mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Joel Fernandes <joelagnelf@nvidia.com>
To: Andrea Righi <arighi@nvidia.com>
Cc: linux-kernel@vger.kernel.org, Tejun Heo <tj@kernel.org>,
	David Vernet <void@manifault.com>,
	Changwoo Min <changwoo@igalia.com>,
	Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	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>
Subject: Re: [PATCH v4 14/15] Remove the ext server BW before changing tasks to FAIR
Date: Wed, 18 Jun 2025 09:21:07 -0400	[thread overview]
Message-ID: <33a80bba-22b7-4c2e-9acb-14d590dad55f@nvidia.com> (raw)
In-Reply-To: <aFHTSJzanNYjIwJt@gpd4>



On 6/17/2025 4:42 PM, Andrea Righi wrote:
>> +
>> +		/*
>> +		 * We are unloading the sched_ext scheduler, we do not need its
>> +		 * DL server bandwidth anymore, remove it for all CPUs. Whenever
>> +		 * the first SCX task is enqueued (when scx is re-loaded), its DL
>> +		 * server bandwidth will be re-initialized.
>> +		 */
>> +		rq_lock_irqsave(rq, &rf);
>> +		update_rq_clock(rq);
>> +		if (dl_server_active(&rq->ext_server))
>> +			dl_server_stop(&rq->ext_server);
>> +		dl_server_remove_params(&rq->ext_server);
>> +		rq_unlock_irqrestore(rq, &rf);
>> +	}
>> +
>> +
>>  	scx_task_iter_start(&sti);
>>  	while ((p = scx_task_iter_next_locked(&sti))) {
>>  		const struct sched_class *old_class = p->sched_class;
>> @@ -4985,26 +5010,12 @@ static void scx_disable_workfn(struct kthread_work *work)
>>  
>>  	for_each_possible_cpu(cpu) {
>>  		struct rq *rq = cpu_rq(cpu);
>> -		struct rq_flags rf;
>>  
>>  		/*
>>  		 * Invalidate all the rq clocks to prevent getting outdated
>>  		 * rq clocks from a previous scx scheduler.
>>  		 */
>>  		scx_rq_clock_invalidate(rq);
>> -
>> -		/*
>> -		 * We are unloading the sched_ext scheduler, we do not need its
>> -		 * DL server bandwidth anymore, remove it for all CPUs. Whenever
>> -		 * the first SCX task is enqueued (when scx is re-loaded), its DL
>> -		 * server bandwidth will be re-initialized.
>> -		 */
>> -		rq_lock_irqsave(rq, &rf);
>> -		update_rq_clock(rq);
>> -		if (dl_server_active(&rq->ext_server))
>> -			dl_server_stop(&rq->ext_server);
>> -		dl_server_remove_params(&rq->ext_server);
>> -		rq_unlock_irqrestore(rq, &rf);
>>  	}
>
> We should probably remove this for_each_possible_cpu() completely.

Ah right, we only need to call scx_rq_clock_invalidate(rq); per its comment:

+		/*
+		 * Invalidate all the rq clocks to prevent getting outdated
+		 * rq clocks from a previous scx scheduler.
+		 */

So I'll get rid of it and run some tests, thanks!

 - Joel



  reply	other threads:[~2025-06-18 13:21 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-17 20:05 [PATCH v4 00/15] Add a deadline server for sched_ext tasks Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 01/15] sched/debug: Fix updating of ppos on server write ops Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 02/15] sched/debug: Stop and start server based on if it was active Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 03/15] sched/deadline: Clear the defer params Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 04/15] sched/deadline: Prevent setting server as started if params couldn't be applied Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 05/15] sched/deadline: Return EBUSY if dl_bw_cpus is zero Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 06/15] sched: Add support to pick functions to take rf Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 07/15] sched: Add a server arg to dl_server_update_idle_time() Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 08/15] sched/ext: Add a DL server for sched_ext tasks Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 09/15] sched/debug: Add support to change sched_ext server params Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 10/15] sched/deadline: Add support to remove DLserver's bandwidth contribution Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 11/15] sched/ext: Relinquish DL server reservations when not needed Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 12/15] sched_ext: Update rq clock when stopping dl_server Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 13/15] selftests/sched_ext: Add test for sched_ext dl_server Joel Fernandes
2025-06-17 20:05 ` [PATCH v4 14/15] Remove the ext server BW before changing tasks to FAIR Joel Fernandes
2025-06-17 20:12   ` Joel Fernandes
2025-06-17 20:42   ` Andrea Righi
2025-06-18 13:21     ` Joel Fernandes [this message]
2025-06-17 20:05 ` [PATCH v4 15/15] sched/deadline: Fix DL server crash in inactive_timer callback Joel Fernandes

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=33a80bba-22b7-4c2e-9acb-14d590dad55f@nvidia.com \
    --to=joelagnelf@nvidia.com \
    --cc=arighi@nvidia.com \
    --cc=bsegall@google.com \
    --cc=changwoo@igalia.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=tj@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=void@manifault.com \
    --cc=vschneid@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®