Re: [PATCH v2] sched: fix nohz.next_balance update

2015-08-28 Thread Vincent Guittot
On 27 August 2015 at 18:50, Jason Low wrote: > On Thu, 2015-08-27 at 13:21 +0200, Vincent Guittot wrote: >> Hi, >> >> On 3 August 2015 at 11:55, Vincent Guittot >> wrote: >> > Since commit d4573c3e1c99 ("sched: Improve load balancing in the presence >> > of idle CPUs"), the ILB CPU starts with t

Re: [PATCH v2] sched: fix nohz.next_balance update

2015-08-27 Thread Jason Low
On Thu, 2015-08-27 at 13:21 +0200, Vincent Guittot wrote: > Hi, > > On 3 August 2015 at 11:55, Vincent Guittot wrote: > > Since commit d4573c3e1c99 ("sched: Improve load balancing in the presence > > of idle CPUs"), the ILB CPU starts with the idle load balancing of other > > idle CPUs and finish

Re: [PATCH v2] sched: fix nohz.next_balance update

2015-08-27 Thread Vincent Guittot
Hi, On 3 August 2015 at 11:55, Vincent Guittot wrote: > Since commit d4573c3e1c99 ("sched: Improve load balancing in the presence > of idle CPUs"), the ILB CPU starts with the idle load balancing of other > idle CPUs and finishes with itself in order to speed up the spread of tasks > in all idle

[PATCH v2] sched: fix nohz.next_balance update

2015-08-03 Thread Vincent Guittot
Since commit d4573c3e1c99 ("sched: Improve load balancing in the presence of idle CPUs"), the ILB CPU starts with the idle load balancing of other idle CPUs and finishes with itself in order to speed up the spread of tasks in all idle CPUs. The this_rq->next_balance is still used in nohz_idle_bala