_kswapd,
@@ -98,47 +100,50 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd,
DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
- TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+ TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
- TP_ARGS(order, may_writepage, gfp_flags),
+ TP_ARGS(order, may_writepage, gfp_flags, classzone_idx),
TP_STRUCT__entry(
__field( int, order )
__field( int, may_writepage )
__field( gfp_t, gfp_flags )
+ __field( int, classzone_idx )
),
TP_fast_assign(
__entry->order = order;
__entry->may_writepage = may_writepage;
__entry->gfp_flags = gfp_flags;
+ __entry->classzone_idx = classzone_idx;
),
- TP_printk("order=%d may_writepage=%d gfp_flags=%s",
+ TP_printk("order=%d may_writepage=%d gfp_flags=%s classzone_idx=%d",
__entry->order,
__entry->may_writepage,
- show_gfp_flags(__entry->gfp_flags))
+ show_gfp_flags(__entry->gfp_flags),
+ __entry->classzone_idx)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
- TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+ TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
- TP_ARGS(order, may_writepage, gfp_flags)
+ TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
- TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+ TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
- TP_ARGS(order, may_writepage, gfp_flags)
+ TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin,
- TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+ TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
- TP_ARGS(order, may_writepage, gfp_flags)
+ TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
);
DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
@@ -266,16 +271,18 @@ TRACE_EVENT(mm_shrink_slab_end,
DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
- TP_PROTO(int order,
+ TP_PROTO(int classzone_idx,
+ int order,
unsigned long nr_requested,
unsigned long nr_scanned,
unsigned long nr_taken,
isolate_mode_t isolate_mode,
int file),
- TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
+ TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
TP_STRUCT__entry(
+ __field(int, classzone_idx)
__field(int, order)
__field(unsigned long, nr_requested)
__field(unsigned long, nr_scanned)
@@ -285,6 +292,7 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
),
TP_fast_assign(
+ __entry->classzone_idx = classzone_idx;
__entry->order = order;
__entry->nr_requested = nr_requested;
__entry->nr_scanned = nr_scanned;
@@ -293,8 +301,9 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
__entry->file = file;
),
- TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
+ TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
__entry->isolate_mode,
+ __entry->classzone_idx,
__entry->order,
__entry->nr_requested,
__entry->nr_scanned,
@@ -304,27 +313,29 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate,
- TP_PROTO(int order,
+ TP_PROTO(int classzone_idx,
+ int order,
unsigned long nr_requested,
unsigned long nr_scanned,
unsigned long nr_taken,
isolate_mode_t isolate_mode,
int file),
- TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
+ TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
);
DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate,
- TP_PROTO(int order,
+ TP_PROTO(int classzone_idx,
+ int order,
unsigned long nr_requested,
unsigned long nr_scanned,
unsigned long nr_taken,
isolate_mode_t isolate_mode,
int file),
- TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
+ TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c4094d7771a7..a687cfa91166 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1439,7 +1439,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
if (!list_empty(&pages_skipped))
list_splice(&pages_skipped, src);
*nr_scanned = scan;
- trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
+ trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
nr_taken, mode, is_file_lru(lru));
for (scan = 0; scan < MAX_NR_ZONES; scan++) {
nr_pages = nr_zone_taken[scan];
@@ -2885,7 +2885,8 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
trace_mm_vmscan_direct_reclaim_begin(order,
sc.may_writepage,
- gfp_mask);
+ gfp_mask,
+ sc.reclaim_idx);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
@@ -2916,7 +2917,8 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
sc.may_writepage,
- sc.gfp_mask);
+ sc.gfp_mask,
+ sc.reclaim_idx);
/*
* NOTE: Although we can get the priority field, using it
@@ -2964,7 +2966,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
trace_mm_vmscan_memcg_reclaim_begin(0,
sc.may_writepage,
- sc.gfp_mask);
+ sc.gfp_mask,
+ sc.reclaim_idx);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
@@ -3384,7 +3387,8 @@ static int kswapd(void *p)
* but kcompactd is woken to compact for the original
* request (alloc_order).
*/
- trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order);
+ trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx,
+ alloc_order);
reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
if (reclaim_order < alloc_order)
goto kswapd_try_sleep;
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 26/31] mm, page_alloc: remove fair zone allocation policy
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (24 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 25/31] mm, vmscan: add classzone information to tracepoints Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 27/31] mm: page_alloc: cache the last node whose dirty limit is reached Mel Gorman
` (5 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
The fair zone allocation policy interleaves allocation requests between
zones to avoid an age inversion problem whereby new pages are reclaimed to
balance a zone. Reclaim is now node-based so this should no longer be an
issue and the fair zone allocation policy is not free. This patch removes
it.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/mmzone.h | 5 ----
mm/internal.h | 1 -
mm/page_alloc.c | 75 +-------------------------------------------------
mm/vmstat.c | 4 +--
4 files changed, 2 insertions(+), 83 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bb6902b73d16..facee6b83440 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -110,7 +110,6 @@ struct zone_padding {
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
- NR_ALLOC_BATCH,
NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
NR_ZONE_LRU_FILE,
@@ -515,10 +514,6 @@ struct zone {
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;
-enum zone_flags {
- ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
-};
-
enum pgdat_flags {
PGDAT_CONGESTED, /* zone has many dirty pages backed by
* a congested BDI
diff --git a/mm/internal.h b/mm/internal.h
index 1e21b2d3838d..28932cd6a195 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -467,7 +467,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
-#define ALLOC_FAIR 0x100 /* fair zone allocation */
enum ttu_flags;
struct tlbflush_unmap_batch;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eb31f114d0d8..d4815a30965b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2630,7 +2630,6 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
else
page = list_first_entry(list, struct page, lru);
- __dec_zone_state(zone, NR_ALLOC_BATCH);
list_del(&page->lru);
pcp->count--;
@@ -2656,15 +2655,10 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
spin_unlock(&zone->lock);
if (!page)
goto failed;
- __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
__mod_zone_freepage_state(zone, -(1 << order),
get_pcppage_migratetype(page));
}
- if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
- !test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
- set_bit(ZONE_FAIR_DEPLETED, &zone->flags);
-
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
@@ -2875,40 +2869,18 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
}
#ifdef CONFIG_NUMA
-static bool zone_local(struct zone *local_zone, struct zone *zone)
-{
- return local_zone->node == zone->node;
-}
-
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
RECLAIM_DISTANCE;
}
#else /* CONFIG_NUMA */
-static bool zone_local(struct zone *local_zone, struct zone *zone)
-{
- return true;
-}
-
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return true;
}
#endif /* CONFIG_NUMA */
-static void reset_alloc_batches(struct zone *preferred_zone)
-{
- struct zone *zone = preferred_zone->zone_pgdat->node_zones;
-
- do {
- mod_zone_page_state(zone, NR_ALLOC_BATCH,
- high_wmark_pages(zone) - low_wmark_pages(zone) -
- atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
- clear_bit(ZONE_FAIR_DEPLETED, &zone->flags);
- } while (zone++ != preferred_zone);
-}
-
/*
* get_page_from_freelist goes through the zonelist trying to allocate
* a page.
@@ -2919,10 +2891,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
{
struct zoneref *z = ac->preferred_zoneref;
struct zone *zone;
- bool fair_skipped = false;
- bool apply_fair = (alloc_flags & ALLOC_FAIR);
-
-zonelist_scan:
/*
* Scan zonelist, looking for a zone with enough free.
* See also __cpuset_node_allowed() comment in kernel/cpuset.c.
@@ -2937,23 +2905,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
!__cpuset_zone_allowed(zone, gfp_mask))
continue;
/*
- * Distribute pages in proportion to the individual
- * zone size to ensure fair page aging. The zone a
- * page was allocated in should have no effect on the
- * time the page has in memory before being reclaimed.
- */
- if (apply_fair) {
- if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
- fair_skipped = true;
- continue;
- }
- if (!zone_local(ac->preferred_zoneref->zone, zone)) {
- if (fair_skipped)
- goto reset_fair;
- apply_fair = false;
- }
- }
- /*
* When allocating a page cache page for writing, we
* want to get it from a node that is within its dirty
* limit, such that no single node holds more than its
@@ -3024,23 +2975,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
}
}
- /*
- * The first pass makes sure allocations are spread fairly within the
- * local node. However, the local node might have free pages left
- * after the fairness batches are exhausted, and remote zones haven't
- * even been considered yet. Try once more without fairness, and
- * include remote zones now, before entering the slowpath and waking
- * kswapd: prefer spilling to a remote zone over swapping locally.
- */
- if (fair_skipped) {
-reset_fair:
- apply_fair = false;
- fair_skipped = false;
- reset_alloc_batches(ac->preferred_zoneref->zone);
- z = ac->preferred_zoneref;
- goto zonelist_scan;
- }
-
return NULL;
}
@@ -3789,7 +3723,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
{
struct page *page;
unsigned int cpuset_mems_cookie;
- unsigned int alloc_flags = ALLOC_WMARK_LOW|ALLOC_FAIR;
+ unsigned int alloc_flags = ALLOC_WMARK_LOW;
gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
struct alloc_context ac = {
.high_zoneidx = gfp_zone(gfp_mask),
@@ -6001,9 +5935,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
zone_seqlock_init(zone);
zone_pcp_init(zone);
- /* For bootup, initialized properly in watermark setup */
- mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
-
if (!size)
continue;
@@ -6856,10 +6787,6 @@ static void __setup_per_zone_wmarks(void)
zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp;
zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
- __mod_zone_page_state(zone, NR_ALLOC_BATCH,
- high_wmark_pages(zone) - low_wmark_pages(zone) -
- atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-
spin_unlock_irqrestore(&zone->lock, flags);
}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index e544d7e7d8f0..905ea9ae2d5a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -908,7 +908,6 @@ int fragmentation_index(struct zone *zone, unsigned int order)
const char * const vmstat_text[] = {
/* enum zone_stat_item countes */
"nr_free_pages",
- "nr_alloc_batch",
"nr_zone_anon_lru",
"nr_zone_file_lru",
"nr_zone_write_pending",
@@ -1619,10 +1618,9 @@ int vmstat_refresh(struct ctl_table *table, int write,
val = atomic_long_read(&vm_zone_stat[i]);
if (val < 0) {
switch (i) {
- case NR_ALLOC_BATCH:
case NR_PAGES_SCANNED:
/*
- * These are often seen to go negative in
+ * This is often seen to go negative in
* recent kernels, but not to go permanently
* negative. Whilst it would be nicer not to
* have exceptions, rooting them out would be
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 27/31] mm: page_alloc: cache the last node whose dirty limit is reached
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (25 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 26/31] mm, page_alloc: remove fair zone allocation policy Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 28/31] mm: vmstat: replace __count_zone_vm_events with a zone id equivalent Mel Gorman
` (4 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
If a page is about to be dirtied then the page allocator attempts to limit
the total number of dirty pages that exists in any given zone. The call
to node_dirty_ok is expensive so this patch records if the last pgdat
examined hit the dirty limits. In some cases, this reduces the number of
calls to node_dirty_ok().
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
mm/page_alloc.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d4815a30965b..69ffaadc31ed 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2891,6 +2891,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
{
struct zoneref *z = ac->preferred_zoneref;
struct zone *zone;
+ struct pglist_data *last_pgdat_dirty_limit = NULL;
+
/*
* Scan zonelist, looking for a zone with enough free.
* See also __cpuset_node_allowed() comment in kernel/cpuset.c.
@@ -2923,8 +2925,15 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
* will require awareness of nodes in the
* dirty-throttling and the flusher threads.
*/
- if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat))
- continue;
+ if (ac->spread_dirty_pages) {
+ if (last_pgdat_dirty_limit == zone->zone_pgdat)
+ continue;
+
+ if (!node_dirty_ok(zone->zone_pgdat)) {
+ last_pgdat_dirty_limit = zone->zone_pgdat;
+ continue;
+ }
+ }
mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
if (!zone_watermark_fast(zone, order, mark,
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 28/31] mm: vmstat: replace __count_zone_vm_events with a zone id equivalent
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (26 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 27/31] mm: page_alloc: cache the last node whose dirty limit is reached Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 29/31] mm: vmstat: account per-zone stalls and pages skipped during reclaim Mel Gorman
` (3 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
This is partially a preparation patch for more vmstat work but it also has
the slight advantage that __count_zid_vm_events is cheaper to calculate
than __count_zone_vm_events().
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/vmstat.h | 5 ++---
mm/page_alloc.c | 2 +-
2 files changed, 3 insertions(+), 4 deletions(-)
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 552d0db4fca2..0e53874a66a9 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -101,9 +101,8 @@ static inline void vm_events_fold_cpu(int cpu)
#define count_vm_vmacache_event(x) do {} while (0)
#endif
-#define __count_zone_vm_events(item, zone, delta) \
- __count_vm_events(item##_NORMAL - ZONE_NORMAL + \
- zone_idx(zone), delta)
+#define __count_zid_vm_events(item, zid, delta) \
+ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
/*
* Zone and node-based page accounting with per cpu differentials.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 69ffaadc31ed..d3eb15c35bb1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2659,7 +2659,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
get_pcppage_migratetype(page));
}
- __count_zone_vm_events(PGALLOC, zone, 1 << order);
+ __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 29/31] mm: vmstat: account per-zone stalls and pages skipped during reclaim
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (27 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 28/31] mm: vmstat: replace __count_zone_vm_events with a zone id equivalent Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 30/31] mm, vmstat: print node-based stats in zoneinfo file Mel Gorman
` (2 subsequent siblings)
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
The vmstat allocstall was fairly useful in the general sense but
node-based LRUs change that. It's important to know if a stall was for an
address-limited allocation request as this will require skipping pages
from other zones. This patch adds pgstall_* counters to replace
allocstall. The sum of the counters will equal the old allocstall so it
can be trivially recalculated. A high number of address-limited
allocation requests may result in a lot of useless LRU scanning for
suitable pages.
As address-limited allocations require pages to be skipped, it's important
to know how much useless LRU scanning took place so this patch adds
pgskip* counters. This yields the following model
1. The number of address-space limited stalls can be accounted for (pgstall)
2. The amount of useless work required to reclaim the data is accounted (pgskip)
3. The total number of scans is available from pgscan_kswapd and pgscan_direct
so from that the ratio of useful to useless scans can be calculated.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/vm_event_item.h | 4 +++-
mm/vmscan.c | 15 +++++++++++++--
mm/vmstat.c | 3 ++-
3 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 1798ff542517..6d47f66f0e9c 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -23,6 +23,8 @@
enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
FOR_ALL_ZONES(PGALLOC),
+ FOR_ALL_ZONES(PGSTALL),
+ FOR_ALL_ZONES(PGSCAN_SKIP),
PGFREE, PGACTIVATE, PGDEACTIVATE,
PGFAULT, PGMAJFAULT,
PGLAZYFREED,
@@ -37,7 +39,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
#endif
PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
- PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+ PAGEOUTRUN, PGROTATED,
DROP_PAGECACHE, DROP_SLAB,
#ifdef CONFIG_NUMA_BALANCING
NUMA_PTE_UPDATES,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a687cfa91166..151c30dd27e2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1394,6 +1394,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
struct list_head *src = &lruvec->lists[lru];
unsigned long nr_taken = 0;
unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
+ unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
unsigned long scan, nr_pages;
LIST_HEAD(pages_skipped);
@@ -1408,6 +1409,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
if (page_zonenum(page) > sc->reclaim_idx) {
list_move(&page->lru, &pages_skipped);
+ nr_skipped[page_zonenum(page)]++;
continue;
}
@@ -1436,8 +1438,17 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
* scanning would soon rescan the same pages to skip and put the
* system at risk of premature OOM.
*/
- if (!list_empty(&pages_skipped))
+ if (!list_empty(&pages_skipped)) {
+ int zid;
+
list_splice(&pages_skipped, src);
+ for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+ if (!nr_skipped[zid])
+ continue;
+
+ __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
+ }
+ }
*nr_scanned = scan;
trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
nr_taken, mode, is_file_lru(lru));
@@ -2676,7 +2687,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
delayacct_freepages_start();
if (global_reclaim(sc))
- count_vm_event(ALLOCSTALL);
+ __count_zid_vm_events(PGSTALL, sc->reclaim_idx, 1);
do {
vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 905ea9ae2d5a..b9a9844e3142 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -970,6 +970,8 @@ const char * const vmstat_text[] = {
"pswpout",
TEXTS_FOR_ZONES("pgalloc")
+ TEXTS_FOR_ZONES("pgstall")
+ TEXTS_FOR_ZONES("pgskip")
"pgfree",
"pgactivate",
@@ -995,7 +997,6 @@ const char * const vmstat_text[] = {
"kswapd_low_wmark_hit_quickly",
"kswapd_high_wmark_hit_quickly",
"pageoutrun",
- "allocstall",
"pgrotated",
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 30/31] mm, vmstat: print node-based stats in zoneinfo file
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (28 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 29/31] mm: vmstat: account per-zone stalls and pages skipped during reclaim Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries Mel Gorman
2016-07-04 1:37 ` [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Minchan Kim
31 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
There are a number of stats that were previously accessible via zoneinfo
that are now invisible. While it is possible to create a new file for the
node stats, this may be missed by users. Instead this patch prints the
stats under the first populated zone in /proc/zoneinfo.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
mm/vmstat.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b9a9844e3142..ce09be63e8c7 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1402,11 +1402,35 @@ static const struct file_operations pagetypeinfo_file_ops = {
.release = seq_release,
};
+static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone)
+{
+ int zid;
+
+ for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+ struct zone *compare = &pgdat->node_zones[zid];
+
+ if (populated_zone(compare))
+ return zone == compare;
+ }
+
+ /* The zone must be somewhere! */
+ WARN_ON_ONCE(1);
+ return false;
+}
+
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
struct zone *zone)
{
int i;
seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
+ if (is_zone_first_populated(pgdat, zone)) {
+ seq_printf(m, "\n per-node stats");
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+ seq_printf(m, "\n %-12s %lu",
+ vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
+ node_page_state(pgdat, i));
+ }
+ }
seq_printf(m,
"\n pages free %lu"
"\n min %lu"
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (29 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 30/31] mm, vmstat: print node-based stats in zoneinfo file Mel Gorman
@ 2016-07-01 20:01 ` Mel Gorman
2016-07-06 0:02 ` Minchan Kim
2016-07-06 18:12 ` Dave Hansen
2016-07-04 1:37 ` [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Minchan Kim
31 siblings, 2 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 20:01 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
The number of LRU pages, dirty pages and writeback pages must be accounted
for on both zones and nodes because of the reclaim retry logic, compaction
retry logic and highmem calculations all depending on per-zone stats.
The retry logic is only critical for allocations that can use any zones.
Hence this patch will not retry reclaim or compaction for such allocations.
This should not be a problem for reclaim as zone-constrained allocations
are immune from OOM kill. For retries, a very rough approximation is made
whether to retry or not. While it is possible this will make the wrong
decision on occasion, it will not infinite loop as the number of reclaim
attempts is capped by MAX_RECLAIM_RETRIES.
The highmem calculations only care about the global count of file pages
in highmem. Hence, a global counter is used instead of per-zone stats.
With this, the per-zone double accounting disappears.
Suggested by: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
include/linux/mm_inline.h | 20 +++++++++++--
include/linux/mmzone.h | 4 ---
include/linux/swap.h | 1 -
mm/compaction.c | 22 ++++++++++++++-
mm/migrate.c | 2 --
mm/page-writeback.c | 13 ++++-----
mm/page_alloc.c | 71 ++++++++++++++++++++++++++++++++---------------
mm/vmscan.c | 16 -----------
mm/vmstat.c | 3 --
9 files changed, 92 insertions(+), 60 deletions(-)
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 9aadcc781857..c68680aac044 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -4,6 +4,22 @@
#include <linux/huge_mm.h>
#include <linux/swap.h>
+#ifdef CONFIG_HIGHMEM
+extern unsigned long highmem_file_pages;
+
+static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
+ int nr_pages)
+{
+ if (is_highmem_idx(zid) && is_file_lru(lru))
+ highmem_file_pages += nr_pages;
+}
+#else
+static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
+ int nr_pages)
+{
+}
+#endif
+
/**
* page_is_file_cache - should the page be on a file LRU or anon LRU?
* @page: the page to test
@@ -29,9 +45,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec,
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
__mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
- __mod_zone_page_state(&pgdat->node_zones[zid],
- NR_ZONE_LRU_BASE + !!is_file_lru(lru),
- nr_pages);
+ acct_highmem_file_pages(zid, lru, nr_pages);
}
static __always_inline void update_lru_size(struct lruvec *lruvec,
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index facee6b83440..9268528c20c0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -110,10 +110,6 @@ struct zone_padding {
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
- NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
- NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
- NR_ZONE_LRU_FILE,
- NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */
NR_MLOCK, /* mlock()ed pages found and moved off LRU */
NR_SLAB_RECLAIMABLE,
NR_SLAB_UNRECLAIMABLE,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b17cc4830fa6..cc753c639e3d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -307,7 +307,6 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
struct vm_area_struct *vma);
/* linux/mm/vmscan.c */
-extern unsigned long zone_reclaimable_pages(struct zone *zone);
extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
diff --git a/mm/compaction.c b/mm/compaction.c
index a0bd85712516..dfe7dafe8e8b 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1446,6 +1446,13 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
{
struct zone *zone;
struct zoneref *z;
+ pg_data_t *last_pgdat = NULL;
+
+#ifdef CONFIG_HIGHMEM
+ /* Do not retry compaction for zone-constrained allocations */
+ if (!is_highmem_idx(ac->high_zoneidx))
+ return false;
+#endif
/*
* Make sure at least one zone would pass __compaction_suitable if we continue
@@ -1456,14 +1463,27 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
unsigned long available;
enum compact_result compact_result;
+ if (last_pgdat == zone->zone_pgdat)
+ continue;
+
+ /*
+ * This over-estimates the number of pages available for
+ * reclaim/compaction but walking the LRU would take too
+ * long. The consequences are that compaction may retry
+ * longer than it should for a zone-constrained allocation
+ * request.
+ */
+ last_pgdat = zone->zone_pgdat;
+ available = pgdat_reclaimable_pages(zone->zone_pgdat) / order;
+
/*
* Do not consider all the reclaimable memory because we do not
* want to trash just for a single high order allocation which
* is even not guaranteed to appear even if __compaction_suitable
* is happy about the watermark check.
*/
- available = zone_reclaimable_pages(zone) / order;
available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
+ available = min(zone->managed_pages, available);
compact_result = __compaction_suitable(zone, order, alloc_flags,
ac_classzone_idx(ac), available);
if (compact_result != COMPACT_SKIPPED &&
diff --git a/mm/migrate.c b/mm/migrate.c
index c77997dc6ed7..ed2f85e61de1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -513,9 +513,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
}
if (dirty && mapping_cap_account_dirty(mapping)) {
__dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
- __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
__inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
- __dec_zone_state(newzone, NR_ZONE_WRITE_PENDING);
}
}
local_irq_enable();
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3c02aa603f5a..8db1db234915 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -299,6 +299,9 @@ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
return nr_pages;
}
+#ifdef CONFIG_HIGHMEM
+unsigned long highmem_file_pages;
+#endif
static unsigned long highmem_dirtyable_memory(unsigned long total)
{
@@ -306,18 +309,17 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
int node;
unsigned long x = 0;
int i;
+ unsigned long dirtyable = highmem_file_pages;
for_each_node_state(node, N_HIGH_MEMORY) {
for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) {
struct zone *z;
- unsigned long dirtyable;
if (!is_highmem_idx(i))
continue;
z = &NODE_DATA(node)->node_zones[i];
- dirtyable = zone_page_state(z, NR_FREE_PAGES) +
- zone_page_state(z, NR_ZONE_LRU_FILE);
+ dirtyable += zone_page_state(z, NR_FREE_PAGES);
/* watch for underflows */
dirtyable -= min(dirtyable, high_wmark_pages(z));
@@ -2460,7 +2462,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY);
__inc_node_page_state(page, NR_FILE_DIRTY);
- __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
__inc_node_page_state(page, NR_DIRTIED);
__inc_wb_stat(wb, WB_RECLAIMABLE);
__inc_wb_stat(wb, WB_DIRTIED);
@@ -2482,7 +2483,6 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
if (mapping_cap_account_dirty(mapping)) {
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
dec_node_page_state(page, NR_FILE_DIRTY);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
dec_wb_stat(wb, WB_RECLAIMABLE);
task_io_account_cancelled_write(PAGE_SIZE);
}
@@ -2739,7 +2739,6 @@ int clear_page_dirty_for_io(struct page *page)
if (TestClearPageDirty(page)) {
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
dec_node_page_state(page, NR_FILE_DIRTY);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
dec_wb_stat(wb, WB_RECLAIMABLE);
ret = 1;
}
@@ -2786,7 +2785,6 @@ int test_clear_page_writeback(struct page *page)
if (ret) {
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
dec_node_page_state(page, NR_WRITEBACK);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
inc_node_page_state(page, NR_WRITTEN);
}
unlock_page_memcg(page);
@@ -2841,7 +2839,6 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
if (!ret) {
mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
inc_node_page_state(page, NR_WRITEBACK);
- inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
}
unlock_page_memcg(page);
return ret;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d3eb15c35bb1..9581185cb31a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3445,6 +3445,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
{
struct zone *zone;
struct zoneref *z;
+ pg_data_t *current_pgdat = NULL;
/*
* Make sure we converge to OOM if we cannot make any progress
@@ -3454,6 +3455,14 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
return false;
/*
+ * Blindly retry allocation requests that cannot use all zones. We do
+ * not have a reliable and fast means of calculating reclaimable, dirty
+ * and writeback pages in eligible zones.
+ */
+ if (IS_ENABLED(CONFIG_HIGHMEM) && !is_highmem_idx(gfp_zone(gfp_mask)))
+ goto out;
+
+ /*
* Keep reclaiming pages while there is a chance this will lead somewhere.
* If none of the target zones can satisfy our allocation request even
* if all reclaimable pages are considered then we are screwed and have
@@ -3463,36 +3472,54 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
ac->nodemask) {
unsigned long available;
unsigned long reclaimable;
+ unsigned long write_pending = 0;
+ int zid;
+
+ if (current_pgdat == zone->zone_pgdat)
+ continue;
- available = reclaimable = zone_reclaimable_pages(zone);
+ current_pgdat = zone->zone_pgdat;
+ available = reclaimable = pgdat_reclaimable_pages(current_pgdat);
available -= DIV_ROUND_UP(no_progress_loops * available,
MAX_RECLAIM_RETRIES);
- available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
+ write_pending = node_page_state(current_pgdat, NR_WRITEBACK) +
+ node_page_state(current_pgdat, NR_FILE_DIRTY);
- /*
- * Would the allocation succeed if we reclaimed the whole
- * available?
- */
- if (__zone_watermark_ok(zone, order, min_wmark_pages(zone),
- ac_classzone_idx(ac), alloc_flags, available)) {
- /*
- * If we didn't make any progress and have a lot of
- * dirty + writeback pages then we should wait for
- * an IO to complete to slow down the reclaim and
- * prevent from pre mature OOM
- */
- if (!did_some_progress) {
- unsigned long write_pending;
+ /* Account for all free pages on eligible zones */
+ for (zid = 0; zid <= zone_idx(zone); zid++) {
+ struct zone *acct_zone = ¤t_pgdat->node_zones[zid];
- write_pending = zone_page_state_snapshot(zone,
- NR_ZONE_WRITE_PENDING);
+ available += zone_page_state_snapshot(acct_zone, NR_FREE_PAGES);
+ }
- if (2 * write_pending > reclaimable) {
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- return true;
- }
+ /*
+ * If we didn't make any progress and have a lot of
+ * dirty + writeback pages then we should wait for an IO to
+ * complete to slow down the reclaim and prevent from premature
+ * OOM.
+ */
+ if (!did_some_progress) {
+ if (2 * write_pending > reclaimable) {
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
+ return true;
}
+ }
+ /*
+ * Would the allocation succeed if we reclaimed the whole
+ * available? This is approximate because there is no
+ * accurate count of reclaimable pages per zone.
+ */
+ for (zid = 0; zid <= zone_idx(zone); zid++) {
+ struct zone *check_zone = ¤t_pgdat->node_zones[zid];
+ unsigned long estimate;
+
+ estimate = min(check_zone->managed_pages, available);
+ if (__zone_watermark_ok(check_zone, order,
+ min_wmark_pages(check_zone), ac_classzone_idx(ac),
+ alloc_flags, available)) {
+ }
+out:
/*
* Memory allocation/reclaim might be called from a WQ
* context and the current implementation of the WQ
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 151c30dd27e2..c538a8cab43b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -194,22 +194,6 @@ static bool sane_reclaim(struct scan_control *sc)
}
#endif
-/*
- * This misses isolated pages which are not accounted for to save counters.
- * As the data only determines if reclaim or compaction continues, it is
- * not expected that isolated pages will be a dominating factor.
- */
-unsigned long zone_reclaimable_pages(struct zone *zone)
-{
- unsigned long nr;
-
- nr = zone_page_state_snapshot(zone, NR_ZONE_LRU_FILE);
- if (get_nr_swap_pages() > 0)
- nr += zone_page_state_snapshot(zone, NR_ZONE_LRU_ANON);
-
- return nr;
-}
-
unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat)
{
unsigned long nr;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index ce09be63e8c7..524c082072be 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -908,9 +908,6 @@ int fragmentation_index(struct zone *zone, unsigned int order)
const char * const vmstat_text[] = {
/* enum zone_stat_item countes */
"nr_free_pages",
- "nr_zone_anon_lru",
- "nr_zone_file_lru",
- "nr_zone_write_pending",
"nr_mlock",
"nr_slab_reclaimable",
"nr_slab_unreclaimable",
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
* Re: [PATCH 00/31] Move LRU page reclaim from zones to nodes v8
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
` (30 preceding siblings ...)
2016-07-01 20:01 ` [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries Mel Gorman
@ 2016-07-04 1:37 ` Minchan Kim
2016-07-04 4:34 ` Mel Gorman
31 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-04 1:37 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:08PM +0100, Mel Gorman wrote:
> (Sorry for the resend, I accidentally sent the branch that still had the
> Signed-off-by's from mmotm still applied which is incorrect.)
>
> Previous releases double accounted LRU stats on the zone and the node
> because it was required by should_reclaim_retry. The last patch in the
> series removes the double accounting. It's not integrated with the series
> as reviewers may not like the solution. If not, it can be safely dropped
> without a major impact to the results.
>
> Changelog since v7
> o Rebase onto current mmots
> o Avoid double accounting of stats in node and zone
> o Kswapd will avoid more reclaim if an eligible zone is available
> o Remove some duplications of sc->reclaim_idx and classzone_idx
> o Print per-node stats in zoneinfo
>
> Changelog since v6
> o Correct reclaim_idx when direct reclaiming for memcg
> o Also account LRU pages per zone for compaction/reclaim
> o Add page_pgdat helper with more efficient lookup
> o Init pgdat LRU lock only once
> o Slight optimisation to wake_all_kswapds
> o Always wake kcompactd when kswapd is going to sleep
> o Rebase to mmotm as of June 15th, 2016
>
> Changelog since v5
> o Rebase and adjust to changes
>
> Changelog since v4
> o Rebase on top of v3 of page allocator optimisation series
>
> Changelog since v3
> o Rebase on top of the page allocator optimisation series
> o Remove RFC tag
>
> This is the latest version of a series that moves LRUs from the zones to
> the node that is based upon 4.7-rc4 with Andrew's tree applied. While this
> is a current rebase, the test results were based on mmotm as of June 23rd.
> Conceptually, this series is simple but there are a lot of details. Some
> of the broad motivations for this are;
>
> 1. The residency of a page partially depends on what zone the page was
> allocated from. This is partially combatted by the fair zone allocation
> policy but that is a partial solution that introduces overhead in the
> page allocator paths.
>
> 2. Currently, reclaim on node 0 behaves slightly different to node 1. For
> example, direct reclaim scans in zonelist order and reclaims even if
> the zone is over the high watermark regardless of the age of pages
> in that LRU. Kswapd on the other hand starts reclaim on the highest
> unbalanced zone. A difference in distribution of file/anon pages due
> to when they were allocated results can result in a difference in
> again. While the fair zone allocation policy mitigates some of the
> problems here, the page reclaim results on a multi-zone node will
> always be different to a single-zone node.
> it was scheduled on as a result.
>
> 3. kswapd and the page allocator scan zones in the opposite order to
> avoid interfering with each other but it's sensitive to timing. This
> mitigates the page allocator using pages that were allocated very recently
> in the ideal case but it's sensitive to timing. When kswapd is allocating
> from lower zones then it's great but during the rebalancing of the highest
> zone, the page allocator and kswapd interfere with each other. It's worse
> if the highest zone is small and difficult to balance.
>
> 4. slab shrinkers are node-based which makes it harder to identify the exact
> relationship between slab reclaim and LRU reclaim.
>
> The reason we have zone-based reclaim is that we used to have
> large highmem zones in common configurations and it was necessary
> to quickly find ZONE_NORMAL pages for reclaim. Today, this is much
> less of a concern as machines with lots of memory will (or should) use
> 64-bit kernels. Combinations of 32-bit hardware and 64-bit hardware are
> rare. Machines that do use highmem should have relatively low highmem:lowmem
> ratios than we worried about in the past.
Hello Mel,
I agree the direction absolutely. However, I have a concern on highmem
system as you already mentioned.
Embedded products still use 2 ~ 3 ratio (highmem:lowmem).
In such system, LRU churning by skipping other zone pages frequently
might be significant for the performance.
How big ratio between highmem:lowmem do you think a problem?
>
> Conceptually, moving to node LRUs should be easier to understand. The
> page allocator plays fewer tricks to game reclaim and reclaim behaves
> similarly on all nodes.
>
> The series has been tested on a 16 core UMA machine and a 2-socket 48
> core NUMA machine. The UMA results are presented in most cases as the NUMA
> machine behaved similarly.
I guess you would already test below with various highmem system(e.g.,
2:1, 3:1, 4:1 and so on). If you have, could you mind sharing it?
>
> pagealloc
> ---------
>
> This is a microbenchmark that shows the benefit of removing the fair zone
> allocation policy. It was tested uip to order-4 but only orders 0 and 1 are
> shown as the other orders were comparable.
>
> 4.7.0-rc4 4.7.0-rc4
> mmotm-20160623 nodelru-v8
> Min total-odr0-1 490.00 ( 0.00%) 463.00 ( 5.51%)
> Min total-odr0-2 349.00 ( 0.00%) 325.00 ( 6.88%)
> Min total-odr0-4 288.00 ( 0.00%) 272.00 ( 5.56%)
> Min total-odr0-8 250.00 ( 0.00%) 235.00 ( 6.00%)
> Min total-odr0-16 234.00 ( 0.00%) 222.00 ( 5.13%)
> Min total-odr0-32 223.00 ( 0.00%) 205.00 ( 8.07%)
> Min total-odr0-64 217.00 ( 0.00%) 202.00 ( 6.91%)
> Min total-odr0-128 214.00 ( 0.00%) 207.00 ( 3.27%)
> Min total-odr0-256 242.00 ( 0.00%) 242.00 ( 0.00%)
> Min total-odr0-512 272.00 ( 0.00%) 265.00 ( 2.57%)
> Min total-odr0-1024 290.00 ( 0.00%) 283.00 ( 2.41%)
> Min total-odr0-2048 302.00 ( 0.00%) 296.00 ( 1.99%)
> Min total-odr0-4096 311.00 ( 0.00%) 306.00 ( 1.61%)
> Min total-odr0-8192 314.00 ( 0.00%) 309.00 ( 1.59%)
> Min total-odr0-16384 315.00 ( 0.00%) 309.00 ( 1.90%)
> Min total-odr1-1 741.00 ( 0.00%) 716.00 ( 3.37%)
> Min total-odr1-2 565.00 ( 0.00%) 524.00 ( 7.26%)
> Min total-odr1-4 457.00 ( 0.00%) 427.00 ( 6.56%)
> Min total-odr1-8 408.00 ( 0.00%) 371.00 ( 9.07%)
> Min total-odr1-16 383.00 ( 0.00%) 344.00 ( 10.18%)
> Min total-odr1-32 378.00 ( 0.00%) 334.00 ( 11.64%)
> Min total-odr1-64 383.00 ( 0.00%) 334.00 ( 12.79%)
> Min total-odr1-128 376.00 ( 0.00%) 342.00 ( 9.04%)
> Min total-odr1-256 381.00 ( 0.00%) 343.00 ( 9.97%)
> Min total-odr1-512 388.00 ( 0.00%) 349.00 ( 10.05%)
> Min total-odr1-1024 386.00 ( 0.00%) 356.00 ( 7.77%)
> Min total-odr1-2048 389.00 ( 0.00%) 362.00 ( 6.94%)
> Min total-odr1-4096 389.00 ( 0.00%) 362.00 ( 6.94%)
> Min total-odr1-8192 389.00 ( 0.00%) 362.00 ( 6.94%)
>
> This shows a steady improvement throughout. The primary benefit is from
> reduced system CPU usage which is obvious from the overall times;
>
> 4.7.0-rc4 4.7.0-rc4
> mmotm-20160623nodelru-v8
> User 191.39 191.61
> System 2651.24 2504.48
> Elapsed 2904.40 2757.01
>
> The vmstats also showed that the fair zone allocation policy was definitely
> removed as can be seen here;
>
>
> 4.7.0-rc3 4.7.0-rc3
> mmotm-20160623 nodelru-v8
> DMA32 allocs 28794771816 0
> Normal allocs 48432582848 77227356392
> Movable allocs 0 0
>
> tiobench on ext4
> ----------------
>
> tiobench is a benchmark that artifically benefits if old pages remain resident
> while new pages get reclaimed. The fair zone allocation policy mitigates this
> problem so pages age fairly. While the benchmark has problems, it is important
> that tiobench performance remains constant as it implies that page aging
> problems that the fair zone allocation policy fixes are not re-introduced.
