* [PATCH] mm: use global_dirty_limit in throttle_vm_writeout()
@ 2012-03-02 6:14 Fengguang Wu
2012-03-05 20:06 ` Rik van Riel
` (2 more replies)
0 siblings, 3 replies; 4+ messages in thread
From: Fengguang Wu @ 2012-03-02 6:14 UTC (permalink / raw)
To: Andrew Morton
Cc: Johannes Weiner, Jan Kara, Greg Thelen, Ying Han,
KAMEZAWA Hiroyuki, Rik van Riel, Mel Gorman, Minchan Kim,
Linux Memory Management List, LKML
When starting a memory hog task, a desktop box w/o swap is found to go
unresponsive for a long time. It's solely caused by lots of congestion
waits in throttle_vm_writeout():
gnome-system-mo-4201 553.073384: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
gnome-system-mo-4201 553.073386: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
gtali-4237 553.080377: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
gtali-4237 553.080378: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
Xorg-3483 553.103375: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
Xorg-3483 553.103377: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
The root cause is, the dirty threshold is knocked down a lot by the
memory hog task. Fixed by using global_dirty_limit which decreases
gradually on such events and can guarantee we stay above (the also
decreasing) nr_dirty in the progress of following down to the new
dirty threshold.
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
---
mm/page-writeback.c | 1 +
1 file changed, 1 insertion(+)
--- linux.orig/mm/page-writeback.c 2012-03-02 14:05:01.633763187 +0800
+++ linux/mm/page-writeback.c 2012-03-02 14:11:52.929772962 +0800
@@ -1472,6 +1472,7 @@ void throttle_vm_writeout(gfp_t gfp_mask
for ( ; ; ) {
global_dirty_limits(&background_thresh, &dirty_thresh);
+ dirty_thresh = hard_dirty_limit(dirty_thresh);
/*
* Boost the allowable dirty threshold a bit for page
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] mm: use global_dirty_limit in throttle_vm_writeout()
2012-03-02 6:14 [PATCH] mm: use global_dirty_limit in throttle_vm_writeout() Fengguang Wu
@ 2012-03-05 20:06 ` Rik van Riel
2012-03-19 7:37 ` Johannes Weiner
2012-03-21 0:43 ` Minchan Kim
2 siblings, 0 replies; 4+ messages in thread
From: Rik van Riel @ 2012-03-05 20:06 UTC (permalink / raw)
To: Fengguang Wu
Cc: Andrew Morton, Johannes Weiner, Jan Kara, Greg Thelen, Ying Han,
KAMEZAWA Hiroyuki, Mel Gorman, Minchan Kim,
Linux Memory Management List, LKML
On 03/02/2012 01:14 AM, Fengguang Wu wrote:
> When starting a memory hog task, a desktop box w/o swap is found to go
> unresponsive for a long time. It's solely caused by lots of congestion
> waits in throttle_vm_writeout():
>
> gnome-system-mo-4201 553.073384: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
> gnome-system-mo-4201 553.073386: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
> gtali-4237 553.080377: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
> gtali-4237 553.080378: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
> Xorg-3483 553.103375: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
> Xorg-3483 553.103377: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
>
> The root cause is, the dirty threshold is knocked down a lot by the
> memory hog task. Fixed by using global_dirty_limit which decreases
> gradually on such events and can guarantee we stay above (the also
> decreasing) nr_dirty in the progress of following down to the new
> dirty threshold.
