Re: [PATCH v4 1/3] sched: Reduce overestimating rq->avg_idle

2013-09-02 Thread Srikar Dronamraju
* Jason Low [2013-08-29 13:05:34]: > When updating avg_idle, if the delta exceeds some max value, then avg_idle > gets set to the max, regardless of what the previous avg was. This can cause > avg_idle to often be overestimated. > > This patch modifies the way we update avg_idle by always

Re: [PATCH v4 1/3] sched: Reduce overestimating rq-avg_idle

2013-09-02 Thread Srikar Dronamraju
* Jason Low jason.l...@hp.com [2013-08-29 13:05:34]: When updating avg_idle, if the delta exceeds some max value, then avg_idle gets set to the max, regardless of what the previous avg was. This can cause avg_idle to often be overestimated. This patch modifies the way we update avg_idle by

[PATCH v4 1/3] sched: Reduce overestimating rq->avg_idle

2013-08-29 Thread Jason Low
When updating avg_idle, if the delta exceeds some max value, then avg_idle gets set to the max, regardless of what the previous avg was. This can cause avg_idle to often be overestimated. This patch modifies the way we update avg_idle by always updating it with the function call to update_avg()

[PATCH v4 1/3] sched: Reduce overestimating rq-avg_idle

2013-08-29 Thread Jason Low
When updating avg_idle, if the delta exceeds some max value, then avg_idle gets set to the max, regardless of what the previous avg was. This can cause avg_idle to often be overestimated. This patch modifies the way we update avg_idle by always updating it with the function call to update_avg()