Commit 1332a809 authored by Yu Zhao's avatar Yu Zhao Committed by Andrew Morton
Browse files

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: default avatarYu Zhao <yuzhao@google.com>
Acked-by: default avatarBrian Geffon <bgeffon@google.com>
Acked-by: default avatarJan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: default avatarOleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: default avatarSteven Barrett <steven@liquorix.net>
Acked-by: default avatarSuleiman Souhlal <suleiman@google.com>
Tested-by: default avatarDaniel Byrne <djbyrne@mtu.edu>
Tested-by: default avatarDonald Carr <d@chaos-reins.com>
Tested-by: default avatarHolger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: default avatarKonstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: default avatarShuang Zhai <szhai2@cs.rochester.edu>
Tested-by: default avatarSofia Trinh <sofia.trinh@edi.works>
Tested-by: default avatarVaibhav 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: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 354ed597

include/linux/mmzone.h

+2 −0
Original line number Diff line number Diff line
@@ -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 */

mm/vmscan.c

+71 −3
Original line number Diff line number Diff line
@@ -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 @@ static void lru_gen_change_state(bool enabled) 
 *                          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]);