Re: [PATCH 4/5] perf record: mmap output file - v5

[Ingo Molnar <mingo@kernel.org>]

* Peter Zijlstra <peterz@infradead.org> wrote:

> On Tue, Nov 12, 2013 at 10:11:21PM +0100, Ingo Molnar wrote:
> > 
> > * David Ahern <dsahern@gmail.com> wrote:
> > 
> > > > Dunno.. it _should_ all work. Try it and see what it does.. Once the 
> > > > events are bigger than a page things might get 'interesting' though.
> > 
> > Which could be the case with call-graph recording, right?
> 
> Not typically, I think we're limiting call graphs to 127 u64, which is 
> ~1k. Maybe you can blow the single page if you also do a large 
> top-of-stack copy for dwarf/unwind nonsense.

What I meant was dwarf style call graph recording:

 tools/perf/builtin-record.c:                    const unsigned long default_stack_dump_size = 8192;

Doesn't that mean 8K+ events?

> > > one option here is not allow page faults and system wide system 
> > > calls. system wide tracing needs mmap; page faults for a task can 
> > > use write(). I left that option in case something like this came up.
> > 
> > So maybe splice() sounds like the right long term solution after all?
> > :-/
> 
> Right until you put a tracepoint (kprobe) somewhere in whatever function 
> is used to transfer a single page into/from a splice pipe.

That ought to be a far less common occurance than tracing page faults 
though.

> You can always screw yourself over using this stuff, no exceptions.

Granted, as the many notrace markings demonstrate this stuff really wants 
to observe itself observing itself all the time! :)

Thanks,

	Ingo