Re: [PATCH 1/7] sched: warn for high latency with TIF_NEED_RESCHED_LAZY

[Ankur Arora]

Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx> writes:

> On 2024-10-09 09:54:05 [-0700], Ankur Arora wrote:
>> resched_latency_warn() now also warns if TIF_NEED_RESCHED_LAZY is set
>> without rescheduling for more than the latency_warn_ms period.
>
> The description is odd. I think you want to say that
> resched_latency_warn() does not warn if a task has TIF_NEED_RESCHED_LAZY
> has set for longer periods and you want to add this functionality.
>
>> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
>> Cc: Peter Ziljstra <peterz@xxxxxxxxxxxxx>
>> Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
>> Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
>> Signed-off-by: Ankur Arora <ankur.a.arora@xxxxxxxxxx>
> …
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index 694bfcf153cb..1229766b704e 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -5571,7 +5571,7 @@ static u64 cpu_resched_latency(struct rq *rq)
>>  	if (sysctl_resched_latency_warn_once && warned_once)
>>  		return 0;
>>
>> -	if (!need_resched() || !latency_warn_ms)
>> +	if ((!need_resched() && !tif_need_resched_lazy()) || !latency_warn_ms)
>
> tif_need_resched_lazy() is not doing what you think it is doing.

Thanks. My bad.

> tif_test_bit(TIF_NEED_RESCHED_LAZY).

> Either PeterZ makes a helper for this or you need
> tif_test_bit(TIF_NEED_RESCHED_LAZY).

Yeah. tif_test_bit(TIF_NEED_RESCHED_LAZY) and need_resched() will
be identical with !ARCH_HAS_PREEMPT_LAZY but that should be okay in
this context.

--
ankur