>
> 4.7.0-rc4 4.7.0-rc4
> mmotm-20160623 nodelru-v8
> Min PotentialReadSpeed 89.65 ( 0.00%) 90.34 ( 0.77%)
> Min SeqRead-MB/sec-1 82.68 ( 0.00%) 83.13 ( 0.54%)
> Min SeqRead-MB/sec-2 72.76 ( 0.00%) 72.15 ( -0.84%)
> Min SeqRead-MB/sec-4 75.13 ( 0.00%) 74.23 ( -1.20%)
> Min SeqRead-MB/sec-8 64.91 ( 0.00%) 65.25 ( 0.52%)
> Min SeqRead-MB/sec-16 62.24 ( 0.00%) 62.76 ( 0.84%)
> Min RandRead-MB/sec-1 0.88 ( 0.00%) 0.95 ( 7.95%)
> Min RandRead-MB/sec-2 0.95 ( 0.00%) 0.94 ( -1.05%)
> Min RandRead-MB/sec-4 1.43 ( 0.00%) 1.46 ( 2.10%)
> Min RandRead-MB/sec-8 1.61 ( 0.00%) 1.58 ( -1.86%)
> Min RandRead-MB/sec-16 1.80 ( 0.00%) 1.93 ( 7.22%)
> Min SeqWrite-MB/sec-1 76.41 ( 0.00%) 78.84 ( 3.18%)
> Min SeqWrite-MB/sec-2 74.11 ( 0.00%) 73.35 ( -1.03%)
> Min SeqWrite-MB/sec-4 80.05 ( 0.00%) 78.69 ( -1.70%)
> Min SeqWrite-MB/sec-8 72.88 ( 0.00%) 71.38 ( -2.06%)
> Min SeqWrite-MB/sec-16 75.91 ( 0.00%) 75.81 ( -0.13%)
> Min RandWrite-MB/sec-1 1.18 ( 0.00%) 1.12 ( -5.08%)
> Min RandWrite-MB/sec-2 1.02 ( 0.00%) 1.02 ( 0.00%)
> Min RandWrite-MB/sec-4 1.05 ( 0.00%) 0.99 ( -5.71%)
> Min RandWrite-MB/sec-8 0.89 ( 0.00%) 0.92 ( 3.37%)
> Min RandWrite-MB/sec-16 0.92 ( 0.00%) 0.89 ( -3.26%)
>
> This shows that the series has little or not impact on tiobench which is
> desirable. It indicates that the fair zone allocation policy was removed
> in a manner that didn't reintroduce one class of page aging bug. There
> were only minor differences in overall reclaim activity
>
> 4.7.0-rc4 4.7.0-rc4
> mmotm-20160623nodelru-v8
> Minor Faults 645838 644036
> Major Faults 573 593
> Swap Ins 0 0
> Swap Outs 0 0
> Allocation stalls 24 0
> DMA allocs 0 0
> DMA32 allocs 46041453 44154171
> Normal allocs 78053072 79865782
> Movable allocs 0 0
> Direct pages scanned 10969 54504
> Kswapd pages scanned 93375144 93250583
> Kswapd pages reclaimed 93372243 93247714
> Direct pages reclaimed 10969 54504
> Kswapd efficiency 99% 99%
> Kswapd velocity 13741.015 13711.950
> Direct efficiency 100% 100%
> Direct velocity 1.614 8.014
> Percentage direct scans 0% 0%
> Zone normal velocity 8641.875 13719.964
> Zone dma32 velocity 5100.754 0.000
> Zone dma velocity 0.000 0.000
> Page writes by reclaim 0.000 0.000
> Page writes file 0 0
> Page writes anon 0 0
> Page reclaim immediate 37 54
>
> kswapd activity was roughly comparable. There were differences in direct
> reclaim activity but negligible in the context of the overall workload
> (velocity of 8 pages per second with the patches applied, 1.6 pages per
> second in the baseline kernel).
Hmm, nodelru's allocation stall is zero above but how does direct page
scanning/reclaimed happens?
Above, DMA32 allocs in nodelru is almost same but zone dma32 velocity
is zero. What does it means?
>
> pgbench read-only large configuration on ext4
> ---------------------------------------------
>
> pgbench is a database benchmark that can be sensitive to page reclaim
> decisions. This also checks if removing the fair zone allocation policy
> is safe
>
> pgbench Transactions
> 4.7.0-rc4 4.7.0-rc4
> mmotm-20160623 nodelru-v8
> Hmean 1 188.26 ( 0.00%) 189.78 ( 0.81%)
> Hmean 5 330.66 ( 0.00%) 328.69 ( -0.59%)
> Hmean 12 370.32 ( 0.00%) 380.72 ( 2.81%)
> Hmean 21 368.89 ( 0.00%) 369.00 ( 0.03%)
> Hmean 30 382.14 ( 0.00%) 360.89 ( -5.56%)
> Hmean 32 428.87 ( 0.00%) 432.96 ( 0.95%)
>
> Negligible differences again. As with tiobench, overall reclaim activity
> was comparable.
>
> bonnie++ on ext4
> ----------------
>
> No interesting performance difference, negligible differences on reclaim
> stats.
>
> paralleldd on ext4
> ------------------
>
> This workload uses varying numbers of dd instances to read large amounts of
> data from disk.
>
> 4.7.0-rc3 4.7.0-rc3
> mmotm-20160615 nodelru-v7r17
> Amean Elapsd-1 181.57 ( 0.00%) 179.63 ( 1.07%)
> Amean Elapsd-3 188.29 ( 0.00%) 183.68 ( 2.45%)
> Amean Elapsd-5 188.02 ( 0.00%) 181.73 ( 3.35%)
> Amean Elapsd-7 186.07 ( 0.00%) 184.11 ( 1.05%)
> Amean Elapsd-12 188.16 ( 0.00%) 183.51 ( 2.47%)
> Amean Elapsd-16 189.03 ( 0.00%) 181.27 ( 4.10%)
>
> 4.7.0-rc3 4.7.0-rc3
> mmotm-20160615nodelru-v7r17
> User 1439.23 1433.37
> System 8332.31 8216.01
> Elapsed 3619.80 3532.69
>
> There is a slight gain in performance, some of which is from the reduced system
> CPU usage. There areminor differences in reclaim activity but nothing significant
>
> 4.7.0-rc3 4.7.0-rc3
> mmotm-20160615nodelru-v7r17
> Minor Faults 362486 358215
> Major Faults 1143 1113
> Swap Ins 26 0
> Swap Outs 2920 482
> DMA allocs 0 0
> DMA32 allocs 31568814 28598887
> Normal allocs 46539922 49514444
> Movable allocs 0 0
> Allocation stalls 0 0
> Direct pages scanned 0 0
> Kswapd pages scanned 40886878 40849710
> Kswapd pages reclaimed 40869923 40835207
> Direct pages reclaimed 0 0
> Kswapd efficiency 99% 99%
> Kswapd velocity 11295.342 11563.344
> Direct efficiency 100% 100%
> Direct velocity 0.000 0.000
> Slabs scanned 131673 126099
> Direct inode steals 57 60
> Kswapd inode steals 762 18
>
> It basically shows that kswapd was active at roughly the same rate in
> both kernels. There was also comparable slab scanning activity and direct
> reclaim was avoided in both cases. There appears to be a large difference
> in numbers of inodes reclaimed but the workload has few active inodes and
> is likely a timing artifact. It's interesting to note that the node-lru
> did not swap in any pages but given the low swap activity, it's unlikely
> to be significant.
>
> stutter
> -------
>
> stutter simulates a simple workload. One part uses a lot of anonymous
> memory, a second measures mmap latency and a third copies a large file.
> The primary metric is checking for mmap latency.
>
> stutter
> 4.7.0-rc4 4.7.0-rc4
> mmotm-20160623 nodelru-v8
> Min mmap 16.6283 ( 0.00%) 16.1394 ( 2.94%)
> 1st-qrtle mmap 54.7570 ( 0.00%) 55.2975 ( -0.99%)
> 2nd-qrtle mmap 57.3163 ( 0.00%) 57.5230 ( -0.36%)
> 3rd-qrtle mmap 58.9976 ( 0.00%) 58.0537 ( 1.60%)
> Max-90% mmap 59.7433 ( 0.00%) 58.3910 ( 2.26%)
> Max-93% mmap 60.1298 ( 0.00%) 58.4801 ( 2.74%)
> Max-95% mmap 73.4112 ( 0.00%) 58.5537 ( 20.24%)
> Max-99% mmap 92.8542 ( 0.00%) 58.9673 ( 36.49%)
> Max mmap 1440.6569 ( 0.00%) 137.6875 ( 90.44%)
> Mean mmap 59.3493 ( 0.00%) 55.5153 ( 6.46%)
> Best99%Mean mmap 57.2121 ( 0.00%) 55.4194 ( 3.13%)
> Best95%Mean mmap 55.9113 ( 0.00%) 55.2813 ( 1.13%)
> Best90%Mean mmap 55.6199 ( 0.00%) 55.1044 ( 0.93%)
> Best50%Mean mmap 53.2183 ( 0.00%) 52.8330 ( 0.72%)
> Best10%Mean mmap 45.9842 ( 0.00%) 42.3740 ( 7.85%)
> Best5%Mean mmap 43.2256 ( 0.00%) 38.8660 ( 10.09%)
> Best1%Mean mmap 32.9388 ( 0.00%) 27.7577 ( 15.73%)
>
> This shows a number of improvements with the worst-case outlier greatly
> improved.
>
> Some of the vmstats are interesting
>
> 4.7.0-rc4 4.7.0-rc4
> mmotm-20160623nodelru-v8
> Swap Ins 163 239
> Swap Outs 0 0
> Allocation stalls 2603 0
> DMA allocs 0 0
> DMA32 allocs 618719206 1303037965
> Normal allocs 891235743 229914091
> Movable allocs 0 0
> Direct pages scanned 216787 3173
> Kswapd pages scanned 50719775 41732250
> Kswapd pages reclaimed 41541765 41731168
> Direct pages reclaimed 209159 3173
> Kswapd efficiency 81% 99%
> Kswapd velocity 16859.554 14231.043
> Direct efficiency 96% 100%
> Direct velocity 72.061 1.082
> Percentage direct scans 0% 0%
> Zone normal velocity 8431.777 14232.125
> Zone dma32 velocity 8499.838 0.000
> Zone dma velocity 0.000 0.000
> Page writes by reclaim 6215049.000 0.000
> Page writes file 6215049 0
> Page writes anon 0 0
> Page reclaim immediate 70673 143
> Sector Reads 81940800 81489388
> Sector Writes 100158984 99161860
> Page rescued immediate 0 0
> Slabs scanned 1366954 21196
>
> While this is not guaranteed in all cases, this particular test showed
> a large reduction in direct reclaim activity. It's also worth noting
> that no page writes were issued from reclaim context.
>
> This series is not without its hazards. There are at least three areas
> that I'm concerned with even though I could not reproduce any problems in
> that area.
>
> 1. Reclaim/compaction is going to be affected because the amount of reclaim is
> no longer targetted at a specific zone. Compaction works on a per-zone basis
> so there is no guarantee that reclaiming a few THP's worth page pages will
> have a positive impact on compaction success rates.
>
> 2. The Slab/LRU reclaim ratio is affected because the frequency the shrinkers
> are called is now different. This may or may not be a problem but if it
> is, it'll be because shrinkers are not called enough and some balancing
> is required.
>
> 3. The anon/file reclaim ratio may be affected. Pages about to be dirtied are
> distributed between zones and the fair zone allocation policy used to do
> something very similar for anon. The distribution is now different but not
> necessarily in any way that matters but it's still worth bearing in mind.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 00/31] Move LRU page reclaim from zones to nodes v8
2016-07-04 1:37 ` [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Minchan Kim
@ 2016-07-04 4:34 ` Mel Gorman
2016-07-04 8:04 ` Minchan Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-04 4:34 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Mon, Jul 04, 2016 at 10:37:03AM +0900, Minchan Kim wrote:
> > The reason we have zone-based reclaim is that we used to have
> > large highmem zones in common configurations and it was necessary
> > to quickly find ZONE_NORMAL pages for reclaim. Today, this is much
> > less of a concern as machines with lots of memory will (or should) use
> > 64-bit kernels. Combinations of 32-bit hardware and 64-bit hardware are
> > rare. Machines that do use highmem should have relatively low highmem:lowmem
> > ratios than we worried about in the past.
>
> Hello Mel,
>
> I agree the direction absolutely. However, I have a concern on highmem
> system as you already mentioned.
>
> Embedded products still use 2 ~ 3 ratio (highmem:lowmem).
> In such system, LRU churning by skipping other zone pages frequently
> might be significant for the performance.
>
> How big ratio between highmem:lowmem do you think a problem?
>
That's a "how long is a piece of string" type question. The ratio does
not matter as much as whether the workload is both under memory pressure
and requires large amounts of lowmem pages. Even on systems with very high
ratios, it may not be a problem if HIGHPTE is enabled.
> >
> > Conceptually, moving to node LRUs should be easier to understand. The
> > page allocator plays fewer tricks to game reclaim and reclaim behaves
> > similarly on all nodes.
> >
> > The series has been tested on a 16 core UMA machine and a 2-socket 48
> > core NUMA machine. The UMA results are presented in most cases as the NUMA
> > machine behaved similarly.
>
> I guess you would already test below with various highmem system(e.g.,
> 2:1, 3:1, 4:1 and so on). If you have, could you mind sharing it?
>
I haven't that data, the baseline distribution used doesn't even have
32-bit support. Even if it was, the results may not be that interesting.
The workloads used were not necessarily going to trigger lowmem pressure
as HIGHPTE was set on the 32-bit configs.
The skip logic has been checked and it does work. This was done during
development, by forcing the "wrong" reclaim index to use. It was
noticable in system CPU usage and in the "skip" stats. I didn't preserve
this data.
> > 4.7.0-rc4 4.7.0-rc4
> > mmotm-20160623nodelru-v8
> > Minor Faults 645838 644036
> > Major Faults 573 593
> > Swap Ins 0 0
> > Swap Outs 0 0
> > Allocation stalls 24 0
> > DMA allocs 0 0
> > DMA32 allocs 46041453 44154171
> > Normal allocs 78053072 79865782
> > Movable allocs 0 0
> > Direct pages scanned 10969 54504
> > Kswapd pages scanned 93375144 93250583
> > Kswapd pages reclaimed 93372243 93247714
> > Direct pages reclaimed 10969 54504
> > Kswapd efficiency 99% 99%
> > Kswapd velocity 13741.015 13711.950
> > Direct efficiency 100% 100%
> > Direct velocity 1.614 8.014
> > Percentage direct scans 0% 0%
> > Zone normal velocity 8641.875 13719.964
> > Zone dma32 velocity 5100.754 0.000
> > Zone dma velocity 0.000 0.000
> > Page writes by reclaim 0.000 0.000
> > Page writes file 0 0
> > Page writes anon 0 0
> > Page reclaim immediate 37 54
> >
> > kswapd activity was roughly comparable. There were differences in direct
> > reclaim activity but negligible in the context of the overall workload
> > (velocity of 8 pages per second with the patches applied, 1.6 pages per
> > second in the baseline kernel).
>
> Hmm, nodelru's allocation stall is zero above but how does direct page
> scanning/reclaimed happens?
>
Good spot, it's because I used the wrong comparison script -- one that
doesn't understand the different skip and allocation stats and I was
looking primarily at the scanning activity. This is a correct version
4.7.0-rc4 4.7.0-rc4
mmotm-20160623nodelru-v8r26
Minor Faults 645838 643815
Major Faults 573 493
Swap Ins 0 0
Swap Outs 0 0
DMA allocs 0 0
DMA32 allocs 46041453 44174923
Normal allocs 78053072 79816443
Movable allocs 0 0
Allocation stalls 24 31
Stall zone DMA 0 0
Stall zone DMA32 0 0
Stall zone Normal 0 1
Stall zone HighMem 0 0
Stall zone Movable 0 30
Direct pages scanned 10969 14198
Kswapd pages scanned 93375144 93252534
Kswapd pages reclaimed 93372243 93249856
Direct pages reclaimed 10969 14198
Kswapd efficiency 99% 99%
Kswapd velocity 13741.015 13742.771
Direct efficiency 100% 100%
Direct velocity 1.614 2.092
Percentage direct scans 0% 0%
Page writes by reclaim 0 0
Page writes file 0 0
Page writes anon 0 0
Page reclaim immediate 37 29
The points about kswapd and direct reclaim activity still hold.
> Above, DMA32 allocs in nodelru is almost same but zone dma32 velocity
> is zero. What does it means?
>
It's a consequence of using the wrong script when cutting and pasting
the final data. With node-lru, "zone dma32 velocity" is meaningless and
the reporting script no longer includes it.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 00/31] Move LRU page reclaim from zones to nodes v8
2016-07-04 4:34 ` Mel Gorman
@ 2016-07-04 8:04 ` Minchan Kim
2016-07-04 9:55 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-04 8:04 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML, daniel.vetter, intel-gfx, dri-devel,
David Airlie
On Mon, Jul 04, 2016 at 05:34:05AM +0100, Mel Gorman wrote:
> On Mon, Jul 04, 2016 at 10:37:03AM +0900, Minchan Kim wrote:
> > > The reason we have zone-based reclaim is that we used to have
> > > large highmem zones in common configurations and it was necessary
> > > to quickly find ZONE_NORMAL pages for reclaim. Today, this is much
> > > less of a concern as machines with lots of memory will (or should) use
> > > 64-bit kernels. Combinations of 32-bit hardware and 64-bit hardware are
> > > rare. Machines that do use highmem should have relatively low highmem:lowmem
> > > ratios than we worried about in the past.
> >
> > Hello Mel,
> >
> > I agree the direction absolutely. However, I have a concern on highmem
> > system as you already mentioned.
> >
> > Embedded products still use 2 ~ 3 ratio (highmem:lowmem).
> > In such system, LRU churning by skipping other zone pages frequently
> > might be significant for the performance.
> >
> > How big ratio between highmem:lowmem do you think a problem?
> >
>
> That's a "how long is a piece of string" type question. The ratio does
> not matter as much as whether the workload is both under memory pressure
> and requires large amounts of lowmem pages. Even on systems with very high
> ratios, it may not be a problem if HIGHPTE is enabled.
As well page table, pgd/kernelstack/zbud/slab and so on, every kernel
allocations wanted to mask __GFP_HIGHMEM off would be a problem in
32bit system.
It also depends on that how many drivers needed lowmem only we have
in the system.
I don't know how many such driver in the world. When I simply do grep,
I found several cases which mask __GFP_HIGHMEM off and among them,
I guess DRM might be a popular for us. However, it might be really rare
usecase among various i915 usecases.
>
> > >
> > > Conceptually, moving to node LRUs should be easier to understand. The
> > > page allocator plays fewer tricks to game reclaim and reclaim behaves
> > > similarly on all nodes.
> > >
> > > The series has been tested on a 16 core UMA machine and a 2-socket 48
> > > core NUMA machine. The UMA results are presented in most cases as the NUMA
> > > machine behaved similarly.
> >
> > I guess you would already test below with various highmem system(e.g.,
> > 2:1, 3:1, 4:1 and so on). If you have, could you mind sharing it?
> >
>
> I haven't that data, the baseline distribution used doesn't even have
> 32-bit support. Even if it was, the results may not be that interesting.
> The workloads used were not necessarily going to trigger lowmem pressure
> as HIGHPTE was set on the 32-bit configs.
That means we didn't test this on 32-bit with highmem.
I'm not sure it's really too rare case to spend a time for testing.
In fact, I really want to test all series to our production system
which is 32bit and highmem but as we know well, most of embedded
system kernel is rather old so backporting needs lots of time and
care. However, if we miss testing in those system at the moment,
we will be suprised after 1~2 years.
I don't know what kinds of benchmark can we can check it so I cannot
insist on it but you might know it.
Okay, do you have any idea to fix it if we see such regression report
in 32-bit system in future?
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 00/31] Move LRU page reclaim from zones to nodes v8
2016-07-04 8:04 ` Minchan Kim
@ 2016-07-04 9:55 ` Mel Gorman
2016-07-06 1:51 ` Minchan Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-04 9:55 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML, daniel.vetter, intel-gfx, dri-devel,
David Airlie
On Mon, Jul 04, 2016 at 05:04:12PM +0900, Minchan Kim wrote:
> > > How big ratio between highmem:lowmem do you think a problem?
> > >
> >
> > That's a "how long is a piece of string" type question. The ratio does
> > not matter as much as whether the workload is both under memory pressure
> > and requires large amounts of lowmem pages. Even on systems with very high
> > ratios, it may not be a problem if HIGHPTE is enabled.
>
> As well page table, pgd/kernelstack/zbud/slab and so on, every kernel
> allocations wanted to mask __GFP_HIGHMEM off would be a problem in
> 32bit system.
>
The same point applies -- it depends on the rate of these allocations,
not the ratio of highmem:lowmem per se.
> It also depends on that how many drivers needed lowmem only we have
> in the system.
>
> I don't know how many such driver in the world. When I simply do grep,
> I found several cases which mask __GFP_HIGHMEM off and among them,
> I guess DRM might be a popular for us. However, it might be really rare
> usecase among various i915 usecases.
>
It's also perfectly possible that such allocations are long-lived in which
case they are not going to cause many skips. Hence why I cannot make a
general prediction.
> > > > Conceptually, moving to node LRUs should be easier to understand. The
> > > > page allocator plays fewer tricks to game reclaim and reclaim behaves
> > > > similarly on all nodes.
> > > >
> > > > The series has been tested on a 16 core UMA machine and a 2-socket 48
> > > > core NUMA machine. The UMA results are presented in most cases as the NUMA
> > > > machine behaved similarly.
> > >
> > > I guess you would already test below with various highmem system(e.g.,
> > > 2:1, 3:1, 4:1 and so on). If you have, could you mind sharing it?
> > >
> >
> > I haven't that data, the baseline distribution used doesn't even have
> > 32-bit support. Even if it was, the results may not be that interesting.
> > The workloads used were not necessarily going to trigger lowmem pressure
> > as HIGHPTE was set on the 32-bit configs.
>
> That means we didn't test this on 32-bit with highmem.
>
No. I tested the skip logic and noticed that when forced on purpose that
system CPU usage was higher but it functionally worked.
> I'm not sure it's really too rare case to spend a time for testing.
> In fact, I really want to test all series to our production system
> which is 32bit and highmem but as we know well, most of embedded
> system kernel is rather old so backporting needs lots of time and
> care. However, if we miss testing in those system at the moment,
> we will be suprised after 1~2 years.
>
It would be appreciated if it could be tested on such platforms if at all
possible. Even if I did set up a 32-bit x86 system, it won't have the same
allocation/reclaim profile as the platforms you are considering.
> I don't know what kinds of benchmark can we can check it so I cannot
> insist on it but you might know it.
>
One method would be to use fsmark with very large numbers of small files
to force slab to require low memory. It's not representative of many real
workloads unfortunately. Usually such a configuration is for checking the
slab shrinker is working as expected.
> Okay, do you have any idea to fix it if we see such regression report
> in 32-bit system in future?
Two options, neither whose complexity is justified without a "real"
workload to use as a reference.
1. Long-term isolation of highmem pages when reclaim is lowmem
When pages are skipped, they are immediately added back onto the LRU
list. If lowmem reclaim persisted for long periods of time, the same
highmem pages get continually scanned. The idea would be that lowmem
keeps those pages on a separate list until a reclaim for highmem pages
arrives that splices the highmem pages back onto the LRU.
That would reduce the skip rate, the potential corner case is that
highmem pages have to be scanned and reclaimed to free lowmem slab pages.
2. Linear scan lowmem pages if the initial LRU shrink fails
This will break LRU ordering but may be preferable and faster during
memory pressure than skipping LRU pages.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats
2016-07-01 20:01 ` [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats Mel Gorman
@ 2016-07-04 23:50 ` Minchan Kim
2016-07-05 8:14 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-04 23:50 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:09PM +0100, Mel Gorman wrote:
> VM statistic counters for reclaim decisions are zone-based. If the kernel
> is to reclaim on a per-node basis then we need to track per-node
> statistics but there is no infrastructure for that. The most notable
> change is that the old node_page_state is renamed to
> sum_zone_node_page_state. The new node_page_state takes a pglist_data and
> uses per-node stats but none exist yet. There is some renaming such as
> vm_stat to vm_zone_stat and the addition of vm_node_stat and the renaming
> of mod_state to mod_zone_state. Otherwise, this is mostly a mechanical
> patch with no functional change. There is a lot of similarity between the
> node and zone helpers which is unfortunate but there was no obvious way of
> reusing the code and maintaining type safety.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
<snip>
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 7997f52935c9..90b0737ee4be 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -86,8 +86,10 @@ void vm_events_fold_cpu(int cpu)
> *
> * vm_stat contains the global counters
> */
> -atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
> -EXPORT_SYMBOL(vm_stat);
> +atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
> +atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp;
> +EXPORT_SYMBOL(vm_zone_stat);
> +EXPORT_SYMBOL(vm_node_stat);
>
> #ifdef CONFIG_SMP
>
> @@ -172,13 +174,17 @@ void refresh_zone_stat_thresholds(void)
> int threshold;
>
> for_each_populated_zone(zone) {
> + struct pglist_data *pgdat = zone->zone_pgdat;
> unsigned long max_drift, tolerate_drift;
>
> threshold = calculate_normal_threshold(zone);
>
> - for_each_online_cpu(cpu)
> + for_each_online_cpu(cpu) {
> per_cpu_ptr(zone->pageset, cpu)->stat_threshold
> = threshold;
> + per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
> + = threshold;
> + }
I didn't see other patches yet so it might fix it then.
per_cpu_nodestats is per node not zone but it use per-zone threshold
and even overwritten by next zones. I don't think it's not intended.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 02/31] mm, vmscan: move lru_lock to the node
2016-07-01 20:01 ` [PATCH 02/31] mm, vmscan: move lru_lock to the node Mel Gorman
@ 2016-07-05 0:03 ` Minchan Kim
0 siblings, 0 replies; 90+ messages in thread
From: Minchan Kim @ 2016-07-05 0:03 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:10PM +0100, Mel Gorman wrote:
> Node-based reclaim requires node-based LRUs and locking. This is a
> preparation patch that just moves the lru_lock to the node so later
> patches are easier to review. It is a mechanical change but note this
> patch makes contention worse because the LRU lock is hotter and direct
> reclaim and kswapd can contend on the same lock even when reclaiming from
> different zones.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
> Documentation/cgroup-v1/memcg_test.txt | 4 +--
> Documentation/cgroup-v1/memory.txt | 4 +--
> include/linux/mm_types.h | 2 +-
> include/linux/mmzone.h | 10 +++++--
> mm/compaction.c | 10 +++----
> mm/filemap.c | 4 +--
> mm/huge_memory.c | 6 ++---
> mm/memcontrol.c | 6 ++---
> mm/mlock.c | 10 +++----
> mm/page_alloc.c | 4 +--
> mm/page_idle.c | 4 +--
> mm/rmap.c | 2 +-
> mm/swap.c | 30 ++++++++++-----------
> mm/vmscan.c | 48 +++++++++++++++++-----------------
> 14 files changed, 75 insertions(+), 69 deletions(-)
>
> diff --git a/Documentation/cgroup-v1/memcg_test.txt b/Documentation/cgroup-v1/memcg_test.txt
> index 8870b0212150..78a8c2963b38 100644
> --- a/Documentation/cgroup-v1/memcg_test.txt
> +++ b/Documentation/cgroup-v1/memcg_test.txt
> @@ -107,9 +107,9 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
>
> 8. LRU
> Each memcg has its own private LRU. Now, its handling is under global
> - VM's control (means that it's handled under global zone->lru_lock).
> + VM's control (means that it's handled under global zone_lru_lock).
> Almost all routines around memcg's LRU is called by global LRU's
> - list management functions under zone->lru_lock().
> + list management functions under zone_lru_lock().
>
> A special function is mem_cgroup_isolate_pages(). This scans
> memcg's private LRU and call __isolate_lru_page() to extract a page
> diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt
> index b14abf217239..946e69103cdd 100644
> --- a/Documentation/cgroup-v1/memory.txt
> +++ b/Documentation/cgroup-v1/memory.txt
> @@ -267,11 +267,11 @@ When oom event notifier is registered, event will be delivered.
> Other lock order is following:
> PG_locked.
> mm->page_table_lock
> - zone->lru_lock
> + zone_lru_lock
> lock_page_cgroup.
> In many cases, just lock_page_cgroup() is called.
> per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
> - zone->lru_lock, it has no lock of its own.
> + zone_lru_lock, it has no lock of its own.
>
> 2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
>
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index e093e1d3285b..ca2ed9a6c8d8 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -118,7 +118,7 @@ struct page {
> */
> union {
> struct list_head lru; /* Pageout list, eg. active_list
> - * protected by zone->lru_lock !
> + * protected by zone_lru_lock !
> * Can be used as a generic list
> * by the page owner.
> */
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 078ecb81e209..2d5087e3c034 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -93,7 +93,7 @@ struct free_area {
> struct pglist_data;
>
> /*
> - * zone->lock and zone->lru_lock are two of the hottest locks in the kernel.
> + * zone->lock and the zone lru_lock are two of the hottest locks in the kernel.
> * So add a wild amount of padding here to ensure that they fall into separate
> * cachelines. There are very few zone structures in the machine, so space
> * consumption is not a concern here.
> @@ -496,7 +496,6 @@ struct zone {
> /* Write-intensive fields used by page reclaim */
>
> /* Fields commonly accessed by the page reclaim scanner */
> - spinlock_t lru_lock;
> struct lruvec lruvec;
>
> /*
> @@ -690,6 +689,9 @@ typedef struct pglist_data {
> /* Number of pages migrated during the rate limiting time interval */
> unsigned long numabalancing_migrate_nr_pages;
> #endif
> + /* Write-intensive fields used from the page allocator */
page reclaim.
> + ZONE_PADDING(_pad1_)
> + spinlock_t lru_lock;
>
> #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
> /*
Otherwise, looks good to me.
Reviewed-by: Minchan Kim <minchan@kernel.org>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 03/31] mm, vmscan: move LRU lists to node
2016-07-01 20:01 ` [PATCH 03/31] mm, vmscan: move LRU lists to node Mel Gorman
@ 2016-07-05 1:19 ` Minchan Kim
2016-07-05 10:14 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-05 1:19 UTC (permalink / raw)
To: Mel Gorman, Michal Hocko
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:11PM +0100, Mel Gorman wrote:
> This moves the LRU lists from the zone to the node and related data such
> as counters, tracing, congestion tracking and writeback tracking.
> Unfortunately, due to reclaim and compaction retry logic, it is necessary
> to account for the number of LRU pages on both zone and node logic. Most
> reclaim logic is based on the node counters but the retry logic uses the
> zone counters which do not distinguish inactive and inactive sizes. It
active
> would be possible to leave the LRU counters on a per-zone basis but it's a
> heavier calculation across multiple cache lines that is much more frequent
> than the retry checks.
>
> Other than the LRU counters, this is mostly a mechanical patch but note
> that it introduces a number of anomalies. For example, the scans are
> per-zone but using per-node counters. We also mark a node as congested
> when a zone is congested. This causes weird problems that are fixed later
> but is easier to review.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
> arch/tile/mm/pgtable.c | 8 +-
> drivers/base/node.c | 19 +--
> drivers/staging/android/lowmemorykiller.c | 8 +-
> include/linux/backing-dev.h | 2 +-
> include/linux/memcontrol.h | 16 +--
> include/linux/mm_inline.h | 21 ++-
> include/linux/mmzone.h | 69 +++++----
> include/linux/swap.h | 1 +
> include/linux/vm_event_item.h | 10 +-
> include/linux/vmstat.h | 17 +++
> include/trace/events/vmscan.h | 12 +-
> kernel/power/snapshot.c | 10 +-
> mm/backing-dev.c | 15 +-
> mm/compaction.c | 18 +--
> mm/huge_memory.c | 2 +-
> mm/internal.h | 2 +-
> mm/khugepaged.c | 4 +-
> mm/memcontrol.c | 17 +--
> mm/memory-failure.c | 4 +-
> mm/memory_hotplug.c | 2 +-
> mm/mempolicy.c | 2 +-
> mm/migrate.c | 21 +--
> mm/mlock.c | 2 +-
> mm/page-writeback.c | 8 +-
> mm/page_alloc.c | 70 ++++-----
> mm/swap.c | 50 +++----
> mm/vmscan.c | 226 +++++++++++++++++-------------
> mm/vmstat.c | 47 ++++---
> mm/workingset.c | 4 +-
> 29 files changed, 387 insertions(+), 300 deletions(-)
>
> diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
> index c4d5bf841a7f..9e389213580d 100644
> --- a/arch/tile/mm/pgtable.c
> +++ b/arch/tile/mm/pgtable.c
> @@ -45,10 +45,10 @@ void show_mem(unsigned int filter)
> struct zone *zone;
>
> pr_err("Active:%lu inactive:%lu dirty:%lu writeback:%lu unstable:%lu free:%lu\n slab:%lu mapped:%lu pagetables:%lu bounce:%lu pagecache:%lu swap:%lu\n",
> - (global_page_state(NR_ACTIVE_ANON) +
> - global_page_state(NR_ACTIVE_FILE)),
> - (global_page_state(NR_INACTIVE_ANON) +
> - global_page_state(NR_INACTIVE_FILE)),
> + (global_node_page_state(NR_ACTIVE_ANON) +
> + global_node_page_state(NR_ACTIVE_FILE)),
> + (global_node_page_state(NR_INACTIVE_ANON) +
> + global_node_page_state(NR_INACTIVE_FILE)),
> global_page_state(NR_FILE_DIRTY),
> global_page_state(NR_WRITEBACK),
> global_page_state(NR_UNSTABLE_NFS),
> diff --git a/drivers/base/node.c b/drivers/base/node.c
> index 92d8e090c5b3..b7f01a4a642d 100644
> --- a/drivers/base/node.c
> +++ b/drivers/base/node.c
> @@ -56,6 +56,7 @@ static ssize_t node_read_meminfo(struct device *dev,
> {
> int n;
> int nid = dev->id;
> + struct pglist_data *pgdat = NODE_DATA(nid);
> struct sysinfo i;
>
> si_meminfo_node(&i, nid);
> @@ -74,15 +75,15 @@ static ssize_t node_read_meminfo(struct device *dev,
> nid, K(i.totalram),
> nid, K(i.freeram),
> nid, K(i.totalram - i.freeram),
> - nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_ANON) +
> - sum_zone_node_page_state(nid, NR_ACTIVE_FILE)),
> - nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_ANON) +
> - sum_zone_node_page_state(nid, NR_INACTIVE_FILE)),
> - nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_ANON)),
> - nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_ANON)),
> - nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_FILE)),
> - nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_FILE)),
> - nid, K(sum_zone_node_page_state(nid, NR_UNEVICTABLE)),
> + nid, K(node_page_state(pgdat, NR_ACTIVE_ANON) +
> + node_page_state(pgdat, NR_ACTIVE_FILE)),
> + nid, K(node_page_state(pgdat, NR_INACTIVE_ANON) +
> + node_page_state(pgdat, NR_INACTIVE_FILE)),
> + nid, K(node_page_state(pgdat, NR_ACTIVE_ANON)),
> + nid, K(node_page_state(pgdat, NR_INACTIVE_ANON)),
> + nid, K(node_page_state(pgdat, NR_ACTIVE_FILE)),
> + nid, K(node_page_state(pgdat, NR_INACTIVE_FILE)),
> + nid, K(node_page_state(pgdat, NR_UNEVICTABLE)),
> nid, K(sum_zone_node_page_state(nid, NR_MLOCK)));
>
> #ifdef CONFIG_HIGHMEM
> diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
> index 24d2745e9437..93dbcc38eb0f 100644
> --- a/drivers/staging/android/lowmemorykiller.c
> +++ b/drivers/staging/android/lowmemorykiller.c
> @@ -72,10 +72,10 @@ static unsigned long lowmem_deathpending_timeout;
> static unsigned long lowmem_count(struct shrinker *s,
> struct shrink_control *sc)
> {
> - return global_page_state(NR_ACTIVE_ANON) +
> - global_page_state(NR_ACTIVE_FILE) +
> - global_page_state(NR_INACTIVE_ANON) +
> - global_page_state(NR_INACTIVE_FILE);
> + return global_node_page_state(NR_ACTIVE_ANON) +
> + global_node_page_state(NR_ACTIVE_FILE) +
> + global_node_page_state(NR_INACTIVE_ANON) +
> + global_node_page_state(NR_INACTIVE_FILE);
> }
>
> static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
> diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
> index c82794f20110..491a91717788 100644
> --- a/include/linux/backing-dev.h
> +++ b/include/linux/backing-dev.h
> @@ -197,7 +197,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
> }
>
> long congestion_wait(int sync, long timeout);
> -long wait_iff_congested(struct zone *zone, int sync, long timeout);
> +long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout);
> int pdflush_proc_obsolete(struct ctl_table *table, int write,
> void __user *buffer, size_t *lenp, loff_t *ppos);
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 104efa6874db..1927dcb6921e 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -340,7 +340,7 @@ static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
> struct lruvec *lruvec;
>
> if (mem_cgroup_disabled()) {
> - lruvec = &zone->lruvec;
> + lruvec = zone_lruvec(zone);
> goto out;
> }
>
> @@ -352,12 +352,12 @@ static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
> * we have to be prepared to initialize lruvec->zone here;
lruvec->pgdat
> * and if offlined then reonlined, we need to reinitialize it.
