From: Dave Chinner <david@fromorbit.com>
To: Aaron Carroll <aaronc@gelato.unsw.edu.au>
Cc: Bodo Eggert <7eggert@gmx.de>, Jens Axboe <jens.axboe@oracle.com>,
Andi Kleen <andi@firstfloor.org>,
Andrew Morton <akpm@linux-foundation.org>,
Arjan van de Ven <arjan@infradead.org>,
linux-kernel@vger.kernel.org, Alan Cox <alan@lxorguk.ukuu.org.uk>
Subject: Re: [PATCH] Give kjournald a IOPRIO_CLASS_RT io priority
Date: Mon, 6 Oct 2008 14:18:29 +1100 [thread overview]
Message-ID: <20081006031829.GQ30001@disturbed> (raw)
In-Reply-To: <48E71EFC.7040403@gelato.unsw.edu.au>
On Sat, Oct 04, 2008 at 05:45:00PM +1000, Aaron Carroll wrote:
> Dave Chinner wrote:
>> On Thu, Oct 02, 2008 at 05:32:04PM +0200, Bodo Eggert wrote:
>>> Sounds like you need a priority class besides sync and async.
>>
>> There's BIO_META now as well, which I was testing at the same time
>> as RT priority. Marking all the metadata I/O as BIO_META did help,
>> but once again I never got to determining if that was a result of
>> the different tagging or the priority increase.
>
> What exactly do you want META to mean? Strict prioritisation over
> all other non-META requests, or just more frequent and/or larger
> dispatches? Should META requests be sorted?
The real question is "what was it supposed to mean"? AFAICT, it was
added to a couple of filesystems to be used to tag superblock read
I/O. Why - I don't know - there's a distinct lack of documentation
surrounding these bio flags. :/
Realistically, I'm not sure that having a separate queue for
BIO_META will buy us anything, given that noop is quite often the
fastest scheduler for XFS because it enables interleaved metadata
I/O to be merged with data I/O. Like I said, I was not able to spend
the time to determine exactly how BIO_META affected I/O patterns, so
I can't really comment on whether it is really necessary or not.
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
next prev parent reply other threads:[~2008-10-06 3:47 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <bimJN-4cO-5@gated-at.bofh.it>
[not found] ` <biosl-6bq-9@gated-at.bofh.it>
[not found] ` <biqkw-aK-3@gated-at.bofh.it>
[not found] ` <birgx-1pQ-9@gated-at.bofh.it>
[not found] ` <bisPe-3xx-9@gated-at.bofh.it>
[not found] ` <bisYW-3HQ-13@gated-at.bofh.it>
2008-10-02 15:32 ` [PATCH] Give kjournald a IOPRIO_CLASS_RT io priority Bodo Eggert
2008-10-02 23:34 ` Dave Chinner
2008-10-04 7:45 ` Aaron Carroll
2008-10-06 3:18 ` Dave Chinner [this message]
2008-10-07 18:06 ` Jens Axboe
2008-10-07 22:22 ` Dave Chinner
2008-10-09 8:48 ` Jens Axboe
2008-10-02 3:00 Arjan van de Ven
2008-10-02 4:56 ` Andrew Morton
2008-10-02 6:27 ` Jens Axboe
2008-10-02 6:55 ` Andrew Morton
2008-10-02 7:45 ` Jens Axboe
2008-10-02 8:03 ` Andrew Morton
2008-10-02 8:22 ` Jens Axboe
2008-10-02 8:43 ` Andrew Morton
2008-10-02 8:46 ` Jens Axboe
2008-10-02 12:04 ` Theodore Tso
2008-10-02 13:16 ` Arjan van de Ven
2008-10-02 13:46 ` Theodore Tso
2008-10-02 14:33 ` Arjan van de Ven
2008-10-04 14:12 ` Theodore Tso
2008-10-04 17:14 ` Joseph Fannin
2008-10-04 21:27 ` Theodore Tso
2008-10-02 13:12 ` Arjan van de Ven
2008-10-02 20:24 ` Andrew Morton
2008-10-03 4:01 ` Arjan van de Ven
2008-10-03 4:23 ` Arjan van de Ven
2008-10-03 4:40 ` Andrew Morton
2008-10-03 4:43 ` Arjan van de Ven
2008-10-03 4:50 ` Andrew Morton
2008-10-03 5:00 ` Arjan van de Ven
2008-10-03 5:24 ` Andrew Morton
2008-10-03 17:21 ` Arjan van de Ven
2008-10-09 3:00 ` Theodore Tso
2008-10-09 3:38 ` Andrew Morton
2008-10-03 4:45 ` Arjan van de Ven
2008-10-02 6:57 ` Andi Kleen
2008-10-02 7:55 ` Jens Axboe
2008-10-02 9:33 ` Dave Chinner
2008-10-02 9:45 ` Jens Axboe
2008-10-02 13:14 ` Arjan van de Ven
2008-10-02 13:27 ` Jens Axboe
2008-10-02 13:36 ` Arjan van de Ven
2008-10-02 13:47 ` Jens Axboe
2008-10-02 14:26 ` Arjan van de Ven
2008-10-02 16:42 ` Jens Axboe
2008-10-02 19:04 ` Arjan van de Ven
2008-10-02 19:22 ` Jens Axboe
2008-10-02 21:37 ` Andrew Morton
2008-10-02 23:58 ` Dave Chinner
2008-10-03 0:06 ` Andrew Morton
2008-10-03 0:20 ` Andrew Morton
2008-10-02 13:05 ` Arjan van de Ven
2008-10-02 17:11 ` Jens Axboe
-- strict thread matches above, loose matches on Subject: below --
2007-10-15 17:46 [patch] " Arjan van de Ven
2007-10-15 18:47 ` Andrew Morton
2007-10-15 19:28 ` Jens Axboe
2007-10-22 9:10 ` Ingo Molnar
2007-10-22 9:23 ` Andrew Morton
2007-10-22 9:27 ` Ingo Molnar
2007-10-22 9:40 ` Ingo Molnar
2007-10-22 9:49 ` Andrew Morton
2007-10-15 20:13 ` Rik van Riel
2007-10-15 21:12 ` Andrew Morton
[not found] ` <473B18BA.5000709@hp.com>
2007-11-14 17:14 ` Andrew Morton
2007-11-14 17:18 ` Ingo Molnar
2007-11-14 17:51 ` Arjan van de Ven
2007-11-14 18:55 ` Ingo Molnar
2007-11-14 19:43 ` Alan D. Brunelle
2007-11-14 19:24 ` Alan D. Brunelle
2007-11-14 19:50 ` Arjan van de Ven
2007-11-14 19:56 ` Alan D. Brunelle
2007-11-16 16:25 ` Alan D. Brunelle
2007-11-16 16:40 ` Alan D. Brunelle
2007-11-16 18:35 ` Ray Lee
2007-11-16 18:39 ` Alan D. Brunelle
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=20081006031829.GQ30001@disturbed \
--to=david@fromorbit.com \
--cc=7eggert@gmx.de \
--cc=aaronc@gelato.unsw.edu.au \
--cc=akpm@linux-foundation.org \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=andi@firstfloor.org \
--cc=arjan@infradead.org \
--cc=jens.axboe@oracle.com \
--cc=linux-kernel@vger.kernel.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