From: Jiayuan Chen Currently, kswapd_failures is reset in multiple places (kswapd, direct reclaim, PCP freeing, memory-tiers), but there's no way to trace when and why it was reset, making it difficult to debug memory reclaim issues. This patch: 1. Introduce kswapd_clear_hopeless() as a wrapper function to centralize kswapd_failures reset logic. 2. Introduce kswapd_test_hopeless() to encapsulate hopeless node checks, replacing all open-coded kswapd_failures comparisons. 3. Add kswapd_clear_hopeless_reason enum to distinguish reset sources: - KSWAPD_CLEAR_HOPELESS_KSWAPD: reset from kswapd context - KSWAPD_CLEAR_HOPELESS_DIRECT: reset from direct reclaim - KSWAPD_CLEAR_HOPELESS_PCP: reset from PCP page freeing - KSWAPD_CLEAR_HOPELESS_OTHER: reset from other paths 4. Add tracepoints for better observability: - mm_vmscan_kswapd_clear_hopeless: traces each reset with reason - mm_vmscan_kswapd_reclaim_fail: traces each kswapd reclaim failure Test results: $ trace-cmd record -e vmscan:mm_vmscan_kswapd_clear_hopeless -e vmscan:mm_vmscan_kswapd_reclaim_fail $ # generate memory pressure $ trace-cmd report cpus=4 kswapd0-71 [000] 27.216563: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=1 kswapd0-71 [000] 27.217169: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=2 kswapd0-71 [000] 27.217764: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=3 kswapd0-71 [000] 27.218353: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=4 kswapd0-71 [000] 27.218993: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=5 kswapd0-71 [000] 27.219744: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=6 kswapd0-71 [000] 27.220488: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=7 kswapd0-71 [000] 27.221206: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=8 kswapd0-71 [000] 27.221806: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=9 kswapd0-71 [000] 27.222634: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=10 kswapd0-71 [000] 27.223286: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=11 kswapd0-71 [000] 27.223894: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=12 kswapd0-71 [000] 27.224712: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=13 kswapd0-71 [000] 27.225424: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=14 kswapd0-71 [000] 27.226082: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=15 kswapd0-71 [000] 27.226810: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=16 kswapd1-72 [002] 27.386869: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=1 kswapd1-72 [002] 27.387435: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=2 kswapd1-72 [002] 27.388016: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=3 kswapd1-72 [002] 27.388586: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=4 kswapd1-72 [002] 27.389155: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=5 kswapd1-72 [002] 27.389723: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=6 kswapd1-72 [002] 27.390292: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=7 kswapd1-72 [002] 27.392364: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=8 kswapd1-72 [002] 27.392934: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=9 kswapd1-72 [002] 27.393504: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=10 kswapd1-72 [002] 27.394073: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=11 kswapd1-72 [002] 27.394899: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=12 kswapd1-72 [002] 27.395472: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=13 kswapd1-72 [002] 27.396055: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=14 kswapd1-72 [002] 27.396628: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=15 kswapd1-72 [002] 27.397199: mm_vmscan_kswapd_reclaim_fail: nid=1 failures=16 kworker/u18:0-40 [002] 27.410151: mm_vmscan_kswapd_clear_hopeless: nid=0 reason=DIRECT kswapd0-71 [000] 27.439454: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=1 kswapd0-71 [000] 27.440048: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=2 kswapd0-71 [000] 27.440634: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=3 kswapd0-71 [000] 27.441211: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=4 kswapd0-71 [000] 27.441787: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=5 