On Tue, May 13, 2014 at 07:10:02PM +0900, Dongsheng Yang wrote: > On 05/13/2014 07:03 PM, Peter Zijlstra wrote:
> >Now what I think you wanted to do is make it easier to match > >trace_sched_switch() statements with trace_sched_wakeup() statements. > >And since you only get the trace_sched_switch() on dequeue, you want to > >know which trace_sched_wakeup() calls did an enqueue. > > Ha, yes, indeed. In perf sched latency, we need to know the timestamp > when a task enqueue and then we can calculate the delay time. > So I want to take the use of success parameter in trace_sched_wakeup() > to indicate that *this* wakeup did an enqueue. > > But now I think it is okey if you really mind adding more tracepoints in > scheduler. And I posted a patch after your patch in this thread to make > perf sched latency work well. I don't mind adding them per-se, as long as there's a reasonable effort showing it doesn't slow down the wakeup-path.
pgpRSnudjNiBv.pgp
Description: PGP signature
