This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: [RFC][PROTO][PATCH -tip 0/7] kprobes: support jump optimization on x86
- From: Ingo Molnar <mingo at elte dot hu>
- To: Masami Hiramatsu <mhiramat at redhat dot com>
- Cc: "Frank Ch. Eigler" <fche at redhat dot com>, Andi Kleen <andi at firstfloor dot org>, Frederic Weisbecker <fweisbec at gmail dot com>, Ananth N Mavinakayanahalli <ananth at in dot ibm dot com>, Jim Keniston <jkenisto at us dot ibm dot com>, Andrew Morton <akpm at linux-foundation dot org>, Vegard Nossum <vegard dot nossum at gmail dot com>, "H. Peter Anvin" <hpa at zytor dot com>, Steven Rostedt <rostedt at goodmis dot org>, Avi Kivity <avi at redhat dot com>, Satoshi Oshima <satoshi dot oshima dot fk at hitachi dot com>, systemtap-ml <systemtap at sources dot redhat dot com>, LKML <linux-kernel at vger dot kernel dot org>
- Date: Wed, 8 Apr 2009 17:39:07 +0200
- Subject: Re: [RFC][PROTO][PATCH -tip 0/7] kprobes: support jump optimization on x86
- References: <49DA7702.5030308@redhat.com> <20090408011743.GB5977@nowhere> <49DC0307.6080107@redhat.com> <20090408101056.GA14482@elte.hu> <20090408110602.GA14687@one.firstfloor.org> <20090408130150.GC13827@redhat.com> <49DCBC12.3040700@redhat.com>
* Masami Hiramatsu <mhiramat@redhat.com> wrote:
> Frank Ch. Eigler wrote:
> > On Wed, Apr 08, 2009 at 01:06:02PM +0200, Andi Kleen wrote:
> >> [...]
> >>> I'm curious: what is the biggest kprobe count you've ever seen, in
> >>> the field? 1000? 10,000? 100,000? More?
> >> The limit is iirc how much memory the gcc compiling the probes program
> >> consumes before running out of swap space.
> >
> > On a machine with lots of free RAM, gcc will not hold itself back. On
> > my home server, a 40000-kprobe script compiled (pass 4) in about 4
> > seconds using about 200MB RAM.
>
> Hm, when 40,000 kprobes are optimized, it will consume less than
> 8MB ... I guess that is acceptable for recent machines.
That's more than acceptable, especially for some heavy
instrumentation.
So we can forget about this "uses more memory" downside. Performance
matters far more, and jprobes are fantastic in that regard.
Ingo