> */
> - if (unlikely(lruvec->zone != zone))
> - lruvec->zone = zone;
> + if (unlikely(lruvec->pgdat != zone->zone_pgdat))
> + lruvec->pgdat = zone->zone_pgdat;
> return lruvec;
> }
>
> -struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
> +struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
>
> bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
> struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
> @@ -438,7 +438,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
> int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
>
> void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
> - int nr_pages);
> + enum zone_type zid, int nr_pages);
>
> unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
> int nid, unsigned int lru_mask);
> @@ -613,13 +613,13 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
> static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
> struct mem_cgroup *memcg)
> {
> - return &zone->lruvec;
> + return zone_lruvec(zone);
> }
>
> static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
> - struct zone *zone)
> + struct pglist_data *pgdat)
> {
> - return &zone->lruvec;
> + return &pgdat->lruvec;
> }
>
> static inline bool mm_match_cgroup(struct mm_struct *mm,
> diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
> index 5bd29ba4f174..9aadcc781857 100644
> --- a/include/linux/mm_inline.h
> +++ b/include/linux/mm_inline.h
> @@ -23,25 +23,32 @@ static inline int page_is_file_cache(struct page *page)
> }
>
> static __always_inline void __update_lru_size(struct lruvec *lruvec,
> - enum lru_list lru, int nr_pages)
> + enum lru_list lru, enum zone_type zid,
> + int nr_pages)
> {
> - __mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, nr_pages);
> + struct pglist_data *pgdat = lruvec_pgdat(lruvec);
> +
> + __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
> + __mod_zone_page_state(&pgdat->node_zones[zid],
> + NR_ZONE_LRU_BASE + !!is_file_lru(lru),
> + nr_pages);
> }
>
> static __always_inline void update_lru_size(struct lruvec *lruvec,
> - enum lru_list lru, int nr_pages)
> + enum lru_list lru, enum zone_type zid,
> + int nr_pages)
> {
> #ifdef CONFIG_MEMCG
> - mem_cgroup_update_lru_size(lruvec, lru, nr_pages);
> + mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages);
> #else
> - __update_lru_size(lruvec, lru, nr_pages);
> + __update_lru_size(lruvec, lru, zid, nr_pages);
> #endif
> }
>
> static __always_inline void add_page_to_lru_list(struct page *page,
> struct lruvec *lruvec, enum lru_list lru)
> {
> - update_lru_size(lruvec, lru, hpage_nr_pages(page));
> + update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page));
> list_add(&page->lru, &lruvec->lists[lru]);
> }
>
> @@ -49,7 +56,7 @@ static __always_inline void del_page_from_lru_list(struct page *page,
> struct lruvec *lruvec, enum lru_list lru)
> {
> list_del(&page->lru);
> - update_lru_size(lruvec, lru, -hpage_nr_pages(page));
> + update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page));
> }
>
> /**
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 2d5087e3c034..258c20758e80 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -111,12 +111,9 @@ enum zone_stat_item {
> /* First 128 byte cacheline (assuming 64 bit words) */
> NR_FREE_PAGES,
> NR_ALLOC_BATCH,
> - NR_LRU_BASE,
> - NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
> - NR_ACTIVE_ANON, /* " " " " " */
> - NR_INACTIVE_FILE, /* " " " " " */
> - NR_ACTIVE_FILE, /* " " " " " */
> - NR_UNEVICTABLE, /* " " " " " */
> + NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
> + NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
> + NR_ZONE_LRU_FILE,
> NR_MLOCK, /* mlock()ed pages found and moved off LRU */
> NR_ANON_PAGES, /* Mapped anonymous pages */
> NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
> @@ -134,12 +131,9 @@ enum zone_stat_item {
> NR_VMSCAN_WRITE,
> NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */
> NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */
> - NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
> - NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
> NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */
> NR_DIRTIED, /* page dirtyings since bootup */
> NR_WRITTEN, /* page writings since bootup */
> - NR_PAGES_SCANNED, /* pages scanned since last reclaim */
> #if IS_ENABLED(CONFIG_ZSMALLOC)
> NR_ZSPAGES, /* allocated in zsmalloc */
> #endif
> @@ -161,6 +155,15 @@ enum zone_stat_item {
> NR_VM_ZONE_STAT_ITEMS };
>
> enum node_stat_item {
> + NR_LRU_BASE,
> + NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
> + NR_ACTIVE_ANON, /* " " " " " */
> + NR_INACTIVE_FILE, /* " " " " " */
> + NR_ACTIVE_FILE, /* " " " " " */
> + NR_UNEVICTABLE, /* " " " " " */
> + NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
> + NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
> + NR_PAGES_SCANNED, /* pages scanned since last reclaim */
> NR_VM_NODE_STAT_ITEMS
> };
>
> @@ -219,7 +222,7 @@ struct lruvec {
> /* Evictions & activations on the inactive file list */
> atomic_long_t inactive_age;
> #ifdef CONFIG_MEMCG
> - struct zone *zone;
> + struct pglist_data *pgdat;
> #endif
> };
>
> @@ -357,13 +360,6 @@ struct zone {
> #ifdef CONFIG_NUMA
> int node;
> #endif
> -
> - /*
> - * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
> - * this zone's LRU. Maintained by the pageout code.
> - */
> - unsigned int inactive_ratio;
> -
> struct pglist_data *zone_pgdat;
> struct per_cpu_pageset __percpu *pageset;
>
> @@ -495,9 +491,6 @@ struct zone {
>
> /* Write-intensive fields used by page reclaim */
trivial:
We moved lru_lock and lruvec to pgdat so I'm not sure we need ZONE_PADDING,
still.
>
> - /* Fields commonly accessed by the page reclaim scanner */
> - struct lruvec lruvec;
> -
> /*
> * When free pages are below this point, additional steps are taken
> * when reading the number of free pages to avoid per-cpu counter
> @@ -537,17 +530,20 @@ struct zone {
>
> enum zone_flags {
> ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */
> - ZONE_CONGESTED, /* zone has many dirty pages backed by
> + ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
> +};
> +
> +enum pgdat_flags {
> + PGDAT_CONGESTED, /* zone has many dirty pages backed by
node or pgdat, whatever.
> * a congested BDI
> */
> - ZONE_DIRTY, /* reclaim scanning has recently found
> + PGDAT_DIRTY, /* reclaim scanning has recently found
> * many dirty file pages at the tail
> * of the LRU.
> */
> - ZONE_WRITEBACK, /* reclaim scanning has recently found
> + PGDAT_WRITEBACK, /* reclaim scanning has recently found
> * many pages under writeback
> */
> - ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
> };
>
> static inline unsigned long zone_end_pfn(const struct zone *zone)
> @@ -701,12 +697,26 @@ typedef struct pglist_data {
> unsigned long first_deferred_pfn;
> #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
>
> +
Unnecessary change.
> #ifdef CONFIG_TRANSPARENT_HUGEPAGE
> spinlock_t split_queue_lock;
> struct list_head split_queue;
> unsigned long split_queue_len;
> #endif
>
> + /* Fields commonly accessed by the page reclaim scanner */
> + struct lruvec lruvec;
> +
> + /*
> + * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
> + * this node's LRU. Maintained by the pageout code.
> + */
> + unsigned int inactive_ratio;
> +
> + unsigned long flags;
> +
> + ZONE_PADDING(_pad2_)
> +
> /* Per-node vmstats */
> struct per_cpu_nodestat __percpu *per_cpu_nodestats;
> atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS];
> @@ -728,6 +738,11 @@ static inline spinlock_t *zone_lru_lock(struct zone *zone)
> return &zone->zone_pgdat->lru_lock;
> }
>
> +static inline struct lruvec *zone_lruvec(struct zone *zone)
> +{
> + return &zone->zone_pgdat->lruvec;
> +}
> +
> static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
> {
> return pgdat->node_start_pfn + pgdat->node_spanned_pages;
> @@ -779,12 +794,12 @@ extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
>
> extern void lruvec_init(struct lruvec *lruvec);
>
> -static inline struct zone *lruvec_zone(struct lruvec *lruvec)
> +static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
> {
> #ifdef CONFIG_MEMCG
> - return lruvec->zone;
> + return lruvec->pgdat;
> #else
> - return container_of(lruvec, struct zone, lruvec);
> + return container_of(lruvec, struct pglist_data, lruvec);
> #endif
> }
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 0af2bb2028fd..c82f916008b7 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -317,6 +317,7 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
>
> /* linux/mm/vmscan.c */
> extern unsigned long zone_reclaimable_pages(struct zone *zone);
> +extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);
> extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
> gfp_t gfp_mask, nodemask_t *mask);
> extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
> diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
> index 42604173f122..1798ff542517 100644
> --- a/include/linux/vm_event_item.h
> +++ b/include/linux/vm_event_item.h
> @@ -26,11 +26,11 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
> PGFREE, PGACTIVATE, PGDEACTIVATE,
> PGFAULT, PGMAJFAULT,
> PGLAZYFREED,
> - FOR_ALL_ZONES(PGREFILL),
> - FOR_ALL_ZONES(PGSTEAL_KSWAPD),
> - FOR_ALL_ZONES(PGSTEAL_DIRECT),
> - FOR_ALL_ZONES(PGSCAN_KSWAPD),
> - FOR_ALL_ZONES(PGSCAN_DIRECT),
> + PGREFILL,
> + PGSTEAL_KSWAPD,
> + PGSTEAL_DIRECT,
> + PGSCAN_KSWAPD,
> + PGSCAN_DIRECT,
> PGSCAN_DIRECT_THROTTLE,
> #ifdef CONFIG_NUMA
> PGSCAN_ZONE_RECLAIM_FAILED,
> diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
> index d1744aa3ab9c..ced0c3e9da88 100644
> --- a/include/linux/vmstat.h
> +++ b/include/linux/vmstat.h
> @@ -178,6 +178,23 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
> return x;
> }
>
> +static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat,
> + enum zone_stat_item item)
enum node_stat_item
> +{
> + long x = atomic_long_read(&pgdat->vm_stat[item]);
> +
> +#ifdef CONFIG_SMP
> + int cpu;
> + for_each_online_cpu(cpu)
> + x += per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->vm_node_stat_diff[item];
> +
> + if (x < 0)
> + x = 0;
> +#endif
> + return x;
> +}
> +
> +
> #ifdef CONFIG_NUMA
> extern unsigned long sum_zone_node_page_state(int node,
> enum zone_stat_item item);
<snip>
> @@ -1147,9 +1147,9 @@ static void free_one_page(struct zone *zone,
> {
> unsigned long nr_scanned;
> spin_lock(&zone->lock);
> - nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
> + nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
> if (nr_scanned)
> - __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
> + __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
>
> if (unlikely(has_isolate_pageblock(zone) ||
> is_migrate_isolate(migratetype))) {
> @@ -3526,7 +3526,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
>
> available = reclaimable = zone_reclaimable_pages(zone);
> available -= DIV_ROUND_UP(no_progress_loops * available,
> - MAX_RECLAIM_RETRIES);
> + MAX_RECLAIM_RETRIES);
Unnecessary change.
> available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
>
> /*
> @@ -4331,6 +4331,7 @@ void show_free_areas(unsigned int filter)
<snip.
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index e7ffcd259cc4..86a523a761c9 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -191,26 +191,42 @@ static bool sane_reclaim(struct scan_control *sc)
> }
> #endif
>
> +/*
> + * This misses isolated pages which are not accounted for to save counters.
> + * As the data only determines if reclaim or compaction continues, it is
> + * not expected that isolated pages will be a dominating factor.
When I read below commit, one of the reason it was introduced is whether we
should continue to reclaim page or not.
At that time, several people wanted it by my guessing [suggested|acked]-by
so I think we should notice it to them.
Michal?
[9f6c399ddc36, consider isolated pages in zone_reclaimable_pages],
> + */
> unsigned long zone_reclaimable_pages(struct zone *zone)
> {
> unsigned long nr;
>
> - nr = zone_page_state_snapshot(zone, NR_ACTIVE_FILE) +
> - zone_page_state_snapshot(zone, NR_INACTIVE_FILE) +
> - zone_page_state_snapshot(zone, NR_ISOLATED_FILE);
> + nr = zone_page_state_snapshot(zone, NR_ZONE_LRU_FILE);
> + if (get_nr_swap_pages() > 0)
> + nr += zone_page_state_snapshot(zone, NR_ZONE_LRU_ANON);
> +
> + return nr;
> +}
> +
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-01 20:01 ` [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman
@ 2016-07-05 5:59 ` Minchan Kim
2016-07-05 10:26 ` Mel Gorman
2016-07-07 1:20 ` Joonsoo Kim
1 sibling, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-05 5:59 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:16PM +0100, Mel Gorman wrote:
> kswapd goes through some complex steps trying to figure out if it should
> stay awake based on the classzone_idx and the requested order. It is
> unnecessarily complex and passes in an invalid classzone_idx to
> balance_pgdat(). What matters most of all is whether a larger order has
> been requsted and whether kswapd successfully reclaimed at the previous
> order. This patch irons out the logic to check just that and the end
> result is less headache inducing.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
> include/linux/mmzone.h | 5 ++-
> mm/memory_hotplug.c | 5 ++-
> mm/page_alloc.c | 2 +-
> mm/vmscan.c | 102 ++++++++++++++++++++++++++-----------------------
> 4 files changed, 62 insertions(+), 52 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 258c20758e80..eb74e63df5cf 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -667,8 +667,9 @@ typedef struct pglist_data {
> wait_queue_head_t pfmemalloc_wait;
> struct task_struct *kswapd; /* Protected by
> mem_hotplug_begin/end() */
> - int kswapd_max_order;
> - enum zone_type classzone_idx;
> + int kswapd_order;
> + enum zone_type kswapd_classzone_idx;
> +
> #ifdef CONFIG_COMPACTION
> int kcompactd_max_order;
> enum zone_type kcompactd_classzone_idx;
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index c5278360ca66..065140ecd081 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -1209,9 +1209,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
>
> arch_refresh_nodedata(nid, pgdat);
> } else {
> - /* Reset the nr_zones and classzone_idx to 0 before reuse */
> + /* Reset the nr_zones, order and classzone_idx before reuse */
> pgdat->nr_zones = 0;
> - pgdat->classzone_idx = 0;
> + pgdat->kswapd_order = 0;
> + pgdat->kswapd_classzone_idx = 0;
> }
>
> /* we can use NODE_DATA(nid) from here */
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 59e4463e5dce..f58548139bf2 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -6084,7 +6084,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
> unsigned long end_pfn = 0;
>
> /* pg_data_t should be reset to zero when it's allocated */
> - WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
> + WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
>
> reset_deferred_meminit(pgdat);
> pgdat->node_id = nid;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index a52167eabc96..b524d3b72527 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2762,7 +2762,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
>
> /* kswapd must be awake if processes are being throttled */
> if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
> - pgdat->classzone_idx = min(pgdat->classzone_idx,
> + pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
> (enum zone_type)ZONE_NORMAL);
> wake_up_interruptible(&pgdat->kswapd_wait);
> }
> @@ -3238,8 +3238,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> return sc.order;
> }
>
> -static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> - int classzone_idx, int balanced_classzone_idx)
> +static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
> + int classzone_idx)
> {
> long remaining = 0;
> DEFINE_WAIT(wait);
> @@ -3249,9 +3249,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
>
> prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
>
> + /*
> + * If kswapd has not been woken recently, then kswapd goes fully
> + * to sleep. kcompactd may still need to wake if the original
> + * request was high-order.
> + */
> + if (classzone_idx == -1) {
> + wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
> + classzone_idx = MAX_NR_ZONES - 1;
> + goto full_sleep;
> + }
> +
> /* Try to sleep for a short interval */
> - if (prepare_kswapd_sleep(pgdat, order, remaining,
> - balanced_classzone_idx)) {
> + if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
Just trivial but this is clean up patch so I suggest one.
If it doesn't help readability, just ignore, please.
This(ie, first prepare_kswapd_sleep always get 0 remaining value so
it's pointless argument for the function. We could remove it and
check it before second prepare_kswapd_sleep call.
full_sleep:
/*
* After a short sleep, check if it was a premature sleep. If not, then
* go fully to sleep until explicitly woken up.
*/
if (!remaining &&
prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) {
trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
> /*
> * Compaction records what page blocks it recently failed to
> * isolate pages from and skips them in the future scanning.
> @@ -3264,19 +3274,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> * We have freed the memory, now we should compact it to make
> * allocation of the requested order possible.
> */
> - wakeup_kcompactd(pgdat, order, classzone_idx);
> + wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
>
> remaining = schedule_timeout(HZ/10);
> finish_wait(&pgdat->kswapd_wait, &wait);
> prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
> }
>
> +full_sleep:
> /*
> * After a short sleep, check if it was a premature sleep. If not, then
> * go fully to sleep until explicitly woken up.
> */
> - if (prepare_kswapd_sleep(pgdat, order, remaining,
> - balanced_classzone_idx)) {
> + if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
> trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
>
> /*
> @@ -3317,9 +3327,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> */
> static int kswapd(void *p)
> {
> - unsigned long order, new_order;
> - int classzone_idx, new_classzone_idx;
> - int balanced_classzone_idx;
> + unsigned int alloc_order, reclaim_order, classzone_idx;
> pg_data_t *pgdat = (pg_data_t*)p;
> struct task_struct *tsk = current;
>
> @@ -3349,38 +3357,26 @@ static int kswapd(void *p)
> tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
> set_freezable();
>
> - order = new_order = 0;
> - classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
> - balanced_classzone_idx = classzone_idx;
> + pgdat->kswapd_order = alloc_order = reclaim_order = 0;
> + pgdat->kswapd_classzone_idx = classzone_idx = -1;
> for ( ; ; ) {
> bool ret;
>
> +kswapd_try_sleep:
> + kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
> + classzone_idx);
> +
> /*
> - * While we were reclaiming, there might have been another
> - * wakeup, so check the values.
> + * Read the new order and classzone_idx which may be -1 if
> + * kswapd_try_to_sleep() woke up after a short timeout instead
> + * of being woken by the page allocator.
> */
> - new_order = pgdat->kswapd_max_order;
> - new_classzone_idx = pgdat->classzone_idx;
> - pgdat->kswapd_max_order = 0;
> - pgdat->classzone_idx = pgdat->nr_zones - 1;
> -
> - if (order < new_order || classzone_idx > new_classzone_idx) {
> - /*
> - * Don't sleep if someone wants a larger 'order'
> - * allocation or has tigher zone constraints
> - */
> - order = new_order;
> - classzone_idx = new_classzone_idx;
> - } else {
> - kswapd_try_to_sleep(pgdat, order, classzone_idx,
> - balanced_classzone_idx);
> - order = pgdat->kswapd_max_order;
> - classzone_idx = pgdat->classzone_idx;
> - new_order = order;
> - new_classzone_idx = classzone_idx;
> - pgdat->kswapd_max_order = 0;
> - pgdat->classzone_idx = pgdat->nr_zones - 1;
> - }
> + alloc_order = reclaim_order = pgdat->kswapd_order;
> + classzone_idx = pgdat->kswapd_classzone_idx;
> + if (classzone_idx == -1)
> + classzone_idx = MAX_NR_ZONES - 1;
> + pgdat->kswapd_order = 0;
> + pgdat->kswapd_classzone_idx = -1;
>
> ret = try_to_freeze();
> if (kthread_should_stop())
> @@ -3390,12 +3386,24 @@ static int kswapd(void *p)
> * We can speed up thawing tasks if we don't call balance_pgdat
> * after returning from the refrigerator
> */
> - if (!ret) {
> - trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
> + if (ret)
> + continue;
>
> - /* return value ignored until next patch */
> - balance_pgdat(pgdat, order, classzone_idx);
> - }
> + /*
> + * Reclaim begins at the requested order but if a high-order
> + * reclaim fails then kswapd falls back to reclaiming for
> + * order-0. If that happens, kswapd will consider sleeping
> + * for the order it finished reclaiming at (reclaim_order)
> + * but kcompactd is woken to compact for the original
> + * request (alloc_order).
> + */
> + trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order);
> + reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
> + if (reclaim_order < alloc_order)
> + goto kswapd_try_sleep;
> +
> + alloc_order = reclaim_order = pgdat->kswapd_order;
> + classzone_idx = pgdat->kswapd_classzone_idx;
> }
>
> tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
> @@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
> return;
> pgdat = zone->zone_pgdat;
> - if (pgdat->kswapd_max_order < order) {
> - pgdat->kswapd_max_order = order;
> - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
> - }
> + if (pgdat->kswapd_classzone_idx == -1)
> + pgdat->kswapd_classzone_idx = classzone_idx;
It's tricky. Couldn't we change kswapd_classzone_idx to integer type
and remove if above if condition?
> + pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
> + pgdat->kswapd_order = max(pgdat->kswapd_order, order);
> if (!waitqueue_active(&pgdat->kswapd_wait))
> return;
> if (zone_balanced(zone, order, 0))
> --
> 2.6.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone
2016-07-01 20:01 ` [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone Mel Gorman
@ 2016-07-05 6:11 ` Minchan Kim
2016-07-05 10:38 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-05 6:11 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:19PM +0100, Mel Gorman wrote:
> kswapd scans from highest to lowest for a zone that requires balancing.
> This was necessary when reclaim was per-zone to fairly age pages on lower
> zones. Now that we are reclaiming on a per-node basis, any eligible zone
> can be used and pages will still be aged fairly. This patch avoids
> reclaiming excessively unless buffer_heads are over the limit and it's
> necessary to reclaim from a higher zone than requested by the waker of
> kswapd to relieve low memory pressure.
>
> [hillf.zj@alibaba-inc.com: Force kswapd reclaim no more than needed]
> Link: http://lkml.kernel.org/r/1466518566-30034-12-git-send-email-mgorman@techsingularity.net
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Signed-off-by: Hillf Danton <hillf.zj@alibaba-inc.com>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
> mm/vmscan.c | 56 ++++++++++++++++++++++++--------------------------------
> 1 file changed, 24 insertions(+), 32 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 911142d25de2..2f898ba2ee2e 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -3141,31 +3141,36 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
>
> sc.nr_reclaimed = 0;
>
> - /* Scan from the highest requested zone to dma */
> - for (i = classzone_idx; i >= 0; i--) {
> - zone = pgdat->node_zones + i;
> - if (!populated_zone(zone))
> - continue;
> -
> - /*
> - * If the number of buffer_heads in the machine
> - * exceeds the maximum allowed level and this node
> - * has a highmem zone, force kswapd to reclaim from
> - * it to relieve lowmem pressure.
> - */
> - if (buffer_heads_over_limit && is_highmem_idx(i)) {
> - classzone_idx = i;
> - break;
> - }
> + /*
> + * If the number of buffer_heads in the machine exceeds the
> + * maximum allowed level then reclaim from all zones. This is
> + * not specific to highmem as highmem may not exist but it is
> + * it is expected that buffer_heads are stripped in writeback.
> + */
> + if (buffer_heads_over_limit) {
> + for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
> + zone = pgdat->node_zones + i;
> + if (!populated_zone(zone))
> + continue;
>
> - if (!zone_balanced(zone, order, 0)) {
> classzone_idx = i;
> break;
> }
> }
>
> - if (i < 0)
> - goto out;
> + /*
> + * Only reclaim if there are no eligible zones. Check from
> + * high to low zone to avoid prematurely clearing pgdat
> + * congested state.
I cannot understand "prematurely clearing pgdat congested state".
Could you add more words to clear it out?
> + */
> + for (i = classzone_idx; i >= 0; i--) {
> + zone = pgdat->node_zones + i;
> + if (!populated_zone(zone))
> + continue;
> +
> + if (zone_balanced(zone, sc.order, classzone_idx))
If buffer_head is over limit, old logic force to reclaim highmem but
this zone_balanced logic will prevent it.
> + goto out;
> + }
>
> /*
> * Do some background aging of the anon list, to give
> @@ -3211,19 +3216,6 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> break;
>
> /*
> - * Stop reclaiming if any eligible zone is balanced and clear
> - * node writeback or congested.
> - */
> - for (i = 0; i <= classzone_idx; i++) {
> - zone = pgdat->node_zones + i;
> - if (!populated_zone(zone))
> - continue;
> -
> - if (zone_balanced(zone, sc.order, classzone_idx))
> - goto out;
> - }
> -
> - /*
> * Raise priority if scanning rate is too low or there was no
> * progress in reclaiming pages
> */
> --
> 2.6.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric
2016-07-01 20:01 ` [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric Mel Gorman
@ 2016-07-05 6:24 ` Minchan Kim
2016-07-05 10:40 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-05 6:24 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:20PM +0100, Mel Gorman wrote:
> Earlier patches focused on having direct reclaim and kswapd use data that
> is node-centric for reclaiming but shrink_node() itself still uses too
> much zone information. This patch removes unnecessary zone-based
> information with the most important decision being whether to continue
> reclaim or not. Some memcg APIs are adjusted as a result even though
> memcg itself still uses some zone information.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Michal Hocko <mhocko@suse.com>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
> include/linux/memcontrol.h | 19 ++++++++--------
> include/linux/mmzone.h | 4 ++--
> include/linux/swap.h | 2 +-
> mm/memcontrol.c | 4 ++--
> mm/page_alloc.c | 2 +-
> mm/vmscan.c | 57 ++++++++++++++++++++++++++--------------------
> mm/workingset.c | 6 ++---
> 7 files changed, 51 insertions(+), 43 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 1927dcb6921e..48b43c709ed7 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -325,22 +325,23 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
> }
>
> /**
> - * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
> + * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
> + * @node: node of the wanted lruvec
> * @zone: zone of the wanted lruvec
> * @memcg: memcg of the wanted lruvec
> *
> - * Returns the lru list vector holding pages for the given @zone and
> - * @mem. This can be the global zone lruvec, if the memory controller
> + * Returns the lru list vector holding pages for a given @node or a given
> + * @memcg and @zone. This can be the node lruvec, if the memory controller
> * is disabled.
> */
> -static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
> - struct mem_cgroup *memcg)
> +static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
> + struct zone *zone, struct mem_cgroup *memcg)
> {
> struct mem_cgroup_per_zone *mz;
> struct lruvec *lruvec;
>
> if (mem_cgroup_disabled()) {
> - lruvec = zone_lruvec(zone);
> + lruvec = node_lruvec(pgdat);
> goto out;
> }
>
> @@ -610,10 +611,10 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
> {
> }
>
> -static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
> - struct mem_cgroup *memcg)
> +static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
> + struct zone *zone, struct mem_cgroup *memcg)
> {
> - return zone_lruvec(zone);
> + return node_lruvec(pgdat);
> }
>
> static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index eb74e63df5cf..f88cbbb476c8 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -739,9 +739,9 @@ static inline spinlock_t *zone_lru_lock(struct zone *zone)
> return &zone->zone_pgdat->lru_lock;
> }
>
> -static inline struct lruvec *zone_lruvec(struct zone *zone)
> +static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
> {
> - return &zone->zone_pgdat->lruvec;
> + return &pgdat->lruvec;
> }
>
> static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 916e2eddecd6..0ad616d7c381 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -316,7 +316,7 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
> unsigned long nr_pages,
> gfp_t gfp_mask,
> bool may_swap);
> -extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
> +extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
> gfp_t gfp_mask, bool noswap,
> struct zone *zone,
> unsigned long *nr_scanned);
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 50c86ad121bc..c9ebec98e92a 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1432,8 +1432,8 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
> }
> continue;
> }
> - total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
> - zone, &nr_scanned);
> + total += mem_cgroup_shrink_node(victim, gfp_mask, false,
> + zone, &nr_scanned);
> *total_scanned += nr_scanned;
> if (!soft_limit_excess(root_memcg))
> break;
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index f58548139bf2..b76ea2527c09 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -5954,6 +5954,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
> #endif
> pgdat_page_ext_init(pgdat);
> spin_lock_init(&pgdat->lru_lock);
> + lruvec_init(node_lruvec(pgdat));
>
> for (j = 0; j < MAX_NR_ZONES; j++) {
> struct zone *zone = pgdat->node_zones + j;
> @@ -6016,7 +6017,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
> /* For bootup, initialized properly in watermark setup */
> mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
>
> - lruvec_init(zone_lruvec(zone));
> if (!size)
> continue;
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 2f898ba2ee2e..b8e0f76b6e00 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2226,10 +2226,11 @@ static inline void init_tlb_ubc(void)
> /*
> * This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
per-node freer
trivial:
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats
2016-07-04 23:50 ` Minchan Kim
@ 2016-07-05 8:14 ` Mel Gorman
2016-07-06 0:15 ` Minchan Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-05 8:14 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Tue, Jul 05, 2016 at 08:50:18AM +0900, Minchan Kim wrote:
> > @@ -172,13 +174,17 @@ void refresh_zone_stat_thresholds(void)
> > int threshold;
> >
> > for_each_populated_zone(zone) {
> > + struct pglist_data *pgdat = zone->zone_pgdat;
> > unsigned long max_drift, tolerate_drift;
> >
> > threshold = calculate_normal_threshold(zone);
> >
> > - for_each_online_cpu(cpu)
> > + for_each_online_cpu(cpu) {
> > per_cpu_ptr(zone->pageset, cpu)->stat_threshold
> > = threshold;
> > + per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
> > + = threshold;
> > + }
>
> I didn't see other patches yet so it might fix it then.
>
> per_cpu_nodestats is per node not zone but it use per-zone threshold
> and even overwritten by next zones. I don't think it's not intended.
It was intended that the threshold from one zone would be used but now
that you point it out, it would use the threshold for the smallest zone
in the node which is sub-optimal. I applied the patch below on top to
use the threshold from the largest zone. I considered using the sum of
all thresholds but feared it might allow too much per-cpu drift. It can
be switched to the sum if we find a case where vmstat updates are too
high.
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 90b0737ee4be..3345d396a99b 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -169,10 +169,18 @@ int calculate_normal_threshold(struct zone *zone)
*/
void refresh_zone_stat_thresholds(void)
{
+ struct pglist_data *pgdat;
struct zone *zone;
int cpu;
int threshold;
+ /* Zero current pgdat thresholds */
+ for_each_online_pgdat(pgdat) {
+ for_each_online_cpu(cpu) {
+ per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold = 0;
+ }
+ }
+
for_each_populated_zone(zone) {
struct pglist_data *pgdat = zone->zone_pgdat;
unsigned long max_drift, tolerate_drift;
@@ -180,10 +188,15 @@ void refresh_zone_stat_thresholds(void)
threshold = calculate_normal_threshold(zone);
for_each_online_cpu(cpu) {
+ int pgdat_threshold;
+
per_cpu_ptr(zone->pageset, cpu)->stat_threshold
= threshold;
+
+ /* Base nodestat threshold on the largest populated zone. */
+ pgdat_threshold = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold;
per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
- = threshold;
+ = max(threshold, pgdat_threshold);
}
/*
--
Mel Gorman
SUSE Labs
^ permalink raw reply related [flat|nested] 90+ messages in thread
* Re: [PATCH 03/31] mm, vmscan: move LRU lists to node
2016-07-05 1:19 ` Minchan Kim
@ 2016-07-05 10:14 ` Mel Gorman
0 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-05 10:14 UTC (permalink / raw)
To: Minchan Kim
Cc: Michal Hocko, Andrew Morton, Linux-MM, Rik van Riel,
Vlastimil Babka, Johannes Weiner, LKML
On Tue, Jul 05, 2016 at 10:19:57AM +0900, Minchan Kim wrote:
> On Fri, Jul 01, 2016 at 09:01:11PM +0100, Mel Gorman wrote:
> > This moves the LRU lists from the zone to the node and related data such
> > as counters, tracing, congestion tracking and writeback tracking.
> > Unfortunately, due to reclaim and compaction retry logic, it is necessary
> > to account for the number of LRU pages on both zone and node logic. Most
> > reclaim logic is based on the node counters but the retry logic uses the
> > zone counters which do not distinguish inactive and inactive sizes. It
>
> active
>
Fixed.
> > @@ -352,12 +352,12 @@ static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
> > * we have to be prepared to initialize lruvec->zone here;
>
> lruvec->pgdat
>
Fixed.
> > @@ -357,13 +360,6 @@ struct zone {
> > #ifdef CONFIG_NUMA
> > int node;
> > #endif
> > -
> > - /*
> > - * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
> > - * this zone's LRU. Maintained by the pageout code.
> > - */
> > - unsigned int inactive_ratio;
> > -
> > struct pglist_data *zone_pgdat;
> > struct per_cpu_pageset __percpu *pageset;
> >
> > @@ -495,9 +491,6 @@ struct zone {
> >
> > /* Write-intensive fields used by page reclaim */
>
> trivial:
> We moved lru_lock and lruvec to pgdat so I'm not sure we need ZONE_PADDING,
> still.
>
It still separates the page allocator structures from compaction and
vmstats. The comment is misleading so I added a patch to clarify what
the padding is doing.
> >
> > - /* Fields commonly accessed by the page reclaim scanner */
> > - struct lruvec lruvec;
> > -
> > /*
> > * When free pages are below this point, additional steps are taken
> > * when reading the number of free pages to avoid per-cpu counter
> > @@ -537,17 +530,20 @@ struct zone {
> >
> > enum zone_flags {
> > ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */
> > - ZONE_CONGESTED, /* zone has many dirty pages backed by
> > + ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
> > +};
> > +
>
> > +enum pgdat_flags {
> > + PGDAT_CONGESTED, /* zone has many dirty pages backed by
>
> node or pgdat, whatever.
>
Fixed.
> > * a congested BDI
> > */
> > - ZONE_DIRTY, /* reclaim scanning has recently found
> > + PGDAT_DIRTY, /* reclaim scanning has recently found
> > * many dirty file pages at the tail
> > * of the LRU.
> > */
> > - ZONE_WRITEBACK, /* reclaim scanning has recently found
> > + PGDAT_WRITEBACK, /* reclaim scanning has recently found
> > * many pages under writeback
> > */
> > - ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
> > };
> >
> > static inline unsigned long zone_end_pfn(const struct zone *zone)
> > @@ -701,12 +697,26 @@ typedef struct pglist_data {
> > unsigned long first_deferred_pfn;
> > #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
> >
> > +
>
> Unnecessary change.
>
Fixed.
> > diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
> > index d1744aa3ab9c..ced0c3e9da88 100644
> > --- a/include/linux/vmstat.h
> > +++ b/include/linux/vmstat.h
> > @@ -178,6 +178,23 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
> > return x;
> > }
> >
> > +static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat,
> > + enum zone_stat_item item)
>
> enum node_stat_item
>
Fixed
> > @@ -1147,9 +1147,9 @@ static void free_one_page(struct zone *zone,
> > {
> > unsigned long nr_scanned;
> > spin_lock(&zone->lock);
> > - nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
> > + nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
> > if (nr_scanned)
> > - __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
> > + __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
> >
> > if (unlikely(has_isolate_pageblock(zone) ||
> > is_migrate_isolate(migratetype))) {
> > @@ -3526,7 +3526,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
> >
> > available = reclaimable = zone_reclaimable_pages(zone);
> > available -= DIV_ROUND_UP(no_progress_loops * available,
> > - MAX_RECLAIM_RETRIES);
> > + MAX_RECLAIM_RETRIES);
>
> Unnecessary change.
>
Fixed.
> > available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
> >
> > /*
> > @@ -4331,6 +4331,7 @@ void show_free_areas(unsigned int filter)
>
> <snip.
