[PATCH 06/26] perf report: Cache cumulative callchains

From: Namhyung Kim
Date: Fri May 23 2014 - 06:10:53 EST


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.

Tested-by: Arun Sharma <asharma@xxxxxx>
Tested-by: Rodrigo Campos <rodrigo@xxxxxxxxxxx>
Acked-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
---
tools/perf/util/hist.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 44 insertions(+)

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 802af8495f83..b3faabf3d2c2 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -704,7 +704,22 @@ static int
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;
}

@@ -714,6 +729,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
{
struct perf_evsel *evsel = iter->evsel;
struct perf_sample *sample = iter->sample;
+ struct hist_entry **he_cache = iter->priv;
struct hist_entry *he;

he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
@@ -723,6 +739,8 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
return -ENOMEM;

iter->he = he;
+ he_cache[iter->curr++] = he;
+
return hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
}

@@ -747,7 +765,29 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
{
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,
@@ -755,6 +795,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
if (he == NULL)
return -ENOMEM;

+ he_cache[iter->curr++] = he;
+
return hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
}

@@ -765,6 +807,8 @@ iter_finish_cumulative_entry(struct hist_entry_iter *iter,
struct perf_evsel *evsel = iter->evsel;
struct hist_entry *he = iter->he;

+ zfree(&iter->priv);
+
if (he == NULL)
return 0;

--
1.9.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/