On Mon, Feb 12, 2018 at 04:38:05PM +0100, Peter Zijlstra wrote: > On Mon, Feb 12, 2018 at 03:34:44PM +0100, Vincent Guittot wrote: > > > Aside from the above being an unreadable mess, I dislike that it breaks > > > the various isolation crud, we should not touch CPUs outside of our > > > domain. > > > > > > > > > Maybe something like the below? (unfinished) > > > > > > > good catch. I completely miss the isolation stuff. > > But isn't already the case when kicking ilb ? I mean that an idle CPU > > touches > > all idle CPUs and some can be outside its domain during ilb. > > > Shouldn't we test housekeeping_cpu(cpu, HK_FLAG_SCHED) instead if we want to > > make sure that an isolated/full nohz CPU will not be used for updating > > blocked > > load of CPUs outside its domain ? > > I _thought_ we had some 'housekeeping' crud in the ilb selection logic, > but now I can't find it. Frederic?
I think you're referring to nohz_balance_idle(). The call is still there but HK_FLAG_SCHED is unused for now. I initially turned it on by default on nohz_full but some people complained. I don't recall why exactly. Anyway I'm waiting for a suitable interface to use it.
