* [PATCH 01/12] perf test: Add -w/--workload option
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-09 18:39 ` Arnaldo Carvalho de Melo
2022-11-09 17:46 ` [PATCH 02/12] perf test: Replace pipe test workload with noploop Namhyung Kim
` (10 subsequent siblings)
11 siblings, 1 reply; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
The -w/--workload option is to run a simple workload used by testing.
This adds a basic framework to run the workloads and 'noploop' workload
as an example.
$ perf test -w noploop
The noploop does a loop doing nothing (NOP) for a second by default.
It can have an optional argument to specify the time in seconds.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/Build | 2 ++
tools/perf/tests/builtin-test.c | 24 +++++++++++++++++++++
tools/perf/tests/tests.h | 22 +++++++++++++++++++
tools/perf/tests/workloads/Build | 3 +++
tools/perf/tests/workloads/noploop.c | 32 ++++++++++++++++++++++++++++
5 files changed, 83 insertions(+)
create mode 100644 tools/perf/tests/workloads/Build
create mode 100644 tools/perf/tests/workloads/noploop.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 2064a640facb..11b69023011b 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -103,3 +103,5 @@ endif
CFLAGS_attr.o += -DBINDIR="BUILD_STR($(bindir_SQ))" -DPYTHON="BUILD_STR($(PYTHON_WORD))"
CFLAGS_python-use.o += -DPYTHONPATH="BUILD_STR($(OUTPUT)python)" -DPYTHON="BUILD_STR($(PYTHON_WORD))"
CFLAGS_dwarf-unwind.o += -fno-optimize-sibling-calls
+
+perf-y += workloads/
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 7122eae1d98d..ce641ccfcf81 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -118,6 +118,10 @@ static struct test_suite **tests[] = {
arch_tests,
};
+static struct test_workload *workloads[] = {
+ &workload__noploop,
+};
+
static int num_subtests(const struct test_suite *t)
{
int num;
@@ -475,6 +479,21 @@ static int perf_test__list(int argc, const char **argv)
return 0;
}
+static int run_workload(const char *work, int argc, const char **argv)
+{
+ unsigned int i = 0;
+ struct test_workload *twl;
+
+ for (i = 0; i < ARRAY_SIZE(workloads); i++) {
+ twl = workloads[i];
+ if (!strcmp(twl->name, work))
+ return twl->func(argc, argv);
+ }
+
+ pr_info("No workload found: %s\n", work);
+ return -1;
+}
+
int cmd_test(int argc, const char **argv)
{
const char *test_usage[] = {
@@ -482,12 +501,14 @@ int cmd_test(int argc, const char **argv)
NULL,
};
const char *skip = NULL;
+ const char *workload = NULL;
const struct option test_options[] = {
OPT_STRING('s', "skip", &skip, "tests", "tests to skip"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('F', "dont-fork", &dont_fork,
"Do not fork for testcase"),
+ OPT_STRING('w', "workload", &workload, "work", "workload to run for testing"),
OPT_END()
};
const char * const test_subcommands[] = { "list", NULL };
@@ -504,6 +525,9 @@ int cmd_test(int argc, const char **argv)
if (argc >= 1 && !strcmp(argv[0], "list"))
return perf_test__list(argc - 1, argv + 1);
+ if (workload)
+ return run_workload(workload, argc, argv);
+
symbol_conf.priv_size = sizeof(int);
symbol_conf.sort_by_name = true;
symbol_conf.try_vmlinux_path = true;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 5bbb8f6a48fc..d315d0d6fc97 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -180,4 +180,26 @@ int test__arch_unwind_sample(struct perf_sample *sample,
DECLARE_SUITE(vectors_page);
#endif
+/*
+ * Define test workloads to be used in test suites.