>
> > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > index e7ffcd259cc4..86a523a761c9 100644
> > --- a/mm/vmscan.c
> > +++ b/mm/vmscan.c
> > @@ -191,26 +191,42 @@ static bool sane_reclaim(struct scan_control *sc)
> > }
> > #endif
> >
> > +/*
> > + * This misses isolated pages which are not accounted for to save counters.
> > + * As the data only determines if reclaim or compaction continues, it is
> > + * not expected that isolated pages will be a dominating factor.
>
> When I read below commit, one of the reason it was introduced is whether we
> should continue to reclaim page or not.
> At that time, several people wanted it by my guessing [suggested|acked]-by
> so I think we should notice it to them.
>
> Michal?
>
Ultimately this gets fixed up at the end of the series when
zone_reclaimable_pages gets removed again to avoid double accounting.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-05 5:59 ` Minchan Kim
@ 2016-07-05 10:26 ` Mel Gorman
2016-07-06 0:30 ` Minchan Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-05 10:26 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Tue, Jul 05, 2016 at 02:59:31PM +0900, Minchan Kim wrote:
> > @@ -3249,9 +3249,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> >
> > prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
> >
> > + /*
> > + * If kswapd has not been woken recently, then kswapd goes fully
> > + * to sleep. kcompactd may still need to wake if the original
> > + * request was high-order.
> > + */
> > + if (classzone_idx == -1) {
> > + wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
> > + classzone_idx = MAX_NR_ZONES - 1;
> > + goto full_sleep;
> > + }
> > +
> > /* Try to sleep for a short interval */
> > - if (prepare_kswapd_sleep(pgdat, order, remaining,
> > - balanced_classzone_idx)) {
> > + if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
>
>
> Just trivial but this is clean up patch so I suggest one.
> If it doesn't help readability, just ignore, please.
>
> This(ie, first prepare_kswapd_sleep always get 0 remaining value so
> it's pointless argument for the function. We could remove it and
> check it before second prepare_kswapd_sleep call.
>
Yeah, fair point. I added a new patch that does this near the end of
the series with the other patches that avoid unnecessarily passing
parameters.
> > @@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> > if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
> > return;
> > pgdat = zone->zone_pgdat;
> > - if (pgdat->kswapd_max_order < order) {
> > - pgdat->kswapd_max_order = order;
> > - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
> > - }
> > + if (pgdat->kswapd_classzone_idx == -1)
> > + pgdat->kswapd_classzone_idx = classzone_idx;
>
> It's tricky. Couldn't we change kswapd_classzone_idx to integer type
> and remove if above if condition?
>
It's tricky and not necessarily better overall. It's perfectly possible
to be woken up for zone index 0 so it's changing -1 to another magic
value.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone
2016-07-05 6:11 ` Minchan Kim
@ 2016-07-05 10:38 ` Mel Gorman
2016-07-06 1:25 ` Minchan Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-05 10:38 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Tue, Jul 05, 2016 at 03:11:17PM +0900, Minchan Kim wrote:
> > - if (i < 0)
> > - goto out;
> > + /*
> > + * Only reclaim if there are no eligible zones. Check from
> > + * high to low zone to avoid prematurely clearing pgdat
> > + * congested state.
>
> I cannot understand "prematurely clearing pgdat congested state".
> Could you add more words to clear it out?
>
It's surprisingly difficult to concisely explain. Is this any better?
/*
* Only reclaim if there are no eligible zones. Check from
* high to low zone as allocations prefer higher zones.
* Scanning from low to high zone would allow congestion to be
* cleared during a very small window when a small low
* zone was balanced even under extreme pressure when the
* overall node may be congested.
*/
> > + */
> > + for (i = classzone_idx; i >= 0; i--) {
> > + zone = pgdat->node_zones + i;
> > + if (!populated_zone(zone))
> > + continue;
> > +
> > + if (zone_balanced(zone, sc.order, classzone_idx))
>
> If buffer_head is over limit, old logic force to reclaim highmem but
> this zone_balanced logic will prevent it.
>
The old logic was always busted on 64-bit because is_highmem would always
be 0. The original intent appears to be that buffer_heads_over_limit
would release the buffers when pages went inactive. There are a number
of things we treated inconsistently that get fixed up in the series and
buffer_heads_over_limit is one of them.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric
2016-07-05 6:24 ` Minchan Kim
@ 2016-07-05 10:40 ` Mel Gorman
0 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-05 10:40 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Tue, Jul 05, 2016 at 03:24:36PM +0900, Minchan Kim wrote:
> > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > index 2f898ba2ee2e..b8e0f76b6e00 100644
> > --- a/mm/vmscan.c
> > +++ b/mm/vmscan.c
> > @@ -2226,10 +2226,11 @@ static inline void init_tlb_ubc(void)
> > /*
> > * This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
>
> per-node freer
>
Fixed.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries
2016-07-01 20:01 ` [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries Mel Gorman
@ 2016-07-06 0:02 ` Minchan Kim
2016-07-06 8:58 ` Mel Gorman
2016-07-06 18:12 ` Dave Hansen
1 sibling, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-06 0:02 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:39PM +0100, Mel Gorman wrote:
> The number of LRU pages, dirty pages and writeback pages must be accounted
> for on both zones and nodes because of the reclaim retry logic, compaction
> retry logic and highmem calculations all depending on per-zone stats.
>
> The retry logic is only critical for allocations that can use any zones.
Sorry, I cannot follow this assertion.
Could you explain?
> Hence this patch will not retry reclaim or compaction for such allocations.
What is such allocations?
> This should not be a problem for reclaim as zone-constrained allocations
> are immune from OOM kill. For retries, a very rough approximation is made
zone-constrained allocations are immune from OOM kill?
Please explain it, too.
Sorry for the many questions but I cannot review code without clear
understanding of assumption/background which I couldn't notice.
> whether to retry or not. While it is possible this will make the wrong
> decision on occasion, it will not infinite loop as the number of reclaim
> attempts is capped by MAX_RECLAIM_RETRIES.
>
> The highmem calculations only care about the global count of file pages
> in highmem. Hence, a global counter is used instead of per-zone stats.
> With this, the per-zone double accounting disappears.
>
> Suggested by: Michal Hocko <mhocko@kernel.org>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> ---
> include/linux/mm_inline.h | 20 +++++++++++--
> include/linux/mmzone.h | 4 ---
> include/linux/swap.h | 1 -
> mm/compaction.c | 22 ++++++++++++++-
> mm/migrate.c | 2 --
> mm/page-writeback.c | 13 ++++-----
> mm/page_alloc.c | 71 ++++++++++++++++++++++++++++++++---------------
> mm/vmscan.c | 16 -----------
> mm/vmstat.c | 3 --
> 9 files changed, 92 insertions(+), 60 deletions(-)
>
> diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
> index 9aadcc781857..c68680aac044 100644
> --- a/include/linux/mm_inline.h
> +++ b/include/linux/mm_inline.h
> @@ -4,6 +4,22 @@
> #include <linux/huge_mm.h>
> #include <linux/swap.h>
>
> +#ifdef CONFIG_HIGHMEM
> +extern unsigned long highmem_file_pages;
> +
> +static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
> + int nr_pages)
> +{
> + if (is_highmem_idx(zid) && is_file_lru(lru))
> + highmem_file_pages += nr_pages;
> +}
> +#else
> +static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
> + int nr_pages)
> +{
> +}
> +#endif
> +
> /**
> * page_is_file_cache - should the page be on a file LRU or anon LRU?
> * @page: the page to test
> @@ -29,9 +45,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec,
> struct pglist_data *pgdat = lruvec_pgdat(lruvec);
>
> __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
> - __mod_zone_page_state(&pgdat->node_zones[zid],
> - NR_ZONE_LRU_BASE + !!is_file_lru(lru),
> - nr_pages);
> + acct_highmem_file_pages(zid, lru, nr_pages);
> }
>
> static __always_inline void update_lru_size(struct lruvec *lruvec,
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index facee6b83440..9268528c20c0 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -110,10 +110,6 @@ struct zone_padding {
> enum zone_stat_item {
> /* First 128 byte cacheline (assuming 64 bit words) */
> NR_FREE_PAGES,
> - NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
> - NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
> - NR_ZONE_LRU_FILE,
> - NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */
> NR_MLOCK, /* mlock()ed pages found and moved off LRU */
> NR_SLAB_RECLAIMABLE,
> NR_SLAB_UNRECLAIMABLE,
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index b17cc4830fa6..cc753c639e3d 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -307,7 +307,6 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
> struct vm_area_struct *vma);
>
> /* linux/mm/vmscan.c */
> -extern unsigned long zone_reclaimable_pages(struct zone *zone);
> extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);
> extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
> gfp_t gfp_mask, nodemask_t *mask);
> diff --git a/mm/compaction.c b/mm/compaction.c
> index a0bd85712516..dfe7dafe8e8b 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -1446,6 +1446,13 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
> {
> struct zone *zone;
> struct zoneref *z;
> + pg_data_t *last_pgdat = NULL;
> +
> +#ifdef CONFIG_HIGHMEM
> + /* Do not retry compaction for zone-constrained allocations */
> + if (!is_highmem_idx(ac->high_zoneidx))
> + return false;
> +#endif
>
> /*
> * Make sure at least one zone would pass __compaction_suitable if we continue
> @@ -1456,14 +1463,27 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
> unsigned long available;
> enum compact_result compact_result;
>
> + if (last_pgdat == zone->zone_pgdat)
> + continue;
> +
> + /*
> + * This over-estimates the number of pages available for
> + * reclaim/compaction but walking the LRU would take too
> + * long. The consequences are that compaction may retry
> + * longer than it should for a zone-constrained allocation
> + * request.
> + */
> + last_pgdat = zone->zone_pgdat;
> + available = pgdat_reclaimable_pages(zone->zone_pgdat) / order;
> +
> /*
> * Do not consider all the reclaimable memory because we do not
> * want to trash just for a single high order allocation which
> * is even not guaranteed to appear even if __compaction_suitable
> * is happy about the watermark check.
> */
> - available = zone_reclaimable_pages(zone) / order;
> available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
> + available = min(zone->managed_pages, available);
> compact_result = __compaction_suitable(zone, order, alloc_flags,
> ac_classzone_idx(ac), available);
> if (compact_result != COMPACT_SKIPPED &&
> diff --git a/mm/migrate.c b/mm/migrate.c
> index c77997dc6ed7..ed2f85e61de1 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -513,9 +513,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
> }
> if (dirty && mapping_cap_account_dirty(mapping)) {
> __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
> - __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
> __inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
> - __dec_zone_state(newzone, NR_ZONE_WRITE_PENDING);
> }
> }
> local_irq_enable();
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 3c02aa603f5a..8db1db234915 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -299,6 +299,9 @@ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
>
> return nr_pages;
> }
> +#ifdef CONFIG_HIGHMEM
> +unsigned long highmem_file_pages;
> +#endif
>
> static unsigned long highmem_dirtyable_memory(unsigned long total)
> {
> @@ -306,18 +309,17 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
> int node;
> unsigned long x = 0;
> int i;
> + unsigned long dirtyable = highmem_file_pages;
>
> for_each_node_state(node, N_HIGH_MEMORY) {
> for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) {
> struct zone *z;
> - unsigned long dirtyable;
>
> if (!is_highmem_idx(i))
> continue;
>
> z = &NODE_DATA(node)->node_zones[i];
> - dirtyable = zone_page_state(z, NR_FREE_PAGES) +
> - zone_page_state(z, NR_ZONE_LRU_FILE);
> + dirtyable += zone_page_state(z, NR_FREE_PAGES);
>
> /* watch for underflows */
> dirtyable -= min(dirtyable, high_wmark_pages(z));
> @@ -2460,7 +2462,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
>
> mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY);
> __inc_node_page_state(page, NR_FILE_DIRTY);
> - __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> __inc_node_page_state(page, NR_DIRTIED);
> __inc_wb_stat(wb, WB_RECLAIMABLE);
> __inc_wb_stat(wb, WB_DIRTIED);
> @@ -2482,7 +2483,6 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
> if (mapping_cap_account_dirty(mapping)) {
> mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
> dec_node_page_state(page, NR_FILE_DIRTY);
> - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> dec_wb_stat(wb, WB_RECLAIMABLE);
> task_io_account_cancelled_write(PAGE_SIZE);
> }
> @@ -2739,7 +2739,6 @@ int clear_page_dirty_for_io(struct page *page)
> if (TestClearPageDirty(page)) {
> mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
> dec_node_page_state(page, NR_FILE_DIRTY);
> - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> dec_wb_stat(wb, WB_RECLAIMABLE);
> ret = 1;
> }
> @@ -2786,7 +2785,6 @@ int test_clear_page_writeback(struct page *page)
> if (ret) {
> mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
> dec_node_page_state(page, NR_WRITEBACK);
> - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> inc_node_page_state(page, NR_WRITTEN);
> }
> unlock_page_memcg(page);
> @@ -2841,7 +2839,6 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
> if (!ret) {
> mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
> inc_node_page_state(page, NR_WRITEBACK);
> - inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> }
> unlock_page_memcg(page);
> return ret;
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index d3eb15c35bb1..9581185cb31a 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3445,6 +3445,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
> {
> struct zone *zone;
> struct zoneref *z;
> + pg_data_t *current_pgdat = NULL;
>
> /*
> * Make sure we converge to OOM if we cannot make any progress
> @@ -3454,6 +3455,14 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
> return false;
>
> /*
> + * Blindly retry allocation requests that cannot use all zones. We do
> + * not have a reliable and fast means of calculating reclaimable, dirty
> + * and writeback pages in eligible zones.
> + */
> + if (IS_ENABLED(CONFIG_HIGHMEM) && !is_highmem_idx(gfp_zone(gfp_mask)))
> + goto out;
> +
> + /*
> * Keep reclaiming pages while there is a chance this will lead somewhere.
> * If none of the target zones can satisfy our allocation request even
> * if all reclaimable pages are considered then we are screwed and have
> @@ -3463,36 +3472,54 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
> ac->nodemask) {
> unsigned long available;
> unsigned long reclaimable;
> + unsigned long write_pending = 0;
> + int zid;
> +
> + if (current_pgdat == zone->zone_pgdat)
> + continue;
>
> - available = reclaimable = zone_reclaimable_pages(zone);
> + current_pgdat = zone->zone_pgdat;
> + available = reclaimable = pgdat_reclaimable_pages(current_pgdat);
> available -= DIV_ROUND_UP(no_progress_loops * available,
> MAX_RECLAIM_RETRIES);
> - available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
> + write_pending = node_page_state(current_pgdat, NR_WRITEBACK) +
> + node_page_state(current_pgdat, NR_FILE_DIRTY);
>
> - /*
> - * Would the allocation succeed if we reclaimed the whole
> - * available?
> - */
> - if (__zone_watermark_ok(zone, order, min_wmark_pages(zone),
> - ac_classzone_idx(ac), alloc_flags, available)) {
> - /*
> - * If we didn't make any progress and have a lot of
> - * dirty + writeback pages then we should wait for
> - * an IO to complete to slow down the reclaim and
> - * prevent from pre mature OOM
> - */
> - if (!did_some_progress) {
> - unsigned long write_pending;
> + /* Account for all free pages on eligible zones */
> + for (zid = 0; zid <= zone_idx(zone); zid++) {
> + struct zone *acct_zone = ¤t_pgdat->node_zones[zid];
>
> - write_pending = zone_page_state_snapshot(zone,
> - NR_ZONE_WRITE_PENDING);
> + available += zone_page_state_snapshot(acct_zone, NR_FREE_PAGES);
> + }
>
> - if (2 * write_pending > reclaimable) {
> - congestion_wait(BLK_RW_ASYNC, HZ/10);
> - return true;
> - }
> + /*
> + * If we didn't make any progress and have a lot of
> + * dirty + writeback pages then we should wait for an IO to
> + * complete to slow down the reclaim and prevent from premature
> + * OOM.
> + */
> + if (!did_some_progress) {
> + if (2 * write_pending > reclaimable) {
> + congestion_wait(BLK_RW_ASYNC, HZ/10);
> + return true;
> }
> + }
>
> + /*
> + * Would the allocation succeed if we reclaimed the whole
> + * available? This is approximate because there is no
> + * accurate count of reclaimable pages per zone.
> + */
> + for (zid = 0; zid <= zone_idx(zone); zid++) {
> + struct zone *check_zone = ¤t_pgdat->node_zones[zid];
> + unsigned long estimate;
> +
> + estimate = min(check_zone->managed_pages, available);
> + if (__zone_watermark_ok(check_zone, order,
> + min_wmark_pages(check_zone), ac_classzone_idx(ac),
> + alloc_flags, available)) {
> + }
> +out:
> /*
> * Memory allocation/reclaim might be called from a WQ
> * context and the current implementation of the WQ
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 151c30dd27e2..c538a8cab43b 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -194,22 +194,6 @@ static bool sane_reclaim(struct scan_control *sc)
> }
> #endif
>
> -/*
> - * This misses isolated pages which are not accounted for to save counters.
> - * As the data only determines if reclaim or compaction continues, it is
> - * not expected that isolated pages will be a dominating factor.
> - */
> -unsigned long zone_reclaimable_pages(struct zone *zone)
> -{
> - unsigned long nr;
> -
> - nr = zone_page_state_snapshot(zone, NR_ZONE_LRU_FILE);
> - if (get_nr_swap_pages() > 0)
> - nr += zone_page_state_snapshot(zone, NR_ZONE_LRU_ANON);
> -
> - return nr;
> -}
> -
> unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat)
> {
> unsigned long nr;
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index ce09be63e8c7..524c082072be 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -908,9 +908,6 @@ int fragmentation_index(struct zone *zone, unsigned int order)
> const char * const vmstat_text[] = {
> /* enum zone_stat_item countes */
> "nr_free_pages",
> - "nr_zone_anon_lru",
> - "nr_zone_file_lru",
> - "nr_zone_write_pending",
> "nr_mlock",
> "nr_slab_reclaimable",
> "nr_slab_unreclaimable",
> --
> 2.6.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats
2016-07-05 8:14 ` Mel Gorman
@ 2016-07-06 0:15 ` Minchan Kim
0 siblings, 0 replies; 90+ messages in thread
From: Minchan Kim @ 2016-07-06 0:15 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Tue, Jul 05, 2016 at 09:14:05AM +0100, Mel Gorman wrote:
> On Tue, Jul 05, 2016 at 08:50:18AM +0900, Minchan Kim wrote:
> > > @@ -172,13 +174,17 @@ void refresh_zone_stat_thresholds(void)
> > > int threshold;
> > >
> > > for_each_populated_zone(zone) {
> > > + struct pglist_data *pgdat = zone->zone_pgdat;
> > > unsigned long max_drift, tolerate_drift;
> > >
> > > threshold = calculate_normal_threshold(zone);
> > >
> > > - for_each_online_cpu(cpu)
> > > + for_each_online_cpu(cpu) {
> > > per_cpu_ptr(zone->pageset, cpu)->stat_threshold
> > > = threshold;
> > > + per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
> > > + = threshold;
> > > + }
> >
> > I didn't see other patches yet so it might fix it then.
> >
> > per_cpu_nodestats is per node not zone but it use per-zone threshold
> > and even overwritten by next zones. I don't think it's not intended.
>
> It was intended that the threshold from one zone would be used but now
> that you point it out, it would use the threshold for the smallest zone
> in the node which is sub-optimal. I applied the patch below on top to
> use the threshold from the largest zone. I considered using the sum of
> all thresholds but feared it might allow too much per-cpu drift. It can
> be switched to the sum if we find a case where vmstat updates are too
> high.
Fair enough.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-05 10:26 ` Mel Gorman
@ 2016-07-06 0:30 ` Minchan Kim
2016-07-06 8:31 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-06 0:30 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Tue, Jul 05, 2016 at 11:26:39AM +0100, Mel Gorman wrote:
<snip>
> > > @@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> > > if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
> > > return;
> > > pgdat = zone->zone_pgdat;
> > > - if (pgdat->kswapd_max_order < order) {
> > > - pgdat->kswapd_max_order = order;
> > > - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
> > > - }
> > > + if (pgdat->kswapd_classzone_idx == -1)
> > > + pgdat->kswapd_classzone_idx = classzone_idx;
> >
> > It's tricky. Couldn't we change kswapd_classzone_idx to integer type
> > and remove if above if condition?
> >
>
> It's tricky and not necessarily better overall. It's perfectly possible
> to be woken up for zone index 0 so it's changing -1 to another magic
> value.
I don't get it. What is a problem with this?
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c538a8c..6eb23f5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3413,9 +3413,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
return;
pgdat = zone->zone_pgdat;
- if (pgdat->kswapd_classzone_idx == -1)
- pgdat->kswapd_classzone_idx = classzone_idx;
- pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+ pgdat->kswapd_classzone_idx = max_t(int, pgdat->kswapd_classzone_idx, classzone_idx);
pgdat->kswapd_order = max(pgdat->kswapd_order, order);
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
^ permalink raw reply related [flat|nested] 90+ messages in thread
* Re: [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone
2016-07-05 10:38 ` Mel Gorman
@ 2016-07-06 1:25 ` Minchan Kim
2016-07-06 8:42 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-06 1:25 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Tue, Jul 05, 2016 at 11:38:06AM +0100, Mel Gorman wrote:
> On Tue, Jul 05, 2016 at 03:11:17PM +0900, Minchan Kim wrote:
> > > - if (i < 0)
> > > - goto out;
> > > + /*
> > > + * Only reclaim if there are no eligible zones. Check from
> > > + * high to low zone to avoid prematurely clearing pgdat
> > > + * congested state.
> >
> > I cannot understand "prematurely clearing pgdat congested state".
> > Could you add more words to clear it out?
> >
>
> It's surprisingly difficult to concisely explain. Is this any better?
>
> /*
> * Only reclaim if there are no eligible zones. Check from
> * high to low zone as allocations prefer higher zones.
> * Scanning from low to high zone would allow congestion to be
> * cleared during a very small window when a small low
> * zone was balanced even under extreme pressure when the
> * overall node may be congested.
> */
Surely, it's better. Thanks for the explaining.
I doubt we need such corner case logic at this moment and how it works well
without consistent scan from other callers of zone_balanced where scans
from low to high.
> > > + */
> > > + for (i = classzone_idx; i >= 0; i--) {
> > > + zone = pgdat->node_zones + i;
> > > + if (!populated_zone(zone))
> > > + continue;
> > > +
> > > + if (zone_balanced(zone, sc.order, classzone_idx))
> >
> > If buffer_head is over limit, old logic force to reclaim highmem but
> > this zone_balanced logic will prevent it.
> >
>
> The old logic was always busted on 64-bit because is_highmem would always
> be 0. The original intent appears to be that buffer_heads_over_limit
> would release the buffers when pages went inactive. There are a number
Yes but the difference is in old, it was handled both direct and background
reclaim once buffers_heads is over the limit but your change slightly
changs it so kswapd couldn't reclaim high zone if any eligible zone
is balanced. I don't know how big difference it can make but we saw
highmem buffer_head problems several times, IIRC. So, I just wanted
to notice it to you. whether it's handled or not, it's up to you.
> of things we treated inconsistently that get fixed up in the series and
> buffer_heads_over_limit is one of them.
>
> --
> Mel Gorman
> SUSE Labs
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 00/31] Move LRU page reclaim from zones to nodes v8
2016-07-04 9:55 ` Mel Gorman
@ 2016-07-06 1:51 ` Minchan Kim
0 siblings, 0 replies; 90+ messages in thread
From: Minchan Kim @ 2016-07-06 1:51 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML, daniel.vetter, intel-gfx, dri-devel,
David Airlie
On Mon, Jul 04, 2016 at 10:55:09AM +0100, Mel Gorman wrote:
> On Mon, Jul 04, 2016 at 05:04:12PM +0900, Minchan Kim wrote:
> > > > How big ratio between highmem:lowmem do you think a problem?
> > > >
> > >
> > > That's a "how long is a piece of string" type question. The ratio does
> > > not matter as much as whether the workload is both under memory pressure
> > > and requires large amounts of lowmem pages. Even on systems with very high
> > > ratios, it may not be a problem if HIGHPTE is enabled.
> >
> > As well page table, pgd/kernelstack/zbud/slab and so on, every kernel
> > allocations wanted to mask __GFP_HIGHMEM off would be a problem in
> > 32bit system.
> >
>
> The same point applies -- it depends on the rate of these allocations,
> not the ratio of highmem:lowmem per se.
>
> > It also depends on that how many drivers needed lowmem only we have
> > in the system.
> >
> > I don't know how many such driver in the world. When I simply do grep,
> > I found several cases which mask __GFP_HIGHMEM off and among them,
> > I guess DRM might be a popular for us. However, it might be really rare
> > usecase among various i915 usecases.
> >
>
> It's also perfectly possible that such allocations are long-lived in which
> case they are not going to cause many skips. Hence why I cannot make a
> general prediction.
>
> > > > > Conceptually, moving to node LRUs should be easier to understand. The
> > > > > page allocator plays fewer tricks to game reclaim and reclaim behaves
> > > > > similarly on all nodes.
> > > > >
> > > > > The series has been tested on a 16 core UMA machine and a 2-socket 48
> > > > > core NUMA machine. The UMA results are presented in most cases as the NUMA
> > > > > machine behaved similarly.
> > > >
> > > > I guess you would already test below with various highmem system(e.g.,
> > > > 2:1, 3:1, 4:1 and so on). If you have, could you mind sharing it?
> > > >
> > >
> > > I haven't that data, the baseline distribution used doesn't even have
> > > 32-bit support. Even if it was, the results may not be that interesting.
> > > The workloads used were not necessarily going to trigger lowmem pressure
> > > as HIGHPTE was set on the 32-bit configs.
> >
> > That means we didn't test this on 32-bit with highmem.
> >
>
> No. I tested the skip logic and noticed that when forced on purpose that
> system CPU usage was higher but it functionally worked.
Yeb, it would work well functionally. I meant not functionally but
performance point of view, system cpu usage and majfault rate
and so on.
>
> > I'm not sure it's really too rare case to spend a time for testing.
> > In fact, I really want to test all series to our production system
> > which is 32bit and highmem but as we know well, most of embedded
> > system kernel is rather old so backporting needs lots of time and
> > care. However, if we miss testing in those system at the moment,
> > we will be suprised after 1~2 years.
> >
>
> It would be appreciated if it could be tested on such platforms if at all
> possible. Even if I did set up a 32-bit x86 system, it won't have the same
> allocation/reclaim profile as the platforms you are considering.
Yeb. I just finished reviewing of all patches and found no *big* problem
with my brain so my remanining homework is just testing which would find
what my brain have missed.
I will give the backporing to old 32-bit production kernel a shot and
report if something strange happens.
Thanks for great work, Mel!
>
> > I don't know what kinds of benchmark can we can check it so I cannot
> > insist on it but you might know it.
> >
>
> One method would be to use fsmark with very large numbers of small files
> to force slab to require low memory. It's not representative of many real
> workloads unfortunately. Usually such a configuration is for checking the
> slab shrinker is working as expected.
Thanks for the suggestion.
>
> > Okay, do you have any idea to fix it if we see such regression report
> > in 32-bit system in future?
>
> Two options, neither whose complexity is justified without a "real"
> workload to use as a reference.
>
> 1. Long-term isolation of highmem pages when reclaim is lowmem
>
> When pages are skipped, they are immediately added back onto the LRU
> list. If lowmem reclaim persisted for long periods of time, the same
> highmem pages get continually scanned. The idea would be that lowmem
> keeps those pages on a separate list until a reclaim for highmem pages
> arrives that splices the highmem pages back onto the LRU.
>
> That would reduce the skip rate, the potential corner case is that
> highmem pages have to be scanned and reclaimed to free lowmem slab pages.
>
> 2. Linear scan lowmem pages if the initial LRU shrink fails
>
> This will break LRU ordering but may be preferable and faster during
> memory pressure than skipping LRU pages.
Okay. I guess it would be better to include this in descripion of [4/31].
>
> --
> Mel Gorman
> SUSE Labs
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-06 0:30 ` Minchan Kim
@ 2016-07-06 8:31 ` Mel Gorman
2016-07-07 5:51 ` Minchan Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-06 8:31 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Wed, Jul 06, 2016 at 09:30:54AM +0900, Minchan Kim wrote:
> On Tue, Jul 05, 2016 at 11:26:39AM +0100, Mel Gorman wrote:
>
> <snip>
>
> > > > @@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> > > > if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
> > > > return;
> > > > pgdat = zone->zone_pgdat;
> > > > - if (pgdat->kswapd_max_order < order) {
> > > > - pgdat->kswapd_max_order = order;
> > > > - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
> > > > - }
> > > > + if (pgdat->kswapd_classzone_idx == -1)
> > > > + pgdat->kswapd_classzone_idx = classzone_idx;
> > >
> > > It's tricky. Couldn't we change kswapd_classzone_idx to integer type
> > > and remove if above if condition?
> > >
> >
> > It's tricky and not necessarily better overall. It's perfectly possible
> > to be woken up for zone index 0 so it's changing -1 to another magic
> > value.
>
> I don't get it. What is a problem with this?
>
It becomes difficult to tell the difference between "no wakeup and init to
zone 0" and "wakeup and reclaim for zone 0". At least that's the problem
I ran into when I tried before settling on -1.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone
2016-07-06 1:25 ` Minchan Kim
@ 2016-07-06 8:42 ` Mel Gorman
2016-07-07 6:27 ` Minchan Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-06 8:42 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Wed, Jul 06, 2016 at 10:25:54AM +0900, Minchan Kim wrote:
> On Tue, Jul 05, 2016 at 11:38:06AM +0100, Mel Gorman wrote:
> > On Tue, Jul 05, 2016 at 03:11:17PM +0900, Minchan Kim wrote:
> > > > - if (i < 0)
> > > > - goto out;
> > > > + /*
> > > > + * Only reclaim if there are no eligible zones. Check from
> > > > + * high to low zone to avoid prematurely clearing pgdat
> > > > + * congested state.
> > >
> > > I cannot understand "prematurely clearing pgdat congested state".
> > > Could you add more words to clear it out?
> > >
> >
> > It's surprisingly difficult to concisely explain. Is this any better?
> >
> > /*
> > * Only reclaim if there are no eligible zones. Check from
> > * high to low zone as allocations prefer higher zones.
> > * Scanning from low to high zone would allow congestion to be
> > * cleared during a very small window when a small low
> > * zone was balanced even under extreme pressure when the
> > * overall node may be congested.
> > */
>
> Surely, it's better. Thanks for the explaining.
>
> I doubt we need such corner case logic at this moment and how it works well
> without consistent scan from other callers of zone_balanced where scans
> from low to high.
>
I observed that if scanning from low to high here that under heavy memory
pressure that kswapd would scan much more aggressively but unable to reclaim
pages. Granted, part of the problem at the time was that kswapd was woken
based on the first zone in the zoneref instead of the highest zone allowed
by the allocation request which gets addressed by "mm, page_alloc: wake
kswapd based on the highest eligible zone".
> > > > + */
> > > > + for (i = classzone_idx; i >= 0; i--) {
> > > > + zone = pgdat->node_zones + i;
> > > > + if (!populated_zone(zone))
> > > > + continue;
> > > > +
> > > > + if (zone_balanced(zone, sc.order, classzone_idx))
> > >
> > > If buffer_head is over limit, old logic force to reclaim highmem but
> > > this zone_balanced logic will prevent it.
> > >
> >
> > The old logic was always busted on 64-bit because is_highmem would always
> > be 0. The original intent appears to be that buffer_heads_over_limit
> > would release the buffers when pages went inactive. There are a number
>
> Yes but the difference is in old, it was handled both direct and background
> reclaim once buffers_heads is over the limit but your change slightly
> changs it so kswapd couldn't reclaim high zone if any eligible zone
> is balanced. I don't know how big difference it can make but we saw
> highmem buffer_head problems several times, IIRC. So, I just wanted
> to notice it to you. whether it's handled or not, it's up to you.
>
The last time I remember buffer_heads_over_limit was an NTFS filesystem
using small sub-page block sizes with a large highmem:lowmem ratio. If a
similar situation is encountered then a test patch would be something like;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index dc12af938a8d..a8ebd1871f16 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3151,7 +3151,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
* zone was balanced even under extreme pressure when the
* overall node may be congested.
*/
- for (i = sc.reclaim_idx; i >= 0; i--) {
+ for (i = sc.reclaim_idx; i >= 0 && !buffer_heads_over_limit; i--) {
zone = pgdat->node_zones + i;
if (!populated_zone(zone))
continue;
I'm not going to go with it for now because buffer_heads_over_limit is not
necessarily a problem unless lowmem is factor. We don't want background
reclaim to go ahead unnecessarily just because buffer_heads_over_limit.
It could be distinguished by only forcing reclaim to go ahead on systems
with highmem.
--
Mel Gorman
SUSE Labs
^ permalink raw reply related [flat|nested] 90+ messages in thread
* Re: [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries
2016-07-06 0:02 ` Minchan Kim
@ 2016-07-06 8:58 ` Mel Gorman
2016-07-06 9:33 ` Mel Gorman
2016-07-07 6:47 ` Minchan Kim
0 siblings, 2 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-06 8:58 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Wed, Jul 06, 2016 at 09:02:52AM +0900, Minchan Kim wrote:
> On Fri, Jul 01, 2016 at 09:01:39PM +0100, Mel Gorman wrote:
> > The number of LRU pages, dirty pages and writeback pages must be accounted
> > for on both zones and nodes because of the reclaim retry logic, compaction
> > retry logic and highmem calculations all depending on per-zone stats.
> >
> > The retry logic is only critical for allocations that can use any zones.
>
> Sorry, I cannot follow this assertion.
> Could you explain?
>
The patch has been reworked since and I tried clarifying the changelog.
Does this help?
--- 8<----
mm, vmstat: remove zone and node double accounting by approximating retries
The number of LRU pages, dirty pages and writeback pages must be accounted
for on both zones and nodes because of the reclaim retry logic, compaction
retry logic and highmem calculations all depending on per-zone stats.
Many lowmem allocations are immune from OOM kill due to a check in
__alloc_pages_may_oom for (ac->high_zoneidx < ZONE_NORMAL) since commit
03668b3ceb0c ("oom: avoid oom killer for lowmem allocations"). The exception
is costly high-order allocations or allocations that cannot fail. If the
__alloc_pages_may_oom avoids OOM-kill for low-order lowmem allocations
then a check in __alloc_pages_slowpath will always retry.
Hence this patch will always retry reclaim for zone-constrained allocations
in should_reclaim_retry.
As there is no guarantee enough memory can ever be freed to satisfy
compaction, this patch avoids retrying compaction for zone-contrained
allocations.o
In combination, that means that the per-node stats can be used when deciding
whether to continue reclaim using a rough approximation. While it is
possible this will make the wrong decision on occasion, it will not infinite
loop as the number of reclaim attempts is capped by MAX_RECLAIM_RETRIES.
The final step is calculating the number of dirtyable highmem pages. As
those calculations only care about the global count of file pages in
highmem. This patch uses a global counter used instead of per-zone stats
as it is sufficient.
In combination, this allows the per-zone LRU and dirty state counters to
be removed.
Suggested by: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 9aadcc781857..c68680aac044 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -4,6 +4,22 @@
#include <linux/huge_mm.h>
#include <linux/swap.h>
+#ifdef CONFIG_HIGHMEM
+extern unsigned long highmem_file_pages;
+
+static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
+ int nr_pages)
+{
+ if (is_highmem_idx(zid) && is_file_lru(lru))
+ highmem_file_pages += nr_pages;
+}
+#else
+static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
+ int nr_pages)
+{
+}
+#endif
+
/**
* page_is_file_cache - should the page be on a file LRU or anon LRU?
* @page: the page to test
@@ -29,9 +45,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec,
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
__mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
- __mod_zone_page_state(&pgdat->node_zones[zid],
- NR_ZONE_LRU_BASE + !!is_file_lru(lru),
- nr_pages);
+ acct_highmem_file_pages(zid, lru, nr_pages);
}
static __always_inline void update_lru_size(struct lruvec *lruvec,
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bd33e6f1bed0..a3b7f45aac56 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -110,10 +110,6 @@ struct zone_padding {
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
- NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
- NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
- NR_ZONE_LRU_FILE,
- NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */
NR_MLOCK, /* mlock()ed pages found and moved off LRU */
NR_SLAB_RECLAIMABLE,
NR_SLAB_UNRECLAIMABLE,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b17cc4830fa6..cc753c639e3d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -307,7 +307,6 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
struct vm_area_struct *vma);
/* linux/mm/vmscan.c */
-extern unsigned long zone_reclaimable_pages(struct zone *zone);
extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
diff --git a/mm/compaction.c b/mm/compaction.c
index a0bd85712516..dfe7dafe8e8b 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1446,6 +1446,13 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
{
struct zone *zone;
struct zoneref *z;
+ pg_data_t *last_pgdat = NULL;
+
+#ifdef CONFIG_HIGHMEM
+ /* Do not retry compaction for zone-constrained allocations */
+ if (!is_highmem_idx(ac->high_zoneidx))
+ return false;
+#endif
/*
* Make sure at least one zone would pass __compaction_suitable if we continue
@@ -1456,14 +1463,27 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
unsigned long available;
enum compact_result compact_result;
+ if (last_pgdat == zone->zone_pgdat)
+ continue;
+
+ /*
+ * This over-estimates the number of pages available for
+ * reclaim/compaction but walking the LRU would take too
+ * long. The consequences are that compaction may retry
+ * longer than it should for a zone-constrained allocation
+ * request.
