mm/lruvec: trace LRU add drains and drain-all requests
Subsystems (2)
PATCH v4 1/1 mm/lruvec: trace LRU add drains and drain-all requests
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_add_drain_all to capture callers of __lru_add_drain_all and whether they set the force flag for all CPUs. The tracepoint resembles the signature of the enclosing function, but is needed because of potential inlining.
---
v4:
- renamed nr_folio_add to nr_folios in lru_add_drain()
- renamed nr to nr_folios in tracepoint for consistency
v3: https://lore.kernel.org/linux-mm/[email protected]/
- restored and renamed tracepoint in __lru_add_drain_all
v2: https://lore.kernel.org/linux-mm/[email protected]/
- removed mm_lru_drain_all tracepoint
v1: https://lore.kernel.org/linux-mm/[email protected]/
include/trace/events/pagemap.h | 37 ++++++++++++++++++++++++++++++++++ mm/swap.c | 7 ++++++- 2 files changed, 43 insertions(+), 1 deletion(-)
include/trace/events/pagemap.h +37 -0
@@ -77,6 +77,43 @@ 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_folios), + +TP_ARGS (cpu, nr_folios), + +TP_STRUCT__entry ( + __field(int, cpu ) + __field(unsigned int, nr_folios ) + ), + +TP_fast_assign ( + __entry->cpu = cpu; + __entry->nr_folios = nr_folios; + ), + +TP_printk ("cpu=%d nr_folios=%u" , __entry->cpu, __entry->nr_folios) +); + +TRACE_EVENT (mm_lru_add_drain_all, + + TP_PROTO(bool force_all_cpus), + +TP_ARGS (force_all_cpus), + +TP_STRUCT__entry ( +__field (bool, force_all_cpus ) + ), + +TP_fast_assign ( + __entry->force_all_cpus = force_all_cpus; + ), + +TP_printk ("force_all_cpus=%s" , + __entry->force_all_cpus ?"true" :"false" ) +); +#endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */
mm/swap.c +6 -1
@@ -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 =folio_batch_count (fbatch); -if (folio_batch_count (fbatch)) +if (nr_folios) {folio_batch_move_lru (fbatch, lru_add); +trace_mm_lru_add_drain (cpu, nr_folios); + } fbatch = &fbatches->lru_move_tail;/* Disabling interrupts below acts as a compiler barrier. */
@@ -869,6 +872,8 @@ static inline void __lru_add_drain_all(bool force_all_cpus)if (WARN_ON (!mm_percpu_wq))return ; +trace_mm_lru_add_drain_all (force_all_cpus); +/* * Guarantee folio_batch counter stores visible by this CPU * are visible to other CPUs before loading the current drain
Signature · 1 line
2.54.0
Quoted 8 lines · 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_drainto report the CPU andlru_addbatch count when anlru_addbatch is drained. This allows tracing to distinguish full drains from partial drains and attribute them to the calling stack.
Quoted 8 lines
Add
mm_lru_add_drain_allto capture callers of__lru_add_drain_alland whether they set the force flag for all CPUs. The tracepoint resembles the signature of the enclosing function, but is needed because of potential inlining.Signed-off-by JP Kobryn <[email protected]>Reviewed-by Barry Song <[email protected]>Acked-by Shakeel Butt <[email protected]>
Quoted 92 lines
---
v4:
- renamednr_folio_addtonr_foliosinlru_add_drain()
- renamed nr tonr_foliosin tracepoint for consistencyv3: https://lore.kernel.org/linux-mm/[email protected]/
- restored and renamed tracepoint in__lru_add_drain_allv2: https://lore.kernel.org/linux-mm/[email protected]/
- removedmm_lru_drain_alltracepointv1: https://lore.kernel.org/linux-mm/[email protected]/
include/trace/events/pagemap.h | 37 ++++++++++++++++++++++++++++++++++ mm/swap.c | 7 ++++++- 2 files changed, 43 insertions(+), 1 deletion(-)include/trace/events/pagemap.h +37
-0@@ -77,6 +77,43 @@ 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_folios), + +TP_ARGS (cpu, nr_folios), + +TP_STRUCT__entry ( + __field(int, cpu ) + __field(unsigned int, nr_folios ) + ), + +TP_fast_assign ( + __entry->cpu = cpu; + __entry->nr_folios = nr_folios; + ), + +TP_printk ("cpu=%d nr_folios=%u" , __entry->cpu, __entry->nr_folios) +); + +TRACE_EVENT (mm_lru_add_drain_all, + + TP_PROTO(bool force_all_cpus), + +TP_ARGS (force_all_cpus), + +TP_STRUCT__entry ( +__field (bool, force_all_cpus ) + ), + +TP_fast_assign ( + __entry->force_all_cpus = force_all_cpus; + ), + +TP_printk ("force_all_cpus=%s" , + __entry->force_all_cpus ?"true" :"false" ) +); +#endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ mm/swap.c +6
-1@@ -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 =folio_batch_count (fbatch); -if (folio_batch_count (fbatch)) +if (nr_folios) {folio_batch_move_lru (fbatch, lru_add); +trace_mm_lru_add_drain (cpu, nr_folios); + } fbatch = &fbatches->lru_move_tail;/* Disabling interrupts below acts as a compiler barrier. */ @@ -869,6 +872,8 @@ static inline void __lru_add_drain_all(bool force_all_cpus)if (WARN_ON (!mm_percpu_wq))return ; +trace_mm_lru_add_drain_all (force_all_cpus); +/* * Guarantee folio_batch counter stores visible by this CPU * are visible to other CPUs before loading the current drain