[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <xhsmh4itjlnnt.mognet@vschneid-thinkpadt14sgen2i.remote.csb>
Date: Wed, 03 Sep 2025 14:35:02 +0200
From: Valentin Schneider <vschneid@...hat.com>
To: "Christoph Lameter (Ampere)" <cl@...two.org>
Cc: Adam Li <adamli@...amperecomputing.com>, mingo@...hat.com,
peterz@...radead.org, juri.lelli@...hat.com, vincent.guittot@...aro.org,
dietmar.eggemann@....com, rostedt@...dmis.org, bsegall@...gle.com,
mgorman@...e.de, frederic@...nel.org, linux-kernel@...r.kernel.org,
patches@...erecomputing.com
Subject: Re: [PATCH] sched/nohz: Fix NOHZ imbalance by adding options for
ILB CPU
On 28/08/25 08:44, Christoph Lameter (Ampere) wrote:
> On Thu, 28 Aug 2025, Valentin Schneider wrote:
>
>> > Yes, binding the threads to CPU can work around the performance
>> > issue caused by load imbalance. Should we document that 'nohz_full' may cause
>> > the scheduler load balancing not working well and CPU affinity is preferred?
>> >
>>
>> Yeah I guess we could highlight that.
>
> We need to make sure that the idle cpus are used when available and
> needed. Otherwise the scheduler is buggy.
>
> Such a load balancing action means that there is a cpu that is running
> multiple processes. Therefore the timer interrrupt and the scheduler
> processing is active on at least one cpu. We can therefore do something
> about the situation.
>
> The scheduler needs to move one of the processes onto the idle cpu.
AFAICT we have (at least) two options:
1) Trigger NOHZ balancing on a busy housekeeping CPU (what this patch does)
This is somewhat against idle load balancing rules (only spend CPU time
on that if there is no "genuine" work to run), but I guess from a CPU
isolation PoV this can be tallied as just another housekeeping activity
2) Trigger NOHZ balancing on an idle NOHZ_FULL CPU
That doesn't steal useful CPU time, but that also potentially causes
interference, albeit only if racing with the NOHZ_FULL workload spawning
(which shouldn't be the steady state).
The more I think about it the more I'm leaning towards 1), but I'd like
other folks' opinion.
Powered by blists - more mailing lists