mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Chen, Yu C" <yu.c.chen@intel.com>
To: Shakeel Butt <shakeel.butt@linux.dev>
Cc: <peterz@infradead.org>, <akpm@linux-foundation.org>,
	<mkoutny@suse.com>, <mingo@redhat.com>, <tj@kernel.org>,
	<hannes@cmpxchg.org>, <corbet@lwn.net>, <mgorman@suse.de>,
	<mhocko@kernel.org>, <muchun.song@linux.dev>,
	<roman.gushchin@linux.dev>, <tim.c.chen@intel.com>,
	<aubrey.li@intel.com>, <libo.chen@oracle.com>,
	<kprateek.nayak@amd.com>, <vineethr@linux.ibm.com>,
	<venkat88@linux.ibm.com>, <ayushjai@amd.com>,
	<cgroups@vger.kernel.org>, <linux-doc@vger.kernel.org>,
	<linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>,
	<yu.chen.surf@foxmail.com>
Subject: Re: [PATCH v5 2/2] sched/numa: add statistics of numa balance task
Date: Sat, 24 May 2025 17:07:57 +0800	[thread overview]
Message-ID: <ad9f8af5-6bac-48c0-924b-498863370079@intel.com> (raw)
In-Reply-To: <cx4s4pnw5ymr4bxxmvrkhc457krq46eh6zamlr4ikp7tn3jsno@xzchjlnnawe5>

Hi Shakeel,

On 5/24/2025 7:42 AM, Shakeel Butt wrote:
> On Fri, May 23, 2025 at 08:51:15PM +0800, Chen Yu wrote:
>> On systems with NUMA balancing enabled, it has been found
>> that tracking task activities resulting from NUMA balancing
>> is beneficial. NUMA balancing employs two mechanisms for task
>> migration: one is to migrate a task to an idle CPU within its
>> preferred node, and the other is to swap tasks located on
>> different nodes when they are on each other's preferred nodes.
>>
>> The kernel already provides NUMA page migration statistics in
>> /sys/fs/cgroup/mytest/memory.stat and /proc/{PID}/sched. However,
>> it lacks statistics regarding task migration and swapping.
>> Therefore, relevant counts for task migration and swapping should
>> be added.
>>
>> The following two new fields:
>>
>> numa_task_migrated
>> numa_task_swapped
>>
>> will be shown in /sys/fs/cgroup/{GROUP}/memory.stat, /proc/{PID}/sched
>> and /proc/vmstat
> 
> Hmm these are scheduler events, how are these relevant to memory cgroup
> or vmstat? 
> Any reason to not expose these in cpu.stat?
> 

I understand that in theory they are scheduling activities.
The reason for including these statistics here was mainly that
I assumed there is a close relationship between page migration
and task migration in Numa Balance. Specifically, task migration
is triggered when page migration fails.
Placing these statistics closer to the existing Numa Balance page
statistics in /sys/fs/cgroup/{GROUP}/memory.stat and /proc/vmstat
may help users query relevant data from a single file, avoiding
the need to search through scattered files.
Notably, these events are associated with a task’s working set
(footprint) rather than pure CPU cycles IMO. I took a look at
the cpu_cfs_stat_show() for cpu.stat, it seems that a lot of
code is needed if we want to expose them in cpu.stat, while
reusing existing interface of count_memcg_event_mm() is simpler.

thanks,
Chenyu





  reply	other threads:[~2025-05-24  9:08 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-23 12:48 [PATCH v5 0/2] sched/numa: add statistics of numa balance task migration Chen Yu
2025-05-23 12:51 ` [PATCH v5 1/2] sched/numa: fix task swap by skipping kernel threads Chen Yu
2025-05-23 23:22   ` Shakeel Butt
2025-05-23 12:51 ` [PATCH v5 2/2] sched/numa: add statistics of numa balance task Chen Yu
2025-05-23 23:42   ` Shakeel Butt
2025-05-24  9:07     ` Chen, Yu C [this message]
2025-05-24 17:32       ` Shakeel Butt
2025-05-25 12:35         ` Chen, Yu C
2025-05-27 17:48           ` Shakeel Butt
2025-05-29  5:04             ` Chen, Yu C
2025-05-26 13:35     ` Michal Koutný
2025-05-27  9:20       ` Chen, Yu C
2025-05-27 18:15         ` Shakeel Butt
2025-06-02 16:53           ` Michal Koutný
2025-06-03 14:46             ` Chen, Yu C
2025-06-17  9:30               ` Michal Koutný
2025-06-19 13:03                 ` Chen, Yu C
2025-06-19 14:06                   ` Michal Koutný
2025-05-23 22:06 ` [PATCH v5 0/2] sched/numa: add statistics of numa balance task migration Andrew Morton
2025-05-23 23:52   ` Shakeel Butt
2025-05-28  0:21     ` Andrew Morton

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=ad9f8af5-6bac-48c0-924b-498863370079@intel.com \
    --to=yu.c.chen@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=aubrey.li@intel.com \
    --cc=ayushjai@amd.com \
    --cc=cgroups@vger.kernel.org \
    --cc=corbet@lwn.net \
    --cc=hannes@cmpxchg.org \
    --cc=kprateek.nayak@amd.com \
    --cc=libo.chen@oracle.com \
    --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=mingo@redhat.com \
    --cc=mkoutny@suse.com \
    --cc=muchun.song@linux.dev \
    --cc=peterz@infradead.org \
    --cc=roman.gushchin@linux.dev \
    --cc=shakeel.butt@linux.dev \
    --cc=tim.c.chen@intel.com \
    --cc=tj@kernel.org \
    --cc=venkat88@linux.ibm.com \
    --cc=vineethr@linux.ibm.com \
    --cc=yu.chen.surf@foxmail.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

all inboxes | Powered by JetHome®