Re: [PATCH v2 -tip] sched/deadline: switched_to_dl() -- skip if task is current

2014-01-28 Thread Juri Lelli
On 01/28/2014 08:26 AM, Kirill Tkhai wrote: > v2: Changed comment > > When p is current and it's not of dl class, then there are no other > dl taks in the rq. If we had had pushable tasks in some other rq, ^ tasks > they would have been pushed earlier. So, skip "p == rq->curr" case. > >

Re: [PATCH v2 -tip] sched/deadline: switched_to_dl() -- skip if task is current

2014-01-28 Thread Juri Lelli
On 01/28/2014 08:26 AM, Kirill Tkhai wrote: v2: Changed comment When p is current and it's not of dl class, then there are no other dl taks in the rq. If we had had pushable tasks in some other rq, ^ tasks they would have been pushed earlier. So, skip p == rq-curr case. [This is

[PATCH v2 -tip] sched/deadline: switched_to_dl() -- skip if task is current

2014-01-27 Thread Kirill Tkhai
v2: Changed comment When p is current and it's not of dl class, then there are no other dl taks in the rq. If we had had pushable tasks in some other rq, they would have been pushed earlier. So, skip "p == rq->curr" case. [This is confirmed by Juri Lelli and LKML was CC'ed, but unfotunately I

[PATCH v2 -tip] sched/deadline: switched_to_dl() -- skip if task is current

2014-01-27 Thread Kirill Tkhai
v2: Changed comment When p is current and it's not of dl class, then there are no other dl taks in the rq. If we had had pushable tasks in some other rq, they would have been pushed earlier. So, skip p == rq-curr case. [This is confirmed by Juri Lelli and LKML was CC'ed, but unfotunately I