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>
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ee2ca3e..9a7e54d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -89,7 +89,7 @@
if ((sort__has_parent || symbol_conf.use_callchain) &&
sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent);
+ sample, &parent, al);
if (err)
return err;
}
@@ -180,7 +180,7 @@
if ((sort__has_parent || symbol_conf.use_callchain)
&& sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent);
+ sample, &parent, al);
if (err)
return err;
}
@@ -254,7 +254,7 @@
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent);
+ sample, &parent, al);
if (err)
return err;
}
@@ -681,6 +681,24 @@
return 0;
}
+int
+report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
+ const char *arg, int unset __maybe_unused)
+{
+ if (arg) {
+ int err = regcomp(&ignore_callees_regex, arg, REG_EXTENDED);
+ if (err) {
+ char buf[BUFSIZ];
+ regerror(err, &ignore_callees_regex, buf, sizeof(buf));
+ pr_err("Invalid --ignore-callees regex: %s\n%s", arg, buf);
+ return -1;
+ }
+ have_ignore_callees = 1;
+ }
+
+ return 0;
+}
+
static int
parse_branch_mode(const struct option *opt __maybe_unused,
const char *str __maybe_unused, int unset)
@@ -771,6 +789,9 @@
"Default: fractal,0.5,callee", &parse_callchain_opt, callchain_default_opt),
OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
"alias for inverted call graph"),
+ OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
+ "ignore callees of these functions in call graphs",
+ report_parse_ignore_callees_opt),
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
"only consider symbols in these dsos"),
OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",