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 kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id C0901C433FE for ; Thu, 7 Apr 2022 03:17:47 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 7DC968D0001; Wed, 6 Apr 2022 23:16:13 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 764916B007B; Wed, 6 Apr 2022 23:16:13 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 590A08D0001; Wed, 6 Apr 2022 23:16:13 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0240.hostedemail.com [216.40.44.240]) by kanga.kvack.org (Postfix) with ESMTP id 488026B0078 for ; Wed, 6 Apr 2022 23:16:13 -0400 (EDT) Received: from smtpin24.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay01.hostedemail.com (Postfix) with ESMTP id 06E3C1838A13A for ; Thu, 7 Apr 2022 03:16:03 +0000 (UTC) X-FDA: 79328619006.24.C1DFD7D Received: from mail-il1-f201.google.com (mail-il1-f201.google.com [209.85.166.201]) by imf09.hostedemail.com (Postfix) with ESMTP id 6C41E140003 for ; Thu, 7 Apr 2022 03:16:02 +0000 (UTC) Received: by mail-il1-f201.google.com with SMTP id i14-20020a056e020ece00b002ca198245e6so3009752ilk.4 for ; Wed, 06 Apr 2022 20:16:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=date:in-reply-to:message-id:mime-version:references:subject:from:to :cc:content-transfer-encoding; bh=HWUMxX2GHTS2sU7fxsre8OtJa702AlX1YTnPsDpNr8g=; b=kEWUDg82syhNmhp0q7HqjSi4vFJg5Mty4gsGp6NRMkxh+MCtLCXh7q7Rzwxf2Q2REl ie+GOC4+EdvR+L9kohnAjyipDQ1jAgxBdI+KbUWtBeOKN/TMwA497dxdq13ArcbYq9Q7 W+Uajrf4CuwPO0Tefvr9x6hpDeHQ4xF7duBX/Ak4bMe8ruBSOYuFmkrdeLOdWHywfsrA u1VIEVtXVvsW0hcmdR4mReTX5fvzmpEntQ7R9rbWadDXQSb54Htj4pdZnz/GSF0QGbMr mbTw93nrTfhV2KtfABiIqkWfWYlW8Nqm+WXEoxuRbsznMiKgezd1gYQEwzgM021DZhOE ySCA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:date:in-reply-to:message-id:mime-version :references:subject:from:to:cc:content-transfer-encoding; bh=HWUMxX2GHTS2sU7fxsre8OtJa702AlX1YTnPsDpNr8g=; b=2JwIufpuSAoSfvJqfmertxfdLD2qSNZie4yms0Jliq+HfhggQYZ9Cg/P9gSP1bDmRm Akv0i5U2cUSNXPTQx6V/aqys9d0yvE5eFmysdnnc/TH9dXTJ3kwiyIEOHAghQqNnHGna iwvWte4wtEGgKQTt50BopYipLn4zWehdBsgqMoWm7CvbfTLQ5tcyP6UdnXGjigDyt7GT CnvPyaTZppsNB1u8EIqikMi4wXIk8fRQdTYEDfeF7sqYWkLyXtpnYa/Qv+5h6Tb5NAL5 3udjeJLAyrw0Xn27IeOnaSnvzczMr4C7hS5ImHQmpxlmO0RCFTBduotGVuxWiRklm4T2 SWLw== X-Gm-Message-State: AOAM532zyY/hbZVGNJjqN2Fcei2rARrDKLcwfTryrrLdsSfelQ63MQ/7 JJtTC3+JdHtHUzxQtnnf9OGLm1jMsss= X-Google-Smtp-Source: ABdhPJwb4wEQfjqHqohpxKj+YJeCn5tBx/D54ak9fb5cGlgOENd8TrZRM2TWzSCsc2kdIv61Clqndub2Zyc= X-Received: from yuzhao.bld.corp.google.com ([2620:15c:183:200:9ea2:c755:ae22:6862]) (user=yuzhao job=sendgmr) by 2002:a92:cac3:0:b0:2c9:a265:4cab with SMTP id m3-20020a92cac3000000b002c9a2654cabmr5577295ilq.241.1649301361611; Wed, 06 Apr 2022 20:16:01 -0700 (PDT) Date: Wed, 6 Apr 2022 21:15:15 -0600 In-Reply-To: <20220407031525.2368067-1-yuzhao@google.com> Message-Id: <20220407031525.2368067-4-yuzhao@google.com> Mime-Version: 1.0 References: <20220407031525.2368067-1-yuzhao@google.com> X-Mailer: git-send-email 2.35.1.1094.g7c7d902a7c-goog Subject: [PATCH v10 03/14] mm/vmscan.c: refactor shrink_node() From: Yu Zhao To: Stephen Rothwell , linux-mm@kvack.org Cc: Andi Kleen , Andrew Morton , Aneesh Kumar , Barry Song <21cnbao@gmail.com>, Catalin Marinas , Dave Hansen , Hillf Danton , Jens Axboe , Jesse Barnes , Johannes Weiner , Jonathan Corbet , Linus Torvalds , Matthew Wilcox , Mel Gorman , Michael Larabel , Michal Hocko , Mike Rapoport , Rik van Riel , Vlastimil Babka , Will Deacon , Ying Huang , linux-arm-kernel@lists.infradead.org, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, page-reclaim@google.com, x86@kernel.org, Yu Zhao , Barry Song , Brian Geffon , Jan Alexander Steffens , Oleksandr Natalenko , Steven Barrett , Suleiman Souhlal , Daniel Byrne , Donald Carr , "=?UTF-8?q?Holger=20Hoffst=C3=A4tte?