From: Michal Hocko <mhocko@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>,
David Rientjes <rientjes@google.com>,
Mel Gorman <mgorman@suse.de>,
Hillf Danton <hillf.zj@alibaba-inc.com>, <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
Michal Hocko <mhocko@suse.com>
Subject: [PATCH 3/3] mm: help __GFP_NOFAIL allocations which do not trigger OOM killer
Date: Tue, 20 Dec 2016 14:49:04 +0100 [thread overview]
Message-ID: <20161220134904.21023-4-mhocko@kernel.org> (raw)
In-Reply-To: <20161220134904.21023-1-mhocko@kernel.org>
From: Michal Hocko <mhocko@suse.com>
Now that __GFP_NOFAIL doesn't override decisions to skip the oom killer
we are left with requests which require to loop inside the allocator
without invoking the oom killer (e.g. GFP_NOFS|__GFP_NOFAIL used by fs
code) and so they might, in very unlikely situations, loop for ever -
e.g. other parallel request could starve them.
This patch tries to limit the likelihood of such a lockup by giving
these __GFP_NOFAIL requests a chance to move on by consuming a small
part of memory reserves. We are using ALLOC_HARDER which should be
enough to prevent from the starvation by regular allocation requests,
yet it shouldn't consume enough from the reserves to disrupt high
priority requests (ALLOC_HIGH).
While we are at it, let's introduce a helper __alloc_pages_cpuset_fallback
which enforces the cpusets but allows to fallback to ignore them if
the first attempt fails. __GFP_NOFAIL requests can be considered
important enough to allow cpuset runaway in order for the system to move
on. It is highly unlikely that any of these will be GFP_USER anyway.
Signed-off-by: Michal Hocko <mhocko@suse.com>
---
mm/page_alloc.c | 46 ++++++++++++++++++++++++++++++++++++----------
1 file changed, 36 insertions(+), 10 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2dda7c3eba52..e8e551015d48 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3064,6 +3064,26 @@ void warn_alloc(gfp_t gfp_mask, const char *fmt, ...)
}
static inline struct page *
+__alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order,
+ unsigned int alloc_flags,
+ const struct alloc_context *ac)
+{
+ struct page *page;
+
+ page = get_page_from_freelist(gfp_mask, order,
+ alloc_flags|ALLOC_CPUSET, ac);
+ /*
+ * fallback to ignore cpuset restriction if our nodes
+ * are depleted
+ */
+ if (!page)
+ page = get_page_from_freelist(gfp_mask, order,
+ alloc_flags, ac);
+
+ return page;
+}
+
+static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac, unsigned long *did_some_progress)
{
@@ -3127,17 +3147,13 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
*did_some_progress = 1;
- if (gfp_mask & __GFP_NOFAIL) {
- page = get_page_from_freelist(gfp_mask, order,
- ALLOC_NO_WATERMARKS|ALLOC_CPUSET, ac);
- /*
- * fallback to ignore cpuset restriction if our nodes
- * are depleted
- */
- if (!page)
- page = get_page_from_freelist(gfp_mask, order,
+ /*
+ * Help non-failing allocations by giving them access to memory
+ * reserves
+ */
+ if (gfp_mask & __GFP_NOFAIL)
+ page = __alloc_pages_cpuset_fallback(gfp_mask, order,
ALLOC_NO_WATERMARKS, ac);
- }
}
out:
mutex_unlock(&oom_lock);
@@ -3743,6 +3759,16 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
*/
WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER);
+ /*
+ * Help non-failing allocations by giving them access to memory
+ * reserves but do not use ALLOC_NO_WATERMARKS because this
+ * could deplete whole memory reserves which would just make
+ * the situation worse
+ */
+ page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
+ if (page)
+ goto got_pg;
+
cond_resched();
goto retry;
}
--
2.10.2
next prev parent reply other threads:[~2016-12-20 13:49 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-20 13:49 [PATCH 0/3 -v3] GFP_NOFAIL cleanups Michal Hocko
2016-12-20 13:49 ` [PATCH 1/3] mm: consolidate GFP_NOFAIL checks in the allocator slowpath Michal Hocko
2016-12-20 13:49 ` [PATCH 2/3] mm, oom: do not enfore OOM killer for __GFP_NOFAIL automatically Michal Hocko
2016-12-20 15:31 ` Tetsuo Handa
2016-12-21 8:15 ` Michal Hocko
2017-01-19 18:41 ` Johannes Weiner
2017-01-20 8:33 ` Hillf Danton
2017-01-24 12:40 ` Michal Hocko
2017-01-25 7:00 ` Hillf Danton
2017-01-25 7:59 ` Michal Hocko
2017-01-25 8:41 ` Hillf Danton
2017-01-25 10:19 ` Michal Hocko
2016-12-20 13:49 ` Michal Hocko [this message]
2017-01-02 15:49 ` [PATCH 0/3 -v3] GFP_NOFAIL cleanups Michal Hocko
2017-01-03 1:36 ` Tetsuo Handa
2017-01-03 8:42 ` Michal Hocko
2017-01-03 14:38 ` Tetsuo Handa
2017-01-03 16:25 ` Vlastimil Babka
2017-01-03 20:40 ` Michal Hocko
2017-01-04 14:22 ` Tetsuo Handa
2017-01-04 15:20 ` Michal Hocko
2017-01-05 10:50 ` Tetsuo Handa
2017-01-05 11:54 ` Michal Hocko
2017-01-18 18:42 ` 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=20161220134904.21023-4-mhocko@kernel.org \
--to=mhocko@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=hillf.zj@alibaba-inc.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mhocko@suse.com \
--cc=penguin-kernel@I-love.SAKURA.ne.jp \
--cc=rientjes@google.com \
/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).