Re: [PATCH] perf stat: Support --all-kernel/--all-user

From: Jin, Yao
Date: Mon Oct 14 2019 - 21:57:39 EST




On 10/15/2019 12:23 AM, Arnaldo Carvalho de Melo wrote:
Em Mon, Oct 14, 2019 at 04:42:08PM +0200, Jiri Olsa escreveu:
On Fri, Oct 11, 2019 at 01:05:45PM +0800, Jin Yao wrote:
perf record has supported --all-kernel / --all-user to configure all
used events to run in kernel space or run in user space. But perf
stat doesn't support these options.

It would be useful to support these options in perf-stat too to keep
the same semantics.

Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>

Acked-by: Jiri Olsa <jolsa@xxxxxxxxxx>

What happens if one asks for both? From the patch only the --all-kernel
will stick, right? Is that the behaviour for 'perf record'? Lemme see,
as I recall having this discussion at that time...

Yeah, same thing, and looking at that I wonder why we dong use
perf_evsel__config() in 'perf stat'...

Ok, I'm going to apply it.


Hi Arnaldo,

If we specify both, we will see the error.

root@kbl:~# perf stat --all-kernel --all-user -a -- sleep 1
Error: option `all-user' cannot be used with all-kernel

root@kbl:~# perf record --all-kernel --all-user -a -- sleep 1
Error: option `all-user' cannot be used with all-kernel

For why I don't set them in perf_evsel__config, because perf_evsel__config is called in record but not called in stat.

Thanks for reviewing and applying this patch.

Thanks
Jin Yao

thanks,
jirka

---
tools/perf/Documentation/perf-stat.txt | 6 ++++++
tools/perf/builtin-stat.c | 6 ++++++
tools/perf/util/stat.c | 10 ++++++++++
tools/perf/util/stat.h | 2 ++
4 files changed, 24 insertions(+)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 930c51c01201..a9af4e440e80 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -323,6 +323,12 @@ The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf
Users who wants to get the actual value can apply --no-metric-only.
+--all-kernel::
+Configure all used events to run in kernel space.
+
+--all-user::
+Configure all used events to run in user space.
+
EXAMPLES
--------
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 468fc49420ce..c88d4e118409 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -803,6 +803,12 @@ static struct option stat_options[] = {
OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
"monitor specified metrics or metric groups (separated by ,)",
parse_metric_groups),
+ OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel,
+ "Configure all used events to run in kernel space.",
+ PARSE_OPT_EXCLUSIVE),
+ OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user,
+ "Configure all used events to run in user space.",
+ PARSE_OPT_EXCLUSIVE),
OPT_END()
};
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index ebdd130557fb..6822e4ffe224 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel,
if (config->identifier)
attr->sample_type = PERF_SAMPLE_IDENTIFIER;
+ if (config->all_user) {
+ attr->exclude_kernel = 1;
+ attr->exclude_user = 0;
+ }
+
+ if (config->all_kernel) {
+ attr->exclude_kernel = 0;
+ attr->exclude_user = 1;
+ }
+
/*
* Disabling all counters initially, they will be enabled
* either manually by us or by kernel via enable_on_exec
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index edbeb2f63e8d..081c4a5113c6 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -106,6 +106,8 @@ struct perf_stat_config {
bool big_num;
bool no_merge;
bool walltime_run_table;
+ bool all_kernel;
+ bool all_user;
FILE *output;
unsigned int interval;
unsigned int timeout;
--
2.17.1