From: "Christopher Friesen" <cfriesen@nortel.com>
To: Sonny Rao <sonny@burdell.org>
Cc: linux-kernel@vger.kernel.org,
Marcelo Tosatti <marcelo.tosatti@cyclades.com.br>,
"Theodore Ts'o" <tytso@mit.edu>
Subject: Re: dentry_cache using up all my zone normal memory -- also seen on 2.6.14-rc2
Date: Wed, 21 Sep 2005 14:27:39 -0600 [thread overview]
Message-ID: <4331C23B.4010104@nortel.com> (raw)
In-Reply-To: <20050921200758.GA25362@kevlar.burdell.org>
Sonny Rao wrote:
> If I'm reading this correctly, you seem to have about 1.2 million
> files open and about 3.9 million dentrys objects in lowmem with almost
> no fragmentation.. for those files which are open there certainly
> will be a dentry attached to the inode (how big is inode cache?), but
> the shrinker should be trying to reclaim memory from the other 2.7
> million objects I would think.
I don't know what the code is actually doing. This is testcase
"rename14" from the LTP suite. It runs fine on ppc, ppc64, dual-xeon,
and Xscale.
The inode cache is small...under 300 objects.
> Based on the lack of fragmentation I would guess that either the shrinker isn't
> running or those dentrys are otherwise pinned somehow (parent
> directorys of the open files?) What does the directory structure look
> like?
No idea.
> Just for kicks (again), have you tried ratcheting up the
> /proc/sys/vm/vfs_cache_pressure tunable by a few orders of magnitude ?
Nope. I'm currently rebooting with an instrumentation patch for dentry,
may try this too.
Chris
next prev parent reply other threads:[~2005-09-21 20:27 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-09-21 16:26 dentry_cache using up all my zone normal memory Christopher Friesen
2005-09-21 16:53 ` Christopher Friesen
2005-09-21 19:46 ` dentry_cache using up all my zone normal memory -- also seen on 2.6.14-rc2 Christopher Friesen
2005-09-21 20:07 ` Sonny Rao
2005-09-21 20:27 ` Christopher Friesen [this message]
2005-09-21 20:49 ` Christopher Friesen
2005-09-21 20:59 ` Christopher Friesen
2005-09-21 20:58 ` Sonny Rao
2005-09-21 21:00 ` Dipankar Sarma
2005-09-21 21:14 ` Al Viro
2005-09-21 21:14 ` Trond Myklebust
2005-09-21 21:25 ` Christopher Friesen
2005-09-21 21:29 ` Christopher Friesen
2005-09-21 21:25 ` Christopher Friesen
2005-09-21 22:03 ` Roland Dreier
2005-09-22 3:11 ` Al Viro
2005-09-22 3:54 ` Christopher Friesen
2005-09-22 4:17 ` Al Viro
2005-09-22 14:47 ` Christopher Friesen
2005-09-22 15:16 ` Christopher Friesen
2005-09-22 18:12 ` dentry_cache using up all my zone normal memory -- new data point Christopher Friesen
2005-09-22 18:27 ` dentry_cache using up all my zone normal memory -- also seen on 2.6.14-rc2 Dipankar Sarma
2005-09-22 19:03 ` Christopher Friesen
2005-09-22 19:18 ` Dipankar Sarma
2005-09-22 21:37 ` Christopher Friesen
2005-09-22 21:44 ` Sonny Rao
2005-09-22 21:55 ` Christopher Friesen
2005-09-22 22:04 ` Randy.Dunlap
2005-09-26 4:43 ` [PATCH/RFC] sysrq: updating console_loglevel Randy.Dunlap
2005-09-22 22:05 ` dentry_cache using up all my zone normal memory -- also seen on 2.6.14-rc2 Christopher Friesen
2005-10-04 19:43 ` Dipankar Sarma
2005-10-04 20:02 ` Christopher Friesen
2005-10-05 4:00 ` Dipankar Sarma
2005-09-30 22:03 ` dentry_cache using up all my zone normal memory Christopher Friesen
2005-10-01 23:22 ` Marcelo
2005-10-02 6:04 ` Christopher Friesen
2005-10-02 19:55 ` Marcelo
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=4331C23B.4010104@nortel.com \
--to=cfriesen@nortel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=marcelo.tosatti@cyclades.com.br \
--cc=sonny@burdell.org \
--cc=tytso@mit.edu \
/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