* [PATCH] sched/numa: use down_read_trylock for mmap_sem
@ 2017-05-15 13:13 Vlastimil Babka
2017-05-15 14:27 ` Rik van Riel
` (3 more replies)
0 siblings, 4 replies; 5+ messages in thread
From: Vlastimil Babka @ 2017-05-15 13:13 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra
Cc: Mel Gorman, Rik van Riel, linux-kernel, Vlastimil Babka
A customer has reported a soft-lockup when running a proprietary intensive
memory stress test, where the trace on multiple CPU's looks like this:
RIP: 0010:[<ffffffff810c53fe>]
[<ffffffff810c53fe>] native_queued_spin_lock_slowpath+0x10e/0x190
...
Call Trace:
[<ffffffff81182d07>] queued_spin_lock_slowpath+0x7/0xa
[<ffffffff811bc331>] change_protection_range+0x3b1/0x930
[<ffffffff811d4be8>] change_prot_numa+0x18/0x30
[<ffffffff810adefe>] task_numa_work+0x1fe/0x310
[<ffffffff81098322>] task_work_run+0x72/0x90
Further investigation showed that the lock contention here is pmd_lock().
The task_numa_work() function makes sure that only one thread is let to perform
the work in a single scan period (via cmpxchg), but if there's a thread with
mmap_sem locked for writing for several periods, multiple threads in
task_numa_work() can build up a convoy waiting for mmap_sem for read and then
all get unblocked at once.
This patch changes the down_read() to the trylock version, which prevents the
build up. For a workload experiencing mmap_sem contention, it's probably better
to postpone the NUMA balancing work anyway. This seems to have fixed the soft
lockups involving pmd_lock(), which is in line with the convoy theory.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
kernel/sched/fair.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index dea138964b91..d70f9026defc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2475,7 +2475,8 @@ void task_numa_work(struct callback_head *work)
return;
- down_read(&mm->mmap_sem);
+ if (!down_read_trylock(&mm->mmap_sem))
+ return;
vma = find_vma(mm, start);
if (!vma) {
reset_ptenuma_scan(p);
--
2.12.2
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH] sched/numa: use down_read_trylock for mmap_sem
2017-05-15 13:13 [PATCH] sched/numa: use down_read_trylock for mmap_sem Vlastimil Babka
@ 2017-05-15 14:27 ` Rik van Riel
2017-05-15 14:35 ` Mel Gorman
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Rik van Riel @ 2017-05-15 14:27 UTC (permalink / raw)
To: Vlastimil Babka, Ingo Molnar, Peter Zijlstra; +Cc: Mel Gorman, linux-kernel
On Mon, 2017-05-15 at 15:13 +0200, Vlastimil Babka wrote:
> A customer has reported a soft-lockup when running a proprietary
> intensive
> memory stress test, where the trace on multiple CPU's looks like
> this:
>
> RIP: 0010:[<ffffffff810c53fe>]
> [<ffffffff810c53fe>] native_queued_spin_lock_slowpath+0x10e/0x190
> ...
> Call Trace:
> [<ffffffff81182d07>] queued_spin_lock_slowpath+0x7/0xa
> [<ffffffff811bc331>] change_protection_range+0x3b1/0x930
> [<ffffffff811d4be8>] change_prot_numa+0x18/0x30
> [<ffffffff810adefe>] task_numa_work+0x1fe/0x310
> [<ffffffff81098322>] task_work_run+0x72/0x90
>
> Further investigation showed that the lock contention here is
> pmd_lock().
>
> The task_numa_work() function makes sure that only one thread is let
> to perform
> the work in a single scan period (via cmpxchg), but if there's a
> thread with
> mmap_sem locked for writing for several periods, multiple threads in
> task_numa_work() can build up a convoy waiting for mmap_sem for read
> and then
> all get unblocked at once.
>
> This patch changes the down_read() to the trylock version, which
> prevents the
> build up. For a workload experiencing mmap_sem contention, it's
> probably better
> to postpone the NUMA balancing work anyway. This seems to have fixed
> the soft
> lockups involving pmd_lock(), which is in line with the convoy
> theory.
