From mboxrd@z Thu Jan  1 00:00:00 1970
From: Avi Kivity <avi@redhat.com>
Subject: Re: vmexit cycle cost
Date: Sun, 18 Nov 2012 16:16:37 +0200
Message-ID: <50A8EDC5.7010709@redhat.com>
References: <CAEDV+gKNOXx-5E-U_dCdem=VrkK-gE8j4nt-RScg0Rxq1K-6qw@mail.gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Cc: KVM General <kvm@vger.kernel.org>
To: Christoffer Dall <cdall@cs.columbia.edu>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:20737 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1751954Ab2KROQp (ORCPT <rfc822;kvm@vger.kernel.org>);
	Sun, 18 Nov 2012 09:16:45 -0500
In-Reply-To: <CAEDV+gKNOXx-5E-U_dCdem=VrkK-gE8j4nt-RScg0Rxq1K-6qw@mail.gmail.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On 11/16/2012 06:56 PM, Christoffer Dall wrote:
> Hi all,
> 
> just a quick question: using the kvm-unittest vmexit test, it seems
> using a VMCALL for exit, a round-trip to the host takes roughly 1000
> cycles on a modern processor. This number sounds quite low to me. Can
> anyone verify if it's reasonable or have more data on this number has
> developed over time given newer processors?

It's reasonable, not low (this number can never be low enough).


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