perf report/top: Add option to collapse undesired parts of call graph

For example, in an application with an expensive function implemented
with deeply nested recursive calls, the default call-graph presentation
is dominated by the different callchains within that function.  By
ignoring these callees, we can collect the callchains leading into the
function and compactly identify what to blame for expensive calls.

For example, in this report the callers of garbage_collect() are
scattered across the tree:

  $ perf report -d ruby 2>- | grep -m10 ^[^#]*[a-z]
      22.03%     ruby  [.] gc_mark
                 --- gc_mark
                    |--59.40%-- mark_keyvalue
                    |          st_foreach
                    |          gc_mark_children
                    |          |--99.75%-- rb_gc_mark
                    |          |          rb_vm_mark
                    |          |          gc_mark_children
                    |          |          gc_marks
                    |          |          |--99.00%-- garbage_collect

If we ignore the callees of garbage_collect(), its callers are coalesced:

  $ perf report --ignore-callees garbage_collect -d ruby 2>- | grep -m10 ^[^#]*[a-z]
      72.92%     ruby  [.] garbage_collect
                 --- garbage_collect
                     vm_xmalloc
                    |--47.08%-- ruby_xmalloc
                    |          st_insert2
                    |          rb_hash_aset
                    |          |--98.45%-- features_index_add
                    |          |          rb_provide_feature
                    |          |          rb_require_safe
                    |          |          vm_call_method

Signed-off-by: Greg Price <price@mit.edu>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20130623031720.GW22203@biohazard-cafe.mit.edu
Link: http://lkml.kernel.org/r/20130708115746.GO22203@biohazard-cafe.mit.edu
Cc: Fengguang Wu <fengguang.wu@intel.com>
[ remove spaces at beginning of line, reported by Fengguang Wu ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 15 insertions, 9 deletions

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 5dd5026a82ef..f9f9d6381b9a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1058,11 +1058,10 @@ int machine__process_event(struct machine *machine, union perf_event *event)
 	return ret;
 }
 
-static bool symbol__match_parent_regex(struct symbol *sym)
+static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 {
-	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
+	if (sym->name && !regexec(regex, sym->name, 0, NULL, 0))
 		return 1;
-
 	return 0;
 }
 
@@ -1159,8 +1158,8 @@ struct branch_info *machine__resolve_bstack(struct machine *machine,
 static int machine__resolve_callchain_sample(struct machine *machine,
 					     struct thread *thread,
 					     struct ip_callchain *chain,
-					     struct symbol **parent)
-
+					     struct symbol **parent,
+					     struct addr_location *root_al)
 {
 	u8 cpumode = PERF_RECORD_MISC_USER;
 	unsigned int i;
@@ -1211,8 +1210,15 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 					   MAP__FUNCTION, ip, &al, NULL);
 		if (al.sym != NULL) {
 			if (sort__has_parent && !*parent &&
-			    symbol__match_parent_regex(al.sym))
+			    symbol__match_regex(al.sym, &parent_regex))
 				*parent = al.sym;
+			else if (have_ignore_callees && root_al &&
+			  symbol__match_regex(al.sym, &ignore_callees_regex)) {
+				/* Treat this symbol as the root,
+				   forgetting its callees. */
+				*root_al = al;
+				callchain_cursor_reset(&callchain_cursor);
+			}
 			if (!symbol_conf.use_callchain)
 				break;
 		}
@@ -1237,13 +1243,13 @@ int machine__resolve_callchain(struct machine *machine,
 			       struct perf_evsel *evsel,
 			       struct thread *thread,
 			       struct perf_sample *sample,
-			       struct symbol **parent)
-
+			       struct symbol **parent,
+			       struct addr_location *root_al)
 {
 	int ret;
 
 	ret = machine__resolve_callchain_sample(machine, thread,
-						sample->callchain, parent);
+						sample->callchain, parent, root_al);
 	if (ret)
 		return ret;