linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@suse.de>
To: Werner Almesberger <wa@almesberger.net>
Cc: linux-fsdevel@vger.kernel.org
Subject: Re: elevator priorities vs. full request queues
Date: Tue, 13 Jul 2004 18:59:07 +0200	[thread overview]
Message-ID: <20040713165906.GB29655@suse.de> (raw)
In-Reply-To: <20040713133632.B1795@almesberger.net>

On Tue, Jul 13 2004, Werner Almesberger wrote:
> Jens Axboe wrote:
> > It's just that if default io prio was something other than 0, then it
> > would make sense to set it there.
> 
> Oh, I see. Yes, of course. It actually does this, implicitly,
> since the default value of zero just happens to be what bio_init
> sets already ;-)

Only if you define 0 to be the default value :-)

> > But I suppose you just want io submission to set it, in which case it
> > doesn't matter what bio_init() sets it to.
> 
> Except for those bios that get submitted without ever touching
> submit_bh.

You mean things like bio_map_user/bio_copy_user and (at the other end,
doubt these would count), bios submitted privately to the drive itself
(ala ide-scsi)? The latter can be disregarded imho, nothing to worry
about. The former allocate requests on its own, so you must pass in the
priority there. So instead of assigning bio priority and using that for
request allocation, you are just a step or two further down in the call
chain and specify the priority there directly.

In short, I don't see a problem there.

-- 
Jens Axboe


      reply	other threads:[~2004-07-13 16:59 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-06-22  4:25 elevator priorities vs. full request queues Werner Almesberger
2004-06-22  7:48 ` Jens Axboe
2004-06-22  8:26   ` Werner Almesberger
2004-06-22 10:14     ` Jens Axboe
2004-06-22 19:08       ` Werner Almesberger
2004-06-23 10:14         ` Jens Axboe
2004-06-23 12:46           ` Werner Almesberger
2004-06-23 16:46             ` Jens Axboe
2004-06-23 16:57               ` Werner Almesberger
2004-06-23 17:00                 ` Jens Axboe
2004-06-23 23:02                   ` Werner Almesberger
2004-07-12 23:52           ` Werner Almesberger
2004-07-13  5:37             ` Jens Axboe
2004-07-13 12:29               ` Werner Almesberger
2004-07-13 12:35                 ` Jens Axboe
2004-07-13 16:36                   ` Werner Almesberger
2004-07-13 16:59                     ` Jens Axboe [this message]

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=20040713165906.GB29655@suse.de \
    --to=axboe@suse.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=wa@almesberger.net \
    /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;
as well as URLs for NNTP newsgroup(s).