Re: [PATCH -next v3 2/2] mm: vmscan: add new event to trace shrink lru

[Huan Yang]

在 2023/12/14 9:34, Bixuan Cui 写道:
> [Some people who received this message don't often get email from cuibixuan@xxxxxxxx. Learn why this is important at https://aka.ms/LearnAboutSenderIdentification ]
>
> From: cuibixuan <cuibixuan@xxxxxxxx>
>
> Add a new event to calculate the shrink_inactive_list()/shrink_active_list()
> execution time.
>
> Example of output:
>           kswapd0-103     [007] .....  1098.353020: mm_vmscan_lru_shrink_active_start: nid=0
>           kswapd0-103     [007] .....  1098.353040: mm_vmscan_lru_shrink_active_end: nid=0 nr_taken=32 nr_active=0 nr_deactivated=32 nr_referenced=0 priority=6 flags=RECLAIM_WB_FILE|RECLAIM_WB_ASYNC
>           kswapd0-103     [007] .....  1098.353040: mm_vmscan_lru_shrink_inactive_start: nid=0
>           kswapd0-103     [007] .....  1098.353094: mm_vmscan_lru_shrink_inactive_end: nid=0 nr_scanned=32 nr_reclaimed=0 nr_dirty=0 nr_writeback=0 nr_congested=0 nr_immediate=0 nr_activate_anon=0 nr_activate_file=0 nr_ref_keep=32 nr_unmap_fail=0 priority=6 flags=RECLAIM_WB_ANON|RECLAIM_WB_ASYNC
>           kswapd0-103     [007] .....  1098.353094: mm_vmscan_lru_shrink_inactive_start: nid=0
>           kswapd0-103     [007] .....  1098.353162: mm_vmscan_lru_shrink_inactive_end: nid=0 nr_scanned=32 nr_reclaimed=21 nr_dirty=0 nr_writeback=0 nr_congested=0 nr_immediate=0 nr_activate_anon=0 nr_activate_file=0 nr_ref_keep=11 nr_unmap_fail=0 priority=6 flags=RECLAIM_WB_FILE|RECLAIM_WB_ASYNC
>
> Signed-off-by: Bixuan Cui <cuibixuan@xxxxxxxx>
> ---
>   include/trace/events/vmscan.h | 38 +++++++++++++++++++++++++++++++++--
>   mm/vmscan.c                   | 11 +++++++---
>   2 files changed, 44 insertions(+), 5 deletions(-)
>
> diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
> index b99cd28c9815..02868bdc5999 100644
> --- a/include/trace/events/vmscan.h
> +++ b/include/trace/events/vmscan.h
> @@ -395,7 +395,24 @@ TRACE_EVENT(mm_vmscan_write_folio,
>                  show_reclaim_flags(__entry->reclaim_flags))
>   );
>
> -TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
> +TRACE_EVENT(mm_vmscan_lru_shrink_inactive_start,
> +
> +       TP_PROTO(int nid),
> +
> +       TP_ARGS(nid),
> +
> +       TP_STRUCT__entry(
> +               __field(int, nid)
> +       ),
> +
> +       TP_fast_assign(
> +               __entry->nid = nid;
> +       ),
> +
> +       TP_printk("nid=%d", __entry->nid)
> +);
> +
> +TRACE_EVENT(mm_vmscan_lru_shrink_inactive_end,
>
>          TP_PROTO(int nid,
>                  unsigned long nr_scanned, unsigned long nr_reclaimed,
> @@ -446,7 +463,24 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
>                  show_reclaim_flags(__entry->reclaim_flags))
>   );
>
> -TRACE_EVENT(mm_vmscan_lru_shrink_active,
> +TRACE_EVENT(mm_vmscan_lru_shrink_active_start,
> +
> +       TP_PROTO(int nid),
> +
> +       TP_ARGS(nid),
> +
> +       TP_STRUCT__entry(
> +               __field(int, nid)
> +       ),
> +
> +       TP_fast_assign(
> +               __entry->nid = nid;
> +       ),
> +
> +       TP_printk("nid=%d", __entry->nid)
> +);
> +
> +TRACE_EVENT(mm_vmscan_lru_shrink_active_end,
>
>          TP_PROTO(int nid, unsigned long nr_taken,
>                  unsigned long nr_active, unsigned long nr_deactivated,
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 4e3b835c6b4a..a44d9624d60f 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1906,6 +1906,8 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
>          struct pglist_data *pgdat = lruvec_pgdat(lruvec);
>          bool stalled = false;
>
> +       trace_mm_vmscan_lru_shrink_inactive_start(pgdat->node_id);

Can here add memcg id into shrink trace?

If so, we can attach this trace and collect shrink info into both NODE 
and each MEMCG.

> +
>          while (unlikely(too_many_isolated(pgdat, file, sc))) {
>                  if (stalled)
>                          return 0;
> @@ -1990,7 +1992,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
>          if (file)
>                  sc->nr.file_taken += nr_taken;
>
> -       trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
> +       trace_mm_vmscan_lru_shrink_inactive_end(pgdat->node_id,
>                          nr_scanned, nr_reclaimed, &stat, sc->priority, file);
>          return nr_reclaimed;
>   }
> @@ -2028,6 +2030,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
>          int file = is_file_lru(lru);
>          struct pglist_data *pgdat = lruvec_pgdat(lruvec);
>
> +       trace_mm_vmscan_lru_shrink_active_start(pgdat->node_id);
> +
>          lru_add_drain();
>
>          spin_lock_irq(&lruvec->lru_lock);
> @@ -2107,7 +2111,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
>                  lru_note_cost(lruvec, file, 0, nr_rotated);
>          mem_cgroup_uncharge_list(&l_active);
>          free_unref_page_list(&l_active);
> -       trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
> +       trace_mm_vmscan_lru_shrink_active_end(pgdat->node_id, nr_taken, nr_activate,
>                          nr_deactivate, nr_rotated, sc->priority, file);
>   }
>
> @@ -4524,9 +4528,10 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
>          if (list_empty(&list))
>                  return scanned;
>   retry:
> +       trace_mm_vmscan_lru_shrink_inactive_start(pgdat->node_id);
>          reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false);
>          sc->nr_reclaimed += reclaimed;
> -       trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
> +       trace_mm_vmscan_lru_shrink_inactive_end(pgdat->node_id,
>                          scanned, reclaimed, &stat, sc->priority,
>                          type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
>
> --
> 2.17.1