>
> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Rik van Riel <riel@redhat.com>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] sched/numa: use down_read_trylock for mmap_sem
2017-05-15 13:13 [PATCH] sched/numa: use down_read_trylock for mmap_sem Vlastimil Babka
2017-05-15 14:27 ` Rik van Riel
@ 2017-05-15 14:35 ` Mel Gorman
2017-05-16 8:15 ` Peter Zijlstra
2017-05-23 8:47 ` [tip:sched/core] sched/numa: Use down_read_trylock() for the mmap_sem tip-bot for Vlastimil Babka
3 siblings, 0 replies; 5+ messages in thread
From: Mel Gorman @ 2017-05-15 14:35 UTC (permalink / raw)
To: Vlastimil Babka; +Cc: Ingo Molnar, Peter Zijlstra, Rik van Riel, linux-kernel
On Mon, May 15, 2017 at 03:13:16PM +0200, Vlastimil Babka wrote:
> A customer has reported a soft-lockup when running a proprietary intensive
> memory stress test, where the trace on multiple CPU's looks like this:
>
> RIP: 0010:[<ffffffff810c53fe>]
> [<ffffffff810c53fe>] native_queued_spin_lock_slowpath+0x10e/0x190
> ...
> Call Trace:
> [<ffffffff81182d07>] queued_spin_lock_slowpath+0x7/0xa
> [<ffffffff811bc331>] change_protection_range+0x3b1/0x930
> [<ffffffff811d4be8>] change_prot_numa+0x18/0x30
> [<ffffffff810adefe>] task_numa_work+0x1fe/0x310
> [<ffffffff81098322>] task_work_run+0x72/0x90
>
> Further investigation showed that the lock contention here is pmd_lock().
>
> The task_numa_work() function makes sure that only one thread is let to perform
> the work in a single scan period (via cmpxchg), but if there's a thread with
> mmap_sem locked for writing for several periods, multiple threads in
> task_numa_work() can build up a convoy waiting for mmap_sem for read and then
> all get unblocked at once.
>
> This patch changes the down_read() to the trylock version, which prevents the
> build up. For a workload experiencing mmap_sem contention, it's probably better
> to postpone the NUMA balancing work anyway. This seems to have fixed the soft
> lockups involving pmd_lock(), which is in line with the convoy theory.
>
> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
This skips the entire scan window and defers to the next once.
Potentially, with constant contention, it'll never make progress and
there could be other disruption. However, I cannot see any way how
that's worse than waiting on mmap_sem so
Acked-by: Mel Gorman <mgorman@techsingularity.net>
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] sched/numa: use down_read_trylock for mmap_sem
2017-05-15 13:13 [PATCH] sched/numa: use down_read_trylock for mmap_sem Vlastimil Babka
2017-05-15 14:27 ` Rik van Riel
2017-05-15 14:35 ` Mel Gorman
@ 2017-05-16 8:15 ` Peter Zijlstra
2017-05-23 8:47 ` [tip:sched/core] sched/numa: Use down_read_trylock() for the mmap_sem tip-bot for Vlastimil Babka
3 siblings, 0 replies; 5+ messages in thread
From: Peter Zijlstra @ 2017-05-16 8:15 UTC (permalink / raw)
To: Vlastimil Babka; +Cc: Ingo Molnar, Mel Gorman, Rik van Riel, linux-kernel
On Mon, May 15, 2017 at 03:13:16PM +0200, Vlastimil Babka wrote:
> A customer has reported a soft-lockup when running a proprietary intensive
> memory stress test, where the trace on multiple CPU's looks like this:
>
> RIP: 0010:[<ffffffff810c53fe>]
> [<ffffffff810c53fe>] native_queued_spin_lock_slowpath+0x10e/0x190
> ...
> Call Trace:
> [<ffffffff81182d07>] queued_spin_lock_slowpath+0x7/0xa
> [<ffffffff811bc331>] change_protection_range+0x3b1/0x930
> [<ffffffff811d4be8>] change_prot_numa+0x18/0x30
> [<ffffffff810adefe>] task_numa_work+0x1fe/0x310
> [<ffffffff81098322>] task_work_run+0x72/0x90
>
> Further investigation showed that the lock contention here is pmd_lock().
