archive mirror
 help / color / mirror / Atom feed
From: Andrew Morton <>
To: Lorenzo Allegrucci <>
Cc: Linux Kernel <>
Subject: Re: qsbench, interesting results
Date: Sun, 29 Sep 2002 22:57:43 -0700	[thread overview]
Message-ID: <> (raw)
In-Reply-To: <>

Lorenzo Allegrucci wrote:
> qsbench is a VM benchmark based on sorting a large array
> by quick sort.
> Below are some results of qsbench sorting a 350Mb array
> on a 256+400Mb RAM+swap machine.
> Tested kernels: 2.4.19, 2.5.38 and 2.5.39

Thanks for pointing this out.  It's happening because the VM in
2.5.39 tries to avoid stalling tasks for too long.

That works well, so qsbench just gets in and submits more reads
against the swapdevice much earlier than it used to.  The new IO
scheduler then obligingly promotes the swap reads ahead of the
swap writes and we end up doing a ton of seeking.

The -mm patchset has some kswapd improvements which pull most
of the difference back.

Stronger fixes for this would be a) penalise heavily-faulting
tasks and b) tag swap writeout as needing higher priority at the
block level.

I'll take a look at some preferential throttling later on.  But
I must say that I'm not hugely worried about performance regression
under wild swapstorms.  The correct fix is to go buy some more
RAM, and the kernel should not be trying to cater for underprovisioned
machines if that affects the usual case.

  parent reply	other threads:[~2002-09-30  5:52 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-09-29 14:15 Lorenzo Allegrucci
2002-09-29 16:26 ` bert hubert
2002-09-29 19:56   ` Lorenzo Allegrucci
2002-09-29 20:00     ` bert hubert
2002-09-29 21:05       ` Lorenzo Allegrucci
2002-09-30  5:57 ` Andrew Morton [this message]
2002-10-01 14:05   ` Daniel Phillips
2002-10-01 16:52     ` Rik van Riel
2002-10-01 17:03       ` Daniel Phillips
2002-10-01 17:13         ` Rik van Riel
2002-10-01 17:20           ` Daniel Phillips
2002-10-01 17:29             ` Rik van Riel
2002-10-01 17:38               ` Daniel Phillips
2002-10-01 18:18         ` Lorenzo Allegrucci
2002-10-01 17:15       ` Larry McVoy
2002-10-01 18:04     ` Andrew Morton
2002-10-01 18:20       ` Rik van Riel
2002-10-01 18:35       ` Daniel Phillips

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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \ \ \ \ \
    --subject='Re: qsbench, interesting results' \

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

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).