[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20090503090216.GA22776@elte.hu>
Date: Sun, 3 May 2009 11:02:16 +0200
From: Ingo Molnar <mingo@...e.hu>
To: Steven Rostedt <rostedt@...dmis.org>
Cc: Frederic Weisbecker <fweisbec@...il.com>,
linux-kernel@...r.kernel.org
Subject: Re: BUG: Function graph tracer hang
* Steven Rostedt <rostedt@...dmis.org> wrote:
> > > This is low in my priority of things to do, but I'll at least
> > > add it to my "to do" list.
> >
> > I think we should mark the branch tracer as CONFIG_BROKEN -
> > there's been too many problems with it. Thoughts?
>
> You mean the branch profiler? I've been using it without any
> issues. The issues usually come when we have it combined with
> other tracers on large(?) SMP boxes. I don't hit the cacheline
> bouncing hang on my 4 cores.
i got a boot crash in the branch tracer:
[ 4.472909] calling init_wakeup_tracer+0x0/0x30 @ 1
[ 4.478220] Testing tracer wakeup: PASSED
[ 4.798372] Testing tracer wakeup_rt: PASSED
[ 5.114742] initcall init_wakeup_tracer+0x0/0x30 returned 0 after 621644 usecs
[ 5.122275] calling stack_trace_init+0x0/0x70 @ 1
[ 5.127771] initcall stack_trace_init+0x0/0x70 returned 0 after 396 usecs
[ 5.134836] calling init_graph_trace+0x0/0x20 @ 1
[ 5.139950] Testing tracer function_graph: PASSED
[ 7.088654] initcall init_graph_trace+0x0/0x20 returned 0 after 1903070 usecs
[ 7.096080] calling init_branch_tracer+0x0/0x40 @ 1
[ 7.101400] Testing tracer branch:
config attached.
Ingo
View attachment "config-Sat_May__2_11_01_17_CEST_2009.bad" of type "text/plain" (69185 bytes)
Powered by blists - more mailing lists