From: Stefan Hajnoczi <stefanha@gmail.com>
To: Antoine Martin <antoine@nagafix.co.uk>
Cc: Avi Kivity <avi@redhat.com>, Michael Tokarev <mjt@tls.msk.ru>,
Christoph Hellwig <hch@infradead.org>,
kvm@vger.kernel.org
Subject: Re: raw disks no longer work in latest kvm (kvm-88 was fine)
Date: Sat, 29 May 2010 10:55:18 +0100 [thread overview]
Message-ID: <AANLkTikL_3uDvel-bcwslgElk27ly3Sz9cH3JyPwSaDD@mail.gmail.com> (raw)
In-Reply-To: <4C00E1A3.50109@nagafix.co.uk>
On Sat, May 29, 2010 at 10:42 AM, Antoine Martin <antoine@nagafix.co.uk> wrote:
> Can someone explain the aio options?
> All I can find is this:
> # qemu-system-x86_64 -h | grep -i aio
> [,addr=A][,id=name][,aio=threads|native]
> I assume it means the aio=threads emulates the kernel's aio with
> separate threads? And is therefore likely to be slower, right?
> Is there a reason why aio=native is not the default? Shouldn't
> aio=threads be the fallback?
aio=threads uses posix-aio-compat.c, a POSIX AIO-like implementation
using a thread pool. Each thread services queued I/O requests using
blocking syscalls (e.g. preadv()/pwritev()).
aio=native uses Linux libaio, the native (non-POSIX) AIO interface.
I would expect that aio=native is faster but benchmarks show that this
isn't true for all workloads.
Stefan
next prev parent reply other threads:[~2010-05-29 9:55 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-03-06 20:48 raw disks no longer work in latest kvm (kvm-88 was fine) Antoine Martin
2010-03-06 21:28 ` Michael Tokarev
2010-03-07 4:14 ` Antoine Martin
2010-03-07 9:32 ` Michael Tokarev
2010-03-07 10:00 ` Christoph Hellwig
2010-03-07 13:12 ` Antoine Martin
2010-03-07 13:52 ` Antoine Martin
2010-03-07 15:15 ` Michael Tokarev
2010-03-07 17:11 ` Antoine Martin
2010-03-07 17:18 ` Avi Kivity
2010-03-07 17:21 ` Christoph Hellwig
2010-03-07 17:30 ` Avi Kivity
2010-03-07 17:34 ` Christoph Hellwig
2010-03-07 18:43 ` raw disks no longer work in latest kvm (kvm-88 was fine) [SOLVED] Antoine Martin
2010-03-07 18:55 ` Avi Kivity
2010-03-07 18:01 ` raw disks no longer work in latest kvm (kvm-88 was fine) Antoine Martin
2010-03-07 18:47 ` Avi Kivity
2010-03-07 19:07 ` Antoine Martin
2010-03-07 19:10 ` Avi Kivity
2010-03-07 19:13 ` Antoine Martin
2010-03-07 19:17 ` Avi Kivity
2010-03-07 19:25 ` Antoine Martin
2010-03-07 19:35 ` Avi Kivity
2010-03-13 9:51 ` Antoine Martin
2010-03-14 7:34 ` Avi Kivity
2010-04-08 22:00 ` Antoine Martin
2010-05-22 10:44 ` Antoine Martin
2010-05-22 11:17 ` Michael Tokarev
2010-05-22 11:35 ` Antoine Martin
2010-05-23 8:53 ` Antoine Martin
2010-05-23 11:57 ` Avi Kivity
2010-05-23 14:07 ` Antoine Martin
2010-05-23 14:18 ` Avi Kivity
2010-05-23 14:43 ` Antoine Martin
2010-05-23 14:53 ` Antoine Martin
2010-05-23 14:56 ` Avi Kivity
2010-05-23 15:06 ` Antoine Martin
2010-05-23 15:12 ` Avi Kivity
2010-05-23 16:18 ` Antoine Martin
2010-05-23 17:47 ` Stefan Hajnoczi
2010-05-29 9:42 ` Antoine Martin
2010-05-29 9:55 ` Stefan Hajnoczi [this message]
2010-05-29 10:34 ` Christoph Hellwig
2010-05-29 11:06 ` Stefan Hajnoczi
2010-05-29 10:34 ` Christoph Hellwig
2010-03-07 19:09 ` Asdo
2010-03-07 19:11 ` Antoine Martin
2010-03-07 19:12 ` Avi Kivity
2010-03-07 16:21 ` Avi Kivity
2010-03-08 16:45 ` Anthony Liguori
2010-03-07 9:36 ` Gleb Natapov
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=AANLkTikL_3uDvel-bcwslgElk27ly3Sz9cH3JyPwSaDD@mail.gmail.com \
--to=stefanha@gmail.com \
--cc=antoine@nagafix.co.uk \
--cc=avi@redhat.com \
--cc=hch@infradead.org \
--cc=kvm@vger.kernel.org \
--cc=mjt@tls.msk.ru \
/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).