kswapd0-71 [000] 27.442363: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=6 kswapd0-71 [000] 27.443030: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=7 kswapd0-71 [000] 27.443725: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=8 kswapd0-71 [000] 27.444315: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=9 kswapd0-71 [000] 27.444898: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=10 kswapd0-71 [000] 27.445476: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=11 kswapd0-71 [000] 27.446053: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=12 kswapd0-71 [000] 27.446646: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=13 kswapd0-71 [000] 27.447230: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=14 kswapd0-71 [000] 27.447812: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=15 kswapd0-71 [000] 27.448391: mm_vmscan_kswapd_reclaim_fail: nid=0 failures=16 ann-423 [003] 28.028285: mm_vmscan_kswapd_clear_hopeless: nid=0 reason=PCP Acked-by: Shakeel Butt Suggested-by: Johannes Weiner Signed-off-by: Jiayuan Chen Signed-off-by: Jiayuan Chen --- include/linux/mmzone.h | 19 ++++++++++--- include/trace/events/vmscan.h | 51 +++++++++++++++++++++++++++++++++++ mm/memory-tiers.c | 2 +- mm/page_alloc.c | 4 +-- mm/show_mem.c | 3 +-- mm/vmscan.c | 29 +++++++++++++------- mm/vmstat.c | 2 +- 7 files changed, 91 insertions(+), 19 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3a0f52188ff6..d26fdd48f106 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1534,16 +1534,27 @@ static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) #include void build_all_zonelists(pg_data_t *pgdat); -void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, - enum zone_type highest_zoneidx); -void kswapd_try_clear_hopeless(struct pglist_data *pgdat, - unsigned int order, int highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); + +enum kswapd_clear_hopeless_reason { + KSWAPD_CLEAR_HOPELESS_OTHER = 0, + KSWAPD_CLEAR_HOPELESS_KSWAPD, + KSWAPD_CLEAR_HOPELESS_DIRECT, + KSWAPD_CLEAR_HOPELESS_PCP, +}; + +void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, + enum zone_type highest_zoneidx); +void kswapd_try_clear_hopeless(struct pglist_data *pgdat, + unsigned int order, int highest_zoneidx); +void kswapd_clear_hopeless(pg_data_t *pgdat, enum kswapd_clear_hopeless_reason reason); +bool kswapd_test_hopeless(pg_data_t *pgdat); + /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 490958fa10de..ea58e4656abf 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -40,6 +40,16 @@ {_VMSCAN_THROTTLE_CONGESTED, "VMSCAN_THROTTLE_CONGESTED"} \ ) : "VMSCAN_THROTTLE_NONE" +TRACE_DEFINE_ENUM(KSWAPD_CLEAR_HOPELESS_OTHER); +TRACE_DEFINE_ENUM(KSWAPD_CLEAR_HOPELESS_KSWAPD); +TRACE_DEFINE_ENUM(KSWAPD_CLEAR_HOPELESS_DIRECT); +TRACE_DEFINE_ENUM(KSWAPD_CLEAR_HOPELESS_PCP); + +#define kswapd_clear_hopeless_reason_ops \ + {KSWAPD_CLEAR_HOPELESS_KSWAPD, "KSWAPD"}, \ + {KSWAPD_CLEAR_HOPELESS_DIRECT, "DIRECT"}, \ + {KSWAPD_CLEAR_HOPELESS_PCP, "PCP"}, \ + {KSWAPD_CLEAR_HOPELESS_OTHER, "OTHER"} #define trace_reclaim_flags(file) ( \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ @@ -535,6 +545,47 @@ TRACE_EVENT(mm_vmscan_throttled, __entry->usec_delayed, show_throttle_flags(__entry->reason)) ); + +TRACE_EVENT(mm_vmscan_kswapd_reclaim_fail, + + TP_PROTO(int nid, int failures), + + TP_ARGS(nid, failures), + + TP_STRUCT__entry( + __field(int, nid) + __field(int, failures) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->failures = failures; + ), + + TP_printk("nid=%d failures=%d", + __entry->nid, __entry->failures) +); + +TRACE_EVENT(mm_vmscan_kswapd_clear_hopeless, + + TP_PROTO(int nid, int reason), + + TP_ARGS(nid, reason), + + TP_STRUCT__entry( + __field(int, nid) + __field(int, reason) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->reason = reason; + ), + + TP_printk("nid=%d reason=%s", + __entry->nid, + __print_symbolic(__entry->reason, kswapd_clear_hopeless_reason_ops)) +); #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index 864811fff409..d6ef5ba8e70a 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -956,7 +956,7 @@ static ssize_t demotion_enabled_store(struct kobject *kobj, struct pglist_data *pgdat; for_each_online_pgdat(pgdat) - atomic_set(&pgdat->kswapd_failures, 