Re: "Significant Garbage Collection Improvement For Emacs" - sweep_conses performance improved by 50%?

[Po Lu]

Stefan Monnier <monnier@iro.umontreal.ca> writes:

> Basically you're replacing 1kB blocks with 32kB blocks, which indeed
> seems very reasonable.  Back when I introduced those blocks (and their
> associated bitmaps) I chose 1kB because I wanted something small enough
> that it couldn't be worse than what we had before, not because it was
> the best choice.

It may be worth nothing that I chose a cons and float block size of 4
times the page size while working with the incremental GC, which ends up
16k on most systems.  However, there are also two pairs of markbits in
each block.

I haven't seen anything bad happen from that choice yet.  But there,
BLOCK_ALIGN is gone in the first place, and it relies on valloc
returning suitably aligned memory.