News for hackers. Stuff that matters.
Re:Why does musl make my Rust code so slow? by harrygeez on Tuesday May 05, 2020 @01:19PM (#23082383)
well one of the stated goals of musl is to be simple and correct, and all those mallocs are anything but simple
Re:Why does musl make my Rust code so slow? by littlestymaar on Tuesday May 05, 2020 @02:39PM (#23083268)
That's true for jemalloc, but mimalloc is pretty simple. The reference paper is pretty short and really accessible and IIRC the implementation is around 5klocs. I doubt musl's implementation would much simpler than this.
Re:Why does musl make my Rust code so slow? by dalias on Tuesday May 05, 2020 @09:10PM (#23086951)
5kloc is about 10x larger than musl's existing (old) malloc in source lines. I suspect lots of that is low code density, comments, etc.

I have to lookup what exactly mimalloc is/does every time someone mentions it, because the readme/documentation isn't very descriptive except discussing extensions outside the normal API. I didn't have time to dig through this again today. But I did look at it in some depth on several occasions in the past and it really wasn't suitable for or comparable to what we're doing in musl.

Re:Why does musl make my Rust code so slow? by littlestymaar on Thursday May 07, 2020 @01:56AM (#23100123)
Thanks for clarification, didn't imagine that musl's malloc was that minimalist.

You should definitely have a look at the paper [1] it's only ten page long! (Excluding benchmarks and references)

[1]: https://www.microsoft.com/en-us/research/uploads/prod/2019/0...