> Thanks, nice work charting gettimeofday() against another scaled TSC.
The software that collected the data was written by Markus Kuhn. http://www.cl.cam.ac.uk/~mgk25/time/leap/test/timelog.c I just ran it and made the graphs. > A more portable approach might use getclock(CLOCK_MONOTONIC, ...) That only works if you trust the OS software. Given that we are trying to measure what it does, using the TSC seems like the only really reliable approach. Check the above code. It prints lots of clocks. -- These are my opinions. I hate spam. _______________________________________________ pool mailing list [email protected] http://lists.ntp.org/listinfo/pool
