linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
To: David Rientjes <rientjes@google.com>,
	Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [patch] mm, oom: stop reclaiming if GFP_ATOMIC will start failing soon
Date: Sat, 25 Apr 2020 09:32:02 +0900	[thread overview]
Message-ID: <6ed3e585-394a-42ff-03c4-a9bb8b5fcbc4@I-love.SAKURA.ne.jp> (raw)
In-Reply-To: <alpine.DEB.2.22.394.2004241347310.70176@chino.kir.corp.google.com>

On 2020/04/25 5:48, David Rientjes wrote:
> @@ -4372,11 +4372,21 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
>  					ac->nodemask) {
>  		unsigned long available;
>  		unsigned long reclaimable;
> +		unsigned long free;
>  		unsigned long min_wmark = min_wmark_pages(zone);
>  		bool wmark;
>  
> +		free = zone_page_state_snapshot(zone, NR_FREE_PAGES);
> +		/*
> +		 * If this zone is approaching the point where even order-0
> +		 * GFP_ATOMIC allocations will fail, stop considering reclaim.
> +		 */
> +		if (!__zone_watermark_ok(zone, 0, min_wmark, ac_classzone_idx(ac),
> +					 alloc_flags | ALLOC_HIGH, free))
> +			continue;

This is to trigger the OOM killer more aggressively, isn't it? But where is the
guarantee that this is an allocation request which can trigger the OOM killer?
If this is an allocation request which cannot trigger the OOM killer, wouldn't
this cause premature allocation failures?

> +
>  		available = reclaimable = zone_reclaimable_pages(zone);
> -		available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
> +		available += free;
>  
>  		/*
>  		 * Would the allocation succeed if we reclaimed all
> 


  reply	other threads:[~2020-04-25  0:32 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-24 20:48 [patch] mm, oom: stop reclaiming if GFP_ATOMIC will start failing soon David Rientjes
2020-04-25  0:32 ` Tetsuo Handa [this message]
2020-04-26  0:27 ` Andrew Morton
2020-04-26  3:04   ` Tetsuo Handa
2020-04-27  3:12   ` David Rientjes
2020-04-27  5:03     ` Tetsuo Handa
2020-04-27 20:30     ` Andrew Morton
2020-04-27 23:03       ` David Rientjes
2020-04-27 23:35         ` Andrew Morton
2020-04-28  7:43           ` Michal Hocko
2020-04-29  8:31             ` peter enderborg
2020-04-29  9:00               ` Michal Hocko
2020-04-28  9:38       ` Vlastimil Babka
2020-04-28 21:48         ` David Rientjes
2020-04-28 23:37           ` Tetsuo Handa
2020-04-29  7:51           ` Vlastimil Babka
2020-04-29  9:04             ` Michal Hocko
2020-04-29 10:45               ` Tetsuo Handa
2020-04-29 11:43                 ` Michal Hocko
2020-04-27  8:20   ` peter enderborg
2020-04-27 15:01 ` 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=6ed3e585-394a-42ff-03c4-a9bb8b5fcbc4@I-love.SAKURA.ne.jp \
    --to=penguin-kernel@i-love.sakura.ne.jp \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=rientjes@google.com \
    --cc=vbabka@suse.cz \
    /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).