All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Aaron Lu" <ziqianlu@bytedance.com>
To: "Chen Yu" <yu.c.chen@intel.com>, "Tim Chen" <tim.c.chen@linux.intel.com>
Cc: "Peter Zijlstra" <peterz@infradead.org>,
	 "Ingo Molnar" <mingo@redhat.com>,
	 "K Prateek Nayak" <kprateek.nayak@amd.com>,
	 "Gautham R . Shenoy" <gautham.shenoy@amd.com>,
	 "Vincent Guittot" <vincent.guittot@linaro.org>,
	 "Juri Lelli" <juri.lelli@redhat.com>,
	 "Dietmar Eggemann" <dietmar.eggemann@arm.com>,
	 "Steven Rostedt" <rostedt@goodmis.org>,
	 "Ben Segall" <bsegall@google.com>,
	"Mel Gorman" <mgorman@suse.de>,
	 "Valentin Schneider" <vschneid@redhat.com>,
	 "Madadi Vineeth Reddy" <vineethr@linux.ibm.com>,
	 "Hillf Danton" <hdanton@sina.com>,
	 "Shrikanth Hegde" <sshegde@linux.ibm.com>,
	 "Jianyong Wu" <jianyong.wu@outlook.com>,
	 "Yangyu Chen" <cyy@cyyself.name>,
	 "Tingyin Duan" <tingyin.duan@gmail.com>,
	 "Vern Hao" <vernhao@tencent.com>,
	"Vern Hao" <haoxing990@gmail.com>,
	 "Len Brown" <len.brown@intel.com>,
	"Aubrey Li" <aubrey.li@intel.com>,
	 "Zhao Liu" <zhao1.liu@intel.com>,
	"Chen Yu" <yu.chen.surf@gmail.com>,
	 "Adam Li" <adamli@os.amperecomputing.com>,
	 "Tim Chen" <tim.c.chen@intel.com>,
	<linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v2 17/23] sched/cache: Record the number of active threads per process for cache-aware scheduling
Date: Wed, 17 Dec 2025 17:40:53 +0800	[thread overview]
Message-ID: <20251217094053.GA2073381@bytedance.com> (raw)
In-Reply-To: <d14c517c70f1e19bb1223ae705d9a4311420b2ee.1764801860.git.tim.c.chen@linux.intel.com>

On Wed, Dec 03, 2025 at 03:07:36PM -0800, Tim Chen wrote:
> @@ -1501,6 +1507,7 @@ static void __no_profile task_cache_work(struct callback_head *work)
>  		mm->mm_sched_cpu = m_a_cpu;
>  	}
>  
> +	update_avg(&mm->nr_running_avg, nr_running);

update_avg() doesn't appear to deal with small numbers well and can have
an error as large as 7, e.g. when nr_running < 8, nr_running_avg will
always be 0 and when nr_running >= 8 && < 16, nr_running_avg will be
1 - 8, etc.

AMD Genoa has 8 cores per LLC and this will break exceed_llc_nr() there.

>  	free_cpumask_var(cpus);
>  }

  parent reply	other threads:[~2025-12-17  9:41 UTC|newest]

