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=-2.0 required=3.0 tests=DKIM_ADSP_CUSTOM_MED, DKIM_INVALID,DKIM_SIGNED,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS, USER_AGENT_SANE_1 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 DE3C0C3F2D4 for ; Fri, 28 Feb 2020 09:56:21 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 93A5C246A8 for ; Fri, 28 Feb 2020 09:56:21 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="DR8NbMyb" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 93A5C246A8 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=gmail.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 2516B6B0005; Fri, 28 Feb 2020 04:56:21 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 1DB396B0006; Fri, 28 Feb 2020 04:56:21 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 0A34C6B0007; Fri, 28 Feb 2020 04:56:21 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0180.hostedemail.com [216.40.44.180]) by kanga.kvack.org (Postfix) with ESMTP id E276E6B0005 for ; Fri, 28 Feb 2020 04:56:20 -0500 (EST) Received: from smtpin11.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay03.hostedemail.com (Postfix) with ESMTP id A2CC9824556B for ; Fri, 28 Feb 2020 09:56:20 +0000 (UTC) X-FDA: 76539080520.11.unit24_718c8288e552b X-HE-Tag: unit24_718c8288e552b X-Filterd-Recvd-Size: 8342 Received: from mail-pl1-f193.google.com (mail-pl1-f193.google.com [209.85.214.193]) by imf32.hostedemail.com (Postfix) with ESMTP for ; Fri, 28 Feb 2020 09:56:20 +0000 (UTC) Received: by mail-pl1-f193.google.com with SMTP id y8so1034122pll.13 for ; Fri, 28 Feb 2020 01:56:19 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=date:from:to:cc:subject:message-id:references:mime-version :content-disposition:content-transfer-encoding:in-reply-to :user-agent; bh=2QsN/rdxaIqssMADaDVe6NhtTvdzMSkrjVDdCt3Mft0=; b=DR8NbMyb++08TCBQlly9aRtr9w0nv3yapNpXlboIXFtQZesGe3XoJJeub7sPgN56bU 5TLsME80pB8gXS96LhC9qYSuYsn2vF1+JpUHhcZ7FVaUnratWGpLtu9U+Vtn9ouetWXV 8/3PdSZT5pZUaJbNdn60fCkiJ4h0XzVPAz0asLKAnNUGrkEhEhtmVW4Iu3q2eYTcBnwG Q989urBANB1Jcv0a9M8KUSIR8fZmgoTzU7vT7gWfCLBrdS3Hd96+nV9BmRqoPbrIv6mS WMQlyvhLG3+D51lebvfBLHHgNPkoMWvcBg4wdDezX1uQPgBm+w+MgII6dddqffH8qZsy N9Yg== 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:user-agent; bh=2QsN/rdxaIqssMADaDVe6NhtTvdzMSkrjVDdCt3Mft0=; b=MrOKKW6vCFlZ2jNGunc/8yCTLcIW8iooVBQILmMDhqRg14gZ3+iBzEoqS1YTooYpUt kq6lO3GtjqlG7Tgbr5RCVHzJ9Lej8u4FWEQCj7wEIW+GT0NSEVYBmuz130WBkXxjbstW E/XGWJyEx4BxqbFm56QHw5nvK8SGwVpnour1VR0CdydJeVqJ/ZqCgDLiXA9DbsfPM9f5 5ThPs64YQjqx3dpn8h+m0QqAQVwhVB5D86ZeKjkXWiS6tetx/1TvkzJruhM2Jk+AeY+k q9m0wnFVVGocg6HAoHdaW+aKWmwNJSKM8pinLPI4QScWUwdV+l8Rl8zmGWxeOfc+KtMQ IpWA== X-Gm-Message-State: APjAAAWlIyjl0bIsfjsA2lxf8dkogRgLZl7CZpVbw+5nGVfjt4W/IR0I F4l6nmngN6VXSrevSmx0lNg= X-Google-Smtp-Source: APXvYqzeq5AJZwfx4VpkyGRwt33tMRUzv7T+620AVSjU/lm/WxAKYskVCMbi96DqbZTCn8vH3HbcOQ== X-Received: by 2002:a17:902:d705:: with SMTP id w5mr3364412ply.68.1582883778836; Fri, 28 Feb 2020 01:56:18 -0800 (PST) Received: from js1304-desktop ([114.206.198.176]) by smtp.gmail.com with ESMTPSA id 13sm10090469pfj.68.2020.02.28.01.56.15 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Fri, 28 Feb 2020 01:56:18 -0800 (PST) Date: Fri, 28 Feb 2020 18:56:11 +0900 From: Joonsoo Kim To: Aaron Lu Cc: Johannes Weiner , Andrew Morton , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Michal Hocko , Hugh Dickins , Minchan Kim , Vlastimil Babka , Mel Gorman , kernel-team@lge.com, Huang Ying Subject: Re: [PATCH v2 0/9] workingset protection/detection on the anonymous LRU list Message-ID: <20200228095534.GA30796@js1304-desktop> References: <1582175513-22601-1-git-send-email-iamjoonsoo.kim@lge.com> <20200226193942.30049da9c090b466bdc5ec23@linux-foundation.org> <20200227134806.GC39625@cmpxchg.org> <20200228032358.GB634650@ziqianlu-desktop.localdomain> <20200228040214.GA21040@js1304-desktop> <20200228055726.GA674737@ziqianlu-desktop.localdomain> <20200228065214.GA17349@js1304-desktop> <20200228091700.GA675567@ziqianlu-desktop.localdomain> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline In-Reply-To: <20200228091700.GA675567@ziqianlu-desktop.localdomain> User-Agent: Mutt/1.5.24 (2015-08-30) 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 Fri, Feb 28, 2020 at 05:17:00PM +0800, Aaron Lu wrote: > On Fri, Feb 28, 2020 at 03:52:59PM +0900, Joonsoo Kim wrote: > > On Fri, Feb 28, 2020 at 01:57:26PM +0800, Aaron