On Tue, Jul 22, 2014 at 05:17:29PM +0100, Pawel Moll wrote: > That approach has been also discussed, last time in the mentioned > thread: > > http://thread.gmane.org/gmane.linux.kernel/1611683/focus=1612554 > http://thread.gmane.org/gmane.linux.kernel/1611683/focus=1612554 > > With both Ingo and John showing preference towards the clock alignment, > so that's where I looked this time (I've already done custom perf > ioctls, posix clocks... don't really know how many different ways I've > tried).
I re-read that thread, and it sounds like Ingo also suggested simply tracing the system time updates, leaving the correlation to the perf clock to user space. This is what I mean, too. John and Ingo said that exporting MONO-RAW would be "ideal", and maybe it would be (in the sense of easy-to-use), but only if it were always correct. However, hacking some half baked servo into the kernel will fail, at least some of the time. When it does fail, there is no way to figure out what happened, because the servo code obliterates the information in the original time stamps. So the only reasonable way, IMHO, is to simply provide the needed information in the traces, and then add some user space code to find the relationship between the perf clock and the system clock. The great advantage of this approach is that you don't have to create a perfect servo from day one. The time stamps can be re-analyzed at any time after the fact. And if you are going to use this for clusters, then you really want the global time and not MONO-RAW. I would suggest using CLOCK_TAI. Thanks, Richard -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