=" , Konstantin Kharlamov , Shuang Zhai , Sofia Trinh , Vaibhav Jain Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Rspam-User: X-Stat-Signature: 4d3q4tt9h5exkrd7bb39ngpayqzgddto Authentication-Results: imf09.hostedemail.com; dkim=pass header.d=google.com header.s=20210112 header.b=kEWUDg82; spf=pass (imf09.hostedemail.com: domain of 3cVdOYgYKCHIokpXQeWeeWbU.SecbYdkn-ccalQSa.ehW@flex--yuzhao.bounces.google.com designates 209.85.166.201 as permitted sender) smtp.mailfrom=3cVdOYgYKCHIokpXQeWeeWbU.SecbYdkn-ccalQSa.ehW@flex--yuzhao.bounces.google.com; dmarc=pass (policy=reject) header.from=google.com X-Rspamd-Server: rspam01 X-Rspamd-Queue-Id: 6C41E140003 X-HE-Tag: 1649301362-130893 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: This patch refactors shrink_node() to improve readability for the upcoming changes to mm/vmscan.c. Signed-off-by: Yu Zhao Reviewed-by: Barry Song Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffst=C3=A4tte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain --- mm/vmscan.c | 198 +++++++++++++++++++++++++++------------------------- 1 file changed, 104 insertions(+), 94 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 1678802e03e7..2232cb55af41 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2644,6 +2644,109 @@ enum scan_balance { SCAN_FILE, }; =20 +static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc) +{ + unsigned long file; + struct lruvec *target_lruvec; + + target_lruvec =3D mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); + + /* + * Flush the memory cgroup stats, so that we read accurate per-memcg + * lruvec stats for heuristics. + */ + mem_cgroup_flush_stats(); + + /* + * Determine the scan balance between anon and file LRUs. + */ + spin_lock_irq(&target_lruvec->lru_lock); + sc->anon_cost =3D target_lruvec->anon_cost; + sc->file_cost =3D target_lruvec->file_cost; + spin_unlock_irq(&target_lruvec->lru_lock); + + /* + * Target desirable inactive:active list ratios for the anon + * and file LRU lists. + */ + if (!sc->force_deactivate) { + unsigned long refaults; + + refaults =3D lruvec_page_state(target_lruvec, + WORKINGSET_ACTIVATE_ANON); + if (refaults !=3D target_lruvec->refaults[0] || + inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) + sc->may_deactivate |=3D DEACTIVATE_ANON; + else + sc->may_deactivate &=3D ~DEACTIVATE_ANON; + + /* + * When refaults are being observed, it means a new + * workingset is being established. Deactivate to get + * rid of any stale active pages quickly. + */ + refaults =3D lruvec_page_state(target_lruvec, + WORKINGSET_ACTIVATE_FILE); + if (refaults !=3D target_lruvec->refaults[1] || + inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) + sc->may_deactivate |=3D DEACTIVATE_FILE; + else + sc->may_deactivate &=3D ~DEACTIVATE_FILE; + } else + sc->may_deactivate =3D DEACTIVATE_ANON | DEACTIVATE_FILE; + + /* + * If we have plenty of inactive file pages that aren't + * thrashing, try to reclaim those first before touching + * anonymous pages. + */ + file =3D lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); + if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) + sc->cache_trim_mode =3D 1; + else + sc->cache_trim_mode =3D 0; + + /* + * Prevent the reclaimer from falling into the cache trap: as + * cache pages start out inactive, every cache fault will tip + * the scan balance towards the file LRU. And as the file LRU + * shrinks, so does the window for rotation from references. + * This means we have a runaway feedback loop where a tiny + * thrashing file LRU becomes infinitely more attractive than + * anon pages. Try to detect this based on file LRU size. + */ + if (!cgroup_reclaim(sc)) { + unsigned long total_high_wmark =3D 0; + unsigned long free, anon; + int z; + + free =3D sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); + file =3D node_page_state(pgdat, NR_ACTIVE_FILE) + + node_page_state(pgdat, NR_INACTIVE_FILE); + + for (z =3D 0; z < MAX_NR_ZONES; z++) { + struct zone *zone =3D &pgdat->node_zones[z]; + + if (!managed_zone(zone)) + continue; + + total_high_wmark +=3D high_wmark_pages(zone); + } + + /* + * Consider anon: if that's low too, this isn't a + * runaway file reclaim problem, but rather just + * extreme pressure. Reclaim as per usual then. + */ + anon =3D node_page_state(pgdat, NR_INACTIVE_ANON); + + sc->file_is_tiny =3D + file + free <=3D total_high_wmark && + !