Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-10 Thread Alex Shi
On 01/10/2013 01:52 PM, Namhyung Kim wrote: > On Wed, 09 Jan 2013 16:34:39 +0800, Alex Shi wrote: >> On 01/09/2013 03:54 PM, Namhyung Kim wrote: >>> Hi Alex, >>> >>> On Wed, 09 Jan 2013 15:33:40 +0800, Alex Shi wrote: On 01/09/2013 02:50 PM, Namhyung Kim wrote: > From: Namhyung Kim >

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-10 Thread Preeti U Murthy
On 01/10/2013 11:19 AM, Namhyung Kim wrote: > Hi Preeti, > > On Wed, 09 Jan 2013 13:51:00 +0530, Preeti U. Murthy wrote: >> On 01/09/2013 12:20 PM, Namhyung Kim wrote: >>> From: Namhyung Kim >>> >>> AFAICS @target cpu of select_idle_sibling() is always either prev_cpu >>> or this_cpu. So no

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-10 Thread Alex Shi
On 01/10/2013 01:52 PM, Namhyung Kim wrote: On Wed, 09 Jan 2013 16:34:39 +0800, Alex Shi wrote: On 01/09/2013 03:54 PM, Namhyung Kim wrote: Hi Alex, On Wed, 09 Jan 2013 15:33:40 +0800, Alex Shi wrote: On 01/09/2013 02:50 PM, Namhyung Kim wrote: From: Namhyung Kim namhyung@lge.com

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-10 Thread Preeti U Murthy
On 01/10/2013 11:19 AM, Namhyung Kim wrote: Hi Preeti, On Wed, 09 Jan 2013 13:51:00 +0530, Preeti U. Murthy wrote: On 01/09/2013 12:20 PM, Namhyung Kim wrote: From: Namhyung Kim namhyung@lge.com AFAICS @target cpu of select_idle_sibling() is always either prev_cpu or this_cpu. So no

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Namhyung Kim
On Wed, 09 Jan 2013 16:34:39 +0800, Alex Shi wrote: > On 01/09/2013 03:54 PM, Namhyung Kim wrote: >> Hi Alex, >> >> On Wed, 09 Jan 2013 15:33:40 +0800, Alex Shi wrote: >>> On 01/09/2013 02:50 PM, Namhyung Kim wrote: From: Namhyung Kim AFAICS @target cpu of select_idle_sibling() is

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Namhyung Kim
Hi Preeti, On Wed, 09 Jan 2013 13:51:00 +0530, Preeti U. Murthy wrote: > On 01/09/2013 12:20 PM, Namhyung Kim wrote: >> From: Namhyung Kim >> >> AFAICS @target cpu of select_idle_sibling() is always either prev_cpu >> or this_cpu. So no need to check it again and the conditionals can be >>

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Alex Shi
On 01/09/2013 03:54 PM, Namhyung Kim wrote: > Hi Alex, > > On Wed, 09 Jan 2013 15:33:40 +0800, Alex Shi wrote: >> On 01/09/2013 02:50 PM, Namhyung Kim wrote: >>> From: Namhyung Kim >>> >>> AFAICS @target cpu of select_idle_sibling() is always either prev_cpu >>> or this_cpu. So no need to check

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Preeti U Murthy
On 01/09/2013 12:20 PM, Namhyung Kim wrote: > From: Namhyung Kim > > AFAICS @target cpu of select_idle_sibling() is always either prev_cpu > or this_cpu. So no need to check it again and the conditionals can be > consolidated. > > Cc: Mike Galbraith > Cc: Preeti U Murthy > Cc: Vincent

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Namhyung Kim
On Wed, 09 Jan 2013 15:38:11 +0800, Alex Shi wrote: >> >> Uh, we don't know if the target is this_cpu or previous cpu, If we just >> check the target idle status, we may miss another idle cpu. So this >> patch change the logical in this function. > > But, you can fold wake_affine into

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Namhyung Kim
On Wed, 09 Jan 2013 15:38:11 +0800, Alex Shi wrote: Uh, we don't know if the target is this_cpu or previous cpu, If we just check the target idle status, we may miss another idle cpu. So this patch change the logical in this function. But, you can fold wake_affine into

