From: Wu Fengguang <fengguang.wu@intel.com>
To: Lukas Hejtmanek <xhejtman@ics.muni.cz>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Bill Davidsen <davidsen@tmr.com>
Subject: Re: 2.6.28-rc8 big regression in VM
Date: Wed, 17 Dec 2008 20:44:21 +0800 [thread overview]
Message-ID: <20081217124421.GA22317@localhost> (raw)
In-Reply-To: <20081217123307.GF4480@ics.muni.cz>
On Wed, Dec 17, 2008 at 02:33:07PM +0200, Lukas Hejtmanek wrote:
> On Wed, Dec 17, 2008 at 08:27:26PM +0800, Wu Fengguang wrote:
> > It looks like most of cached pages were successfully freed:
> >
> > 247788 => 69856 pages
> >
> > To get more concrete numbers, could you send more info by running the
> > following commands?
> >
> > cp /proc/meminfo meminfo-1
> > cp /proc/vmstat vmstat-1
> > sync
> > echo 3 > /proc/sys/vm/drop_caches
> > cp /proc/meminfo meminfo-2
> > cp /proc/vmstat vmstat-2
>
> attached.
before after
MemTotal: 2016688 kB 2016688 kB
MemFree: 22680 kB 1306652 kB
Buffers: 238592 kB 360 kB
Cached: 1087428 kB 129516 kB
----------------------------------------------
So the cache memory shrinks a lot.
Maybe your 'free' command is reporting wrong numbers?
Or it's not a quite reproducible problem?
Thanks,
Fengguang
SwapCached: 0 kB 0 kB
Active: 1016536 kB 428240 kB
Inactive: 798812 kB 190976 kB
Active(anon): 412044 kB 411084 kB
Inactive(anon): 150708 kB 150708 kB
Active(file): 604492 kB 17156 kB
Inactive(file): 648104 kB 40268 kB
Unevictable: 0 kB 0 kB
Mlocked: 0 kB 0 kB
SwapTotal: 1542232 kB 1542232 kB
SwapFree: 1542232 kB 1542232 kB
Dirty: 108 kB 48 kB
Writeback: 0 kB 0 kB
AnonPages: 489448 kB 489452 kB
Mapped: 73380 kB 73384 kB
Slab: 114192 kB 26188 kB
SReclaimable: 97304 kB 9576 kB
SUnreclaim: 16888 kB 16612 kB
PageTables: 11304 kB 11368 kB
NFS_Unstable: 0 kB 0 kB
Bounce: 0 kB 0 kB
WritebackTmp: 0 kB 0 kB
CommitLimit: 2550576 kB 2550576 kB
Committed_AS: 818488 kB 818488 kB
VmallocTotal: 34359738367 kB 34359738367 kB
next prev parent reply other threads:[~2008-12-17 12:45 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-12-12 18:38 2.6.28-rc8 big regression in VM Lukas Hejtmanek
2008-12-13 1:21 ` Wu Fengguang
2008-12-13 9:58 ` Lukas Hejtmanek
2008-12-13 14:02 ` Wu Fengguang
2008-12-16 21:08 ` Bill Davidsen
2008-12-15 1:16 ` Wu Fengguang
2008-12-15 2:05 ` KOSAKI Motohiro
2008-12-15 9:53 ` Lukas Hejtmanek
2008-12-15 10:56 ` KOSAKI Motohiro
2008-12-15 9:44 ` Lukas Hejtmanek
2008-12-16 4:59 ` Wu Fengguang
[not found] ` <20081216195219.GA4480@ics.muni.cz>
2008-12-17 12:27 ` Wu Fengguang
2008-12-17 12:33 ` Lukas Hejtmanek
2008-12-17 12:44 ` Wu Fengguang [this message]
2008-12-17 12:49 ` Lukas Hejtmanek
2008-12-17 13:02 ` Wu Fengguang
2008-12-25 10:50 ` Wu Fengguang
2008-12-25 10:58 ` Lukas Hejtmanek
2008-12-25 11:18 ` Wu Fengguang
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=20081217124421.GA22317@localhost \
--to=fengguang.wu@intel.com \
--cc=davidsen@tmr.com \
--cc=linux-kernel@vger.kernel.org \
--cc=xhejtman@ics.muni.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