Messages in this thread Patch in this message | | | Date | Fri, 17 Jan 2020 13:31:03 +0100 | From | Peter Zijlstra <> | Subject | Re: [Patch v8 4/7] sched/fair: Enable periodic update of average thermal pressure |
| |
On Fri, Jan 17, 2020 at 11:40:45AM +0000, Quentin Perret wrote: > On Thursday 16 Jan 2020 at 16:15:02 (+0100), Peter Zijlstra wrote: > > > @@ -10275,6 +10281,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) > > > { > > > struct cfs_rq *cfs_rq; > > > struct sched_entity *se = &curr->se; > > > + unsigned long thermal_pressure = arch_cpu_thermal_pressure(cpu_of(rq)); > > > > > > for_each_sched_entity(se) { > > > cfs_rq = cfs_rq_of(se); > > > @@ -10286,6 +10293,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) > > > > > > update_misfit_status(curr, rq); > > > update_overutilized_status(task_rq(curr)); > > > + update_thermal_load_avg(rq_clock_task(rq), rq, thermal_pressure); > > > } > > > > I'm thinking this is the wrong place; should this not be in > > scheduler_tick(), right before calling sched_class::task_tick() ? Surely > > any execution will affect thermals, not only fair class execution. > > Right, but right now only CFS takes action when we overheat. That is, > only CFS uses capacity_of() which is where the thermal signal gets > reflected.
Sure, but we should still track the thermals unconditionally, even if only CFS consumes it.
> We definitely could (and maybe should) make RT and DL react to thermal > pressure as well when they're both capacity-aware. But perhaps that's > for later ? Thoughts ?
Yeah, that's later head-aches. Even determining what to do there, except panic() is going to be 'interesting'.
| |