From: Paul Brook <paul@codesourcery.com>
To: Rik van Riel <riel@redhat.com>
Cc: qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [RFC][PATCH] make sure disk writes actually hit disk
Date: Sat, 29 Jul 2006 17:31:36 +0100 [thread overview]
Message-ID: <200607291731.36528.paul@codesourcery.com> (raw)
In-Reply-To: <44CB8B35.5090405@redhat.com>
> Easy to do with the fsync infrastructure, but probably not worth
> doing since people are working on the AIO I/O backend, which would
> allow multiple outstanding writes from a guest. That, in turn,
> means I/O completion in the guest can be done when the data really
> hits disk, but without a performance impact.
Not entirely true. That only works if you allow multiple guest IO requests in
parallel, ie. some form of tagged command queueing. This requires either
improving the SCSI emulation, or implementing SATA emulation. AFAIK parallel
IDE doesn't support command queueing.
My impression what that the initial AIO implementation is just straight serial
async operation. IO wouldn't actually go any faster, it just means the guest
can do something else while it's waiting.
Paul
next prev parent reply other threads:[~2006-07-29 16:31 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-07-28 19:54 [Qemu-devel] [RFC][PATCH] make sure disk writes actually hit disk Rik van Riel
2006-07-28 19:58 ` [Qemu-devel] " Rik van Riel
2006-07-28 20:12 ` Anthony Liguori
2006-07-28 20:18 ` Rik van Riel
2006-07-28 20:30 ` Paul Brook
2006-07-28 20:43 ` Rik van Riel
2006-07-28 21:01 ` Paul Brook
2006-07-31 7:08 ` Jens Axboe
2006-07-29 9:57 ` [Qemu-devel] " Fabrice Bellard
2006-07-29 14:59 ` Rik van Riel
2006-07-29 16:04 ` Paul Brook
2006-07-29 16:22 ` Rik van Riel
2006-07-29 16:31 ` Paul Brook [this message]
2006-07-31 7:08 ` Jens Axboe
2006-07-29 17:33 ` Bill C. Riemers
2006-07-30 21:47 ` Jamie Lokier
2006-07-30 21:41 ` Jamie Lokier
2006-07-31 9:52 ` andrzej zaborowski
2006-07-31 10:17 ` Jens Axboe
2006-07-31 17:50 ` andrzej zaborowski
2006-07-31 7:08 ` Jens Axboe
2006-07-31 7:56 ` Jonas Maebe
2006-07-31 8:18 ` Jens Axboe
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=200607291731.36528.paul@codesourcery.com \
--to=paul@codesourcery.com \
--cc=qemu-devel@nongnu.org \
--cc=riel@redhat.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;
as well as URLs for NNTP newsgroup(s).