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 13:52:59 +0100
Message-ID: <20081125125259.GH6703@one.firstfloor.org>
References: <492AE8AC.2090502@cisco.com> <492B8204.5@cisco.com> <87d4gkcdsy.fsf@basil.nowhere.org> <426B9829-823B-40BE-9A7E-9F7EF2ED3412@suse.de> <20081125114815.GG6703@one.firstfloor.org> <CC19AD88-0576-47B2-AC76-A51F317964BD@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]:56071 "EHLO
	one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1752058AbYKYMmj (ORCPT <rfc822;kvm@vger.kernel.org>);
	Tue, 25 Nov 2008 07:42:39 -0500
Content-Disposition: inline
In-Reply-To: <CC19AD88-0576-47B2-AC76-A51F317964BD@suse.de>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

> But yeah - the remapping of HPET timers to virtual HPET timers sounds  
> pretty tough. I wonder if one could overcome that with a little  
> hardware support though ...

For gettimeofday better make TSC work. Even in the best case (no 
virtualization) it is much faster than HPET because it sits in the CPU,
while HPET is far away on the external south bridge.

For other HPET usages (interval timer etc.) which are less
performance critical I suppose vmexits are
not a serious problem so a standard software device model should work.

-Andi