Messages in this thread | | | Subject | Re: [PATCH 3/6] perf script: move printing of 'common' data from print_event and rename | From | Steven Rostedt <> | Date | Thu, 10 Mar 2011 11:05:35 -0500 |
| |
On Thu, 2011-03-10 at 12:51 -0300, Arnaldo Carvalho de Melo wrote: > Em Thu, Mar 10, 2011 at 10:20:53AM -0500, Steven Rostedt escreveu: > > On Wed, Mar 09, 2011 at 10:23:25PM -0700, David Ahern wrote: > > > This change does impact output: latency data is trace specific and is now > > > printed after the common data - comm, tid, cpu, time and event name. > > > > Signed-off-by: David Ahern <daahern@cisco.com> > > > > tools/perf/builtin-script.c | 38 ++++++++++++++++++++++----- > > > tools/perf/util/trace-event-parse.c | 49 +++++++--------------------------- > > > I was hoping after the next merge window to start making a common library > > for parsing events. This way things like powertop and timechart or > > anything that uses the perf interface does not need to write its own > > parsing of events, or expect the event formats to be hardcoded. > > > > The trace-event-parse.c was taking from trace-cmd's parse-events.c code > > and hopefully the two can merge again. The parse-events.c code in > > trace-cmd has gone through several iterations that has made it much more > > robust and flexible. I purposely kept it as a separate libarary not > > dependent on trace-cmd so that it could be used by other utilities like > > perf. > > David is kinda new to this perf/ftrace/trace-cmd/etc soap opera, and he
Lucky him ;)
> has been patient to go thru the motions with Peter, Thomas, Frédéric and > me, going from doing what he wants in 'perf report' to 'perf script', > etc. > > We're almost to the point where his feature is implemented in a > way Frédéric, the one most actively reviewing his work, is satisfied, > right Frédéric?
You must have one of those keyboards where it is easy to make that é
> > I think the merge with the libraries you mention is something that is > not a precondition to merging David's work. > > And his work is at least moving things in the trace parts of tools/, > that was so far dormant.
Note, I'm not saying that his work should be put on hold. I actually want to start it up again. Maybe I worded this response wrong. It was more about bringing David up to speed on what I want to do next than saying not to do this work.
Thanks,
-- Steve
-- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |