From 57e9cc50f4dd926d6c38751799d25cad89fb2bd9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 26 Oct 2022 14:01:33 -0400 Subject: mm: vmscan: split khugepaged stats from direct reclaim stats Direct reclaim stats are useful for identifying a potential source for application latency, as well as spotting issues with kswapd. However, khugepaged currently distorts the picture: as a kernel thread it doesn't impose allocation latencies on userspace, and it explicitly opts out of kswapd reclaim. Its activity showing up in the direct reclaim stats is misleading. Counting it as kswapd reclaim could also cause confusion when trying to understand actual kswapd behavior. Break out khugepaged from the direct reclaim counters into new pgsteal_khugepaged, pgdemote_khugepaged, pgscan_khugepaged counters. Test with a huge executable (CONFIG_READ_ONLY_THP_FOR_FS): pgsteal_kswapd 1342185 pgsteal_direct 0 pgsteal_khugepaged 3623 pgscan_kswapd 1345025 pgscan_direct 0 pgscan_khugepaged 3623 Link: https://lkml.kernel.org/r/20221026180133.377671-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reported-by: Eric Bergen Cc: Matthew Wilcox (Oracle) Cc: Yang Shi Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/vmscan.c | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 55a5b5d66d68..d7c71be6417d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include @@ -1047,6 +1048,24 @@ void drop_slab(void) drop_slab_node(nid); } +static int reclaimer_offset(void) +{ + BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != + PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD); + BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != + PGSCAN_DIRECT - PGSCAN_KSWAPD); + BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != + PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD); + BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != + PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD); + + if (current_is_kswapd()) + return 0; + if (current_is_khugepaged()) + return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD; + return PGSTEAL_DIRECT - PGSTEAL_KSWAPD; +} + static inline int is_page_cache_freeable(struct folio *folio) { /* @@ -1599,10 +1618,7 @@ static unsigned int demote_folio_list(struct list_head *demote_folios, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); - if (current_is_kswapd()) - __count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded); - else - __count_vm_events(PGDEMOTE_DIRECT, nr_succeeded); + __count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded); return nr_succeeded; } @@ -2475,7 +2491,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); - item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; + item = PGSCAN_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); @@ -2492,7 +2508,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, move_folios_to_lru(lruvec, &folio_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); - item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; + item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); @@ -4871,7 +4887,7 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, break; } - item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; + item = PGSCAN_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) { __count_vm_events(item, isolated); __count_vm_events(PGREFILL, sorted); @@ -5049,7 +5065,7 @@ retry: if (walk && walk->batched) reset_batch_size(lruvec, walk); - item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; + item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); __count_memcg_events(memcg, item, reclaimed); -- cgit v1.2.3