From: "Frank Ch. Eigler" <fche@redhat.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>, Roland McGrath <roland@redhat.com>,
Steven Rostedt <rostedt@goodmis.org>,
utrace-devel@redhat.com, linux-kernel@vger.kernel.org,
Linus Torvalds <torvalds@linux-foundation.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH 3/3] utrace-based ftrace "process" engine, v2
Date: Sat, 21 Mar 2009 08:57:06 -0400 [thread overview]
Message-ID: <20090321125706.GB3566@redhat.com> (raw)
In-Reply-To: <20090321050422.d1d99eec.akpm@linux-foundation.org>
Hi -
On Sat, Mar 21, 2009 at 05:04:22AM -0700, Andrew Morton wrote:
> [...]
> > There have been many mixed messages from LKML on the topic - sometimes
> > mentioning systemtap is forbidden, other times necessary. Sorry about
> > that.
>
> heh. We all love systemtap and want it to get better.
Great!
> [...]
> I have strong memories of being traumatised by reading the uprobes
> code. What's the story on all of that nowadays?
uprobes, being a layer upon utrace that provides a kprobes-like
breakpointing API for user threads, is being refactored into several
parts. I don't know about the aesthetics of it all, but I believe the
general future plan is this:
One piece would perform machine code analysis (to classify
instructions for ideal/safe placement of breakpoints or for code
patching), and another thin layer that uses this and utrace to manage
user-space breakpoints. (Systemtap would interface at this point.)
Then a user-space syscallish interface could come along to expose this
to a super-ptrace client (to speed up gdb; perhaps to allow multiple
debuggers). Plus one might as well add an ftrace-engine for it
(directly analogous to the recent kprobe-based one that ftrace people
found "cool".)
> > > Actually it seems that the whole utrace-ftrace thing is a big
> > > distraction and could/should just be omitted. This is a systemtap
> > > feature and should be viewed as such. [...]
> >
> > utrace is a better way to perform user thread management than what is
> > there now, and the utrace-ftrace widget shows how to *hook* thread
> > events such as syscalls in a lighter weight / more managed way than
> > the first one proposed. (That's one reason we've been participating
> > in the ftrace discussions.) Of course it can be made to use the fine
> > syscall pretty-printing code recently added.
>
> eh. Boring. Let's fix systemtap?
There are several constituencies here, some of which find the above
exciting. That's OK and we'd like to help them too.
- FChE
next prev parent reply other threads:[~2009-03-21 12:58 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-21 1:39 [PATCH 0/3] utrace Roland McGrath
2009-03-21 1:41 ` [PATCH 1/3] signals: tracehook_notify_jctl change Roland McGrath
2009-03-21 1:41 ` [PATCH 2/3] utrace core Roland McGrath
2009-03-21 8:49 ` Andrew Morton
2009-03-21 14:08 ` Renzo Davoli
2009-03-21 14:34 ` Ingo Molnar
2009-03-21 16:37 ` Renzo Davoli
2009-03-21 16:44 ` Ingo Molnar
2009-03-23 4:34 ` Roland McGrath
2009-03-23 4:35 ` Roland McGrath
2009-03-23 10:57 ` Will Newton
2009-03-21 1:42 ` [PATCH 3/3] utrace-based ftrace "process" engine, v2 Roland McGrath
2009-03-21 7:43 ` Ingo Molnar
2009-03-21 8:39 ` Andrew Morton
2009-03-21 9:12 ` Ingo Molnar
2009-03-21 11:19 ` Andrew Morton
2009-03-21 11:51 ` Frank Ch. Eigler
2009-03-21 12:04 ` Andrew Morton
2009-03-21 12:57 ` Frank Ch. Eigler [this message]
2009-03-21 15:45 ` Ingo Molnar
2009-03-21 20:35 ` Diego Calleja
2009-03-22 12:17 ` Ingo Molnar
2009-03-21 21:34 ` Andrew Morton
2009-03-21 21:51 ` Frank Ch. Eigler
2009-03-21 22:02 ` Linus Torvalds
2009-03-21 22:20 ` Frank Ch. Eigler
2009-03-21 22:37 ` Alexey Dobriyan
2009-03-21 23:38 ` Frank Ch. Eigler
2009-03-22 10:25 ` Ingo Molnar
2009-03-23 5:33 ` Roland McGrath
2009-03-23 5:20 ` Roland McGrath
2009-03-22 12:37 ` Ingo Molnar
2009-03-23 13:48 ` Alexey Dobriyan
2009-03-23 15:14 ` Oleg Nesterov
2009-03-23 21:44 ` Theodore Tso
2009-03-30 22:18 ` Andrew Morton
2009-03-30 22:52 ` Frank Ch. Eigler
2009-03-31 9:17 ` Peter Zijlstra
2009-03-31 11:27 ` Peter Zijlstra
2009-03-31 11:38 ` Frank Ch. Eigler
2009-03-31 16:25 ` Christoph Hellwig
2009-03-31 20:54 ` Roland McGrath
2009-03-21 21:48 ` Frank Ch. Eigler
2009-03-22 12:08 ` Ingo Molnar
2009-03-22 12:53 ` Ingo Molnar
2009-03-23 20:25 ` Frank Ch. Eigler
2009-03-23 20:39 ` Linus Torvalds
2009-03-23 5:09 ` Roland McGrath
2009-03-24 5:29 ` Ananth N Mavinakayanahalli
2009-03-24 5:54 ` Andrew Morton
2009-03-24 6:10 ` Ananth N Mavinakayanahalli
2009-03-23 4:49 ` Roland McGrath
2009-03-23 6:34 ` Ingo Molnar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20090321125706.GB3566@redhat.com \
--to=fche@redhat.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=roland@redhat.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=utrace-devel@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox