summaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorSuren Baghdasaryan <surenb@google.com>2022-03-22 14:43:54 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-03-22 15:57:06 -0700
commitfa7fc75f6319dcd044e332ad309a86126a610bdf (patch)
treea4589276ad65f2a1299e62c333f20b7e3fdad843 /mm/page_alloc.c
parent1ca75fa7f19d694c58af681fa023295072b03120 (diff)
downloadlinux-fa7fc75f6319dcd044e332ad309a86126a610bdf.tar.bz2
mm: count time in drain_all_pages during direct reclaim as memory pressure
When page allocation in direct reclaim path fails, the system will make one attempt to shrink per-cpu page lists and free pages from high alloc reserves. Draining per-cpu pages into buddy allocator can be a very slow operation because it's done using workqueues and the task in direct reclaim waits for all of them to finish before proceeding. Currently this time is not accounted as psi memory stall. While testing mobile devices under extreme memory pressure, when allocations are failing during direct reclaim, we notices that psi events which would be expected in such conditions were not triggered. After profiling these cases it was determined that the reason for missing psi events was that a big chunk of time spent in direct reclaim is not accounted as memory stall, therefore psi would not reach the levels at which an event is generated. Further investigation revealed that the bulk of that unaccounted time was spent inside drain_all_pages call. A typical captured case when drain_all_pages path gets activated: __alloc_pages_slowpath took 44.644.613ns __perform_reclaim took 751.668ns (1.7%) drain_all_pages took 43.887.167ns (98.3%) PSI in this case records the time spent in __perform_reclaim but ignores drain_all_pages, IOW it misses 98.3% of the time spent in __alloc_pages_slowpath. Annotate __alloc_pages_direct_reclaim in its entirety so that delays from handling page allocation failure in the direct reclaim path are accounted as memory stall. Link: https://lkml.kernel.org/r/20220223194812.1299646-1-surenb@google.com Signed-off-by: Suren Baghdasaryan <surenb@google.com> Reported-by: Tim Murray <timmurray@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c10
1 files changed, 6 insertions, 4 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7d24522b3b54..30d35f24d7a5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4554,13 +4554,12 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac)
{
unsigned int noreclaim_flag;
- unsigned long pflags, progress;
+ unsigned long progress;
cond_resched();
/* We now go into synchronous reclaim */
cpuset_memory_pressure_bump();
- psi_memstall_enter(&pflags);
fs_reclaim_acquire(gfp_mask);
noreclaim_flag = memalloc_noreclaim_save();
@@ -4569,7 +4568,6 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
memalloc_noreclaim_restore(noreclaim_flag);
fs_reclaim_release(gfp_mask);
- psi_memstall_leave(&pflags);
cond_resched();
@@ -4583,11 +4581,13 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
unsigned long *did_some_progress)
{
struct page *page = NULL;
+ unsigned long pflags;
bool drained = false;
+ psi_memstall_enter(&pflags);
*did_some_progress = __perform_reclaim(gfp_mask, order, ac);
if (unlikely(!(*did_some_progress)))
- return NULL;
+ goto out;
retry:
page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
@@ -4603,6 +4603,8 @@ retry:
drained = true;
goto retry;
}
+out:
+ psi_memstall_leave(&pflags);
return page;
}