Re: [PATCH v3 1/4] mm/mglru: add MM_WALK_EMPTY stats and tracepoint

[Baoquan He <baoquan.he@linux.dev>]

On 11/13/26 at 04:49pm, Baoquan He wrote:
> From: Baoquan He <hebaoquan@kylinos.cn>
> 
> Add per-walk counters to measure empty aging walks which traverse
> an mm's page tables but find no folio for the current lruvec (node+memcg).
> These are common on multi-NUMA node systems because lru_gen_use_mm() marks
> an mm for all nodes at every context switch.
> 
> New counters (accumulated in mm_state->stats[]):
> 
>   MM_LEAF_ASSOCIATED   - leaf entries whose folio is in this lruvec
>   MM_WALK_TOTAL        - page-table walks completed
>   MM_WALK_EMPTY        - walks that found no folio in this lruvec
>   MM_LEAF_EMPTY_WALKS  - leaf entries scanned during empty walks
> 
> A new tracepoint, mm_vmscan_lru_gen_walk(), fires after each walk, and the
> debugfs lru_gen output ("TYFALWEE") exposes the new counters.
> 
> Reviewed-by: Barry Song <baohua@kernel.org>
> Signed-off-by: Baoquan He <hebaoquan@kylinos.cn>

> Signed-off-by: Baoquan He <baoquan.he@linux.dev>
~~~
Git format-patch automatically added my linux.dev mail address, I should
have noticed this and remove it.

> ---
>  include/linux/mmzone.h |  4 ++++
>  mm/trace_vmscan.h      | 28 ++++++++++++++++++++++++++++
>  mm/vmscan.c            | 32 ++++++++++++++++++++++++++++----
>  3 files changed, 60 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index c161d563ce8f..a49efd9b74ed 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -579,6 +579,10 @@ enum {
>  	MM_LEAF_YOUNG,		/* young leaf entries */
>  	MM_NONLEAF_FOUND,	/* non-leaf entries found in Bloom filters */
>  	MM_NONLEAF_ADDED,	/* non-leaf entries added to Bloom filters */
> +	MM_LEAF_ASSOCIATED,	/* leaf entries whose folio is in this lruvec (node+memcg) */
> +	MM_WALK_TOTAL,		/* page-table walks completed */
> +	MM_WALK_EMPTY,		/* walks that found no folio in this lruvec */
> +	MM_LEAF_EMPTY_WALKS,	/* leaf entries scanned during empty walks */
>  	NR_MM_STATS
>  };
>  
> diff --git a/mm/trace_vmscan.h b/mm/trace_vmscan.h
> index 565c56428364..4884fc7a35b9 100644
> --- a/mm/trace_vmscan.h
> +++ b/mm/trace_vmscan.h
> @@ -763,6 +763,34 @@ TRACE_EVENT(mm_vmscan_kswapd_clear_hopeless,
>  		__entry->nid,
>  		__print_symbolic(__entry->reason, kswapd_clear_hopeless_reason_ops))
>  );
> +TRACE_EVENT(mm_vmscan_lru_gen_walk,
> +
> +	TP_PROTO(int nid, unsigned long seq, int leaf_total,
> +		 int leaf_associated, bool empty),
> +
> +	TP_ARGS(nid, seq, leaf_total, leaf_associated, empty),
> +
> +	TP_STRUCT__entry(
> +		__field(int, nid)
> +		__field(unsigned long, seq)
> +		__field(int, leaf_total)
> +		__field(int, leaf_associated)
> +		__field(bool, empty)
> +	),
> +
> +	TP_fast_assign(
> +		__entry->nid = nid;
> +		__entry->seq = seq;
> +		__entry->leaf_total = leaf_total;
> +		__entry->leaf_associated = leaf_associated;
> +		__entry->empty = empty;
> +	),
> +
> +	TP_printk("nid=%d seq=%lu leaf_total=%d leaf_associated=%d empty=%d",
> +		__entry->nid, __entry->seq, __entry->leaf_total,
> +		__entry->leaf_associated, __entry->empty)
> +);
> +
>  #endif /* _TRACE_VMSCAN_H */
>  
>  /* This part must be outside protection */
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 96201eae0ceb..98037a562ab6 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -3590,6 +3590,8 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
>  		if (!folio)
>  			continue;
>  
> +		walk->mm_stats[MM_LEAF_ASSOCIATED]++;
> +
>  		if (folio_test_large(folio)) {
>  			const unsigned int max_nr = (end - addr) >> PAGE_SHIFT;
>  
> @@ -3688,6 +3690,8 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
>  		if (!folio)
>  			goto next;
>  
> +		walk->mm_stats[MM_LEAF_ASSOCIATED]++;
> +
>  		if (!pmdp_test_and_clear_young_notify(vma, addr, pmd + i))
>  			goto next;
>  
> @@ -4151,8 +4155,28 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
>  
>  	do {
>  		success = iterate_mm_list(walk, &mm);
> -		if (mm)
> +		if (mm) {
> +			bool empty = false;
> +
>  			walk_mm(mm, walk);
> +			/*
> +			 * A walk that traversed page tables but found no folio
> +			 * belonging to this lruvec (node+memcg) is pure waste.
> +			 */
> +			if (walk->mm_stats[MM_LEAF_TOTAL]) {
> +				walk->mm_stats[MM_WALK_TOTAL]++;
> +				if (walk->mm_stats[MM_LEAF_ASSOCIATED] == 0) {
> +					walk->mm_stats[MM_WALK_EMPTY]++;
> +					walk->mm_stats[MM_LEAF_EMPTY_WALKS] +=
> +						walk->mm_stats[MM_LEAF_TOTAL];
> +					empty = true;
> +				}
> +			}
> +			trace_mm_vmscan_lru_gen_walk(
> +					lruvec_pgdat(lruvec)->node_id, walk->seq,
> +					walk->mm_stats[MM_LEAF_TOTAL],
> +					walk->mm_stats[MM_LEAF_ASSOCIATED], empty);
> +		}
>  	} while (mm);
>  done:
>  	if (success) {
> @@ -5638,14 +5662,14 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
>  
>  	seq_puts(m, "                      ");
>  	for (i = 0; i < NR_MM_STATS; i++) {
> -		const char *s = "xxxx";
> +		const char *s = "xxxxxxxx";
>  		unsigned long n = 0;
>  
>  		if (seq == max_seq && NR_HIST_GENS == 1) {
> -			s = "TYFA";
> +			s = "TYFALWEE";
>  			n = READ_ONCE(mm_state->stats[hist][i]);
>  		} else if (seq != max_seq && NR_HIST_GENS > 1) {
> -			s = "tyfa";
> +			s = "tyfalwee";
>  			n = READ_ONCE(mm_state->stats[hist][i]);
>  		}
>  
> -- 
> 2.52.0
>