Messages in this thread | | | Date | Wed, 21 Aug 2013 17:59:45 +0200 | From | Sebastian Andrzej Siewior <> | Subject | Re: [PATCH RT 0/3] hwlat-detector: Have it actually find hardware latency |
| |
* Steven Rostedt | 2013-08-19 17:33:24 [-0400]:
>Thi patch series fixes up hwlat-detector to check the entire path >of time for a latency being hit, instead of the quick check between >two time stamps. > >It also uses the trace_local_clock() if available, which is much lighter >weight than ktime_get() which might produce false positives. As >the trace clock is used to detect irq latencies, it's suitable for >hardware latency. > >Finally, stop machine is removed and the test is run by a single thread.
Applied, thanks.
Sebastian
| |