Lu wrote: > > > On Fri, Feb 28, 2020 at 01:03:03PM +0900, Joonsoo Kim wrote: > > > > Hello, > > > >=20 > > > > On Fri, Feb 28, 2020 at 11:23:58AM +0800, Aaron Lu wrote: > > > > > On Thu, Feb 27, 2020 at 08:48:06AM -0500, Johannes Weiner wrote= : > > > > > > On Wed, Feb 26, 2020 at 07:39:42PM -0800, Andrew Morton wrote= : > > > > > > > It sounds like the above simple aging changes provide most = of the > > > > > > > improvement, and that the workingset changes are less benef= icial and a > > > > > > > bit more risky/speculative? > > > > > > >=20 > > > > > > > If so, would it be best for us to concentrate on the aging = changes > > > > > > > first, let that settle in and spread out and then turn atte= ntion to the > > > > > > > workingset changes? > > > > > >=20 > > > > > > Those two patches work well for some workloads (like the benc= hmark), > > > > > > but not for others. The full patchset makes sure both types w= ork well. > > > > > >=20 > > > > > > Specifically, the existing aging strategy for anon assumes th= at most > > > > > > anon pages allocated are hot. That's why they all start activ= e and we > > > > > > then do second-chance with the small inactive LRU to filter o= ut the > > > > > > few cold ones to swap out. This is true for many common workl= oads. > > > > > >=20 > > > > > > The benchmark creates a larger-than-memory set of anon pages = with a > > > > > > flat access profile - to the VM a flood of one-off pages. Joo= nsoo's > > > > >=20 > > > > > test: swap-w-rand-mt, which is a multi thread swap write intens= ive > > > > > workload so there will be swap out and swap ins. > > > > >=20 > > > > > > first two patches allow the VM to usher those pages in and ou= t of > > > > >=20 > > > > > Weird part is, the robot says the performance gain comes from t= he 1st > > > > > patch only, which adjust the ratio, not including the 2nd patch= which > > > > > makes anon page starting from inactive list. > > > > >=20 > > > > > I find the performance gain hard to explain... > > > >=20 > > > > Let me explain the reason of the performance gain. > > > >=20 > > > > 1st patch provides more second chance to the anonymous pages. > > >=20 > > > By second chance, do I understand correctely this refers to pages o= n=20 > > > inactive list get moved back to active list? > >=20 > > Yes. > >=20 > > >=20 > > > > In swap-w-rand-mt test, memory used by all threads is greater tha= n the > > > > amount of the system memory, but, memory used by each thread woul= d > > > > not be much. So, although it is a rand test, there is a locality > > > > in each thread's job. More second chance helps to exploit this > > > > locality so performance could be improved. > > >=20 > > > Does this mean there should be fewer vmstat.pswpout and vmstat.pswp= in > > > with patch1 compared to vanilla? > >=20 > > It depends on the workload. If the workload consists of anonymous >=20 > This swap-rand-w-mt workload is anon only. Yes, I know. >=20 > > pages only, I think, yes, pswpout/pswpin would be lower than vanilla >=20 > I think LKP robot has captured these two metrics but the report didn't > show them, which means the number is about the same with or without > patch #1. robot showed these two metrics. See below. 50190319 =B1 31% -35.7% 32291856 =B1 14% proc-vmstat.pswpin 56429784 =B1 21% -42.6% 32386842 =B1 14% proc-vmstat.pswpout pswpin/out are improved. > > with patch #1. With large inactive list, we can easily find the > > frequently referenced page and it would result in less swap in/out. >=20 > But with small inactive list, the pages that would be on inactive list > will stay on active list? I think the larger inactive list is mainly > used to give the anon page a chance to be promoted to active list now > that anon pages land on inactive list first, but on reclaim, I don't se= e > how a larger inactive list can cause fewer swap outs. Point is that larger inactive LRU helps to find hot pages and these hot pages leads to more cache hits. When a cache hit happens, no swap outs happens. But, if a cache miss happens, a new page is added to the LRU and then it causes the reclaim and swap out. > Forgive me for my curiosity and feel free to ignore my question as I > don't want to waste your time on this. Your patchset looks a worthwhile > thing to do, it's just the robot's report on patch1 seems er... I appreciate your attention. Feel free to ask. :) Thanks.