From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:50931)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <avi@cloudius-systems.com>) id 1XbozC-0005HN-9J
	for qemu-devel@nongnu.org; Wed, 08 Oct 2014 07:00:57 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <avi@cloudius-systems.com>) id 1Xboz4-0003uK-Ew
	for qemu-devel@nongnu.org; Wed, 08 Oct 2014 07:00:49 -0400
Received: from mail-wi0-f179.google.com ([209.85.212.179]:63757)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <avi@cloudius-systems.com>) id 1Xboz4-0003uG-A0
	for qemu-devel@nongnu.org; Wed, 08 Oct 2014 07:00:42 -0400
Received: by mail-wi0-f179.google.com with SMTP id d1so10321891wiv.12
	for <qemu-devel@nongnu.org>; Wed, 08 Oct 2014 04:00:41 -0700 (PDT)
Message-ID: <54351956.9030909@cloudius-systems.com>
Date: Wed, 08 Oct 2014 14:00:38 +0300
From: Avi Kivity <avi@cloudius-systems.com>
MIME-Version: 1.0
References: <542A6B70.7090607@huawei.com> <20140930093356.GA3673@redhat.com>
	<5434EB0B.8010800@cloudius-systems.com>
	<20141008091547.GB3872@redhat.com>
	<54350919.8050401@cloudius-systems.com>
	<20141008101443.GA4291@redhat.com>
	<543513E5.8010507@cloudius-systems.com>
	<20141008105515.GA4429@redhat.com>
In-Reply-To: <20141008105515.GA4429@redhat.com>
Content-Type: text/plain; charset=windows-1252; format=flowed
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [QA-virtio]:Why vring size is limited to 1024?
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: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>, qemu-devel@nongnu.org, liuyongan@huawei.com, qinchuanyu@huawei.com, "Zhangjie (HZ)" <zhangjie14@huawei.com>, akong@redhat.com


On 10/08/2014 01:55 PM, Michael S. Tsirkin wrote:
>
>> Inline descriptors will amortize the cache miss over 4 descriptors, and will
>> allow the hardware to prefetch, since the descriptors are linear in memory.
> If descriptors are used in order (as they are with current qemu)
> then aren't they amortized already?
>

The descriptors are only in-order for non-zero-copy net.  They are out 
of order for block and zero-copy net.

(also, the guest has to be careful in how it allocates descriptors).