On Fri, Dec 02, 2016 at 04:19:15PM -0500, kan.li...@intel.com wrote: > From: Kan Liang <kan.li...@intel.com> > > The infrastructure to handle PERF_RECORD_OVERHEAD record type. > A new perf report option is introduced as a knob to show the profiling > overhead information. The option also forces tty output. > > The overhead information is auxillary information, so it should be > possible to access it together with normal sampling information in a > single output file. But the overhead is overall profiling time cost, not > per-sample/event profiling time cost. Making overhead a standard sort > key could confuse the normal samples. > So the information is printed separately in the head of the output. > > Signed-off-by: Kan Liang <kan.li...@intel.com> > --- > tools/perf/Documentation/perf-report.txt | 3 +++ > tools/perf/builtin-report.c | 16 +++++++++++++++- > tools/perf/util/event.c | 9 +++++++++ > tools/perf/util/event.h | 11 +++++++++++ > tools/perf/util/evlist.c | 6 ++++++ > tools/perf/util/evlist.h | 1 + > tools/perf/util/machine.c | 10 ++++++++++ > tools/perf/util/machine.h | 3 +++ > tools/perf/util/session.c | 21 +++++++++++++++++++++ > tools/perf/util/session.h | 3 +++ > tools/perf/util/symbol.h | 3 ++- > tools/perf/util/tool.h | 1 + > 12 files changed, 85 insertions(+), 2 deletions(-)
I think also perf inject needs repipe this overhead handler jirka
