From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754577AbaHUUcA (ORCPT ); Thu, 21 Aug 2014 16:32:00 -0400 Received: from mail-wg0-f47.google.com ([74.125.82.47]:53189 "EHLO mail-wg0-f47.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754015AbaHUUb6 (ORCPT ); Thu, 21 Aug 2014 16:31:58 -0400 Message-ID: <53F65738.10000@redhat.com> Date: Thu, 21 Aug 2014 22:31:52 +0200 From: Paolo Bonzini User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.7.0 MIME-Version: 1.0 To: Raghavendra K T , =?UTF-8?B?UmFkaW0=?= =?UTF-8?B?IEtyxI1tw6HFmQ==?= CC: kvm@vger.kernel.org, linux-kernel@vger.kernel.org, Gleb Natapov , Vinod Chegu , Hui-Zhi Zhao , Christian Borntraeger , Lisa Mitchell Subject: Re: [PATCH v3 4/7] KVM: VMX: dynamise PLE window References: <1408637291-18533-1-git-send-email-rkrcmar@redhat.com> <1408637291-18533-5-git-send-email-rkrcmar@redhat.com> <53F6440B.8010709@linux.vnet.ibm.com> In-Reply-To: <53F6440B.8010709@linux.vnet.ibm.com> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Il 21/08/2014 21:10, Raghavendra K T ha scritto: > 2. can we consider min_ple_window value of 2k. tracing showed that in > overcommit there were several occations of 4k <- 4k situations. Yes, that could be good now that we have adaptive exits. Perhaps even 1k. > 3. Do you think using ( << and >> ) instead of (*, /) saves some cycles > considering we could have potentially have grow,shrink numbers != power > of 2 * is very fast. / a bit less so but it never occurs with the defaults. So I think it's okay. I'm not sure why one would use a multiplier bigger than 2. Paolo