Udo van den Heuvel via devel writes:
> hpet:
That's a fantastically wierd distribution. Here's what my old single
core Athlon64 does:
--8<---------------cut here---------------start------------->8---
ntpsec/attic> ./clocks
res avg min dups CLOCK
1 1498 977 CLOCK_REALTIME
4000000 42 7999938 -2 CLOCK_REALTIME_COARSE
1 1467 908 CLOCK_MONOTONIC
1 1592 977 CLOCK_MONOTONIC_RAW
1 2558 1047 CLOCK_BOOTTIME
Histogram: CLOCK_REALTIME, 1 ns per bucket, 1000000 samples.
ns hits
977 9496
978 30575
1047 325172
1048 498724
1117 68805
1118 55456
1187 7804
1188 3121
1257 91
1258 14
742 samples were bigger than 1258.
--8<---------------cut here---------------end--------------->8---
Can you fix the clock to all cores to a single frequency (using
cpufreq-utils) and try that same test again? If that gives you a
narrower distribution, please try another frequency as well to see if
the peak shifts.
Regards,
Achim.
--
+<[Q+ Matrix-12 WAVE#46+305 Neuron microQkb Andromeda XTk Blofeld]>+
SD adaptation for Waldorf Blofeld V1.15B11:
http://Synth.Stromeko.net/Downloads.html#WaldorfSDada
_______________________________________________
devel mailing list
devel@ntpsec.org
http://lists.ntpsec.org/mailman/listinfo/devel