Thread overview: 120+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-03 23:07 [PATCH v2 00/23] Cache aware scheduling Tim Chen
2025-12-03 23:07 ` [PATCH v2 01/23] sched/cache: Introduce infrastructure for cache-aware load balancing Tim Chen
2025-12-09 11:12   ` Peter Zijlstra
2025-12-09 21:39     ` Tim Chen
2025-12-10  9:37   ` Peter Zijlstra
2025-12-10 13:57     ` Chen, Yu C
2025-12-10 15:11       ` Peter Zijlstra
2025-12-11  9:03   ` Vern Hao
2025-12-16  6:12     ` Chen, Yu C
2025-12-17  1:17       ` Vern Hao
2026-01-15 21:47         ` Tim Chen
     [not found]   ` <fbf52d91-0605-4608-b9cc-e8cc56115fd5@gmail.com>
2025-12-16 22:30     ` Tim Chen
2025-12-03 23:07 ` [PATCH v2 02/23] sched/cache: Record per-LLC utilization to guide cache-aware scheduling decisions Tim Chen
2025-12-09 11:21   ` Peter Zijlstra
2025-12-10 14:02     ` Chen, Yu C
2025-12-10 15:13       ` Peter Zijlstra
2025-12-10 23:58         ` Chen, Yu C
2025-12-03 23:07 ` [PATCH v2 03/23] sched/cache: Introduce helper functions to enforce LLC migration policy Tim Chen
2026-01-22 18:13   ` Yangyu Chen
2026-01-22 20:43     ` Tim Chen
2025-12-03 23:07 ` [PATCH v2 04/23] sched/cache: Make LLC id continuous Tim Chen
2025-12-09 11:58   ` Peter Zijlstra
2025-12-15 20:49     ` Tim Chen
2025-12-16  5:31       ` Chen, Yu C
2025-12-16 19:53         ` Tim Chen
2025-12-17  5:25           ` Chen, Yu C
2025-12-23  5:31   ` K Prateek Nayak
2025-12-24  7:08     ` Chen, Yu C
2025-12-24  8:19       ` K Prateek Nayak
2025-12-24  9:46         ` Chen, Yu C
2025-12-26  3:17           ` K Prateek Nayak
2025-12-03 23:07 ` [PATCH v2 05/23] sched/cache: Assign preferred LLC ID to processes Tim Chen
2025-12-09 12:11   ` Peter Zijlstra
2025-12-09 22:34     ` Tim Chen
2025-12-12  3:34   ` Vern Hao
2025-12-15 19:32     ` Tim Chen
2025-12-19  4:01       ` Vern Hao
2025-12-24 10:20         ` Chen, Yu C
2026-01-07  4:49   ` Jianyong Wu
2026-01-07  8:38     ` Chen, Yu C
2025-12-03 23:07 ` [PATCH v2 06/23] sched/cache: Track LLC-preferred tasks per runqueue Tim Chen
2025-12-09 12:16   ` Peter Zijlstra
2025-12-09 22:55     ` Tim Chen
2025-12-10  9:42       ` Peter Zijlstra
2025-12-16  0:20         ` Chen, Yu C
2025-12-17 10:04   ` Vern Hao
2025-12-17 12:37     ` Chen, Yu C
2025-12-03 23:07 ` [PATCH v2 07/23] sched/cache: Introduce per runqueue task LLC preference counter Tim Chen
2025-12-09 13:06   ` Peter Zijlstra
2025-12-09 23:17     ` Tim Chen
2025-12-10 12:43   ` Peter Zijlstra
2025-12-10 18:36     ` Tim Chen
2025-12-10 12:51   ` Peter Zijlstra
2025-12-10 18:49     ` Tim Chen
2025-12-11 10:31       ` Peter Zijlstra
2025-12-15 19:21         ` Tim Chen
2025-12-16 22:45         ` Tim Chen
2025-12-03 23:07 ` [PATCH v2 08/23] sched/cache: Calculate the per runqueue task LLC preference Tim Chen
2025-12-03 23:07 ` [PATCH v2 09/23] sched/cache: Count tasks prefering destination LLC in a sched group Tim Chen
2025-12-10 12:52   ` Peter Zijlstra
2025-12-10 14:05     ` Chen, Yu C
2025-12-10 15:16       ` Peter Zijlstra
2025-12-10 19:00         ` Tim Chen
2025-12-10 23:50         ` Chen, Yu C
2025-12-03 23:07 ` [PATCH v2 10/23] sched/cache: Check local_group only once in update_sg_lb_stats() Tim Chen
2025-12-03 23:07 ` [PATCH v2 11/23] sched/cache: Prioritize tasks preferring destination LLC during balancing Tim Chen
2025-12-03 23:07 ` [PATCH v2 12/23] sched/cache: Add migrate_llc_task migration type for cache-aware balancing Tim Chen
2025-12-10 13:32   ` Peter Zijlstra
2025-12-16  0:52     ` Chen, Yu C
2025-12-03 23:07 ` [PATCH v2 13/23] sched/cache: Handle moving single tasks to/from their preferred LLC Tim Chen
