This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: [PATCH v2 2.6.38-rc8-tip 0/20] 0: Inode based uprobes
- From: Steven Rostedt <rostedt at goodmis dot org>
- To: Thomas Gleixner <tglx at linutronix dot de>
- Cc: Andi Kleen <andi at firstfloor dot org>, Andrew Morton <akpm at linux-foundation dot org>, Srikar Dronamraju <srikar at linux dot vnet dot ibm dot com>, Peter Zijlstra <peterz at infradead dot org>, Ingo Molnar <mingo at elte dot hu>, Linux-mm <linux-mm at kvack dot org>, Arnaldo Carvalho de Melo <acme at infradead dot org>, Linus Torvalds <torvalds at linux-foundation dot org>, Masami Hiramatsu <masami dot hiramatsu dot pt at hitachi dot com>, Christoph Hellwig <hch at infradead dot org>, Ananth N Mavinakayanahalli <ananth at in dot ibm dot com>, Oleg Nesterov <oleg at redhat dot com>, Jim Keniston <jkenisto at linux dot vnet dot ibm dot com>, Roland McGrath <roland at hack dot frob dot com>, SystemTap <systemtap at sources dot redhat dot com>, LKML <linux-kernel at vger dot kernel dot org>, "Paul E. McKenney" <paulmck at linux dot vnet dot ibm dot com>
- Date: Tue, 15 Mar 2011 16:44:16 -0400
- Subject: Re: [PATCH v2 2.6.38-rc8-tip 0/20] 0: Inode based uprobes
- References: <20110314133403.27435.7901.sendpatchset@localhost6.localdomain6> <20110314163028.a05cec49.akpm@linux-foundation.org> <20110314234754.GP2499@one.firstfloor.org> <alpine.LFD.2.00.1103150114590.2787@localhost6.localdomain6> <20110315180639.GQ2499@one.firstfloor.org> <alpine.LFD.2.00.1103152038280.2787@localhost6.localdomain6> <1300219261.9910.300.camel@gandalf.stny.rr.com> <alpine.LFD.2.00.1103152102430.2787@localhost6.localdomain6>
On Tue, 2011-03-15 at 21:09 +0100, Thomas Gleixner wrote:
> On Tue, 15 Mar 2011, Steven Rostedt wrote:
> I didn't say that ptrace rocks.
>
> All I'm saying is that we want a better argument than a single user
> which is - and yes i tried it more than once - assbackwards beyond all
> imagination.
>
> If gdb, perf, trace can and will make use of it then we have sensible
I'm more interested in the perf/trace than gdb, as the way gdb is mostly
used (at least now) to debug problems in the code with a big hammer
(single step, look at registers/variables). That is, gdb is usually very
interactive and its best to "stop the code" from running to examine what
has happened. gdb is not something you will run on an application that
is being used by others.
With perf/trace things are different, as you want the task to be as
little affected by the tracer as it runs, perhaps even in a production
environment. This is a completely different paradigm.
If gdb uses it, great, but I don't think we should bend over backwards
to make it usable by gdb. Debugging and tracing are different, with
different requirements and needs.
> arguments enough to go there. If systemtap can use it as well then I
> have no problem with that..
Fair enough.
-- Steve