Re: [PATCH -tip] x86/locking/atomic: Use asm_inline for atomic locking insns
From: Uros Bizjak
Date: Sun Mar 02 2025 - 15:56:49 EST
On Fri, Feb 28, 2025 at 5:48 PM Dave Hansen <dave.hansen@xxxxxxxxx> wrote:
>
> On 2/28/25 04:35, Uros Bizjak wrote:
> > The code size of the resulting x86_64 defconfig object file increases
> > for 33.264 kbytes, representing 1.2% code size increase:
> >
> > text data bss dec hex filename
> > 27450107 4633332 814148 32897587 1f5fa33 vmlinux-old.o
> > 27483371 4633784 814148 32931303 1f67de7 vmlinux-new.o
>
> So, first of all, thank you for including some objective measurement of
> the impact if your patches. It's much appreciated.
>
> But I think the patches need to come with a solid theory of why they're
> good. The minimum bar for that, I think, is *some* kind of actual
> real-world performance test. I'm not picky. Just *something* that spends
> a lot of time in the kernel and ideally where a profile points at some
> of the code you're poking here.
>
> I'm seriously not picky: will-it-scale, lmbench, dbench, kernel
> compiles. *ANYTHING*. *ANY* hardware. Run it on your laptop.
>
> But performance patches need to come with performance *numbers*.
Please find lmbench results from unpatched (fedora.0) and patched
(fedora.1) fedora-41 6.13.5 kernels.
lmbench is from [1]
[1] https://fedora.pkgs.org/41/rpm-sphere-x86_64/lmbench-3.0-0.a9.3.x86_64.rpm.html
Some tests show quite different results, but I'd appreciate some help
in interpreting the results. Maybe they show that the price of 33
kbytes is worth the improvement, or they will motivate someone
experienced in kernel benchmarks to benchmark the patch in a more
scientific way.
Thanks,
Uros.
Attachment:
results.tar.bz2
Description: BZip2 compressed data