public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Benjamin LaHaise <bcrl@redhat.com>
To: Linus Torvalds <torvalds@transmeta.com>
Cc: linux-kernel@vger.kernel.org, linux-aio@kvack.org
Subject: Re: patch: aio + bio for raw io
Date: Fri, 8 Feb 2002 19:01:17 -0500	[thread overview]
Message-ID: <20020208190117.A12959@redhat.com> (raw)
In-Reply-To: <20020208025313.A11893@redhat.com> <200202082107.g18L7wx26206@eng2.beaverton.ibm.com> <20020208171327.B12788@redhat.com> <200202082254.g18Mspq08299@penguin.transmeta.com>
In-Reply-To: <200202082254.g18Mspq08299@penguin.transmeta.com>; from torvalds@transmeta.com on Fri, Feb 08, 2002 at 02:54:51PM -0800

On Fri, Feb 08, 2002 at 02:54:51PM -0800, Linus Torvalds wrote:
> bio can handle arbitrarily large IO's, BUT it can never split them. 

I agree that it should not split ios, but it should not needlessly limit 
the size of them either -- that choice should be left to individual 
drivers.

...
> If you are in the small small _small_ minority care about 4MB requests,
> you should build the infrastructure not to make drivers split them, but
> to build up a list of bio's and then submit them all consecutively in
> one go.
> 
> Remember: checking the limits as you build stuff up is easy, and fast. 
> 
> So you should make sure that you never EVER cause anybody to want to
> split a bio. 

Yup.  What we need is an interface for getting the max size of an io -- 
I can see this being needed for filesystems, char devices, network drivers, 
basically anything that we can do aio/"direct" io on.  Given that, I can 
put the split / pipelining code into the generic layer.

		-ben

  parent reply	other threads:[~2002-02-09  0:01 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-02-08  7:53 patch: aio + bio for raw io Benjamin LaHaise
2002-02-08  9:40 ` Suparna Bhattacharya
2002-02-08 22:02   ` Benjamin LaHaise
2002-02-11 18:11     ` Suparna Bhattacharya
2002-02-08 21:07 ` Badari Pulavarty
2002-02-08 21:18   ` arjan
2002-02-08 22:13   ` Benjamin LaHaise
2002-02-08 22:54     ` Linus Torvalds
     [not found]     ` <200202082254.g18Mspq08299@penguin.transmeta.com>
2002-02-09  0:01       ` Benjamin LaHaise [this message]
2002-02-09  0:25         ` Linus Torvalds
2002-02-14  4:46           ` Suparna Bhattacharya
2002-02-11 11:09     ` Jens Axboe
2002-02-11 21:37 ` Badari Pulavarty

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=20020208190117.A12959@redhat.com \
    --to=bcrl@redhat.com \
    --cc=linux-aio@kvack.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@transmeta.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