All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel J Blueman <daniel.blueman@gmail.com>
To: Tobias Oetiker <tobi@oetiker.ch>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>
Subject: Re: unfair io behaviour for high load interactive use still present  in 2.6.31
Date: Tue, 15 Sep 2009 04:02:10 -0700 (PDT)	[thread overview]
Message-ID: <2612a5ee-4141-43d2-a009-090eac352aa2@n2g2000vba.googlegroups.com> (raw)
In-Reply-To: <dkAXF-4Gg-25@gated-at.bofh.it>

On Sep 15, 8:50 am, Tobias Oetiker <t...@oetiker.ch> wrote:
> Experts,
>
> We run several busy NFS file servers with Areca HW Raid + LVM2 + ext3
>
> We find that the read bandwidth falls dramatically as well as the
> response times going up to several seconds as soon as the system
> comes under heavy write strain.

It's worthwhile checking:
 - that the ext3 filesystem starts at a stripe-aligned offset
 - that the ext3 filesystem was created with the correct stripe-width
and stride (chunk) size
 - due to the larger amount of memory, ext4 may be a big win (due to
delayed allocate), if you'll stay with a newer kernel
 - if you have battery backup at the right levels:
  - performance may be better mounting the ext3 filesystem with
'barrier=0'
  - performance may improve mounting 'data=writeback'

Thanks,
  Daniel
--
Daniel J Blueman

       reply	other threads:[~2009-09-15 11:11 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <dkAXF-4Gg-25@gated-at.bofh.it>
2009-09-15 11:02 ` Daniel J Blueman [this message]
2009-09-15 23:21   ` unfair io behaviour for high load interactive use still present in 2.6.31 Tobias Oetiker
     [not found] ` <dkHFQ-1FQ-3@gated-at.bofh.it>
     [not found]   ` <dkNrM-6Fq-11@gated-at.bofh.it>
     [not found]     ` <dkX7N-6wO-15@gated-at.bofh.it>
     [not found]       ` <dkXAT-6SV-9@gated-at.bofh.it>
2009-09-26 19:35         ` Daniel J Blueman
2009-09-15  7:30 Tobias Oetiker
2009-09-15 14:53 ` Corrado Zoccolo
2009-09-15 21:07   ` Tobias Oetiker
2009-09-16  7:29     ` Corrado Zoccolo
2009-09-16  7:54       ` Tobias Oetiker
2009-09-16 12:40       ` Tobias Oetiker

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=2612a5ee-4141-43d2-a009-090eac352aa2@n2g2000vba.googlegroups.com \
    --to=daniel.blueman@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tobi@oetiker.ch \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.