lkml.org 
[lkml]   [2003]   [Jul]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Subject[BENCHMARK] 2.5.74-mm1 with contest
Date
Here are contest benchmarks for 2.5.74-mm1 with my scheduler tweaks:

no_load:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 1 77 94.8 0.0 0.0 1.00
2.5.74 1 79 93.7 0.0 0.0 1.00
2.5.74-mm1 1 79 94.9 0.0 0.0 1.00
cacherun:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 1 75 98.7 0.0 0.0 0.97
2.5.74 1 75 98.7 0.0 0.0 0.95
2.5.74-mm1 1 76 98.7 0.0 0.0 0.96
process_load:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 2 108 67.6 67.0 29.6 1.40
2.5.74 2 109 67.9 65.0 28.4 1.38
2.5.74-mm1 2 106 69.8 60.0 28.3 1.34
ctar_load:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 3 103 74.8 0.0 0.0 1.34
2.5.74 3 104 75.0 0.0 0.0 1.32
2.5.74-mm1 3 109 72.5 1.0 5.5 1.38
xtar_load:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 3 113 66.4 2.0 4.4 1.47
2.5.74 3 106 72.6 1.0 3.8 1.34
2.5.74-mm1 3 123 61.8 2.0 4.8 1.56
io_load:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 4 127 59.1 39.7 16.5 1.65
2.5.74 4 331 23.9 117.5 18.7 4.19
2.5.74-mm1 4 122 63.1 44.6 19.7 1.54
io_other:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 2 112 67.9 43.0 19.6 1.45
2.5.74 2 121 64.5 50.8 22.1 1.53
2.5.74-mm1 2 118 65.3 51.2 24.6 1.49
read_load:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 2 100 76.0 7.8 7.0 1.30
2.5.74 2 104 76.0 6.6 4.8 1.32
2.5.74-mm1 2 106 74.5 8.3 6.6 1.34
list_load:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 2 93 80.6 0.0 7.5 1.21
2.5.74 2 97 79.4 0.0 7.2 1.23
2.5.74-mm1 2 94 81.9 0.0 7.4 1.19
mem_load:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 2 114 68.4 54.0 1.8 1.48
2.5.74 2 97 80.4 59.5 2.0 1.23
2.5.74-mm1 2 99 79.8 51.5 2.0 1.25
dbench_load:
Kernel [runs] Time CPU% Loads LCPU% Ratio
2.5.73-mm1 4 365 20.8 5.0 48.2 4.74
2.5.74 4 334 23.1 5.0 52.7 4.23
2.5.74-mm1 4 255 30.2 5.0 42.0 3.23

A little more here, a little less there. No major changes except for dbench
load which appears to have significantly shorter compile times. As kernel
compiles are not by their nature "interactive", these results are expected.
It is nice to see that it doesn't appear to starve any load unecessarily as
well.

Contest can show the kernel's ability to perform in the setting of different
loads without being choked, but will not show if your audio application will
get to play when it wants to, nor whether your windows will move around the
screen smoothly.

Con

P.S. Does anyone see the irony in the fact that my own benchmark won't show
that my patch does anything?

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

\
 
 \ /
  Last update: 2005-03-22 13:46    [W:0.030 / U:3.956 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site