From: liujing<liujing@cmss.chinamobile.com>
To: akpm<akpm@linux-foundation.org>
Cc: linux-mm<linux-mm@kvack.org>, linux-kernel<linux-kernel@vger.kernel.org>
Subject: The percpu memory used by memcg cannot be cleared
Date: 30 Aug 2024 11:22:39 +0800 [thread overview]
Message-ID: <20240830112239957689310@cmss.chinamobile.com> (raw)
[-- Attachment #1: Type: text/plain, Size: 3936 bytes --]
\r\r\r\r\r\rhello,linux boss\r\r\r\r\r I found a problem in the process of using linux memcg,When I turned swap off, the memcg memory I created with the following script could not be deleted with echo 0 > memory.force_empty, as explained below。\r\r\r\r\r----------------------------------------------------------------------------------------------------------\r\rstep1:swapoff -a\r\r\r\r\r\r\r\rstep2:use this script to create memcg\r\r\r\r\r\r\r#!/bin/bash\r\rmkdir -p /tmp/test\r\rfor i in 'seq 2000'\r\rdo\r\r sudo mkdir -p /sys/fs/cgroup/memory/user.slice/user-0.slice/test$ {i}\r\r sudo echo $$ > /sys/fs/cgroup/memory/user.slice/user-0.slice/test$ {i}/tasks\r\r sudo echo 'data' > /tmp/test/test$ {i}\r\r sudo echo $$ > /sys/fs/cgroup/memory/user.slice/user-0.slice/tasks\r\r sudo rmdir /sys/fs/cgroup/memory/user.slice/user-0.slice/test$ {i}\r\rdone\r\r\r\r\r\r\r\rstep3:view /proc/cgroup and /proc/meminfo files\r\r\r\r\r\r\r[root@localhost ~]# cat /proc/cgroups\r\r#subsys_name hierarchy num_cgroups enabled\r\rcpuset 10 1 1\r\rcpu 4 1 1\r\rcpuacct 4 1 1\r\rblkio 13 1 1\r\rmemory 14 2009 1\r\rdevices 6 94 1\r\r\r\r\r\r\r[root@localhost ~]# cat /proc/meminfo | grep Percpu\r\rPercpu: 600576 kB\r\r\r\r\r\r\r\rstep4:when I use "echo 0 > /sys/fs/cgroup/memory/user.slice/user-0.slice/memory.force_empty", I find the num_cgroups of memory and percpu have no changed\r\r\r\r\r\r\r[root@localhost ~]# echo 0 > /sys/fs/cgroup/memory/user.slice/user-0.slice/memory.force_empty\r\r[root@localhost ~]# cat /proc/cgroups\r\r#subsys_name hierarchy num_cgroups enabled\r\rcpuset 10 1 1\r\rcpu 4 1 1\r\rcpuacct 4 1 1\r\rblkio 13 1 1\r\rmemory 14 2039 1\r\rdevices 6 87 1\r\r\r\r\r\r\r[root@localhost ~]# cat /proc/meminfo | grep Percpu\r\rPercpu: 600576 kB\r\r\r\r\r\r\r\rstep 5: when I use swapon -a to open swap, then echo 0 > /sys/fs/cgroup/memory/user.slice/user-0.slice/memory.force_empty again\r\r\r\r\r\r\r[root@localhost ~]# swapon -a\r\r[root@localhost ~]# echo 0 > /sys/fs/cgroup/memory/user.slice/user-0.slice/memory.force_empty\r\r\r\r\r\r\r\rstep 6: view /proc/cgroup and /proc/meminfo files ,I found the the num_cgroups of memory and percpu have been reduced. \r\r\r\r[root@localhost ~]# cat /proc/cgroups\r\r#subsys_name hierarchy num_cgroups enabled\r\rcpuset 10 1 1\r\rcpu 4 1 1\r\rcpuacct 4 1 1\r\rblkio 13 1 1\r\rmemory 14 185 1\r\rdevices 6 87 1\r\rfreezer 9 1 1\r\r\r\r\r\r\r[root@localhost ~]# cat /proc/meminfo | grep Percpu\r\rPercpu: 120832 kB\r\r--------------------------------------------------------------------------------------------------------\r\r\r\r\r\r\r\rTherefore, I want to know why swap affects memcg memory reclamation, echo 0 > memory.force_empty this interface should force the memory used by the cgroup to be reclaimed. \r\rI want to know why ,I look forward to hearing back from the community.\r\rThanks.\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r-----------------------------------------\r\r刘婧 计算产品部\r\r\r\r手机:18896725597\r\r邮箱:liujing@cmss.chinamobile.com\r\r中移(苏州)软件技术有限公司\r\r\r
[-- Attachment #2: Type: text/html, Size: 16267 bytes --]
next reply other threads:[~2024-08-30 3:22 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-30 3:22 liujing [this message]
2024-08-30 7:13 ` Yosry Ahmed
-- strict thread matches above, loose matches on Subject: below --
2024-08-29 17:06 Liu Jing
2024-08-30 7:08 ` 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=20240830112239957689310@cmss.chinamobile.com \
--to=liujing@cmss.chinamobile.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.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