Messages in this thread | | | Date | Wed, 8 Apr 2015 11:41:14 +0200 | From | Peter Zijlstra <> | Subject | Re: [PATCH v2 2/2] nohz: make nohz_full imply isolcpus |
| |
On Mon, Apr 06, 2015 at 02:16:45PM -0400, cmetcalf@ezchip.com wrote: > From: Chris Metcalf <cmetcalf@ezchip.com> > > It's not clear that nohz_full is useful without isolcpus also > set, since otherwise the scheduler has to run periodically to > try to determine whether to steal work from other cores.
So the Changelog and the patch don't seem to agree with one another.
The Changelog states that nohz_full should depend on isolcpus. The patch implies nohz_full for isolcpus.
These are not the same; and I don't see the argument for the former make sense for the latter.
In specific isolcpus without nohz_full does make sense.
> Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> > Acked-by: Mike Galbraith <umgwanakikbuti@gmail.com> ["thumbs up!"] > Acked-by: Rik van Riel <riel@redhat.com> > --- > kernel/sched/core.c | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c > index f0f831e8a345..275f12c608f2 100644 > --- a/kernel/sched/core.c > +++ b/kernel/sched/core.c > @@ -6836,6 +6836,7 @@ static int init_sched_domains(const struct cpumask *cpu_map) > doms_cur = alloc_sched_domains(ndoms_cur); > if (!doms_cur) > doms_cur = &fallback_doms; > + tick_nohz_full_set_cpus(cpu_isolated_map); > cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); > err = build_sched_domains(doms_cur[0], NULL); > register_sched_domain_sysctl();
| |