From: Aaron Tomlin <atomlin@redhat.com>
To: linux-mm@kvack.org
Cc: akpm@linux-foundation.org, linux-kernel@vger.kernel.org
Subject: [PATCH] mm/page_alloc: try oom if reclaim is unable to make forward progress
Date: Mon, 15 Mar 2021 16:58:37 +0000 [thread overview]
Message-ID: <20210315165837.789593-1-atomlin@redhat.com> (raw)
In the situation where direct reclaim is required to make progress for
compaction but no_progress_loops is already over the limit of
MAX_RECLAIM_RETRIES consider invoking the oom killer.
Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
---
mm/page_alloc.c | 22 ++++++++++++++++++----
1 file changed, 18 insertions(+), 4 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7a2c89b21115..8d748b1b8d1e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4181,6 +4181,16 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
return NULL;
}
+static inline bool
+should_try_oom(int no_progress_loops,
+ enum compact_result last_compact_result)
+{
+ if (no_progress_loops > MAX_RECLAIM_RETRIES && last_compact_result
+ == COMPACT_SKIPPED)
+ return true;
+ return false;
+}
+
static inline bool
should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
enum compact_result compact_result,
@@ -4547,10 +4557,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
* Make sure we converge to OOM if we cannot make any progress
* several times in the row.
*/
- if (*no_progress_loops > MAX_RECLAIM_RETRIES) {
- /* Before OOM, exhaust highatomic_reserve */
- return unreserve_highatomic_pageblock(ac, true);
- }
+ if (*no_progress_loops > MAX_RECLAIM_RETRIES)
+ result false;
+ /* Last chance before OOM, try draining highatomic_reserve once */
+ else if (*no_progress_loops == MAX_RECLAIM_RETRIES)
+ return unreserve_highatomic_pageblock(ac, true)
/*
* Keep reclaiming pages while there is a chance this will lead
@@ -4822,6 +4833,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
did_some_progress > 0, &no_progress_loops))
goto retry;
+ if (should_try_oom(no_progress_loops, compact_result))
+ goto oom:
/*
* It doesn't make any sense to retry for the compaction if the order-0
* reclaim is not able to make any progress because the current
@@ -4839,6 +4852,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
if (check_retry_cpuset(cpuset_mems_cookie, ac))
goto retry_cpuset;
+oom:
/* Reclaim has failed us, start killing things */
page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
if (page)
--
2.26.2
next reply other threads:[~2021-03-15 16:59 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-15 16:58 Aaron Tomlin [this message]
2021-03-15 19:54 ` [PATCH] mm/page_alloc: try oom if reclaim is unable to make forward progress kernel test robot
2021-03-15 19:54 ` kernel test robot
2021-03-15 19:54 ` kernel test robot
2021-03-18 16:16 ` Michal Hocko
2021-03-19 17:29 ` Aaron Tomlin
2021-03-22 10:47 ` Michal Hocko
2021-03-25 21:01 ` Aaron Tomlin
2021-03-26 8:16 ` Michal Hocko
2021-03-26 11:22 ` Aaron Tomlin
2021-03-26 15:36 ` Michal Hocko
2021-03-26 17:00 ` Aaron Tomlin
2021-05-18 14:05 ` Aaron Tomlin
2021-05-19 11:10 ` Michal Hocko
2021-05-19 13:06 ` Aaron Tomlin
2021-05-19 14:50 ` [PATCH] mm/page_alloc: bail out on fatal signal during reclaim/compaction retry attempt Aaron Tomlin
2021-05-19 15:22 ` Vlastimil Babka
2021-05-19 19:08 ` Aaron Tomlin
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=20210315165837.789593-1-atomlin@redhat.com \
--to=atomlin@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).