mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Mike Galbraith <efault@gmx.de>
To: "Justin P. Mattock" <justinmattock@gmail.com>
Cc: Ulrich Lukas <stellplatz-nr.13a@datenparkplatz.de>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: Poor desktop responsiveness with background I/O-operations
Date: Mon, 21 Sep 2009 06:23:54 +0200	[thread overview]
Message-ID: <1253507034.23414.90.camel@marge.simson.net> (raw)
In-Reply-To: <4AB6C73C.1030004@gmail.com>

On Sun, 2009-09-20 at 17:22 -0700, Justin P. Mattock wrote:
> Wow, at first I did not notice anything
> from your *.sh script, but then a few moments
> later, the system became vary sluggish. firefox
> takes about 15 seconds to load. OS is mint linux
> with the latest HEAD on an imac9,1.

CFQ inherits IO priority from the parent on fork(), so nicing a shell or
the dd should (and does) help a LOT.  It also inherits the CPU scheduler
class.  I just checked, and IO does indeed inherit SCHED_IDLE as well as
the RT classes (SCHED_BATCH does nothing).  Setting the dd to SCHED_IDLE
makes a big difference, as it should, so there's a bigger hammer than
nice + ionice.  SCHED_IDLE is CPU_adorable + IO_nicest.

Anyway, the problem seems to have to have at least two facets:
1.  streaming IO causing pagecache reclaim.  That problem doesn't seem
to want to go away.  Fixing that won't help 2 one bit though.

2.  reads are sync, more heavily affected by seek latency than writes.
If the disk your binaries live on is seeking a lot, you pay a LOT.  

Hohum, IO + VM = haaaaard ;-)

	-Mike


  reply	other threads:[~2009-09-21  4:23 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-09-20  3:08 Ulrich Lukas
2009-09-20  4:11 ` Thomas Fjellstrom
2009-09-20  6:07 ` Arjan van de Ven
2009-09-20  8:50   ` Ulrich Lukas
2009-09-20 17:17     ` Nikos Chantziaras
2009-09-20 19:38     ` Mike Galbraith
2009-09-21  0:22       ` Justin P. Mattock
2009-09-21  4:23         ` Mike Galbraith [this message]
2009-09-21  7:48           ` Ulrich Lukas
2009-09-21  8:06             ` Mike Galbraith
2009-09-21 19:47               ` James Cloos
2009-09-21 22:47                 ` Nikos Chantziaras
2009-09-21 23:34                   ` James Cloos
2009-09-22  7:06                 ` Mike Galbraith
2009-09-22  9:20                   ` Mike Galbraith
2009-09-22 11:22                     ` Henrique de Moraes Holschuh
2009-09-22 11:32                       ` Mike Galbraith
2009-09-22 16:58                   ` James Cloos
2009-09-20 17:04   ` Ulrich Lukas
2009-09-20 20:22 ` Jiri Kosina
2009-09-20 22:04   ` Jan Kara
2009-09-21  7:25     ` Mike Galbraith
2009-09-21  7:33       ` Arjan van de Ven
2009-09-21  7:41         ` Mike Galbraith
2009-09-21  7:47           ` Mike Galbraith
2009-09-21  2:59   ` Ulrich Lukas
     [not found] <dmlhK-6ws-5@gated-at.bofh.it>
     [not found] ` <dmnMy-8tg-7@gated-at.bofh.it>
2009-09-20 18:51   ` Sanjoy Mahajan

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=1253507034.23414.90.camel@marge.simson.net \
    --to=efault@gmx.de \
    --cc=justinmattock@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=stellplatz-nr.13a@datenparkplatz.de \
    /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

Powered by JetHome