+ */
+typedef int (*workload_fnptr)(int argc, const char **argv);
+
+struct test_workload {
+ const char *name;
+ workload_fnptr func;
+};
+
+#define DECLARE_WORKLOAD(work) \
+ extern struct test_workload workload__##work
+
+#define DEFINE_WORKLOAD(work) \
+struct test_workload workload__##work = { \
+ .name = #work, \
+ .func = work, \
+}
+
+/* The list of test workloads */
+DECLARE_WORKLOAD(noploop);
+
#endif /* TESTS_H */
diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build
new file mode 100644
index 000000000000..f98e968d4633
--- /dev/null
+++ b/tools/perf/tests/workloads/Build
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+perf-y += noploop.o
diff --git a/tools/perf/tests/workloads/noploop.c b/tools/perf/tests/workloads/noploop.c
new file mode 100644
index 000000000000..9e4d8d024259
--- /dev/null
+++ b/tools/perf/tests/workloads/noploop.c
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+static volatile int done;
+
+static void sighandler(int sig __maybe_unused)
+{
+ done = 1;
+}
+
+static int noploop(int argc, const char **argv)
+{
+ int sec = 1;
+
+ if (argc > 0)
+ sec = atoi(argv[0]);
+
+ signal(SIGINT, sighandler);
+ signal(SIGALRM, sighandler);
+ alarm(sec);
+
+ while (!done)
+ continue;
+
+ return 0;
+}
+
+DEFINE_WORKLOAD(noploop);
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH 01/12] perf test: Add -w/--workload option
2022-11-09 17:46 ` [PATCH 01/12] perf test: Add -w/--workload option Namhyung Kim
@ 2022-11-09 18:39 ` Arnaldo Carvalho de Melo
2022-11-09 19:00 ` Namhyung Kim
0 siblings, 1 reply; 23+ messages in thread
From: Arnaldo Carvalho de Melo @ 2022-11-09 18:39 UTC (permalink / raw)
To: Namhyung Kim
Cc: Jiri Olsa, Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers,
Adrian Hunter, linux-perf-users, Leo Yan, German Gomez,
Zhengjun Xing, James Clark
Em Wed, Nov 09, 2022 at 09:46:24AM -0800, Namhyung Kim escreveu:
> --- /dev/null
> +++ b/tools/perf/tests/workloads/noploop.c
> @@ -0,0 +1,32 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#include <stdlib.h>
> +#include <signal.h>
> +#include <unistd.h>
> +#include <linux/compiler.h>
> +#include "../tests.h"
> +
> +static volatile int done;
> +
> +static void sighandler(int sig __maybe_unused)
> +{
> + done = 1;
> +}
You forgot to do what was done in:
92ea0720ba9cf7f0 perf trace: Use sig_atomic_t to avoid undefined behaviour in a signal handler
691768968f2a13eb perf top: Use sig_atomic_t to avoid undefined behaviour in a signal handler
01513fdc18f395db perf stat: Use sig_atomic_t to avoid undefined behaviour in a signal handler
057929f9d083e80c perf session: Change type to avoid undefined behaviour in a signal handler
853596fb71f7c2f7 perf ftrace: Use sig_atomic_t to avoid UB
7f3374299f9762ba perf daemon: Use sig_atomic_t to avoid UB
8ed28c2b56b78442 perf record: Use sig_atomic_t for signal handlers
f3c9bd4e16a503cb perf build: Update to C standard to gnu11
To speed up the process here is one of those csets:
⬢[acme@toolbox perf]$ git show 01513fdc18f395db
commit 01513fdc18f395dbcc924bc5e9962b12f86f947a
Author: Ian Rogers <irogers@google.com>
Date: Mon Oct 24 11:19:11 2022 -0700
perf stat: Use sig_atomic_t to avoid undefined behaviour in a signal handler
Use sig_atomic_t for variables written/accessed in signal
handlers. This is undefined behavior as per:
