From mboxrd@z Thu Jan  1 00:00:00 1970
From: Avi Kivity <avi@redhat.com>
Subject: Re: [PATCH] IO: Intelligent device lookup on bus
Date: Thu, 21 Jul 2011 13:05:55 +0300
Message-ID: <4E27FA03.2070006@redhat.com>
References: <1311163918-14334-1-git-send-email-levinsasha928@gmail.com>	 <20110720194149.GA21379@amt.cnet> <1311196929.21614.5.camel@lappy>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Cc: Marcelo Tosatti <mtosatti@redhat.com>, kvm@vger.kernel.org
To: Sasha Levin <levinsasha928@gmail.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:33499 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1752153Ab1GUKGA (ORCPT <rfc822;kvm@vger.kernel.org>);
	Thu, 21 Jul 2011 06:06:00 -0400
In-Reply-To: <1311196929.21614.5.camel@lappy>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On 07/21/2011 12:22 AM, Sasha Levin wrote:
> >
> >  Some numbers, please.
> >
>
> I'm not sure how to measure performance in this case. You'd need to
> measure access times to each device before and after the patch, and
> average them.
>

Try registering ~100 PIO ioeventfds, and writing a test case which 
accesses a PIO port that misses all of them, in a loop.  Measure your 
exit rate before an after.

-- 
error compiling committee.c: too many arguments to function