linux-btrace.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Simon Kirby <sim@hostway.ca>
To: linux-btrace@vger.kernel.org
Subject: Re: lots of unplugged by timer normal or abnormal?
Date: Tue, 06 Oct 2009 20:08:03 +0000	[thread overview]
Message-ID: <20091006200803.GA22261@hostway.ca> (raw)
In-Reply-To: <20091006185337.GF26949@hostway.ca>

On Tue, Oct 06, 2009 at 03:50:45PM -0400, Alan D. Brunelle wrote:

> This looks pretty bad - could you tell me what distro you are running on
> as a base? And did this happen before 2.6.30.5 (the poor performance)?
> And could you provide a more complete snippet of blktrace output
> (showing a handful of complete ops)?

Hi, Alan!

The poor performance has been ongoing for some time (these boxes were
built circa 2.6.26, and we hit a number of issues along the way -- 2.6.30
was the first stable kernel for serving files via nfsd, even with EXT3).

I'm figuring the majority of the performance issue are actually with the
AOE driver or the Coraid queue scheduling or RAID implementation, but I
figured that unplugging by timer maybe shouldn't happen even regardless
of how slow the underlying "device" is, hence my email.

It's amd64 Debian lenny (not sure why that matters), 16 GB of RAM, about
and a whole bunch of AOE storage, chopped up via DM, mostly using XFS as
a file system, served via knfsd.  "iostat -x -k 1" shows 100% utilization
fairly often for this particular device.

It's possible that this is just aggravated by memory allocator latency or
something, causing the unplug timer to trigger.  I was just wondering if
this is normal behaviour.

blktrace snippets seem pretty massive:

[sroot@nas04:/root/trace]# blktrace -w 10 /dev/etherd/e7.0
Device: /dev/etherd/e7.0
  CPU  0:                    0 events,      843 KiB data
  CPU  1:                    0 events,      709 KiB data
  CPU  2:                    0 events,      712 KiB data
  CPU  3:                    0 events,      752 KiB data
  CPU  4:                    0 events,      714 KiB data
  CPU  5:                    0 events,      713 KiB data
  CPU  6:                    0 events,      619 KiB data
  CPU  7:                    0 events,      732 KiB data
  Total:                     0 events (dropped 0),     5791 KiB data

I've saved that here:

http://0x.ca/sim/ref/2.6.30.5-hw-fixedxfs/nas04_blktrace_snippet.tgz

...which can be extracted and read with "blkparse etherd_e7.0".

Cheers,

Simon-

  parent reply	other threads:[~2009-10-06 20:08 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-10-06 18:53 lots of unplugged by timer normal or abnormal? Simon Kirby
2009-10-06 19:50 ` Alan D. Brunelle
2009-10-06 20:08 ` Simon Kirby [this message]
2009-10-06 20:20 ` Alan D. Brunelle
2009-10-11 16:44 ` Simon Kirby
2009-10-11 18:35 ` Jens Axboe
2009-10-11 20:58 ` Simon Kirby
2009-10-12  7:18 ` Jens Axboe

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=20091006200803.GA22261@hostway.ca \
    --to=sim@hostway.ca \
    --cc=linux-btrace@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).