linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Yu Zhao <yuzhao@google.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	 Mel Gorman <mgorman@suse.de>, Michal Hocko <mhocko@kernel.org>
Cc: "Andi Kleen" <ak@linux.intel.com>,
	"Aneesh Kumar" <aneesh.kumar@linux.ibm.com>,
	"Barry Song" <21cnbao@gmail.com>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Dave Hansen" <dave.hansen@linux.intel.com>,
	"Hillf Danton" <hdanton@sina.com>, "Jens Axboe" <axboe@kernel.dk>,
	"Jesse Barnes" <jsbarnes@google.com>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Linus Torvalds" <torvalds@linux-foundation.org>,
	"Matthew Wilcox" <willy@infradead.org>,
	"Michael Larabel" <Michael@michaellarabel.com>,
	"Mike Rapoport" <rppt@kernel.org>,
	"Rik van Riel" <riel@surriel.com>,
	"Vlastimil Babka" <vbabka@suse.cz>,
	"Will Deacon" <will@kernel.org>,
	"Ying Huang" <ying.huang@intel.com>,
	linux-arm-kernel@lists.infradead.org, linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	page-reclaim@google.com, x86@kernel.org,
	"Yu Zhao" <yuzhao@google.com>,
	"Brian Geffon" <bgeffon@google.com>,
	"Jan Alexander Steffens" <heftig@archlinux.org>,
	"Oleksandr Natalenko" <oleksandr@natalenko.name>,
	"Steven Barrett" <steven@liquorix.net>,
	"Suleiman Souhlal" <suleiman@google.com>,
	"Daniel Byrne" <djbyrne@mtu.edu>,
	"Donald Carr" <d@chaos-reins.com>,
	"Holger Hoffstätte" <holger@applied-asynchrony.com>,
	"Konstantin Kharlamov" <Hi-Angel@yandex.ru>,
	"Shuang Zhai" <szhai2@cs.rochester.edu>,
	"Sofia Trinh" <sofia.trinh@edi.works>
Subject: [PATCH v7 10/12] mm: multigenerational LRU: thrashing prevention
Date: Tue,  8 Feb 2022 01:19:00 -0700	[thread overview]
Message-ID: <20220208081902.3550911-11-yuzhao@google.com> (raw)
In-Reply-To: <20220208081902.3550911-1-yuzhao@google.com>

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
can't 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's easier to configure because it's agnostic to applications and
   memory sizes.
2) It's more reliable because it's directly wired to the OOM killer.

[1] https://lore.kernel.org/lkml/Ydza%2FzXKY9ATRoh6@google.com/
[2] https://lore.kernel.org/lkml/20211130201652.2218636d@mail.inbox.lv/

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>
---
 mm/vmscan.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 60 insertions(+), 4 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 700c35f2a030..4d37d63668b5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4335,7 +4335,8 @@ static long get_nr_evictable(struct lruvec *lruvec, unsigned long max_seq,
 	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;
@@ -4344,14 +4345,22 @@ static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	DEFINE_MAX_SEQ(lruvec);
 	DEFINE_MIN_SEQ(lruvec);
 
+	if (min_ttl) {
+		int gen = lru_gen_from_seq(min_seq[TYPE_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;
 
@@ -4360,11 +4369,18 @@ static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 
 	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());
 
@@ -4390,11 +4406,28 @@ 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)));
 
+	/*
+	 * 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);
+	}
+
 	current->reclaim_state->mm_walk = NULL;
 }
 
@@ -5107,6 +5140,28 @@ static void lru_gen_change_state(bool enable)
  *                          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;
@@ -5155,6 +5210,7 @@ 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
 };
-- 
2.35.0.263.gb82422642f-goog



  parent reply	other threads:[~2022-02-08  8:19 UTC|newest]

