From: Erik Mouw <mouw@nl.linux.org>
To: Manish Regmi <regmi.manish@gmail.com>
Cc: Arjan van de Ven <arjan@infradead.org>,
linux-kernel@vger.kernel.org, kernelnewbies@nl.linux.org
Subject: Re: Linux disk performance.
Date: Mon, 18 Dec 2006 14:07:02 +0100 [thread overview]
Message-ID: <20061218130702.GA14984@gateway.home> (raw)
In-Reply-To: <652016d30612180439y6cd12089l115e4ef6ce2e59fe@mail.gmail.com>
On Mon, Dec 18, 2006 at 06:24:39PM +0545, Manish Regmi wrote:
> On 12/18/06, Arjan van de Ven <arjan@infradead.org> wrote:
> >if you want truely really smooth writes you'll have to work for it,
> >since "bumpy" writes tend to be better for performance so naturally the
> >kernel will favor those.
> >
> >to get smooth writes you'll need to do a threaded setup where you do an
> >msync/fdatasync/sync_file_range on a frequent-but-regular interval from
> >a thread. Be aware that this is quite likely to give you lower maximum
> >performance than the batching behavior though.
> >
>
> Thanks...
>
> But isn't O_DIRECT supposed to bypass buffering in Kernel?
It is.
> Doesn't it directly write to disk?
Yes, but it still uses an IO scheduler.
> I tried to put fdatasync() at regular intervals but there was no
> visible effect.
In your first message you mentioned you were using an ancient 2.6.10
kernel. That kernel uses the anticipatory IO scheduler. Update to the
latest stable kernel (2.6.19.1 at time of writing) and it will default
to the CFQ scheduler which has a smoother writeout, plus you can give
your process a different IO scheduling class and level (see
Documentation/block/ioprio.txt).
Erik
next prev parent reply other threads:[~2006-12-18 13:18 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-12-18 4:07 Linux disk performance Manish Regmi
2006-12-18 8:35 ` Arjan van de Ven
2006-12-18 12:39 ` Manish Regmi
2006-12-18 12:54 ` Nick Piggin
2006-12-18 13:07 ` Erik Mouw [this message]
2006-12-19 6:22 ` Manish Regmi
2006-12-19 6:38 ` Nick Piggin
2006-12-19 12:18 ` Arjan van de Ven
2006-12-20 11:17 ` Manish Regmi
2006-12-22 0:14 ` Bhanu Kalyan Chetlapalli
2006-12-22 5:30 ` Manish Regmi
2006-12-22 5:39 ` Bhanu Kalyan Chetlapalli
2006-12-22 5:56 ` Manish Regmi
2006-12-20 22:29 ` Bill Davidsen
2006-12-21 6:03 ` Manish Regmi
2006-12-21 7:15 ` Daniel Cheng
2006-12-21 13:22 ` Erik Mouw
2006-12-22 5:39 ` Manish Regmi
2006-12-27 15:50 ` Phillip Susi
2007-01-01 1:59 ` Bill Davidsen
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=20061218130702.GA14984@gateway.home \
--to=mouw@nl.linux.org \
--cc=arjan@infradead.org \
--cc=kernelnewbies@nl.linux.org \
--cc=linux-kernel@vger.kernel.org \
--cc=regmi.manish@gmail.com \
/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