On Thu, Oct 29, 2020 at 05:56:12PM +0000, Valentin Schneider wrote: > > On 29/10/20 17:43, Peter Zijlstra wrote: > > On Thu, Oct 29, 2020 at 04:27:26PM +0000, Valentin Schneider wrote: > >> Don't you want those directly after the ->migration_disabled write? > >> esp. for migrate_enable(), if that preempt_enable() leads to a context > >> switch then the disable->enable deltas won't reflect the kernel view. > >> > >> That delta may indeed include the time it took to run the stopper and > >> fix the task's affinity on migrate_enable(), but it could include all > >> sorts of other higher-priority tasks. > > > > I can put them in the preempt_disable() section I suppose, but these > > tracers should be looking at task_sched_runtime(), not walltime, and > > then the preemption doesn't matter. > > > > True. I was thinking of how to process it downstream, and the first thing > that came to mind was that rd->overutilized flag which we do monitor > fairly closely; however that is system-wide while migrate_disable() is > task-specific. > > > Also, a distinct lack of actual users atm.. :/ > > If you'd rather ditch this one altogether until someone asks for it, that > also works for me.
Yeah, I can pull this patch until we get someone that actually needs it.
