[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <c1366d06-1d2f-44d5-8414-fcc0ba7d7490@amd.com>
Date: Tue, 20 Jan 2026 09:03:56 +0530
From: K Prateek Nayak <kprateek.nayak@....com>
To: Zicheng Qu <quzicheng@...wei.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>,
<vschneid@...hat.com>, <vatsa@...ux.vnet.ibm.com>,
<dhaval@...ux.vnet.ibm.com>, <linux-kernel@...r.kernel.org>
CC: <tanghui20@...wei.com>, <zhangqiao22@...wei.com>
Subject: Re: [PATCH] sched: Re-evaluate scheduling when migrating queued tasks
out of throttled cgroups
Hello Zicheng,
On 1/19/2026 7:00 PM, Zicheng Qu wrote:
> @@ -9120,12 +9121,16 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup)
> sched_change_group(tsk);
> if (!for_autogroup)
> scx_cgroup_move_task(tsk);
> + if (scope->queued)
> + queued = true;
nit. This can just be "queued = scope->queued"
Other than that, this fix looks good. Feel free to include:
Reviewed-by: K Prateek Nayak <kprateek.nayak@....com>
> if (scope->running)
> resched = true;
> }
>
> if (resched)
> resched_curr(rq);
> + else if (queued)
> + wakeup_preempt(rq, tsk, 0);
>
> __balance_callbacks(rq, &rq_guard.rf);
> }
--
Thanks and Regards,
Prateek
Powered by blists - more mailing lists