Messages in this thread | | | Date | Tue, 1 Mar 2011 16:11:40 +0100 | Subject | Re: [PATCH 4/6] perf script: dump software events too | From | Frederic Weisbecker <> |
| |
2011/3/1 David Ahern <daahern@cisco.com>: > I don't follow what you mean. > > This is the same place that tracepoints are dumped. In the > PERF_TYPE_TRACEPOINT case process_event == print_event which dumps the > lines to stdout.
No it's not. scripting_ops can be either default_scripting_ops, perl_scripting_ops or python_scripting_ops.
Hence process_sample_event() doesn't necessarily ends up pretty print events. It can also invoke a script that may decide to do what it wants with events.
pretty printing must be an endpoint decision.
> I came in added a switch that invokes a different handler for software > events. Software events will be processed differently than tracepoint. > The print_event function and its pretty_print function are not designed > to dump software events (and eventually hardware events).
Why shouldn't it be designed to dump software events? It's called print_event(). Its current version is rather something I would call "limited". But it was not designed to be limited.
Ideally, we should have print_tracepoint_event() in trace-event-parse.c, print_software_event() where you want, and have print_event() in builtin-script.c that wraps on those.
| |