[PATCH v2 1/2] mm: vmscan: add cgroup IDs to vmscan tracepoints
From: Thomas Ballasi <hidden>
Date: 2025-12-16 14:03:33
Also in:
linux-mm
Subsystem:
memory management, memory management - mglru (multi-gen lru), memory management - reclaim, the rest, tracing · Maintainers:
Andrew Morton, Johannes Weiner, Linus Torvalds, Steven Rostedt, Masami Hiramatsu
Memory reclaim events are currently difficult to attribute to specific cgroups, making debugging memory pressure issues challenging. This patch adds memory cgroup ID (memcg_id) to key vmscan tracepoints to enable better correlation and analysis. For operations not associated with a specific cgroup, the field is defaulted to 0. Signed-off-by: Thomas Ballasi <redacted> --- include/trace/events/vmscan.h | 65 +++++++++++++++++++++-------------- mm/vmscan.c | 17 ++++----- 2 files changed, 48 insertions(+), 34 deletions(-)
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index d2123dd960d59..afc9f80d03f34 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h@@ -114,85 +114,92 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd, DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(int order, gfp_t gfp_flags, unsigned short memcg_id), - TP_ARGS(order, gfp_flags), + TP_ARGS(order, gfp_flags, memcg_id), TP_STRUCT__entry( __field( int, order ) __field( unsigned long, gfp_flags ) + __field( unsigned short, memcg_id ) ), TP_fast_assign( __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; + __entry->memcg_id = memcg_id; ), - TP_printk("order=%d gfp_flags=%s", + TP_printk("order=%d gfp_flags=%s memcg_id=%u", __entry->order, - show_gfp_flags(__entry->gfp_flags)) + show_gfp_flags(__entry->gfp_flags), + __entry->memcg_id) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(int order, gfp_t gfp_flags, unsigned short memcg_id), - TP_ARGS(order, gfp_flags) + TP_ARGS(order, gfp_flags, memcg_id) ); #ifdef CONFIG_MEMCG DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(int order, gfp_t gfp_flags, unsigned short memcg_id), - TP_ARGS(order, gfp_flags) + TP_ARGS(order, gfp_flags, memcg_id) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(int order, gfp_t gfp_flags, unsigned short memcg_id), - TP_ARGS(order, gfp_flags) + TP_ARGS(order, gfp_flags, memcg_id) ); #endif /* CONFIG_MEMCG */ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, unsigned short memcg_id), - TP_ARGS(nr_reclaimed), + TP_ARGS(nr_reclaimed, memcg_id), TP_STRUCT__entry( __field( unsigned long, nr_reclaimed ) + __field( unsigned short, memcg_id ) ), TP_fast_assign( __entry->nr_reclaimed = nr_reclaimed; + __entry->memcg_id = memcg_id; ), - TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed) + TP_printk("nr_reclaimed=%lu memcg_id=%u", + __entry->nr_reclaimed, + __entry->memcg_id) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, unsigned short memcg_id), - TP_ARGS(nr_reclaimed) + TP_ARGS(nr_reclaimed, memcg_id) ); #ifdef CONFIG_MEMCG DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, unsigned short memcg_id), - TP_ARGS(nr_reclaimed) + TP_ARGS(nr_reclaimed, memcg_id) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, unsigned short memcg_id), - TP_ARGS(nr_reclaimed) + TP_ARGS(nr_reclaimed, memcg_id) ); #endif /* CONFIG_MEMCG */
@@ -209,6 +216,7 @@ TRACE_EVENT(mm_shrink_slab_start, __field(struct shrinker *, shr) __field(void *, shrink) __field(int, nid) + __field(unsigned short, memcg_id) __field(long, nr_objects_to_shrink) __field(unsigned long, gfp_flags) __field(unsigned long, cache_items)
@@ -221,6 +229,7 @@ TRACE_EVENT(mm_shrink_slab_start, __entry->shr = shr; __entry->shrink = shr->scan_objects; __entry->nid = sc->nid; + __entry->memcg_id = sc->memcg ? mem_cgroup_id(sc->memcg) : 0; __entry->nr_objects_to_shrink = nr_objects_to_shrink; __entry->gfp_flags = (__force unsigned long)sc->gfp_mask; __entry->cache_items = cache_items;
@@ -229,10 +238,11 @@ TRACE_EVENT(mm_shrink_slab_start, __entry->priority = priority; ), - TP_printk("%pS %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d", + TP_printk("%pS %p: nid: %d memcg_id: %u objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d", __entry->shrink, __entry->shr, __entry->nid, + __entry->memcg_id, __entry->nr_objects_to_shrink, show_gfp_flags(__entry->gfp_flags), __entry->cache_items,
@@ -242,15 +252,16 @@ TRACE_EVENT(mm_shrink_slab_start, ); TRACE_EVENT(mm_shrink_slab_end, - TP_PROTO(struct shrinker *shr, int nid, int shrinker_retval, + TP_PROTO(struct shrinker *shr, struct shrink_control *sc, int shrinker_retval, long unused_scan_cnt, long new_scan_cnt, long total_scan), - TP_ARGS(shr, nid, shrinker_retval, unused_scan_cnt, new_scan_cnt, + TP_ARGS(shr, sc, shrinker_retval, unused_scan_cnt, new_scan_cnt, total_scan), TP_STRUCT__entry( __field(struct shrinker *, shr) __field(int, nid) + __field(unsigned short, memcg_id) __field(void *, shrink) __field(long, unused_scan) __field(long, new_scan)
@@ -260,7 +271,8 @@ TRACE_EVENT(mm_shrink_slab_end, TP_fast_assign( __entry->shr = shr; - __entry->nid = nid; + __entry->nid = sc->nid; + __entry->memcg_id = sc->memcg ? mem_cgroup_id(sc->memcg) : 0; __entry->shrink = shr->scan_objects; __entry->unused_scan = unused_scan_cnt; __entry->new_scan = new_scan_cnt;
@@ -268,10 +280,11 @@ TRACE_EVENT(mm_shrink_slab_end, __entry->total_scan = total_scan; ), - TP_printk("%pS %p: nid: %d unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d", + TP_printk("%pS %p: nid: %d memcg_id: %u unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d", __entry->shrink, __entry->shr, __entry->nid, + __entry->memcg_id, __entry->unused_scan, __entry->new_scan, __entry->total_scan,
@@ -463,9 +476,9 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin, DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned long nr_reclaimed, unsigned short memcg_id), - TP_ARGS(nr_reclaimed) + TP_ARGS(nr_reclaimed, memcg_id) ); TRACE_EVENT(mm_vmscan_throttled,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 258f5472f1e90..0e65ec3a087a5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c@@ -931,7 +931,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, */ new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); - trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); + trace_mm_shrink_slab_end(shrinker, shrinkctl, freed, nr, new_nr, total_scan); return freed; }
@@ -7092,11 +7092,11 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, return 1; set_task_reclaim_state(current, &sc.reclaim_state); - trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); + trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask, 0); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); - trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); + trace_mm_vmscan_direct_reclaim_end(nr_reclaimed, 0); set_task_reclaim_state(current, NULL); return nr_reclaimed;
@@ -7126,7 +7126,8 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, - sc.gfp_mask); + sc.gfp_mask, + mem_cgroup_id(memcg)); /* * NOTE: Although we can get the priority field, using it
@@ -7137,7 +7138,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, */ shrink_lruvec(lruvec, &sc); - trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); + trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed, mem_cgroup_id(memcg)); *nr_scanned = sc.nr_scanned;
@@ -7171,13 +7172,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); - trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); + trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask, mem_cgroup_id(memcg)); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); - trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); + trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed, mem_cgroup_id(memcg)); set_task_reclaim_state(current, NULL); return nr_reclaimed;
@@ -8072,7 +8073,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in fs_reclaim_release(sc.gfp_mask); psi_memstall_leave(&pflags); - trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); + trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed, 0); return sc.nr_reclaimed >= nr_pages; }
--
2.33.8