linux-kernel - Re: [External] Re: [PATCH] cgroup/rstat: record the cumulative per-cpu time of cgroup and its descendants

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <ZLcJ1nH8KzWzoQWj@slm.duckdns.org>
Date:   Tue, 18 Jul 2023 11:53:26 -1000
From:   Tejun Heo <tj@...nel.org>
To:     Hao Jia <jiahao.os@...edance.com>
Cc:     lizefan.x@...edance.com, hannes@...xchg.org, mkoutny@...e.com,
        cgroups@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [External] Re: [PATCH] cgroup/rstat: record the cumulative
 per-cpu time of cgroup and its descendants

On Tue, Jul 18, 2023 at 06:08:50PM +0800, Hao Jia wrote:
> https://github.com/jiaozhouxiaojia/cgv2-stat-percpu_test/tree/main

Isn't that just adding the same numbers twice and verifying that? Maybe I'm
misunderstanding you. Here's a simpler case:

  # cd /sys/fs/cgroup
  # mkdir -p asdf/test0
  # grep usage_usec asdf/test0/cpu.stat
  usage_usec 0
  # echo $$ > asdf/test0/cgroup.procs
  # stress -c 1 & sleep 1; kill %%
  [1] 122329
  stress: info: [122329] dispatching hogs: 1 cpu, 0 io, 0 vm, 0 hdd
  # grep usage_usec asdf/test0/cpu.stat
  usage_usec 1000956
  [1]+  Terminated              stress -c 1
  # grep usage_usec asdf/cpu.stat
  usage_usec 1002548
  # echo $$ > /sys/fs/cgroup/cgroup.procs
  # rmdir asdf/test0
  # grep usage_usec asdf/cpu.stat
  usage_usec 1006338

So, we run `stress -c 1` for 1 second in the asdf/test0 cgroup and
asdf/cpu.stat correctly reports the cumulative usage. After removing
asdf/test0 cgroup, asdf's usage_usec is still there. What's missing here?
What are you adding?

Thanks.

-- 
tejun