+ */
+ last_pgdat = zone->zone_pgdat;
+ available = pgdat_reclaimable_pages(zone->zone_pgdat) / order;
+
/*
* Do not consider all the reclaimable memory because we do not
* want to trash just for a single high order allocation which
* is even not guaranteed to appear even if __compaction_suitable
* is happy about the watermark check.
*/
- available = zone_reclaimable_pages(zone) / order;
available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
+ available = min(zone->managed_pages, available);
compact_result = __compaction_suitable(zone, order, alloc_flags,
ac_classzone_idx(ac), available);
if (compact_result != COMPACT_SKIPPED &&
diff --git a/mm/migrate.c b/mm/migrate.c
index c77997dc6ed7..ed2f85e61de1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -513,9 +513,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
}
if (dirty && mapping_cap_account_dirty(mapping)) {
__dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
- __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
__inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
- __dec_zone_state(newzone, NR_ZONE_WRITE_PENDING);
}
}
local_irq_enable();
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3c02aa603f5a..8db1db234915 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -299,6 +299,9 @@ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
return nr_pages;
}
+#ifdef CONFIG_HIGHMEM
+unsigned long highmem_file_pages;
+#endif
static unsigned long highmem_dirtyable_memory(unsigned long total)
{
@@ -306,18 +309,17 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
int node;
unsigned long x = 0;
int i;
+ unsigned long dirtyable = highmem_file_pages;
for_each_node_state(node, N_HIGH_MEMORY) {
for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) {
struct zone *z;
- unsigned long dirtyable;
if (!is_highmem_idx(i))
continue;
z = &NODE_DATA(node)->node_zones[i];
- dirtyable = zone_page_state(z, NR_FREE_PAGES) +
- zone_page_state(z, NR_ZONE_LRU_FILE);
+ dirtyable += zone_page_state(z, NR_FREE_PAGES);
/* watch for underflows */
dirtyable -= min(dirtyable, high_wmark_pages(z));
@@ -2460,7 +2462,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY);
__inc_node_page_state(page, NR_FILE_DIRTY);
- __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
__inc_node_page_state(page, NR_DIRTIED);
__inc_wb_stat(wb, WB_RECLAIMABLE);
__inc_wb_stat(wb, WB_DIRTIED);
@@ -2482,7 +2483,6 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
if (mapping_cap_account_dirty(mapping)) {
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
dec_node_page_state(page, NR_FILE_DIRTY);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
dec_wb_stat(wb, WB_RECLAIMABLE);
task_io_account_cancelled_write(PAGE_SIZE);
}
@@ -2739,7 +2739,6 @@ int clear_page_dirty_for_io(struct page *page)
if (TestClearPageDirty(page)) {
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
dec_node_page_state(page, NR_FILE_DIRTY);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
dec_wb_stat(wb, WB_RECLAIMABLE);
ret = 1;
}
@@ -2786,7 +2785,6 @@ int test_clear_page_writeback(struct page *page)
if (ret) {
mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
dec_node_page_state(page, NR_WRITEBACK);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
inc_node_page_state(page, NR_WRITTEN);
}
unlock_page_memcg(page);
@@ -2841,7 +2839,6 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
if (!ret) {
mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
inc_node_page_state(page, NR_WRITEBACK);
- inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
}
unlock_page_memcg(page);
return ret;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 030114f55b0e..ded48e580abc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3445,6 +3445,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
{
struct zone *zone;
struct zoneref *z;
+ pg_data_t *current_pgdat = NULL;
/*
* Make sure we converge to OOM if we cannot make any progress
@@ -3454,6 +3455,14 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
return false;
/*
+ * Blindly retry allocation requests that cannot use all zones. We do
+ * not have a reliable and fast means of calculating reclaimable, dirty
+ * and writeback pages in eligible zones.
+ */
+ if (IS_ENABLED(CONFIG_HIGHMEM) && !is_highmem_idx(gfp_zone(gfp_mask)))
+ goto out;
+
+ /*
* Keep reclaiming pages while there is a chance this will lead somewhere.
* If none of the target zones can satisfy our allocation request even
* if all reclaimable pages are considered then we are screwed and have
@@ -3463,18 +3472,38 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
ac->nodemask) {
unsigned long available;
unsigned long reclaimable;
+ int zid;
- available = reclaimable = zone_reclaimable_pages(zone);
+ if (current_pgdat == zone->zone_pgdat)
+ continue;
+
+ current_pgdat = zone->zone_pgdat;
+ available = reclaimable = pgdat_reclaimable_pages(current_pgdat);
available -= DIV_ROUND_UP(no_progress_loops * available,
MAX_RECLAIM_RETRIES);
- available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
+
+ /* Account for all free pages on eligible zones */
+ for (zid = 0; zid <= zone_idx(zone); zid++) {
+ struct zone *acct_zone = ¤t_pgdat->node_zones[zid];
+
+ available += zone_page_state_snapshot(acct_zone, NR_FREE_PAGES);
+ }
/*
* Would the allocation succeed if we reclaimed the whole
- * available?
+ * available? This is approximate because there is no
+ * accurate count of reclaimable pages per zone.
*/
- if (__zone_watermark_ok(zone, order, min_wmark_pages(zone),
- ac_classzone_idx(ac), alloc_flags, available)) {
+ for (zid = 0; zid <= zone_idx(zone); zid++) {
+ struct zone *check_zone = ¤t_pgdat->node_zones[zid];
+ unsigned long estimate;
+
+ estimate = min(check_zone->managed_pages, available);
+ if (!__zone_watermark_ok(check_zone, order,
+ min_wmark_pages(check_zone), ac_classzone_idx(ac),
+ alloc_flags, estimate))
+ continue;
+
/*
* If we didn't make any progress and have a lot of
* dirty + writeback pages then we should wait for
@@ -3484,15 +3513,16 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
if (!did_some_progress) {
unsigned long write_pending;
- write_pending = zone_page_state_snapshot(zone,
- NR_ZONE_WRITE_PENDING);
+ write_pending =
+ node_page_state(current_pgdat, NR_WRITEBACK) +
+ node_page_state(current_pgdat, NR_FILE_DIRTY);
if (2 * write_pending > reclaimable) {
congestion_wait(BLK_RW_ASYNC, HZ/10);
return true;
}
}
-
+out:
/*
* Memory allocation/reclaim might be called from a WQ
* context and the current implementation of the WQ
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9eed2d3e05f3..a8ebd1871f16 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -194,22 +194,6 @@ static bool sane_reclaim(struct scan_control *sc)
}
#endif
-/*
- * This misses isolated pages which are not accounted for to save counters.
- * As the data only determines if reclaim or compaction continues, it is
- * not expected that isolated pages will be a dominating factor.
- */
-unsigned long zone_reclaimable_pages(struct zone *zone)
-{
- unsigned long nr;
-
- nr = zone_page_state_snapshot(zone, NR_ZONE_LRU_FILE);
- if (get_nr_swap_pages() > 0)
- nr += zone_page_state_snapshot(zone, NR_ZONE_LRU_ANON);
-
- return nr;
-}
-
unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat)
{
unsigned long nr;
@@ -3167,7 +3151,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
* zone was balanced even under extreme pressure when the
* overall node may be congested.
*/
- for (i = sc.reclaim_idx; i >= 0; i--) {
+ for (i = sc.reclaim_idx; i >= 0 && !buffer_heads_over_limit; i--) {
zone = pgdat->node_zones + i;
if (!populated_zone(zone))
continue;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 60372f31fee3..7415775faf08 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -921,9 +921,6 @@ int fragmentation_index(struct zone *zone, unsigned int order)
const char * const vmstat_text[] = {
/* enum zone_stat_item countes */
"nr_free_pages",
- "nr_zone_anon_lru",
- "nr_zone_file_lru",
- "nr_zone_write_pending",
"nr_mlock",
"nr_slab_reclaimable",
"nr_slab_unreclaimable",
--
Mel Gorman
SUSE Labs
^ permalink raw reply related [flat|nested] 90+ messages in thread
* Re: [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries
2016-07-06 8:58 ` Mel Gorman
@ 2016-07-06 9:33 ` Mel Gorman
2016-07-07 6:47 ` Minchan Kim
1 sibling, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-06 9:33 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Wed, Jul 06, 2016 at 09:58:50AM +0100, Mel Gorman wrote:
> On Wed, Jul 06, 2016 at 09:02:52AM +0900, Minchan Kim wrote:
> > On Fri, Jul 01, 2016 at 09:01:39PM +0100, Mel Gorman wrote:
> > > The number of LRU pages, dirty pages and writeback pages must be accounted
> > > for on both zones and nodes because of the reclaim retry logic, compaction
> > > retry logic and highmem calculations all depending on per-zone stats.
> > >
> > > The retry logic is only critical for allocations that can use any zones.
> >
> > Sorry, I cannot follow this assertion.
> > Could you explain?
> >
>
> The patch has been reworked since and I tried clarifying the changelog.
> Does this help?
>
It occurred to me at breakfast that this should be more consistent with
the OOM killer on both 32-bit and 64-bit so;
diff --git a/mm/compaction.c b/mm/compaction.c
index dfe7dafe8e8b..640532831b94 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1448,11 +1448,9 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
struct zoneref *z;
pg_data_t *last_pgdat = NULL;
-#ifdef CONFIG_HIGHMEM
/* Do not retry compaction for zone-constrained allocations */
- if (!is_highmem_idx(ac->high_zoneidx))
+ if (ac->high_zoneidx < ZONE_NORMAL)
return false;
-#endif
/*
* Make sure at least one zone would pass __compaction_suitable if we continue
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ded48e580abc..194a8162528b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3455,11 +3455,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
return false;
/*
- * Blindly retry allocation requests that cannot use all zones. We do
- * not have a reliable and fast means of calculating reclaimable, dirty
- * and writeback pages in eligible zones.
+ * Blindly retry lowmem allocation requests that are often ignored by
+ * the OOM killer as we not have a reliable and fast means of
+ * calculating reclaimable, dirty and writeback pages in eligible zones.
*/
- if (IS_ENABLED(CONFIG_HIGHMEM) && !is_highmem_idx(gfp_zone(gfp_mask)))
+ if (ac->high_zoneidx < ZONE_NORMAL)
goto out;
/*
^ permalink raw reply related [flat|nested] 90+ messages in thread
* Re: [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries
2016-07-01 20:01 ` [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries Mel Gorman
2016-07-06 0:02 ` Minchan Kim
@ 2016-07-06 18:12 ` Dave Hansen
2016-07-07 11:26 ` Mel Gorman
1 sibling, 1 reply; 90+ messages in thread
From: Dave Hansen @ 2016-07-06 18:12 UTC (permalink / raw)
To: Mel Gorman, Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML
On 07/01/2016 01:01 PM, Mel Gorman wrote:
> +#ifdef CONFIG_HIGHMEM
> +extern unsigned long highmem_file_pages;
> +
> +static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
> + int nr_pages)
> +{
> + if (is_highmem_idx(zid) && is_file_lru(lru))
> + highmem_file_pages += nr_pages;
> +}
> +#else
Shouldn't highmem_file_pages technically be an atomic_t (or atomic64_t)?
We could have highmem on two nodes which take two different LRU locks.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-01 20:01 ` [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis Mel Gorman
@ 2016-07-07 1:12 ` Joonsoo Kim
2016-07-07 9:48 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-07 1:12 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:12PM +0100, Mel Gorman wrote:
> This patch makes reclaim decisions on a per-node basis. A reclaimer knows
> what zone is required by the allocation request and skips pages from
> higher zones. In many cases this will be ok because it's a GFP_HIGHMEM
> request of some description. On 64-bit, ZONE_DMA32 requests will cause
> some problems but 32-bit devices on 64-bit platforms are increasingly
> rare. Historically it would have been a major problem on 32-bit with big
> Highmem:Lowmem ratios but such configurations are also now rare and even
> where they exist, they are not encouraged. If it really becomes a
> problem, it'll manifest as very low reclaim efficiencies.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> ---
> mm/vmscan.c | 79 ++++++++++++++++++++++++++++++++++++++++++-------------------
> 1 file changed, 55 insertions(+), 24 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 86a523a761c9..766b36bec829 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -84,6 +84,9 @@ struct scan_control {
> /* Scan (total_size >> priority) pages at once */
> int priority;
>
> + /* The highest zone to isolate pages for reclaim from */
> + enum zone_type reclaim_idx;
> +
> unsigned int may_writepage:1;
>
> /* Can mapped pages be reclaimed? */
> @@ -1392,6 +1395,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
> unsigned long nr_taken = 0;
> unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
> unsigned long scan, nr_pages;
> + LIST_HEAD(pages_skipped);
>
> for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
> !list_empty(src); scan++) {
> @@ -1402,6 +1406,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
>
> VM_BUG_ON_PAGE(!PageLRU(page), page);
>
> + if (page_zonenum(page) > sc->reclaim_idx) {
> + list_move(&page->lru, &pages_skipped);
> + continue;
> + }
> +
Hello, Mel.
I think that we don't need to skip LRU pages in active list. What we'd
like to do is just skipping actual reclaim since it doesn't make
freepage that we need. It's unrelated to skip the page in active list.
And, I have a concern that if inactive LRU is full with higher zone's
LRU pages, reclaim with low reclaim_idx could be stuck. This would be
easily possible if fair zone allocation policy is removed because we
will allocate the page on higher zone first.
Thanks.
> switch (__isolate_lru_page(page, mode)) {
> case 0:
> nr_pages = hpage_nr_pages(page);
> @@ -1420,6 +1429,15 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
> }
> }
>
> + /*
> + * Splice any skipped pages to the start of the LRU list. Note that
> + * this disrupts the LRU order when reclaiming for lower zones but
> + * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX
> + * scanning would soon rescan the same pages to skip and put the
> + * system at risk of premature OOM.
> + */
> + if (!list_empty(&pages_skipped))
> + list_splice(&pages_skipped, src);
> *nr_scanned = scan;
> trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
> nr_taken, mode, is_file_lru(lru));
> @@ -1589,7 +1607,7 @@ static int current_may_throttle(void)
> }
>
> /*
> - * shrink_inactive_list() is a helper for shrink_zone(). It returns the number
> + * shrink_inactive_list() is a helper for shrink_node(). It returns the number
> * of reclaimed pages
> */
> static noinline_for_stack unsigned long
> @@ -2401,12 +2419,13 @@ static inline bool should_continue_reclaim(struct zone *zone,
> }
> }
>
> -static bool shrink_zone(struct zone *zone, struct scan_control *sc,
> - bool is_classzone)
> +static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
> + enum zone_type classzone_idx)
> {
> struct reclaim_state *reclaim_state = current->reclaim_state;
> unsigned long nr_reclaimed, nr_scanned;
> bool reclaimable = false;
> + struct zone *zone = &pgdat->node_zones[classzone_idx];
>
> do {
> struct mem_cgroup *root = sc->target_mem_cgroup;
> @@ -2438,7 +2457,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
> shrink_zone_memcg(zone, memcg, sc, &lru_pages);
> zone_lru_pages += lru_pages;
>
> - if (memcg && is_classzone)
> + if (!global_reclaim(sc))
> shrink_slab(sc->gfp_mask, zone_to_nid(zone),
> memcg, sc->nr_scanned - scanned,
> lru_pages);
> @@ -2469,7 +2488,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
> * Shrink the slab caches in the same proportion that
> * the eligible LRU pages were scanned.
> */
> - if (global_reclaim(sc) && is_classzone)
> + if (global_reclaim(sc))
> shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
> sc->nr_scanned - nr_scanned,
> zone_lru_pages);
> @@ -2553,7 +2572,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
> unsigned long nr_soft_reclaimed;
> unsigned long nr_soft_scanned;
> gfp_t orig_mask;
> - enum zone_type requested_highidx = gfp_zone(sc->gfp_mask);
> + enum zone_type classzone_idx;
>
> /*
> * If the number of buffer_heads in the machine exceeds the maximum
> @@ -2561,17 +2580,23 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
> * highmem pages could be pinning lowmem pages storing buffer_heads
> */
> orig_mask = sc->gfp_mask;
> - if (buffer_heads_over_limit)
> + if (buffer_heads_over_limit) {
> sc->gfp_mask |= __GFP_HIGHMEM;
> + sc->reclaim_idx = classzone_idx = gfp_zone(sc->gfp_mask);
> + }
>
> for_each_zone_zonelist_nodemask(zone, z, zonelist,
> - gfp_zone(sc->gfp_mask), sc->nodemask) {
> - enum zone_type classzone_idx;
> -
> + sc->reclaim_idx, sc->nodemask) {
> if (!populated_zone(zone))
> continue;
>
> - classzone_idx = requested_highidx;
> + /*
> + * Note that reclaim_idx does not change as it is the highest
> + * zone reclaimed from which for empty zones is a no-op but
> + * classzone_idx is used by shrink_node to test if the slabs
> + * should be shrunk on a given node.
> + */
> + classzone_idx = sc->reclaim_idx;
> while (!populated_zone(zone->zone_pgdat->node_zones +
> classzone_idx))
> classzone_idx--;
> @@ -2600,8 +2625,8 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
> */
> if (IS_ENABLED(CONFIG_COMPACTION) &&
> sc->order > PAGE_ALLOC_COSTLY_ORDER &&
> - zonelist_zone_idx(z) <= requested_highidx &&
> - compaction_ready(zone, sc->order, requested_highidx)) {
> + zonelist_zone_idx(z) <= classzone_idx &&
> + compaction_ready(zone, sc->order, classzone_idx)) {
> sc->compaction_ready = true;
> continue;
> }
> @@ -2621,7 +2646,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
> /* need some check for avoid more shrink_zone() */
> }
>
> - shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
> + shrink_node(zone->zone_pgdat, sc, classzone_idx);
> }
>
> /*
> @@ -2847,6 +2872,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
> struct scan_control sc = {
> .nr_to_reclaim = SWAP_CLUSTER_MAX,
> .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
> + .reclaim_idx = gfp_zone(gfp_mask),
> .order = order,
> .nodemask = nodemask,
> .priority = DEF_PRIORITY,
> @@ -2886,6 +2912,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
> .target_mem_cgroup = memcg,
> .may_writepage = !laptop_mode,
> .may_unmap = 1,
> + .reclaim_idx = MAX_NR_ZONES - 1,
> .may_swap = !noswap,
> };
> unsigned long lru_pages;
> @@ -2924,6 +2951,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
> .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
> .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
> (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
> + .reclaim_idx = MAX_NR_ZONES - 1,
> .target_mem_cgroup = memcg,
> .priority = DEF_PRIORITY,
> .may_writepage = !laptop_mode,
> @@ -3118,7 +3146,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
> balance_gap, classzone_idx))
> return true;
>
> - shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
> + shrink_node(zone->zone_pgdat, sc, classzone_idx);
>
> /* TODO: ANOMALY */
> clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
> @@ -3167,6 +3195,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> unsigned long nr_soft_scanned;
> struct scan_control sc = {
> .gfp_mask = GFP_KERNEL,
> + .reclaim_idx = MAX_NR_ZONES - 1,
> .order = order,
> .priority = DEF_PRIORITY,
> .may_writepage = !laptop_mode,
> @@ -3237,15 +3266,14 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> sc.may_writepage = 1;
>
> /*
> - * Now scan the zone in the dma->highmem direction, stopping
> - * at the last zone which needs scanning.
> - *
> - * We do this because the page allocator works in the opposite
> - * direction. This prevents the page allocator from allocating
> - * pages behind kswapd's direction of progress, which would
> - * cause too much scanning of the lower zones.
> + * Continue scanning in the highmem->dma direction stopping at
> + * the last zone which needs scanning. This may reclaim lowmem
> + * pages that are not necessary for zone balancing but it
> + * preserves LRU ordering. It is assumed that the bulk of
> + * allocation requests can use arbitrary zones with the
> + * possible exception of big highmem:lowmem configurations.
> */
> - for (i = 0; i <= end_zone; i++) {
> + for (i = end_zone; i >= 0; i--) {
> struct zone *zone = pgdat->node_zones + i;
>
> if (!populated_zone(zone))
> @@ -3256,6 +3284,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> continue;
>
> sc.nr_scanned = 0;
> + sc.reclaim_idx = i;
>
> nr_soft_scanned = 0;
> /*
> @@ -3513,6 +3542,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
> struct scan_control sc = {
> .nr_to_reclaim = nr_to_reclaim,
> .gfp_mask = GFP_HIGHUSER_MOVABLE,
> + .reclaim_idx = MAX_NR_ZONES - 1,
> .priority = DEF_PRIORITY,
> .may_writepage = 1,
> .may_unmap = 1,
> @@ -3704,6 +3734,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
> .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
> .may_unmap = !!(zone_reclaim_mode & RECLAIM_UNMAP),
> .may_swap = 1,
> + .reclaim_idx = zone_idx(zone),
> };
>
> cond_resched();
> @@ -3723,7 +3754,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
> * priorities until we have enough memory freed.
> */
> do {
> - shrink_zone(zone, &sc, true);
> + shrink_node(zone->zone_pgdat, &sc, zone_idx(zone));
> } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
> }
>
> --
> 2.6.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-01 20:01 ` [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-07-05 5:59 ` Minchan Kim
@ 2016-07-07 1:20 ` Joonsoo Kim
2016-07-07 10:17 ` Mel Gorman
1 sibling, 1 reply; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-07 1:20 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:16PM +0100, Mel Gorman wrote:
> kswapd goes through some complex steps trying to figure out if it should
> stay awake based on the classzone_idx and the requested order. It is
> unnecessarily complex and passes in an invalid classzone_idx to
> balance_pgdat(). What matters most of all is whether a larger order has
> been requsted and whether kswapd successfully reclaimed at the previous
> order. This patch irons out the logic to check just that and the end
> result is less headache inducing.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
> include/linux/mmzone.h | 5 ++-
> mm/memory_hotplug.c | 5 ++-
> mm/page_alloc.c | 2 +-
> mm/vmscan.c | 102 ++++++++++++++++++++++++++-----------------------
> 4 files changed, 62 insertions(+), 52 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 258c20758e80..eb74e63df5cf 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -667,8 +667,9 @@ typedef struct pglist_data {
> wait_queue_head_t pfmemalloc_wait;
> struct task_struct *kswapd; /* Protected by
> mem_hotplug_begin/end() */
> - int kswapd_max_order;
> - enum zone_type classzone_idx;
> + int kswapd_order;
> + enum zone_type kswapd_classzone_idx;
> +
> #ifdef CONFIG_COMPACTION
> int kcompactd_max_order;
> enum zone_type kcompactd_classzone_idx;
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index c5278360ca66..065140ecd081 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -1209,9 +1209,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
>
> arch_refresh_nodedata(nid, pgdat);
> } else {
> - /* Reset the nr_zones and classzone_idx to 0 before reuse */
> + /* Reset the nr_zones, order and classzone_idx before reuse */
> pgdat->nr_zones = 0;
> - pgdat->classzone_idx = 0;
> + pgdat->kswapd_order = 0;
> + pgdat->kswapd_classzone_idx = 0;
> }
>
> /* we can use NODE_DATA(nid) from here */
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 59e4463e5dce..f58548139bf2 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -6084,7 +6084,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
> unsigned long end_pfn = 0;
>
> /* pg_data_t should be reset to zero when it's allocated */
> - WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
> + WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
>
> reset_deferred_meminit(pgdat);
> pgdat->node_id = nid;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index a52167eabc96..b524d3b72527 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2762,7 +2762,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
>
> /* kswapd must be awake if processes are being throttled */
> if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
> - pgdat->classzone_idx = min(pgdat->classzone_idx,
> + pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
> (enum zone_type)ZONE_NORMAL);
> wake_up_interruptible(&pgdat->kswapd_wait);
> }
> @@ -3238,8 +3238,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> return sc.order;
> }
>
> -static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> - int classzone_idx, int balanced_classzone_idx)
> +static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
> + int classzone_idx)
> {
> long remaining = 0;
> DEFINE_WAIT(wait);
> @@ -3249,9 +3249,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
>
> prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
>
> + /*
> + * If kswapd has not been woken recently, then kswapd goes fully
> + * to sleep. kcompactd may still need to wake if the original
> + * request was high-order.
> + */
> + if (classzone_idx == -1) {
> + wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
> + classzone_idx = MAX_NR_ZONES - 1;
> + goto full_sleep;
> + }
Passing -1 to kcompactd would cause the problem?
> +
> /* Try to sleep for a short interval */
> - if (prepare_kswapd_sleep(pgdat, order, remaining,
> - balanced_classzone_idx)) {
> + if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
> /*
> * Compaction records what page blocks it recently failed to
> * isolate pages from and skips them in the future scanning.
> @@ -3264,19 +3274,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> * We have freed the memory, now we should compact it to make
> * allocation of the requested order possible.
> */
> - wakeup_kcompactd(pgdat, order, classzone_idx);
> + wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
>
> remaining = schedule_timeout(HZ/10);
> finish_wait(&pgdat->kswapd_wait, &wait);
> prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
> }
>
> +full_sleep:
> /*
> * After a short sleep, check if it was a premature sleep. If not, then
> * go fully to sleep until explicitly woken up.
> */
> - if (prepare_kswapd_sleep(pgdat, order, remaining,
> - balanced_classzone_idx)) {
> + if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
> trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
>
> /*
> @@ -3317,9 +3327,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> */
> static int kswapd(void *p)
> {
> - unsigned long order, new_order;
> - int classzone_idx, new_classzone_idx;
> - int balanced_classzone_idx;
> + unsigned int alloc_order, reclaim_order, classzone_idx;
> pg_data_t *pgdat = (pg_data_t*)p;
> struct task_struct *tsk = current;
>
> @@ -3349,38 +3357,26 @@ static int kswapd(void *p)
> tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
> set_freezable();
>
> - order = new_order = 0;
> - classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
> - balanced_classzone_idx = classzone_idx;
> + pgdat->kswapd_order = alloc_order = reclaim_order = 0;
> + pgdat->kswapd_classzone_idx = classzone_idx = -1;
> for ( ; ; ) {
> bool ret;
>
> +kswapd_try_sleep:
> + kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
> + classzone_idx);
> +
> /*
> - * While we were reclaiming, there might have been another
> - * wakeup, so check the values.
> + * Read the new order and classzone_idx which may be -1 if
> + * kswapd_try_to_sleep() woke up after a short timeout instead
> + * of being woken by the page allocator.
> */
> - new_order = pgdat->kswapd_max_order;
> - new_classzone_idx = pgdat->classzone_idx;
> - pgdat->kswapd_max_order = 0;
> - pgdat->classzone_idx = pgdat->nr_zones - 1;
> -
> - if (order < new_order || classzone_idx > new_classzone_idx) {
> - /*
> - * Don't sleep if someone wants a larger 'order'
> - * allocation or has tigher zone constraints
> - */
> - order = new_order;
> - classzone_idx = new_classzone_idx;
> - } else {
> - kswapd_try_to_sleep(pgdat, order, classzone_idx,
> - balanced_classzone_idx);
> - order = pgdat->kswapd_max_order;
> - classzone_idx = pgdat->classzone_idx;
> - new_order = order;
> - new_classzone_idx = classzone_idx;
> - pgdat->kswapd_max_order = 0;
> - pgdat->classzone_idx = pgdat->nr_zones - 1;
> - }
> + alloc_order = reclaim_order = pgdat->kswapd_order;
> + classzone_idx = pgdat->kswapd_classzone_idx;
> + if (classzone_idx == -1)
> + classzone_idx = MAX_NR_ZONES - 1;
> + pgdat->kswapd_order = 0;
> + pgdat->kswapd_classzone_idx = -1;
>
> ret = try_to_freeze();
> if (kthread_should_stop())
> @@ -3390,12 +3386,24 @@ static int kswapd(void *p)
> * We can speed up thawing tasks if we don't call balance_pgdat
> * after returning from the refrigerator
> */
> - if (!ret) {
> - trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
> + if (ret)
> + continue;
>
> - /* return value ignored until next patch */
> - balance_pgdat(pgdat, order, classzone_idx);
> - }
> + /*
> + * Reclaim begins at the requested order but if a high-order
> + * reclaim fails then kswapd falls back to reclaiming for
> + * order-0. If that happens, kswapd will consider sleeping
> + * for the order it finished reclaiming at (reclaim_order)
> + * but kcompactd is woken to compact for the original
> + * request (alloc_order).
> + */
> + trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order);
> + reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
> + if (reclaim_order < alloc_order)
> + goto kswapd_try_sleep;
This 'goto' would cause kswapd to sleep prematurely. We need to check
*new* pgdat->kswapd_order and classzone_idx even in this case.
> +
> + alloc_order = reclaim_order = pgdat->kswapd_order;
> + classzone_idx = pgdat->kswapd_classzone_idx;
> }
>
> tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
> @@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
> return;
> pgdat = zone->zone_pgdat;
> - if (pgdat->kswapd_max_order < order) {
> - pgdat->kswapd_max_order = order;
> - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
> - }
> + if (pgdat->kswapd_classzone_idx == -1)
> + pgdat->kswapd_classzone_idx = classzone_idx;
> + pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
> + pgdat->kswapd_order = max(pgdat->kswapd_order, order);
Now, updating pgdat->skwapd_max_order and classzone_idx happens
unconditionally. Before your patch, it is only updated toward hard
constraint (e.g. higher order).
And, I'd like to know why max() is used for classzone_idx rather than
min()? I think that kswapd should balance the lowest zone requested.
Thanks.
> if (!waitqueue_active(&pgdat->kswapd_wait))
> return;
> if (zone_balanced(zone, order, 0))
> --
> 2.6.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 20/31] mm, vmscan: only wakeup kswapd once per node for the requested classzone
2016-07-01 20:01 ` [PATCH 20/31] mm, vmscan: only wakeup kswapd once per node for the requested classzone Mel Gorman
@ 2016-07-07 1:24 ` Joonsoo Kim
2016-07-07 10:58 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-07 1:24 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:28PM +0100, Mel Gorman wrote:
> kswapd is woken when zones are below the low watermark but the wakeup
> decision is not taking the classzone into account. Now that reclaim is
> node-based, it is only required to wake kswapd once per node and only if
> all zones are unbalanced for the requested classzone.
>
> Note that one node might be checked multiple times if the zonelist is
> ordered by node because there is no cheap way of tracking what nodes have
> already been visited. For zone-ordering, each node should be checked only
> once.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
> mm/page_alloc.c | 8 ++++++--
> mm/vmscan.c | 13 +++++++++++--
> 2 files changed, 17 insertions(+), 4 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 441f482bf9a2..2fe2fbb4f2ad 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3410,10 +3410,14 @@ static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
> {
> struct zoneref *z;
> struct zone *zone;
> + pg_data_t *last_pgdat = NULL;
>
> for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
> - ac->high_zoneidx, ac->nodemask)
> - wakeup_kswapd(zone, order, ac_classzone_idx(ac));
> + ac->high_zoneidx, ac->nodemask) {
> + if (last_pgdat != zone->zone_pgdat)
> + wakeup_kswapd(zone, order, ac_classzone_idx(ac));
> + last_pgdat = zone->zone_pgdat;
> + }
> }
In wakeup_kswapd(), there is a check if it is a populated zone or not.
If first zone in node is not a populated zone, wakeup_kswapd() would be
skipped. Though, I'm not sure if zonelist can include a un-populated
zone. Perhaps, moving populated zone check in wakeup_kswapd() to here
would be a safe code.
Thanks.
>
> static inline unsigned int
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index c1c8b77d8cb4..e02091be0e12 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -3420,6 +3420,7 @@ static int kswapd(void *p)
> void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> {
> pg_data_t *pgdat;
> + int z;
>
> if (!populated_zone(zone))
> return;
> @@ -3433,8 +3434,16 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> pgdat->kswapd_order = max(pgdat->kswapd_order, order);
> if (!waitqueue_active(&pgdat->kswapd_wait))
> return;
> - if (zone_balanced(zone, order, 0))
> - return;
> +
> + /* Only wake kswapd if all zones are unbalanced */
> + for (z = 0; z <= classzone_idx; z++) {
> + zone = pgdat->node_zones + z;
> + if (!populated_zone(zone))
> + continue;
> +
> + if (zone_balanced(zone, order, classzone_idx))
> + return;
> + }
>
> trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
> wake_up_interruptible(&pgdat->kswapd_wait);
> --
> 2.6.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 09/31] mm, vmscan: by default have direct reclaim only shrink once per node
2016-07-01 20:01 ` [PATCH 09/31] mm, vmscan: by default have direct reclaim only shrink once per node Mel Gorman
@ 2016-07-07 1:43 ` Joonsoo Kim
2016-07-07 10:27 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-07 1:43 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 01, 2016 at 09:01:17PM +0100, Mel Gorman wrote:
> Direct reclaim iterates over all zones in the zonelist and shrinking them
> but this is in conflict with node-based reclaim. In the default case,
> only shrink once per node.
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
> mm/vmscan.c | 19 +++++++++++--------
> 1 file changed, 11 insertions(+), 8 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index b524d3b72527..34656173a670 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2552,14 +2552,6 @@ static inline bool compaction_ready(struct zone *zone, int order, int classzone_
> * try to reclaim pages from zones which will satisfy the caller's allocation
> * request.
> *
> - * We reclaim from a zone even if that zone is over high_wmark_pages(zone).
> - * Because:
> - * a) The caller may be trying to free *extra* pages to satisfy a higher-order
> - * allocation or
> - * b) The target zone may be at high_wmark_pages(zone) but the lower zones
> - * must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
> - * zone defense algorithm.
> - *
> * If a zone is deemed to be full of pinned pages then just give it a light
> * scan then give up on it.
> */
> @@ -2571,6 +2563,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
> unsigned long nr_soft_scanned;
> gfp_t orig_mask;
> enum zone_type classzone_idx;
> + pg_data_t *last_pgdat = NULL;
>
> /*
> * If the number of buffer_heads in the machine exceeds the maximum
> @@ -2600,6 +2593,16 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
> classzone_idx--;
>
> /*
> + * Shrink each node in the zonelist once. If the zonelist is
> + * ordered by zone (not the default) then a node may be
> + * shrunk multiple times but in that case the user prefers
> + * lower zones being preserved
> + */
> + if (zone->zone_pgdat == last_pgdat)
> + continue;
> + last_pgdat = zone->zone_pgdat;
> +
> + /*
After this change, compaction_ready() which uses zone information
would be called with highest zone in node. So, if some lower zone in
that node is compaction-ready, we cannot stop the reclaim.
Thanks.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-06 8:31 ` Mel Gorman
@ 2016-07-07 5:51 ` Minchan Kim
2016-07-07 9:56 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-07 5:51 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Wed, Jul 06, 2016 at 09:31:21AM +0100, Mel Gorman wrote:
> On Wed, Jul 06, 2016 at 09:30:54AM +0900, Minchan Kim wrote:
> > On Tue, Jul 05, 2016 at 11:26:39AM +0100, Mel Gorman wrote:
> >
> > <snip>
> >
> > > > > @@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> > > > > if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
> > > > > return;
> > > > > pgdat = zone->zone_pgdat;
> > > > > - if (pgdat->kswapd_max_order < order) {
> > > > > - pgdat->kswapd_max_order = order;
> > > > > - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
> > > > > - }
> > > > > + if (pgdat->kswapd_classzone_idx == -1)
> > > > > + pgdat->kswapd_classzone_idx = classzone_idx;
> > > >
> > > > It's tricky. Couldn't we change kswapd_classzone_idx to integer type
> > > > and remove if above if condition?
> > > >
> > >
> > > It's tricky and not necessarily better overall. It's perfectly possible
> > > to be woken up for zone index 0 so it's changing -1 to another magic
> > > value.
> >
> > I don't get it. What is a problem with this?
> >
>
> It becomes difficult to tell the difference between "no wakeup and init to
> zone 0" and "wakeup and reclaim for zone 0". At least that's the problem
> I ran into when I tried before settling on -1.
Sorry for bothering you several times. I cannot parse what you mean.
I didn't mean -1 is problem here but why do we need below two lines
I removed?
IOW, what's the problem if we apply below patch?
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c538a8c..6eb23f5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3413,9 +3413,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
return;
pgdat = zone->zone_pgdat;
- if (pgdat->kswapd_classzone_idx == -1)
- pgdat->kswapd_classzone_idx = classzone_idx;
- pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+ pgdat->kswapd_classzone_idx = max_t(int, pgdat->kswapd_classzone_idx, classzone_idx);
pgdat->kswapd_order = max(pgdat->kswapd_order, order);
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
>
> --
> Mel Gorman
> SUSE Labs
^ permalink raw reply related [flat|nested] 90+ messages in thread
* Re: [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone
2016-07-06 8:42 ` Mel Gorman
@ 2016-07-07 6:27 ` Minchan Kim
2016-07-07 10:55 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Minchan Kim @ 2016-07-07 6:27 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Wed, Jul 06, 2016 at 09:42:00AM +0100, Mel Gorman wrote:
<snip>
> > > >
> > > > If buffer_head is over limit, old logic force to reclaim highmem but
> > > > this zone_balanced logic will prevent it.
