kernbench 0.41 review

by on

This is a cpu throughput benchmark originally devised and used by Martin J

License: GPL (GNU General Public License)
File size: 9K
Developer: Con Kolivas
0 stars award from

This is a cpu throughput benchmark originally devised and used by Martin J. Bligh. It is designed to compare kernels on the same machine, or to compare hardware. To compare hardware you need to be running the same architecture machines (eg i386) and run kernbench on the same kernel source tree.

kernbench runs a kernel at various numbers of concurrent jobs: 1/2 number of cpus, optimal (default is 4xnumber of cpus) and maximal job count. Optionally it can also run single threaded. It then prints out a number of useful statistics for the average of each group of runs.

You need at least 2Gb of ram for this to be a true throughput benchmark or else you will get swapstorms.

Ideally it should be run in single user mode on a non-journalled filesystem. To compare results it should always be run in the same kernel tree.


You need a kernel tree (any will do) and the applications 'time' and 'awk'
installed. 'time' is different to the builtin time used by BASH and has more
features desired for this benchmark.

Simply cd into the kernel tree directory and type



kernbench [-n runs] [-o jobs] [-s] [-H] [-O] [-M] [-h] [-v]
n : number of times to perform benchmark (default 5)
o : number of jobs for optimal run (default 4 * cpu)
s : perform single threaded runs (default don't)
H : don't perform half load runs (default do)
O : don't perform optimal load runs (default do)
M : don't perform maximal load runs (default do)
f : fast run
h : print this help
v : print version number

What's New in This Release:
All runs now use the oldconfig if it exists.
Only one warmup run is now done before all the benchmarks.
Logging to kernbench.log was added.
Standard deviation statistics were added.
The code was cleaned up substantially to reuse code where possible.

kernbench 0.41 keywords