@@ -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);
@@ -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);
should_reclaim_retry() is not ALLOC_CPUSET aware and that means that it considers reclaimability of NUMA nodes which are outside of the cpuset. If other nodes have a lot of reclaimable memory then should_reclaim_retry would instruct page allocator to retry even though there is no memory reclaimable on the cpuset nodemask. This is not really a huge problem because the number of retries without any reclaim progress is bound but it could be certainly improved. This is a cold path so this shouldn't really have a measurable impact on performance on most workloads. 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 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(). --from Michal V2: Update the problem description. --from Michal Suggested-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Zhongkun He <hezhongkun.hzk@bytedance.com> Acked-by: Michal Hocko <mhocko@suse.com> --- mm/compaction.c | 6 ++++++ mm/page_alloc.c | 5 +++++ 2 files changed, 11 insertions(+)