>
> The task_numa_work() function makes sure that only one thread is let to perform
> the work in a single scan period (via cmpxchg), but if there's a thread with
> mmap_sem locked for writing for several periods, multiple threads in
> task_numa_work() can build up a convoy waiting for mmap_sem for read and then
> all get unblocked at once.
>
> This patch changes the down_read() to the trylock version, which prevents the
> build up. For a workload experiencing mmap_sem contention, it's probably better
> to postpone the NUMA balancing work anyway. This seems to have fixed the soft
> lockups involving pmd_lock(), which is in line with the convoy theory.
>
> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Thanks!
^ permalink raw reply [flat|nested] 5+ messages in thread
* [tip:sched/core] sched/numa: Use down_read_trylock() for the mmap_sem
2017-05-15 13:13 [PATCH] sched/numa: use down_read_trylock for mmap_sem Vlastimil Babka
` (2 preceding siblings ...)
2017-05-16 8:15 ` Peter Zijlstra
@ 2017-05-23 8:47 ` tip-bot for Vlastimil Babka
3 siblings, 0 replies; 5+ messages in thread
From: tip-bot for Vlastimil Babka @ 2017-05-23 8:47 UTC (permalink / raw)
To: linux-tip-commits
Cc: vbabka, torvalds, hpa, tglx, mingo, linux-kernel, riel, mgorman, peterz
Commit-ID: 8655d5497735b288f8a9b458bd22e7d1bf95bb61
Gitweb: http://git.kernel.org/tip/8655d5497735b288f8a9b458bd22e7d1bf95bb61
Author: Vlastimil Babka <vbabka@suse.cz>
AuthorDate: Mon, 15 May 2017 15:13:16 +0200
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 23 May 2017 10:01:34 +0200
sched/numa: Use down_read_trylock() for the mmap_sem
A customer has reported a soft-lockup when running an intensive
memory stress test, where the trace on multiple CPU's looks like this:
RIP: 0010:[<ffffffff810c53fe>]
[<ffffffff810c53fe>] native_queued_spin_lock_slowpath+0x10e/0x190
...
Call Trace:
[<ffffffff81182d07>] queued_spin_lock_slowpath+0x7/0xa
[<ffffffff811bc331>] change_protection_range+0x3b1/0x930
[<ffffffff811d4be8>] change_prot_numa+0x18/0x30
[<ffffffff810adefe>] task_numa_work+0x1fe/0x310
[<ffffffff81098322>] task_work_run+0x72/0x90
Further investigation showed that the lock contention here is pmd_lock().
The task_numa_work() function makes sure that only one thread is let to perform
the work in a single scan period (via cmpxchg), but if there's a thread with
mmap_sem locked for writing for several periods, multiple threads in
task_numa_work() can build up a convoy waiting for mmap_sem for read and then
all get unblocked at once.
This patch changes the down_read() to the trylock version, which prevents the
build up. For a workload experiencing mmap_sem contention, it's probably better
to postpone the NUMA balancing work anyway. This seems to have fixed the soft
lockups involving pmd_lock(), which is in line with the convoy theory.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170515131316.21909-1-vbabka@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
kernel/sched/fair.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 219fe58..47a0c55 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2470,7 +2470,8 @@ void task_numa_work(struct callback_head *work)
return;
- down_read(&mm->mmap_sem);
+ if (!down_read_trylock(&mm->mmap_sem))
+ return;
vma = find_vma(mm, start);
if (!vma) {
reset_ptenuma_scan(p);
^ permalink raw reply related [flat|nested] 5+ messages in thread
end of thread, other threads:[~2017-05-23 8:50 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-05-15 13:13 [PATCH] sched/numa: use down_read_trylock for mmap_sem Vlastimil Babka
2017-05-15 14:27 ` Rik van Riel
2017-05-15 14:35 ` Mel Gorman
2017-05-16 8:15 ` Peter Zijlstra
2017-05-23 8:47 ` [tip:sched/core] sched/numa: Use down_read_trylock() for the mmap_sem tip-bot for Vlastimil Babka
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).