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 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id BA799C433EF for ; Wed, 10 Nov 2021 08:49:57 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 65667611C0 for ; Wed, 10 Nov 2021 08:49:57 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 65667611C0 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=linaro.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=kvack.org Received: by kanga.kvack.org (Postfix) id EEE5B6B006C; Wed, 10 Nov 2021 03:49:56 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id E9E8F6B0071; Wed, 10 Nov 2021 03:49:56 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id D672D6B0072; Wed, 10 Nov 2021 03:49:56 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0193.hostedemail.com [216.40.44.193]) by kanga.kvack.org (Postfix) with ESMTP id C8D0C6B006C for ; Wed, 10 Nov 2021 03:49:56 -0500 (EST) Received: from smtpin04.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay03.hostedemail.com (Postfix) with ESMTP id 83BE9824C458 for ; Wed, 10 Nov 2021 08:49:56 +0000 (UTC) X-FDA: 78792397992.04.295B3C5 Received: from mail-yb1-f174.google.com (mail-yb1-f174.google.com [209.85.219.174]) by imf17.hostedemail.com (Postfix) with ESMTP id 24C26F000090 for ; Wed, 10 Nov 2021 08:49:56 +0000 (UTC) Received: by mail-yb1-f174.google.com with SMTP id g17so4513203ybe.13 for ; Wed, 10 Nov 2021 00:49:55 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=MdY7UHYrrQKUh664qRerLGbjRpq6Ut9+FyTMES+mZMA=; b=adkFPVgInFqFZaK3aYlFhHDbqe1L/NtOxaJNQDr6Mtb6K0LJTBb1HjR6ZuL21GX0HS 0vldBJFBDAvrwoyMnYkbLuJJzjU7HI9+/M527Q1B8eIyro2wVZBR5FGVcqin18SGDUoE qmWMJfe4BKuUEEKy5RoxUuJqJYv2slbA7uBqN8DU/5Nojf7LP8MS42SCBFK4KgA46WFY p5Ai/URphyJiuQyHuWY4gtqnBWMX7iydkJaN9xIv+DuCUSPD2ve+G8UHcZbCnCghulqy pxPSyhAoOvlrWMG7k93Dan66vODdgbMPKaLW9/YJuXop4Vkv1tqOZnZcvh0GPClgTV8D 1KxQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=MdY7UHYrrQKUh664qRerLGbjRpq6Ut9+FyTMES+mZMA=; b=F0+AWcqHBVNm+Sc6s+s+V+kIjB+wWCS/aHoIoP+YqyQLuDQsv/b2TFt1bnhTCPjeoU nw01EEqK47LWIqqmBddUpceAIxLZACQ/AKj998yYpmlwWzhbyf5QWvUZX1YltPm1ujf/ xRTcgXfJxWX7xMaC52bwxzl7OqVGtuoN8CRsZ0+YvzY4jATzLgGjGRhF89p9dHxNDNsa O9qAOrXqxpigEYaUqtx0PPza/Mrs/vO551yHpOCceC8mOPtuSJsS6ICxzMsJDMbytm// tidWngO1ZFMdSRA27EJjCGbydhOtTacfHD9gUnsFqqo1y94wp20xP7RS/zQESb9TQF1C fVyA== X-Gm-Message-State: AOAM533u8uXHEhfHQxP5KmaV1W3V8gJ3Yhz0YQ36ZwSpEe15QLnDaXB0 pQlrg1gFmF4vch9jgA3rOJ7eOa7HYLsCXa0f7WUxyg== X-Google-Smtp-Source: ABdhPJyiByNSWYWf4OWZb3PV1Mje8S/tHcHo299QTRuWZG5r1Tj6CfGJov0W5akiZe9Gtq+/t5qYWaZrzCFi2s2swYE= X-Received: by 2002:a25:d707:: with SMTP id o7mr16002187ybg.546.1636534195291; Wed, 10 Nov 2021 00:49:55 -0800 (PST) MIME-Version: 1.0 References: <1634278612-17055-1-git-send-email-huangzhaoyang@gmail.com> In-Reply-To: From: Vincent Guittot Date: Wed, 10 Nov 2021 09:49:44 +0100 Message-ID: Subject: Re: [Resend PATCH] psi : calc cfs task memstall time more precisely To: Peter Zijlstra Cc: Johannes Weiner , Huangzhaoyang , Andrew Morton , Michal Hocko , Vladimir Davydov , Zhaoyang Huang , linux-mm@kvack.org, linux-kernel@vger.kernel.org Content-Type: text/plain; charset="UTF-8" X-Rspamd-Server: rspam02 X-Rspamd-Queue-Id: 24C26F000090 X-Stat-Signature: kfd58rxyrt7a4ebhdi5tsae8f584ctqj Authentication-Results: imf17.hostedemail.com; dkim=pass header.d=linaro.org header.s=google header.b=adkFPVgI; spf=pass (imf17.hostedemail.com: domain of vincent.guittot@linaro.org designates 209.85.219.174 as permitted sender) smtp.mailfrom=vincent.guittot@linaro.org; dmarc=pass (policy=none) header.from=linaro.org X-HE-Tag: 1636534196-591592 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000396, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: On Tue, 9 Nov 2021 at 15:56, Peter Zijlstra wrote: > > On Tue, Nov 02, 2021 at 03:47:33PM -0400, Johannes Weiner wrote: > > CC peterz as well for rt and timekeeping magic > > > > On Fri, Oct 15, 2021 at 02:16:52PM +0800, Huangzhaoyang wrote: > > > From: Zhaoyang Huang > > > > > > In an EAS enabled system, there are two scenarios discordant to current design, > > > > > > 1. workload used to be heavy uneven among cores for sake of scheduler policy. > > > RT task usually preempts CFS task in little core. > > > 2. CFS task's memstall time is counted as simple as exit - entry so far, which > > > ignore the preempted time by RT, DL and Irqs. > > It ignores preemption full-stop. I don't see why RT/IRQ should be > special cased here. > > > > With these two constraints, the percpu nonidle time would be mainly consumed by > > > none CFS tasks and couldn't be averaged. Eliminating them by calc the time growth > > > via the proportion of cfs_rq's utilization on the whole rq. > > > > > +static unsigned long psi_memtime_fixup(u32 growth) > > > +{ > > > + struct rq *rq = task_rq(current); > > > + unsigned long growth_fixed = (unsigned long)growth; > > > + > > > + if (!(current->policy == SCHED_NORMAL || current->policy == SCHED_BATCH)) > > > + return growth_fixed; > > > + > > > + if (current->in_memstall) > > > + growth_fixed = div64_ul((1024 - rq->avg_rt.util_avg - rq->avg_dl.util_avg > > > + - rq->avg_irq.util_avg + 1) * growth, 1024); > > > + > > > + return growth_fixed; > > > +} > > > + > > > static void init_triggers(struct psi_group *group, u64 now) > > > { > > > struct psi_trigger *t; > > > @@ -658,6 +675,7 @@ static void record_times(struct psi_group_cpu *groupc, u64 now) > > > } > > > > > > if (groupc->state_mask & (1 << PSI_MEM_SOME)) { > > > + delta = psi_memtime_fixup(delta); > > > > Ok, so we want to deduct IRQ and RT preemption time from the memstall > > period of an active reclaimer, since it's technically not stalled on > > memory during this time but on CPU. > > > > However, we do NOT want to deduct IRQ and RT time from memstalls that > > are sleeping on refaults swapins, since they are not affected by what > > is going on on the CPU. > > I think that focus on RT/IRQ is mis-guided here, and the implementation > is horrendous. > > So the fundamental question seems to be; and I think Johannes is the one > to answer that: What time-base do these metrics want to use? > > Do some of these states want to account in task-time instead of > wall-time perhaps? I can't quite remember, but vague memories are > telling me most of the PSI accounting was about blocked tasks, not > running tasks, which makes all this rather more complicated. I tend to agree with this. Using rq_clock_task(rq) instead of cpu_clock(cpu) will remove the time spent under interrupt as an example and AFAICT, rq->clock_task is updated before calling psi function > > Randomly scaling time as proposed seems almost certainly wrong. What > would that make the stats mean?