[lkml]   [2012]   [Dec]   [20]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 01/18] sched: select_task_rq_fair clean up

On Tue, 11 Dec 2012 12:00:55 +0530, Preeti U. Murthy wrote:
> On 12/11/2012 10:58 AM, Alex Shi wrote:
>> On 12/11/2012 12:23 PM, Preeti U Murthy wrote:
>>> Hi Alex,
>>> On 12/10/2012 01:52 PM, Alex Shi wrote:
>>>> It is impossible to miss a task allowed cpu in a eligible group.
>>> The one thing I am concerned with here is if there is a possibility of
>>> the task changing its tsk_cpus_allowed() while this code is running.
>>> i.e find_idlest_group() finds an idle group,then the tsk_cpus_allowed()
>>> for the task changes,perhaps by the user himself,which might not include
>>> the cpus in the idle group.After this find_idlest_cpu() is called.I mean
>>> a race condition in short.Then we might not have an eligible cpu in that
>>> group right?
>> your worry make sense, but the code handle the situation, in
>> select_task_rq(), it will check the cpu allowed again. if the answer is
>> no, it will fallback to old cpu.
>>>> And since find_idlest_group only return a different group which
>>>> excludes old cpu, it's also imporissible to find a new cpu same as old
>>>> cpu.
> I doubt this will work correctly.Consider the following situation:sched
> domain begins with sd that encloses both socket1 and socket2
> cpu0 cpu1 | cpu2 cpu3
> -----------|-------------
> socket1 | socket2
> old cpu = cpu1
> Iteration1:
> 1.find_idlest_group() returns socket2 to be idlest.
> 2.task changes tsk_allowed_cpus to 0,1
> 3.find_idlest_cpu() returns cpu2

AFAIK The tsk->cpus_allowed cannot be changed during the operation since
it's protected by tsk->pi_lock. I can see the following comment:

* The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
static inline
int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);


 \ /
  Last update: 2012-12-21 06:01    [W:0.091 / U:0.296 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site