https://wiki.sei.cmu.edu/confluence/display/c/SIG31-C.+Do+not+access+shared+objects+in+signal+handlers
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20221024181913.630986-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e52601a54b26d669..d5e1670bca204450 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -173,7 +173,7 @@ static struct target target = {
#define METRIC_ONLY_LEN 20
-static volatile pid_t child_pid = -1;
+static volatile sig_atomic_t child_pid = -1;
static int detailed_run = 0;
static bool transaction_run;
static bool topdown_run = false;
@@ -208,7 +208,7 @@ struct perf_stat {
static struct perf_stat perf_stat;
#define STAT_RECORD perf_stat.record
-static volatile int done = 0;
+static volatile sig_atomic_t done = 0;
static struct perf_stat_config stat_config = {
.aggr_mode = AGGR_GLOBAL,
@@ -580,7 +580,7 @@ static void disable_counters(void)
}
}
-static volatile int workload_exec_errno;
+static volatile sig_atomic_t workload_exec_errno;
/*
* evlist__prepare_workload will send a SIGUSR1
@@ -1039,7 +1039,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
evlist__print_counters(evsel_list, &stat_config, &target, ts, argc, argv);
}
-static volatile int signr = -1;
+static volatile sig_atomic_t signr = -1;
static void skip_signal(int signo)
{
⬢[acme@toolbox perf]$
> +
> +static int noploop(int argc, const char **argv)
> +{
> + int sec = 1;
> +
> + if (argc > 0)
> + sec = atoi(argv[0]);
> +
> + signal(SIGINT, sighandler);
> + signal(SIGALRM, sighandler);
> + alarm(sec);
> +
> + while (!done)
> + continue;
> +
> + return 0;
> +}
> +
> +DEFINE_WORKLOAD(noploop);
> --
> 2.38.1.431.g37b22c650d-goog
--
- Arnaldo
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH 01/12] perf test: Add -w/--workload option
2022-11-09 18:39 ` Arnaldo Carvalho de Melo
@ 2022-11-09 19:00 ` Namhyung Kim
0 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 19:00 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Jiri Olsa, Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers,
Adrian Hunter, linux-perf-users, Leo Yan, German Gomez,
Zhengjun Xing, James Clark
Hi Arnaldo,
On Wed, Nov 9, 2022 at 10:39 AM Arnaldo Carvalho de Melo
<acme@kernel.org> wrote:
>
> Em Wed, Nov 09, 2022 at 09:46:24AM -0800, Namhyung Kim escreveu:
> > --- /dev/null
> > +++ b/tools/perf/tests/workloads/noploop.c
> > @@ -0,0 +1,32 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +#include <stdlib.h>
> > +#include <signal.h>
> > +#include <unistd.h>
> > +#include <linux/compiler.h>
> > +#include "../tests.h"
> > +
> > +static volatile int done;
> > +
> > +static void sighandler(int sig __maybe_unused)
> > +{
> > + done = 1;
> > +}
>
> You forgot to do what was done in:
Oops, right. Will fix in v2.
Thanks,
Namhyung
>
> 92ea0720ba9cf7f0 perf trace: Use sig_atomic_t to avoid undefined behaviour in a signal handler
> 691768968f2a13eb perf top: Use sig_atomic_t to avoid undefined behaviour in a signal handler
> 01513fdc18f395db perf stat: Use sig_atomic_t to avoid undefined behaviour in a signal handler
> 057929f9d083e80c perf session: Change type to avoid undefined behaviour in a signal handler
> 853596fb71f7c2f7 perf ftrace: Use sig_atomic_t to avoid UB
> 7f3374299f9762ba perf daemon: Use sig_atomic_t to avoid UB
> 8ed28c2b56b78442 perf record: Use sig_atomic_t for signal handlers
> f3c9bd4e16a503cb perf build: Update to C standard to gnu11
