From: Andrea Arcangeli <andrea@suse.de>
To: Chris Chabot <chabotc@reviewboard.com>
Cc: linux-kernel@vger.kernel.org, Rik van Riel <riel@conectiva.com.br>
Subject: blkdev speedup
Date: Thu, 17 Jan 2002 15:13:56 +0100 [thread overview]
Message-ID: <20020117151356.G4847@athlon.random> (raw)
In-Reply-To: <20020116200459.E835@athlon.random> <3C460255.4020805@reviewboard.com>
In-Reply-To: <3C460255.4020805@reviewboard.com>; from chabotc@reviewboard.com on Wed, Jan 16, 2002 at 11:44:37PM +0100
On Wed, Jan 16, 2002 at 11:44:37PM +0100, Chris Chabot wrote:
>
> > Test hardware:
> > 4 way Dell, 4 GB physical RAM, SCSI/RAID subsystem,
> > DB runs on FS.
>
> Can we first make sure that the other factors dont plat a rol in this
> benchmark? I have a couple (14+) Dell servers here, and i know for a
> fact that most of their RAID systems are heavely borked in the
> performance department.
>
> All kernels upto 2.4.1x performed horibly, and all kernels after 2.4.16
> or so perform horibly again! Somewhere inbetween some magic seemed to
> happen in the block layer / elevator code / etc, that caused performance
> to increase upto 100% on the Dell PERC adapters. (started @ the first
> release of the AA VM). However after a few small releases, the
if you're using the blkdev directly, then please try to mount the blkdev
with a 4k filesystem before making your benchmark, that should give you
the magic performance back. 2.4.10 intentionally were defaulting to 4k
I/O, this is probably what made the difference for you.
Andrea
next prev parent reply other threads:[~2002-01-17 14:14 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <Pine.LNX.4.33L.0201162235480.32617-100000@imladris.surriel .com>
2002-01-16 19:04 ` Rik spreading bullshit about VM Andrea Arcangeli
2002-01-16 20:11 ` Jose Luis Domingo Lopez
2002-01-16 20:58 ` Richard Gooch
2002-01-16 21:10 ` Dave Jones
2002-01-16 21:17 ` Rik van Riel
2002-01-17 13:42 ` [lkml] " Ian Soboroff
2002-01-18 3:21 ` ...Re: " Dan Mann
2002-01-17 0:20 ` Luigi Genoni
2002-01-16 21:17 ` Craig Knox
2002-01-16 20:58 ` Bongani Hlope
2002-01-16 20:55 ` John Levon
2002-01-16 21:21 ` Bongani Hlope
2002-01-16 21:29 ` Adam Kropelin
2002-01-17 14:17 ` async buffer flushing reported slowdown (could be a driver issue?) Andrea Arcangeli
2002-01-18 0:28 ` Adam Kropelin
2002-01-16 21:58 ` Rik spreading bullshit about VM Diego Calleja
2002-01-16 22:02 ` Rik van Riel
2002-01-17 14:35 ` bugfix backed out Andrea Arcangeli
2002-01-17 15:04 ` Rik van Riel
2002-01-17 15:52 ` Andrea Arcangeli
2002-01-17 14:25 ` oom failures with mem=4m Andrea Arcangeli
2002-01-16 21:59 ` Rik spreading bullshit about VM Diego Calleja
2002-01-16 22:44 ` Chris Chabot
2002-01-17 8:18 ` Christoph Rohland
2002-01-17 14:13 ` Andrea Arcangeli [this message]
2002-01-17 0:07 ` Erik Mouw
2002-01-17 0:25 ` J Sloan
2002-01-17 1:15 ` Erik Mouw
2002-01-17 17:40 ` bill davidsen
2002-01-17 14:14 ` Alan Cox
2002-01-18 4:30 ` Bosko Radivojevic
2002-01-18 4:36 ` vm philosophising Rik van Riel
2002-01-18 4:58 ` Matthew Johnson
2002-01-18 5:12 ` Rik van Riel
2002-01-18 5:18 ` Ryan Cumming
2002-01-18 5:43 ` Matthew Johnson
2002-01-21 17:55 ` Bill Davidsen
2002-01-18 6:05 ` Matthew Johnson
2002-01-18 14:42 ` Tommy Faasen
2002-01-18 15:52 ` listmail
2002-01-21 15:50 ` The Doctor What
2002-01-21 16:16 ` Mike Harrold
2002-01-18 15:55 ` Mr. Shannon Aldinger
2002-01-18 18:39 ` Oliver Xymoron
2002-01-18 19:23 ` Alan Cox
2002-01-18 20:17 ` David Schwartz
2002-01-18 21:39 ` Alan Cox
2002-01-19 4:42 ` David Luyer
2002-01-19 18:00 ` Rob Landley
2002-01-20 5:42 ` Stevie O
2002-01-17 0:38 ` Rik spreading bullshit about VM Rik van Riel
2002-01-17 1:50 ` Nicolas Pitre
2002-01-17 11:45 ` Rik van Riel
2002-01-17 12:02 ` Stephan von Krawczynski
2002-01-17 2:14 ` Andrea Scrimieri
2002-01-17 12:07 ` Rik van Riel
2002-01-17 13:11 ` Andrea Scrimieri
2002-01-17 13:15 ` Rik van Riel
2002-01-17 14:02 ` Alan Cox
2002-01-17 21:41 ` Trever L. Adams
2002-01-18 1:46 ` brian
2002-01-17 1:52 ` Stephen Satchell
2002-01-17 13:26 ` Alan Cox
2002-01-17 15:10 ` clarification about redhat and vm Andrea Arcangeli
2002-01-17 15:21 ` Rik van Riel
2002-01-17 16:17 ` Alan Cox
2002-01-17 16:31 ` Andrea Arcangeli
2002-01-18 16:46 ` Wilhelm Nuesser
2002-01-18 19:07 ` Andrea Arcangeli
2002-01-19 10:50 ` Christoph Rohland
2002-01-19 13:54 ` Alan Cox
2002-01-19 17:38 ` Andrea Arcangeli
2002-01-18 16:53 ` Willi Nüßer
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=20020117151356.G4847@athlon.random \
--to=andrea@suse.de \
--cc=chabotc@reviewboard.com \
--cc=linux-kernel@vger.kernel.org \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.