From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756696AbdCWXfZ (ORCPT ); Thu, 23 Mar 2017 19:35:25 -0400 Received: from shards.monkeyblade.net ([184.105.139.130]:58750 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756659AbdCWXfY (ORCPT ); Thu, 23 Mar 2017 19:35:24 -0400 Date: Thu, 23 Mar 2017 16:35:20 -0700 (PDT) Message-Id: <20170323.163520.123614131649571916.davem@davemloft.net> To: willy@infradead.org Cc: pasha.tatashin@oracle.com, linux-kernel@vger.kernel.org, sparclinux@vger.kernel.org, linux-mm@kvack.org, linuxppc-dev@lists.ozlabs.org, linux-s390@vger.kernel.or Subject: Re: [v1 0/5] parallelized "struct page" zeroing From: David Miller In-Reply-To: <20170323232638.GB29134@bombadil.infradead.org> References: <1490310113-824438-1-git-send-email-pasha.tatashin@oracle.com> <20170323232638.GB29134@bombadil.infradead.org> 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]); Thu, 23 Mar 2017 16:35:23 -0700 (PDT) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Matthew Wilcox Date: Thu, 23 Mar 2017 16:26:38 -0700 > On Thu, Mar 23, 2017 at 07:01:48PM -0400, Pavel Tatashin wrote: >> When deferred struct page initialization feature is enabled, we get a >> performance gain of initializing vmemmap in parallel after other CPUs are >> started. However, we still zero the memory for vmemmap using one boot CPU. >> This patch-set fixes the memset-zeroing limitation by deferring it as well. >> >> Here is example performance gain on SPARC with 32T: >> base >> https://hastebin.com/ozanelatat.go >> >> fix >> https://hastebin.com/utonawukof.go >> >> As you can see without the fix it takes: 97.89s to boot >> With the fix it takes: 46.91 to boot. > > How long does it take if we just don't zero this memory at all? We seem > to be initialising most of struct page in __init_single_page(), so it > seems like a lot of additional complexity to conditionally zero the rest > of struct page. Alternatively, just zero out the entire vmemmap area when it is setup in the kernel page tables.