[lld] [llvm] [LLD][COFF] Prefetch inputs early-on to improve link times (PR #169224)

[Hans Wennborg via llvm-commits]

https://github.com/zmodem commented:

Those are nice numbers!

I wonder what this does in more low-RAM situations though. Will it increase swapping, or is the OS smart enough to hold back a little on the prefetching then?

We've had reports (https://crbug.com/428641952) that lld is using too much RAM when linking PDBs, and this sounds like it could potentially make that worse.

(Related to that bug, I've been wondering if we could do more of the opposite, and call `mapped_file_region::dontNeed()` when we're done writing out an object file's code and debug symbols to the final outputs.)

https://github.com/llvm/llvm-project/pull/169224