Re:How to get consistent results when benchmarking on Linux?
by ThrowawayR2 on Sunday August 04, 2019 @12:15PM
(#20607381)
Good information but it rather depends on what the goal of the benchmarking is. Many (most?) of those changes aim for consistency at the expense of making the benchmark server vastly different from the configuration of a normal end-user server, raising the question of how to translate the benchmark results into usable information for the end-user.
[ Parent
| on HN ]
Re:How to get consistent results when benchmarking on Linux?
by dendibakh on Sunday August 04, 2019 @02:30PM
(#20608345)
Yep. And I think I stated that in the beginning of the article. :)
This one:
> It is important that you understand one thing before we start. If you use all the advices in this article it is not how your application will run in practice. If you want to compare two different versions of the same program you should use suggestions described above. If you want to get absolute numbers to understand how your app will behave in the field, you should not make any artificial tuning to the system, as the client might have default settings.