I'm interested in learning more about the performance possibilities of mmap for the case read-only X 64-bit-only and found this interesting article by Justin Willmert [0] from 2020-11-05 on using the Linux-specific MAP_POPULATE flag to prefault memory on a single-thread to increase performance.<p>Surprisingly, the article didn't appear to have been submitted previously when I searched for its URL.<p>And seeing as there are lots of HN folks who know a lot more about it than me, I submitted it to see what I could learn from the comments.<p>Edit 0: also found that it wasn't on archive.org so I submitted it there [1].<p>Edit 1: and just to make sure that this nice article is saved for posterity, I submitted it to archive.is too [2].<p>[0] <a href="https://justinwillmert.com/about/" rel="nofollow">https://justinwillmert.com/about/</a>
"an experimental physicist with an affinity for modeling and analysis. I am particularly interested in melding computational physics and software engineering to solve novel problems."<p>[1] <a href="https://web.archive.org/web/20210810021537/https://justinwillmert.com/articles/2020/prefaulting-memory-mapped-arrays-in-julia/" rel="nofollow">https://web.archive.org/web/20210810021537/https://justinwil...</a><p>[2] <a href="https://archive.is/VjtSh" rel="nofollow">https://archive.is/VjtSh</a>
I looked at the source code for UnixMaps.jl. It seems to call :jl_mmap (exported by Julia's underlying C++ source code). I wonder why this style might be preferred to, say, calling libc directly?