From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([208.118.235.92]:51245)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1TTYkd-0008Lg-4q
	for qemu-devel@nongnu.org; Wed, 31 Oct 2012 09:54:39 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1TTYkc-0003sE-5A
	for qemu-devel@nongnu.org; Wed, 31 Oct 2012 09:54:35 -0400
Received: from mx1.redhat.com ([209.132.183.28]:4375)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1TTYkb-0003s6-T4
	for qemu-devel@nongnu.org; Wed, 31 Oct 2012 09:54:34 -0400
Message-ID: <509127DC.5000707@redhat.com>
Date: Wed, 31 Oct 2012 14:30:04 +0100
From: Paolo Bonzini <pbonzini@redhat.com>
MIME-Version: 1.0
References: <1351688609-18984-1-git-send-email-stefanha@redhat.com>
In-Reply-To: <1351688609-18984-1-git-send-email-stefanha@redhat.com>
Content-Type: text/plain; charset=ISO-8859-15
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [PATCH] aio: Use g_slice_alloc() for AIOCB pooling
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>, Anthony Liguori <aliguori@us.ibm.com>, qemu-devel@nongnu.org

Il 31/10/2012 14:03, Stefan Hajnoczi ha scritto:
> AIO control blocks are frequently acquired and released because each aio
> request involves at least one AIOCB.  Therefore pool them to avoid heap
> allocation overhead.
> 
> The problem with the freelist approach in AIOPool is thread-safety.  If
> we want BlockDriverStates to associate with AioContexts that execute in
> multiple threads, then a global freelist becomes a problem.
> 
> This patch drops the freelist and instead uses g_slice_alloc() which is
> tuned for per-thread fixed-size object pools.  qemu_aio_get() and
> qemu_aio_release() are now thread-safe.
> 
> Note that the change from g_malloc0() to g_slice_alloc() should be safe
> since the freelist reuse case doesn't zero the AIOCB either.
> 
> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

Good idea, should of course be split in multiple patches. :)

Paolo