From: Andrew Morton <akpm@digeo.com>
To: Andrea Arcangeli <andrea@suse.de>
Cc: Rik van Riel <riel@conectiva.com.br>,
Con Kolivas <conman@kolivas.net>,
linux kernel mailing list <linux-kernel@vger.kernel.org>,
marcelo@conectiva.com.br
Subject: Re: [BENCHMARK] 2.4.{18,19{-ck9},20rc1{-aa1}} with contest
Date: Sun, 10 Nov 2002 20:03:01 -0800 [thread overview]
Message-ID: <3DCF2BF5.5DD165DD@digeo.com> (raw)
In-Reply-To: 20021111015445.GB5343@x30.random
Andrea Arcangeli wrote:
>
> the slowdown happens in this case:
>
> queue 5 6 7 8 9
>
> insert read 3
>
> queue 3 5 6 7 8 9
read-latency will not do that.
> However I think even read-latency is more a workarond to a problem in
> the I/O queue dimensions.
The problem is the 2.4 algorithm. If a read is not mergeable or
insertable it is placed at the tail of the queue. Which is the
worst possible place it can be put because applications wait on
reads, not on writes.
next prev parent reply other threads:[~2002-11-11 3:56 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-11-09 2:00 [BENCHMARK] 2.4.{18,19{-ck9},20rc1{-aa1}} with contest Con Kolivas
2002-11-09 2:36 ` Andrew Morton
2002-11-09 3:26 ` Con Kolivas
2002-11-09 4:15 ` Andrew Morton
2002-11-09 5:12 ` Con Kolivas
2002-11-09 11:21 ` Jens Axboe
2002-11-09 13:09 ` Con Kolivas
2002-11-09 13:35 ` Stephen Lord
2002-11-09 13:54 ` Jens Axboe
2002-11-09 21:12 ` Arador
2002-11-10 2:26 ` Andrea Arcangeli
2002-11-09 21:53 ` Con Kolivas
2002-11-10 10:09 ` Jens Axboe
2002-11-10 16:23 ` Andrea Arcangeli
2002-11-11 4:26 ` Con Kolivas
2002-11-10 10:12 ` Kjartan Maraas
2002-11-10 10:17 ` Jens Axboe
2002-11-10 16:27 ` Andrea Arcangeli
2002-11-09 11:20 ` Jens Axboe
2002-11-10 2:44 ` Andrea Arcangeli
2002-11-10 3:56 ` Matt Reppert
2002-11-10 9:58 ` Con Kolivas
2002-11-10 10:06 ` Jens Axboe
2002-11-10 16:21 ` Andrea Arcangeli
2002-11-10 16:20 ` Andrea Arcangeli
2002-11-10 19:32 ` Rik van Riel
2002-11-10 20:10 ` Andrea Arcangeli
2002-11-10 20:52 ` Andrew Morton
2002-11-10 21:05 ` Rik van Riel
2002-11-11 1:54 ` Andrea Arcangeli
2002-11-11 4:03 ` Andrew Morton [this message]
2002-11-11 4:06 ` Andrea Arcangeli
2002-11-11 4:22 ` Andrew Morton
2002-11-11 4:39 ` Andrea Arcangeli
2002-11-11 5:10 ` Andrew Morton
2002-11-11 5:23 ` Andrea Arcangeli
2002-11-11 7:58 ` William Lee Irwin III
2002-11-11 13:56 ` Rik van Riel
2002-11-11 13:45 ` Rik van Riel
2002-11-11 14:09 ` Jens Axboe
2002-11-11 15:48 ` Andrea Arcangeli
2002-11-11 15:43 ` Andrea Arcangeli
2002-11-10 20:56 ` Andrew Morton
2002-11-11 1:08 ` Andrea Arcangeli
-- strict thread matches above, loose matches on Subject: below --
2002-11-09 3:44 Dieter Nützel
2002-11-09 3:54 ` Con Kolivas
2002-11-09 4:02 ` Dieter Nützel
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=3DCF2BF5.5DD165DD@digeo.com \
--to=akpm@digeo.com \
--cc=andrea@suse.de \
--cc=conman@kolivas.net \
--cc=linux-kernel@vger.kernel.org \
--cc=marcelo@conectiva.com.br \
--cc=riel@conectiva.com.br \
/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