qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: John Coiner <jcoiner@stanfordalumni.org>
To: qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [patch] non-blocking disk IO
Date: Mon, 03 Oct 2005 18:29:39 -0400	[thread overview]
Message-ID: <4341B0D3.7050804@stanfordalumni.org> (raw)
In-Reply-To: <20051003135837.GC3511@suse.de>



Jens Axboe wrote:
  > Why not use aio for this instead, seems like a better fit than spawning
> a thread per block device? That would still require a thread for
> handling completions, but you could easily just use a single completion
> thread for all devices for this as it would not need to do any real
> work.

Pthreads vs. AIO is an open question.

The pthreads implementation works with all disk image formats, without 
modifying any format-specific code. To use AIO, each image format driver 
would have to be modified.

QEMU already uses pthreads, therefore using pthreads does not add a new 
dependency on the host platform. (Or so I thought. The build on Windows 
broke anyway. Haha... my bad...)

My questions are:
  * Which QEMU host platforms support Posix AIO?
  * Which host platform has the slowest pthreads library, and how many 
cycles will it waste on pthreads overhead?
  * What is the likely performance benefit of using AIO?

When I have time, I'll hack AIO into the "raw" image driver, and take 
some benchmarks on a linux host.

Thanks.

-John

  reply	other threads:[~2005-10-03 22:33 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-10-03  6:49 [Qemu-devel] [patch] non-blocking disk IO John Coiner
2005-10-03  7:09 ` Magnus Damm
2005-10-03  9:57 ` Elefterios Stamatogiannakis
2005-10-03 12:58   ` Christian MICHON
2005-10-04  7:17     ` John Coiner
2005-10-04  7:46       ` Christian MICHON
2005-10-04  8:52       ` Elefterios Stamatogiannakis
2005-10-04  9:35         ` Christian MICHON
2005-10-04 11:19           ` Christian MICHON
2005-10-04 12:22             ` Jens Axboe
2005-10-04 13:14             ` John Coiner
2005-10-04 13:20               ` Christian MICHON
2005-10-03 13:58 ` Jens Axboe
2005-10-03 22:29   ` John Coiner [this message]
2005-10-04  6:41     ` Jens Axboe
2005-10-04  1:35   ` Troy Benjegerdes
2005-10-04  3:25     ` John Coiner
2005-10-04  3:49     ` Henrik Nordstrom
2005-10-04  5:24       ` Troy Benjegerdes
2005-10-04  6:44         ` Jens Axboe
2005-10-03 18:33 ` Fabrice Bellard
2005-10-04 20:40 ` Brad Campbell
2005-10-04 23:03   ` John Coiner
2005-10-05 11:27     ` Brad Campbell
2005-10-05 14:28       ` Troy Benjegerdes
2005-11-28 22:41         ` Ryan Rempel
  -- strict thread matches above, loose matches on Subject: below --
2005-10-03 12:41 John Coiner
2005-10-04  1:34 ` Troy Benjegerdes
2005-10-04  3:16   ` John Coiner
2005-10-04 14:26     ` Troy Benjegerdes
2005-10-04 22:11       ` John Coiner
2005-10-05  3:17         ` Troy Benjegerdes

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=4341B0D3.7050804@stanfordalumni.org \
    --to=jcoiner@stanfordalumni.org \
    --cc=qemu-devel@nongnu.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;
as well as URLs for NNTP newsgroup(s).