diff options
author | Yu Zhao <yuzhao@google.com> | 2022-09-18 02:00:08 -0600 |
---|---|---|
committer | Andrew Morton <akpm@linux-foundation.org> | 2022-09-26 19:46:10 -0700 |
commit | 1332a809d95a4fc763cabe5ecb6d4fb6a6d941b2 (patch) | |
tree | 728bcd584840912639227175a0acae34c28d4765 | |
parent | 354ed597442952fb680c9cafc7e4eb8a76f9514c (diff) | |
download | linux-1332a809d95a4fc763cabe5ecb6d4fb6a6d941b2.tar.bz2 |
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 [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/20101028191523.GA14972@google.com/
Link: https://lkml.kernel.org/r/20220918080010.2920238-12-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Acked-by: Brian Geffon <bgeffon@google.com>
Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Steven Barrett <steven@liquorix.net>
Acked-by: Suleiman Souhlal <suleiman@google.com>
Tested-by: Daniel Byrne <djbyrne@mtu.edu>
Tested-by: Donald Carr <d@chaos-reins.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
Tested-by: Sofia Trinh <sofia.trinh@edi.works>
Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r-- | include/linux/mmzone.h | 2 | ||||
-rw-r--r-- | mm/vmscan.c | 74 |
2 files changed, 73 insertions, 3 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 95c58c7fbdff..87347945270b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -422,6 +422,8 @@ 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, lazily sorted on eviction */ struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ diff --git a/mm/vmscan.c b/mm/vmscan.c index 2f4be18b57cb..128a67db8db6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4293,6 +4293,7 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap) 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); @@ -4422,7 +4423,7 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsig return false; } -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; unsigned long nr_to_scan; @@ -4436,16 +4437,36 @@ static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc) mem_cgroup_calculate_protection(NULL, memcg); if (mem_cgroup_below_min(memcg)) - return; + return false; need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, swappiness, &nr_to_scan); + + 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; + + /* the size is likely too small to be helpful */ + if (!nr_to_scan && sc->priority != DEF_PRIORITY) + return false; + } + if (need_aging) try_to_inc_max_seq(lruvec, max_seq, sc, swappiness); + + 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_WARN_ON_ONCE(!current_is_kswapd()); @@ -4468,12 +4489,32 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) 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))); clear_mm_walk(); + + /* check the order to exclude compaction-induced reclaim */ + if (success || !min_ttl || sc->order) + return; + + /* + * The main goal is to OOM kill if every generation from all memcgs is + * younger than min_ttl. However, another possibility is all memcgs are + * either below min or empty. + */ + if (mutex_trylock(&oom_lock)) { + struct oom_control oc = { + .gfp_mask = sc->gfp_mask, + }; + + out_of_memory(&oc); + + mutex_unlock(&oom_lock); + } } /* @@ -5231,6 +5272,28 @@ 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_enabled(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; @@ -5279,6 +5342,7 @@ static struct kobj_attribute lru_gen_enabled_attr = __ATTR( ); static struct attribute *lru_gen_attrs[] = { + &lru_gen_min_ttl_attr.attr, &lru_gen_enabled_attr.attr, NULL }; @@ -5294,12 +5358,16 @@ static struct attribute_group lru_gen_attr_group = { 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]); |