Re: [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing

2013-01-18 Thread Alex Shi
On 01/16/2013 11:08 PM, Morten Rasmussen wrote: > On Wed, Jan 16, 2013 at 07:32:49AM +, Alex Shi wrote: >> On 01/15/2013 01:00 AM, Morten Rasmussen wrote: > Why multiply rq->util by nr_running? >>> >>> Let's take an example where rq->util = 50, nr_running = 2, and putil = >>> 10

Re: [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing

2013-01-16 Thread Morten Rasmussen
On Wed, Jan 16, 2013 at 07:32:49AM +, Alex Shi wrote: > On 01/15/2013 01:00 AM, Morten Rasmussen wrote: > >>> Why multiply rq->util by nr_running? > >>> > > > >>> > > Let's take an example where rq->util = 50, nr_running = 2, and putil = > >>> > > 10. In this case the value of putil doesn't re

Re: [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing

2013-01-16 Thread Namhyung Kim
On Wed, 16 Jan 2013 14:11:53 +0800, Alex Shi wrote: > On 01/14/2013 03:13 PM, Namhyung Kim wrote: >> On Fri, 11 Jan 2013 11:47:03 +0800, Alex Shi wrote: >>> Um, change to leader_cpu? >> >> vacantest? ;-) > > hard to the ward in google. are you sure it is better than leader_cpu? :) Nop. My Engli

Re: [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing

2013-01-15 Thread Alex Shi
On 01/15/2013 01:00 AM, Morten Rasmussen wrote: >>> Why multiply rq->util by nr_running? >>> > > >>> > > Let's take an example where rq->util = 50, nr_running = 2, and putil = >>> > > 10. In this case the value of putil doesn't really matter as vacancy >>> > > would be negative anyway since FULL_U

Re: [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing

2013-01-15 Thread Alex Shi
On 01/14/2013 03:13 PM, Namhyung Kim wrote: > On Fri, 11 Jan 2013 11:47:03 +0800, Alex Shi wrote: >> On 01/11/2013 01:17 AM, Morten Rasmussen wrote: >>> On Sat, Jan 05, 2013 at 08:37:46AM +, Alex Shi wrote: If the wake/exec task is small enough, utils < 12.5%, it will has the chance t

Re: [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing

2013-01-14 Thread Morten Rasmussen
On Fri, Jan 11, 2013 at 03:47:03AM +, Alex Shi wrote: > On 01/11/2013 01:17 AM, Morten Rasmussen wrote: > > On Sat, Jan 05, 2013 at 08:37:46AM +, Alex Shi wrote: > >> If the wake/exec task is small enough, utils < 12.5%, it will > >> has the chance to be packed into a cpu which is busy but

Re: [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing

2013-01-13 Thread Namhyung Kim
On Fri, 11 Jan 2013 11:47:03 +0800, Alex Shi wrote: > On 01/11/2013 01:17 AM, Morten Rasmussen wrote: >> On Sat, Jan 05, 2013 at 08:37:46AM +, Alex Shi wrote: >>> If the wake/exec task is small enough, utils < 12.5%, it will >>> has the chance to be packed into a cpu which is busy but still has

Re: [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing

2013-01-10 Thread Alex Shi
On 01/11/2013 01:17 AM, Morten Rasmussen wrote: > On Sat, Jan 05, 2013 at 08:37:46AM +, Alex Shi wrote: >> If the wake/exec task is small enough, utils < 12.5%, it will >> has the chance to be packed into a cpu which is busy but still has space to >> handle it. >> >> Signed-off-by: Alex Shi >>

Re: [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing

2013-01-10 Thread Morten Rasmussen
On Sat, Jan 05, 2013 at 08:37:46AM +, Alex Shi wrote: > If the wake/exec task is small enough, utils < 12.5%, it will > has the chance to be packed into a cpu which is busy but still has space to > handle it. > > Signed-off-by: Alex Shi > --- > kernel/sched/fair.c | 51 ++