| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20200508075817.10588-5-yao.jin@linux.intel.com>
Date: Fri, 8 May 2020 15:58:17 +0800
From: Jin Yao <yao.jin@...ux.intel.com>
To: acme@...nel.org, jolsa@...nel.org, peterz@...radead.org,
mingo@...hat.com, alexander.shishkin@...ux.intel.com
Cc: Linux-kernel@...r.kernel.org, ak@...ux.intel.com,
kan.liang@...el.com, yao.jin@...el.com,
Jin Yao <yao.jin@...ux.intel.com>
Subject: [PATCH v4 4/4] perf stat: Report summary for interval mode
Currently perf-stat supports to print counts at regular interval (-I),
but it's not very easy for user to get the overall statistics.
The patch uses 'evsel->prev_raw_counts' to get counts for summary.
Copy the counts to 'evsel->counts' after printing the interval results.
Next, we just follow the non-interval processing.
Let's see some examples,
root@...-ppc:~# perf stat -e cycles -I1000 --interval-count 2
# time counts unit events
1.000412064 2,281,114 cycles
2.001383658 2,547,880 cycles
Performance counter stats for 'system wide':
4,828,994 cycles
2.002860349 seconds time elapsed
root@...-ppc:~# perf stat -e cycles,instructions -I1000 --interval-count 2
# time counts unit events
1.000389902 1,536,093 cycles
1.000389902 420,226 instructions # 0.27 insn per cycle
2.001433453 2,213,952 cycles
2.001433453 735,465 instructions # 0.33 insn per cycle
Performance counter stats for 'system wide':
3,750,045 cycles
1,155,691 instructions # 0.31 insn per cycle
2.003023361 seconds time elapsed
root@...-ppc:~# perf stat -M CPI,IPC -I1000 --interval-count 2
# time counts unit events
1.000435121 905,303 inst_retired.any # 2.9 CPI
1.000435121 2,663,333 cycles
1.000435121 914,702 inst_retired.any # 0.3 IPC
1.000435121 2,676,559 cpu_clk_unhalted.thread
2.001615941 1,951,092 inst_retired.any # 1.8 CPI
2.001615941 3,551,357 cycles
2.001615941 1,950,837 inst_retired.any # 0.5 IPC
2.001615941 3,551,044 cpu_clk_unhalted.thread
Performance counter stats for 'system wide':
2,856,395 inst_retired.any # 2.2 CPI
6,214,690 cycles
2,865,539 inst_retired.any # 0.5 IPC
6,227,603 cpu_clk_unhalted.thread
2.003403078 seconds time elapsed
v4:
---
Move affinity setup and read_counter_cpu to a new function
read_affinity_counters. It's only called when stat_config.summary
is not set.
v3:
---
Use evsel->prev_raw_counts for summary counts
v2:
---
Rebase to perf/core branch
Signed-off-by: Jin Yao <yao.jin@...ux.intel.com>
---
tools/perf/builtin-stat.c | 27 ++++++++++++++++++++++++---
tools/perf/util/stat.c | 2 +-
tools/perf/util/stat.h | 1 +
3 files changed, 26 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f3b3a59ac7d2..d6a6aa6b997d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -314,14 +314,14 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
return 0;
}
-static void read_counters(struct timespec *rs)
+static int read_affinity_counters(struct timespec *rs)
{
struct evsel *counter;
struct affinity affinity;
int i, ncpus, cpu;
if (affinity__setup(&affinity) < 0)
- return;
+ return -1;
ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus);
if (!target__has_cpu(&target) || target__has_per_thread(&target))
@@ -341,6 +341,15 @@ static void read_counters(struct timespec *rs)
}
}
affinity__cleanup(&affinity);
+ return 0;
+}
+
+static void read_counters(struct timespec *rs)
+{
+ struct evsel *counter;
+
+ if (!stat_config.summary && (read_affinity_counters(rs) < 0))
+ return;
evlist__for_each_entry(evsel_list, counter) {
if (counter->err)
@@ -394,6 +403,7 @@ static void runtime_stat_reset(struct perf_stat_config *config)
static void process_interval(void)
{
struct timespec ts, rs;
+ struct stats walltime_nsecs_stats_bak;
clock_gettime(CLOCK_MONOTONIC, &ts);
diff_timespec(&rs, &ts, &ref_time);
@@ -407,9 +417,11 @@ static void process_interval(void)
pr_err("failed to write stat round event\n");
}
+ walltime_nsecs_stats_bak = walltime_nsecs_stats;
init_stats(&walltime_nsecs_stats);
update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000);
print_counters(&rs, 0, NULL);
+ walltime_nsecs_stats = walltime_nsecs_stats_bak;
}
static void enable_counters(void)
@@ -765,6 +777,15 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
update_stats(&walltime_nsecs_stats, t1 - t0);
+ if (interval) {
+ stat_config.interval = 0;
+ stat_config.summary = true;
+ perf_evlist__copy_prev_raw_counts(evsel_list);
+ perf_evlist__reset_prev_raw_counts(evsel_list);
+ runtime_stat_reset(&stat_config);
+ perf_stat__reset_shadow_per_stat(&rt_stat);
+ }
+
/*
* Closing a group leader splits the group, and as we only disable
* group leaders, results in remaining events becoming enabled. To
@@ -2159,7 +2180,7 @@ int cmd_stat(int argc, const char **argv)
}
}
- if (!forever && status != -1 && !interval)
+ if (!forever && status != -1 && (!interval || stat_config.summary))
print_counters(NULL, argc, argv);
if (STAT_RECORD) {
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index aadc723ce871..49e832a9c109 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -388,7 +388,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
* interval mode, otherwise overall avg running
* averages will be shown for each interval.
*/
- if (config->interval) {
+ if (config->interval || config->summary) {
for (i = 0; i < 3; i++)
init_stats(&ps->res_stats[i]);
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 62cf72c71869..c60e9e5d6474 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -110,6 +110,7 @@ struct perf_stat_config {
bool all_kernel;
bool all_user;
bool percore_show_thread;
+ bool summary;
FILE *output;
unsigned int interval;
unsigned int timeout;
--
2.17.1
Powered by blists - more mailing lists