>
> To speed up the process here is one of those csets:
>
> ⬢[acme@toolbox perf]$ git show 01513fdc18f395db
> commit 01513fdc18f395dbcc924bc5e9962b12f86f947a
> Author: Ian Rogers <irogers@google.com>
> Date: Mon Oct 24 11:19:11 2022 -0700
>
> perf stat: Use sig_atomic_t to avoid undefined behaviour in a signal handler
>
> Use sig_atomic_t for variables written/accessed in signal
> handlers. This is undefined behavior as per:
>
> https://wiki.sei.cmu.edu/confluence/display/c/SIG31-C.+Do+not+access+shared+objects+in+signal+handlers
>
> Signed-off-by: Ian Rogers <irogers@google.com>
> Cc: Adrian Hunter <adrian.hunter@intel.com>
> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
> Cc: German Gomez <german.gomez@arm.com>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Jiri Olsa <jolsa@kernel.org>
> Cc: Leo Yan <leo.yan@linaro.org>
> Cc: Mark Rutland <mark.rutland@arm.com>
> Cc: Namhyung Kim <namhyung@kernel.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Stephane Eranian <eranian@google.com>
> Link: https://lore.kernel.org/r/20221024181913.630986-7-irogers@google.com
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
>
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index e52601a54b26d669..d5e1670bca204450 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -173,7 +173,7 @@ static struct target target = {
>
> #define METRIC_ONLY_LEN 20
>
> -static volatile pid_t child_pid = -1;
> +static volatile sig_atomic_t child_pid = -1;
> static int detailed_run = 0;
> static bool transaction_run;
> static bool topdown_run = false;
> @@ -208,7 +208,7 @@ struct perf_stat {
> static struct perf_stat perf_stat;
> #define STAT_RECORD perf_stat.record
>
> -static volatile int done = 0;
> +static volatile sig_atomic_t done = 0;
>
> static struct perf_stat_config stat_config = {
> .aggr_mode = AGGR_GLOBAL,
> @@ -580,7 +580,7 @@ static void disable_counters(void)
> }
> }
>
> -static volatile int workload_exec_errno;
> +static volatile sig_atomic_t workload_exec_errno;
>
> /*
> * evlist__prepare_workload will send a SIGUSR1
> @@ -1039,7 +1039,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
> evlist__print_counters(evsel_list, &stat_config, &target, ts, argc, argv);
> }
>
> -static volatile int signr = -1;
> +static volatile sig_atomic_t signr = -1;
>
> static void skip_signal(int signo)
> {
> ⬢[acme@toolbox perf]$
>
> > +
> > +static int noploop(int argc, const char **argv)
> > +{
> > + int sec = 1;
> > +
> > + if (argc > 0)
> > + sec = atoi(argv[0]);
> > +
> > + signal(SIGINT, sighandler);
> > + signal(SIGALRM, sighandler);
> > + alarm(sec);
> > +
> > + while (!done)
> > + continue;
> > +
> > + return 0;
> > +}
> > +
> > +DEFINE_WORKLOAD(noploop);
> > --
> > 2.38.1.431.g37b22c650d-goog
>
> --
>
> - Arnaldo
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH 02/12] perf test: Replace pipe test workload with noploop
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
2022-11-09 17:46 ` [PATCH 01/12] perf test: Add -w/--workload option Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-09 17:46 ` [PATCH 03/12] perf test: Add 'thloop' test workload Namhyung Kim
` (9 subsequent siblings)
11 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
So that it can get rid of requirement of a compiler.
Also define and use more local symbols to ease future changes.
