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=-15.4 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,NICE_REPLY_A,SPF_HELO_NONE,SPF_PASS,USER_AGENT_SANE_1 autolearn=ham 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 C866FC433E0 for ; Thu, 11 Feb 2021 13:10:54 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 34E3964DFF for ; Thu, 11 Feb 2021 13:10:53 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 34E3964DFF Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=suse.cz Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 8CFC16B00EC; Thu, 11 Feb 2021 08:10:52 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 87F7E6B00ED; Thu, 11 Feb 2021 08:10:52 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 794FE6B00EE; Thu, 11 Feb 2021 08:10:52 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0005.hostedemail.com [216.40.44.5]) by kanga.kvack.org (Postfix) with ESMTP id 62E186B00EC for ; Thu, 11 Feb 2021 08:10:52 -0500 (EST) Received: from smtpin16.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay02.hostedemail.com (Postfix) with ESMTP id 284B93632 for ; Thu, 11 Feb 2021 13:10:52 +0000 (UTC) X-FDA: 77806021944.16.test14_2b0513827618 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin16.hostedemail.com (Postfix) with ESMTP id 07607100E690B for ; Thu, 11 Feb 2021 13:10:52 +0000 (UTC) X-HE-Tag: test14_2b0513827618 X-Filterd-Recvd-Size: 5632 Received: from mx2.suse.de (mx2.suse.de [195.135.220.15]) by imf43.hostedemail.com (Postfix) with ESMTP for ; Thu, 11 Feb 2021 13:10:51 +0000 (UTC) X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (unknown [195.135.221.27]) by mx2.suse.de (Postfix) with ESMTP id 23232AC69; Thu, 11 Feb 2021 13:10:50 +0000 (UTC) To: Yang Shi , guro@fb.com, ktkhai@virtuozzo.com, shakeelb@google.com, david@fromorbit.com, hannes@cmpxchg.org, mhocko@suse.com, akpm@linux-foundation.org Cc: linux-mm@kvack.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org References: <20210209174646.1310591-1-shy828301@gmail.com> <20210209174646.1310591-13-shy828301@gmail.com> From: Vlastimil Babka Subject: Re: [v7 PATCH 12/12] mm: vmscan: shrink deferred objects proportional to priority Message-ID: Date: Thu, 11 Feb 2021 14:10:49 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.7.0 MIME-Version: 1.0 In-Reply-To: <20210209174646.1310591-13-shy828301@gmail.com> Content-Type: text/plain; charset=utf-8 Content-Language: en-US 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 2/9/21 6:46 PM, Yang Shi wrote: > The number of deferred objects might get windup to an absurd number, an= d it > results in clamp of slab objects. It is undesirable for sustaining wor= kingset. >=20 > So shrink deferred objects proportional to priority and cap nr_deferred= to twice > of cache items. Makes sense to me, minimally it's simpler than the old code and avoiding = absurd growth of nr_deferred should be a good thing, as well as the "proportiona= l to priority" part. I just suspect there's a bit of unnecessary bias in the implementation, a= s explained below: > The idea is borrowed from Dave Chinner's patch: > https://lore.kernel.org/linux-xfs/20191031234618.15403-13-david@fromorb= it.com/ >=20 > Tested with kernel build and vfs metadata heavy workload in our product= ion > environment, no regression is spotted so far. >=20 > Signed-off-by: Yang Shi > --- > mm/vmscan.c | 40 +++++----------------------------------- > 1 file changed, 5 insertions(+), 35 deletions(-) >=20 > diff --git a/mm/vmscan.c b/mm/vmscan.c > index 66163082cc6f..d670b119d6bd 100644 > --- a/mm/vmscan.c > +++ b/mm/vmscan.c > @@ -654,7 +654,6 @@ static unsigned long do_shrink_slab(struct shrink_c= ontrol *shrinkctl, > */ > nr =3D count_nr_deferred(shrinker, shrinkctl); > =20 > - total_scan =3D nr; > if (shrinker->seeks) { > delta =3D freeable >> priority; > delta *=3D 4; > @@ -668,37 +667,9 @@ static unsigned long do_shrink_slab(struct shrink_= control *shrinkctl, > delta =3D freeable / 2; > } > =20 > + total_scan =3D nr >> priority; > total_scan +=3D delta; So, our scan goal consists of the part based on freeable objects (delta),= plus a part of the defferred objects (nr >> priority). Fine. > - if (total_scan < 0) { > - pr_err("shrink_slab: %pS negative objects to delete nr=3D%ld\n", > - shrinker->scan_objects, total_scan); > - total_scan =3D freeable; > - next_deferred =3D nr; > - } else > - next_deferred =3D total_scan; > - > - /* > - * We need to avoid excessive windup on filesystem shrinkers > - * due to large numbers of GFP_NOFS allocations causing the > - * shrinkers to return -1 all the time. This results in a large > - * nr being built up so when a shrink that can do some work > - * comes along it empties the entire cache due to nr >>> > - * freeable. This is bad for sustaining a working set in > - * memory. > - * > - * Hence only allow the shrinker to scan the entire cache when > - * a large delta change is calculated directly. > - */ > - if (delta < freeable / 4) > - total_scan =3D min(total_scan, freeable / 2); > - > - /* > - * Avoid risking looping forever due to too large nr value: > - * never try to free more than twice the estimate number of > - * freeable entries. > - */ > - if (total_scan > freeable * 2) > - total_scan =3D freeable * 2; > + total_scan =3D min(total_scan, (2 * freeable)); Probably unnecessary as we cap next_deferred below anyway? So total_scan = cannot grow without limits anymore. But can't hurt. > trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, > freeable, delta, total_scan, priority); > @@ -737,10 +708,9 @@ static unsigned long do_shrink_slab(struct shrink_= control *shrinkctl, > cond_resched(); > } > =20 > - if (next_deferred >=3D scanned) > - next_deferred -=3D scanned; > - else > - next_deferred =3D 0; > + next_deferred =3D max_t(long, (nr - scanned), 0) + total_scan; And here's the bias I think. Suppose we scanned 0 due to e.g. GFP_NOFS. W= e count as newly deferred both the "delta" part of total_scan, which is fine, but= also the "nr >> priority" part, where we failed to our share of the "reduce nr_deferred" work, but I don't think it means we should also increase nr_deferred by that amount of failed work. OTOH if we succeed and scan exactly the whole goal, we are subtracting fr= om nr_deferred both the "nr >> priority" part, which is correct, but also de= lta, which was new work, not deferred one, so that's incorrect IMHO as well. So the calculation should probably be something like this? next_deferred =3D max_t(long, nr + delta - scanned, 0); Thanks, Vlastimil > + next_deferred =3D min(next_deferred, (2 * freeable)); > + > /* > * move the unused scan count back into the shrinker in a > * manner that handles concurrent updates. >=20