[PATCH] mm/lruvec: trace LRU add drains and drain-all queuing

[PATCH] mm/lruvec: trace LRU add drains and drain-all queuing

[JP Kobryn]

LRU add batches can be drained before they reach capacity. This can be a
source of LRU lock contention, but it is not currently possible to
attribute these drains to callers with existing tracepoints.

Add mm_lru_add_drain to report the CPU and lru_add batch count when an
lru_add batch is drained. This allows tracing to distinguish full drains
from partial drains and attribute them to the calling stack.

Add mm_lru_drain_all_queue to report when lru_add_drain_all() queues
per-CPU drain work. This captures the requester stack and target CPU for
remote drain work. The event is named as a drain-all queue event because
the queued work can be needed for batches other than lru_add.

Signed-off-by: JP Kobryn <jp.kobryn@linux.dev>
---
 include/trace/events/pagemap.h | 40 ++++++++++++++++++++++++++++++++++
 mm/swap.c                      |  6 ++++-
 2 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h
index 171524d3526d..ea8fc46bedb0 100644
--- a/include/trace/events/pagemap.h
+++ b/include/trace/events/pagemap.h
@@ -77,6 +77,46 @@ TRACE_EVENT(mm_lru_activate,
 	TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn)
 );
 
+TRACE_EVENT(mm_lru_add_drain,
+
+	TP_PROTO(int cpu, unsigned int nr),
+
+	TP_ARGS(cpu, nr),
+
+	TP_STRUCT__entry(
+		__field(int,		cpu	)
+		__field(unsigned int,	nr	)
+	),
+
+	TP_fast_assign(
+		__entry->cpu	= cpu;
+		__entry->nr	= nr;
+	),
+
+	TP_printk("cpu=%d nr=%u", __entry->cpu, __entry->nr)
+);
+
+TRACE_EVENT(mm_lru_drain_all_queue,
+
+	TP_PROTO(int target_cpu, bool force_all_cpus),
+
+	TP_ARGS(target_cpu, force_all_cpus),
+
+	TP_STRUCT__entry(
+		__field(int,	target_cpu	)
+		__field(bool,	force_all_cpus	)
+	),
+
+	TP_fast_assign(
+		__entry->target_cpu	= target_cpu;
+		__entry->force_all_cpus	= force_all_cpus;
+	),
+
+	TP_printk("target_cpu=%d force_all_cpus=%s",
+		__entry->target_cpu,
+		__entry->force_all_cpus ? "true" : "false")
+);
+
 #endif /* _TRACE_PAGEMAP_H */
 
 /* This part must be outside protection */
diff --git a/mm/swap.c b/mm/swap.c
index 588f50d8f1a8..c385b93582eb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -694,9 +694,12 @@ void lru_add_drain_cpu(int cpu)
 {
 	struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu);
 	struct folio_batch *fbatch = &fbatches->lru_add;
+	unsigned int nr_folios_add = folio_batch_count(fbatch);
 
-	if (folio_batch_count(fbatch))
+	if (nr_folios_add) {
 		folio_batch_move_lru(fbatch, lru_add);
+		trace_mm_lru_add_drain(cpu, nr_folios_add);
+	}
 
 	fbatch = &fbatches->lru_move_tail;
 	/* Disabling interrupts below acts as a compiler barrier. */
@@ -928,6 +931,7 @@ static inline void __lru_add_drain_all(bool force_all_cpus)
 		if (cpu_needs_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			queue_work_on(cpu, mm_percpu_wq, work);
+			trace_mm_lru_drain_all_queue(cpu, force_all_cpus);
 			__cpumask_set_cpu(cpu, &has_work);
 		}
 	}
-- 
2.54.0

Re: [PATCH] mm/lruvec: trace LRU add drains and drain-all queuing

[Barry Song]

