perf report: Add --hierarchy option

The --hierarchy option is to show output in hierarchy mode.  It extends
folding/unfolding in the TUI and GTK browsers to support sort items as
well as callchains.  Users can toggle the items to see the performance
result at wanted level.

  $ perf report --hierarchy --tui
   Overhead       Command / Shared Object / Symbol
  --------------------------------------------------
  +  32.96%       gnome-shell
  -  15.11%       swapper
     -  14.97%       [kernel.vmlinux]
           6.82%        [k] intel_idle
           0.66%        [k] menu_select
           0.43%        [k] __hrtimer_start_range_ns
  ...

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Pekka Enberg <penberg@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1456326830-30456-17-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 89cab84e92fdad5ed705e2c810d24ed45d329364..12113992ac9d0f5ceca0b003cec568717c4208e5 100644 (file)
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -401,6 +401,9 @@ include::itrace.txt[]
 --raw-trace::
        When displaying traceevent output, do not use print fmt or plugins.
 
+--hierarchy::
+       Enable hierarchical output.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO

diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index e0ce9573b79bd26ddfe8cb4aee6eade061a09a12..5950b5a24efdf6024ca58a2da084d9cd43295c12 100644 (file)
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -27,3 +27,4 @@ Skip collecing build-id when recording: perf record -B
 To change sampling frequency to 100 Hz: perf record -F 100
 See assembly instructions with percentage: perf annotate <symbol>
 If you prefer Intel style assembly, try: perf annotate -M intel
+For hierarchical output, try: perf report --hierarchy

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 760e886ca9d9c0be2a860b56c4c3416be2d7f00e..f4d8244449ca429b5c15775eca15f4cdb3dc5470 100644 (file)
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -811,6 +811,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                    "only show processor socket that match with this filter"),
        OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
                    "Show raw trace event output (do not use print fmt or plugins)"),
+       OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
+                   "Show entries in a hierarchy"),
        OPT_END()
        };
        struct perf_data_file file = {
@@ -920,6 +922,21 @@ repeat:
                symbol_conf.cumulate_callchain = false;
        }
 
+       if (symbol_conf.report_hierarchy) {
+               /* disable incompatible options */
+               symbol_conf.event_group = false;
+               symbol_conf.cumulate_callchain = false;
+
+               if (field_order) {
+                       pr_err("Error: --hierarchy and --fields options cannot be used together\n");
+                       parse_options_usage(report_usage, options, "F", 1);
+                       parse_options_usage(NULL, options, "hierarchy", 0);
+                       goto error;
+               }
+
+               sort__need_collapse = true;
+       }
+
        /* Force tty output for header output and per-thread stat. */
        if (report.header || report.header_only || report.show_threads)
                use_browser = 0;