From: Johannes Weiner <hannes@cmpxchg.org>
To: Michal Hocko <mhocko@suse.cz>
Cc: Rik van Riel <riel@redhat.com>,
Satoru Moriya <satoru.moriya@hds.com>,
Mel Gorman <mgorman@suse.de>,
Andrew Morton <akpm@linux-foundation.org>,
Hugh Dickins <hughd@google.com>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [patch 2/8] mm: vmscan: disregard swappiness shortly before going OOM
Date: Fri, 14 Dec 2012 19:18:51 -0500 [thread overview]
Message-ID: <20121215001850.GA21353@cmpxchg.org> (raw)
In-Reply-To: <20121214161345.GA18780@dhcp22.suse.cz>
On Fri, Dec 14, 2012 at 05:13:45PM +0100, Michal Hocko wrote:
> On Fri 14-12-12 10:43:55, Rik van Riel wrote:
> > On 12/14/2012 03:37 AM, Michal Hocko wrote:
> >
> > >I can answer the later. Because memsw comes with its price and
> > >swappiness is much cheaper. On the other hand it makes sense that
> > >swappiness==0 doesn't swap at all. Or do you think we should get back to
> > >_almost_ doesn't swap at all?
> >
> > swappiness==0 will swap in emergencies, specifically when we have
> > almost no page cache left, we will still swap things out:
> >
> > if (global_reclaim(sc)) {
> > free = zone_page_state(zone, NR_FREE_PAGES);
> > if (unlikely(file + free <= high_wmark_pages(zone))) {
> > /*
> > * If we have very few page cache pages, force-scan
> > * anon pages.
> > */
> > fraction[0] = 1;
> > fraction[1] = 0;
> > denominator = 1;
> > goto out;
> >
> > This makes sense, because people who set swappiness==0 but
> > do have swap space available would probably prefer some
> > emergency swapping over an OOM kill.
>
> Yes, but this is the global reclaim path. I was arguing about
> swappiness==0 & memcg. As this patch doesn't make a big difference for
> the global case (as both the changelog and you mentioned) then we should
> focus on whether this is desirable change for the memcg path. I think it
> makes sense to keep "no swapping at all for memcg semantic" as we have
> it currently.
I would prefer we could agree on one thing, though. Having global
reclaim behave different from memcg reclaim violates the principle of
least surprise. Having the code behave like that implicitely without
any mention of global_reclaim() and vm_swappiness() is unacceptable.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2012-12-15 0:19 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-12 21:43 [patch 0/8] page reclaim bits Johannes Weiner
2012-12-12 21:43 ` [patch 1/8] mm: memcg: only evict file pages when we have plenty Johannes Weiner
2012-12-12 21:53 ` Rik van Riel
2012-12-12 22:28 ` Johannes Weiner
2012-12-13 10:07 ` Mel Gorman
2012-12-13 14:44 ` Mel Gorman
2012-12-13 14:55 ` Michal Hocko
2012-12-16 1:21 ` Simon Jeons
2012-12-17 15:54 ` Michal Hocko
2012-12-19 5:21 ` Simon Jeons
2012-12-19 9:20 ` Mel Gorman
2012-12-13 5:36 ` Simon Jeons
2012-12-13 5:34 ` Simon Jeons
2012-12-12 21:43 ` [patch 2/8] mm: vmscan: disregard swappiness shortly before going OOM Johannes Weiner
2012-12-12 22:01 ` Rik van Riel
2012-12-13 5:56 ` Simon Jeons
2012-12-13 10:34 ` Mel Gorman
2012-12-13 15:29 ` Michal Hocko
2012-12-13 16:05 ` Michal Hocko
2012-12-13 22:25 ` Satoru Moriya
2012-12-14 4:50 ` Johannes Weiner
2012-12-14 8:37 ` Michal Hocko
2012-12-14 15:43 ` Rik van Riel
2012-12-14 16:13 ` Michal Hocko
2012-12-15 0:18 ` Johannes Weiner [this message]
2012-12-17 16:37 ` Michal Hocko
2012-12-17 17:54 ` Johannes Weiner
2012-12-17 19:58 ` Michal Hocko
2012-12-14 20:17 ` Satoru Moriya
2012-12-14 19:44 ` Satoru Moriya
2012-12-13 19:05 ` Johannes Weiner
2012-12-13 19:47 ` Mel Gorman
2012-12-12 21:43 ` [patch 3/8] mm: vmscan: save work scanning (almost) empty LRU lists Johannes Weiner
2012-12-12 22:02 ` Rik van Riel
2012-12-13 10:41 ` Mel Gorman
2012-12-13 19:33 ` Johannes Weiner
2012-12-13 15:43 ` Michal Hocko
2012-12-13 19:38 ` Johannes Weiner
2012-12-14 8:46 ` Michal Hocko
2012-12-12 21:43 ` [patch 4/8] mm: vmscan: clarify LRU balancing close to OOM Johannes Weiner
2012-12-12 22:03 ` Rik van Riel
2012-12-13 10:46 ` Mel Gorman
2012-12-12 21:43 ` [patch 5/8] mm: vmscan: improve comment on low-page cache handling Johannes Weiner
2012-12-12 22:04 ` Rik van Riel
2012-12-13 10:47 ` Mel Gorman
2012-12-13 16:07 ` Michal Hocko
2012-12-12 21:43 ` [patch 6/8] mm: vmscan: clean up get_scan_count() Johannes Weiner
2012-12-12 22:06 ` Rik van Riel
2012-12-13 11:07 ` Mel Gorman
2012-12-13 16:18 ` Michal Hocko
2012-12-12 21:43 ` [patch 7/8] mm: vmscan: compaction works against zones, not lruvecs Johannes Weiner
2012-12-12 22:31 ` Rik van Riel
2012-12-13 11:12 ` Mel Gorman
2012-12-13 16:48 ` Michal Hocko
2012-12-12 21:43 ` [patch 8/8] mm: reduce rmap overhead for ex-KSM page copies created on swap faults Johannes Weiner
2012-12-12 22:34 ` Rik van Riel
2012-12-12 21:50 ` [patch 0/8] page reclaim bits Andrew Morton
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=20121215001850.GA21353@cmpxchg.org \
--to=hannes@cmpxchg.org \
--cc=akpm@linux-foundation.org \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mhocko@suse.cz \
--cc=riel@redhat.com \
--cc=satoru.moriya@hds.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