From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 1/1] KVM: x86: avoid unnecessary bitmap allocation when memslot is clean Date: Wed, 28 Apr 2010 13:27:39 +0300 Message-ID: <4BD80D9B.3090102@redhat.com> References: <20100426185657.7f68c3ad.yoshikawa.takuya@oss.ntt.co.jp> <20100426185854.5d606a04.yoshikawa.takuya@oss.ntt.co.jp> <4BD6E412.7090202@redhat.com> <4BD6EACF.6070205@oss.ntt.co.jp> <4BD7B6F2.9010105@oss.ntt.co.jp> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: mtosatti@redhat.com, kvm@vger.kernel.org To: Takuya Yoshikawa Return-path: Received: from mx1.redhat.com ([209.132.183.28]:21426 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751006Ab0D1K1n (ORCPT ); Wed, 28 Apr 2010 06:27:43 -0400 In-Reply-To: <4BD7B6F2.9010105@oss.ntt.co.jp> Sender: kvm-owner@vger.kernel.org List-ID: On 04/28/2010 07:17 AM, Takuya Yoshikawa wrote: > (2010/04/27 22:46), Takuya Yoshikawa wrote: >> (2010/04/27 22:18), Avi Kivity wrote: >> >>>> Furthermore, the reduced allocations seem to produce good effects for >>>> other cases too. Actually, I observed that the time for the ioctl was >>>> more stable than the original one and the average time for dirty slots >>>> was also reduced by some extent. >>> >>> Can you explain why the dirty slots were improved? >> >> I cannot do exactly, but vmalloc() might affect the following >> allocations? >> > > > Oh, this might be the effect of tlb flush or something? > - I'm not so confident about mm, but vmalloc(),vfree() does this kind > of thing? Yes, vmalloc() does tlb flushes, perhaps that's the cause. -- error compiling committee.c: too many arguments to function