Re: 2.6.5-mjb1

[Marcus Hartig]

Martin J. Bligh wrote:

> The main thing that looks different is that loops per run is lower.
> What does that mean?

Hmm. Sorry, here seems to be an error with my first run of the -mjb1 
bench. Now, in the second try it has the loops running as the others, I 
think. And a good performance...

x11.log:
cpu_hz = 2.0885e+09
cpu_load=0.800000  loops per run = 645177
total latency = 1.953125 ms
cpu latency = 1.562500 ms
max diff = 3.06248 ms (overrun 0)
within 1ms = 38919, factor = 99.9794%
within 2ms = 38927, factor = 100%
deviation = 0.0216797

proc.log:
cpu_hz = 2.0885e+09
cpu_load=0.800000  loops per run = 645114
total latency = 1.953125 ms
cpu latency = 1.562500 ms
max diff = 2.96921 ms (overrun 0)
within 1ms = 15422, factor = 99.987%
within 2ms = 15424, factor = 100%
deviation = 0.0223192

diskwrite.log:
cpu_hz = 2.0885e+09
cpu_load=0.800000  loops per run = 645226
total latency = 1.953125 ms
cpu latency = 1.562500 ms
max diff = 4.64053 ms (overrun 2)
within 1ms = 13345, factor = 99.9176%
within 2ms = 13354, factor = 99.985%
deviation = 0.0517744

diskcopy.log:
cpu_hz = 2.0885e+09
cpu_load=0.800000  loops per run = 644902
total latency = 1.953125 ms
cpu latency = 1.562500 ms
max diff = 3.45113 ms (overrun 0)
within 1ms = 40427, factor = 99.9357%
within 2ms = 40453, factor = 100%
deviation = 0.0407751

diskread.log:
cpu_hz = 2.0885e+09
cpu_load=0.800000  loops per run = 644972
total latency = 1.953125 ms
cpu latency = 1.562500 ms
max diff = 3.2573 ms (overrun 0)
within 1ms = 38383, factor = 99.9401%
within 2ms = 38406, factor = 100%
deviation = 0.0324159


Marcus
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/