public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Nick Piggin <nickpiggin@yahoo.com.au>
To: Klaus Dittrich <kladit@t-online.de>
Cc: Jan-Frode Myklebust <janfrode@parallab.uib.no>,
	Andrew Morton <akpm@osdl.org>,
	linux-kernel@vger.kernel.org
Subject: Re: dentry cache leak? Re: rsync out of memory 2.6.8-rc2
Date: Thu, 29 Jul 2004 13:31:41 +1000	[thread overview]
Message-ID: <41086F9D.2000801@yahoo.com.au> (raw)
In-Reply-To: <4107C109.2070600@xeon2.local.here>

Klaus Dittrich wrote:

> Nick Piggin wrote:
>
>>
>> Your vfs_cache_pressure probably wants to be higher than 500. Make it 
>> 10000.
>
>
> *No problems when using 10000.
> But I think of this as workaround only.
>

Yes it is just a workaround.

> I have read the "Scaling dcache with RCU" article from linuxjournal.com
> to get some insight how things should work. Pretty complicated.
>

Yes, prune_dcache is the only one called in response to memory pressure.
Basically you wouldn't have to worry about dcache internals for your sort
of machine. For example, RCU delayed freeing would not cause any problem.

The problem has probably been triggered either by a small change in the
page scanner, however the underlying problem is that the slab pressure
calculation isn't ideal on highmem systems, so in vfs intensive workloads
(lots of files), it is easy for ZONE_NORMAL allocations to OOM without
actually scanning much slab.


  reply	other threads:[~2004-07-29  3:31 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-07-26 15:06 dentry cache leak? Re: rsync out of memory 2.6.8-rc2 Klaus Dittrich
2004-07-26 19:37 ` Andrew Morton
2004-07-26 20:02   ` Klaus Dittrich
2004-07-26 20:38     ` Andrew Morton
2004-07-26 21:39       ` Klaus Dittrich
2004-07-26 22:14         ` Jan-Frode Myklebust
2004-07-27 20:43           ` Klaus Dittrich
2004-07-27 21:05             ` Klaus Dittrich
2004-07-28  1:21               ` Nick Piggin
2004-07-28 15:06                 ` Klaus Dittrich
2004-07-29  3:31                   ` Nick Piggin [this message]
2004-07-29 21:07 ` Andrew Morton
2004-07-30 16:30   ` Marcelo Tosatti
2004-07-30 19:47     ` Andrew Morton
2004-07-31  2:01       ` Marcelo Tosatti
2004-07-31 17:23       ` Linus Torvalds
2004-07-31 21:39         ` Andrew Morton
2004-08-03  6:55           ` Nick Piggin
  -- strict thread matches above, loose matches on Subject: below --
2004-08-01  9:47 Klaus Dittrich
2004-07-19  9:19 Klaus Dittrich
2004-07-19 11:20 ` dentry cache leak? " bert hubert
     [not found]   ` <20040719113228.GA15295@outpost.ds9a.nl>
2004-07-19 12:56     ` Klaus Dittrich
2004-07-26  1:06       ` 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=41086F9D.2000801@yahoo.com.au \
    --to=nickpiggin@yahoo.com.au \
    --cc=akpm@osdl.org \
    --cc=janfrode@parallab.uib.no \
    --cc=kladit@t-online.de \
    --cc=linux-kernel@vger.kernel.org \
    /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