| Message ID | 1613151184-21213-1-git-send-email-charante@codeaurora.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [V2] mm: compaction: update the COMPACT[STALL|FAIL] events properly | expand |
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 >
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>
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
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(+)