Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Vincent Guittot
On 10 April 2013 08:07, Michael Wang wrote: > On 04/09/2013 03:08 PM, Vincent Guittot wrote: >> On 2 April 2013 05:23, Alex Shi wrote: >>> Except using runnable load average in background, move_tasks is also >>> the key functions in load balance. We need consider the runnable load >>> average in

Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Michael Wang
On 04/09/2013 03:08 PM, Vincent Guittot wrote: > On 2 April 2013 05:23, Alex Shi wrote: >> Except using runnable load average in background, move_tasks is also >> the key functions in load balance. We need consider the runnable load >> average in it in order to the apple to apple load comparison.

Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Alex Shi
On 04/09/2013 11:16 PM, Vincent Guittot wrote: >> > Thanks a lot for info sharing! Vincent. >> > >> > But I checked the rq->avg and task->se.avg, seems none of them are >> > possible be updated on different CPU at the same time. So my printk >> > didn't catch this with benchmark kbuild and aim7 on

Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Vincent Guittot
On 9 April 2013 16:48, Alex Shi wrote: > On 04/09/2013 07:56 PM, Vincent Guittot wrote: >> On 9 April 2013 12:38, Alex Shi wrote: >>> On 04/09/2013 04:58 PM, Vincent Guittot wrote: How do you ensure that runnable_avg_period and runnable_avg_sum are coherent ? an update of the st

Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Alex Shi
On 04/09/2013 07:56 PM, Vincent Guittot wrote: > On 9 April 2013 12:38, Alex Shi wrote: >> On 04/09/2013 04:58 PM, Vincent Guittot wrote: >>> How do you ensure that runnable_avg_period and runnable_avg_sum are >>> coherent ? an update of the statistic can occur in the middle of your >>

Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Vincent Guittot
On 9 April 2013 12:38, Alex Shi wrote: > On 04/09/2013 04:58 PM, Vincent Guittot wrote: >> How do you ensure that runnable_avg_period and runnable_avg_sum are >> coherent ? an update of the statistic can occur in the middle of your >> sequence. >>> > >>> > Thanks for your question,

Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Alex Shi
On 04/09/2013 04:58 PM, Vincent Guittot wrote: >>> >> How do you ensure that runnable_avg_period and runnable_avg_sum are >>> >> coherent ? an update of the statistic can occur in the middle of your >>> >> sequence. >> > >> > Thanks for your question, Vincent! >> > the runnable_avg_period and runna

Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Vincent Guittot
On 9 April 2013 10:05, Alex Shi wrote: > On 04/09/2013 03:08 PM, Vincent Guittot wrote: >> On 2 April 2013 05:23, Alex Shi wrote: >>> Except using runnable load average in background, move_tasks is also >>> the key functions in load balance. We need consider the runnable load >>> average in it in

Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Alex Shi
On 04/09/2013 03:08 PM, Vincent Guittot wrote: > On 2 April 2013 05:23, Alex Shi wrote: >> Except using runnable load average in background, move_tasks is also >> the key functions in load balance. We need consider the runnable load >> average in it in order to the apple to apple load comparison.

Re: [patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-09 Thread Vincent Guittot
On 2 April 2013 05:23, Alex Shi wrote: > Except using runnable load average in background, move_tasks is also > the key functions in load balance. We need consider the runnable load > average in it in order to the apple to apple load comparison. > > Signed-off-by: Alex Shi > --- > kernel/sched/f

[patch v3 6/8] sched: consider runnable load average in move_tasks

2013-04-01 Thread Alex Shi
Except using runnable load average in background, move_tasks is also the key functions in load balance. We need consider the runnable load average in it in order to the apple to apple load comparison. Signed-off-by: Alex Shi --- kernel/sched/fair.c | 11 ++- 1 file changed, 10 insertions