$ sudo ./perf test -v pipe
87: perf pipe recording and injection test :
--- start ---
test child forked, pid 748003
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
748014 748014 -1 |perf
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
99.83% perf perf [.] noploop
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
99.85% perf perf [.] noploop
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.160 MB /tmp/perf.data.2XYPdw (4007 samples) ]
99.83% perf perf [.] noploop
test child finished with 0
---- end ----
perf pipe recording and injection test: Ok
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/shell/pipe_test.sh | 55 ++++++-----------------------
1 file changed, 10 insertions(+), 45 deletions(-)
diff --git a/tools/perf/tests/shell/pipe_test.sh b/tools/perf/tests/shell/pipe_test.sh
index 1b32b4f28391..8dd115dd35a7 100755
--- a/tools/perf/tests/shell/pipe_test.sh
+++ b/tools/perf/tests/shell/pipe_test.sh
@@ -2,68 +2,33 @@
# perf pipe recording and injection test
# SPDX-License-Identifier: GPL-2.0
-# skip if there's no compiler
-if ! [ -x "$(command -v cc)" ]; then
- echo "failed: no compiler, install gcc"
- exit 2
-fi
-
-file=$(mktemp /tmp/test.file.XXXXXX)
data=$(mktemp /tmp/perf.data.XXXXXX)
+prog="perf test -w noploop"
+task="perf"
+sym="noploop"
-cat <<EOF | cc -o ${file} -x c -
-#include <signal.h>
-#include <stdlib.h>
-#include <unistd.h>
-
-volatile int done;
-
-void sigalrm(int sig) {
- done = 1;
-}
-
-__attribute__((noinline)) void noploop(void) {
- while (!done)
- continue;
-}
-
-int main(int argc, char *argv[]) {
- int sec = 1;
-
- if (argc > 1)
- sec = atoi(argv[1]);
-
- signal(SIGALRM, sigalrm);
- alarm(sec);
-
- noploop();
- return 0;
-}
-EOF
-
-
-if ! perf record -e task-clock:u -o - ${file} | perf report -i - --task | grep test.file; then
+if ! perf record -e task-clock:u -o - ${prog} | perf report -i - --task | grep ${task}; then
echo "cannot find the test file in the perf report"
exit 1
fi
-if ! perf record -e task-clock:u -o - ${file} | perf inject -b | perf report -i - | grep noploop; then
+if ! perf record -e task-clock:u -o - ${prog} | perf inject -b | perf report -i - | grep ${sym}; then
echo "cannot find noploop function in pipe #1"
exit 1
fi
-perf record -e task-clock:u -o - ${file} | perf inject -b -o ${data}
-if ! perf report -i ${data} | grep noploop; then
+perf record -e task-clock:u -o - ${prog} | perf inject -b -o ${data}
+if ! perf report -i ${data} | grep ${sym}; then
echo "cannot find noploop function in pipe #2"
exit 1
fi
-perf record -e task-clock:u -o ${data} ${file}
-if ! perf inject -b -i ${data} | perf report -i - | grep noploop; then
+perf record -e task-clock:u -o ${data} ${prog}
+if ! perf inject -b -i ${data} | perf report -i - | grep ${sym}; then
echo "cannot find noploop function in pipe #3"
exit 1
fi
-rm -f ${file} ${data} ${data}.old
+rm -f ${data} ${data}.old
exit 0
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH 03/12] perf test: Add 'thloop' test workload
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
2022-11-09 17:46 ` [PATCH 01/12] perf test: Add -w/--workload option Namhyung Kim
2022-11-09 17:46 ` [PATCH 02/12] perf test: Replace pipe test workload with noploop Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-09 18:39 ` Arnaldo Carvalho de Melo
2022-11-09 17:46 ` [PATCH 04/12] perf test: Replace record test workload with thloop Namhyung Kim
` (8 subsequent siblings)
11 siblings, 1 reply; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
The thloop is similar to noploop but runs in two threads. This is
needed to verify perf record --per-thread to handle multi-threaded
programs properly.
$ perf test -w thloop
It also takes an optional argument to specify runtime in seconds
(default: 1).
