Re: [PATCH][2.6] Completely out of line spinlocks / i386

[Zwane Mwaikambo]

On Thu, 12 Aug 2004, William Lee Irwin III wrote:

> On Wed, Aug 11, 2004 at 07:04:24PM -0700, William Lee Irwin III wrote:
> > Odd, it was either you or mpm who told me the results. I personally
> > never even tried running the thing. I was merely told some other, prior
> > attempt at doing some kind of spinlock uninlining failed to run, this
> > thing did, and that it shaved that memorable amount off of .text size.
> > I recall I compiled it myself and saw about half as much reduction
> > (120KB instead of 220KB), possibly due to .config or compiler differences.
> > I'll dust things off and so on.
>
> Okay, the results on 2.6.8-rc4 (COOL had a bit of porting, basically
> dropping the hunks associated with spin_lock_flags_string or whatever
> it is). Chose the .config largely to be vaguely deterministic, but had
> to nuke the "System is too big" check in arch/x86_64/boot/tools/build.c.
>
>               text    data     bss     dec     hex filename
> mainline: 20708323        6603052 1878448 29189823        1bd66bf vmlinux
> cool:     20619594        6588166 1878448 29086208        1bbd200 vmlinux
> C-func:   19969264        6583128 1878384 28430776        1b1d1b8 vmlinux

Shit that's quite the variance, which compiler are you using?
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/