perf report: Fix and improve the displaying of per-thread event counters
Improve and fix the handling of per-thread counter stats
recorded via perf record -s. Previously we only displayed
it in debug printouts (-D) and even that output was hard
to disambiguate.
I moved everything to utils/values.[ch] so that we may reuse
it in perf stat.
We get something like this now:
# PID TID cache-misses cache-references
4658 4659 495581 3238779
4658 4662 498246 3236823
4658 4663 499531 3243162
Then it'll be easy to add --pretty=raw to display a single line per thread/event.
By the way, -S was also used for --symbol... So I used -T/--thread here.
perf report: Add -T/--threads to display per-thread counter values
We get something like this now:
# PID TID cache-misses cache-references
4658 4659 495581 3238779
4658 4662 498246 3236823
4658 4663 499531 3243162
Per-thread arrays of counter values are managed in utils/values.[ch]
Signed-off-by: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 99274ce..4163918 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -17,6 +17,7 @@
#include "util/string.h"
#include "util/callchain.h"
#include "util/strlist.h"
+#include "util/values.h"
#include "perf.h"
#include "util/header.h"
@@ -53,6 +54,9 @@
static int full_paths;
static int show_nr_samples;
+static int show_threads;
+static struct perf_read_values show_threads_values;
+
static unsigned long page_size;
static unsigned long mmap_window = 32;
@@ -1473,6 +1477,9 @@
free(rem_sq_bracket);
+ if (show_threads)
+ perf_read_values_display(fp, &show_threads_values);
+
return ret;
}
@@ -1758,6 +1765,16 @@
{
struct perf_counter_attr *attr = perf_header__find_attr(event->read.id);
+ if (show_threads) {
+ char *name = attr ? __event_name(attr->type, attr->config)
+ : "unknown";
+ perf_read_values_add_value(&show_threads_values,
+ event->read.pid, event->read.tid,
+ event->read.id,
+ name,
+ event->read.value);
+ }
+
dprintf("%p [%p]: PERF_EVENT_READ: %d %d %s %Lu\n",
(void *)(offset + head),
(void *)(long)(event->header.size),
@@ -1839,6 +1856,9 @@
register_idle_thread();
+ if (show_threads)
+ perf_read_values_init(&show_threads_values);
+
input = open(input_name, O_RDONLY);
if (input < 0) {
fprintf(stderr, " failed to open file: %s", input_name);
@@ -1993,6 +2013,9 @@
output__resort(total);
output__fprintf(stdout, total);
+ if (show_threads)
+ perf_read_values_destroy(&show_threads_values);
+
return rc;
}
@@ -2066,6 +2089,8 @@
"load module symbols - WARNING: use only with -k and LIVE kernel"),
OPT_BOOLEAN('n', "show-nr-samples", &show_nr_samples,
"Show a column with the number of samples"),
+ OPT_BOOLEAN('T', "threads", &show_threads,
+ "Show per-thread event counters"),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent"),
OPT_BOOLEAN('P', "full-paths", &full_paths,
