From: Chen Yu <chen.yu@linux.dev>
To: Luo Gengkun <luogengkun@huaweicloud.com>, tim.c.chen@linux.intel.com
Cc: peterz@infradead.org, mingo@redhat.com, juri.lelli@redhat.com,
vincent.guittot@linaro.org, tim.c.chen@linux.intel.com,
yu.c.chen@intel.com, kprateek.nayak@amd.com,
dietmar.eggemann@arm.com, rostedt@goodmis.org,
bsegall@google.com, mgorman@suse.de, vschneid@redhat.com,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v11 1/2] sched/cache: Reduce the overhead of task_cache_work by only scan the visisted cpus
Date: Mon, 16 Nov 2026 15:24:25 +0800 [thread overview]
Message-ID: <avqvqemiHxuQVH8b@three-body> (raw)
In-Reply-To: <20261111110409.1498035-2-luogengkun@huaweicloud.com>
On Wed, Nov 11, 2026 at 11:04:08AM +0000, Luo Gengkun wrote:
> Date: Wed, 11 Nov 2026 11:04:08 +0000
> From: Luo Gengkun <luogengkun@huaweicloud.com>
> To: peterz@infradead.org, mingo@redhat.com, juri.lelli@redhat.com,
> vincent.guittot@linaro.org, tim.c.chen@linux.intel.com,
> yu.c.chen@intel.com, kprateek.nayak@amd.com
> Cc: dietmar.eggemann@arm.com, rostedt@goodmis.org, bsegall@google.com,
> mgorman@suse.de, vschneid@redhat.com, linux-kernel@vger.kernel.org
> Subject: [PATCH v11 1/2] sched/cache: Reduce the overhead of
> task_cache_work by only scan the visisted cpus
> X-Mailer: git-send-email 2.34.1
>
> The overhead of task_cache_work() is high, especially in multi-NUMA systems.
> Currently, task_cache_work() tries to find the pref_llc by scanning all CPUs
> in the system. However, most of these scans are meaningless, such as those
> for CPUs that have never been visited or were accessed a long time ago.
>
> To address this problem, introduce visited_cpus to track the visited CPUs
> and evict them once they have not been accessed for a duration exceeding
> llc_epoch_affinity_timeout.
>
> Now that we know exactly which CPUs to scan from visited_cpus, we can remove
> get_scan_cpumasks().
>
> Below are the Redis test results conducted on AMD server.
>
> When NUMA balancing is disabled:
>
> valkey-benchmark rps | baseline | schedcache | schedcache_visit
> | (no cache aware) | (without this series) | (with this series)
> ----------------------+---------------------+---------------------+-----------+-------------------+--------
> | p99 latency(ms) | p99 latency(ms) | DIFF(%) | p99 latency(ms) | DIFF(%)
> 400000 | 0.436 | 0.554 | -25.68% | 0.441 | -1.14%
>
> Additionally, the output of perf top -e cycles:k highlights the overhead
> incurred by task_cache_work():
>
> valkey-benchmark rps | schedcache | schedcache_visit
> | (without this series) | (with this series)
> ----------------------+-------------------------------------------+---------------------------------------
> 400000 | 0.81% [kernel] [k] task_cache_work | 0.02% [kernel] [k] task_cache_work
>
> The trace data is shown below:
>
> echo NO_SC_VISIT > /sys/kernel/debug/sched/features
> redis-server-24660 [195] ..... 2916.005989: sched_cache_scan: comm=redis-server pid=24660 scan=384
> valkey-benchmar-48836 [317] ..... 2916.005993: sched_cache_scan: comm=valkey-benchmar pid=48836 scan=384
> valkey-benchmar-48487 [310] ..... 2916.006002: sched_cache_scan: comm=valkey-benchmar pid=48487 scan=384
>
> echo SC_VISIT > /sys/kernel/debug/sched/features
> redis-server-29080 [225] ..... 2876.257909: sched_cache_scan: comm=redis-server pid=29080 scan=14
> redis-server-26694 [018] ..... 2876.257909: sched_cache_scan: comm=redis-server pid=26694 scan=13
> valkey-benchmar-48198 [103] ..... 2876.257909: sched_cache_scan: comm=valkey-benchmar pid=48198 scan=16
>
SC_VISIT is not in the formal patch, so maybe adjust the comment above to say that this SC_VISIT is a trial
test feature and provide the link. But it is still OK to keep this as it is now.
Tim, may I know if this version looks good to you?
thanks,
Chenyu
>
> Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
> Tested-by: Chen Yu <yu.c.chen@intel.com>
> Reviewed-by: Chen Yu <yu.c.chen@intel.com>
> Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
>
next prev parent reply other threads:[~2026-11-16 7:23 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-11 11:04 [PATCH v11 0/2] Cache aware scheduling: Reduce the overhead of task_cache_work Luo Gengkun
2026-11-11 11:04 ` [PATCH v11 1/2] sched/cache: Reduce the overhead of task_cache_work by only scan the visisted cpus Luo Gengkun
2026-11-16 7:24 ` Chen Yu [this message]
2026-11-16 23:38 ` Tim Chen
2026-11-17 18:27 ` Tim Chen
2026-11-11 11:04 ` [PATCH v11 2/2] -- DO NOT APPLY!!! -- sched/cache/debug: Add trace event and sched feature to track scan cost Luo Gengkun
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=avqvqemiHxuQVH8b@three-body \
--to=chen.yu@linux.dev \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=juri.lelli@redhat.com \
--cc=kprateek.nayak@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luogengkun@huaweicloud.com \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tim.c.chen@linux.intel.com \
--cc=vincent.guittot@linaro.org \
--cc=vschneid@redhat.com \
--cc=yu.c.chen@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.