Messages in this thread | | | Date | Wed, 15 Jan 2014 22:28:10 +0800 | From | Alex Shi <> | Subject | Re: [RFC PATCH] sched: find the latest idle cpu |
| |
On 01/15/2014 04:05 PM, Michael wang wrote: > On 01/15/2014 02:45 PM, Alex Shi wrote: > [snip] >> >> yes, to save your scenario, we need to know the next timer for idle cpu, >> but that is not enough, interrupt is totally unpredictable. So, I'd >> rather bear the coarse method now. >>> >>> So what about just check 'ts->tick_stopped' and record one ticking idle >>> cpu? the cost could be lower than time comparison, we could reduce the >>> risk may be...(well, not so risky since the logical only works when >>> system is relaxing with several cpu idle) >> >> first, nohz full also stop tick. second, tick_stopped can not reflect >> the interrupt. when the idle cpu was interrupted, it's waken, then be a >> good candidate for task running. > > IMHO, if we have to do gamble here, we better choose the cheaper bet, > unless we could prove this 'coarse method' have more higher chance for > BINGO than just check 'tick_stopped'...
Tick stopped on a nohz full CPU, but the cpu still had a task running... > > BTW, may be the logical should be in the select_idle_sibling()?
both of functions need to be considered. > > Regards, > Michael Wang > >> >
-- Thanks Alex
| |