From: Zeng Jingxiang <linuszeng@xxxxxxxxxxx>
Commit 14aa8b2d5c2e ("mm/mglru: don't sync disk for each aging cycle")
removed the opportunity to wake up flushers during the MGLRU page
reclamation process can lead to an increased likelihood of triggering OOM
when encountering many dirty pages during reclamation on MGLRU.
This leads to premature OOM if there are too many dirty pages in cgroup:
Killed
dd invoked oom-killer: gfp_mask=0x101cca(GFP_HIGHUSER_MOVABLE|__GFP_WRITE),
order=0, oom_score_adj=0
Call Trace:
<TASK>
dump_stack_lvl+0x5f/0x80
dump_stack+0x14/0x20
dump_header+0x46/0x1b0
oom_kill_process+0x104/0x220
out_of_memory+0x112/0x5a0
mem_cgroup_out_of_memory+0x13b/0x150
try_charge_memcg+0x44f/0x5c0
charge_memcg+0x34/0x50
__mem_cgroup_charge+0x31/0x90
filemap_add_folio+0x4b/0xf0
__filemap_get_folio+0x1a4/0x5b0
? srso_return_thunk+0x5/0x5f
? __block_commit_write+0x82/0xb0
ext4_da_write_begin+0xe5/0x270
generic_perform_write+0x134/0x2b0
ext4_buffered_write_iter+0x57/0xd0
ext4_file_write_iter+0x76/0x7d0
? selinux_file_permission+0x119/0x150
? srso_return_thunk+0x5/0x5f
? srso_return_thunk+0x5/0x5f
vfs_write+0x30c/0x440
ksys_write+0x65/0xe0
__x64_sys_write+0x1e/0x30
x64_sys_call+0x11c2/0x1d50
do_syscall_64+0x47/0x110
entry_SYSCALL_64_after_hwframe+0x76/0x7e
memory: usage 308224kB, limit 308224kB, failcnt 2589
swap: usage 0kB, limit 9007199254740988kB, failcnt 0
...
file_dirty 303247360
file_writeback 0
...
oom-kill:constraint=CONSTRAINT_MEMCG,nodemask=(null),cpuset=test,
mems_allowed=0,oom_memcg=/test,task_memcg=/test,task=dd,pid=4404,uid=0
Memory cgroup out of memory: Killed process 4404 (dd) total-vm:10512kB,
anon-rss:1152kB, file-rss:1824kB, shmem-rss:0kB, UID:0 pgtables:76kB
oom_score_adj:0
The flusher wake up was removed to decrease SSD wearing, but if we are
seeing all dirty folios at the tail of an LRU, not waking up the flusher
could lead to thrashing easily. So wake it up when a mem cgroups is about
to OOM due to dirty caches.
Link: https://lkml.kernel.org/r/20240829102543.189453-1-jingxiangzeng.cas@xxxxxxxxx
Link: https://lkml.kernel.org/r/20240913084506.3606292-1-jingxiangzeng.cas@xxxxxxxxx
Fixes: 14aa8b2d5c2e ("mm/mglru: don't sync disk for each aging cycle")
Signed-off-by: Zeng Jingxiang <linuszeng@xxxxxxxxxxx>
Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
Cc: T.J. Mercier <tjmercier@xxxxxxxxxx>
Cc: Wei Xu <weixugc@xxxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
---
Changes from v2:
- Acquire the lock before calling the folio_check_dirty_writeback
function.
- Link to v2: https://lore.kernel.org/all/20240913084506.3606292-1-jingxiangzeng.cas@xxxxxxxxx/
Changes from v1:
- Add code to count the number of unqueued_dirty in the sort_folio
function.
- Link to v1: https://lore.kernel.org/all/20240829102543.189453-1-jingxiangzeng.cas@xxxxxxxxx/
---
mm/vmscan.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 749cdc110c74..12c285a96353 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4290,6 +4290,8 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
int delta = folio_nr_pages(folio);
int refs = folio_lru_refs(folio);
int tier = lru_tier_from_refs(refs);
+ bool dirty = folio_test_dirty(folio);
+ bool writeback = folio_test_writeback(folio);
struct lru_gen_folio *lrugen = &lruvec->lrugen;
VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio);
@@ -4330,8 +4332,10 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
}
/* waiting for writeback */
- if (folio_test_locked(folio) || folio_test_writeback(folio) ||
- (type == LRU_GEN_FILE && folio_test_dirty(folio))) {
+ if (folio_test_locked(folio) || dirty ||
+ (type == LRU_GEN_FILE && writeback)) {
+ if (type == LRU_GEN_FILE && dirty && !writeback)
+ sc->nr.unqueued_dirty += delta;
gen = folio_inc_gen(lruvec, folio, true);
list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
return true;
@@ -4448,6 +4452,7 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc,
scanned, skipped, isolated,
type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
+ sc->nr.taken += isolated;
/*
* There might not be eligible folios due to reclaim_idx. Check the
* remaining to prevent livelock if it's not making progress.
@@ -4920,6 +4925,13 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
if (try_to_shrink_lruvec(lruvec, sc))
lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG);
+ /*
+ * If too many pages in the coldest generation that cannot
+ * be isolated, wake up flusher.
+ */
+ if (sc->nr.unqueued_dirty > sc->nr.taken)
+ wakeup_flusher_threads(WB_REASON_VMSCAN);
+
clear_mm_walk();
blk_finish_plug(&plug);
--
2.43.5
