From: Waiman Long <longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
To: Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>,
Michal Hocko <mhocko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
Vladimir Davydov
<vdavydov.dev-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
Andrew Morton
<akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>,
Petr Mladek <pmladek-IBi9RG/b67k@public.gmane.org>,
Steven Rostedt <rostedt-nx8X9YLhiw1AfugRpC6u6w@public.gmane.org>,
Sergey Senozhatsky
<senozhatsky-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>,
Andy Shevchenko
<andriy.shevchenko-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>,
Rasmus Villemoes
<linux-qQsb+v5E8BnlAoU/VqSP6n9LOBIZ5rWg@public.gmane.org>
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org,
Ira Weiny <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
Rafael Aquini <aquini-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
Waiman Long <longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Subject: [PATCH v2 3/3] mm/page_owner: Dump memcg information
Date: Sat, 29 Jan 2022 15:53:15 -0500 [thread overview]
Message-ID: <20220129205315.478628-4-longman@redhat.com> (raw)
In-Reply-To: <20220129205315.478628-1-longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
It was found that a number of offlined memcgs were not freed because
they were pinned by some charged pages that were present. Even "echo
1 > /proc/sys/vm/drop_caches" wasn't able to free those pages. These
offlined but not freed memcgs tend to increase in number over time with
the side effect that percpu memory consumption as shown in /proc/meminfo
also increases over time.
In order to find out more information about those pages that pin
offlined memcgs, the page_owner feature is extended to dump memory
cgroup information especially whether the cgroup is offlined or not.
Signed-off-by: Waiman Long <longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
mm/page_owner.c | 31 +++++++++++++++++++++++++++++++
1 file changed, 31 insertions(+)
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 28dac73e0542..8dc5cd0fa227 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -10,6 +10,7 @@
#include <linux/migrate.h>
#include <linux/stackdepot.h>
#include <linux/seq_file.h>
+#include <linux/memcontrol.h>
#include <linux/sched/clock.h>
#include "internal.h"
@@ -331,6 +332,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
depot_stack_handle_t handle)
{
int ret, pageblock_mt, page_mt;
+ unsigned long __maybe_unused memcg_data;
char *kbuf;
count = min_t(size_t, count, PAGE_SIZE);
@@ -365,6 +367,35 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
migrate_reason_names[page_owner->last_migrate_reason]);
}
+#ifdef CONFIG_MEMCG
+ /*
+ * Look for memcg information and print it out
+ */
+ memcg_data = READ_ONCE(page->memcg_data);
+ if (memcg_data) {
+ struct mem_cgroup *memcg = page_memcg_check(page);
+ bool onlined;
+ char name[80];
+
+ if (memcg_data & MEMCG_DATA_OBJCGS)
+ ret += scnprintf(kbuf + ret, count - ret,
+ "Slab cache page\n");
+
+ if (!memcg)
+ goto copy_out;
+
+ onlined = (memcg->css.flags & CSS_ONLINE);
+ cgroup_name(memcg->css.cgroup, name, sizeof(name));
+ ret += scnprintf(kbuf + ret, count - ret,
+ "Charged %sto %smemcg %s\n",
+ PageMemcgKmem(page) ? "(via objcg) " : "",
+ onlined ? "" : "offlined ",
+ name);
+ }
+
+copy_out:
+#endif
+
ret += snprintf(kbuf + ret, count - ret, "\n");
if (ret >= count)
goto err;
--
2.27.0
next prev parent reply other threads:[~2022-01-29 20:53 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-29 20:53 [PATCH v2 0/3] mm/page_owner: Extend page_owner to show memcg information Waiman Long
[not found] ` <20220129205315.478628-1-longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-01-29 20:53 ` [PATCH v2 1/3] lib/vsprintf: Avoid redundant work with 0 size Waiman Long
