Re: [PATCH -v2 15/17] sched: Fix migrate_disable() vs rt/dl balancing

[Valentin Schneider]

On 06/10/20 14:48, Peter Zijlstra wrote:
> On Tue, Oct 06, 2020 at 12:20:43PM +0100, Valentin Schneider wrote:
>>
>> An alternative I could see would be to prevent those piles from forming
>> altogether, say by issuing a similar push_cpu_stop() on migrate_disable()
>> if the next pushable task is already migrate_disable(); but that's a
>> proactive approach whereas yours is reactive, so I'm pretty sure that's
>> bound to perform worse.
>
> I think it is always possible to form pileups. Just start enough tasks
> such that newer, higher priority, tasks have to preempt existing tasks.
>
> Also, we might not be able to place the task elsewhere, suppose we have
> all our M CPUs filled with an RT task, then when the lowest priority
> task has migrate_disable(), wake the highest priority task.
>
> Per the SMP invariant, this new highest priority task must preempt the
> lowest priority task currently running, otherwise we would not be
> running the M highest prio tasks.
>

Right, and it goes the other way around for the migrate_disable() task: if
it becomes one of the M highest prio tasks, then it *must* run, and
push/pulling its CPU's current away is the only way to do so...

> That's not to say it might not still be beneficial from trying to avoid
> them, but we must assume a pilup will occur, therefore my focus was on
> dealing with them as best we can first.

"Funny" all that... Thanks!