From: Roger Larsson <roger.larsson@norran.net>
To: Martin Dalecki <dalecki@evision-ventures.com>,
Pavel Machek <pavel@suse.cz>
Cc: Jens Axboe <axboe@suse.de>, kernel list <linux-kernel@vger.kernel.org>
Subject: Re: another IDE cleanup: kill duplicated code
Date: Tue, 12 Feb 2002 20:19:14 +0100 [thread overview]
Message-ID: <200202121922.g1CJMPi23466@mailc.telia.com> (raw)
In-Reply-To: <20020211221102.GA131@elf.ucw.cz> <3C68F3F3.8030709@evision-ventures.com>
In-Reply-To: <3C68F3F3.8030709@evision-ventures.com>
On Tuesday den 12 February 2002 11.52, Martin Dalecki wrote:
>
> If you are already at it, I would like to ask to you consider seriously
> the removal of the
> following entries in the ide drivers /proc control files:
>
> [snip]
> ide_add_setting(drive, "file_readahead", ...
> &max_readahead[major][minor], NULL);
>
> Those calls can be found in ide-cd.c, ide-disk,c and ide-floppy.c
>
> [snip]
>
> The second of them is trying to control a file-system level constant
> inside the actual block device driver.
> This is a blatant violation of the layering principle in software
> design, and should go as soon as
> possible.
It really should go (the only one working is for ide-disk) but
you need to add another way to tune readahead per disk too...
Tuning this parameter gives quite a bit improved performance
when reading from several big files at a time! A diff of two big files
is enough to show it: from 10MB/s to 25MB/s (2.4.17-rc1)
(due to less time lost seeking)
/RogerL
--
Roger Larsson
Skellefteå
Sweden
next prev parent reply other threads:[~2002-02-12 19:23 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-02-11 22:11 Pavel Machek
2002-02-12 10:52 ` Martin Dalecki
2002-02-12 12:28 ` Vojtech Pavlik
2002-02-12 12:45 ` Martin Dalecki
2002-02-12 12:57 ` Vojtech Pavlik
2002-02-12 13:17 ` Martin Dalecki
2002-02-12 13:43 ` Vojtech Pavlik
2002-02-12 13:58 ` Martin Dalecki
2002-02-12 14:42 ` Vojtech Pavlik
2002-02-12 15:23 ` Martin Dalecki
2002-02-12 15:28 ` Vojtech Pavlik
2002-02-12 15:35 ` Martin Dalecki
2002-02-12 16:56 ` Jens Axboe
2002-02-13 5:50 ` Andre Hedrick
2002-02-13 7:28 ` Vojtech Pavlik
2002-02-13 10:53 ` Martin Dalecki
2002-02-13 10:35 ` Martin Dalecki
2002-02-13 10:29 ` Andre Hedrick
2002-02-13 10:56 ` Pavel Machek
2002-02-13 11:11 ` Martin Dalecki
2002-02-13 11:25 ` Matthias Andree
2002-02-12 18:28 ` Andreas Dilger
2002-02-13 12:35 ` Martin Dalecki
2002-02-13 16:24 ` Andreas Dilger
2002-02-13 16:31 ` Martin Dalecki
2002-02-12 16:57 ` Jens Axboe
2002-02-13 5:46 ` Andre Hedrick
2002-02-13 6:42 ` Jens Axboe
2002-02-13 7:30 ` Andre Hedrick
2002-02-13 7:47 ` Jens Axboe
2002-02-13 7:44 ` Andre Hedrick
2002-02-13 7:58 ` Jens Axboe
2002-02-13 20:38 ` Rik van Riel
2002-02-13 11:01 ` Martin Dalecki
2002-02-13 11:03 ` Jens Axboe
2002-02-13 11:27 ` Vojtech Pavlik
2002-02-13 7:05 ` Vojtech Pavlik
2002-02-12 12:50 ` Martin Dalecki
2002-02-12 19:19 ` Roger Larsson [this message]
2002-02-13 10:56 ` Martin Dalecki
2002-02-12 20:03 ` Andrew Morton
2002-02-13 10:47 ` Martin Dalecki
2002-02-13 18:52 ` Andrew Morton
2002-02-14 10:04 ` Martin Dalecki
2002-02-14 10:19 ` Andrew Morton
2002-02-13 5:52 ` Andre Hedrick
2002-02-13 7:30 ` Vojtech Pavlik
2002-02-13 7:27 ` Andre Hedrick
2002-02-13 10:39 ` Vojtech Pavlik
2002-02-13 10:46 ` Andre Hedrick
2002-02-13 11:26 ` Vojtech Pavlik
2002-02-13 11:26 ` Andre Hedrick
2002-02-13 11:03 ` Daniel Egger
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=200202121922.g1CJMPi23466@mailc.telia.com \
--to=roger.larsson@norran.net \
--cc=axboe@suse.de \
--cc=dalecki@evision-ventures.com \
--cc=linux-kernel@vger.kernel.org \
--cc=pavel@suse.cz \
/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
all inboxes | Powered by JetHome®