From mboxrd@z Thu Jan  1 00:00:00 1970
From: Avi Kivity <avi@redhat.com>
Subject: Re: assign-dev: Purpose of interrupt_work
Date: Mon, 12 Oct 2009 11:07:18 +0200
Message-ID: <4AD2F1C6.8030407@redhat.com>
References: <4AD2D4B6.7030203@web.de> <20091012071310.GT16702@redhat.com> <4AD2DA57.6030006@web.de> <20091012074513.GV16702@redhat.com> <4AD2DFE2.4050406@web.de> <4AD2EB2D.5080909@redhat.com> <20091012090509.GZ16702@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Cc: Jan Kiszka <jan.kiszka@web.de>, kvm-devel <kvm@vger.kernel.org>
To: Gleb Natapov <gleb@redhat.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:40353 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1754846AbZJLJHq (ORCPT <rfc822;kvm@vger.kernel.org>);
	Mon, 12 Oct 2009 05:07:46 -0400
In-Reply-To: <20091012090509.GZ16702@redhat.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On 10/12/2009 11:05 AM, Gleb Natapov wrote:
>
>> I'm worried about disabling irqs for non-device-assignment cases.
>> It would be more palatable if ioapic was completely O(1) (there are
>> some per-vcpu loops in there, shouldn't be too bad for 16 vcpus, but
>> we want to scale).
>>
>>      
> We can change it to hash for directed irqs (still not O(1)),

Or cache the vcpu pointer in the redirection table entry.

> but for
> broadcast irq the loop will be required.
>    

That's fine, those are rare.

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