linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Roman Gushchin <guro@fb.com>
To: <linux-mm@kvack.org>
Cc: Roman Gushchin <guro@fb.com>, Michal Hocko <mhocko@kernel.org>,
	Vladimir Davydov <vdavydov.dev@gmail.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>,
	David Rientjes <rientjes@google.com>, Tejun Heo <tj@kernel.org>,
	<kernel-team@fb.com>, <cgroups@vger.kernel.org>,
	<linux-doc@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: [v6 3/4] mm, oom: introduce oom_priority for memory cgroups
Date: Wed, 23 Aug 2017 17:52:00 +0100	[thread overview]
Message-ID: <20170823165201.24086-4-guro@fb.com> (raw)
In-Reply-To: <20170823165201.24086-1-guro@fb.com>

Introduce a per-memory-cgroup oom_priority setting: an integer number
within the [-10000, 10000] range, which defines the order in which
the OOM killer selects victim memory cgroups.

OOM killer prefers memory cgroups with larger priority if they are
populated with eligible tasks.

The oom_priority value is compared within sibling cgroups.

The root cgroup has the oom_priority 0, which cannot be changed.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: kernel-team@fb.com
Cc: cgroups@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
---
 include/linux/memcontrol.h |  3 +++
 mm/memcontrol.c            | 52 ++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index c57ee47c35bb..915f0c19a2b5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -206,6 +206,9 @@ struct mem_cgroup {
 	/* cached OOM score */
 	long oom_score;
 
+	/* OOM killer priority */
+	short oom_priority;
+
 	/* handle for "memory.events" */
 	struct cgroup_file events_file;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a620aaae6201..a173e5b0d4d8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2749,6 +2749,7 @@ static void select_victim_memcg(struct mem_cgroup *root, struct oom_control *oc)
 	for (;;) {
 		struct cgroup_subsys_state *css;
 		struct mem_cgroup *memcg = NULL;
+		short prio = SHRT_MIN;
 		long score = LONG_MIN;
 
 		css_for_each_child(css, &root->css) {
@@ -2760,7 +2761,12 @@ static void select_victim_memcg(struct mem_cgroup *root, struct oom_control *oc)
 			if (iter->oom_score == 0)
 				continue;
 
-			if (iter->oom_score > score) {
+			if (iter->oom_priority > prio) {
+				memcg = iter;
+				prio = iter->oom_priority;
+				score = iter->oom_score;
+			} else if (iter->oom_priority == prio &&
+				   iter->oom_score > score) {
 				memcg = iter;
 				score = iter->oom_score;
 			}
@@ -2830,7 +2836,15 @@ bool mem_cgroup_select_oom_victim(struct oom_control *oc)
 	 * For system-wide OOMs we should consider tasks in the root cgroup
 	 * with oom_score larger than oc->chosen_points.
 	 */
-	if (!oc->memcg) {
+	if (!oc->memcg && !(oc->chosen_memcg &&
+			    oc->chosen_memcg->oom_priority > 0)) {
+		/*
+		 * Root memcg has priority 0, so if chosen memcg has lower
+		 * priority, any task in root cgroup is preferable.
+		 */
+		if (oc->chosen_memcg && oc->chosen_memcg->oom_priority < 0)
+			oc->chosen_points = 0;
+
 		select_victim_root_cgroup_task(oc);
 
 		if (oc->chosen_task && oc->chosen_memcg) {
@@ -5426,6 +5440,34 @@ static ssize_t memory_oom_kill_all_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static int memory_oom_priority_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	seq_printf(m, "%d\n", memcg->oom_priority);
+
+	return 0;
+}
+
+static ssize_t memory_oom_priority_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	int oom_priority;
+	int err;
+
+	err = kstrtoint(strstrip(buf), 0, &oom_priority);
+	if (err)
+		return err;
+
+	if (oom_priority < -10000 || oom_priority > 10000)
+		return -EINVAL;
+
+	memcg->oom_priority = (short)oom_priority;
+
+	return nbytes;
+}
+
 static int memory_events_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
@@ -5552,6 +5594,12 @@ static struct cftype memory_files[] = {
 		.write = memory_oom_kill_all_write,
 	},
 	{
+		.name = "oom_priority",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = memory_oom_priority_show,
+		.write = memory_oom_priority_write,
+	},
+	{
 		.name = "events",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.file_offset = offsetof(struct mem_cgroup, events_file),
-- 
2.13.5

  parent reply	other threads:[~2017-08-23 16:53 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-08-23 16:51 [v6 1/4] mm, oom: refactor the oom_kill_process() function Roman Gushchin
2017-08-23 16:51 ` [v6 0/4] cgroup-aware OOM killer Roman Gushchin
2017-08-23 16:51 ` [v6 2/4] mm, oom: " Roman Gushchin
2017-08-23 23:19   ` David Rientjes
2017-08-25 10:57     ` Roman Gushchin
2017-08-24 11:47   ` Michal Hocko
2017-08-24 12:28     ` Roman Gushchin
2017-08-24 12:58       ` Michal Hocko
2017-08-24 13:58         ` Roman Gushchin
2017-08-24 14:13           ` Michal Hocko
2017-08-24 14:58             ` Roman Gushchin
2017-08-25  8:14               ` Michal Hocko
2017-08-25 10:39                 ` Roman Gushchin
2017-08-25 10:58                   ` Michal Hocko
2017-08-30 11:22                 ` Roman Gushchin
2017-08-30 20:56                   ` David Rientjes
2017-08-31 13:34                     ` Roman Gushchin
2017-08-31 20:01                       ` David Rientjes
2017-08-23 16:52 ` Roman Gushchin [this message]
2017-08-24 12:10   ` [v6 3/4] mm, oom: introduce oom_priority for memory cgroups Michal Hocko
2017-08-24 12:51     ` Roman Gushchin
2017-08-24 13:48       ` Michal Hocko
2017-08-24 14:11         ` Roman Gushchin
2017-08-28 20:54           ` David Rientjes
2017-08-23 16:52 ` [v6 4/4] mm, oom, docs: describe the cgroup-aware OOM killer Roman Gushchin
2017-08-24 11:15 ` [v6 1/4] mm, oom: refactor the oom_kill_process() function Michal Hocko

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=20170823165201.24086-4-guro@fb.com \
    --to=guro@fb.com \
    --cc=cgroups@vger.kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=kernel-team@fb.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=penguin-kernel@I-love.SAKURA.ne.jp \
    --cc=rientjes@google.com \
    --cc=tj@kernel.org \
    --cc=vdavydov.dev@gmail.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).