* Josh Poimboeuf <jpoim...@redhat.com> wrote:
> Anyway, I used some linker magic to temporarily move the unwinder code to the
> end of .text, so that unwinder changes don't add unexpected side effects to
> the
> microbenchmark behavior. Now I'm getting more consistent results: the packed
> struct is measuring ~2% slower. The slight slowdown might just be explained
> by
> the fact that GCC generates some extra instructions for extracting the fields
> out of the packed struct.
Yeah, the 16-bit field accesses versus a zero-extended 32-bit field are more
complex to access even on x86 that has a fair amount of 16-bit legacy.
> In the meantime, I found a ~10% speedup by making the "fast lookup table"
> block
> size a power-of-two (256) to get rid of the need for a slow 'div' instruction.
>
> I think I'm done performance tweaking for now. I'll keep the packed struct,
> and
> add the code for the 'div' removal, and hope to submit v3 soon.
Sounds good to me!
~2% slowdown for ~30% RAM savings for a debug data structure that is about as
large as a typical kernel's total .text is a decent trade-off.
Thanks,
Ingo
