From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43)
	id 1LASAR-0001sB-Jx
	for qemu-devel@nongnu.org; Wed, 10 Dec 2008 11:44:07 -0500
Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43)
	id 1LASAQ-0001rz-Tj
	for qemu-devel@nongnu.org; Wed, 10 Dec 2008 11:44:07 -0500
Received: from [199.232.76.173] (port=57643 helo=monty-python.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1LASAQ-0001rw-NZ
	for qemu-devel@nongnu.org; Wed, 10 Dec 2008 11:44:06 -0500
Received: from mx2.redhat.com ([66.187.237.31]:52768)
	by monty-python.gnu.org with esmtp (Exim 4.60)
	(envelope-from <aarcange@redhat.com>) id 1LASAQ-00063r-9r
	for qemu-devel@nongnu.org; Wed, 10 Dec 2008 11:44:06 -0500
Date: Wed, 10 Dec 2008 17:44:01 +0100
From: Andrea Arcangeli <aarcange@redhat.com>
Subject: Re: [Qemu-devel] [RFC] Replace posix-aio with custom thread pool
Message-ID: <20081210164401.GF18814@random.random>
References: <1228512061-25398-1-git-send-email-aliguori@us.ibm.com>
	<493E941D.4000608@redhat.com> <493E965E.5050701@us.ibm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <493E965E.5050701@us.ibm.com>
Reply-To: qemu-devel@nongnu.org
List-Id: qemu-devel.nongnu.org
List-Unsubscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.gnu.org/pipermail/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: qemu-devel@nongnu.org
Cc: Gerd Hoffmann <kraxel@redhat.com>, kvm-devel <kvm@vger.kernel.org>

On Tue, Dec 09, 2008 at 10:01:34AM -0600, Anthony Liguori wrote:
> Yes, that's what I'm going to do before committing it.

I've been hacking on this too, just to push out a full tested patchset
without the _em badness... problem is if we use more than one thread,
there's a thread race between lseek and writev, pread/pwrite don't
have the issue as they store the pos on the kernel stack, and they
don't pass through the shared file->f_pos. We'd really need
preadv/pwritev...

To solve this in userland without kernel aio we'd need to open (not
just dup) the file in each thread, then the file->f_pos will become
thread local and we can cache the last lseek value and avoid the lseek
syscall for contiguous I/O. Or we need to reduce the number of threads
to 1 per fd (screwing seeking I/O). kernel aio wouldn't have this
trouble and a single fd/file would be enough, but that would only work
on linux.