From: Vlastimil Babka <vbabka@suse.cz> To: Michal Hocko <mhocko@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org>, Arkadiusz Miskiewicz <a.miskiewicz@gmail.com>, Ralf-Peter Rohbeck <Ralf-Peter.Rohbeck@quantum.com>, Olaf Hering <olaf@aepfle.de>, linux-kernel@vger.kernel.org, Linus Torvalds <torvalds@linux-foundation.org>, linux-mm@kvack.org, Mel Gorman <mgorman@techsingularity.net>, Joonsoo Kim <iamjoonsoo.kim@lge.com>, David Rientjes <rientjes@google.com>, Rik van Riel <riel@redhat.com> Subject: Re: [PATCH 2/4] mm, compaction: more reliably increase direct compaction priority Date: Thu, 22 Sep 2016 14:51:48 +0200 [thread overview] Message-ID: <f1670976-b4da-5d2c-0a85-37f9a87d6868@suse.cz> (raw) In-Reply-To: <20160921171348.GF24210@dhcp22.suse.cz> On 09/21/2016 07:13 PM, Michal Hocko wrote: > On Tue 06-09-16 15:52:56, Vlastimil Babka wrote: > [...] >> @@ -3204,6 +3199,15 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, >> if (compaction_retries <= max_retries) >> return true; >> >> + /* >> + * Make sure there is at least one attempt at the highest priority >> + * if we exhausted all retries at the lower priorities >> + */ >> +check_priority: >> + if (*compact_priority > MIN_COMPACT_PRIORITY) { >> + (*compact_priority)--; >> + return true; > > Don't we want to reset compaction_retries here? Otherwise we can consume > all retries on the lower priorities. Good point, patch-fix below. > Other than that it looks good to me. With that you can add > Acked-by: Michal Hocko <mhocko@suse.com> Thanks! >> + } >> return false; >> } >> #else > ----8<---- >From 465e1bd61b7a6d6901a44f09b1a76514dbc220fa Mon Sep 17 00:00:00 2001 From: Vlastimil Babka <vbabka@suse.cz> Date: Thu, 22 Sep 2016 13:54:32 +0200 Subject: [PATCH] mm, compaction: more reliably increase direct compaction priority-fix When increasing the compaction priority, also reset retries. Otherwise we can consume all retries on the lower priorities. Suggested-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Vlastimil Babka <vbabka@suse.cz> --- mm/page_alloc.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f8bed910e3cf..82fdb690ac62 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3162,7 +3162,7 @@ static inline bool should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, enum compact_result compact_result, enum compact_priority *compact_priority, - int compaction_retries) + int *compaction_retries) { int max_retries = MAX_COMPACT_RETRIES; @@ -3196,16 +3196,17 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, */ if (order > PAGE_ALLOC_COSTLY_ORDER) max_retries /= 4; - if (compaction_retries <= max_retries) + if (*compaction_retries <= max_retries) return true; /* - * Make sure there is at least one attempt at the highest priority - * if we exhausted all retries at the lower priorities + * Make sure there are attempts at the highest priority if we exhausted + * all retries or failed at the lower priorities. */ check_priority: if (*compact_priority > MIN_COMPACT_PRIORITY) { (*compact_priority)--; + *compaction_retries = 0; return true; } return false; @@ -3224,7 +3225,7 @@ static inline bool should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags, enum compact_result compact_result, enum compact_priority *compact_priority, - int compaction_retries) + int *compaction_retries) { struct zone *zone; struct zoneref *z; @@ -3663,7 +3664,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, if (did_some_progress > 0 && should_compact_retry(ac, order, alloc_flags, compact_result, &compact_priority, - compaction_retries)) + &compaction_retries)) goto retry; /* Reclaim has failed us, start killing things */ -- 2.10.0
WARNING: multiple messages have this Message-ID (diff)
