From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S935155AbcJUPMZ (ORCPT ); Fri, 21 Oct 2016 11:12:25 -0400 Received: from shards.monkeyblade.net ([184.105.139.130]:56008 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932934AbcJUPMW (ORCPT ); Fri, 21 Oct 2016 11:12:22 -0400 Date: Fri, 21 Oct 2016 11:12:19 -0400 (EDT) Message-Id: <20161021.111219.988688105971081562.davem@davemloft.net> To: borntraeger@de.ibm.com Cc: peterz@infradead.org, npiggin@gmail.com, linux-kernel@vger.kernel.org, linux-s390@vger.kernel.org, linux-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, heiko.carstens@de.ibm.com, schwidefsky@de.ibm.com, noamc@ezchip.com, virtualization@lists.linux-foundation.org, xen-devel@lists.xenproject.org, kvm@vger.kernel.org Subject: Re: [PATCH/RFC 0/5] cpu_relax: introduce yield, remove lowlatency From: David Miller In-Reply-To: <2cf23cb7-05c5-0a2d-2ed5-aa90d582f802@de.ibm.com> References: <1477051138-1610-1-git-send-email-borntraeger@de.ibm.com> <20161021.105727.140184460493941551.davem@davemloft.net> <2cf23cb7-05c5-0a2d-2ed5-aa90d582f802@de.ibm.com> X-Mailer: Mew version 6.7 on Emacs 24.5 / Mule 6.0 (HANACHIRUSATO) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.5.12 (shards.monkeyblade.net [149.20.54.216]); Fri, 21 Oct 2016 08:12:21 -0700 (PDT) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Christian Borntraeger Date: Fri, 21 Oct 2016 17:08:54 +0200 > On 10/21/2016 04:57 PM, David Miller wrote: >> From: Christian Borntraeger >> Date: Fri, 21 Oct 2016 13:58:53 +0200 >> >>> For spinning loops people did often use barrier() or cpu_relax(). >>> For most architectures cpu_relax and barrier are the same, but on >>> some architectures cpu_relax can add some latency. For example on s390 >>> cpu_relax gives up the time slice to the hypervisor. On power cpu_relax >>> tries to give some of the CPU to the neighbor threads. To reduce the >>> latency another variant cpu_relax_lowlatency was introduced. Before this >>> is used in more and more places, lets revert the logic of provide a new >>> function cpu_relax_yield that can spend some time and for s390 yields >>> the guest CPU. >> >> Sparc64, fwiw, behaves similarly to powerpc. > > As sparc currently defines cpu_relax_lowlatency to cpu_relax, this patch set > should be a no-op then for sparc, correct? > > My intend was that cpu_relax should not add a huge latency but can certainly > push some cpu power to hardware threads of the same core. This seems to be > the case for sparc/power and some arc variants. Agreed.