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 <[email protected]>
---
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
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a
member of the Code Aurora Forum, hosted by The Linux Foundation
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 <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
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
>
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 <[email protected]>
Acked-by: David Rientjes <[email protected]>