(sc->may_deactivate & DEACTIVATE_ANON) && + anon >> sc->priority; + } +} + /* * Determine how aggressively the anon and file LRU lists should be * scanned. The relative value of each set of LRU lists is determined @@ -3114,109 +3217,16 @@ static void shrink_node(pg_data_t *pgdat, struct s= can_control *sc) unsigned long nr_reclaimed, nr_scanned; struct lruvec *target_lruvec; bool reclaimable =3D false; - unsigned long file; =20 target_lruvec =3D mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); =20 again: - /* - * Flush the memory cgroup stats, so that we read accurate per-memcg - * lruvec stats for heuristics. - */ - mem_cgroup_flush_stats(); - memset(&sc->nr, 0, sizeof(sc->nr)); =20 nr_reclaimed =3D sc->nr_reclaimed; nr_scanned =3D sc->nr_scanned; =20 - /* - * Determine the scan balance between anon and file LRUs. - */ - spin_lock_irq(&target_lruvec->lru_lock); - sc->anon_cost =3D target_lruvec->anon_cost; - sc->file_cost =3D target_lruvec->file_cost; - spin_unlock_irq(&target_lruvec->lru_lock); - - /* - * Target desirable inactive:active list ratios for the anon - * and file LRU lists. - */ - if (!sc->force_deactivate) { - unsigned long refaults; - - refaults =3D lruvec_page_state(target_lruvec, - WORKINGSET_ACTIVATE_ANON); - if (refaults !=3D target_lruvec->refaults[0] || - inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) - sc->may_deactivate |=3D DEACTIVATE_ANON; - else - sc->may_deactivate &=3D ~DEACTIVATE_ANON; - - /* - * When refaults are being observed, it means a new - * workingset is being established. Deactivate to get - * rid of any stale active pages quickly. - */ - refaults =3D lruvec_page_state(target_lruvec, - WORKINGSET_ACTIVATE_FILE); - if (refaults !=3D target_lruvec->refaults[1] || - inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) - sc->may_deactivate |=3D DEACTIVATE_FILE; - else - sc->may_deactivate &=3D ~DEACTIVATE_FILE; - } else - sc->may_deactivate =3D DEACTIVATE_ANON | DEACTIVATE_FILE; - - /* - * If we have plenty of inactive file pages that aren't - * thrashing, try to reclaim those first before touching - * anonymous pages. - */ - file =3D lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); - if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) - sc->cache_trim_mode =3D 1; - else - sc->cache_trim_mode =3D 0; - - /* - * Prevent the reclaimer from falling into the cache trap: as - * cache pages start out inactive, every cache fault will tip - * the scan balance towards the file LRU. And as the file LRU - * shrinks, so does the window for rotation from references. - * This means we have a runaway feedback loop where a tiny - * thrashing file LRU becomes infinitely more attractive than - * anon pages. Try to detect this based on file LRU size. - */ - if (!cgroup_reclaim(sc)) { - unsigned long total_high_wmark =3D 0; - unsigned long free, anon; - int z; - - free =3D sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); - file =3D node_page_state(pgdat, NR_ACTIVE_FILE) + - node_page_state(pgdat, NR_INACTIVE_FILE); - - for (z =3D 0; z < MAX_NR_ZONES; z++) { - struct zone *zone =3D &pgdat->node_zones[z]; - if (!managed_zone(zone)) - continue; - - total_high_wmark +=3D high_wmark_pages(zone); - } - - /* - * Consider anon: if that's low too, this isn't a - * runaway file reclaim problem, but rather just - * extreme pressure. Reclaim as per usual then. - */ - anon =3D node_page_state(pgdat, NR_INACTIVE_ANON); - - sc->file_is_tiny =3D - file + free <=3D total_high_wmark && - !(sc->may_deactivate & DEACTIVATE_ANON) && - anon >> sc->priority; - } + prepare_scan_count(pgdat, sc); =20 shrink_node_memcgs(pgdat, sc); =20 --=20 2.35.1.1094.g7c7d902a7c-goog