From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751605AbdFAIqP (ORCPT ); Thu, 1 Jun 2017 04:46:15 -0400 Received: from mx2.suse.de ([195.135.220.15]:42580 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751404AbdFAIqN (ORCPT ); Thu, 1 Jun 2017 04:46:13 -0400 Date: Thu, 1 Jun 2017 10:46:09 +0200 From: Michal Hocko To: Pasha Tatashin Cc: linux-kernel@vger.kernel.org, sparclinux@vger.kernel.org, linux-mm@kvack.org, linuxppc-dev@lists.ozlabs.org, linux-s390@vger.kernel.org, borntraeger@de.ibm.com, heiko.carstens@de.ibm.com, davem@davemloft.net Subject: Re: [v3 0/9] parallelized "struct page" zeroing Message-ID: <20170601084609.GF32677@dhcp22.suse.cz> References: <20170509181234.GA4397@dhcp22.suse.cz> <20170515193817.GC7551@dhcp22.suse.cz> <9b3d68aa-d2b6-2b02-4e75-f8372cbeb041@oracle.com> <20170516083601.GB2481@dhcp22.suse.cz> <07a6772b-711d-4fdc-f688-db76f1ec4c45@oracle.com> <20170529115358.GJ19725@dhcp22.suse.cz> <20170531163131.GY27783@dhcp22.suse.cz> <2fa60098-d9be-f57d-cb86-3b55cfe915b7@oracle.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <2fa60098-d9be-f57d-cb86-3b55cfe915b7@oracle.com> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed 31-05-17 23:35:48, Pasha Tatashin wrote: > >OK, so why cannot we make zero_struct_page 8x 8B stores, other arches > >would do memset. You said it would be slower but would that be > >measurable? I am sorry to be so persistent here but I would be really > >happier if this didn't depend on the deferred initialization. If this is > >absolutely a no-go then I can live with that of course. > > Hi Michal, > > This is actually a very good idea. I just did some measurements, and it > looks like performance is very good. > > Here is data from SPARC-M7 with 3312G memory with single thread performance: > > Current: > memset() in memblock allocator takes: 8.83s > __init_single_page() take: 8.63s > > Option 1: > memset() in __init_single_page() takes: 61.09s (as we discussed because of > membar overhead, memset should really be optimized to do STBI only when size > is 1 page or bigger). > > Option 2: > > 8 stores (stx) in __init_single_page(): 8.525s! > > So, even for single thread performance we can double the initialization > speed of "struct page" on SPARC by removing memset() from memblock, and > using 8 stx in __init_single_page(). It appears we never miss L1 in > __init_single_page() after the initial 8 stx. OK, that is good to hear and it actually matches my understanding that writes to a single cacheline should add an overhead. Thanks! -- Michal Hocko SUSE Labs