> > > >
> > >
> > > The old logic was always busted on 64-bit because is_highmem would always
> > > be 0. The original intent appears to be that buffer_heads_over_limit
> > > would release the buffers when pages went inactive. There are a number
> >
> > Yes but the difference is in old, it was handled both direct and background
> > reclaim once buffers_heads is over the limit but your change slightly
> > changs it so kswapd couldn't reclaim high zone if any eligible zone
> > is balanced. I don't know how big difference it can make but we saw
> > highmem buffer_head problems several times, IIRC. So, I just wanted
> > to notice it to you. whether it's handled or not, it's up to you.
> >
>
> The last time I remember buffer_heads_over_limit was an NTFS filesystem
> using small sub-page block sizes with a large highmem:lowmem ratio. If a
> similar situation is encountered then a test patch would be something like;
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index dc12af938a8d..a8ebd1871f16 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -3151,7 +3151,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> * zone was balanced even under extreme pressure when the
> * overall node may be congested.
> */
> - for (i = sc.reclaim_idx; i >= 0; i--) {
> + for (i = sc.reclaim_idx; i >= 0 && !buffer_heads_over_limit; i--) {
> zone = pgdat->node_zones + i;
> if (!populated_zone(zone))
> continue;
>
> I'm not going to go with it for now because buffer_heads_over_limit is not
> necessarily a problem unless lowmem is factor. We don't want background
> reclaim to go ahead unnecessarily just because buffer_heads_over_limit.
> It could be distinguished by only forcing reclaim to go ahead on systems
> with highmem.
If you don't think it's a problem, I don't want to insist on it because I don't
have any report/workload right now. Instead, please write some comment in there
for others to understand why kswapd is okay to ignore buffer_heads_over_limit
unlike direct reclaim. Such non-symmetric behavior is really hard to follow
without any description.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries
2016-07-06 8:58 ` Mel Gorman
2016-07-06 9:33 ` Mel Gorman
@ 2016-07-07 6:47 ` Minchan Kim
1 sibling, 0 replies; 90+ messages in thread
From: Minchan Kim @ 2016-07-07 6:47 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Wed, Jul 06, 2016 at 09:58:50AM +0100, Mel Gorman wrote:
> On Wed, Jul 06, 2016 at 09:02:52AM +0900, Minchan Kim wrote:
> > On Fri, Jul 01, 2016 at 09:01:39PM +0100, Mel Gorman wrote:
> > > The number of LRU pages, dirty pages and writeback pages must be accounted
> > > for on both zones and nodes because of the reclaim retry logic, compaction
> > > retry logic and highmem calculations all depending on per-zone stats.
> > >
> > > The retry logic is only critical for allocations that can use any zones.
> >
> > Sorry, I cannot follow this assertion.
> > Could you explain?
> >
>
> The patch has been reworked since and I tried clarifying the changelog.
> Does this help?
Thanks. It is surely better than old but not clear to me, yet.
>
> --- 8<----
> mm, vmstat: remove zone and node double accounting by approximating retries
>
> The number of LRU pages, dirty pages and writeback pages must be accounted
> for on both zones and nodes because of the reclaim retry logic, compaction
> retry logic and highmem calculations all depending on per-zone stats.
>
> Many lowmem allocations are immune from OOM kill due to a check in
> __alloc_pages_may_oom for (ac->high_zoneidx < ZONE_NORMAL) since commit
> 03668b3ceb0c ("oom: avoid oom killer for lowmem allocations"). The exception
> is costly high-order allocations or allocations that cannot fail. If the
> __alloc_pages_may_oom avoids OOM-kill for low-order lowmem allocations
> then a check in __alloc_pages_slowpath will always retry.
If I read code rightly, __alloc_pages_slowpath will never retry in that case
because __alloc_pages_may_oom will return 0's did_some_progress vaule
so it would go to warn_alloc_failed unless direct compaction is successful.
>
> Hence this patch will always retry reclaim for zone-constrained allocations
> in should_reclaim_retry.
>
> As there is no guarantee enough memory can ever be freed to satisfy
> compaction, this patch avoids retrying compaction for zone-contrained
> allocations.o
>
> In combination, that means that the per-node stats can be used when deciding
> whether to continue reclaim using a rough approximation. While it is
> possible this will make the wrong decision on occasion, it will not infinite
> loop as the number of reclaim attempts is capped by MAX_RECLAIM_RETRIES.
>
> The final step is calculating the number of dirtyable highmem pages. As
> those calculations only care about the global count of file pages in
> highmem. This patch uses a global counter used instead of per-zone stats
> as it is sufficient.
>
> In combination, this allows the per-zone LRU and dirty state counters to
> be removed.
>
> Suggested by: Michal Hocko <mhocko@kernel.org>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
>
> diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
> index 9aadcc781857..c68680aac044 100644
> --- a/include/linux/mm_inline.h
> +++ b/include/linux/mm_inline.h
> @@ -4,6 +4,22 @@
> #include <linux/huge_mm.h>
> #include <linux/swap.h>
>
> +#ifdef CONFIG_HIGHMEM
> +extern unsigned long highmem_file_pages;
> +
> +static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
> + int nr_pages)
> +{
> + if (is_highmem_idx(zid) && is_file_lru(lru))
> + highmem_file_pages += nr_pages;
> +}
> +#else
> +static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
> + int nr_pages)
> +{
> +}
> +#endif
> +
> /**
> * page_is_file_cache - should the page be on a file LRU or anon LRU?
> * @page: the page to test
> @@ -29,9 +45,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec,
> struct pglist_data *pgdat = lruvec_pgdat(lruvec);
>
> __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
> - __mod_zone_page_state(&pgdat->node_zones[zid],
> - NR_ZONE_LRU_BASE + !!is_file_lru(lru),
> - nr_pages);
> + acct_highmem_file_pages(zid, lru, nr_pages);
> }
>
> static __always_inline void update_lru_size(struct lruvec *lruvec,
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index bd33e6f1bed0..a3b7f45aac56 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -110,10 +110,6 @@ struct zone_padding {
> enum zone_stat_item {
> /* First 128 byte cacheline (assuming 64 bit words) */
> NR_FREE_PAGES,
> - NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
> - NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
> - NR_ZONE_LRU_FILE,
> - NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */
> NR_MLOCK, /* mlock()ed pages found and moved off LRU */
> NR_SLAB_RECLAIMABLE,
> NR_SLAB_UNRECLAIMABLE,
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index b17cc4830fa6..cc753c639e3d 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -307,7 +307,6 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
> struct vm_area_struct *vma);
>
> /* linux/mm/vmscan.c */
> -extern unsigned long zone_reclaimable_pages(struct zone *zone);
> extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);
> extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
> gfp_t gfp_mask, nodemask_t *mask);
> diff --git a/mm/compaction.c b/mm/compaction.c
> index a0bd85712516..dfe7dafe8e8b 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -1446,6 +1446,13 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
> {
> struct zone *zone;
> struct zoneref *z;
> + pg_data_t *last_pgdat = NULL;
> +
> +#ifdef CONFIG_HIGHMEM
> + /* Do not retry compaction for zone-constrained allocations */
> + if (!is_highmem_idx(ac->high_zoneidx))
> + return false;
> +#endif
>
> /*
> * Make sure at least one zone would pass __compaction_suitable if we continue
> @@ -1456,14 +1463,27 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
> unsigned long available;
> enum compact_result compact_result;
>
> + if (last_pgdat == zone->zone_pgdat)
> + continue;
> +
> + /*
> + * This over-estimates the number of pages available for
> + * reclaim/compaction but walking the LRU would take too
> + * long. The consequences are that compaction may retry
> + * longer than it should for a zone-constrained allocation
> + * request.
> + */
> + last_pgdat = zone->zone_pgdat;
> + available = pgdat_reclaimable_pages(zone->zone_pgdat) / order;
> +
> /*
> * Do not consider all the reclaimable memory because we do not
> * want to trash just for a single high order allocation which
> * is even not guaranteed to appear even if __compaction_suitable
> * is happy about the watermark check.
> */
> - available = zone_reclaimable_pages(zone) / order;
> available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
> + available = min(zone->managed_pages, available);
> compact_result = __compaction_suitable(zone, order, alloc_flags,
> ac_classzone_idx(ac), available);
> if (compact_result != COMPACT_SKIPPED &&
> diff --git a/mm/migrate.c b/mm/migrate.c
> index c77997dc6ed7..ed2f85e61de1 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -513,9 +513,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
> }
> if (dirty && mapping_cap_account_dirty(mapping)) {
> __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
> - __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
> __inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
> - __dec_zone_state(newzone, NR_ZONE_WRITE_PENDING);
> }
> }
> local_irq_enable();
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 3c02aa603f5a..8db1db234915 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -299,6 +299,9 @@ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
>
> return nr_pages;
> }
> +#ifdef CONFIG_HIGHMEM
> +unsigned long highmem_file_pages;
> +#endif
>
> static unsigned long highmem_dirtyable_memory(unsigned long total)
> {
> @@ -306,18 +309,17 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
> int node;
> unsigned long x = 0;
> int i;
> + unsigned long dirtyable = highmem_file_pages;
>
> for_each_node_state(node, N_HIGH_MEMORY) {
> for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) {
> struct zone *z;
> - unsigned long dirtyable;
>
> if (!is_highmem_idx(i))
> continue;
>
> z = &NODE_DATA(node)->node_zones[i];
> - dirtyable = zone_page_state(z, NR_FREE_PAGES) +
> - zone_page_state(z, NR_ZONE_LRU_FILE);
> + dirtyable += zone_page_state(z, NR_FREE_PAGES);
>
> /* watch for underflows */
> dirtyable -= min(dirtyable, high_wmark_pages(z));
> @@ -2460,7 +2462,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
>
> mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY);
> __inc_node_page_state(page, NR_FILE_DIRTY);
> - __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> __inc_node_page_state(page, NR_DIRTIED);
> __inc_wb_stat(wb, WB_RECLAIMABLE);
> __inc_wb_stat(wb, WB_DIRTIED);
> @@ -2482,7 +2483,6 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
> if (mapping_cap_account_dirty(mapping)) {
> mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
> dec_node_page_state(page, NR_FILE_DIRTY);
> - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> dec_wb_stat(wb, WB_RECLAIMABLE);
> task_io_account_cancelled_write(PAGE_SIZE);
> }
> @@ -2739,7 +2739,6 @@ int clear_page_dirty_for_io(struct page *page)
> if (TestClearPageDirty(page)) {
> mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
> dec_node_page_state(page, NR_FILE_DIRTY);
> - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> dec_wb_stat(wb, WB_RECLAIMABLE);
> ret = 1;
> }
> @@ -2786,7 +2785,6 @@ int test_clear_page_writeback(struct page *page)
> if (ret) {
> mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
> dec_node_page_state(page, NR_WRITEBACK);
> - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> inc_node_page_state(page, NR_WRITTEN);
> }
> unlock_page_memcg(page);
> @@ -2841,7 +2839,6 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
> if (!ret) {
> mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
> inc_node_page_state(page, NR_WRITEBACK);
> - inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
> }
> unlock_page_memcg(page);
> return ret;
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 030114f55b0e..ded48e580abc 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3445,6 +3445,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
> {
> struct zone *zone;
> struct zoneref *z;
> + pg_data_t *current_pgdat = NULL;
>
> /*
> * Make sure we converge to OOM if we cannot make any progress
> @@ -3454,6 +3455,14 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
> return false;
>
> /*
> + * Blindly retry allocation requests that cannot use all zones. We do
> + * not have a reliable and fast means of calculating reclaimable, dirty
> + * and writeback pages in eligible zones.
> + */
> + if (IS_ENABLED(CONFIG_HIGHMEM) && !is_highmem_idx(gfp_zone(gfp_mask)))
> + goto out;
> +
> + /*
> * Keep reclaiming pages while there is a chance this will lead somewhere.
> * If none of the target zones can satisfy our allocation request even
> * if all reclaimable pages are considered then we are screwed and have
> @@ -3463,18 +3472,38 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
> ac->nodemask) {
> unsigned long available;
> unsigned long reclaimable;
> + int zid;
>
> - available = reclaimable = zone_reclaimable_pages(zone);
> + if (current_pgdat == zone->zone_pgdat)
> + continue;
> +
> + current_pgdat = zone->zone_pgdat;
> + available = reclaimable = pgdat_reclaimable_pages(current_pgdat);
> available -= DIV_ROUND_UP(no_progress_loops * available,
> MAX_RECLAIM_RETRIES);
> - available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
> +
> + /* Account for all free pages on eligible zones */
> + for (zid = 0; zid <= zone_idx(zone); zid++) {
> + struct zone *acct_zone = ¤t_pgdat->node_zones[zid];
> +
> + available += zone_page_state_snapshot(acct_zone, NR_FREE_PAGES);
> + }
>
> /*
> * Would the allocation succeed if we reclaimed the whole
> - * available?
> + * available? This is approximate because there is no
> + * accurate count of reclaimable pages per zone.
> */
> - if (__zone_watermark_ok(zone, order, min_wmark_pages(zone),
> - ac_classzone_idx(ac), alloc_flags, available)) {
> + for (zid = 0; zid <= zone_idx(zone); zid++) {
> + struct zone *check_zone = ¤t_pgdat->node_zones[zid];
> + unsigned long estimate;
> +
> + estimate = min(check_zone->managed_pages, available);
> + if (!__zone_watermark_ok(check_zone, order,
> + min_wmark_pages(check_zone), ac_classzone_idx(ac),
> + alloc_flags, estimate))
> + continue;
> +
> /*
> * If we didn't make any progress and have a lot of
> * dirty + writeback pages then we should wait for
> @@ -3484,15 +3513,16 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
> if (!did_some_progress) {
> unsigned long write_pending;
>
> - write_pending = zone_page_state_snapshot(zone,
> - NR_ZONE_WRITE_PENDING);
> + write_pending =
> + node_page_state(current_pgdat, NR_WRITEBACK) +
> + node_page_state(current_pgdat, NR_FILE_DIRTY);
>
> if (2 * write_pending > reclaimable) {
> congestion_wait(BLK_RW_ASYNC, HZ/10);
> return true;
> }
> }
> -
> +out:
> /*
> * Memory allocation/reclaim might be called from a WQ
> * context and the current implementation of the WQ
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 9eed2d3e05f3..a8ebd1871f16 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -194,22 +194,6 @@ static bool sane_reclaim(struct scan_control *sc)
> }
> #endif
>
> -/*
> - * This misses isolated pages which are not accounted for to save counters.
> - * As the data only determines if reclaim or compaction continues, it is
> - * not expected that isolated pages will be a dominating factor.
> - */
> -unsigned long zone_reclaimable_pages(struct zone *zone)
> -{
> - unsigned long nr;
> -
> - nr = zone_page_state_snapshot(zone, NR_ZONE_LRU_FILE);
> - if (get_nr_swap_pages() > 0)
> - nr += zone_page_state_snapshot(zone, NR_ZONE_LRU_ANON);
> -
> - return nr;
> -}
> -
> unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat)
> {
> unsigned long nr;
> @@ -3167,7 +3151,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> * zone was balanced even under extreme pressure when the
> * overall node may be congested.
> */
> - for (i = sc.reclaim_idx; i >= 0; i--) {
> + for (i = sc.reclaim_idx; i >= 0 && !buffer_heads_over_limit; i--) {
> zone = pgdat->node_zones + i;
> if (!populated_zone(zone))
> continue;
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 60372f31fee3..7415775faf08 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -921,9 +921,6 @@ int fragmentation_index(struct zone *zone, unsigned int order)
> const char * const vmstat_text[] = {
> /* enum zone_stat_item countes */
> "nr_free_pages",
> - "nr_zone_anon_lru",
> - "nr_zone_file_lru",
> - "nr_zone_write_pending",
> "nr_mlock",
> "nr_slab_reclaimable",
> "nr_slab_unreclaimable",
>
> --
> Mel Gorman
> SUSE Labs
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-07 1:12 ` Joonsoo Kim
@ 2016-07-07 9:48 ` Mel Gorman
2016-07-08 2:28 ` Joonsoo Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-07 9:48 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 07, 2016 at 10:12:12AM +0900, Joonsoo Kim wrote:
> > @@ -1402,6 +1406,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
> >
> > VM_BUG_ON_PAGE(!PageLRU(page), page);
> >
> > + if (page_zonenum(page) > sc->reclaim_idx) {
> > + list_move(&page->lru, &pages_skipped);
> > + continue;
> > + }
> > +
>
> I think that we don't need to skip LRU pages in active list. What we'd
> like to do is just skipping actual reclaim since it doesn't make
> freepage that we need. It's unrelated to skip the page in active list.
>
Why?
The active aging is sometimes about simply aging the LRU list. Aging the
active list based on the timing of when a zone-constrained allocation arrives
potentially introduces the same zone-balancing problems we currently have
and applying them to node-lru.
> And, I have a concern that if inactive LRU is full with higher zone's
> LRU pages, reclaim with low reclaim_idx could be stuck.
That is an outside possibility but unlikely given that it would require
that all outstanding allocation requests are zone-contrained. If it happens
that a premature OOM is encountered while the active list is large then
inactive_list_is_low could take scan_control as a parameter and use a
different ratio for zone-contrained allocations if scan priority is elevated.
It would be preferred to have an actual test case for this so the
altered ratio can be tested instead of introducing code that may be
useless or dead.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-07 5:51 ` Minchan Kim
@ 2016-07-07 9:56 ` Mel Gorman
0 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-07 9:56 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 07, 2016 at 02:51:21PM +0900, Minchan Kim wrote:
> > It becomes difficult to tell the difference between "no wakeup and init to
> > zone 0" and "wakeup and reclaim for zone 0". At least that's the problem
> > I ran into when I tried before settling on -1.
>
> Sorry for bothering you several times. I cannot parse what you mean.
> I didn't mean -1 is problem here but why do we need below two lines
> I removed?
>
What you have should be fine. The hazard initially was that both
classzone_idx and kswapd_classzone_idx are enum and the signedness of
enum is implementation-dependent. Using max_t avoids that but it's a
subtle. I prefer the obvious check of kswapd_classzone_idx == 1 because
it is clearer that we're checking for an initialised value instead of
depending on a side-effect of the casting in max_t to do the right thing.
I can apply it if you wish, I just don't think it helps.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-07 1:20 ` Joonsoo Kim
@ 2016-07-07 10:17 ` Mel Gorman
2016-07-08 2:44 ` Joonsoo Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-07 10:17 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 07, 2016 at 10:20:39AM +0900, Joonsoo Kim wrote:
> > @@ -3249,9 +3249,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> >
> > prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
> >
> > + /*
> > + * If kswapd has not been woken recently, then kswapd goes fully
> > + * to sleep. kcompactd may still need to wake if the original
> > + * request was high-order.
> > + */
> > + if (classzone_idx == -1) {
> > + wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
> > + classzone_idx = MAX_NR_ZONES - 1;
> > + goto full_sleep;
> > + }
>
> Passing -1 to kcompactd would cause the problem?
>
No, it ends up doing a wakeup and then going back to sleep which is not
what is required. I'll fix it.
> > @@ -3390,12 +3386,24 @@ static int kswapd(void *p)
> > * We can speed up thawing tasks if we don't call balance_pgdat
> > * after returning from the refrigerator
> > */
> > - if (!ret) {
> > - trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
> > + if (ret)
> > + continue;
> >
> > - /* return value ignored until next patch */
> > - balance_pgdat(pgdat, order, classzone_idx);
> > - }
> > + /*
> > + * Reclaim begins at the requested order but if a high-order
> > + * reclaim fails then kswapd falls back to reclaiming for
> > + * order-0. If that happens, kswapd will consider sleeping
> > + * for the order it finished reclaiming at (reclaim_order)
> > + * but kcompactd is woken to compact for the original
> > + * request (alloc_order).
> > + */
> > + trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order);
> > + reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
> > + if (reclaim_order < alloc_order)
> > + goto kswapd_try_sleep;
>
> This 'goto' would cause kswapd to sleep prematurely. We need to check
> *new* pgdat->kswapd_order and classzone_idx even in this case.
>
It only matters if the next request coming is also high-order requests but
one thing that needs to be avoided is kswapd staying awake periods of time
constantly reclaiming for high-order pages. This is why the check means
"If we reclaimed for high-order and failed, then consider sleeping now".
If allocations still require it, they direct reclaim instead.
"Fixing" this potentially causes reclaim storms from kswapd.
> > @@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> > if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
> > return;
> > pgdat = zone->zone_pgdat;
> > - if (pgdat->kswapd_max_order < order) {
> > - pgdat->kswapd_max_order = order;
> > - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
> > - }
> > + if (pgdat->kswapd_classzone_idx == -1)
> > + pgdat->kswapd_classzone_idx = classzone_idx;
> > + pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
> > + pgdat->kswapd_order = max(pgdat->kswapd_order, order);
>
> Now, updating pgdat->skwapd_max_order and classzone_idx happens
> unconditionally. Before your patch, it is only updated toward hard
> constraint (e.g. higher order).
>
So? It's updating the request to suit the requirements of all pending
allocation requests that woke kswapd.
> And, I'd like to know why max() is used for classzone_idx rather than
> min()? I think that kswapd should balance the lowest zone requested.
>
If there are two allocation requests -- one zone-constraned and the other
zone-unconstrained, it does not make sense to have kswapd skip the pages
usable for the zone-unconstrained and waste a load of CPU. You could
argue that using min would satisfy the zone-constrained allocation faster
but that's at the cost of delaying the zone-unconstrained allocation and
wasting CPU. Bear in mind that using max may mean some lowmem pages get
freed anyway due to LRU order.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 09/31] mm, vmscan: by default have direct reclaim only shrink once per node
2016-07-07 1:43 ` Joonsoo Kim
@ 2016-07-07 10:27 ` Mel Gorman
0 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-07 10:27 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 07, 2016 at 10:43:22AM +0900, Joonsoo Kim wrote:
> > @@ -2600,6 +2593,16 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
> > classzone_idx--;
> >
> > /*
> > + * Shrink each node in the zonelist once. If the zonelist is
> > + * ordered by zone (not the default) then a node may be
> > + * shrunk multiple times but in that case the user prefers
> > + * lower zones being preserved
> > + */
> > + if (zone->zone_pgdat == last_pgdat)
> > + continue;
> > + last_pgdat = zone->zone_pgdat;
> > +
> > + /*
>
> After this change, compaction_ready() which uses zone information
> would be called with highest zone in node. So, if some lower zone in
> that node is compaction-ready, we cannot stop the reclaim.
>
Yes. It only impacts direct reclaim but potentially it's an issue. I'll
fix it.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone
2016-07-07 6:27 ` Minchan Kim
@ 2016-07-07 10:55 ` Mel Gorman
0 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-07 10:55 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 07, 2016 at 03:27:01PM +0900, Minchan Kim wrote:
> > I'm not going to go with it for now because buffer_heads_over_limit is not
> > necessarily a problem unless lowmem is factor. We don't want background
> > reclaim to go ahead unnecessarily just because buffer_heads_over_limit.
> > It could be distinguished by only forcing reclaim to go ahead on systems
> > with highmem.
>
> If you don't think it's a problem, I don't want to insist on it because I don't
> have any report/workload right now. Instead, please write some comment in there
> for others to understand why kswapd is okay to ignore buffer_heads_over_limit
> unlike direct reclaim. Such non-symmetric behavior is really hard to follow
> without any description.
Ok, I'll add a patch later in the series that addresses the issue.
Currently it's called "mm, vmscan: Have kswapd reclaim from all zones if
reclaiming and buffer_heads_over_limit".
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 20/31] mm, vmscan: only wakeup kswapd once per node for the requested classzone
2016-07-07 1:24 ` Joonsoo Kim
@ 2016-07-07 10:58 ` Mel Gorman
0 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-07 10:58 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 07, 2016 at 10:24:23AM +0900, Joonsoo Kim wrote:
> On Fri, Jul 01, 2016 at 09:01:28PM +0100, Mel Gorman wrote:
> > kswapd is woken when zones are below the low watermark but the wakeup
> > decision is not taking the classzone into account. Now that reclaim is
> > node-based, it is only required to wake kswapd once per node and only if
> > all zones are unbalanced for the requested classzone.
> >
> > Note that one node might be checked multiple times if the zonelist is
> > ordered by node because there is no cheap way of tracking what nodes have
> > already been visited. For zone-ordering, each node should be checked only
> > once.
> >
> > Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> > Acked-by: Vlastimil Babka <vbabka@suse.cz>
> > ---
> > mm/page_alloc.c | 8 ++++++--
> > mm/vmscan.c | 13 +++++++++++--
> > 2 files changed, 17 insertions(+), 4 deletions(-)
> >
> > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > index 441f482bf9a2..2fe2fbb4f2ad 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -3410,10 +3410,14 @@ static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
> > {
> > struct zoneref *z;
> > struct zone *zone;
> > + pg_data_t *last_pgdat = NULL;
> >
> > for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
> > - ac->high_zoneidx, ac->nodemask)
> > - wakeup_kswapd(zone, order, ac_classzone_idx(ac));
> > + ac->high_zoneidx, ac->nodemask) {
> > + if (last_pgdat != zone->zone_pgdat)
> > + wakeup_kswapd(zone, order, ac_classzone_idx(ac));
> > + last_pgdat = zone->zone_pgdat;
> > + }
> > }
>
> In wakeup_kswapd(), there is a check if it is a populated zone or not.
It's redundant.
> If first zone in node is not a populated zone, wakeup_kswapd() would be
> skipped. Though, I'm not sure if zonelist can include a un-populated
> zone.
Zonelists do not contain unpopulated zones.
> Perhaps, moving populated zone check in wakeup_kswapd() to here
> would be a safe code.
>
If anything was going to happen to it, it should be deleted. It's a
minor cleanup.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries
2016-07-06 18:12 ` Dave Hansen
@ 2016-07-07 11:26 ` Mel Gorman
0 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-07 11:26 UTC (permalink / raw)
To: Dave Hansen
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Wed, Jul 06, 2016 at 11:12:52AM -0700, Dave Hansen wrote:
> On 07/01/2016 01:01 PM, Mel Gorman wrote:
> > +#ifdef CONFIG_HIGHMEM
> > +extern unsigned long highmem_file_pages;
> > +
> > +static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
> > + int nr_pages)
> > +{
> > + if (is_highmem_idx(zid) && is_file_lru(lru))
> > + highmem_file_pages += nr_pages;
> > +}
> > +#else
>
> Shouldn't highmem_file_pages technically be an atomic_t (or atomic64_t)?
> We could have highmem on two nodes which take two different LRU locks.
It would require a NUMA machine with highmem or very weird
configurations but sure, atomic is safer.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-07 9:48 ` Mel Gorman
@ 2016-07-08 2:28 ` Joonsoo Kim
2016-07-08 10:05 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-08 2:28 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 07, 2016 at 10:48:08AM +0100, Mel Gorman wrote:
> On Thu, Jul 07, 2016 at 10:12:12AM +0900, Joonsoo Kim wrote:
> > > @@ -1402,6 +1406,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
> > >
> > > VM_BUG_ON_PAGE(!PageLRU(page), page);
> > >
> > > + if (page_zonenum(page) > sc->reclaim_idx) {
> > > + list_move(&page->lru, &pages_skipped);
> > > + continue;
> > > + }
> > > +
> >
> > I think that we don't need to skip LRU pages in active list. What we'd
> > like to do is just skipping actual reclaim since it doesn't make
> > freepage that we need. It's unrelated to skip the page in active list.
> >
>
> Why?
>
> The active aging is sometimes about simply aging the LRU list. Aging the
> active list based on the timing of when a zone-constrained allocation arrives
> potentially introduces the same zone-balancing problems we currently have
> and applying them to node-lru.
Could you explain more? I don't understand why aging the active list
based on the timing of when a zone-constrained allocation arrives
introduces the zone-balancing problem again.
I think that if above logic is applied to both the active/inactive
list, it could cause zone-balancing problem. LRU pages on lower zone
can be resident on memory with more chance. What we want to do with
node-lru is aging all the lru pages equally as much as possible. So,
basically, we need to age active/inactive list regardless allocation
type. But, there is a possibility that zone-constrained allocation
would reclaim too many LRU pages unnecessarily to satisfy zone-constrained
allocation, so we need to implement skipping such a page. It can be
done by just skipping the page in inactive list.
>
> > And, I have a concern that if inactive LRU is full with higher zone's
> > LRU pages, reclaim with low reclaim_idx could be stuck.
>
> That is an outside possibility but unlikely given that it would require
> that all outstanding allocation requests are zone-contrained. If it happens
I'm not sure that it is outside possibility. It can also happens if there
is zone-contrained allocation requestor and parallel memory hogger. In
this case, memory would be reclaimed by memory hogger but memory hogger would
consume them again so inactive LRU is continually full with higher
zone's LRU pages and zone-contrained allocation requestor cannot
progress.
> that a premature OOM is encountered while the active list is large then
> inactive_list_is_low could take scan_control as a parameter and use a
> different ratio for zone-contrained allocations if scan priority is elevated.
It would work.
> It would be preferred to have an actual test case for this so the
> altered ratio can be tested instead of introducing code that may be
> useless or dead.
Yes, actual test case would be preferred. I will try to implement
an artificial test case by myself but I'm not sure when I can do it.
Thanks.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-07 10:17 ` Mel Gorman
@ 2016-07-08 2:44 ` Joonsoo Kim
2016-07-08 10:11 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-08 2:44 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 07, 2016 at 11:17:01AM +0100, Mel Gorman wrote:
> On Thu, Jul 07, 2016 at 10:20:39AM +0900, Joonsoo Kim wrote:
> > > @@ -3249,9 +3249,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
> > >
> > > prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
> > >
> > > + /*
> > > + * If kswapd has not been woken recently, then kswapd goes fully
> > > + * to sleep. kcompactd may still need to wake if the original
> > > + * request was high-order.
> > > + */
> > > + if (classzone_idx == -1) {
> > > + wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
> > > + classzone_idx = MAX_NR_ZONES - 1;
> > > + goto full_sleep;
> > > + }
> >
> > Passing -1 to kcompactd would cause the problem?
> >
>
> No, it ends up doing a wakeup and then going back to sleep which is not
> what is required. I'll fix it.
>
> > > @@ -3390,12 +3386,24 @@ static int kswapd(void *p)
> > > * We can speed up thawing tasks if we don't call balance_pgdat
> > > * after returning from the refrigerator
> > > */
> > > - if (!ret) {
> > > - trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
> > > + if (ret)
> > > + continue;
> > >
> > > - /* return value ignored until next patch */
> > > - balance_pgdat(pgdat, order, classzone_idx);
> > > - }
> > > + /*
> > > + * Reclaim begins at the requested order but if a high-order
> > > + * reclaim fails then kswapd falls back to reclaiming for
> > > + * order-0. If that happens, kswapd will consider sleeping
> > > + * for the order it finished reclaiming at (reclaim_order)
> > > + * but kcompactd is woken to compact for the original
> > > + * request (alloc_order).
> > > + */
> > > + trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order);
> > > + reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
> > > + if (reclaim_order < alloc_order)
> > > + goto kswapd_try_sleep;
> >
> > This 'goto' would cause kswapd to sleep prematurely. We need to check
> > *new* pgdat->kswapd_order and classzone_idx even in this case.
> >
>
> It only matters if the next request coming is also high-order requests but
> one thing that needs to be avoided is kswapd staying awake periods of time
> constantly reclaiming for high-order pages. This is why the check means
> "If we reclaimed for high-order and failed, then consider sleeping now".
> If allocations still require it, they direct reclaim instead.
But, assume that next request is zone-constrained allocation. We need
to balance memory for it but kswapd would skip it.
>
> "Fixing" this potentially causes reclaim storms from kswapd.
>
> > > @@ -3418,10 +3426,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
> > > if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
> > > return;
> > > pgdat = zone->zone_pgdat;
> > > - if (pgdat->kswapd_max_order < order) {
> > > - pgdat->kswapd_max_order = order;
> > > - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
> > > - }
> > > + if (pgdat->kswapd_classzone_idx == -1)
> > > + pgdat->kswapd_classzone_idx = classzone_idx;
> > > + pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
> > > + pgdat->kswapd_order = max(pgdat->kswapd_order, order);
> >
> > Now, updating pgdat->skwapd_max_order and classzone_idx happens
> > unconditionally. Before your patch, it is only updated toward hard
> > constraint (e.g. higher order).
> >
>
> So? It's updating the request to suit the requirements of all pending
> allocation requests that woke kswapd.
>
> > And, I'd like to know why max() is used for classzone_idx rather than
> > min()? I think that kswapd should balance the lowest zone requested.
> >
>
> If there are two allocation requests -- one zone-constraned and the other
> zone-unconstrained, it does not make sense to have kswapd skip the pages
> usable for the zone-unconstrained and waste a load of CPU. You could
I agree that, in this case, it's not good to skip the pages usable
for the zone-unconstrained request. But, what I am concerned is that
kswapd stop reclaim prematurely in the view of zone-constrained
requestor. Kswapd decide to stop reclaim if one of eligible zone is
balanced and this max() makes eligible zone higher than the one
zone-unconstrained requestor want.
Thanks.
> argue that using min would satisfy the zone-constrained allocation faster
> but that's at the cost of delaying the zone-unconstrained allocation and
> wasting CPU. Bear in mind that using max may mean some lowmem pages get
> freed anyway due to LRU order.
>
> --
> Mel Gorman
> SUSE Labs
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-08 2:28 ` Joonsoo Kim
@ 2016-07-08 10:05 ` Mel Gorman
2016-07-14 6:28 ` Joonsoo Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-08 10:05 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 08, 2016 at 11:28:52AM +0900, Joonsoo Kim wrote:
> On Thu, Jul 07, 2016 at 10:48:08AM +0100, Mel Gorman wrote:
> > On Thu, Jul 07, 2016 at 10:12:12AM +0900, Joonsoo Kim wrote:
> > > > @@ -1402,6 +1406,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
> > > >
> > > > VM_BUG_ON_PAGE(!PageLRU(page), page);
> > > >
> > > > + if (page_zonenum(page) > sc->reclaim_idx) {
> > > > + list_move(&page->lru, &pages_skipped);
> > > > + continue;
> > > > + }
> > > > +
> > >
> > > I think that we don't need to skip LRU pages in active list. What we'd
> > > like to do is just skipping actual reclaim since it doesn't make
> > > freepage that we need. It's unrelated to skip the page in active list.
> > >
> >
> > Why?
> >
> > The active aging is sometimes about simply aging the LRU list. Aging the
> > active list based on the timing of when a zone-constrained allocation arrives
> > potentially introduces the same zone-balancing problems we currently have
> > and applying them to node-lru.
>
> Could you explain more? I don't understand why aging the active list
> based on the timing of when a zone-constrained allocation arrives
> introduces the zone-balancing problem again.
>
I mispoke. Avoid rotation of the active list based on the timing of a
zone-constrained allocation is what I think potentially introduces problems.
If there are zone-constrained allocations aging the active list then I worry
that pages would be artificially preserved on the active list. No matter
what we do, there is distortion of the aging for zone-constrained allocation
because right now, it may deactivate high zone pages sooner than expected.
> I think that if above logic is applied to both the active/inactive
> list, it could cause zone-balancing problem. LRU pages on lower zone
> can be resident on memory with more chance.
If anything, with node-based LRU, it's high zone pages that can be resident
on memory for longer but only if there are zone-constrained allocations.
If we always reclaim based on age regardless of allocation requirements
then there is a risk that high zones are reclaimed far earlier than expected.
Basically, whether we skip pages in the active list or not there are
distortions with page aging and the impact is workload dependent. Right now,
I see no clear advantage to special casing active aging.
If we suspect this is a problem in the future, it would be a simple matter
of adding an additional bool parameter to isolate_lru_pages.
> > > And, I have a concern that if inactive LRU is full with higher zone's
> > > LRU pages, reclaim with low reclaim_idx could be stuck.
> >
> > That is an outside possibility but unlikely given that it would require
> > that all outstanding allocation requests are zone-contrained. If it happens
>
> I'm not sure that it is outside possibility. It can also happens if there
> is zone-contrained allocation requestor and parallel memory hogger. In
> this case, memory would be reclaimed by memory hogger but memory hogger would
> consume them again so inactive LRU is continually full with higher
> zone's LRU pages and zone-contrained allocation requestor cannot
> progress.
>
The same memory hogger will also be reclaiming the highmem pages and
reallocating highmem pages.
> > It would be preferred to have an actual test case for this so the
> > altered ratio can be tested instead of introducing code that may be
> > useless or dead.