0); + kswapd_clear_hopeless(pgdat, KSWAPD_CLEAR_HOPELESS_OTHER); } return count; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c380f063e8b7..1b1dedc7ede1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2916,9 +2916,9 @@ static bool free_frozen_page_commit(struct zone *zone, * 'hopeless node' to stay in that state for a while. Let * kswapd work again by resetting kswapd_failures. */ - if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES && + if (kswapd_test_hopeless(pgdat) && next_memory_node(pgdat->node_id) < MAX_NUMNODES) - atomic_set(&pgdat->kswapd_failures, 0); + kswapd_clear_hopeless(pgdat, KSWAPD_CLEAR_HOPELESS_PCP); } return ret; } diff --git a/mm/show_mem.c b/mm/show_mem.c index 3a4b5207635d..24078ac3e6bc 100644 --- a/mm/show_mem.c +++ b/mm/show_mem.c @@ -278,8 +278,7 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z #endif K(node_page_state(pgdat, NR_PAGETABLE)), K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)), - str_yes_no(atomic_read(&pgdat->kswapd_failures) >= - MAX_RECLAIM_RETRIES), + str_yes_no(kswapd_test_hopeless(pgdat)), K(node_page_state(pgdat, NR_BALLOON_PAGES))); } diff --git a/mm/vmscan.c b/mm/vmscan.c index ecd019b8b452..0ec2baa4ed4e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -507,7 +507,7 @@ static bool skip_throttle_noprogress(pg_data_t *pgdat) * If kswapd is disabled, reschedule if necessary but do not * throttle as the system is likely near OOM. */ - if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES) + if (kswapd_test_hopeless(pgdat)) return true; /* @@ -6453,7 +6453,7 @@ static bool allow_direct_reclaim(pg_data_t *pgdat) int i; bool wmark_ok; - if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES) + if (kswapd_test_hopeless(pgdat)) return true; for_each_managed_zone_pgdat(zone, pgdat, i, ZONE_NORMAL) { @@ -6862,7 +6862,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ - if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES) + if (kswapd_test_hopeless(pgdat)) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { @@ -7134,8 +7134,11 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) * watermark_high at this point. We need to avoid increasing the * failure count to prevent the kswapd thread from stopping. */ - if (!sc.nr_reclaimed && !boosted) - atomic_inc(&pgdat->kswapd_failures); + if (!sc.nr_reclaimed && !boosted) { + int fail_cnt = atomic_inc_return(&pgdat->kswapd_failures); + /* kswapd context, low overhead to trace every failure */ + trace_mm_vmscan_kswapd_reclaim_fail(pgdat->node_id, fail_cnt); + } out: clear_reclaim_active(pgdat, highest_zoneidx); @@ -7394,7 +7397,7 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, return; /* Hopeless node, leave it to direct reclaim if possible */ - if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES || + if (kswapd_test_hopeless(pgdat) || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* @@ -7414,9 +7417,11 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, wake_up_interruptible(&pgdat->kswapd_wait); } -static void kswapd_clear_hopeless(pg_data_t *pgdat) +void kswapd_clear_hopeless(pg_data_t *pgdat, enum kswapd_clear_hopeless_reason reason) { - atomic_set(&pgdat->kswapd_failures, 0); + /* Only trace actual resets, not redundant zero-to-zero */ + if (atomic_xchg(&pgdat->kswapd_failures, 0)) + trace_mm_vmscan_kswapd_clear_hopeless(pgdat->node_id, reason); } /* @@ -7429,7 +7434,13 @@ void kswapd_try_clear_hopeless(struct pglist_data *pgdat, unsigned int order, int highest_zoneidx) { if (pgdat_balanced(pgdat, order, highest_zoneidx)) - kswapd_clear_hopeless(pgdat); + kswapd_clear_hopeless(pgdat, current_is_kswapd() ? + KSWAPD_CLEAR_HOPELESS_KSWAPD : KSWAPD_CLEAR_HOPELESS_DIRECT); +} + +bool kswapd_test_hopeless(pg_data_t *pgdat) +{ + return atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES; } #ifdef CONFIG_HIBERNATION diff --git a/mm/vmstat.c b/mm/vmstat.c index 65de88cdf40e..3d65f5c9c224 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1855,7 +1855,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n start_pfn: %lu" "\n reserved_highatomic: %lu" "\n free_highatomic: %lu", - atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES, + kswapd_test_hopeless(pgdat), zone->zone_start_pfn, zone->nr_reserved_highatomic, zone->nr_free_highatomic); -- 2.43.0