On Fri, Jul 11, 2025 at 07:43:06AM -0000, Jan Drögehoff wrote:
> These kind of benchmarks are worthless and cannot be reliably
> reproduced by anyone.
Here's a radical idea. Instead of going through all of that effort to
produce nonreproducible, useless results, they could install the
Phoronix Test Suite [1] and instantly gain access to a huge repitour of
fully reproducible automated tests involving real-world workloads.
If the existing tests are inadequate, add new ones, so we'll have a
useful, reproducible example we can use to figure out where performance
regressions (if any) are coming from.
[1] My issues with Phoronix (and their benchmarks) are editorial in nature;
but their methodology and tools are solid.
- Solomon
--
Solomon Peachy pizza at shaftnet dot org (email&xmpp)
@pizza:shaftnet dot org (matrix)
Dowling Park, FL speachy (libera.chat)
Attachment:
signature.asc
Description: PGP signature
-- _______________________________________________ devel mailing list -- devel@xxxxxxxxxxxxxxxxxxxxxxx To unsubscribe send an email to devel-leave@xxxxxxxxxxxxxxxxxxxxxxx Fedora Code of Conduct: https://docs.fedoraproject.org/en-US/project/code-of-conduct/ List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines List Archives: https://lists.fedoraproject.org/archives/list/devel@xxxxxxxxxxxxxxxxxxxxxxx Do not reply to spam, report it: https://pagure.io/fedora-infrastructure/new_issue
