From: Kellystewart00@yahoo.com.au
To: gentoo-user@lists.gentoo.org
Subject: Re: [gentoo-user] Performance problem at writing big files and Multitasking
Date: Tue, 27 Feb 2007 07:49:39 GMT [thread overview]
Message-ID: <1623124876-1172562578-cardhu_decombobulator_blackberry.rim.net-2082807461-@bxe008-cell00.bisx.prodap.on.blackberry> (raw)
In-Reply-To: <20070226162835.GG4105@huxley>
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="Windows-1252", Size: 1972 bytes --]
Sent via BlackBerry® from Vodafone
-----Original Message-----
From: Matthias Bethke <matthias@towiski.de>
Date: Mon, 26 Feb 2007 17:28:35
To:gentoo-user@lists.gentoo.org
Subject: Re: [gentoo-user] Performance problem at writing big files and Multitasking
Hi Daniel,
on Saturday, 2007-02-10 at 12:49:14, you wrote:
> I will give short overview what i have tried so far.
>
> 1. Trying different I/O Scheduler ( cfq anticipatory and deadline)
> 2. Enabling Low latency kernel and Preemptible kernel
> 3. Setting 1000 HZ for timer frequency
> 4. Tried the new kernel 2.6.19-gentoo-r6 and even the testing version
> 2.6.20-gentoo with core 2 enabled in processor type
Oh, so it is a multicore CPU---sorry if you mentioned it already, I
had deleted the start of the thread already when I read Benno's advice.
In that case, try 100 Hz scheduling period as well. I've had very bad
experiences with I/O and 250 Hz or higher on a dual Xeon. My guess is
that it was a cache effect and therefore shouldn't happen on the
Core2Duo, but it might still be worth a try.
> As i am using Xfce i installed the diskperf-plugin which monitors disk
> I/O. The monitoring is divided in disk-read and disk-write.
> I recognized that every time when reading stops writing starts. So is
> this staggering of writing to disk normal as the programs have to read
> data they want to write to disk? On my previous machine i didn't
> recognize such a behaviour.
So you're reading and writing from/to the same disk? I'd expect that
behavior then, because the I/O scheduler tries to satisfy requests with
as little thrashing as possible. So if there are enough write requests
queued up it may keep the HD busy writing for a while before reading the
next chunk from somewhere else.
cheers!
Matthias
--
I prefer encrypted and signed messages. KeyID: FAC37665
Fingerprint: 8C16 3F0A A6FC DF0D 19B0 8DEF 48D9 1700 FAC3 7665
éí¢¬z¸\x1eÚ(¢¸&j)b b²
next prev parent reply other threads:[~2007-02-27 7:56 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <7LFgI-6qK-17@gated-at.bofh.it>
[not found] ` <7LFqt-6Eo-27@gated-at.bofh.it>
[not found] ` <7LUIK-4Qn-3@gated-at.bofh.it>
2007-02-07 16:00 ` [gentoo-user] Performance problem at writing big files and Multitasking Mike
2007-02-07 16:39 ` Daniel Pielmeier
2007-02-07 18:08 ` Benno Schulenberg
2007-02-07 21:39 ` Daniel Pielmeier
2007-02-10 11:49 ` Daniel Pielmeier
2007-02-26 16:28 ` Matthias Bethke
2007-02-27 7:49 ` Kellystewart00 [this message]
2007-02-06 20:31 Daniel Pielmeier
2007-02-06 20:50 ` Michael Schreckenbauer
2007-02-06 21:25 ` Daniel Pielmeier
2007-02-06 21:16 ` Etaoin Shrdlu
2007-02-06 21:28 ` Daniel Pielmeier
2007-02-08 10:42 ` Frédéric Grosshans
2007-02-08 18:34 ` Daniel Pielmeier
2007-02-08 19:12 ` Etaoin Shrdlu
2007-02-08 23:14 ` Iain Buchanan
2007-02-06 22:25 ` Daniel Pielmeier
2007-02-07 12:59 ` Daniel Pielmeier
2007-02-07 19:16 ` Tom Naujokas
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=1623124876-1172562578-cardhu_decombobulator_blackberry.rim.net-2082807461-@bxe008-cell00.bisx.prodap.on.blackberry \
--to=kellystewart00@yahoo.com.au \
--cc=gentoo-user@lists.gentoo.org \
/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