Messages in this thread | | | Date | Tue, 19 May 2015 15:40:07 +0900 | From | Namhyung Kim <> | Subject | Re: [PATCH 07/40] perf tools: Handle indexed data file properly |
| |
On Mon, May 18, 2015 at 08:37:28PM +0200, Jiri Olsa wrote: > On Mon, May 18, 2015 at 09:30:22AM +0900, Namhyung Kim wrote: > > When perf detects data file has index table, process header part first > > and then rest data files in a row. Note that the indexed sample data is > > recorded for each cpu/thread separately, it's already ordered with > > respect to themselves so no need to use the ordered event queue > > interface. > > > > Signed-off-by: Namhyung Kim <namhyung@kernel.org> > > --- > > tools/perf/perf.c | 1 + > > tools/perf/perf.h | 2 ++ > > tools/perf/util/session.c | 55 +++++++++++++++++++++++++++++++++++++++-------- > > 3 files changed, 49 insertions(+), 9 deletions(-) > > > > diff --git a/tools/perf/perf.c b/tools/perf/perf.c > > index b857fcbd00cf..960942d9a0b7 100644 > > --- a/tools/perf/perf.c > > +++ b/tools/perf/perf.c > > @@ -27,6 +27,7 @@ const char perf_more_info_string[] = > > int use_browser = -1; > > static int use_pager = -1; > > const char *input_name; > > +bool perf_has_index; > > I probably missed some discussion here, but why is this not > perf_session function? I saw some non session related functions > further in the patchset using this.. is that the reason? > > it seems fairly perf_session specific.. might be worth to > keep it there? just asking ;-)
I agree. But it requires to pass a pointer to session wherever processing samples. Arnaldo said that he wanted to remove accesses to a session in general. So I added the global variable.
https://lkml.org/lkml/2015/3/3/353
Thanks, Namhyung
| |