All of lore.kernel.org
 help / color / mirror / Atom feed
From: Benjamin LaHaise <bcrl@redhat.com>
To: Eff Norwood <enorwood@effrem.com>
Cc: nfs@lists.sourceforge.net
Subject: Re: huge number of intr/s on large nfs server
Date: Thu, 17 Oct 2002 22:05:43 -0400	[thread overview]
Message-ID: <20021017220543.C3702@redhat.com> (raw)
In-Reply-To: <CFEAJJEGMGECBCJFLGDBGEMACFAA.enorwood@effrem.com>; from enorwood@effrem.com on Wed, Oct 16, 2002 at 07:49:38PM -0700

On Wed, Oct 16, 2002 at 07:49:38PM -0700, Eff Norwood wrote:
> This system in question is a SuperMicro P4DL6 MB with dual Xeon 2.4's and
> 2.0GB of memory. One of the PCI-X slots/busses has a 3ware 7850 IDE RAID

Can you try running a non-SMP kernel?  At least one nfs server I'm running 
does pretty well with a UP kernel, even though it is getting in the 
neighbourhood of 10-20k interrupts per second.  Note that it is using 
async writes, and gets about 40MB/s with ext3 and is 100% busy when being 
written to, with the bulk of the time spent computing raid checksum blocks 
and copying data around and in prune_icache.  With an SMP system, there is 
likely to be contention introduced by interrupts floating back and forth 
between CPUs when the single client writing case is really not helped by 
SMP in the current knfsd.  Binding various interrupts to specific CPUs may 
help things here, but part of the problem lies with knfsd allowing multiple 
processes to back up in generic_file_write, which serializes on the inode 
semaphore.  This is pure overhead that a UP system won't suffer from quite 
as dramatically.  Also, make sure your journal is on a separate disk.  
Cheers,

		-ben


-------------------------------------------------------
This sf.net email is sponsored by: viaVerio will pay you up to
$1,000 for every account that you consolidate with us.
http://ad.doubleclick.net/clk;4749864;7604308;v?
http://www.viaverio.com/consolidator/osdn.cfm
_______________________________________________
NFS maillist  -  NFS@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nfs

  parent reply	other threads:[~2002-10-18  2:05 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-10-14 20:21 huge number of intr/s on large nfs server Eff Norwood
2002-10-15  8:13 ` Bogdan Costescu
2002-10-15 16:50   ` Eff Norwood
2002-10-15 17:02     ` Bogdan Costescu
2002-10-15 21:22 ` Andrew Theurer
2002-10-16 20:06   ` Eff Norwood
2002-10-16 22:51     ` Donavan Pantke
2002-10-16 23:18       ` Eff Norwood
2002-10-16 23:28         ` Donavan Pantke
2002-10-17  2:28 ` Benjamin LaHaise
2002-10-17  2:49   ` Eff Norwood
2002-10-17 11:15     ` Alex Thiel
2002-10-17 16:42       ` Eff Norwood
2002-10-17 13:33     ` Andrew Theurer
2002-10-17 16:59       ` Eff Norwood
2002-10-18  2:05     ` Benjamin LaHaise [this message]
2002-10-18  2:19       ` Eff Norwood
  -- strict thread matches above, loose matches on Subject: below --
2002-10-15 14:02 Heflin, Roger A.
2002-10-16  2:41 ` Eff Norwood
2002-10-15 19:27 Heflin, Roger A.
2002-10-15 20:51 ` Eric Whiting
2002-10-16  2:58   ` Eff Norwood
2002-10-16  2:54 ` Eff Norwood
2002-10-15 21:40 Heflin, Roger A.
2002-10-15 23:05 ` Eric Whiting

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=20021017220543.C3702@redhat.com \
    --to=bcrl@redhat.com \
    --cc=enorwood@effrem.com \
    --cc=nfs@lists.sourceforge.net \
    /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.