oom, trace: add oom detection tracepoints

should_reclaim_retry is the central decision point for declaring the
OOM.  It might be really useful to expose data used for this decision
making when debugging an unexpected oom situations.

Say we have an OOM report:
[   52.264001] mem_eater invoked oom-killer: gfp_mask=0x24280ca(GFP_HIGHUSER_MOVABLE|__GFP_ZERO), nodemask=0, order=0, oom_score_adj=0
[   52.267549] CPU: 3 PID: 3148 Comm: mem_eater Tainted: G        W       4.8.0-oomtrace3-00006-gb21338b386d2 #1024

Now we can check the tracepoint data to see how we have ended up in this
situation:
       mem_eater-3148  [003] ....    52.432801: reclaim_retry_zone: node=0 zone=DMA32 order=0 reclaimable=51 available=11134 min_wmark=11084 no_progress_loops=1 wmark_check=1
       mem_eater-3148  [003] ....    52.433269: reclaim_retry_zone: node=0 zone=DMA32 order=0 reclaimable=51 available=11103 min_wmark=11084 no_progress_loops=1 wmark_check=1
       mem_eater-3148  [003] ....    52.433712: reclaim_retry_zone: node=0 zone=DMA32 order=0 reclaimable=51 available=11100 min_wmark=11084 no_progress_loops=2 wmark_check=1
       mem_eater-3148  [003] ....    52.434067: reclaim_retry_zone: node=0 zone=DMA32 order=0 reclaimable=51 available=11097 min_wmark=11084 no_progress_loops=3 wmark_check=1
       mem_eater-3148  [003] ....    52.434414: reclaim_retry_zone: node=0 zone=DMA32 order=0 reclaimable=51 available=11094 min_wmark=11084 no_progress_loops=4 wmark_check=1
       mem_eater-3148  [003] ....    52.434761: reclaim_retry_zone: node=0 zone=DMA32 order=0 reclaimable=51 available=11091 min_wmark=11084 no_progress_loops=5 wmark_check=1
       mem_eater-3148  [003] ....    52.435108: reclaim_retry_zone: node=0 zone=DMA32 order=0 reclaimable=51 available=11087 min_wmark=11084 no_progress_loops=6 wmark_check=1
       mem_eater-3148  [003] ....    52.435478: reclaim_retry_zone: node=0 zone=DMA32 order=0 reclaimable=51 available=11084 min_wmark=11084 no_progress_loops=7 wmark_check=0
       mem_eater-3148  [003] ....    52.435478: reclaim_retry_zone: node=0 zone=DMA order=0 reclaimable=0 available=1126 min_wmark=179 no_progress_loops=7 wmark_check=0

The above shows that we can quickly deduce that the reclaim stopped
making any progress (see no_progress_loops increased in each round) and
while there were still some 51 reclaimable pages they couldn't be
dropped for some reason (vmscan trace points would tell us more about
that part).  available will represent reclaimable + free_pages scaled
down per no_progress_loops factor.  This is essentially an optimistic
estimate of how much memory we would have when reclaiming everything.
This can be compared to min_wmark to get a rought idea but the
wmark_check tells the result of the watermark check which is more
precise (includes lowmem reserves, considers the order etc.).  As we can
see no zone is eligible in the end and that is why we have triggered the
oom in this situation.

Please note that higher order requests might fail on the wmark_check
even when there is much more memory available than min_wmark - e.g.
when the memory is fragmented.  A follow up tracepoint will help to
debug those situations.

Link: http://lkml.kernel.org/r/20161220130135.15719-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Michal Hocko 2017-02-22 15:42:00 -08:00 committed by Linus Torvalds
parent aff28015fe
commit d379f01de0
2 changed files with 50 additions and 2 deletions

View File

@ -4,6 +4,7 @@
#if !defined(_TRACE_OOM_H) || defined(TRACE_HEADER_MULTI_READ) #if !defined(_TRACE_OOM_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_OOM_H #define _TRACE_OOM_H
#include <linux/tracepoint.h> #include <linux/tracepoint.h>
#include <trace/events/mmflags.h>
TRACE_EVENT(oom_score_adj_update, TRACE_EVENT(oom_score_adj_update,
@ -27,6 +28,47 @@ TRACE_EVENT(oom_score_adj_update,
__entry->pid, __entry->comm, __entry->oom_score_adj) __entry->pid, __entry->comm, __entry->oom_score_adj)
); );
TRACE_EVENT(reclaim_retry_zone,
TP_PROTO(struct zoneref *zoneref,
int order,
unsigned long reclaimable,
unsigned long available,
unsigned long min_wmark,
int no_progress_loops,
bool wmark_check),
TP_ARGS(zoneref, order, reclaimable, available, min_wmark, no_progress_loops, wmark_check),
TP_STRUCT__entry(
__field( int, node)
__field( int, zone_idx)
__field( int, order)
__field( unsigned long, reclaimable)
__field( unsigned long, available)
__field( unsigned long, min_wmark)
__field( int, no_progress_loops)
__field( bool, wmark_check)
),
TP_fast_assign(
__entry->node = zone_to_nid(zoneref->zone);
__entry->zone_idx = zoneref->zone_idx;
__entry->order = order;
__entry->reclaimable = reclaimable;
__entry->available = available;
__entry->min_wmark = min_wmark;
__entry->no_progress_loops = no_progress_loops;
__entry->wmark_check = wmark_check;
),
TP_printk("node=%d zone=%-8s order=%d reclaimable=%lu available=%lu min_wmark=%lu no_progress_loops=%d wmark_check=%d",
__entry->node, __print_symbolic(__entry->zone_idx, ZONE_TYPE),
__entry->order,
__entry->reclaimable, __entry->available, __entry->min_wmark,
__entry->no_progress_loops,
__entry->wmark_check)
);
#endif #endif
/* This part must be outside protection */ /* This part must be outside protection */

View File

@ -55,6 +55,7 @@
#include <linux/kmemleak.h> #include <linux/kmemleak.h>
#include <linux/compaction.h> #include <linux/compaction.h>
#include <trace/events/kmem.h> #include <trace/events/kmem.h>
#include <trace/events/oom.h>
#include <linux/prefetch.h> #include <linux/prefetch.h>
#include <linux/mm_inline.h> #include <linux/mm_inline.h>
#include <linux/migrate.h> #include <linux/migrate.h>
@ -3468,6 +3469,8 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
ac->nodemask) { ac->nodemask) {
unsigned long available; unsigned long available;
unsigned long reclaimable; unsigned long reclaimable;
unsigned long min_wmark = min_wmark_pages(zone);
bool wmark;
available = reclaimable = zone_reclaimable_pages(zone); available = reclaimable = zone_reclaimable_pages(zone);
available -= DIV_ROUND_UP((*no_progress_loops) * available, available -= DIV_ROUND_UP((*no_progress_loops) * available,
@ -3478,8 +3481,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
* Would the allocation succeed if we reclaimed the whole * Would the allocation succeed if we reclaimed the whole
* available? * available?
*/ */
if (__zone_watermark_ok(zone, order, min_wmark_pages(zone), wmark = __zone_watermark_ok(zone, order, min_wmark,
ac_classzone_idx(ac), alloc_flags, available)) { ac_classzone_idx(ac), alloc_flags, available);
trace_reclaim_retry_zone(z, order, reclaimable,
available, min_wmark, *no_progress_loops, wmark);
if (wmark) {
/* /*
* If we didn't make any progress and have a lot of * If we didn't make any progress and have a lot of
* dirty + writeback pages then we should wait for * dirty + writeback pages then we should wait for