Benchmarks
Hello everyone,
If someone make some modifications to kernel code and want to know how much overead those modifications has caused, what are the benchmarks that one should use to calculate the overhead of the added code.
please cc the reply to me.
Thanks a lot.
--
Sushant Sharma
http://cs.unm.edu/~sushant
Quoted 5 lines · Sharma Sushant
Hello everyone,
If someone make some modifications to kernel code and want to know how much overead those modifications has caused, what are the benchmarks that one should use to calculate the overhead of the added code.
please cc the reply to me.
it really depends on what area of the kernel you're changing.. there's no "golden" benchmark that tests the entire kernel and gives one nice answer... there are however a lot of smaller benchmarks that test a portion of the kernel....
Well that would very much depend on what you're changing. For example, if it is a file system modification, then use file system benchmarks. However, those same benchmarks would not be appropriate for changes in the network stack. A pre-written benchmark may not even exist. You should use your knowledge of what you are changing to choose an appropriate benchmark that will stress that part of the kernel.
Avishay Traeger
http://www.fsl.cs.sunysb.edu/~avishay/
Quoted 15 lines · Sharma Sushant
Hello everyone,
If someone make some modifications to kernel code and want to know how much overead those modifications has caused, what are the benchmarks that one should use to calculate the overhead of the added code.
please cc the reply to me.
Thanks a lot.--
Sushant Sharma
http://cs.unm.edu/~sushant
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Quoted 7 lines · Avishay Traeger
Well that would very much depend on what you're changing. For example, if it is a file system modification, then use file system benchmarks. However, those same benchmarks would not be appropriate for changes in the network stack. A pre-written benchmark may not even exist. You should use your knowledge of what you are changing to choose an appropriate benchmark that will stress that part of the kernel.
Or, as is often the case, write a benchmark app yourself to test the specific thing you've changed.
--
Jesper Juhl <[email protected]>
Don't top-post http://www.catb.org/~esr/jargon/html/T/top-post.html
Plain text mails only, please http://www.expita.com/nomime.html