[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <7747fd63-0677-4485-862f-5d794f9e6a85@amd.com>
Date: Mon, 1 Sep 2025 09:27:46 +0530
From: K Prateek Nayak <kprateek.nayak@....com>
To: Shrikanth Hegde <sshegde@...ux.ibm.com>, Andrea Righi <arighi@...dia.com>
CC: Peter Zijlstra <peterz@...radead.org>, Dietmar Eggemann
<dietmar.eggemann@....com>, Steven Rostedt <rostedt@...dmis.org>, Ben Segall
<bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>, Valentin Schneider
<vschneid@...hat.com>, Swapnil Sapkal <swapnil.sapkal@....com>, Ricardo Neri
<ricardo.neri-calderon@...ux.intel.com>, Tim Chen
<tim.c.chen@...ux.intel.com>, Vinicius Costa Gomes
<vinicius.gomes@...el.com>, Ingo Molnar <mingo@...hat.com>, Juri Lelli
<juri.lelli@...hat.com>, Vincent Guittot <vincent.guittot@...aro.org>,
linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v7 4/8] powerpc/smp: Introduce CONFIG_SCHED_MC to guard MC
scheduling bits
(Trimming the cc to kernel/sched/ folks)
On 8/26/2025 2:57 PM, Shrikanth Hegde wrote:
>
>
> On 8/26/25 9:43 AM, K Prateek Nayak wrote:
>> PowerPC enables the MC scheduling domain by default on systems with
>> coregroup support without having a SCHED_MC config in Kconfig.
>>
>> The scheduler uses CONFIG_SCHED_MC to introduce the MC domain in the
>> default topology (core) and to optimize the default CPU selection
>> routine (sched-ext).
>
> Curious to know if sched_ext usage. i see below code.
>
> if (static_branch_maybe(CONFIG_SCHED_MC, &scx_selcpu_topo_llc))
>
> scx_selcpu_topo_llc = true if there is sd_llc. One can have llc domain without MC domain.
> I am wondering whats the reason behind the clubbing.
Seems to be an artifact carried forward since commit dfa4ed29b18c
("sched_ext: Introduce LLC awareness to the default idle selection
policy")
The commit 860a45219bce ("sched_ext: Introduce NUMA awareness to the
default idle selection policy") continued to build on top of that except
that it was fine to put the NUMA bits behind CONFIG_NUMA check since
topology.c only adds SD_NUMA under those circumstances but sd_llc is
just the highest SD_SHARE_LLC domain and shouldn't really depend on
CONFIG_SCHED_MC.
The ext part already has a check for llc_numa_mismatch() to only
enable "scx_selcpu_topo_numa" when llc and NUMA boundaries don't
overlap so I think that dependency on CONFIG_SCHED_MC can be safely
removed.
--
Thanks and Regards,
Prateek
Powered by blists - more mailing lists