>
> Yes, actual test case would be preferred. I will try to implement
> an artificial test case by myself but I'm not sure when I can do it.
>
That would be appreciated.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-08 2:44 ` Joonsoo Kim
@ 2016-07-08 10:11 ` Mel Gorman
2016-07-14 5:23 ` Joonsoo Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-08 10:11 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 08, 2016 at 11:44:47AM +0900, Joonsoo Kim wrote:
> > > > @@ -3390,12 +3386,24 @@ static int kswapd(void *p)
> > > > * We can speed up thawing tasks if we don't call balance_pgdat
> > > > * after returning from the refrigerator
> > > > */
> > > > - if (!ret) {
> > > > - trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
> > > > + if (ret)
> > > > + continue;
> > > >
> > > > - /* return value ignored until next patch */
> > > > - balance_pgdat(pgdat, order, classzone_idx);
> > > > - }
> > > > + /*
> > > > + * Reclaim begins at the requested order but if a high-order
> > > > + * reclaim fails then kswapd falls back to reclaiming for
> > > > + * order-0. If that happens, kswapd will consider sleeping
> > > > + * for the order it finished reclaiming at (reclaim_order)
> > > > + * but kcompactd is woken to compact for the original
> > > > + * request (alloc_order).
> > > > + */
> > > > + trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order);
> > > > + reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
> > > > + if (reclaim_order < alloc_order)
> > > > + goto kswapd_try_sleep;
> > >
> > > This 'goto' would cause kswapd to sleep prematurely. We need to check
> > > *new* pgdat->kswapd_order and classzone_idx even in this case.
> > >
> >
> > It only matters if the next request coming is also high-order requests but
> > one thing that needs to be avoided is kswapd staying awake periods of time
> > constantly reclaiming for high-order pages. This is why the check means
> > "If we reclaimed for high-order and failed, then consider sleeping now".
> > If allocations still require it, they direct reclaim instead.
>
> But, assume that next request is zone-constrained allocation. We need
> to balance memory for it but kswapd would skip it.
>
Then it'll also be woken up again in the very near future as the
zone-constrained allocation. If the zone is at the min watermark, then
it'll have direct reclaimed but between min and low, it'll be a simple
wakeup.
The premature sleep, wakeup with new requests logic was a complete mess.
However, what I did do is remove the -1 handling of kswapd_classzone_idx
handling and the goto full-sleep. In the event of a premature wakeup,
it'll recheck for wakeups and if none has occured, it'll use the old
classzone information.
Note that it will *not* use the original allocation order if it's a
premature sleep. This is because it's known that high-order reclaim
failed in the near past and restarting it has a high risk of
overreclaiming.
> > > And, I'd like to know why max() is used for classzone_idx rather than
> > > min()? I think that kswapd should balance the lowest zone requested.
> > >
> >
> > If there are two allocation requests -- one zone-constraned and the other
> > zone-unconstrained, it does not make sense to have kswapd skip the pages
> > usable for the zone-unconstrained and waste a load of CPU. You could
>
> I agree that, in this case, it's not good to skip the pages usable
> for the zone-unconstrained request. But, what I am concerned is that
> kswapd stop reclaim prematurely in the view of zone-constrained
> requestor.
It doesn't stop reclaiming for the lower zones. It's reclaiming the LRU
for the whole node that may or may not have lower zone pages at the end
of the LRU. If it does, then the allocation request will be satisfied.
If it does not, then kswapd will think the node is balanced and get
rewoken to do a zone-constrained reclaim pass.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-08 10:11 ` Mel Gorman
@ 2016-07-14 5:23 ` Joonsoo Kim
2016-07-14 8:32 ` Vlastimil Babka
2016-07-14 9:05 ` Mel Gorman
0 siblings, 2 replies; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-14 5:23 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 08, 2016 at 11:11:47AM +0100, Mel Gorman wrote:
> On Fri, Jul 08, 2016 at 11:44:47AM +0900, Joonsoo Kim wrote:
> > > > > @@ -3390,12 +3386,24 @@ static int kswapd(void *p)
> > > > > * We can speed up thawing tasks if we don't call balance_pgdat
> > > > > * after returning from the refrigerator
> > > > > */
> > > > > - if (!ret) {
> > > > > - trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
> > > > > + if (ret)
> > > > > + continue;
> > > > >
> > > > > - /* return value ignored until next patch */
> > > > > - balance_pgdat(pgdat, order, classzone_idx);
> > > > > - }
> > > > > + /*
> > > > > + * Reclaim begins at the requested order but if a high-order
> > > > > + * reclaim fails then kswapd falls back to reclaiming for
> > > > > + * order-0. If that happens, kswapd will consider sleeping
> > > > > + * for the order it finished reclaiming at (reclaim_order)
> > > > > + * but kcompactd is woken to compact for the original
> > > > > + * request (alloc_order).
> > > > > + */
> > > > > + trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order);
> > > > > + reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
> > > > > + if (reclaim_order < alloc_order)
> > > > > + goto kswapd_try_sleep;
> > > >
> > > > This 'goto' would cause kswapd to sleep prematurely. We need to check
> > > > *new* pgdat->kswapd_order and classzone_idx even in this case.
> > > >
> > >
> > > It only matters if the next request coming is also high-order requests but
> > > one thing that needs to be avoided is kswapd staying awake periods of time
> > > constantly reclaiming for high-order pages. This is why the check means
> > > "If we reclaimed for high-order and failed, then consider sleeping now".
> > > If allocations still require it, they direct reclaim instead.
> >
> > But, assume that next request is zone-constrained allocation. We need
> > to balance memory for it but kswapd would skip it.
> >
>
> Then it'll also be woken up again in the very near future as the
> zone-constrained allocation. If the zone is at the min watermark, then
> it'll have direct reclaimed but between min and low, it'll be a simple
> wakeup.
>
> The premature sleep, wakeup with new requests logic was a complete mess.
> However, what I did do is remove the -1 handling of kswapd_classzone_idx
> handling and the goto full-sleep. In the event of a premature wakeup,
> it'll recheck for wakeups and if none has occured, it'll use the old
> classzone information.
>
> Note that it will *not* use the original allocation order if it's a
> premature sleep. This is because it's known that high-order reclaim
> failed in the near past and restarting it has a high risk of
> overreclaiming.
>
> > > > And, I'd like to know why max() is used for classzone_idx rather than
> > > > min()? I think that kswapd should balance the lowest zone requested.
> > > >
> > >
> > > If there are two allocation requests -- one zone-constraned and the other
> > > zone-unconstrained, it does not make sense to have kswapd skip the pages
> > > usable for the zone-unconstrained and waste a load of CPU. You could
> >
> > I agree that, in this case, it's not good to skip the pages usable
> > for the zone-unconstrained request. But, what I am concerned is that
> > kswapd stop reclaim prematurely in the view of zone-constrained
> > requestor.
>
> It doesn't stop reclaiming for the lower zones. It's reclaiming the LRU
> for the whole node that may or may not have lower zone pages at the end
> of the LRU. If it does, then the allocation request will be satisfied.
> If it does not, then kswapd will think the node is balanced and get
> rewoken to do a zone-constrained reclaim pass.
If zone-constrained request could go direct reclaim pass, there would
be no problem. But, please assume that request is zone-constrained
without __GFP_DIRECT_RECLAIM which is common for some device driver
implementation. And, please assume one more thing that this request
always comes with zone-unconstrained allocation request. In this case,
your max() logic will set kswapd_classzone_idx to highest zone index
and re-worken kswapd would not balance for low zone again. In the end,
zone-constrained allocation request without __GFP_DIRECT_RECLAIM could
fail.
Thanks.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-08 10:05 ` Mel Gorman
@ 2016-07-14 6:28 ` Joonsoo Kim
2016-07-14 7:48 ` Vlastimil Babka
2016-07-18 12:11 ` Mel Gorman
0 siblings, 2 replies; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-14 6:28 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Fri, Jul 08, 2016 at 11:05:32AM +0100, Mel Gorman wrote:
> On Fri, Jul 08, 2016 at 11:28:52AM +0900, Joonsoo Kim wrote:
> > On Thu, Jul 07, 2016 at 10:48:08AM +0100, Mel Gorman wrote:
> > > On Thu, Jul 07, 2016 at 10:12:12AM +0900, Joonsoo Kim wrote:
> > > > > @@ -1402,6 +1406,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
> > > > >
> > > > > VM_BUG_ON_PAGE(!PageLRU(page), page);
> > > > >
> > > > > + if (page_zonenum(page) > sc->reclaim_idx) {
> > > > > + list_move(&page->lru, &pages_skipped);
> > > > > + continue;
> > > > > + }
> > > > > +
> > > >
> > > > I think that we don't need to skip LRU pages in active list. What we'd
> > > > like to do is just skipping actual reclaim since it doesn't make
> > > > freepage that we need. It's unrelated to skip the page in active list.
> > > >
> > >
> > > Why?
> > >
> > > The active aging is sometimes about simply aging the LRU list. Aging the
> > > active list based on the timing of when a zone-constrained allocation arrives
> > > potentially introduces the same zone-balancing problems we currently have
> > > and applying them to node-lru.
> >
> > Could you explain more? I don't understand why aging the active list
> > based on the timing of when a zone-constrained allocation arrives
> > introduces the zone-balancing problem again.
> >
>
> I mispoke. Avoid rotation of the active list based on the timing of a
> zone-constrained allocation is what I think potentially introduces problems.
> If there are zone-constrained allocations aging the active list then I worry
> that pages would be artificially preserved on the active list. No matter
> what we do, there is distortion of the aging for zone-constrained allocation
> because right now, it may deactivate high zone pages sooner than expected.
>
> > I think that if above logic is applied to both the active/inactive
> > list, it could cause zone-balancing problem. LRU pages on lower zone
> > can be resident on memory with more chance.
>
> If anything, with node-based LRU, it's high zone pages that can be resident
> on memory for longer but only if there are zone-constrained allocations.
> If we always reclaim based on age regardless of allocation requirements
> then there is a risk that high zones are reclaimed far earlier than expected.
>
> Basically, whether we skip pages in the active list or not there are
> distortions with page aging and the impact is workload dependent. Right now,
> I see no clear advantage to special casing active aging.
>
> If we suspect this is a problem in the future, it would be a simple matter
> of adding an additional bool parameter to isolate_lru_pages.
Okay. I agree that it would be a simple matter.
>
> > > > And, I have a concern that if inactive LRU is full with higher zone's
> > > > LRU pages, reclaim with low reclaim_idx could be stuck.
> > >
> > > That is an outside possibility but unlikely given that it would require
> > > that all outstanding allocation requests are zone-contrained. If it happens
> >
> > I'm not sure that it is outside possibility. It can also happens if there
> > is zone-contrained allocation requestor and parallel memory hogger. In
> > this case, memory would be reclaimed by memory hogger but memory hogger would
> > consume them again so inactive LRU is continually full with higher
> > zone's LRU pages and zone-contrained allocation requestor cannot
> > progress.
> >
>
> The same memory hogger will also be reclaiming the highmem pages and
> reallocating highmem pages.
>
> > > It would be preferred to have an actual test case for this so the
> > > altered ratio can be tested instead of introducing code that may be
> > > useless or dead.
> >
> > Yes, actual test case would be preferred. I will try to implement
> > an artificial test case by myself but I'm not sure when I can do it.
> >
>
> That would be appreciated.
I make an artificial test case and test this series by using next tree
(next-20160713) and found a regression.
My test setup is:
memory: 2048 mb
movablecore: 1500 mb (imitates highmem system to test effect of skip logic)
swapoff
forever repeat: sequential read file (1500 mb) (using mmap) by 2 threads
3000 processes fork
lowmem is roughly 500 mb and it is enough to keep 3000 processes. I
test this artificial scenario with v4.7-rc5 and find no problem. But,
with next-20160713, OOM kill is triggered as below.
-------- oops -------
fork invoked oom-killer: gfp_mask=0x27000c0(GFP_KERNEL_ACCOUNT|__GFP_NOTRACK), order=2, oom_score_adj=0
fork cpuset=/ mems_allowed=0
CPU: 0 PID: 10478 Comm: fork Not tainted 4.7.0-rc7-next-20160713 #646
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014
0000000000000000 ffff880014273b18 ffffffff8142b8c3 ffff880014273d20
ffff88001c44a500 ffff880014273b90 ffffffff81240b6e ffffffff81e6f0e0
ffff880014273b40 ffffffff810de08d ffff880014273b60 0000000000000206
Call Trace:
[<ffffffff8142b8c3>] dump_stack+0x85/0xc2
[<ffffffff81240b6e>] dump_header+0x5c/0x22e
[<ffffffff810de08d>] ? trace_hardirqs_on+0xd/0x10
[<ffffffff811b3381>] oom_kill_process+0x221/0x3f0
[<ffffffff810901b7>] ? has_capability_noaudit+0x17/0x20
[<ffffffff811b3acf>] out_of_memory+0x52f/0x560
[<ffffffff811b377c>] ? out_of_memory+0x1dc/0x560
[<ffffffff811ba004>] __alloc_pages_nodemask+0x1154/0x11b0
[<ffffffff810813a1>] ? copy_process.part.30+0x121/0x1bf0
[<ffffffff810813a1>] copy_process.part.30+0x121/0x1bf0
[<ffffffff811ebb06>] ? handle_mm_fault+0xb36/0x13d0
[<ffffffff810fb60d>] ? debug_lockdep_rcu_enabled+0x1d/0x20
[<ffffffff81083066>] _do_fork+0xe6/0x6a0
[<ffffffff810836c9>] SyS_clone+0x19/0x20
[<ffffffff81003e13>] do_syscall_64+0x73/0x1e0
[<ffffffff81858ec3>] entry_SYSCALL64_slow_path+0x25/0x25
Mem-Info:
active_anon:19756 inactive_anon:18 isolated_anon:0
active_file:142480 inactive_file:266065 isolated_file:0
unevictable:0 dirty:0 writeback:0 unstable:0
slab_reclaimable:6777 slab_unreclaimable:19127
mapped:389778 shmem:95 pagetables:17512 bounce:0
free:9533 free_pcp:80 free_cma:0
Node 0 active_anon:79024kB inactive_anon:72kB active_file:569920kB inactive_file:1064260kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:1559112kB dirty:0kB writeback:0kB shmem:0kB shmem_thp
: 0kB shmem_pmdmapped: 0kB anon_thp: 380kB writeback_tmp:0kB unstable:0kB all_unreclaimable? yes
Node 0 DMA free:2172kB min:204kB low:252kB high:300kB present:15992kB managed:15908kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:2272kB kernel_stack:1216kB pagetables:2436kB bounce:0kB free_pcp:0k
B local_pcp:0kB free_cma:0kB node_pages_scanned:15639736
lowmem_reserve[]: 0 493 493 1955
Node 0 DMA32 free:6372kB min:6492kB low:8112kB high:9732kB present:2080632kB managed:508600kB mlocked:0kB slab_reclaimable:27108kB slab_unreclaimable:74236kB kernel_stack:32752kB pagetables:67612kB bounce:
0kB free_pcp:112kB local_pcp:12kB free_cma:0kB node_pages_scanned:16302012
lowmem_reserve[]: 0 0 0 1462
Node 0 Normal free:0kB min:0kB low:0kB high:0kB present:18446744073708015752kB managed:0kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB lo
cal_pcp:0kB free_cma:0kB node_pages_scanned:17033632
lowmem_reserve[]: 0 0 0 11698
Node 0 Movable free:29588kB min:19256kB low:24068kB high:28880kB present:1535864kB managed:1500964kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_
pcp:208kB local_pcp:112kB free_cma:0kB node_pages_scanned:17725436
lowmem_reserve[]: 0 0 0 0
Node 0 DMA: 1*4kB (M) 1*8kB (U) 1*16kB (M) 1*32kB (M) 1*64kB (M) 2*128kB (UM) 1*256kB (M) 1*512kB (U) 1*1024kB (U) 0*2048kB 0*4096kB = 2172kB
Node 0 DMA32: 60*4kB (ME) 45*8kB (UME) 24*16kB (ME) 13*32kB (UM) 12*64kB (UM) 6*128kB (UM) 6*256kB (M) 4*512kB (UM) 0*1024kB 0*2048kB 0*4096kB = 6520kB
Node 0 Normal: 0*4kB 0*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 0kB
Node 0 Movable: 1*4kB (M) 130*8kB (M) 68*16kB (M) 30*32kB (M) 13*64kB (M) 9*128kB (M) 4*256kB (M) 0*512kB 1*1024kB (M) 1*2048kB (M) 5*4096kB (M) = 29652kB
Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB
408717 total pagecache pages
0 pages in swap cache
Swap cache stats: add 0, delete 0, find 0/0
Free swap = 0kB
Total swap = 0kB
524156 pages RAM
0 pages HighMem/MovableOnly
17788 pages reserved
0 pages cma reserved
0 pages hwpoisoned
-------- another one -------
fork invoked oom-killer: gfp_mask=0x25080c0(GFP_KERNEL_ACCOUNT|__GFP_ZERO), order=0, oom_score_adj=0
fork cpuset=/ mems_allowed=0
CPU: 3 PID: 7538 Comm: fork Not tainted 4.7.0-rc7-next-20160713 #646
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014
0000000000000000 ffff8800141eb960 ffffffff8142b8c3 ffff8800141ebb68
ffff88001c46a500 ffff8800141eb9d8 ffffffff81240b6e ffffffff81e6f0e0
ffff8800141eb988 ffffffff810de08d ffff8800141eb9a8 0000000000000206
Call Trace:
[<ffffffff8142b8c3>] dump_stack+0x85/0xc2
[<ffffffff81240b6e>] dump_header+0x5c/0x22e
[<ffffffff810de08d>] ? trace_hardirqs_on+0xd/0x10
[<ffffffff811b3381>] oom_kill_process+0x221/0x3f0
[<ffffffff810901b7>] ? has_capability_noaudit+0x17/0x20
[<ffffffff811b3acf>] out_of_memory+0x52f/0x560
[<ffffffff811b377c>] ? out_of_memory+0x1dc/0x560
[<ffffffff811ba004>] __alloc_pages_nodemask+0x1154/0x11b0
[<ffffffff8120ed61>] ? alloc_pages_current+0xa1/0x1f0
[<ffffffff8120ed61>] alloc_pages_current+0xa1/0x1f0
[<ffffffff811eae37>] ? __pmd_alloc+0x37/0x1d0
[<ffffffff811eae37>] __pmd_alloc+0x37/0x1d0
[<ffffffff811ed627>] copy_page_range+0x947/0xa50
[<ffffffff811f9386>] ? anon_vma_fork+0xd6/0x150
[<ffffffff81432bd2>] ? __rb_insert_augmented+0x132/0x210
[<ffffffff81082035>] copy_process.part.30+0xdb5/0x1bf0
[<ffffffff81083066>] _do_fork+0xe6/0x6a0
[<ffffffff810836c9>] SyS_clone+0x19/0x20
[<ffffffff81003e13>] do_syscall_64+0x73/0x1e0
[<ffffffff81858ec3>] entry_SYSCALL64_slow_path+0x25/0x25
Mem-Info:
active_anon:18779 inactive_anon:18 isolated_anon:0
active_file:91577 inactive_file:320615 isolated_file:0
unevictable:0 dirty:0 writeback:0 unstable:0
slab_reclaimable:6741 slab_unreclaimable:18124
mapped:389774 shmem:95 pagetables:18332 bounce:0
free:8194 free_pcp:140 free_cma:0
Node 0 active_anon:75116kB inactive_anon:72kB active_file:366308kB inactive_file:1282460kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:1559096kB dirty:0kB writeback:0kB shmem:0kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 380kB writeback_tmp:0kB unstable:0kB all_unreclaimable? yes
Node 0 DMA free:2172kB min:204kB low:252kB high:300kB present:15992kB managed:15908kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:2380kB kernel_stack:1632kB pagetables:3632kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB node_pages_scanned:13673372
lowmem_reserve[]: 0 493 493 1955
Node 0 DMA32 free:6444kB min:6492kB low:8112kB high:9732kB present:2080632kB managed:508600kB mlocked:0kB slab_reclaimable:26964kB slab_unreclaimable:70116kB kernel_stack:30496kB pagetables:69696kB bounce:0kB free_pcp:316kB local_pcp:100kB free_cma:0kB node_pages_scanned:13673372
lowmem_reserve[]: 0 0 0 1462
Node 0 Normal free:0kB min:0kB low:0kB high:0kB present:18446744073708015752kB managed:0kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB node_pages_scanned:13673832
lowmem_reserve[]: 0 0 0 11698
Node 0 Movable free:24200kB min:19256kB low:24068kB high:28880kB present:1535864kB managed:1500964kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:956kB local_pcp:100kB free_cma:0kB node_pages_scanned:1504
lowmem_reserve[]: 0 0 0 0
Node 0 DMA: 2*4kB (M) 0*8kB 1*16kB (M) 0*32kB 1*64kB (M) 0*128kB 2*256kB (UM) 1*512kB (M) 1*1024kB (U) 0*2048kB 0*4096kB = 2136kB
Node 0 DMA32: 58*4kB (ME) 40*8kB (UME) 27*16kB (UME) 15*32kB (ME) 8*64kB (UM) 5*128kB (M) 10*256kB (UM) 1*512kB (U) 1*1024kB (M) 0*2048kB 0*4096kB = 6712kB
Node 0 Normal: 0*4kB 0*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 0kB
Node 0 Movable: 40*4kB (M) 8*8kB (M) 3*16kB (M) 6*32kB (M) 7*64kB (M) 2*128kB (M) 1*256kB (M) 2*512kB (M) 2*1024kB (M) 1*2048kB (M) 5*4096kB (M) = 27024kB
Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB
411446 total pagecache pages
0 pages in swap cache
Swap cache stats: add 0, delete 0, find 0/0
Free swap = 0kB
Total swap = 0kB
524156 pages RAM
0 pages HighMem/MovableOnly
17788 pages reserved
0 pages cma reserved
Size of active/inactive_file is larger than size of movable zone so I guess
there is reclaimable pages on DMA32 and it would mean that there is some problems
related to skip logic. Could you help how to check it?
Thanks.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-14 6:28 ` Joonsoo Kim
@ 2016-07-14 7:48 ` Vlastimil Babka
2016-07-18 4:52 ` Joonsoo Kim
2016-07-18 12:11 ` Mel Gorman
1 sibling, 1 reply; 90+ messages in thread
From: Vlastimil Babka @ 2016-07-14 7:48 UTC (permalink / raw)
To: Joonsoo Kim, Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Johannes Weiner, LKML
On 07/14/2016 08:28 AM, Joonsoo Kim wrote:
> On Fri, Jul 08, 2016 at 11:05:32AM +0100, Mel Gorman wrote:
>> On Fri, Jul 08, 2016 at 11:28:52AM +0900, Joonsoo Kim wrote:
>>> On Thu, Jul 07, 2016 at 10:48:08AM +0100, Mel Gorman wrote:
>>>> On Thu, Jul 07, 2016 at 10:12:12AM +0900, Joonsoo Kim wrote:
>>>>>> @@ -1402,6 +1406,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
>>>>>>
>>>>>> VM_BUG_ON_PAGE(!PageLRU(page), page);
>>>>>>
>>>>>> + if (page_zonenum(page) > sc->reclaim_idx) {
>>>>>> + list_move(&page->lru, &pages_skipped);
>>>>>> + continue;
>>>>>> + }
>>>>>> +
>>>>>
>>>>> I think that we don't need to skip LRU pages in active list. What we'd
>>>>> like to do is just skipping actual reclaim since it doesn't make
>>>>> freepage that we need. It's unrelated to skip the page in active list.
>>>>>
>>>>
>>>> Why?
>>>>
>>>> The active aging is sometimes about simply aging the LRU list. Aging the
>>>> active list based on the timing of when a zone-constrained allocation arrives
>>>> potentially introduces the same zone-balancing problems we currently have
>>>> and applying them to node-lru.
>>>
>>> Could you explain more? I don't understand why aging the active list
>>> based on the timing of when a zone-constrained allocation arrives
>>> introduces the zone-balancing problem again.
>>>
>>
>> I mispoke. Avoid rotation of the active list based on the timing of a
>> zone-constrained allocation is what I think potentially introduces problems.
>> If there are zone-constrained allocations aging the active list then I worry
>> that pages would be artificially preserved on the active list. No matter
>> what we do, there is distortion of the aging for zone-constrained allocation
>> because right now, it may deactivate high zone pages sooner than expected.
>>
>>> I think that if above logic is applied to both the active/inactive
>>> list, it could cause zone-balancing problem. LRU pages on lower zone
>>> can be resident on memory with more chance.
>>
>> If anything, with node-based LRU, it's high zone pages that can be resident
>> on memory for longer but only if there are zone-constrained allocations.
>> If we always reclaim based on age regardless of allocation requirements
>> then there is a risk that high zones are reclaimed far earlier than expected.
>>
>> Basically, whether we skip pages in the active list or not there are
>> distortions with page aging and the impact is workload dependent. Right now,
>> I see no clear advantage to special casing active aging.
>>
>> If we suspect this is a problem in the future, it would be a simple matter
>> of adding an additional bool parameter to isolate_lru_pages.
>
> Okay. I agree that it would be a simple matter.
>
>>
>>>>> And, I have a concern that if inactive LRU is full with higher zone's
>>>>> LRU pages, reclaim with low reclaim_idx could be stuck.
>>>>
>>>> That is an outside possibility but unlikely given that it would require
>>>> that all outstanding allocation requests are zone-contrained. If it happens
>>>
>>> I'm not sure that it is outside possibility. It can also happens if there
>>> is zone-contrained allocation requestor and parallel memory hogger. In
>>> this case, memory would be reclaimed by memory hogger but memory hogger would
>>> consume them again so inactive LRU is continually full with higher
>>> zone's LRU pages and zone-contrained allocation requestor cannot
>>> progress.
>>>
>>
>> The same memory hogger will also be reclaiming the highmem pages and
>> reallocating highmem pages.
>>
>>>> It would be preferred to have an actual test case for this so the
>>>> altered ratio can be tested instead of introducing code that may be
>>>> useless or dead.
>>>
>>> Yes, actual test case would be preferred. I will try to implement
>>> an artificial test case by myself but I'm not sure when I can do it.
>>>
>>
>> That would be appreciated.
>
> I make an artificial test case and test this series by using next tree
> (next-20160713) and found a regression.
>
[...]
> Mem-Info:
> active_anon:18779 inactive_anon:18 isolated_anon:0
> active_file:91577 inactive_file:320615 isolated_file:0
> unevictable:0 dirty:0 writeback:0 unstable:0
> slab_reclaimable:6741 slab_unreclaimable:18124
> mapped:389774 shmem:95 pagetables:18332 bounce:0
> free:8194 free_pcp:140 free_cma:0
> Node 0 active_anon:75116kB inactive_anon:72kB active_file:366308kB inactive_file:1282460kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:1559096kB dirty:0kB writeback:0kB shmem:0kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 380kB writeback_tmp:0kB unstable:0kB all_unreclaimable? yes
> Node 0 DMA free:2172kB min:204kB low:252kB high:300kB present:15992kB managed:15908kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:2380kB kernel_stack:1632kB pagetables:3632kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB node_pages_scanned:13673372
> lowmem_reserve[]: 0 493 493 1955
> Node 0 DMA32 free:6444kB min:6492kB low:8112kB high:9732kB present:2080632kB managed:508600kB mlocked:0kB slab_reclaimable:26964kB slab_unreclaimable:70116kB kernel_stack:30496kB pagetables:69696kB bounce:0kB free_pcp:316kB local_pcp:100kB free_cma:0kB node_pages_scanned:13673372
> lowmem_reserve[]: 0 0 0 1462
> Node 0 Normal free:0kB min:0kB low:0kB high:0kB present:18446744073708015752kB managed:0kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB node_pages_scanned:13673832
present:18446744073708015752kB
Although unlikely related to your report, that itself doesn't look
right. Any idea if that's due to your configuration and would be printed
also in the mainline kernel in case of OOM (or if /proc/zoneinfo has
similarly bogus value), or is something caused by a patch in mmotm?
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-14 5:23 ` Joonsoo Kim
@ 2016-07-14 8:32 ` Vlastimil Babka
2016-07-18 5:07 ` Joonsoo Kim
2016-07-14 9:05 ` Mel Gorman
1 sibling, 1 reply; 90+ messages in thread
From: Vlastimil Babka @ 2016-07-14 8:32 UTC (permalink / raw)
To: Joonsoo Kim, Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Johannes Weiner, LKML
On 07/14/2016 07:23 AM, Joonsoo Kim wrote:
> On Fri, Jul 08, 2016 at 11:11:47AM +0100, Mel Gorman wrote:
>> On Fri, Jul 08, 2016 at 11:44:47AM +0900, Joonsoo Kim wrote:
>>
>> It doesn't stop reclaiming for the lower zones. It's reclaiming the LRU
>> for the whole node that may or may not have lower zone pages at the end
>> of the LRU. If it does, then the allocation request will be satisfied.
>> If it does not, then kswapd will think the node is balanced and get
>> rewoken to do a zone-constrained reclaim pass.
>
> If zone-constrained request could go direct reclaim pass, there would
> be no problem. But, please assume that request is zone-constrained
> without __GFP_DIRECT_RECLAIM which is common for some device driver
> implementation. And, please assume one more thing that this request
> always comes with zone-unconstrained allocation request. In this case,
> your max() logic will set kswapd_classzone_idx to highest zone index
> and re-worken kswapd would not balance for low zone again. In the end,
> zone-constrained allocation request without __GFP_DIRECT_RECLAIM could
> fail.
I don't think there's a problem in the scenario? Kswapd will keep being
woken up and reclaim from the node lru. It will hit and free any low
zone pages that are on the lru, even though it doesn't "balance for low
zone". Eventually it will either satisfy the constrained allocation by
reclaiming those low-zone pages during the repeated wakeups, or the
low-zone wakeups will stop coming together with higher-zone wakeups and
then it will reclaim the low-zone pages in a single low-zone wakeup. If
the zone-constrained request is not allowed to fail, then it will just
keep waking up kswapd and waiting for the progress. If it's allowed to
fail (i.e. not __GFP_NOFAIL), but not allowed to direct reclaim, it goes
"goto nopage" rather quickly in __alloc_pages_slowpath(), without any
waiting for kswapd's progress, so there's not really much difference
whether the kswapd wakeup picked up a low classzone or not. Note the
__GFP_NOFAIL but ~__GFP_DIRECT_RECLAIM is a WARN_ON_ONCE() scenario, so
definitely not common...
> Thanks.
>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-14 5:23 ` Joonsoo Kim
2016-07-14 8:32 ` Vlastimil Babka
@ 2016-07-14 9:05 ` Mel Gorman
2016-07-18 5:03 ` Joonsoo Kim
1 sibling, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-14 9:05 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 14, 2016 at 02:23:32PM +0900, Joonsoo Kim wrote:
> >
> > > > > And, I'd like to know why max() is used for classzone_idx rather than
> > > > > min()? I think that kswapd should balance the lowest zone requested.
> > > > >
> > > >
> > > > If there are two allocation requests -- one zone-constraned and the other
> > > > zone-unconstrained, it does not make sense to have kswapd skip the pages
> > > > usable for the zone-unconstrained and waste a load of CPU. You could
> > >
> > > I agree that, in this case, it's not good to skip the pages usable
> > > for the zone-unconstrained request. But, what I am concerned is that
> > > kswapd stop reclaim prematurely in the view of zone-constrained
> > > requestor.
> >
> > It doesn't stop reclaiming for the lower zones. It's reclaiming the LRU
> > for the whole node that may or may not have lower zone pages at the end
> > of the LRU. If it does, then the allocation request will be satisfied.
> > If it does not, then kswapd will think the node is balanced and get
> > rewoken to do a zone-constrained reclaim pass.
>
> If zone-constrained request could go direct reclaim pass, there would
> be no problem. But, please assume that request is zone-constrained
> without __GFP_DIRECT_RECLAIM which is common for some device driver
> implementation.
Then it's likely GFP_ATOMIC and it'll wake kswapd on each failure. If
kswapd is containtly awake for highmem requests then we're reclaiming
everything anyway. Remember that if kswapd is reclaiming for higher zones,
it'll still cover the lower zones eventually. There is no guarantee that
skipping the highmem pages will satisfy the atomic allocations any faster
but consuming the CPU to skip the pages is a definite cost.
Even worse, skipping highmem pages when a highmem pages are required may
ake lowmem pressure worse because those pages are freed faster and can
be consumed by zone-unconstrained requests.
If this really is a problem in practice then we can consider having
allocation requests that are zone-constrained and !__GFP_DIRECT_RECLAIM
set a flag and use the min classzone for the wakeup. That flag remains
set until kswapd takes at least one pass using the lower classzone and
clears it. The classzone will not be adjusted higher until that flag is
cleared. I don't think we should do it without evidence that it's a real
problem because kswapd potentially uses useless CPU and the potential for
higher lowmem pressure.
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-14 7:48 ` Vlastimil Babka
@ 2016-07-18 4:52 ` Joonsoo Kim
0 siblings, 0 replies; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-18 4:52 UTC (permalink / raw)
To: Vlastimil Babka
Cc: Mel Gorman, Andrew Morton, Linux-MM, Rik van Riel, Johannes Weiner, LKML
On Thu, Jul 14, 2016 at 09:48:41AM +0200, Vlastimil Babka wrote:
> On 07/14/2016 08:28 AM, Joonsoo Kim wrote:
> >On Fri, Jul 08, 2016 at 11:05:32AM +0100, Mel Gorman wrote:
> >>On Fri, Jul 08, 2016 at 11:28:52AM +0900, Joonsoo Kim wrote:
> >>>On Thu, Jul 07, 2016 at 10:48:08AM +0100, Mel Gorman wrote:
> >>>>On Thu, Jul 07, 2016 at 10:12:12AM +0900, Joonsoo Kim wrote:
> >>>>>>@@ -1402,6 +1406,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
> >>>>>>
> >>>>>> VM_BUG_ON_PAGE(!PageLRU(page), page);
> >>>>>>
> >>>>>>+ if (page_zonenum(page) > sc->reclaim_idx) {
> >>>>>>+ list_move(&page->lru, &pages_skipped);
> >>>>>>+ continue;
> >>>>>>+ }
> >>>>>>+
> >>>>>
> >>>>>I think that we don't need to skip LRU pages in active list. What we'd
> >>>>>like to do is just skipping actual reclaim since it doesn't make
> >>>>>freepage that we need. It's unrelated to skip the page in active list.
> >>>>>
> >>>>
> >>>>Why?
> >>>>
> >>>>The active aging is sometimes about simply aging the LRU list. Aging the
> >>>>active list based on the timing of when a zone-constrained allocation arrives
> >>>>potentially introduces the same zone-balancing problems we currently have
> >>>>and applying them to node-lru.
> >>>
> >>>Could you explain more? I don't understand why aging the active list
> >>>based on the timing of when a zone-constrained allocation arrives
> >>>introduces the zone-balancing problem again.
> >>>
> >>
> >>I mispoke. Avoid rotation of the active list based on the timing of a
> >>zone-constrained allocation is what I think potentially introduces problems.
> >>If there are zone-constrained allocations aging the active list then I worry
> >>that pages would be artificially preserved on the active list. No matter
> >>what we do, there is distortion of the aging for zone-constrained allocation
> >>because right now, it may deactivate high zone pages sooner than expected.
> >>
> >>>I think that if above logic is applied to both the active/inactive
> >>>list, it could cause zone-balancing problem. LRU pages on lower zone
> >>>can be resident on memory with more chance.
> >>
> >>If anything, with node-based LRU, it's high zone pages that can be resident
> >>on memory for longer but only if there are zone-constrained allocations.
> >>If we always reclaim based on age regardless of allocation requirements
> >>then there is a risk that high zones are reclaimed far earlier than expected.
> >>
> >>Basically, whether we skip pages in the active list or not there are
> >>distortions with page aging and the impact is workload dependent. Right now,
> >>I see no clear advantage to special casing active aging.
> >>
> >>If we suspect this is a problem in the future, it would be a simple matter
> >>of adding an additional bool parameter to isolate_lru_pages.
> >
> >Okay. I agree that it would be a simple matter.
> >
> >>
> >>>>>And, I have a concern that if inactive LRU is full with higher zone's
> >>>>>LRU pages, reclaim with low reclaim_idx could be stuck.
> >>>>
> >>>>That is an outside possibility but unlikely given that it would require
> >>>>that all outstanding allocation requests are zone-contrained. If it happens
> >>>
> >>>I'm not sure that it is outside possibility. It can also happens if there
> >>>is zone-contrained allocation requestor and parallel memory hogger. In
> >>>this case, memory would be reclaimed by memory hogger but memory hogger would
> >>>consume them again so inactive LRU is continually full with higher
> >>>zone's LRU pages and zone-contrained allocation requestor cannot
> >>>progress.
> >>>
> >>
> >>The same memory hogger will also be reclaiming the highmem pages and
> >>reallocating highmem pages.
