[V2] mm: compaction: update the COMPACT[STALL|FAIL] events properly
diff mbox series

Message ID 1613151184-21213-1-git-send-email-charante@codeaurora.org
State Accepted
Commit 06dac2f467fe9269a433aa5056dd2ee1d20475e9
Headers show
Series
  • [V2] mm: compaction: update the COMPACT[STALL|FAIL] events properly
Related show

Commit Message

Charan Teja Kalla Feb. 12, 2021, 5:33 p.m. UTC
By definition, COMPACT[STALL|FAIL] events needs to be counted when there
is 'At least in one zone compaction wasn't deferred or skipped from the
direct compaction'. And when compaction is skipped or deferred,
COMPACT_SKIPPED will be returned but it will still go and update these
compaction events which is wrong in the sense that COMPACT[STALL|FAIL]
is counted without even trying the compaction.

Correct this by skipping the counting of these events when
COMPACT_SKIPPED is returned for compaction. This indirectly also avoid
the unnecessary try into the get_page_from_freelist() when compaction is
not even tried.

There is a corner case where compaction is skipped but still count
COMPACTSTALL event, which is that IRQ came and freed the page and the
same is captured in capture_control.

Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>
---

changes in V1: https://lore.kernel.org/patchwork/patch/1373665/

 mm/compaction.c | 8 ++++++++
 mm/page_alloc.c | 2 ++
 2 files changed, 10 insertions(+)

Comments

Vlastimil Babka Feb. 12, 2021, 5:38 p.m. UTC | #1
On 2/12/21 6:33 PM, Charan Teja Reddy wrote:
> By definition, COMPACT[STALL|FAIL] events needs to be counted when there
> is 'At least in one zone compaction wasn't deferred or skipped from the
> direct compaction'. And when compaction is skipped or deferred,
> COMPACT_SKIPPED will be returned but it will still go and update these
> compaction events which is wrong in the sense that COMPACT[STALL|FAIL]
> is counted without even trying the compaction.
> 
> Correct this by skipping the counting of these events when
> COMPACT_SKIPPED is returned for compaction. This indirectly also avoid
> the unnecessary try into the get_page_from_freelist() when compaction is
> not even tried.
> 
> There is a corner case where compaction is skipped but still count
> COMPACTSTALL event, which is that IRQ came and freed the page and the
> same is captured in capture_control.
> 
> Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>

Acked-by: Vlastimil Babka <vbabka@suse.cz>
Thanks!

> ---
> 
> changes in V1: https://lore.kernel.org/patchwork/patch/1373665/
> 
>  mm/compaction.c | 8 ++++++++
>  mm/page_alloc.c | 2 ++
>  2 files changed, 10 insertions(+)
> 
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 190ccda..104ebef 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -2487,6 +2487,14 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
>  	 */
>  	WRITE_ONCE(current->capture_control, NULL);
>  	*capture = READ_ONCE(capc.page);
> +	/*
> +	 * Technically, it is also possible that compaction is skipped but
> +	 * the page is still captured out of luck(IRQ came and freed the page).
> +	 * Returning COMPACT_SUCCESS in such cases helps in properly accounting
> +	 * the COMPACT[STALL|FAIL] when compaction is skipped.
> +	 */
> +	if (*capture)
> +		ret = COMPACT_SUCCESS;
>  
>  	return ret;
>  }
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 519a60d..531f244 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -4152,6 +4152,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
>  	memalloc_noreclaim_restore(noreclaim_flag);
>  	psi_memstall_leave(&pflags);
>  
> +	if (*compact_result == COMPACT_SKIPPED)
> +		return NULL;
>  	/*
>  	 * At least in one zone compaction wasn't deferred or skipped, so let's
>  	 * count a compaction stall
>
David Rientjes Feb. 12, 2021, 9:16 p.m. UTC | #2
On Fri, 12 Feb 2021, Charan Teja Reddy wrote:

> By definition, COMPACT[STALL|FAIL] events needs to be counted when there
> is 'At least in one zone compaction wasn't deferred or skipped from the
> direct compaction'. And when compaction is skipped or deferred,
> COMPACT_SKIPPED will be returned but it will still go and update these
> compaction events which is wrong in the sense that COMPACT[STALL|FAIL]
> is counted without even trying the compaction.
> 
> Correct this by skipping the counting of these events when
> COMPACT_SKIPPED is returned for compaction. This indirectly also avoid
> the unnecessary try into the get_page_from_freelist() when compaction is
> not even tried.
> 
> There is a corner case where compaction is skipped but still count
> COMPACTSTALL event, which is that IRQ came and freed the page and the
> same is captured in capture_control.
> 
> Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>

Acked-by: David Rientjes <rientjes@google.com>

Patch
diff mbox series

diff --git a/mm/compaction.c b/mm/compaction.c
index 190ccda..104ebef 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2487,6 +2487,14 @@  static enum compact_result compact_zone_order(struct zone *zone, int order,
 	 */
 	WRITE_ONCE(current->capture_control, NULL);
 	*capture = READ_ONCE(capc.page);
+	/*
+	 * Technically, it is also possible that compaction is skipped but
+	 * the page is still captured out of luck(IRQ came and freed the page).
+	 * Returning COMPACT_SUCCESS in such cases helps in properly accounting
+	 * the COMPACT[STALL|FAIL] when compaction is skipped.
+	 */
+	if (*capture)
+		ret = COMPACT_SUCCESS;
 
 	return ret;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 519a60d..531f244 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4152,6 +4152,8 @@  __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	memalloc_noreclaim_restore(noreclaim_flag);
 	psi_memstall_leave(&pflags);
 
+	if (*compact_result == COMPACT_SKIPPED)
+		return NULL;
 	/*
 	 * At least in one zone compaction wasn't deferred or skipped, so let's
 	 * count a compaction stall