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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id EA9B2C433F5 for ; Tue, 12 Apr 2022 04:20:58 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S239631AbiDLEXL (ORCPT ); Tue, 12 Apr 2022 00:23:11 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:41254 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1345877AbiDLEWt (ORCPT ); Tue, 12 Apr 2022 00:22:49 -0400 Received: from dfw.source.kernel.org (dfw.source.kernel.org [139.178.84.217]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id DFACC2A704 for ; Mon, 11 Apr 2022 21:20:20 -0700 (PDT) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id 7B38D6177F for ; Tue, 12 Apr 2022 04:20:20 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id CF5DEC385A1; Tue, 12 Apr 2022 04:20:19 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1649737219; bh=SfbVXI0mPMO1AC7/JwSckEMngQ2ga4UkO/pT693nMbg=; h=Date:To:From:Subject:From; b=ISl3IUKYgvzdFwgxkjoJXPs34zvM1s+JApds7zu8bmduvS+MW3zy4b/gaTxKYWTpX RiyKV7DPJ1VIXoaTgTo/iQ/hGxhsIm0M5OmUwZ283R09FvER0lAOocPC7JTPkmEtq/ USAwzr0kV+lxbE4nj4o+9i8XTBViKKRn5x8xNVEQ= Date: Mon, 11 Apr 2022 21:20:19 -0700 To: mm-commits@vger.kernel.org, will@kernel.org, vaibhav@linux.ibm.com, szhai2@cs.rochester.edu, suleiman@google.com, steven@liquorix.net, sofia.trinh@edi.works, shy828301@gmail.com, oleksandr@natalenko.name, mgorman@techsingularity.net, holger@applied-asynchrony.com, Hi-Angel@yandex.ru, heftig@archlinux.org, hannes@cmpxchg.org, djbyrne@mtu.edu, d@chaos-reins.com, bgeffon@google.com, baohua@kernel.org, yuzhao@google.com, akpm@linux-foundation.org From: Andrew Morton Subject: + mm-multi-gen-lru-thrashing-prevention.patch added to -mm tree Message-Id: <20220412042019.CF5DEC385A1@smtp.kernel.org> Precedence: bulk Reply-To: linux-kernel@vger.kernel.org List-ID: X-Mailing-List: mm-commits@vger.kernel.org The patch titled Subject: mm: multi-gen LRU: thrashing prevention has been added to the -mm tree. Its filename is mm-multi-gen-lru-thrashing-prevention.patch This patch should soon appear at https://ozlabs.org/~akpm/mmots/broken-out/mm-multi-gen-lru-thrashing-prevention.patch and later at https://ozlabs.org/~akpm/mmotm/broken-out/mm-multi-gen-lru-thrashing-prevention.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Yu Zhao Subject: mm: multi-gen LRU: thrashing prevention Add /sys/kernel/mm/lru_gen/min_ttl_ms for thrashing prevention, as requested by many desktop users [1]. When set to value N, it prevents the working set of N milliseconds from getting evicted. The OOM killer is triggered if this working set cannot be kept in memory. Based on the average human detectable lag (~100ms), N=1000 usually eliminates intolerable lags due to thrashing. Larger values like N=3000 make lags less noticeable at the risk of premature OOM kills. Compared with the size-based approach, e.g., [2], this time-based approach has the following advantages: 1. It is easier to configure because it is agnostic to applications and memory sizes. 2. It is more reliable because it is directly wired to the OOM killer. [1] https://lore.kernel.org/r/Ydza%2FzXKY9ATRoh6@google.com/ [2] https://lore.kernel.org/r/20211130201652.2218636d@mail.inbox.lv/ Link: https://lkml.kernel.org/r/20220407031525.2368067-12-yuzhao@google.com Signed-off-by: Yu Zhao 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 Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Barry Song Cc: Johannes Weiner Cc: Mel Gorman Cc: Will Deacon Cc: Yang Shi Signed-off-by: Andrew Morton --- --- a/include/linux/mmzone.h~mm-multi-gen-lru-thrashing-prevention +++ a/include/linux/mmzone.h @@ -416,6 +416,8 @@ struct lru_gen_struct { unsigned long max_seq; /* the eviction increments the oldest generation numbers */ unsigned long min_seq[ANON_AND_FILE]; + /* the birth time of each generation in jiffies */ + unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists */ struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the sizes of the above lists */ --- a/mm/vmscan.c~mm-multi-gen-lru-thrashing-prevention +++ a/mm/vmscan.c @@ -4192,6 +4192,7 @@ static void inc_max_seq(struct lruvec *l for (type = 0; type < ANON_AND_FILE; type++) reset_ctrl_pos(lruvec, type, false); + WRITE_ONCE(lrugen->timestamps[next], jiffies); /* make sure preceding modifications appear */ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); @@ -4317,7 +4318,8 @@ static long get_nr_evictable(struct lruv return total > 0 ? total : 0; } -static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc) +static bool age_lruvec(struct lruvec *lruvec, struct scan_control *sc, + unsigned long min_ttl) { bool need_aging; long nr_to_scan; @@ -4326,14 +4328,22 @@ static void age_lruvec(struct lruvec *lr DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); + if (min_ttl) { + int gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); + unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); + + if (time_is_after_jiffies(birth + min_ttl)) + return false; + } + mem_cgroup_calculate_protection(NULL, memcg); if (mem_cgroup_below_min(memcg)) - return; + return false; nr_to_scan = get_nr_evictable(lruvec, max_seq, min_seq, swappiness, &need_aging); if (!nr_to_scan) - return; + return false; nr_to_scan >>= sc->priority; @@ -4342,11 +4352,18 @@ static void age_lruvec(struct lruvec *lr if (nr_to_scan && need_aging && (!mem_cgroup_below_low(memcg) || sc->memcg_low_reclaim)) try_to_inc_max_seq(lruvec, max_seq, sc, swappiness, false); + + return true; } +/* to protect the working set of the last N jiffies */ +static unsigned long lru_gen_min_ttl __read_mostly; + static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; + bool success = false; + unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); VM_BUG_ON(!current_is_kswapd()); @@ -4372,12 +4389,29 @@ static void lru_gen_age_node(struct pgli do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); - age_lruvec(lruvec, sc); + if (age_lruvec(lruvec, sc, min_ttl)) + success = true; cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); current->reclaim_state->mm_walk = NULL; + + /* + * The main goal is to OOM kill if every generation from all memcgs is + * younger than min_ttl. However, another theoretical possibility is all + * memcgs are either below min or empty. + */ + if (!success && mutex_trylock(&oom_lock)) { + struct oom_control oc = { + .gfp_mask = sc->gfp_mask, + .order = sc->order, + }; + + out_of_memory(&oc); + + mutex_unlock(&oom_lock); + } } /* @@ -5092,6 +5126,28 @@ unlock: * sysfs interface ******************************************************************************/ +static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); +} + +static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t len) +{ + unsigned int msecs; + + if (kstrtouint(buf, 0, &msecs)) + return -EINVAL; + + WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs)); + + return len; +} + +static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR( + min_ttl_ms, 0644, show_min_ttl, store_min_ttl +); + static ssize_t show_enable(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; @@ -5140,6 +5196,7 @@ static struct kobj_attribute lru_gen_ena ); static struct attribute *lru_gen_attrs[] = { + &lru_gen_min_ttl_attr.attr, &lru_gen_enabled_attr.attr, NULL }; @@ -5155,12 +5212,16 @@ static struct attribute_group lru_gen_at void lru_gen_init_lruvec(struct lruvec *lruvec) { + int i; int gen, type, zone; struct lru_gen_struct *lrugen = &lruvec->lrugen; lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); + for (i = 0; i <= MIN_NR_GENS + 1; i++) + lrugen->timestamps[i] = jiffies; + for_each_gen_type_zone(gen, type, zone) INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]); _ Patches currently in -mm which might be from yuzhao@google.com are mm-x86-arm64-add-arch_has_hw_pte_young.patch mm-x86-add-config_arch_has_nonleaf_pmd_young.patch mm-vmscanc-refactor-shrink_node.patch revert-include-linux-mm_inlineh-fold-__update_lru_size-into-its-sole-caller.patch mm-multi-gen-lru-groundwork.patch mm-multi-gen-lru-minimal-implementation.patch mm-multi-gen-lru-exploit-locality-in-rmap.patch mm-multi-gen-lru-support-page-table-walks.patch mm-multi-gen-lru-optimize-multiple-memcgs.patch mm-multi-gen-lru-kill-switch.patch mm-multi-gen-lru-thrashing-prevention.patch mm-multi-gen-lru-debugfs-interface.patch mm-multi-gen-lru-admin-guide.patch mm-multi-gen-lru-design-doc.patch