linux-kernel - Re: [PATCH 4/4] sched/rt: Split cpupri_vec->cpumask to per NUMA node to reduce contention

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] [day] [month] [year] [list]

Message-ID: <36eb3d2e-03f3-4829-b0f6-94b0f3371629@intel.com>
Date: Mon, 21 Jul 2025 19:23:59 +0800
From: "Chen, Yu C" <yu.c.chen@...el.com>
To: Pan Deng <pan.deng@...el.com>
CC: <linux-kernel@...r.kernel.org>, <tianyou.li@...el.com>,
	<tim.c.chen@...ux.intel.com>, <peterz@...radead.org>, <mingo@...nel.org>
Subject: Re: [PATCH 4/4] sched/rt: Split cpupri_vec->cpumask to per NUMA node
 to reduce contention

On 7/7/2025 10:35 AM, Pan Deng wrote:
> When running a multi-instance FFmpeg workload on HCC system, significant
> contention is observed on bitmap of `cpupri_vec->cpumask`.
> 
> The SUT is a 2-socket machine with 240 physical cores and 480 logical
> CPUs. 60 FFmpeg instances are launched, each pinned to 4 physical cores
> (8 logical CPUs) for transcoding tasks. Sub-threads use RT priority 99
> with FIFO scheduling. FPS is used as score.
> 
> perf c2c tool reveals:
> cpumask (bitmap) cache line of `cpupri_vec->mask`:
> - bits are loaded during cpupri_find
> - bits are stored during cpupri_set
> - cycles per load: ~2.2K to 8.7K
> 
> This change splits `cpupri_vec->cpumask` into per-NUMA-node data to
> mitigate false sharing.
> 
> As a result:
> - FPS improves by ~3.8%
> - Kernel cycles% drops from ~20% to ~18.7%
> - Cache line contention is mitigated, perf-c2c shows cycles per load
>    drops from ~2.2K-8.7K to ~0.5K-2.2K
> 

This brings noticeable improvement for RT workload, and it would
be even more convincing if we can have try on normal task workload,
at least not bring regression(schbench/hackbenc, etc).

thanks,
Chenyu

> Note: CONFIG_CPUMASK_OFFSTACK=n remains unchanged.
>