Re: [PATCH 2/6] sched/dl: fix yield task artificial overrun

2014-10-30 Thread Juri Lelli
Hi, On 29/10/14 22:49, Wanpeng Li wrote: > Hi Juri, > 2014/10/30 0:33, Juri Lelli: >> Hi, >> >> On 27/10/14 01:41, Wanpeng Li wrote: >>> The yield semantic of deadline class is to reduce remaining runtime to >>> zero, and then update_curr_dl() will stop it. However, comsumed bandwidth >>> is reduc

Re: [PATCH 2/6] sched/dl: fix yield task artificial overrun

2014-10-29 Thread Wanpeng Li
Hi Juri, 2014/10/30 0:33, Juri Lelli: Hi, On 27/10/14 01:41, Wanpeng Li wrote: The yield semantic of deadline class is to reduce remaining runtime to zero, and then update_curr_dl() will stop it. However, comsumed bandwidth is reduced from the budget of yield task again even if it has already b

Re: [PATCH 2/6] sched/dl: fix yield task artificial overrun

2014-10-29 Thread Juri Lelli
Hi, On 27/10/14 01:41, Wanpeng Li wrote: > The yield semantic of deadline class is to reduce remaining runtime to > zero, and then update_curr_dl() will stop it. However, comsumed bandwidth > is reduced from the budget of yield task again even if it has already been > set to zero which leads to

[PATCH 2/6] sched/dl: fix yield task artificial overrun

2014-10-26 Thread Wanpeng Li
The yield semantic of deadline class is to reduce remaining runtime to zero, and then update_curr_dl() will stop it. However, comsumed bandwidth is reduced from the budget of yield task again even if it has already been set to zero which leads to artificial overrun. This patch fix it by reduce