2025-12-03 23:07 ` [PATCH v2 14/23] sched/cache: Consider LLC preference when selecting tasks for load balancing Tim Chen
2025-12-10 15:58   ` Peter Zijlstra
2025-12-03 23:07 ` [PATCH v2 15/23] sched/cache: Respect LLC preference in task migration and detach Tim Chen
2025-12-10 16:30   ` Peter Zijlstra
2025-12-16  7:30     ` Chen, Yu C
2025-12-03 23:07 ` [PATCH v2 16/23] sched/cache: Introduce sched_cache_present to enable cache aware scheduling for multi LLCs NUMA node Tim Chen
2025-12-10 16:32   ` Peter Zijlstra
2025-12-10 16:52     ` Peter Zijlstra
2025-12-16  7:36       ` Chen, Yu C
2025-12-16  7:31     ` Chen, Yu C
2025-12-03 23:07 ` [PATCH v2 17/23] sched/cache: Record the number of active threads per process for cache-aware scheduling Tim Chen
2025-12-10 16:51   ` Peter Zijlstra
2025-12-16  7:40     ` Chen, Yu C
2025-12-17  9:40   ` Aaron Lu [this message]
2025-12-17 12:51     ` Chen, Yu C
2025-12-19  3:32       ` Aaron Lu
2025-12-03 23:07 ` [PATCH v2 18/23] sched/cache: Disable cache aware scheduling for processes with high thread counts Tim Chen
2025-12-03 23:07 ` [PATCH v2 19/23] sched/cache: Avoid cache-aware scheduling for memory-heavy processes Tim Chen
2025-12-18  3:59   ` Vern Hao
2025-12-18  8:32     ` Chen, Yu C
2025-12-18  9:42       ` Vern Hao
2025-12-19  3:14         ` K Prateek Nayak
2025-12-19 12:55           ` Chen, Yu C
2025-12-22  2:49             ` Vern Hao
2025-12-22  2:19           ` Vern Hao
2025-12-03 23:07 ` [PATCH v2 20/23] sched/cache: Add user control to adjust the parameters of cache-aware scheduling Tim Chen
2025-12-10 17:02   ` Peter Zijlstra
2025-12-16  7:42     ` Chen, Yu C
2025-12-19  4:14   ` Vern Hao
2025-12-19 13:21     ` Chen, Yu C
2025-12-19 13:39     ` Chen, Yu C
2025-12-23 12:12   ` Yangyu Chen
2025-12-23 16:44     ` Yangyu Chen
2025-12-24  3:28       ` Yangyu Chen
2025-12-24  7:51         ` Chen, Yu C
2025-12-24 12:15           ` Yangyu Chen
2026-01-15 10:03   ` Jianyong Wu
2026-01-15 12:13     ` Chen, Yu C
2026-01-21 15:21   ` Yangyu Chen
2026-01-21 15:38     ` Chen, Yu C
2025-12-03 23:07 ` [PATCH v2 21/23] -- DO NOT APPLY!!! -- sched/cache/stats: Add schedstat for cache aware load balancing Tim Chen
2025-12-19  5:03   ` Yangyu Chen
2025-12-19 14:41     ` Chen, Yu C
2025-12-19 14:48       ` Yangyu Chen
2025-12-03 23:07 ` [PATCH v2 22/23] -- DO NOT APPLY!!! -- sched/cache/debug: Add ftrace to track the load balance statistics Tim Chen
2025-12-03 23:07 ` [PATCH v2 23/23] -- DO NOT APPLY!!! -- sched/cache/debug: Display the per LLC occupancy for each process via proc fs Tim Chen
2025-12-17  9:59   ` Aaron Lu
2025-12-17 13:01     ` Chen, Yu C
2025-12-19  3:19 ` [PATCH v2 00/23] Cache aware scheduling Aaron Lu
2025-12-19 13:04   ` Chen, Yu C

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=20251217094053.GA2073381@bytedance.com \
    --to=ziqianlu@bytedance.com \
    --cc=adamli@os.amperecomputing.com \
    --cc=aubrey.li@intel.com \
    --cc=bsegall@google.com \
    --cc=cyy@cyyself.name \
    --cc=dietmar.eggemann@arm.com \
    --cc=gautham.shenoy@amd.com \
    --cc=haoxing990@gmail.com \
    --cc=hdanton@sina.com \
    --cc=jianyong.wu@outlook.com \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=sshegde@linux.ibm.com \
    --cc=tim.c.chen@intel.com \
    --cc=tim.c.chen@linux.intel.com \
    --cc=tingyin.duan@gmail.com \
    --cc=vernhao@tencent.com \
    --cc=vincent.guittot@linaro.org \
    --cc=vineethr@linux.ibm.com \
    --cc=vschneid@redhat.com \
    --cc=yu.c.chen@intel.com \
    --cc=yu.chen.surf@gmail.com \
    --cc=zhao1.liu@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.