From: Hillf Danton <dhillf@gmail.com>
To: Rik van Riel <riel@redhat.com>
Cc: linux-mm@kvack.org, lkml <linux-kernel@vger.kernel.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Mel Gorman <mel@csn.ul.ie>, Johannes Weiner <hannes@cmpxchg.org>,
Andrew Morton <akpm@linux-foundation.org>,
Minchan Kim <minchan.kim@gmail.com>,
Hillf Danton <dhillf@gmail.com>
Subject: Re: [PATCH v3 -mm 1/3] mm: reclaim at order 0 when compaction is enabled
Date: Sun, 29 Jan 2012 21:25:37 +0800 [thread overview]
Message-ID: <CAJd=RBC+yfoFhNrsu7XCS1_84_HVKb4R_JavHh3Fb-_47_nWQA@mail.gmail.com> (raw)
In-Reply-To: <20120126145914.58619765@cuia.bos.redhat.com>
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=UTF-8, Size: 2438 bytes --]
Hi Rik
On Fri, Jan 27, 2012 at 3:59 AM, Rik van Riel <riel@redhat.com> wrote:
[...]
> @@ -2754,7 +2754,7 @@ loop_again:
> Â Â Â Â Â Â Â Â */
> Â Â Â Â Â Â Â Â for (i = 0; i <= end_zone; i++) {
> Â Â Â Â Â Â Â Â Â Â Â Â struct zone *zone = pgdat->node_zones + i;
> - Â Â Â Â Â Â Â Â Â Â Â int nr_slab;
> + Â Â Â Â Â Â Â Â Â Â Â int nr_slab, testorder;
> Â Â Â Â Â Â Â Â Â Â Â Â unsigned long balance_gap;
>
> Â Â Â Â Â Â Â Â Â Â Â Â if (!populated_zone(zone))
> @@ -2787,7 +2787,20 @@ loop_again:
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â (zone->present_pages +
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â KSWAPD_ZONE_BALANCE_GAP_RATIO);
> - Â Â Â Â Â Â Â Â Â Â Â if (!zone_watermark_ok_safe(zone, order,
> + Â Â Â Â Â Â Â Â Â Â Â /*
> + Â Â Â Â Â Â Â Â Â Â Â Â * Kswapd reclaims only single pages with compaction
> + Â Â Â Â Â Â Â Â Â Â Â Â * enabled. Trying too hard to reclaim until contiguous
> + Â Â Â Â Â Â Â Â Â Â Â Â * free pages have become available can hurt performance
> + Â Â Â Â Â Â Â Â Â Â Â Â * by evicting too much useful data from memory.
> + Â Â Â Â Â Â Â Â Â Â Â Â * Do not reclaim more than needed for compaction.
> + Â Â Â Â Â Â Â Â Â Â Â Â */
> + Â Â Â Â Â Â Â Â Â Â Â testorder = order;
> + Â Â Â Â Â Â Â Â Â Â Â if (COMPACTION_BUILD && order &&
> + Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â compaction_suitable(zone, order) !=
> + Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â COMPACT_SKIPPED)
> + Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â testorder = 0;
> +
> + Â Â Â Â Â Â Â Â Â Â Â if (!zone_watermark_ok_safe(zone, testorder,
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â high_wmark_pages(zone) + balance_gap,
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â end_zone, 0)) {
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â shrink_zone(priority, zone, &sc);
Hard to understand that zone is shrunk as hard as it was,
with water mark checked with new order, tippoint please.
Hillf
ÿôèº{.nÇ+·®+%Ëÿ±éݶ\x17¥wÿº{.nÇ+·¥{±þG«éÿ{ayº\x1dÊÚë,j\a¢f£¢·hïêÿêçz_è®\x03(éÝ¢j"ú\x1a¶^[m§ÿÿ¾\a«þG«éÿ¢¸?¨èÚ&£ø§~á¶iOæ¬z·vØ^\x14\x04\x1a¶^[m§ÿÿÃ\fÿ¶ìÿ¢¸?I¥
next prev parent reply other threads:[~2012-01-29 13:25 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-01-26 19:54 [PATCH v3 -mm 0/3] kswapd vs compaction improvements Rik van Riel
2012-01-26 19:59 ` [PATCH v3 -mm 1/3] mm: reclaim at order 0 when compaction is enabled Rik van Riel
2012-01-27 9:13 ` Hillf Danton
2012-01-27 16:35 ` Rik van Riel
2012-01-30 10:26 ` Mel Gorman
2012-01-27 23:31 ` Andrew Morton
2012-01-29 13:25 ` Hillf Danton [this message]
2012-01-30 10:36 ` Mel Gorman
2012-01-26 19:59 ` [PATCH v3 -mm 2/3] mm: kswapd carefully call compaction Rik van Riel
2012-01-27 23:36 ` Andrew Morton
2012-01-26 20:01 ` [PATCH v3 -mm 3/3] mm: only defer compaction for failed order and higher Rik van Riel
2012-01-30 10:47 ` Mel Gorman
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='CAJd=RBC+yfoFhNrsu7XCS1_84_HVKb4R_JavHh3Fb-_47_nWQA@mail.gmail.com' \
--to=dhillf@gmail.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=minchan.kim@gmail.com \
--cc=riel@redhat.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).