kprobes performance on i386 vs x86_64

[Masami Hiramatsu]

Hi,

Keshavamurthy, Anil S wrote:
> Possible. Can you rerun the same tests again with some dummy
> post-kprobe-handler as djprobes will not come into effect if you have
> post-kprobe-handler.

You are right.
By the way, that is the effects of the kprobe-booster
(djprobe is not merged yet).

Thanks,

-- 
Masami HIRAMATSU
Linux Technology Center
Hitachi, Ltd., Systems Development Laboratory
E-mail: masami.hiramatsu.pt@hitachi.com


> 
> Thanks,
> 
> -Anil Keshavamurthy
> Open Source Technology Center/SSG
> Intel Corp.
> (w) 503-712-4476
> email: anil.s.keshavamurthy@intel.com
> 
> -----Original Message-----
> From: systemtap-owner@sourceware.org
> [mailto:systemtap-owner@sourceware.org] On Behalf Of Martin Hunt
> Sent: Monday, January 22, 2007 11:56 AM
> To: systemtap@sources.redhat.com
> Subject: kprobes performance on i386 vs x86_64
> 
> Is there a reason why i386 kprobes are 2-3 times faster than x86_64 on
> 2.6.19? This is on the same hardware. Is djprobes only working on i386
> or something?
> 
> Martin
> 
> 
>