Messages in this thread | | | Subject | Re: [RFC] perf: need to expose sched_clock to correlate user samples with kernel samples | From | Steven Rostedt <> | Date | Tue, 05 Feb 2013 20:19:55 -0500 |
| |
On Tue, 2013-02-05 at 14:28 -0800, John Stultz wrote: > I prefer the ioctl method, since its less likely to be re-purposed/misused. > > Though I'd be most comfortable with finding some way for perf-timestamps > to be CLOCK_MONOTONIC based (or maybe CLOCK_MONOTONIC_RAW if it would be > easier), and just avoid all together adding another time domain that > doesn't really have clear definition (other then "what perf uses").
Perhaps add a new perf system call? Does everything need to go through the one great mighty perf_ioctl aka sys_perf_event_open()? I mean, if there's something that can be agnostic to an event, but still very much related to perf, perhaps another perf syscall should be created.
If people are worried about adding a bunch of new perf syscalls, maybe add a sys_perf_control() system call that works like an ioctl but without a file descriptor. Something for things that don't require an event attached to it, like to retrieve a time stamp counter that perf uses, but done in a way that it could be used for other things perf related that does not require an event.
-- Steve
| |