Re: [PATCH 2/3] mm/mglru: add tracepoint for scan_folios()

[Steven Rostedt]

On Fri, 11 Sep 2026 15:28:47 +0800
Ridong Chen <ridong.chen@xxxxxxxxx> wrote:

> diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
> index 8a872990b4be..c39dfacef033 100644
> --- a/include/trace/events/vmscan.h
> +++ b/include/trace/events/vmscan.h
> @@ -392,6 +392,69 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
>  		__print_symbolic(__entry->lru, LRU_NAMES))
>  );
>  
> +TRACE_EVENT(mm_mglru_scan_folios,
> +
> +	TP_PROTO(u64 memcg_id,
> +		int highest_zoneidx,
> +		int order,
> +		unsigned long nr_requested,
> +		unsigned long nr_scanned,
> +		unsigned long nr_sorted,
> +		unsigned long nr_skipped,
> +		unsigned long nr_taken,
> +		int lru,
> +		unsigned long max_seq,
> +		int tier,
> +		unsigned long min_seq),
> +
> +	TP_ARGS(memcg_id, highest_zoneidx, order, nr_requested, nr_scanned,
> +		nr_sorted, nr_skipped, nr_taken, lru, max_seq, tier, min_seq),
> +
> +	TP_STRUCT__entry(
> +		__field(u64, memcg_id)
> +		__field(int, highest_zoneidx)
> +		__field(int, order)
> +		__field(unsigned long, nr_requested)
> +		__field(unsigned long, nr_scanned)
> +		__field(unsigned long, nr_sorted)
> +		__field(unsigned long, nr_skipped)
> +		__field(unsigned long, nr_taken)
> +		__field(int, lru)
> +		__field(unsigned long, max_seq)
> +		__field(int, tier)
> +		__field(unsigned long, min_seq)

Please keep "int"s together. This creates a structure that is used to write
into the ring buffer. On 64bit machines, the above would add 4 bytes of
padding after each int, whereas:

		__field(unsigned long, max_seq)
		__field(unsigned long, min_seq)
		__field(int, lru)
		__field(int, tier)


would not.

> +	),
> +
> +	TP_fast_assign(
> +		__entry->memcg_id = memcg_id;
> +		__entry->highest_zoneidx = highest_zoneidx;
> +		__entry->order = order;
> +		__entry->nr_requested = nr_requested;
> +		__entry->nr_scanned = nr_scanned;
> +		__entry->nr_sorted = nr_sorted;
> +		__entry->nr_skipped = nr_skipped;
> +		__entry->nr_taken = nr_taken;
> +		__entry->lru = lru;
> +		__entry->max_seq = max_seq;
> +		__entry->tier = tier;
> +		__entry->min_seq = min_seq;
> +	),
> +
> +	TP_printk("memcg_id=%llu classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_sorted=%lu nr_skipped=%lu nr_taken=%lu lru=%s max_seq=%lu tier=%d min_seq=%lu",
> +		__entry->memcg_id,
> +		__entry->highest_zoneidx,
> +		__entry->order,
> +		__entry->nr_requested,
> +		__entry->nr_scanned,
> +		__entry->nr_sorted,
> +		__entry->nr_skipped,
> +		__entry->nr_taken,
> +		__print_symbolic(__entry->lru, LRU_NAMES),
> +		__entry->max_seq,
> +		__entry->tier,
> +		__entry->min_seq)
> +);
> +
>  TRACE_EVENT(mm_vmscan_write_folio,
>  
>  	TP_PROTO(struct folio *folio),
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 2554a6513aa8..bd1b9ecf2e84 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -4876,6 +4876,12 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
>  	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
>  				scanned, skipped, isolated,
>  				type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
> +	trace_mm_mglru_scan_folios(mem_cgroup_id(lruvec_memcg(lruvec)),
> +				   sc->reclaim_idx, sc->order, nr_to_scan,
> +				   scanned, sorted, skipped, isolated,
> +				   type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON,
> +				   lrugen->max_seq, tier,
> +				   lrugen->min_seq[type]);

Can't this information be processed in the tracepoint? That is:

	TP_PROTO(struct lruvec *lruvec,
		 struct scan_control *sc,
		 struct lru_gen_folio *lrugen,
		 unsigned long nr_requested,
		 unsigned long nr_scanned,
		 unsigned long nr_sorted,
		 unsigned long nr_skipped,
		 unsigned long nr_taken,
		 int type),

	TP_ARGS(lruvec, sc, lrugen, nr_requested, nr_scanned,
		nr_sorted, nr_skipped, nr_taken, type),

	TP_STRUCT__entry(
		__field(u64, memcg_id)
		__field(int, highest_zoneidx)
		__field(int, order)
		__field(unsigned long, nr_requested)
		__field(unsigned long, nr_scanned)
		__field(unsigned long, nr_sorted)
		__field(unsigned long, nr_skipped)
		__field(unsigned long, nr_taken)
		__field(unsigned long, max_seq)
		__field(unsigned long, min_seq)
		__field(int, lru)
		__field(int, tier)
	),

	TP_fast_assign(
		__entry->memcg_id = mem_cgroup_id(lruvec_memcg(lruvec));
		__entry->highest_zoneidx = sc->reclaim_idx;
		__entry->order = sc->order;
		__entry->nr_requested = nr_requested;
		__entry->nr_scanned = nr_scanned;
		__entry->nr_sorted = nr_sorted;
		__entry->nr_skipped = nr_skipped;
		__entry->nr_taken = nr_taken;
		__entry->lru = type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON;
		__entry->max_seq = lrugen->max_seq;
		__entry->tier = tier;
		__entry->min_seq = lrugen->min_seq;
	),


This moves the code to generate the parameters into the TP_fast_assign()
which is in a separate text section. It remove code from the work flow
improving instruction cache.

Same can be done for that trace_mm_vmscan_lru_isolate() trace event.

-- Steve

>  
>  	*isolatedp = isolated;
>  	return scanned;
> --