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-02-08  8:18 [PATCH v7 00/12] Multigenerational LRU Framework Yu Zhao
2022-02-08  8:18 ` [PATCH v7 01/12] mm: x86, arm64: add arch_has_hw_pte_young() Yu Zhao
2022-02-08  8:24   ` Yu Zhao
2022-02-08 10:33   ` Will Deacon
2022-02-08  8:18 ` [PATCH v7 02/12] mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG Yu Zhao
2022-02-08  8:27   ` Yu Zhao
2022-02-08  8:18 ` [PATCH v7 03/12] mm/vmscan.c: refactor shrink_node() Yu Zhao
2022-02-08  8:18 ` [PATCH v7 04/12] mm: multigenerational LRU: groundwork Yu Zhao
2022-02-08  8:28   ` Yu Zhao
2022-02-10 20:41   ` Johannes Weiner
2022-02-15  9:43     ` Yu Zhao
2022-02-15 21:53       ` Johannes Weiner
2022-02-21  8:14         ` Yu Zhao
2022-02-23 21:18           ` Yu Zhao
2022-02-25 16:34             ` Minchan Kim
2022-03-03 15:29           ` Johannes Weiner
2022-03-03 19:26             ` Yu Zhao
2022-03-03 21:43               ` Johannes Weiner
2022-03-11 10:16       ` Barry Song
2022-03-11 23:45         ` Yu Zhao
2022-03-12 10:37           ` Barry Song
2022-03-12 21:11             ` Yu Zhao
2022-03-13  4:57               ` Barry Song
2022-03-14 11:11                 ` Barry Song
2022-03-14 16:45                   ` Yu Zhao
2022-03-14 23:38                     ` Barry Song
     [not found]                       ` <CAOUHufa9eY44QadfGTzsxa2=hEvqwahXd7Canck5Gt-N6c4UKA@mail.gmail.com>
     [not found]                         ` <CAGsJ_4zvj5rmz7DkW-kJx+jmUT9G8muLJ9De--NZma9ey0Oavw@mail.gmail.com>
2022-03-15 10:29                           ` Barry Song
2022-03-16  2:46                             ` Yu Zhao
2022-03-16  4:37                               ` Barry Song
2022-03-16  5:44                                 ` Yu Zhao
2022-03-16  6:06                                   ` Barry Song
2022-03-16 21:37                                     ` Yu Zhao
2022-02-10 21:37   ` Matthew Wilcox
2022-02-13 21:16     ` Yu Zhao
2022-02-08  8:18 ` [PATCH v7 05/12] mm: multigenerational LRU: minimal implementation Yu Zhao
2022-02-08  8:33   ` Yu Zhao
2022-02-08 16:50   ` Johannes Weiner
2022-02-10  2:53     ` Yu Zhao
2022-02-13 10:04   ` Hillf Danton
2022-02-17  0:13     ` Yu Zhao
2022-02-23  8:27   ` Huang, Ying
2022-02-23  9:36     ` Yu Zhao
2022-02-24  0:59       ` Huang, Ying
2022-02-24  1:34         ` Yu Zhao
2022-02-24  3:31           ` Huang, Ying
2022-02-24  4:09             ` Yu Zhao
2022-02-24  5:27               ` Huang, Ying
2022-02-24  5:35                 ` Yu Zhao
2022-02-08  8:18 ` [PATCH v7 06/12] mm: multigenerational LRU: exploit locality in rmap Yu Zhao
2022-02-08  8:40   ` Yu Zhao
2022-02-08  8:18 ` [PATCH v7 07/12] mm: multigenerational LRU: support page table walks Yu Zhao
2022-02-08  8:39   ` Yu Zhao
2022-02-08  8:18 ` [PATCH v7 08/12] mm: multigenerational LRU: optimize multiple memcgs Yu Zhao
2022-02-08  8:18 ` [PATCH v7 09/12] mm: multigenerational LRU: runtime switch Yu Zhao
2022-02-08  8:42   ` Yu Zhao
2022-02-08  8:19 ` Yu Zhao [this message]
2022-02-08  8:43   ` [PATCH v7 10/12] mm: multigenerational LRU: thrashing prevention Yu Zhao
2022-02-08  8:19 ` [PATCH v7 11/12] mm: multigenerational LRU: debugfs interface Yu Zhao
2022-02-18 18:56   ` [page-reclaim] " David Rientjes
2022-02-08  8:19 ` [PATCH v7 12/12] mm: multigenerational LRU: documentation Yu Zhao
2022-02-08  8:44   ` Yu Zhao
2022-02-14 10:28   ` Mike Rapoport
2022-02-16  3:22     ` Yu Zhao
2022-02-21  9:01       ` Mike Rapoport
2022-02-22  1:47         ` Yu Zhao
2022-02-23 10:58           ` Mike Rapoport
2022-02-23 21:20             ` Yu Zhao
2022-02-08 10:11 ` [PATCH v7 00/12] Multigenerational LRU Framework Oleksandr Natalenko
2022-02-08 11:14   ` Michal Hocko
2022-02-08 11:23     ` Oleksandr Natalenko
2022-02-11 20:12 ` Alexey Avramov
2022-02-12 21:01   ` Yu Zhao
2022-03-03  6:06 ` Vaibhav Jain
2022-03-03  6:47   ` Yu Zhao

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220208081902.3550911-11-yuzhao@google.com \
    --to=yuzhao@google.com \
    --cc=21cnbao@gmail.com \
    --cc=Hi-Angel@yandex.ru \
    --cc=Michael@michaellarabel.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=axboe@kernel.dk \
    --cc=bgeffon@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=corbet@lwn.net \
    --cc=d@chaos-reins.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=djbyrne@mtu.edu \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=heftig@archlinux.org \
    --cc=holger@applied-asynchrony.com \
    --cc=jsbarnes@google.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@kernel.org \
    --cc=oleksandr@natalenko.name \
    --cc=page-reclaim@google.com \
    --cc=riel@surriel.com \
    --cc=rppt@kernel.org \
    --cc=sofia.trinh@edi.works \
    --cc=steven@liquorix.net \
    --cc=suleiman@google.com \
    --cc=szhai2@cs.rochester.edu \
    --cc=torvalds@linux-foundation.org \
    --cc=vbabka@suse.cz \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    --cc=ying.huang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).