From: Roy Sigurd Karlsbakk <roy@karlsbakk.net>
To: "Martin J. Bligh" <Martin.Bligh@us.ibm.com>,
Andrew Morton <akpm@zip.com.au>
Cc: linux-kernel@vger.kernel.org
Subject: Re: [BUG+FIX] 2.4 buggercache sucks
Date: Fri, 30 Aug 2002 11:21:06 +0200 [thread overview]
Message-ID: <200208301121.06437.roy@karlsbakk.net> (raw)
In-Reply-To: <318656043.1030603363@[10.10.2.3]>
> > I mean - this code solved _my_ problem. Without it the server OOMs within
> > minutes of high load, as explained earlier. I'd rather like a clean fix
> > in 2.4 than this, although it works.
>
> I'm sure Andrew could explain this better than I - he wrote the
> code, I just whined about the problem. Basically he frees the
> buffer_head immediately after he's used it, which could at least
> in theory degrade performance a little if it could have been reused.
> Now, nobody's ever really benchmarked that, so a more conservative
> approach is likely to be taken, unless someone can prove it doesn't
> degrade performance much for people who don't need the fix. One
> of the cases people were running scared of was something doing
> continual overwrites of a file, I think something like:
>
> for (i=0;i<BIGNUMBER;i++) {
> lseek (0);
> write 4K of data;
> }
>
> Or something.
>
> Was your workload doing lots of reads, or lots of writes? Or both?
I was downloading large files @ ~ 4Mbps from 20-50 clients - filesize ~3GB
the box has 1GB memory minus (no highmem) - so - 900 megs. After some time it
starts swapping and it OOMs. Same happens with several userspace httpd's
roy
--
Roy Sigurd Karlsbakk, Datavaktmester
ProntoTV AS - http://www.pronto.tv/
Tel: +47 9801 3356
Computers are like air conditioners.
They stop working when you open Windows.
next prev parent reply other threads:[~2002-08-30 9:16 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-05-23 13:11 [BUG] 2.4 VM sucks. Again Roy Sigurd Karlsbakk
2002-05-23 14:54 ` Martin J. Bligh
2002-05-23 16:29 ` Roy Sigurd Karlsbakk
2002-05-23 16:46 ` Martin J. Bligh
2002-05-24 10:04 ` Roy Sigurd Karlsbakk
2002-05-24 14:35 ` Martin J. Bligh
2002-05-24 19:32 ` Andrew Morton
2002-05-30 10:29 ` Roy Sigurd Karlsbakk
2002-05-30 19:28 ` Andrew Morton
2002-05-31 16:56 ` Roy Sigurd Karlsbakk
2002-05-31 18:19 ` Andrea Arcangeli
2002-06-18 11:26 ` Roy Sigurd Karlsbakk
2002-06-18 19:42 ` Andrew Morton
2002-06-19 11:26 ` Roy Sigurd Karlsbakk
2002-07-10 7:50 ` [2.4 BUFFERING BUG] (was [BUG] 2.4 VM sucks. Again) Roy Sigurd Karlsbakk
2002-07-10 8:05 ` Andrew Morton
2002-07-10 8:14 ` Roy Sigurd Karlsbakk
2002-08-28 9:28 ` [BUG+FIX] 2.4 buggercache sucks Roy Sigurd Karlsbakk
2002-08-28 15:30 ` Martin J. Bligh
2002-08-29 8:00 ` Roy Sigurd Karlsbakk
2002-08-29 13:42 ` Martin J. Bligh
2002-08-30 9:21 ` Roy Sigurd Karlsbakk [this message]
2002-08-30 17:19 ` Martin J. Bligh
2002-08-30 18:49 ` Andrew Morton
2002-05-24 15:11 ` [BUG] 2.4 VM sucks. Again Alan Cox
2002-05-24 15:53 ` Martin J. Bligh
2002-05-24 16:14 ` Alan Cox
2002-05-24 16:31 ` Martin J. Bligh
2002-05-24 17:30 ` Austin Gonyou
2002-05-24 17:43 ` Martin J. Bligh
2002-05-24 18:03 ` Austin Gonyou
2002-05-24 18:10 ` Martin J. Bligh
2002-05-24 18:29 ` 2.4 Kernel Perf discussion [Was Re: [BUG] 2.4 VM sucks. Again] Austin Gonyou
2002-05-24 19:01 ` Stephen Frost
2002-05-27 9:24 ` [BUG] 2.4 VM sucks. Again Marco Colombo
2002-05-27 22:24 ` Austin Gonyou
2002-05-27 23:08 ` Austin Gonyou
2002-05-27 11:12 ` Roy Sigurd Karlsbakk
2002-05-27 14:31 ` Alan Cox
2002-05-27 13:43 ` Roy Sigurd Karlsbakk
2002-05-23 16:03 ` Johannes Erdfelt
2002-05-23 16:33 ` Roy Sigurd Karlsbakk
2002-05-23 22:50 ` Luigi Genoni
2002-05-24 11:53 ` Roy Sigurd Karlsbakk
2002-05-23 18:12 ` jlnance
2002-05-24 10:36 ` Roy Sigurd Karlsbakk
2002-05-31 21:21 ` Andrea Arcangeli
2002-06-01 12:36 ` Roy Sigurd Karlsbakk
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=200208301121.06437.roy@karlsbakk.net \
--to=roy@karlsbakk.net \
--cc=Martin.Bligh@us.ibm.com \
--cc=akpm@zip.com.au \
--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;
as well as URLs for NNTP newsgroup(s).