Re: [PATCH] sched: Do not stop cpu in set_cpus_allowed_ptr() if task is not running

2014-09-16 Thread Preeti U Murthy
On 09/15/2014 03:32 PM, Kirill Tkhai wrote: > Hi, Preeti, > > В Пн, 15/09/2014 в 15:18 +0530, Preeti Murthy пишет: >> Hi Kirill, >> >> Which tree is this patch based on? __migrate_task() does a >> double_rq_lock/unlock() today in mainline, doesn't it? I don't >> however see that in your patch. >

Re: [PATCH] sched: Do not stop cpu in set_cpus_allowed_ptr() if task is not running

2014-09-15 Thread Peter Zijlstra
On Mon, Sep 15, 2014 at 02:02:30PM +0400, Kirill Tkhai wrote: > Hi, Preeti, > > В Пн, 15/09/2014 в 15:18 +0530, Preeti Murthy пишет: > > Hi Kirill, > > > > Which tree is this patch based on? __migrate_task() does a > > double_rq_lock/unlock() today in mainline, doesn't it? I don't > > however see

Re: [PATCH] sched: Do not stop cpu in set_cpus_allowed_ptr() if task is not running

2014-09-15 Thread Kirill Tkhai
Hi, Preeti, В Пн, 15/09/2014 в 15:18 +0530, Preeti Murthy пишет: > Hi Kirill, > > Which tree is this patch based on? __migrate_task() does a > double_rq_lock/unlock() today in mainline, doesn't it? I don't > however see that in your patch. it's based on recent tip tree: https://git.kernel.org/cg

Re: [PATCH] sched: Do not stop cpu in set_cpus_allowed_ptr() if task is not running

2014-09-15 Thread Preeti Murthy
Hi Kirill, Which tree is this patch based on? __migrate_task() does a double_rq_lock/unlock() today in mainline, doesn't it? I don't however see that in your patch. Regards Preeti U Murthy On Fri, Sep 12, 2014 at 4:33 PM, Kirill Tkhai wrote: > > If a task is queued but not running on it rq, we

Re: [PATCH] sched: Do not stop cpu in set_cpus_allowed_ptr() if task is not running

2014-09-14 Thread Kirill Tkhai
On 14.09.2014 13:55, Peter Zijlstra wrote: > On Sun, Sep 14, 2014 at 01:20:32PM +0400, Kirill Tkhai wrote: >> On 14.09.2014 13:13, Peter Zijlstra wrote: >> Peter, haven't I moved the sequence from __migrate_task?? >> >> Rechecked again; yes, patch makes __migrate_task using new move_queued_task. >

Re: [PATCH] sched: Do not stop cpu in set_cpus_allowed_ptr() if task is not running

2014-09-14 Thread Peter Zijlstra
On Sun, Sep 14, 2014 at 01:20:32PM +0400, Kirill Tkhai wrote: > On 14.09.2014 13:13, Peter Zijlstra wrote: > Peter, haven't I moved the sequence from __migrate_task?? > > Rechecked again; yes, patch makes __migrate_task using new move_queued_task. Yes you have ... urgh.. that's what you get for t

Re: [PATCH] sched: Do not stop cpu in set_cpus_allowed_ptr() if task is not running

2014-09-14 Thread Kirill Tkhai
On 14.09.2014 13:13, Peter Zijlstra wrote: > On Fri, Sep 12, 2014 at 03:03:34PM +0400, Kirill Tkhai wrote: >> >> If a task is queued but not running on it rq, we can simply migrate >> it without migration thread and switching of context. >> >> Signed-off-by: Kirill Tkhai >> --- >> kernel/sched/co

Re: [PATCH] sched: Do not stop cpu in set_cpus_allowed_ptr() if task is not running

2014-09-14 Thread Peter Zijlstra
On Fri, Sep 12, 2014 at 03:03:34PM +0400, Kirill Tkhai wrote: > > If a task is queued but not running on it rq, we can simply migrate > it without migration thread and switching of context. > > Signed-off-by: Kirill Tkhai > --- > kernel/sched/core.c | 47 --

[PATCH] sched: Do not stop cpu in set_cpus_allowed_ptr() if task is not running

2014-09-12 Thread Kirill Tkhai
If a task is queued but not running on it rq, we can simply migrate it without migration thread and switching of context. Signed-off-by: Kirill Tkhai --- kernel/sched/core.c | 47 --- 1 file changed, 32 insertions(+), 15 deletions(-) diff --git a/k