>
> Signed-off-by: Fengguang Wu<fengguang.wu@intel.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] mm: use global_dirty_limit in throttle_vm_writeout()
2012-03-02 6:14 [PATCH] mm: use global_dirty_limit in throttle_vm_writeout() Fengguang Wu
2012-03-05 20:06 ` Rik van Riel
@ 2012-03-19 7:37 ` Johannes Weiner
2012-03-21 0:43 ` Minchan Kim
2 siblings, 0 replies; 4+ messages in thread
From: Johannes Weiner @ 2012-03-19 7:37 UTC (permalink / raw)
To: Fengguang Wu
Cc: Andrew Morton, Jan Kara, Greg Thelen, Ying Han,
KAMEZAWA Hiroyuki, Rik van Riel, Mel Gorman, Minchan Kim,
Linux Memory Management List, LKML
On Fri, Mar 02, 2012 at 02:14:51PM +0800, Fengguang Wu wrote:
> When starting a memory hog task, a desktop box w/o swap is found to go
> unresponsive for a long time. It's solely caused by lots of congestion
> waits in throttle_vm_writeout():
>
> gnome-system-mo-4201 553.073384: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
> gnome-system-mo-4201 553.073386: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
> gtali-4237 553.080377: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
> gtali-4237 553.080378: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
> Xorg-3483 553.103375: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
> Xorg-3483 553.103377: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
>
> The root cause is, the dirty threshold is knocked down a lot by the
> memory hog task. Fixed by using global_dirty_limit which decreases
> gradually on such events and can guarantee we stay above (the also
> decreasing) nr_dirty in the progress of following down to the new
> dirty threshold.
>
> Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] mm: use global_dirty_limit in throttle_vm_writeout()
2012-03-02 6:14 [PATCH] mm: use global_dirty_limit in throttle_vm_writeout() Fengguang Wu
2012-03-05 20:06 ` Rik van Riel
2012-03-19 7:37 ` Johannes Weiner
@ 2012-03-21 0:43 ` Minchan Kim
2 siblings, 0 replies; 4+ messages in thread
From: Minchan Kim @ 2012-03-21 0:43 UTC (permalink / raw)
To: Fengguang Wu
Cc: Andrew Morton, Johannes Weiner, Jan Kara, Greg Thelen, Ying Han,
KAMEZAWA Hiroyuki, Rik van Riel, Mel Gorman, Minchan Kim,
Linux Memory Management List, LKML
Hi Wu,
Sorry for late response.
I have a question.
On Fri, Mar 02, 2012 at 02:14:51PM +0800, Fengguang Wu wrote:
> When starting a memory hog task, a desktop box w/o swap is found to go
> unresponsive for a long time. It's solely caused by lots of congestion
> waits in throttle_vm_writeout():
>
> gnome-system-mo-4201 553.073384: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
> gnome-system-mo-4201 553.073386: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
> gtali-4237 553.080377: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
> gtali-4237 553.080378: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
> Xorg-3483 553.103375: congestion_wait: throttle_vm_writeout+0x70/0x7f shrink_mem_cgroup_zone+0x48f/0x4a1
> Xorg-3483 553.103377: writeback_congestion_wait: usec_timeout=100000 usec_delayed=100000
>
> The root cause is, the dirty threshold is knocked down a lot by the
> memory hog task. Fixed by using global_dirty_limit which decreases
AFAIUC, memory hog task, you mean it consumes lots of anon pages, not file-backed pages.
So global_dirty_limits would get small available_memory by global_reclaimable_pages
so that it ends up dirty threshold is knocked down.
Could you confirm my understanding?
Thanks.
> gradually on such events and can guarantee we stay above (the also
> decreasing) nr_dirty in the progress of following down to the new
> dirty threshold.
>
> Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
> ---
> mm/page-writeback.c | 1 +
> 1 file changed, 1 insertion(+)
>
> --- linux.orig/mm/page-writeback.c 2012-03-02 14:05:01.633763187 +0800
> +++ linux/mm/page-writeback.c 2012-03-02 14:11:52.929772962 +0800
> @@ -1472,6 +1472,7 @@ void throttle_vm_writeout(gfp_t gfp_mask
>
> for ( ; ; ) {
> global_dirty_limits(&background_thresh, &dirty_thresh);
> + dirty_thresh = hard_dirty_limit(dirty_thresh);
>
> /*
> * Boost the allowable dirty threshold a bit for page
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2012-03-21 0:43 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2012-03-02 6:14 [PATCH] mm: use global_dirty_limit in throttle_vm_writeout() Fengguang Wu
2012-03-05 20:06 ` Rik van Riel
2012-03-19 7:37 ` Johannes Weiner
2012-03-21 0:43 ` Minchan Kim
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).