> >>
> >>>>It would be preferred to have an actual test case for this so the
> >>>>altered ratio can be tested instead of introducing code that may be
> >>>>useless or dead.
> >>>
> >>>Yes, actual test case would be preferred. I will try to implement
> >>>an artificial test case by myself but I'm not sure when I can do it.
> >>>
> >>
> >>That would be appreciated.
> >
> >I make an artificial test case and test this series by using next tree
> >(next-20160713) and found a regression.
> >
>
> [...]
>
> >Mem-Info:
> >active_anon:18779 inactive_anon:18 isolated_anon:0
> > active_file:91577 inactive_file:320615 isolated_file:0
> > unevictable:0 dirty:0 writeback:0 unstable:0
> > slab_reclaimable:6741 slab_unreclaimable:18124
> > mapped:389774 shmem:95 pagetables:18332 bounce:0
> > free:8194 free_pcp:140 free_cma:0
> >Node 0 active_anon:75116kB inactive_anon:72kB active_file:366308kB inactive_file:1282460kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:1559096kB dirty:0kB writeback:0kB shmem:0kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 380kB writeback_tmp:0kB unstable:0kB all_unreclaimable? yes
> >Node 0 DMA free:2172kB min:204kB low:252kB high:300kB present:15992kB managed:15908kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:2380kB kernel_stack:1632kB pagetables:3632kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB node_pages_scanned:13673372
> >lowmem_reserve[]: 0 493 493 1955
> >Node 0 DMA32 free:6444kB min:6492kB low:8112kB high:9732kB present:2080632kB managed:508600kB mlocked:0kB slab_reclaimable:26964kB slab_unreclaimable:70116kB kernel_stack:30496kB pagetables:69696kB bounce:0kB free_pcp:316kB local_pcp:100kB free_cma:0kB node_pages_scanned:13673372
> >lowmem_reserve[]: 0 0 0 1462
> >Node 0 Normal free:0kB min:0kB low:0kB high:0kB present:18446744073708015752kB managed:0kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB node_pages_scanned:13673832
>
> present:18446744073708015752kB
>
> Although unlikely related to your report, that itself doesn't look
> right. Any idea if that's due to your configuration and would be
> printed also in the mainline kernel in case of OOM (or if
> /proc/zoneinfo has similarly bogus value), or is something caused by
> a patch in mmotm?
Wrong present count is due to a bug when enabling MOVABLE_ZONE.
v4.7-rc5 also has the same problems.
I testes above tests with work-around of this present count bug and
find that result is the same. v4.7-rc5 is okay but next-20160713 isn't okay.
As I said before, this setup just imitate highmem system and problem
would also exist on highmem system.
In addition, on above setup, I measured hackbench performance while
there is a concurrent file reader and found that hackbench slow down
roughly 10% with nodelru.
Thanks.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-14 9:05 ` Mel Gorman
@ 2016-07-18 5:03 ` Joonsoo Kim
0 siblings, 0 replies; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-18 5:03 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 14, 2016 at 10:05:00AM +0100, Mel Gorman wrote:
> On Thu, Jul 14, 2016 at 02:23:32PM +0900, Joonsoo Kim wrote:
> > >
> > > > > > And, I'd like to know why max() is used for classzone_idx rather than
> > > > > > min()? I think that kswapd should balance the lowest zone requested.
> > > > > >
> > > > >
> > > > > If there are two allocation requests -- one zone-constraned and the other
> > > > > zone-unconstrained, it does not make sense to have kswapd skip the pages
> > > > > usable for the zone-unconstrained and waste a load of CPU. You could
> > > >
> > > > I agree that, in this case, it's not good to skip the pages usable
> > > > for the zone-unconstrained request. But, what I am concerned is that
> > > > kswapd stop reclaim prematurely in the view of zone-constrained
> > > > requestor.
> > >
> > > It doesn't stop reclaiming for the lower zones. It's reclaiming the LRU
> > > for the whole node that may or may not have lower zone pages at the end
> > > of the LRU. If it does, then the allocation request will be satisfied.
> > > If it does not, then kswapd will think the node is balanced and get
> > > rewoken to do a zone-constrained reclaim pass.
> >
> > If zone-constrained request could go direct reclaim pass, there would
> > be no problem. But, please assume that request is zone-constrained
> > without __GFP_DIRECT_RECLAIM which is common for some device driver
> > implementation.
>
> Then it's likely GFP_ATOMIC and it'll wake kswapd on each failure. If
> kswapd is containtly awake for highmem requests then we're reclaiming
> everything anyway. Remember that if kswapd is reclaiming for higher zones,
> it'll still cover the lower zones eventually. There is no guarantee that
> skipping the highmem pages will satisfy the atomic allocations any faster
> but consuming the CPU to skip the pages is a definite cost.
Okay.
>
> Even worse, skipping highmem pages when a highmem pages are required may
> ake lowmem pressure worse because those pages are freed faster and can
> be consumed by zone-unconstrained requests.
Okay.
>
> If this really is a problem in practice then we can consider having
> allocation requests that are zone-constrained and !__GFP_DIRECT_RECLAIM
> set a flag and use the min classzone for the wakeup. That flag remains
> set until kswapd takes at least one pass using the lower classzone and
> clears it. The classzone will not be adjusted higher until that flag is
It would work.
> cleared. I don't think we should do it without evidence that it's a real
> problem because kswapd potentially uses useless CPU and the potential for
> higher lowmem pressure.
Hmmm... I think differently. Your patch changes current behaviour
without any evidence. Code simplification cannot compensate
potential stability issue. Before your patch, kswapd try to
balance for minimum classzone so until dis-advantage of this approach
is proved, it's better to keep original logic.
Thanks.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-14 8:32 ` Vlastimil Babka
@ 2016-07-18 5:07 ` Joonsoo Kim
2016-07-18 6:51 ` Vlastimil Babka
0 siblings, 1 reply; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-18 5:07 UTC (permalink / raw)
To: Vlastimil Babka
Cc: Mel Gorman, Andrew Morton, Linux-MM, Rik van Riel, Johannes Weiner, LKML
On Thu, Jul 14, 2016 at 10:32:09AM +0200, Vlastimil Babka wrote:
> On 07/14/2016 07:23 AM, Joonsoo Kim wrote:
> >On Fri, Jul 08, 2016 at 11:11:47AM +0100, Mel Gorman wrote:
> >>On Fri, Jul 08, 2016 at 11:44:47AM +0900, Joonsoo Kim wrote:
> >>
> >>It doesn't stop reclaiming for the lower zones. It's reclaiming the LRU
> >>for the whole node that may or may not have lower zone pages at the end
> >>of the LRU. If it does, then the allocation request will be satisfied.
> >>If it does not, then kswapd will think the node is balanced and get
> >>rewoken to do a zone-constrained reclaim pass.
> >
> >If zone-constrained request could go direct reclaim pass, there would
> >be no problem. But, please assume that request is zone-constrained
> >without __GFP_DIRECT_RECLAIM which is common for some device driver
> >implementation. And, please assume one more thing that this request
> >always comes with zone-unconstrained allocation request. In this case,
> >your max() logic will set kswapd_classzone_idx to highest zone index
> >and re-worken kswapd would not balance for low zone again. In the end,
> >zone-constrained allocation request without __GFP_DIRECT_RECLAIM could
> >fail.
>
> I don't think there's a problem in the scenario? Kswapd will keep
> being woken up and reclaim from the node lru. It will hit and free
> any low zone pages that are on the lru, even though it doesn't
> "balance for low zone". Eventually it will either satisfy the
> constrained allocation by reclaiming those low-zone pages during the
> repeated wakeups, or the low-zone wakeups will stop coming together
> with higher-zone wakeups and then it will reclaim the low-zone pages
> in a single low-zone wakeup. If the zone-constrained request is not
Yes, probability of this would be low.
> allowed to fail, then it will just keep waking up kswapd and waiting
> for the progress. If it's allowed to fail (i.e. not __GFP_NOFAIL),
> but not allowed to direct reclaim, it goes "goto nopage" rather
> quickly in __alloc_pages_slowpath(), without any waiting for
> kswapd's progress, so there's not really much difference whether the
> kswapd wakeup picked up a low classzone or not. Note the
Hmm... Even if allocation could fail, we should do our best to prevent
failure. Relying on luck isn't good idea to me.
Thanks.
> __GFP_NOFAIL but ~__GFP_DIRECT_RECLAIM is a WARN_ON_ONCE() scenario,
> so definitely not common...
>
> >Thanks.
> >
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-18 5:07 ` Joonsoo Kim
@ 2016-07-18 6:51 ` Vlastimil Babka
2016-07-18 7:24 ` Joonsoo Kim
0 siblings, 1 reply; 90+ messages in thread
From: Vlastimil Babka @ 2016-07-18 6:51 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Mel Gorman, Andrew Morton, Linux-MM, Rik van Riel, Johannes Weiner, LKML
On 07/18/2016 07:07 AM, Joonsoo Kim wrote:
> On Thu, Jul 14, 2016 at 10:32:09AM +0200, Vlastimil Babka wrote:
>> On 07/14/2016 07:23 AM, Joonsoo Kim wrote:
>>
>> I don't think there's a problem in the scenario? Kswapd will keep
>> being woken up and reclaim from the node lru. It will hit and free
>> any low zone pages that are on the lru, even though it doesn't
>> "balance for low zone". Eventually it will either satisfy the
>> constrained allocation by reclaiming those low-zone pages during the
>> repeated wakeups, or the low-zone wakeups will stop coming together
>> with higher-zone wakeups and then it will reclaim the low-zone pages
>> in a single low-zone wakeup. If the zone-constrained request is not
>
> Yes, probability of this would be low.
>
>> allowed to fail, then it will just keep waking up kswapd and waiting
>> for the progress. If it's allowed to fail (i.e. not __GFP_NOFAIL),
>> but not allowed to direct reclaim, it goes "goto nopage" rather
>> quickly in __alloc_pages_slowpath(), without any waiting for
>> kswapd's progress, so there's not really much difference whether the
>> kswapd wakeup picked up a low classzone or not. Note the
>
> Hmm... Even if allocation could fail, we should do our best to prevent
> failure. Relying on luck isn't good idea to me.
But "Doing our best" has to have some sane limits. Allocation, that
cannot direct reclaim, already relies on luck. And we are not really
changing this. The allocation will "goto nopage" before kswapd can even
wake up and start doing something, regardless of classzone_idx used.
> Thanks.
>
>> __GFP_NOFAIL but ~__GFP_DIRECT_RECLAIM is a WARN_ON_ONCE() scenario,
>> so definitely not common...
>>
>>> Thanks.
>>>
>>
>> --
>> To unsubscribe, send a message with 'unsubscribe linux-mm' in
>> the body to majordomo@kvack.org. For more info on Linux MM,
>> see: http://www.linux-mm.org/ .
>> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps
2016-07-18 6:51 ` Vlastimil Babka
@ 2016-07-18 7:24 ` Joonsoo Kim
0 siblings, 0 replies; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-18 7:24 UTC (permalink / raw)
To: Vlastimil Babka
Cc: Mel Gorman, Andrew Morton, Linux-MM, Rik van Riel, Johannes Weiner, LKML
On Mon, Jul 18, 2016 at 08:51:16AM +0200, Vlastimil Babka wrote:
> On 07/18/2016 07:07 AM, Joonsoo Kim wrote:
> >On Thu, Jul 14, 2016 at 10:32:09AM +0200, Vlastimil Babka wrote:
> >>On 07/14/2016 07:23 AM, Joonsoo Kim wrote:
> >>
> >>I don't think there's a problem in the scenario? Kswapd will keep
> >>being woken up and reclaim from the node lru. It will hit and free
> >>any low zone pages that are on the lru, even though it doesn't
> >>"balance for low zone". Eventually it will either satisfy the
> >>constrained allocation by reclaiming those low-zone pages during the
> >>repeated wakeups, or the low-zone wakeups will stop coming together
> >>with higher-zone wakeups and then it will reclaim the low-zone pages
> >>in a single low-zone wakeup. If the zone-constrained request is not
> >
> >Yes, probability of this would be low.
> >
> >>allowed to fail, then it will just keep waking up kswapd and waiting
> >>for the progress. If it's allowed to fail (i.e. not __GFP_NOFAIL),
> >>but not allowed to direct reclaim, it goes "goto nopage" rather
> >>quickly in __alloc_pages_slowpath(), without any waiting for
> >>kswapd's progress, so there's not really much difference whether the
> >>kswapd wakeup picked up a low classzone or not. Note the
> >
> >Hmm... Even if allocation could fail, we should do our best to prevent
> >failure. Relying on luck isn't good idea to me.
>
> But "Doing our best" has to have some sane limits. Allocation, that
Ensuring to do something for the requested zone at least once isn't insane.
> cannot direct reclaim, already relies on luck. And we are not really
> changing this. The allocation will "goto nopage" before kswapd can
> even wake up and start doing something, regardless of classzone_idx
> used.
But, this patch makes things worse. Even if next allocation comes
after kswapd is waking up and doing something, low zone would not be
balanced due to max classzone_idx and allocation could fail. It is
what this patch changes and I worry.
Thanks.
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-14 6:28 ` Joonsoo Kim
2016-07-14 7:48 ` Vlastimil Babka
@ 2016-07-18 12:11 ` Mel Gorman
2016-07-18 14:27 ` Mel Gorman
1 sibling, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-18 12:11 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Thu, Jul 14, 2016 at 03:28:37PM +0900, Joonsoo Kim wrote:
> > That would be appreciated.
>
> I make an artificial test case and test this series by using next tree
> (next-20160713) and found a regression.
>
> My test setup is:
>
> memory: 2048 mb
> movablecore: 1500 mb (imitates highmem system to test effect of skip logic)
This is not an equivalent test to highmem. Movable cannot store page table
pages and the highmem:lowmem ratio with this configuration is higher than
it should be. The OOM is still odd but the differences are worth
highlighting.
> fork invoked oom-killer: gfp_mask=0x27000c0(GFP_KERNEL_ACCOUNT|__GFP_NOTRACK), order=2, oom_score_adj=0
> fork cpuset=/ mems_allowed=0
Ok, high-order allocation failure for an allocation request that can
enter direct reclaim.
> Node 0 active_anon:79024kB inactive_anon:72kB active_file:569920kB inactive_file:1064260kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:1559112kB dirty:0kB writeback:0kB shmem:0kB shmem_thp
> : 0kB shmem_pmdmapped: 0kB anon_thp: 380kB writeback_tmp:0kB unstable:0kB all_unreclaimable? yes
> Node 0 DMA free:2172kB min:204kB low:252kB high:300kB present:15992kB managed:15908kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:2272kB kernel_stack:1216kB pagetables:2436kB bounce:0kB free_pcp:0k
> B local_pcp:0kB free_cma:0kB node_pages_scanned:15639736
> lowmem_reserve[]: 0 493 493 1955
> Node 0 DMA32 free:6372kB min:6492kB low:8112kB high:9732kB present:2080632kB managed:508600kB mlocked:0kB slab_reclaimable:27108kB slab_unreclaimable:74236kB kernel_stack:32752kB pagetables:67612kB bounce:
> 0kB free_pcp:112kB local_pcp:12kB free_cma:0kB node_pages_scanned:16302012
> lowmem_reserve[]: 0 0 0 1462
> Node 0 Normal free:0kB min:0kB low:0kB high:0kB present:18446744073708015752kB managed:0kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB lo
> cal_pcp:0kB free_cma:0kB node_pages_scanned:17033632
> lowmem_reserve[]: 0 0 0 11698
> Node 0 Movable free:29588kB min:19256kB low:24068kB high:28880kB present:1535864kB managed:1500964kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_
> pcp:208kB local_pcp:112kB free_cma:0kB node_pages_scanned:17725436
Present is corrupt but it's also interesting to note that
all_unreclaimable is true.
> lowmem_reserve[]: 0 0 0 0
> Node 0 DMA: 1*4kB (M) 1*8kB (U) 1*16kB (M) 1*32kB (M) 1*64kB (M) 2*128kB (UM) 1*256kB (M) 1*512kB (U) 1*1024kB (U) 0*2048kB 0*4096kB = 2172kB
> Node 0 DMA32: 60*4kB (ME) 45*8kB (UME) 24*16kB (ME) 13*32kB (UM) 12*64kB (UM) 6*128kB (UM) 6*256kB (M) 4*512kB (UM) 0*1024kB 0*2048kB 0*4096kB = 6520kB
> Node 0 Normal: 0*4kB 0*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 0kB
> Node 0 Movable: 1*4kB (M) 130*8kB (M) 68*16kB (M) 30*32kB (M) 13*64kB (M) 9*128kB (M) 4*256kB (M) 0*512kB 1*1024kB (M) 1*2048kB (M) 5*4096kB (M) = 29652kB
> Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB
And it's true even though enough free pages are actually free so it's
not even trying to do the allocation.
The all_unreclaimable logic is related to the number of pages scanned
but currently pages skipped contributes to pages scanned. That is one
possibility. The other is that if all pages scanned are skipped then the
OOM killer can believe there is zero progress.
Try this to start with;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3f06a7a0d135..c3e509c693bf 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1408,7 +1408,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
isolate_mode_t mode, enum lru_list lru)
{
struct list_head *src = &lruvec->lists[lru];
- unsigned long nr_taken = 0;
+ unsigned long nr_taken = 0, total_skipped = 0;
unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
unsigned long scan, nr_pages;
@@ -1462,10 +1462,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
if (!nr_skipped[zid])
continue;
+ total_skipped += nr_skipped[zid];
__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
}
}
- *nr_scanned = scan;
+ *nr_scanned = scan - total_skipped;
trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
nr_taken, mode, is_file_lru(lru));
update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken);
--
Mel Gorman
SUSE Labs
^ permalink raw reply related [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-18 12:11 ` Mel Gorman
@ 2016-07-18 14:27 ` Mel Gorman
2016-07-19 8:30 ` Joonsoo Kim
0 siblings, 1 reply; 90+ messages in thread
From: Mel Gorman @ 2016-07-18 14:27 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Mon, Jul 18, 2016 at 01:11:22PM +0100, Mel Gorman wrote:
> The all_unreclaimable logic is related to the number of pages scanned
> but currently pages skipped contributes to pages scanned. That is one
> possibility. The other is that if all pages scanned are skipped then the
> OOM killer can believe there is zero progress.
>
> Try this to start with;
>
And if that fails, try this heavier handed version that will scan the full
LRU potentially to isolate at least a single page if it's available for
zone-constrained allocations. It's compile-tested only
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a6f31617a08c..6a35691c8b94 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1408,14 +1408,14 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
isolate_mode_t mode, enum lru_list lru)
{
struct list_head *src = &lruvec->lists[lru];
- unsigned long nr_taken = 0;
+ unsigned long nr_taken = 0, total_skipped = 0;
unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
unsigned long scan, nr_pages;
LIST_HEAD(pages_skipped);
for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
- !list_empty(src); scan++) {
+ !list_empty(src) && scan == total_skipped; scan++) {
struct page *page;
page = lru_to_page(src);
@@ -1426,6 +1426,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
if (page_zonenum(page) > sc->reclaim_idx) {
list_move(&page->lru, &pages_skipped);
nr_skipped[page_zonenum(page)]++;
+ total_skipped++;
continue;
}
@@ -1465,7 +1466,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
}
}
- *nr_scanned = scan;
+ *nr_scanned = scan - total_skipped;
trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
nr_taken, mode, is_file_lru(lru));
update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken);
--
Mel Gorman
SUSE Labs
^ permalink raw reply related [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-18 14:27 ` Mel Gorman
@ 2016-07-19 8:30 ` Joonsoo Kim
2016-07-19 14:25 ` Mel Gorman
0 siblings, 1 reply; 90+ messages in thread
From: Joonsoo Kim @ 2016-07-19 8:30 UTC (permalink / raw)
To: Mel Gorman
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Mon, Jul 18, 2016 at 03:27:14PM +0100, Mel Gorman wrote:
> On Mon, Jul 18, 2016 at 01:11:22PM +0100, Mel Gorman wrote:
> > The all_unreclaimable logic is related to the number of pages scanned
> > but currently pages skipped contributes to pages scanned. That is one
> > possibility. The other is that if all pages scanned are skipped then the
> > OOM killer can believe there is zero progress.
> >
> > Try this to start with;
> >
>
> And if that fails, try this heavier handed version that will scan the full
> LRU potentially to isolate at least a single page if it's available for
> zone-constrained allocations. It's compile-tested only
I tested both patches but they don't work for me. Notable difference
is that all_unreclaimable is now "no".
Just attach the oops log from heavier version.
Thanks.
fork invoked oom-killer: gfp_mask=0x27000c0(GFP_KERNEL_ACCOUNT|__GFP_NOTRACK), order=2, oom_score_adj=0
fork cpuset=/ mems_allowed=0
CPU: 1 PID: 7484 Comm: fork Not tainted 4.7.0-rc7-next-20160713+ #657
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014
0000000000000000 ffff880019f6bb18 ffffffff8142b8d3 ffff880019f6bd20
ffff88001c2c2500 ffff880019f6bb90 ffffffff81240b7e ffffffff81e6f0e0
ffff880019f6bb40 ffffffff810de08d ffff880019f6bb60 0000000000000206
Call Trace:
[<ffffffff8142b8d3>] dump_stack+0x85/0xc2
[<ffffffff81240b7e>] dump_header+0x5c/0x22e
[<ffffffff810de08d>] ? trace_hardirqs_on+0xd/0x10
[<ffffffff811b3381>] oom_kill_process+0x221/0x3f0
[<ffffffff810901b7>] ? has_capability_noaudit+0x17/0x20
[<ffffffff811b3acf>] out_of_memory+0x52f/0x560
[<ffffffff811b377c>] ? out_of_memory+0x1dc/0x560
[<ffffffff811ba004>] __alloc_pages_nodemask+0x1154/0x11b0
[<ffffffff810813a1>] ? copy_process.part.30+0x121/0x1bf0
[<ffffffff810813a1>] copy_process.part.30+0x121/0x1bf0
[<ffffffff811ebb16>] ? handle_mm_fault+0xb36/0x13d0
[<ffffffff810fb60d>] ? debug_lockdep_rcu_enabled+0x1d/0x20
[<ffffffff81083066>] _do_fork+0xe6/0x6a0
[<ffffffff810836c9>] SyS_clone+0x19/0x20
[<ffffffff81003e13>] do_syscall_64+0x73/0x1e0
[<ffffffff81858ec3>] entry_SYSCALL64_slow_path+0x25/0x25
Mem-Info:
active_anon:23909 inactive_anon:18 isolated_anon:0
active_file:289985 inactive_file:101445 isolated_file:0
unevictable:0 dirty:0 writeback:0 unstable:0
slab_reclaimable:6696 slab_unreclaimable:22083
mapped:381662 shmem:95 pagetables:21600 bounce:0
free:8378 free_pcp:227 free_cma:0
Node 0 active_anon:95676kB inactive_anon:72kB active_file:1160056kB inactive_file:405792kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:1526812kB dirty:4kB writeback:0kB shmem:0kB shmem_thp
: 0kB shmem_pmdmapped: 0kB anon_thp: 380kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no
Node 0 DMA free:2176kB min:204kB low:252kB high:300kB present:15992kB managed:15908kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:2328kB kernel_stack:1472kB pagetables:2940kB bounce:0kB free_pcp:0k
B local_pcp:0kB free_cma:0kB node_pages_scanned:1668
lowmem_reserve[]: 0 493 493 1955
Node 0 DMA32 free:8188kB min:6492kB low:8112kB high:9732kB present:2080632kB managed:508600kB mlocked:0kB slab_reclaimable:26784kB slab_unreclaimable:86004kB kernel_stack:40704kB pagetables:83460kB bounce:
0kB free_pcp:208kB local_pcp:0kB free_cma:0kB node_pages_scanned:12000
lowmem_reserve[]: 0 0 0 1462
Node 0 Movable free:23648kB min:19256kB low:24068kB high:28880kB present:1535864kB managed:1500964kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_
pcp:748kB local_pcp:0kB free_cma:0kB node_pages_scanned:12000
lowmem_reserve[]: 0 0 0 0
Node 0 DMA: 2*4kB (M) 0*8kB 2*16kB (UM) 2*32kB (UM) 0*64kB 2*128kB (UM) 1*256kB (U) 1*512kB (M) 1*1024kB (M) 0*2048kB 0*4096kB = 2152kB
Node 0 DMA32: 21*4kB (EH) 14*8kB (UMEH) 14*16kB (UMEH) 17*32kB (UM) 11*64kB (ME) 13*128kB (UME) 14*256kB (UME) 1*512kB (U) 1*1024kB (M) 0*2048kB 0*4096kB = 8452kB
Node 0 Movable: 87*4kB (M) 106*8kB (M) 82*16kB (M) 39*32kB (M) 11*64kB (M) 4*128kB (M) 0*256kB 1*512kB (M) 0*1024kB 1*2048kB (M) 4*4096kB (M) = 23916kB
Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB
391491 total pagecache pages
0 pages in swap cache
Swap cache stats: add 0, delete 0, find 0/0
Free swap = 0kB
Total swap = 0kB
908122 pages RAM
0 pages HighMem/MovableOnly
401754 pages reserved
0 pages cma reserved
0 pages hwpoisoned
^ permalink raw reply [flat|nested] 90+ messages in thread
* Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
2016-07-19 8:30 ` Joonsoo Kim
@ 2016-07-19 14:25 ` Mel Gorman
0 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-19 14:25 UTC (permalink / raw)
To: Joonsoo Kim
Cc: Andrew Morton, Linux-MM, Rik van Riel, Vlastimil Babka,
Johannes Weiner, LKML
On Tue, Jul 19, 2016 at 05:30:31PM +0900, Joonsoo Kim wrote:
> On Mon, Jul 18, 2016 at 03:27:14PM +0100, Mel Gorman wrote:
> > On Mon, Jul 18, 2016 at 01:11:22PM +0100, Mel Gorman wrote:
> > > The all_unreclaimable logic is related to the number of pages scanned
> > > but currently pages skipped contributes to pages scanned. That is one
> > > possibility. The other is that if all pages scanned are skipped then the
> > > OOM killer can believe there is zero progress.
> > >
> > > Try this to start with;
> > >
> >
> > And if that fails, try this heavier handed version that will scan the full
> > LRU potentially to isolate at least a single page if it's available for
> > zone-constrained allocations. It's compile-tested only
>
> I tested both patches but they don't work for me. Notable difference
> is that all_unreclaimable is now "no".
>
Ok, that's good to know at least. It at least indicates that skips
accounted as scans are a contributory factor.
> Just attach the oops log from heavier version.
>
Apparently, isolating at least one page is not enough. Please try the
following. If it fails, please post the test script you're using. I can
simulate what you describe (mapped reads combined with lots of forks)
but no guarantee I'll get it exactly right. I think it's ok to not
account skips as scans because the skips are already accounted for.
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a6f31617a08c..0dc443b52228 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1415,7 +1415,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
LIST_HEAD(pages_skipped);
for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
- !list_empty(src); scan++) {
+ !list_empty(src);) {
struct page *page;
page = lru_to_page(src);
@@ -1428,6 +1428,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
nr_skipped[page_zonenum(page)]++;
continue;
}
+`
+ /* Pages skipped do not contribute to scan */
+ scan++;
switch (__isolate_lru_page(page, mode)) {
case 0:
--
Mel Gorman
SUSE Labs
^ permalink raw reply related [flat|nested] 90+ messages in thread
* [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone
2016-07-01 15:37 Mel Gorman
@ 2016-07-01 15:37 ` Mel Gorman
0 siblings, 0 replies; 90+ messages in thread
From: Mel Gorman @ 2016-07-01 15:37 UTC (permalink / raw)
To: Andrew Morton, Linux-MM
Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman
kswapd scans from highest to lowest for a zone that requires balancing.
This was necessary when reclaim was per-zone to fairly age pages on lower
zones. Now that we are reclaiming on a per-node basis, any eligible zone
can be used and pages will still be aged fairly. This patch avoids
reclaiming excessively unless buffer_heads are over the limit and it's
necessary to reclaim from a higher zone than requested by the waker of
kswapd to relieve low memory pressure.
[hillf.zj@alibaba-inc.com: Force kswapd reclaim no more than needed]
Link: http://lkml.kernel.org/r/1466518566-30034-12-git-send-email-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
mm/vmscan.c | 56 ++++++++++++++++++++++++--------------------------------
1 file changed, 24 insertions(+), 32 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 911142d25de2..2f898ba2ee2e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3141,31 +3141,36 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
sc.nr_reclaimed = 0;
- /* Scan from the highest requested zone to dma */
- for (i = classzone_idx; i >= 0; i--) {
- zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
- continue;
-
- /*
- * If the number of buffer_heads in the machine
- * exceeds the maximum allowed level and this node
- * has a highmem zone, force kswapd to reclaim from
- * it to relieve lowmem pressure.
- */
- if (buffer_heads_over_limit && is_highmem_idx(i)) {
- classzone_idx = i;
- break;
- }
+ /*
+ * If the number of buffer_heads in the machine exceeds the
+ * maximum allowed level then reclaim from all zones. This is
+ * not specific to highmem as highmem may not exist but it is
+ * it is expected that buffer_heads are stripped in writeback.
+ */
+ if (buffer_heads_over_limit) {
+ for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
+ zone = pgdat->node_zones + i;
+ if (!populated_zone(zone))
+ continue;
- if (!zone_balanced(zone, order, 0)) {
classzone_idx = i;
break;
}
}
- if (i < 0)
- goto out;
+ /*
+ * Only reclaim if there are no eligible zones. Check from
+ * high to low zone to avoid prematurely clearing pgdat
+ * congested state.
+ */
+ for (i = classzone_idx; i >= 0; i--) {
+ zone = pgdat->node_zones + i;
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone_balanced(zone, sc.order, classzone_idx))
+ goto out;
+ }
/*
* Do some background aging of the anon list, to give
@@ -3211,19 +3216,6 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
break;
/*
- * Stop reclaiming if any eligible zone is balanced and clear
- * node writeback or congested.
- */
- for (i = 0; i <= classzone_idx; i++) {
- zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
- continue;
-
- if (zone_balanced(zone, sc.order, classzone_idx))
- goto out;
- }
-
- /*
* Raise priority if scanning rate is too low or there was no
* progress in reclaiming pages
*/
--
2.6.4
^ permalink raw reply related [flat|nested] 90+ messages in thread
end of thread, other threads:[~2016-07-19 14:25 UTC | newest]
Thread overview: 90+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-07-01 20:01 [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Mel Gorman
2016-07-01 20:01 ` [PATCH 01/31] mm, vmstat: add infrastructure for per-node vmstats Mel Gorman
2016-07-04 23:50 ` Minchan Kim
2016-07-05 8:14 ` Mel Gorman
2016-07-06 0:15 ` Minchan Kim
2016-07-01 20:01 ` [PATCH 02/31] mm, vmscan: move lru_lock to the node Mel Gorman
2016-07-05 0:03 ` Minchan Kim
2016-07-01 20:01 ` [PATCH 03/31] mm, vmscan: move LRU lists to node Mel Gorman
2016-07-05 1:19 ` Minchan Kim
2016-07-05 10:14 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis Mel Gorman
2016-07-07 1:12 ` Joonsoo Kim
2016-07-07 9:48 ` Mel Gorman
2016-07-08 2:28 ` Joonsoo Kim
2016-07-08 10:05 ` Mel Gorman
2016-07-14 6:28 ` Joonsoo Kim
2016-07-14 7:48 ` Vlastimil Babka
2016-07-18 4:52 ` Joonsoo Kim
2016-07-18 12:11 ` Mel Gorman
2016-07-18 14:27 ` Mel Gorman
2016-07-19 8:30 ` Joonsoo Kim
2016-07-19 14:25 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 05/31] mm, vmscan: have kswapd only scan based on the highest requested zone Mel Gorman
2016-07-01 20:01 ` [PATCH 06/31] mm, vmscan: make kswapd reclaim in terms of nodes Mel Gorman
2016-07-01 20:01 ` [PATCH 07/31] mm, vmscan: remove balance gap Mel Gorman
2016-07-01 20:01 ` [PATCH 08/31] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-07-05 5:59 ` Minchan Kim
2016-07-05 10:26 ` Mel Gorman
2016-07-06 0:30 ` Minchan Kim
2016-07-06 8:31 ` Mel Gorman
2016-07-07 5:51 ` Minchan Kim
2016-07-07 9:56 ` Mel Gorman
2016-07-07 1:20 ` Joonsoo Kim
2016-07-07 10:17 ` Mel Gorman
2016-07-08 2:44 ` Joonsoo Kim
2016-07-08 10:11 ` Mel Gorman
2016-07-14 5:23 ` Joonsoo Kim
2016-07-14 8:32 ` Vlastimil Babka
2016-07-18 5:07 ` Joonsoo Kim
2016-07-18 6:51 ` Vlastimil Babka
2016-07-18 7:24 ` Joonsoo Kim
2016-07-14 9:05 ` Mel Gorman
2016-07-18 5:03 ` Joonsoo Kim
2016-07-01 20:01 ` [PATCH 09/31] mm, vmscan: by default have direct reclaim only shrink once per node Mel Gorman
2016-07-07 1:43 ` Joonsoo Kim
2016-07-07 10:27 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 10/31] mm, vmscan: remove duplicate logic clearing node congestion and dirty state Mel Gorman
2016-07-01 20:01 ` [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone Mel Gorman
2016-07-05 6:11 ` Minchan Kim
2016-07-05 10:38 ` Mel Gorman
2016-07-06 1:25 ` Minchan Kim
2016-07-06 8:42 ` Mel Gorman
2016-07-07 6:27 ` Minchan Kim
2016-07-07 10:55 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric Mel Gorman
2016-07-05 6:24 ` Minchan Kim
2016-07-05 10:40 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 13/31] mm, memcg: move memcg limit enforcement from zones to nodes Mel Gorman
2016-07-01 20:01 ` [PATCH 14/31] mm, workingset: make working set detection node-aware Mel Gorman
2016-07-01 20:01 ` [PATCH 15/31] mm, page_alloc: consider dirtyable memory in terms of nodes Mel Gorman
2016-07-01 20:01 ` [PATCH 16/31] mm: move page mapped accounting to the node Mel Gorman
2016-07-01 20:01 ` [PATCH 17/31] mm: rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
2016-07-01 20:01 ` [PATCH 18/31] mm: move most file-based accounting to the node Mel Gorman
2016-07-01 20:01 ` [PATCH 19/31] mm: move vmscan writes and file write " Mel Gorman
2016-07-01 20:01 ` [PATCH 20/31] mm, vmscan: only wakeup kswapd once per node for the requested classzone Mel Gorman
2016-07-07 1:24 ` Joonsoo Kim
2016-07-07 10:58 ` Mel Gorman
2016-07-01 20:01 ` [PATCH 21/31] mm, page_alloc: Wake kswapd based on the highest eligible zone Mel Gorman
2016-07-01 20:01 ` [PATCH 22/31] mm: convert zone_reclaim to node_reclaim Mel Gorman
2016-07-01 20:01 ` [PATCH 23/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to shrink_node Mel Gorman
2016-07-01 20:01 ` [PATCH 24/31] mm, vmscan: Avoid passing in classzone_idx unnecessarily to compaction_ready Mel Gorman
2016-07-01 20:01 ` [PATCH 25/31] mm, vmscan: add classzone information to tracepoints Mel Gorman
2016-07-01 20:01 ` [PATCH 26/31] mm, page_alloc: remove fair zone allocation policy Mel Gorman
2016-07-01 20:01 ` [PATCH 27/31] mm: page_alloc: cache the last node whose dirty limit is reached Mel Gorman
2016-07-01 20:01 ` [PATCH 28/31] mm: vmstat: replace __count_zone_vm_events with a zone id equivalent Mel Gorman
2016-07-01 20:01 ` [PATCH 29/31] mm: vmstat: account per-zone stalls and pages skipped during reclaim Mel Gorman
2016-07-01 20:01 ` [PATCH 30/31] mm, vmstat: print node-based stats in zoneinfo file Mel Gorman
2016-07-01 20:01 ` [PATCH 31/31] mm, vmstat: Remove zone and node double accounting by approximating retries Mel Gorman
2016-07-06 0:02 ` Minchan Kim
2016-07-06 8:58 ` Mel Gorman
2016-07-06 9:33 ` Mel Gorman
2016-07-07 6:47 ` Minchan Kim
2016-07-06 18:12 ` Dave Hansen
2016-07-07 11:26 ` Mel Gorman
2016-07-04 1:37 ` [PATCH 00/31] Move LRU page reclaim from zones to nodes v8 Minchan Kim
2016-07-04 4:34 ` Mel Gorman
2016-07-04 8:04 ` Minchan Kim
2016-07-04 9:55 ` Mel Gorman
2016-07-06 1:51 ` Minchan Kim
-- strict thread matches above, loose matches on Subject: below --
2016-07-01 15:37 Mel Gorman
2016-07-01 15:37 ` [PATCH 11/31] mm: vmscan: do not reclaim from kswapd if there is any eligible zone Mel Gorman
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).