From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
To: Zhang Yanfei <zhangyanfei.ok@hotmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Vlastimil Babka <vbabka@suse.cz>, Mel Gorman <mgorman@suse.de>,
David Rientjes <rientjes@google.com>,
Rik van Riel <riel@redhat.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 4/4] mm/compaction: enhance compaction finish condition
Date: Mon, 2 Feb 2015 16:12:23 +0900 [thread overview]
Message-ID: <20150202071223.GD6488@js1304-P5Q-DELUXE> (raw)
In-Reply-To: <BLU436-SMTP337E19C27F309D20380A81833E0@phx.gbl>
On Sat, Jan 31, 2015 at 11:58:03PM +0800, Zhang Yanfei wrote:
> At 2015/1/30 20:34, Joonsoo Kim wrote:
> > From: Joonsoo <iamjoonsoo.kim@lge.com>
> >
> > Compaction has anti fragmentation algorithm. It is that freepage
> > should be more than pageblock order to finish the compaction if we don't
> > find any freepage in requested migratetype buddy list. This is for
> > mitigating fragmentation, but, there is a lack of migratetype
> > consideration and it is too excessive compared to page allocator's anti
> > fragmentation algorithm.
> >
> > Not considering migratetype would cause premature finish of compaction.
> > For example, if allocation request is for unmovable migratetype,
> > freepage with CMA migratetype doesn't help that allocation and
> > compaction should not be stopped. But, current logic regards this
> > situation as compaction is no longer needed, so finish the compaction.
> >
> > Secondly, condition is too excessive compared to page allocator's logic.
> > We can steal freepage from other migratetype and change pageblock
> > migratetype on more relaxed conditions in page allocator. This is designed
> > to prevent fragmentation and we can use it here. Imposing hard constraint
> > only to the compaction doesn't help much in this case since page allocator
> > would cause fragmentation again.
>
> Changing both two behaviours in compaction may change the high order allocation
> behaviours in the buddy allocator slowpath, so just as Vlastimil suggested,
> some data from allocator should be necessary and helpful, IMHO.
As Vlastimil said, fragmentation effect should be checked. I will do
it and report the result on next version.
Thanks.
prev parent reply other threads:[~2015-02-02 7:10 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-01-30 12:34 [PATCH v2 0/4] enhance compaction success rate Joonsoo Kim
2015-01-30 12:34 ` [PATCH v2 1/4] mm/compaction: fix wrong order check in compact_finished() Joonsoo Kim
2015-01-30 13:27 ` Vlastimil Babka
2015-01-31 7:38 ` Zhang Yanfei
2015-01-30 12:34 ` [PATCH v2 2/4] mm/compaction: stop the isolation when we isolate enough freepage Joonsoo Kim
2015-01-30 13:47 ` Vlastimil Babka
2015-01-31 7:49 ` Zhang Yanfei
2015-01-31 8:31 ` Vlastimil Babka
2015-01-31 10:17 ` Zhang Yanfei
2015-01-30 12:34 ` [PATCH v2 3/4] mm/page_alloc: separate steal decision from steal behaviour part Joonsoo Kim
2015-01-30 14:27 ` Vlastimil Babka
2015-02-02 7:02 ` Joonsoo Kim
2015-01-31 12:38 ` Zhang Yanfei
2015-02-02 7:03 ` Joonsoo Kim
2015-01-30 12:34 ` [PATCH v2 4/4] mm/compaction: enhance compaction finish condition Joonsoo Kim
2015-01-30 14:43 ` Vlastimil Babka
2015-02-02 7:11 ` Joonsoo Kim
2015-01-31 15:58 ` Zhang Yanfei
2015-02-02 7:12 ` Joonsoo Kim [this message]
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=20150202071223.GD6488@js1304-P5Q-DELUXE \
--to=iamjoonsoo.kim@lge.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=riel@redhat.com \
--cc=rientjes@google.com \
--cc=vbabka@suse.cz \
--cc=zhangyanfei.ok@hotmail.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).