From: Rik van Riel <riel@redhat.com>
To: Mel Gorman <mgorman@suse.de>, Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
Hugh Dickins <hughd@google.com>,
Tim Chen <tim.c.chen@linux.intel.com>,
Dave Chinner <david@fromorbit.com>,
Yuanhan Liu <yuanhan.liu@linux.intel.com>,
Bob Liu <bob.liu@oracle.com>, Jan Kara <jack@suse.cz>,
Linux Kernel <linux-kernel@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>,
Linux-FSDevel <linux-fsdevel@vger.kernel.org>
Subject: Re: [PATCH 3/3] mm: vmscan: Use proportional scanning during direct reclaim and full scan at DEF_PRIORITY
Date: Thu, 22 May 2014 12:04:12 -0400 [thread overview]
Message-ID: <537E1FFC.40608@redhat.com> (raw)
In-Reply-To: <1400749779-24879-4-git-send-email-mgorman@suse.de>
On 05/22/2014 05:09 AM, Mel Gorman wrote:
> Commit "mm: vmscan: obey proportional scanning requirements for kswapd"
> ensured that file/anon lists were scanned proportionally for reclaim from
> kswapd but ignored it for direct reclaim. The intent was to minimse direct
> reclaim latency but Yuanhan Liu pointer out that it substitutes one long
> stall for many small stalls and distorts aging for normal workloads like
> streaming readers/writers. Hugh Dickins pointed out that a side-effect of
> the same commit was that when one LRU list dropped to zero that the entirety
> of the other list was shrunk leading to excessive reclaim in memcgs.
> This patch scans the file/anon lists proportionally for direct reclaim
> to similarly age page whether reclaimed by kswapd or direct reclaim but
> takes care to abort reclaim if one LRU drops to zero after reclaiming the
> requested number of pages.
>
> Note that there are fewer allocation stalls even though the amount
> of direct reclaim scanning is very approximately the same.
>
> Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
--
All rights reversed
next prev parent reply other threads:[~2014-05-22 16:04 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-05-22 9:09 [PATCH 0/3] Shrinkers and proportional reclaim Mel Gorman
2014-05-22 9:09 ` [PATCH 1/3] fs/superblock: Unregister sb shrinker before ->kill_sb() Mel Gorman
2014-05-22 15:52 ` Rik van Riel
2014-05-22 9:09 ` [PATCH 2/3] fs/superblock: Avoid locking counting inodes and dentries before reclaiming them Mel Gorman
2014-05-22 15:59 ` Rik van Riel
2014-05-22 9:09 ` [PATCH 3/3] mm: vmscan: Use proportional scanning during direct reclaim and full scan at DEF_PRIORITY Mel Gorman
2014-05-22 16:04 ` Rik van Riel [this message]
2014-05-22 16:14 ` [PATCH 0/3] Shrinkers and proportional reclaim Yuanhan Liu
2014-05-22 16:30 ` Mel Gorman
2014-05-23 2:43 ` Yuanhan Liu
2014-05-22 17:22 ` Tim Chen
2014-05-26 21:44 ` Hugh Dickins
2014-05-27 2:37 ` Dave Chinner
2014-05-27 21:17 ` Hugh Dickins
2014-05-27 23:02 ` Konstantin Khlebnikov
2014-05-27 23:19 ` Hugh Dickins
2014-05-28 1:37 ` Dave Chinner
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=537E1FFC.40608@redhat.com \
--to=riel@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=bob.liu@oracle.com \
--cc=david@fromorbit.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=tim.c.chen@linux.intel.com \
--cc=yuanhan.liu@linux.intel.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).