From mboxrd@z Thu Jan  1 00:00:00 1970
From: Michael Tokarev <mjt@tls.msk.ru>
Subject: Re: block virtio excessive VIRTIO_PCI_ISR reads
Date: Wed, 28 Oct 2009 17:59:33 +0300
Message-ID: <4AE85C55.7010806@msgid.tls.msk.ru>
References: <41be791c0910280740t7942bb7cj692ba54725bcc5eb@mail.gmail.com> <4AE859BD.106@codemonkey.ws>
Mime-Version: 1.0
Content-Type: text/plain; charset=windows-1252;
	format=flowed
Content-Transfer-Encoding: QUOTED-PRINTABLE
Cc: Saul Tamari <stamari@gmail.com>, kvm <kvm@vger.kernel.org>
To: Anthony Liguori <anthony@codemonkey.ws>
Return-path: <kvm-owner@vger.kernel.org>
Received: from isrv.corpit.ru ([81.13.33.159]:39143 "EHLO isrv.corpit.ru"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1752062AbZJ1O7b (ORCPT <rfc822;kvm@vger.kernel.org>);
	Wed, 28 Oct 2009 10:59:31 -0400
In-Reply-To: <4AE859BD.106@codemonkey.ws>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

Anthony Liguori wrote:
> Saul Tamari wrote:
>> Hi,
>>
>> There seems to be a bug in the VirtIO guest device driver (tested wi=
th
>> 2.6.31.5 kernel).
>> The bug causes frequent & excessive VIRTIO_PCI_ISR reads (causing PI=
O
>> vm-exits) for a device that is not being used.
>>
>> The setup I=92m using includes two VirtIO block devices =96 vda & vd=
b.
>> While running heavy IO on vdb I notice a lot of VIRTIO_PCI_ISR port
>> reads for the PIO ports of vda too.
>> For each vdb IO operation passed to the hypervisor by the virtio=20
>> driver I see:
>> 1. One VIRTIO_PCI_QUEUE_NOTIFY write on vdb
>> 2. One VIRTIO_PCI_ISR read on vdb
>> 3. One VIRTIO_PCI_ISR read on vda (while not explicitly using vda)
>=20
> That's because it's using a shared interrupt and each device needs to=
=20
> check whether it's got pending work to do.
>=20
> You can eliminate this by using MSI-x.

So the next question is how to use MSI-x.. ;)

Thanks!

/mjt