public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Clemens Ladisch <cladisch@googlemail.com>
To: Arthur Marsh <arthur.marsh@internode.on.net>
Cc: Andrea Arcangeli <aarcange@redhat.com>,
	alsa-user@lists.sourceforge.net, linux-kernel@vger.kernel.org
Subject: Re: [Alsa-user] new source of MIDI playback slow-down identified - 5a03b051ed87e72b959f32a86054e1142ac4cf55 thp: use compaction in kswapd for GFP_ATOMIC order > 0
Date: Tue, 22 Feb 2011 08:37:23 +0100	[thread overview]
Message-ID: <4D6367B3.9050306@googlemail.com> (raw)
In-Reply-To: <g0ia38-jj6.ln1@ppp121-45-136-118.lns11.adl6.internode.on.net>

Arthur Marsh wrote:
> I'm experiencing MIDI playback slow-downs when I'm observing kswapd0 
> active (a few percent of cpu in top output) in recent kernels.
> 
> I git-bisected the problem down to:
> 
> commit 5a03b051ed87e72b959f32a86054e1142ac4cf55
> Author: Andrea Arcangeli <aarcange@redhat.com>
> Date:   Thu Jan 13 15:47:11 2011 -0800
> 
>      thp: use compaction in kswapd for GFP_ATOMIC order > 0
> 
>      This takes advantage of memory compaction to properly generate pages of
>      order > 0 if regular page reclaim fails and priority level becomes more
>      severe and we don't reach the proper watermarks.
> 
>      Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
>      Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
>      Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
> 
> I ran git-bisect over the weekend, building and installing ALSA 1.0.24 
> with each kernel. After identifying the above commit, I rebuilt the 2.6 
> head with that commit reverted and verified that the problem was no 
> longer present.

Apparently, huge page compaction disables interrupts for much too long.

> MIDI playback was via aplaymidi -p 17:0 to a Soundblaster Audigy 2 ZS 
> (SB0350) wavetable.

The ALSA sequencer uses either the system timer or an HR timer at 1 kHz
to deliver MIDI commands (notes); the wavetable driver requires its own
interrupts in regular 5.3 ms intervals.


Regards,
Clemens

       reply	other threads:[~2011-02-22  7:43 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <g0ia38-jj6.ln1@ppp121-45-136-118.lns11.adl6.internode.on.net>
2011-02-22  7:37 ` Clemens Ladisch [this message]
2011-02-22  7:46   ` [Alsa-user] new source of MIDI playback slow-down identified - 5a03b051ed87e72b959f32a86054e1142ac4cf55 thp: use compaction in kswapd for GFP_ATOMIC order > 0 Arthur Marsh
2011-02-22 13:40   ` Andrea Arcangeli
2011-02-22 16:15     ` Andrea Arcangeli
2011-02-22 16:59       ` Mel Gorman
2011-02-22 17:08         ` Andrea Arcangeli
2011-02-22 17:37           ` Mel Gorman
2011-02-22 17:47       ` Arthur Marsh
2011-02-22 19:43         ` Andrea Arcangeli
2011-02-23  9:15           ` Mel Gorman
2011-02-23 11:41             ` Arthur Marsh
2011-02-23 13:50               ` Clemens Ladisch
2011-02-23 17:01               ` Mel Gorman
2011-02-23 17:40                 ` Andrea Arcangeli
2011-02-23 16:24         ` Andrea Arcangeli
2011-02-23 16:36           ` Andrea Arcangeli
2011-02-23 16:40             ` Andrea Arcangeli
2011-02-23 16:47               ` Andrea Arcangeli
2011-02-23 16:55           ` Andrea Arcangeli
2011-02-23 20:07             ` Arthur Marsh
2011-02-23 21:25               ` Andrea Arcangeli
2011-02-23 21:55                 ` Arthur Marsh
2011-02-23 23:59                   ` Andrea Arcangeli
2011-02-24  1:40                     ` Arthur Marsh
2011-02-24  1:54                       ` Andrea Arcangeli
2011-02-26  6:43                         ` Andrea Arcangeli
2011-02-27  8:48                           ` Arthur Marsh
2011-02-23 17:10           ` Mel Gorman
2011-02-23 17:27             ` Andrea Arcangeli
2011-02-23 17:44               ` Mel Gorman
2011-02-23 18:14                 ` Andrea Arcangeli

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=4D6367B3.9050306@googlemail.com \
    --to=cladisch@googlemail.com \
    --cc=aarcange@redhat.com \
    --cc=alsa-user@lists.sourceforge.net \
    --cc=arthur.marsh@internode.on.net \
    --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