From: Vlastimil Babka <vbabka@suse.cz> To: Michal Hocko <mhocko@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org>, Arkadiusz Miskiewicz <a.miskiewicz@gmail.com>, Ralf-Peter Rohbeck <Ralf-Peter.Rohbeck@quantum.com>, Olaf Hering <olaf@aepfle.de>, linux-kernel@vger.kernel.org, Linus Torvalds <torvalds@linux-foundation.org>, linux-mm@kvack.org, Mel Gorman <mgorman@techsingularity.net>, Joonsoo Kim <iamjoonsoo.kim@lge.com>, David Rientjes <rientjes@google.com>, Rik van Riel <riel@redhat.com> Subject: Re: [PATCH 2/4] mm, compaction: more reliably increase direct compaction priority Date: Thu, 22 Sep 2016 14:51:48 +0200 [thread overview] Message-ID: <f1670976-b4da-5d2c-0a85-37f9a87d6868@suse.cz> (raw) In-Reply-To: <20160921171348.GF24210@dhcp22.suse.cz> On 09/21/2016 07:13 PM, Michal Hocko wrote: > On Tue 06-09-16 15:52:56, Vlastimil Babka wrote: > [...] >> @@ -3204,6 +3199,15 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, >> if (compaction_retries <= max_retries) >> return true; >> >> + /* >> + * Make sure there is at least one attempt at the highest priority >> + * if we exhausted all retries at the lower priorities >> + */ >> +check_priority: >> + if (*compact_priority > MIN_COMPACT_PRIORITY) { >> + (*compact_priority)--; >> + return true; > > Don't we want to reset compaction_retries here? Otherwise we can consume > all retries on the lower priorities. Good point, patch-fix below. > Other than that it looks good to me. With that you can add > Acked-by: Michal Hocko <mhocko@suse.com> Thanks! >> + } >> return false; >> } >> #else > ----8<----
next prev parent reply other threads:[~2016-09-22 12:51 UTC|newest] Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-09-06 13:52 [PATCH 0/4] reintroduce compaction feedback for OOM decisions Vlastimil Babka 2016-09-06 13:52 ` Vlastimil Babka 2016-09-06 13:52 ` [PATCH 1/4] Revert "mm, oom: prevent premature OOM killer invocation for high order request" Vlastimil Babka 2016-09-06 13:52 ` Vlastimil Babka 2016-09-21 17:04 ` Michal Hocko 2016-09-21 17:04 ` Michal Hocko 2016-09-06 13:52 ` [PATCH 2/4] mm, compaction: more reliably increase direct compaction priority Vlastimil Babka 2016-09-06 13:52 ` Vlastimil Babka 2016-09-21 17:13 ` Michal Hocko 2016-09-21 17:13 ` Michal Hocko 2016-09-22 12:51 ` Vlastimil Babka [this message] 2016-09-22 12:51 ` Vlastimil Babka 2016-09-22 14:08 ` Michal Hocko 2016-09-22 14:08 ` Michal Hocko 2016-09-22 14:52 ` Michal Hocko 2016-09-22 14:52 ` Michal Hocko 2016-09-22 14:59 ` Vlastimil Babka 2016-09-22 14:59 ` Vlastimil Babka 2016-09-22 15:06 ` Vlastimil Babka 2016-09-22 15:06 ` Vlastimil Babka 2016-09-23 4:04 ` Hillf Danton 2016-09-23 4:04 ` Hillf Danton 2016-09-23 6:55 ` Vlastimil Babka 2016-09-23 6:55 ` Vlastimil Babka 2016-09-23 8:23 ` Michal Hocko 2016-09-23 8:23 ` Michal Hocko 2016-09-23 10:47 ` Vlastimil Babka 2016-09-23 10:47 ` Vlastimil Babka 2016-09-23 12:06 ` Michal Hocko 2016-09-23 12:06 ` Michal Hocko 2016-09-06 13:52 ` [PATCH 3/4] mm, compaction: restrict full priority to non-costly orders Vlastimil Babka 2016-09-06 13:52 ` Vlastimil Babka 2016-09-21 17:15 ` Michal Hocko 2016-09-21 17:15 ` Michal Hocko 2016-09-06 13:52 ` [PATCH 4/4] mm, compaction: make full priority ignore pageblock suitability Vlastimil Babka 2016-09-06 13:52 ` Vlastimil Babka 2016-09-15 18:51 ` [PATCH 0/4] reintroduce compaction feedback for OOM decisions Arkadiusz Miskiewicz 2016-09-15 18:51 ` Arkadiusz Miskiewicz 2016-09-21 17:18 ` Michal Hocko 2016-09-21 17:18 ` Michal Hocko 2016-09-22 15:18 ` Vlastimil Babka 2016-09-22 15:18 ` Vlastimil Babka 2016-09-23 8:26 ` Michal Hocko 2016-09-23 8:26 ` Michal Hocko 2016-09-23 10:55 ` Vlastimil Babka 2016-09-23 10:55 ` Vlastimil Babka 2016-09-23 12:09 ` Michal Hocko 2016-09-23 12:09 ` Michal Hocko
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=f1670976-b4da-5d2c-0a85-37f9a87d6868@suse.cz \ --to=vbabka@suse.cz \ --cc=Ralf-Peter.Rohbeck@quantum.com \ --cc=a.miskiewicz@gmail.com \ --cc=akpm@linux-foundation.org \ --cc=iamjoonsoo.kim@lge.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=mgorman@techsingularity.net \ --cc=mhocko@kernel.org \ --cc=olaf@aepfle.de \ --cc=riel@redhat.com \ --cc=rientjes@google.com \ --cc=torvalds@linux-foundation.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.