From mboxrd@z Thu Jan  1 00:00:00 1970
From: Andi Kleen <andi@firstfloor.org>
Subject: Re: gettimeofday "slow" in RHEL4 guests
Date: Tue, 25 Nov 2008 12:48:15 +0100
Message-ID: <20081125114815.GG6703@one.firstfloor.org>
References: <492AE8AC.2090502@cisco.com> <492B8204.5@cisco.com> <87d4gkcdsy.fsf@basil.nowhere.org> <426B9829-823B-40BE-9A7E-9F7EF2ED3412@suse.de>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Andi Kleen <andi@firstfloor.org>,
	"David S. Ahern" <daahern@cisco.com>,
	kvm-devel <kvm@vger.kernel.org>,
	Marcelo Tosatti <mtosatti@redhat.com>,
	Glauber de Oliveira Costa <gcosta@redhat.com>,
	Avi Kivity <avi@redhat.com>
To: Alexander Graf <agraf@suse.de>
Return-path: <kvm-owner@vger.kernel.org>
Received: from one.firstfloor.org ([213.235.205.2]:42517 "EHLO
	one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1752723AbYKYLhz (ORCPT <rfc822;kvm@vger.kernel.org>);
	Tue, 25 Nov 2008 06:37:55 -0500
Content-Disposition: inline
In-Reply-To: <426B9829-823B-40BE-9A7E-9F7EF2ED3412@suse.de>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

> Why does hpet need to be slow? Can't you just 1:1 pass through one of  
> the hpet timers if you only have a limited amount of vms?

HPET is not a truly virtualizable device, it's all the counters
in one block that cannot be really mapped to different people.

Also most systems have very little counters and Linux typically needs two
at least (system timer and /dev/hpet)

> If done cleverly this might even work if #hpet > #cpu.

Sure with a device model, but that needs vmexits.

-Andi