[not found] ` <20220129205315.478628-2-longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-01-30 20:49 ` David Rientjes
[not found] ` <d99b3c4b-7b6e-529-6e4b-b91b65c92d81-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2022-01-30 20:57 ` Waiman Long
2022-01-31 10:25 ` Andy Shevchenko
2022-01-31 10:30 ` Andy Shevchenko
[not found] ` <Yfe6SfG4CqzWSaMM-XvqNBM/wLWRrdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2022-01-31 10:34 ` Andy Shevchenko
2022-01-31 11:02 ` Rasmus Villemoes
[not found] ` <d44824d4-2dd1-a8ab-d3ee-ac67b749ca6f-qQsb+v5E8BnlAoU/VqSP6n9LOBIZ5rWg@public.gmane.org>
2022-01-31 11:22 ` Andy Shevchenko
2022-01-31 18:48 ` Waiman Long
[not found] ` <c33b6435-1b27-32af-b14c-0f3a0318dcca-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-02-01 7:12 ` Rasmus Villemoes
[not found] ` <f3bcf541-e77b-ca93-ef5c-862f4de99366-qQsb+v5E8BnlAoU/VqSP6n9LOBIZ5rWg@public.gmane.org>
2022-02-01 16:01 ` Waiman Long
2022-01-31 2:53 ` Sergey Senozhatsky
2022-01-31 18:17 ` Roman Gushchin
2022-01-29 20:53 ` [PATCH v2 2/3] mm/page_owner: Use scnprintf() to avoid excessive buffer overrun check Waiman Long
[not found] ` <20220129205315.478628-3-longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-01-31 2:58 ` Sergey Senozhatsky
2022-01-29 20:53 ` Waiman Long [this message]
[not found] ` <20220129205315.478628-4-longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-01-30 6:33 ` [PATCH v2 3/3] mm/page_owner: Dump memcg information Mike Rapoport
2022-01-30 18:22 ` Waiman Long
[not found] ` <82c99093-e44b-7fac-14ab-9e8392d107ea-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-01-30 20:51 ` David Rientjes
2022-01-31 9:38 ` Michal Hocko
[not found] ` <YfeuK5j7cbgM+Oo+-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2022-01-31 16:53 ` Johannes Weiner
[not found] ` <YfgT/9tEREQNiiAN-druUgvl0LCNAfugRpC6u6w@public.gmane.org>
2022-01-31 18:15 ` Roman Gushchin
[not found] ` <YfgnUZQBRkqhrEIb-cx5fftMpWqeCjSd+JxjunQ2O0Ztt9esIQQ4Iyu8u01E@public.gmane.org>
2022-01-31 18:25 ` Michal Hocko
[not found] ` <Yfgpknwr1tMnPkqh-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2022-01-31 18:38 ` Waiman Long
[not found] ` <12686956-612d-d89b-5641-470d5e913090-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-02-01 10:49 ` Michal Hocko
2022-02-01 16:41 ` Waiman Long
[not found] ` <268a8bdf-4c70-b967-f34c-2293b54186f0-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-02-02 8:57 ` Michal Hocko
[not found] ` <YfpHbtffFi2x1L4p-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2022-02-02 15:54 ` Roman Gushchin
2022-02-02 16:38 ` Michal Hocko
[not found] ` <YfqzbwAPKpshXSLK-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2022-02-02 17:51 ` Roman Gushchin
[not found] ` <YfrEpOGObnc0mYAW-cx5fftMpWqeCjSd+JxjunQ2O0Ztt9esIQQ4Iyu8u01E@public.gmane.org>
2022-02-02 17:56 ` Michal Hocko
2022-02-02 16:29 ` Waiman Long
2022-01-31 19:01 ` Waiman Long
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=20220129205315.478628-4-longman@redhat.com \
--to=longman-h+wxahxf7alqt0dzr+alfa@public.gmane.org \
--cc=akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org \
--cc=andriy.shevchenko-VuQAYsv1563Yd54FQh9/CA@public.gmane.org \
--cc=aquini-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org \
--cc=ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org \
--cc=linux-qQsb+v5E8BnlAoU/VqSP6n9LOBIZ5rWg@public.gmane.org \
--cc=mhocko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=pmladek-IBi9RG/b67k@public.gmane.org \
--cc=rostedt-nx8X9YLhiw1AfugRpC6u6w@public.gmane.org \
--cc=senozhatsky-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org \
--cc=vdavydov.dev-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
/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).