From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-3.5 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,SPF_HELO_NONE, SPF_PASS autolearn=no autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id E0781C4361B for ; Mon, 14 Dec 2020 18:10:25 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 4BE172250E for ; Mon, 14 Dec 2020 18:10:25 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 4BE172250E Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=joelfernandes.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 6708B6B005D; Mon, 14 Dec 2020 13:10:24 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 5FA046B0068; Mon, 14 Dec 2020 13:10:24 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 44C6E6B006C; Mon, 14 Dec 2020 13:10:24 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0069.hostedemail.com [216.40.44.69]) by kanga.kvack.org (Postfix) with ESMTP id 2BC916B005D for ; Mon, 14 Dec 2020 13:10:24 -0500 (EST) Received: from smtpin28.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay05.hostedemail.com (Postfix) with ESMTP id E2D20181AEF21 for ; Mon, 14 Dec 2020 18:10:23 +0000 (UTC) X-FDA: 77592677526.28.joke30_17065522741c Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin28.hostedemail.com (Postfix) with ESMTP id 7C1A96C1A for ; Mon, 14 Dec 2020 18:10:23 +0000 (UTC) X-HE-Tag: joke30_17065522741c X-Filterd-Recvd-Size: 7859 Received: from mail-qk1-f195.google.com (mail-qk1-f195.google.com [209.85.222.195]) by imf10.hostedemail.com (Postfix) with ESMTP for ; Mon, 14 Dec 2020 18:10:22 +0000 (UTC) Received: by mail-qk1-f195.google.com with SMTP id 19so16450023qkm.8 for ; Mon, 14 Dec 2020 10:10:22 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=joelfernandes.org; s=google; h=date:from:to:cc:subject:message-id:references:mime-version :content-disposition:content-transfer-encoding:in-reply-to; bh=80A3v/WEjVbaiRbX2zqJ242KMRN7qmG3DpyY691VhNU=; b=IrTGKI/n7ayvbWMN0a7X/KHMS9wogZpz8jXczVP3WHMLZ2OioqQf8rwZllbIOzir+t sEehucHHdhqGg1HiD4LHnj3oQN1C+HBI6SoP8p8tqD+mZQ5fFFEKtrGaaBMzERcJdPvM 9bIFtqhqJVo8i4kNOZFi0T7+9sY9Rwpb/0OIw= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:date:from:to:cc:subject:message-id:references :mime-version:content-disposition:content-transfer-encoding :in-reply-to; bh=80A3v/WEjVbaiRbX2zqJ242KMRN7qmG3DpyY691VhNU=; b=b/QRnSxqLFKhx94pP4T2mA6JuJwc91O5KXtSq3NVqUYh8c0W59mRbpAW3Zq3W3/mPa AIMM22Vm57hAGkNs26v9m11zSDxVOU8adQFQ7jeKtyFtz+EaofpzB/ubTroPro2wukRf CVUauiiSCLc2XW3TbgCVjPPe6MtcTF/tj4FSpBxF1yZaeJz2deC45fpJbFGvlG7KRW8R 3yVmzMZzuVJUHAjBqBuea69nNVlDvTEJAdf6IERqzVhLJ6HEwmRqgIlj5XJuTp1vfolA vt0Sys76WLznwq6+v+ApaiGQ0fVIgakm5J2z3YvLyWperTqhgRBoP0yQcXnPdCMuC0ss XbyQ== X-Gm-Message-State: AOAM532nLciUIGQX6OVFqmdHquXuBNrCtZQ5/nOis+rxCAzSIxukWG8F Tn5GI5s3czdJHdofL6HBumEsNw== X-Google-Smtp-Source: ABdhPJyfBtJ7ukfd4lWK/6JV64PA0nYgtm5rutT93yEigIeKNLOh4kyhUcVeIWDo3MK9DwEflPfRgw== X-Received: by 2002:ae9:e10d:: with SMTP id g13mr33504576qkm.444.1607969422214; Mon, 14 Dec 2020 10:10:22 -0800 (PST) Received: from localhost ([2620:15c:6:411:cad3:ffff:feb3:bd59]) by smtp.gmail.com with ESMTPSA id i13sm5321115qkk.83.2020.12.14.10.10.20 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 14 Dec 2020 10:10:20 -0800 (PST) Date: Mon, 14 Dec 2020 13:10:20 -0500 From: Joel Fernandes To: Laurent Dufour Cc: Chinwen Chang , Haiyan Song , akpm@linux-foundation.org, mhocko@kernel.org, peterz@infradead.org, kirill@shutemov.name, ak@linux.intel.com, dave@stgolabs.net, jack@suse.cz, Matthew Wilcox , aneesh.kumar@linux.ibm.com, benh@kernel.crashing.org, mpe@ellerman.id.au, paulus@samba.org, Thomas Gleixner , Ingo Molnar , hpa@zytor.com, Will Deacon , Sergey Senozhatsky , sergey.senozhatsky.work@gmail.com, Andrea Arcangeli , Alexei Starovoitov , kemi.wang@intel.com, Daniel Jordan , David Rientjes , Jerome Glisse , Ganesh Mahendran , Minchan Kim , Punit Agrawal , vinayak menon , Yang Shi , zhong jiang , Balbir Singh , sj38.park@gmail.com, Michel Lespinasse , Mike Rapoport , linux-kernel@vger.kernel.org, linux-mm@kvack.org, haren@linux.vnet.ibm.com, npiggin@gmail.com, paulmck@linux.vnet.ibm.com, Tim Chen , linuxppc-dev@lists.ozlabs.org, x86@kernel.org, miles.chen@mediatek.com Subject: Re: [PATCH v12 00/31] Speculative page faults Message-ID: References: <20190416134522.17540-1-ldufour@linux.ibm.com> <20190606065129.d5s3534p23twksgp@haiyan.sh.intel.com> <3d3cefa2-0ebb-e86d-b060-7ba67c48a59f@linux.ibm.com> <1c412ebe-c213-ee67-d261-c70ddcd34b79@linux.ibm.com> <20190620081945.hwj6ruqddefnxg6z@haiyan.sh.intel.com> <1594027500.30360.32.camel@mtkswgap22> <490c0811-50cd-0802-2cbc-9c031ef309f6@linux.ibm.com> <1594099897.30360.58.camel@mtkswgap22> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline In-Reply-To: Content-Transfer-Encoding: quoted-printable X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: On Mon, Dec 14, 2020 at 10:36:29AM +0100, Laurent Dufour wrote: > Le 14/12/2020 =E0 03:03, Joel Fernandes a =E9crit=A0: > > On Tue, Jul 07, 2020 at 01:31:37PM +0800, Chinwen Chang wrote: > > [..] > > > > > Hi Laurent, > > > > >=20 > > > > > We merged SPF v11 and some patches from v12 into our platforms.= After > > > > > several experiments, we observed SPF has obvious improvements o= n the > > > > > launch time of applications, especially for those high-TLP ones= , > > > > >=20 > > > > > # launch time of applications(s): > > > > >=20 > > > > > package version w/ SPF w/o SPF improve= (%) > > > > > ---------------------------------------------------------------= --- > > > > > Baidu maps 10.13.3 0.887 0.98 9.49 > > > > > Taobao 8.4.0.35 1.227 1.293 5.10 > > > > > Meituan 9.12.401 1.107 1.543 28.26 > > > > > WeChat 7.0.3 2.353 2.68 12.20 > > > > > Honor of Kings 1.43.1.6 6.63 6.713 1.24 > > > >=20 > > > > That's great news, thanks for reporting this! > > > >=20 > > > > >=20 > > > > > By the way, we have verified our platforms with those patches a= nd > > > > > achieved the goal of mass production. > > > >=20 > > > > Another good news! > > > > For my information, what is your targeted hardware? > > > >=20 > > > > Cheers, > > > > Laurent. > > >=20 > > > Hi Laurent, > > >=20 > > > Our targeted hardware belongs to ARM64 multi-core series. > >=20 > > Hello! > >=20 > > I was trying to develop an intuition about why does SPF give improvem= ent for > > you on small CPU systems. This is just a high-level theory but: > >=20 > > 1. Assume the improvement is because of elimination of "blocking" on > > mmap_sem. > > Could it be that the mmap_sem is acquired in write-mode unnecessarily= in some > > places, thus causing blocking on mmap_sem in other paths? If so, is i= t > > feasible to convert such usages to acquiring them in read-mode? >=20 > That's correct, and the goal of this series is to try not holding the > mmap_sem in read mode during page fault processing. >=20 > Converting mmap_sem holder from write to read mode is not so easy and t= hat > work as already been done in some places. If you think there are areas = where > this could be done, you're welcome to send patches fixing that. >=20 > > 2. Assume the improvement is because of lesser read-side contention o= n > > mmap_sem. > > On small CPU systems, I would not expect reducing cache-line bouncing= to give > > such a dramatic improvement in performance as you are seeing. >=20 > I don't think cache line bouncing reduction is the main sourcec of > performance improvement, I would rather think this is the lower part he= re. > I guess this is mainly because during loading time a lot of page fault = is > occuring and thus SPF is reducing the contention on the mmap_sem. Thanks for the reply. I think I also wrongly assumed that acquiring mmap rwsem in write mode in a syscall makes SPF moot. Peter explained to me on= IRC that tere's still perf improvement in write mode if an unrelated VMA is modified while another VMA is faulting. CMIIW - not an mm expert by any stretch. Thanks! - Joel