Re: [PATCH 16/16] sched: Select least loaded CPU on preferred NUMA node

2013-07-11 Thread Mel Gorman
On Thu, Jul 11, 2013 at 02:39:02PM +0200, Peter Zijlstra wrote: > On Thu, Jul 11, 2013 at 10:47:00AM +0100, Mel Gorman wrote: > > +++ b/kernel/sched/fair.c > > @@ -841,29 +841,81 @@ static unsigned int task_scan_max(struct task_struct > > *p) > > */ > > unsigned int sysctl_numa_balancing_settle

Re: [PATCH 16/16] sched: Select least loaded CPU on preferred NUMA node

2013-07-11 Thread Peter Zijlstra
On Thu, Jul 11, 2013 at 10:47:00AM +0100, Mel Gorman wrote: > +++ b/kernel/sched/fair.c > @@ -841,29 +841,81 @@ static unsigned int task_scan_max(struct task_struct *p) > */ > unsigned int sysctl_numa_balancing_settle_count __read_mostly = 3; > > +static unsigned long source_load(int cpu, int

[PATCH 16/16] sched: Select least loaded CPU on preferred NUMA node

2013-07-11 Thread Mel Gorman
This patch replaces find_idlest_cpu_node with task_numa_find_cpu. find_idlest_cpu_node has two critical limitations. It does not take the scheduling class into account when calculating the load and it is unsuitable for using when comparing loads between NUMA nodes. task_numa_find_cpu uses similar