perf report: Cache cumulative callchains
It is possble that a callchain has cycles or recursive calls. In that
case it'll end up having entries more than 100% overhead in the
output. In order to prevent such entries, cache each callchain node
and skip if same entry already cumulated.
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/1401335910-16832-8-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 37c28fc..bf03db5 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -700,7 +700,22 @@
iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
struct addr_location *al __maybe_unused)
{
+ struct hist_entry **he_cache;
+
callchain_cursor_commit(&callchain_cursor);
+
+ /*
+ * This is for detecting cycles or recursions so that they're
+ * cumulated only one time to prevent entries more than 100%
+ * overhead.
+ */
+ he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
+ if (he_cache == NULL)
+ return -ENOMEM;
+
+ iter->priv = he_cache;
+ iter->curr = 0;
+
return 0;
}
@@ -710,6 +725,7 @@
{
struct perf_evsel *evsel = iter->evsel;
struct perf_sample *sample = iter->sample;
+ struct hist_entry **he_cache = iter->priv;
struct hist_entry *he;
int err = 0;
@@ -720,6 +736,7 @@
return -ENOMEM;
iter->he = he;
+ he_cache[iter->curr++] = he;
/*
* The iter->he will be over-written after ->add_next_entry()
@@ -754,7 +771,29 @@
{
struct perf_evsel *evsel = iter->evsel;
struct perf_sample *sample = iter->sample;
+ struct hist_entry **he_cache = iter->priv;
struct hist_entry *he;
+ struct hist_entry he_tmp = {
+ .cpu = al->cpu,
+ .thread = al->thread,
+ .comm = thread__comm(al->thread),
+ .ip = al->addr,
+ .ms = {
+ .map = al->map,
+ .sym = al->sym,
+ },
+ .parent = iter->parent,
+ };
+ int i;
+
+ /*
+ * Check if there's duplicate entries in the callchain.
+ * It's possible that it has cycles or recursive calls.
+ */
+ for (i = 0; i < iter->curr; i++) {
+ if (hist_entry__cmp(he_cache[i], &he_tmp) == 0)
+ return 0;
+ }
he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
sample->period, sample->weight,
@@ -763,6 +802,7 @@
return -ENOMEM;
iter->he = he;
+ he_cache[iter->curr++] = he;
return 0;
}
@@ -771,7 +811,9 @@
iter_finish_cumulative_entry(struct hist_entry_iter *iter,
struct addr_location *al __maybe_unused)
{
+ zfree(&iter->priv);
iter->he = NULL;
+
return 0;
}