My days as a LWN subscriber are now far behind but gosh reading the comments there was a blast. I had forgotten how good proper technical discussions used to be.
[1] https://lore.kernel.org/lkml/20240222203726.1101861-1-willy@...
Is it common to add an unused data structure into the kernel without understanding its performance characteristics? If they are available it is not obvious to someone who has read the article, read the commit message, read lkml, went looking for benchmarks, and has still come up with no concept of how this might perform in realistic or synthetic scenarios.
> Seriously, a simple google search or taking a minute to follow the first link in the article would have shown you that the patch set obviously came with a benchmark [1].
If you're referring to the table with headers "number xarray maple rhash rosebush", it's an estimate of memory usage, not a benchmark. And the author (Matthew Wilcox) says "I've assumed an average chain length of 10 for rhashtable in the above memory calculations", which folks questioned. So there's reason to doubt its correctness.
> It’s someone posting a patch to the kernel mailing list, not some random kid on GitHub, there is no point assuming they are an idiot to try to shine.
Let's just let the work speak rather than flagging the author as an idiot or genius...at present rosebush is unproven and based on questionable assumptions. That might change in future rounds.
> Reviewers were, as ever, skeptical in the face of assertions about performance without corresponding measurements. Peng Zhang asked "how much performance improvement is expected if it is applied to dcache?" Wilcox didn't reply to Zhang's question.
Am I reading this right that the author supplied no actual (benchmarking) evidence to support their proposed performance optimization?