perf top: Add --children option

The --children option is for showing accumulated overhead (period)
value as well as self overhead.  It should be used with one of -g or
--call-graph option.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arun Sharma <asharma@fb.com>
Tested-by: Rodrigo Campos <rodrigo@sdfg.com.ar>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1401335910-16832-21-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>

diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index dcfa54c851e9d6ee1dcd1b0ffed15a6863ee881e..180ae02137a519acf1b3d779a92eb651db6b4aff 100644 (file)
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -119,7 +119,7 @@ Default is to monitor all CPUS.
 --fields=::
        Specify output field - multiple keys can be specified in CSV format.
        Following fields are available:
-       overhead, overhead_sys, overhead_us, sample and period.
+       overhead, overhead_sys, overhead_us, overhead_children, sample and period.
        Also it can contain any sort key(s).
 
        By default, every sort keys not specified in --field will be appended
@@ -161,6 +161,12 @@ Default is to monitor all CPUS.
        Setup and enable call-graph (stack chain/backtrace) recording,
        implies -g.
 
+--children::
+       Accumulate callchain of children to parent entry so that then can
+       show up in the output.  The output will have a new "Children" column
+       and will be sorted on the data.  It requires -g/--call-graph option
+       enabled.
+
 --max-stack::
        Set the stack depth limit when parsing the callchain, anything
        beyond the specified depth will be ignored. This is a trade-off

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b1cb5f589ade4f2c9b0be59a856f5a895d3b2320..fea55e3fc931675ad68766deca7d1710d0f42449 100644 (file)
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1098,6 +1098,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
        OPT_CALLBACK(0, "call-graph", &top.record_opts,
                     "mode[,dump_size]", record_callchain_help,
                     &parse_callchain_opt),
+       OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+                   "Accumulate callchains of children and show total overhead as well"),
        OPT_INTEGER(0, "max-stack", &top.max_stack,
                    "Set the maximum stack depth when parsing the callchain. "
                    "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
@@ -1203,6 +1205,11 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
        top.sym_evsel = perf_evlist__first(top.evlist);
 
+       if (!symbol_conf.use_callchain) {
+               symbol_conf.cumulate_callchain = false;
+               perf_hpp__cancel_cumulate();
+       }
+
        symbol_conf.priv_size = sizeof(struct annotation);
 
        symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);