On Tue, Jun 9, 2026 at 12:12 PM JP Kobryn <jp.kobryn@linux.dev> wrote:
>
> LRU add batches can be drained before they reach capacity. This can be a
> source of LRU lock contention, but it is not currently possible to
> attribute these drains to callers with existing tracepoints.
>
> Add mm_lru_add_drain to report the CPU and lru_add batch count when an
> lru_add batch is drained. This allows tracing to distinguish full drains
> from partial drains and attribute them to the calling stack.
>
> Add mm_lru_drain_all_queue to report when lru_add_drain_all() queues
> per-CPU drain work. This captures the requester stack and target CPU for
> remote drain work. The event is named as a drain-all queue event because
> the queued work can be needed for batches other than lru_add.
>
> Signed-off-by: JP Kobryn <jp.kobryn@linux.dev>
> ---
>  include/trace/events/pagemap.h | 40 ++++++++++++++++++++++++++++++++++
>  mm/swap.c                      |  6 ++++-
>  2 files changed, 45 insertions(+), 1 deletion(-)
>
> diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h
> index 171524d3526d..ea8fc46bedb0 100644
> --- a/include/trace/events/pagemap.h
> +++ b/include/trace/events/pagemap.h
> @@ -77,6 +77,46 @@ TRACE_EVENT(mm_lru_activate,
>         TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn)
>  );
>
> +TRACE_EVENT(mm_lru_add_drain,
> +
> +       TP_PROTO(int cpu, unsigned int nr),
> +
> +       TP_ARGS(cpu, nr),
> +
> +       TP_STRUCT__entry(
> +               __field(int,            cpu     )
> +               __field(unsigned int,   nr      )
> +       ),
> +
> +       TP_fast_assign(
> +               __entry->cpu    = cpu;
> +               __entry->nr     = nr;
> +       ),
> +
> +       TP_printk("cpu=%d nr=%u", __entry->cpu, __entry->nr)
> +);
> +
> +TRACE_EVENT(mm_lru_drain_all_queue,
> +
> +       TP_PROTO(int target_cpu, bool force_all_cpus),
> +
> +       TP_ARGS(target_cpu, force_all_cpus),
> +
> +       TP_STRUCT__entry(
> +               __field(int,    target_cpu      )
> +               __field(bool,   force_all_cpus  )
> +       ),
> +
> +       TP_fast_assign(
> +               __entry->target_cpu     = target_cpu;
> +               __entry->force_all_cpus = force_all_cpus;
> +       ),
> +
> +       TP_printk("target_cpu=%d force_all_cpus=%s",
> +               __entry->target_cpu,
> +               __entry->force_all_cpus ? "true" : "false")
> +);
> +
>  #endif /* _TRACE_PAGEMAP_H */
>
>  /* This part must be outside protection */
> diff --git a/mm/swap.c b/mm/swap.c
> index 588f50d8f1a8..c385b93582eb 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -694,9 +694,12 @@ void lru_add_drain_cpu(int cpu)
>  {
>         struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu);
>         struct folio_batch *fbatch = &fbatches->lru_add;
> +       unsigned int nr_folios_add = folio_batch_count(fbatch);
>
> -       if (folio_batch_count(fbatch))
> +       if (nr_folios_add) {
>                 folio_batch_move_lru(fbatch, lru_add);
> +               trace_mm_lru_add_drain(cpu, nr_folios_add);
> +       }
>
>         fbatch = &fbatches->lru_move_tail;
>         /* Disabling interrupts below acts as a compiler barrier. */
> @@ -928,6 +931,7 @@ static inline void __lru_add_drain_all(bool force_all_cpus)
>                 if (cpu_needs_drain(cpu)) {
>                         INIT_WORK(work, lru_add_drain_per_cpu);
>                         queue_work_on(cpu, mm_percpu_wq, work);
> +                       trace_mm_lru_drain_all_queue(cpu, force_all_cpus);

Do you need tracing on each CPU individually, or is tracing the
entire __lru_add_drain_all() invocation sufficient?

Do you also need this_gen and lru_drain_gen to be traced?

By the way, I'm not sure drain_all_queue is the best name here.
Why not simply use add_drain_all()? It would match the existing
function name better.

Best Regards
Barry