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Preeti U Murthy
On 01/09/2013 12:20 PM, Namhyung Kim wrote: From: Namhyung Kim namhyung@lge.com AFAICS @target cpu of select_idle_sibling() is always either prev_cpu or this_cpu. So no need to check it again and the conditionals can be consolidated. Cc: Mike Galbraith efa...@gmx.de Cc: Preeti U

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Alex Shi
On 01/09/2013 03:54 PM, Namhyung Kim wrote: Hi Alex, On Wed, 09 Jan 2013 15:33:40 +0800, Alex Shi wrote: On 01/09/2013 02:50 PM, Namhyung Kim wrote: From: Namhyung Kim namhyung@lge.com AFAICS @target cpu of select_idle_sibling() is always either prev_cpu or this_cpu. So no need to

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Namhyung Kim
Hi Preeti, On Wed, 09 Jan 2013 13:51:00 +0530, Preeti U. Murthy wrote: On 01/09/2013 12:20 PM, Namhyung Kim wrote: From: Namhyung Kim namhyung@lge.com AFAICS @target cpu of select_idle_sibling() is always either prev_cpu or this_cpu. So no need to check it again and the conditionals

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-09 Thread Namhyung Kim
On Wed, 09 Jan 2013 16:34:39 +0800, Alex Shi wrote: On 01/09/2013 03:54 PM, Namhyung Kim wrote: Hi Alex, On Wed, 09 Jan 2013 15:33:40 +0800, Alex Shi wrote: On 01/09/2013 02:50 PM, Namhyung Kim wrote: From: Namhyung Kim namhyung@lge.com AFAICS @target cpu of select_idle_sibling() is

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-08 Thread Namhyung Kim
Hi Alex, On Wed, 09 Jan 2013 15:33:40 +0800, Alex Shi wrote: > On 01/09/2013 02:50 PM, Namhyung Kim wrote: >> From: Namhyung Kim >> >> AFAICS @target cpu of select_idle_sibling() is always either prev_cpu >> or this_cpu. So no need to check it again and the conditionals can be >> consolidated.

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-08 Thread Alex Shi
> > Uh, we don't know if the target is this_cpu or previous cpu, If we just > check the target idle status, we may miss another idle cpu. So this > patch change the logical in this function. But, you can fold wake_affine into select_idle_sibling(). that will save a complicate calculation

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-08 Thread Alex Shi
On 01/09/2013 02:50 PM, Namhyung Kim wrote: > From: Namhyung Kim > > AFAICS @target cpu of select_idle_sibling() is always either prev_cpu > or this_cpu. So no need to check it again and the conditionals can be > consolidated. > > Cc: Mike Galbraith > Cc: Preeti U Murthy > Cc: Vincent

[PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-08 Thread Namhyung Kim
From: Namhyung Kim AFAICS @target cpu of select_idle_sibling() is always either prev_cpu or this_cpu. So no need to check it again and the conditionals can be consolidated. Cc: Mike Galbraith Cc: Preeti U Murthy Cc: Vincent Guittot Cc: Alex Shi Signed-off-by: Namhyung Kim ---

[PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-08 Thread Namhyung Kim
From: Namhyung Kim namhyung@lge.com AFAICS @target cpu of select_idle_sibling() is always either prev_cpu or this_cpu. So no need to check it again and the conditionals can be consolidated. Cc: Mike Galbraith efa...@gmx.de Cc: Preeti U Murthy pre...@linux.vnet.ibm.com Cc: Vincent Guittot

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-08 Thread Alex Shi
On 01/09/2013 02:50 PM, Namhyung Kim wrote: From: Namhyung Kim namhyung@lge.com AFAICS @target cpu of select_idle_sibling() is always either prev_cpu or this_cpu. So no need to check it again and the conditionals can be consolidated. Cc: Mike Galbraith efa...@gmx.de Cc: Preeti U

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-08 Thread Alex Shi
Uh, we don't know if the target is this_cpu or previous cpu, If we just check the target idle status, we may miss another idle cpu. So this patch change the logical in this function. But, you can fold wake_affine into select_idle_sibling(). that will save a complicate calculation whichever

Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling

2013-01-08 Thread Namhyung Kim
Hi Alex, On Wed, 09 Jan 2013 15:33:40 +0800, Alex Shi wrote: On 01/09/2013 02:50 PM, Namhyung Kim wrote: From: Namhyung Kim namhyung@lge.com AFAICS @target cpu of select_idle_sibling() is always either prev_cpu or this_cpu. So no need to check it again and the conditionals can be