This is the mail archive of the
systemtap@sources.redhat.com
mailing list for the systemtap project.
RE: instrumenting vs. module loading
- From: "Chen, Brad" <brad dot chen at intel dot com>
- To: "Frank Ch. Eigler" <fche at redhat dot com>
- Cc: <systemtap at sources dot redhat dot com>
- Date: Fri, 13 May 2005 09:53:21 -0700
- Subject: RE: instrumenting vs. module loading
I've added these cases to the test document, which I'm
preparing to check into CVS hopefully today.
Brad
-----Original Message-----
From: systemtap-owner@sources.redhat.com
[mailto:systemtap-owner@sources.redhat.com] On Behalf Of Frank Ch.
Eigler
Sent: Friday, May 13, 2005 8:18 AM
To: systemtap@sources.redhat.com
Subject: Re: instrumenting vs. module loading
Hi -
Ananth N Mavinakayanahalli wrote:
> [...]
> On more thought, we won't see any such issues - we won't have the
> breakpoint hit at all - the whole text gets overlaid right? [...]
It sounds at least like a race condition (probe executing on one CPU,
another one performing a module load/unload). Anyway, systemtap will
endavour to provide more safety in this regard than kprobes alone
would.
(Brad, this scenario should go into your testing paper, as could my
kprobes stress-testing suggestions in http://tinyurl.com/7m74w, which
is an even meaner version of Rusty's ia64 idea.)
- FChE