I found a problem in my test machine that should_reclaim_retry() do
not get the right node if i set the cpuset.mems.
The should_reclaim_retry() and try_to_compact_pages() are iterating
nodes which are not allowed by cpusets and that makes the retry loop
happening more than unnecessary.
1.Test step and the machines.
------------
root@vm:/sys/fs/cgroup/test# numactl -H | grep size
node 0 size: 9477 MB
node 1 size: 10079 MB
node 2 size: 10079 MB
node 3 size: 10078 MB
root@vm:/sys/fs/cgroup/test# cat cpuset.mems
2
root@vm:/sys/fs/cgroup/test# stress --vm 1 --vm-bytes 12g --vm-keep
stress: info: [33430] dispatching hogs: 0 cpu, 0 io, 1 vm, 0 hdd
stress: FAIL: [33430] (425) <-- worker 33431 got signal 9
stress: WARN: [33430] (427) now reaping child worker processes
stress: FAIL: [33430] (461) failed run completed in 2s
2. reclaim_retry_zone info:
We can only alloc pages from node=2, but the reclaim_retry_zone is
node=0 and return true.
root@vm:/sys/kernel/debug/tracing# cat trace
stress-33431 [001] ..... 13223.617311: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=1 wmark_check=1
stress-33431 [001] ..... 13223.617682: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=2 wmark_check=1
stress-33431 [001] ..... 13223.618103: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=3 wmark_check=1
stress-33431 [001] ..... 13223.618454: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=4 wmark_check=1
stress-33431 [001] ..... 13223.618770: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=5 wmark_check=1
stress-33431 [001] ..... 13223.619150: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=6 wmark_check=1
stress-33431 [001] ..... 13223.619510: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=7 wmark_check=1
stress-33431 [001] ..... 13223.619850: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=8 wmark_check=1
stress-33431 [001] ..... 13223.620171: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=9 wmark_check=1
stress-33431 [001] ..... 13223.620533: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=10 wmark_check=1
stress-33431 [001] ..... 13223.620894: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=11 wmark_check=1
stress-33431 [001] ..... 13223.621224: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=12 wmark_check=1
stress-33431 [001] ..... 13223.621551: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=13 wmark_check=1
stress-33431 [001] ..... 13223.621847: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=14 wmark_check=1
stress-33431 [001] ..... 13223.622200: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=15 wmark_check=1
stress-33431 [001] ..... 13223.622580: reclaim_retry_zone: node=0 zone=Normal order=0 reclaimable=4260 available=1772019 min_wmark=5962 no_progress_loops=16 wmark_check=1
3. Root cause:
Nodemask usually comes from mempolicy in policy_nodemask(), which
is always NULL unless the memory policy is bind or prefer_many.
nodemask = NULL
__alloc_pages_noprof()
prepare_alloc_pages
ac->nodemask = &cpuset_current_mems_allowed;
get_page_from_freelist()
ac.nodemask = nodemask; /*set NULL*/
__alloc_pages_slowpath() {
f (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
ac->nodemask = NULL;
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->highest_zoneidx, ac->nodemask);
/* so ac.nodemask = NULL */
}
According to the function flow above, we do not have the memory limit to
follow cpuset.mems, so we need to add it.
Test result:
Try 3 times with different cpuset.mems and alloc large memorys than that numa size.
echo 1 > cpuset.mems
stress --vm 1 --vm-bytes 12g --vm-hang 0
---------------
echo 2 > cpuset.mems
stress --vm 1 --vm-bytes 12g --vm-hang 0
---------------
echo 3 > cpuset.mems
stress --vm 1 --vm-bytes 12g --vm-hang 0
The retry trace look like:
stress-2139 [003] ..... 666.934104: reclaim_retry_zone: node=1 zone=Normal order=0 reclaimable=7 available=7355 min_wmark=8598 no_progress_loops=1 wmark_check=0
stress-2204 [010] ..... 695.447393: reclaim_retry_zone: node=2 zone=Normal order=0 reclaimable=2 available=6916 min_wmark=8598 no_progress_loops=1 wmark_check=0
stress-2271 [008] ..... 725.683058: reclaim_retry_zone: node=3 zone=Normal order=0 reclaimable=17 available=8079 min_wmark=8597 no_progress_loops=1 wmark_check=0
With this patch, we can check the right node and get less retry in __alloc_pages_slowpath()
because there is nothing to do.
V1:
Do the same with the page allocator using __cpuset_zone_allowed().
Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
Signed-off-by: Zhongkun He <hezhongkun.hzk@xxxxxxxxxxxxx>
---
mm/compaction.c | 6 ++++++
mm/page_alloc.c | 5 +++++
2 files changed, 11 insertions(+)
diff --git a/mm/compaction.c b/mm/compaction.c
index d1041fbce679..a2b16b08cbbf 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -23,6 +23,7 @@
#include <linux/freezer.h>
#include <linux/page_owner.h>
#include <linux/psi.h>
+#include <linux/cpuset.h>
#include "internal.h"
#ifdef CONFIG_COMPACTION
@@ -2822,6 +2823,11 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
ac->highest_zoneidx, ac->nodemask) {
enum compact_result status;
+ if (cpusets_enabled() &&
+ (alloc_flags & ALLOC_CPUSET) &&
+ !__cpuset_zone_allowed(zone, gfp_mask))
+ continue;
+
if (prio > MIN_COMPACT_PRIORITY
&& compaction_deferred(zone, order)) {
rc = max_t(enum compact_result, COMPACT_DEFERRED, rc);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 29608ca294cf..8a67d760b71a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4128,6 +4128,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
unsigned long min_wmark = min_wmark_pages(zone);
bool wmark;
+ if (cpusets_enabled() &&
+ (alloc_flags & ALLOC_CPUSET) &&
+ !__cpuset_zone_allowed(zone, gfp_mask))
+ continue;
+
available = reclaimable = zone_reclaimable_pages(zone);
available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
--
2.20.1
