Re: [PATCH v3] mm: compaction: update the cc->nr_migratepages when allocating or freeing the freepages

[Vlastimil Babka]

On 2/20/24 07:16, Baolin Wang wrote:
> Currently we will use 'cc->nr_freepages >= cc->nr_migratepages' comparison
> to ensure that enough freepages are isolated in isolate_freepages(), however
> it just decreases the cc->nr_freepages without updating cc->nr_migratepages
> in compaction_alloc(), which will waste more CPU cycles and cause too many
> freepages to be isolated.
> 
> So we should also update the cc->nr_migratepages when allocating or freeing
> the freepages to avoid isolating excess freepages. And I can see fewer free
> pages are scanned and isolated when running thpcompact on my Arm64 server:
>                                        k6.7         k6.7_patched
> Ops Compaction pages isolated      120692036.00   118160797.00
> Ops Compaction migrate scanned     131210329.00   154093268.00
> Ops Compaction free scanned       1090587971.00  1080632536.00
> Ops Compact scan efficiency               12.03          14.26
> 
> Moreover, I did not see an obvious latency improvements, this is likely because
> isolating freepages is not the bottleneck in the thpcompact test case.
>                               k6.7                  k6.7_patched
> Amean     fault-both-1      1089.76 (   0.00%)     1080.16 *   0.88%*
> Amean     fault-both-3      1616.48 (   0.00%)     1636.65 *  -1.25%*
> Amean     fault-both-5      2266.66 (   0.00%)     2219.20 *   2.09%*
> Amean     fault-both-7      2909.84 (   0.00%)     2801.90 *   3.71%*
> Amean     fault-both-12     4861.26 (   0.00%)     4733.25 *   2.63%*
> Amean     fault-both-18     7351.11 (   0.00%)     6950.51 *   5.45%*
> Amean     fault-both-24     9059.30 (   0.00%)     9159.99 *  -1.11%*
> Amean     fault-both-30    10685.68 (   0.00%)    11399.02 *  -6.68%*
> 
> Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> Acked-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>

Reviewed-by: Vlastimil Babka <vbabka@xxxxxxx>

Thanks.

> ---
> Hi Andrew, please use this patch to replace below 2 old patches. Thanks.
> https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git/commit/?h=mm-everything-2024-02-20-04-19&id=cb30899d456d64fb83ee3e3d95cd9fbb18735d87
> https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git/commit/?h=mm-everything-2024-02-20-04-19&id=65713d1c4fc498d35dc1f7c1234ef815aa128429
> 
> Changes from v2:
>  - Add acked tag from Mel.
>  - Fix the mm_compaction_migratepages trace event.
> Changes from v1:
>  - Rebased on the latest mm-unstable branch.
> ---
>  include/trace/events/compaction.h |  6 +++---
>  mm/compaction.c                   | 12 ++++++++++--
>  2 files changed, 13 insertions(+), 5 deletions(-)
> 
> diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
> index 2b2a975efd20..d05759d18538 100644
> --- a/include/trace/events/compaction.h
> +++ b/include/trace/events/compaction.h
> @@ -78,10 +78,10 @@ DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_fast_isolate_freepage
>  #ifdef CONFIG_COMPACTION
>  TRACE_EVENT(mm_compaction_migratepages,
>  
> -	TP_PROTO(struct compact_control *cc,
> +	TP_PROTO(unsigned int nr_migratepages,
>  		unsigned int nr_succeeded),
>  
> -	TP_ARGS(cc, nr_succeeded),
> +	TP_ARGS(nr_migratepages, nr_succeeded),
>  
>  	TP_STRUCT__entry(
>  		__field(unsigned long, nr_migrated)
> @@ -90,7 +90,7 @@ TRACE_EVENT(mm_compaction_migratepages,
>  
>  	TP_fast_assign(
>  		__entry->nr_migrated = nr_succeeded;
> -		__entry->nr_failed = cc->nr_migratepages - nr_succeeded;
> +		__entry->nr_failed = nr_migratepages - nr_succeeded;
>  	),
>  
>  	TP_printk("nr_migrated=%lu nr_failed=%lu",
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 4494b2914386..218089b29f13 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -1798,6 +1798,7 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
>  	dst = list_entry(cc->freepages.next, struct folio, lru);
>  	list_del(&dst->lru);
>  	cc->nr_freepages--;
> +	cc->nr_migratepages--;
>  
>  	return dst;
>  }
> @@ -1813,6 +1814,7 @@ static void compaction_free(struct folio *dst, unsigned long data)
>  
>  	list_add(&dst->lru, &cc->freepages);
>  	cc->nr_freepages++;
> +	cc->nr_migratepages++;
>  }
>  
>  /* possible outcome of isolate_migratepages */
> @@ -2435,7 +2437,7 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
>  	unsigned long last_migrated_pfn;
>  	const bool sync = cc->mode != MIGRATE_ASYNC;
>  	bool update_cached;
> -	unsigned int nr_succeeded = 0;
> +	unsigned int nr_succeeded = 0, nr_migratepages;
>  
>  	/*
>  	 * These counters track activities during zone compaction.  Initialize
> @@ -2553,11 +2555,17 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
>  				pageblock_start_pfn(cc->migrate_pfn - 1));
>  		}
>  
> +		/*
> +		 * Record the number of pages to migrate since the
> +		 * compaction_alloc/free() will update cc->nr_migratepages
> +		 * properly.
> +		 */
> +		nr_migratepages = cc->nr_migratepages;
>  		err = migrate_pages(&cc->migratepages, compaction_alloc,
>  				compaction_free, (unsigned long)cc, cc->mode,
>  				MR_COMPACTION, &nr_succeeded);
>  
> -		trace_mm_compaction_migratepages(cc, nr_succeeded);
> +		trace_mm_compaction_migratepages(nr_migratepages, nr_succeeded);
>  
>  		/* All pages were either migrated or will be released */
>  		cc->nr_migratepages = 0;