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/builtin-test.c | 1 +
tools/perf/tests/tests.h | 1 +
tools/perf/tests/workloads/Build | 1 +
tools/perf/tests/workloads/thloop.c | 53 +++++++++++++++++++++++++++++
4 files changed, 56 insertions(+)
create mode 100644 tools/perf/tests/workloads/thloop.c
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index ce641ccfcf81..161f38476e77 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -120,6 +120,7 @@ static struct test_suite **tests[] = {
static struct test_workload *workloads[] = {
&workload__noploop,
+ &workload__thloop,
};
static int num_subtests(const struct test_suite *t)
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index d315d0d6fc97..e6edfeeadaeb 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -201,5 +201,6 @@ struct test_workload workload__##work = { \
/* The list of test workloads */
DECLARE_WORKLOAD(noploop);
+DECLARE_WORKLOAD(thloop);
#endif /* TESTS_H */
diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build
index f98e968d4633..b8964b1099c0 100644
--- a/tools/perf/tests/workloads/Build
+++ b/tools/perf/tests/workloads/Build
@@ -1,3 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
perf-y += noploop.o
+perf-y += thloop.o
diff --git a/tools/perf/tests/workloads/thloop.c b/tools/perf/tests/workloads/thloop.c
new file mode 100644
index 000000000000..7fd3ac79e732
--- /dev/null
+++ b/tools/perf/tests/workloads/thloop.c
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <pthread.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+static volatile int done;
+static volatile unsigned count;
+
+/* We want to check this symbol in perf report */
+noinline void test_loop(void);
+
+static void sighandler(int sig __maybe_unused)
+{
+ done = 1;
+}
+
+noinline void test_loop(void)
+{
+ while (!done)
+ count++;
+}
+
+static void *thfunc(void *arg)
+{
+ void (*loop_fn)(void) = arg;
+
+ loop_fn();
+ return NULL;
+}
+
+static int thloop(int argc, const char **argv)
+{
+ int sec = 1;
+ pthread_t th;
+
+ if (argc > 0)
+ sec = atoi(argv[0]);
+
+ signal(SIGINT, sighandler);
+ signal(SIGALRM, sighandler);
+ alarm(sec);
+
+ pthread_create(&th, NULL, thfunc, test_loop);
+ test_loop();
+ pthread_join(th, NULL);
+
+ return 0;
+}
+
+DEFINE_WORKLOAD(thloop);
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH 03/12] perf test: Add 'thloop' test workload
2022-11-09 17:46 ` [PATCH 03/12] perf test: Add 'thloop' test workload Namhyung Kim
@ 2022-11-09 18:39 ` Arnaldo Carvalho de Melo
0 siblings, 0 replies; 23+ messages in thread
From: Arnaldo Carvalho de Melo @ 2022-11-09 18:39 UTC (permalink / raw)
To: Namhyung Kim
Cc: Jiri Olsa, Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers,
Adrian Hunter, linux-perf-users, Leo Yan, German Gomez,
Zhengjun Xing, James Clark
Em Wed, Nov 09, 2022 at 09:46:26AM -0800, Namhyung Kim escreveu:
> The thloop is similar to noploop but runs in two threads. This is
> needed to verify perf record --per-thread to handle multi-threaded
> programs properly.
>
> $ perf test -w thloop
>
> It also takes an optional argument to specify runtime in seconds
> (default: 1).
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> tools/perf/tests/builtin-test.c | 1 +
> tools/perf/tests/tests.h | 1 +
> tools/perf/tests/workloads/Build | 1 +
> tools/perf/tests/workloads/thloop.c | 53 +++++++++++++++++++++++++++++
> 4 files changed, 56 insertions(+)
> create mode 100644 tools/perf/tests/workloads/thloop.c
>
> diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
> index ce641ccfcf81..161f38476e77 100644
> --- a/tools/perf/tests/builtin-test.c
> +++ b/tools/perf/tests/builtin-test.c
> @@ -120,6 +120,7 @@ static struct test_suite **tests[] = {
>
> static struct test_workload *workloads[] = {
> &workload__noploop,
> + &workload__thloop,
> };
>
> static int num_subtests(const struct test_suite *t)
> diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
> index d315d0d6fc97..e6edfeeadaeb 100644
> --- a/tools/perf/tests/tests.h
> +++ b/tools/perf/tests/tests.h
> @@ -201,5 +201,6 @@ struct test_workload workload__##work = { \
>
> /* The list of test workloads */
> DECLARE_WORKLOAD(noploop);
> +DECLARE_WORKLOAD(thloop);
>
> #endif /* TESTS_H */
> diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build
> index f98e968d4633..b8964b1099c0 100644
> --- a/tools/perf/tests/workloads/Build
> +++ b/tools/perf/tests/workloads/Build
> @@ -1,3 +1,4 @@
> # SPDX-License-Identifier: GPL-2.0
>
> perf-y += noploop.o
> +perf-y += thloop.o
> diff --git a/tools/perf/tests/workloads/thloop.c b/tools/perf/tests/workloads/thloop.c
> new file mode 100644
> index 000000000000..7fd3ac79e732
> --- /dev/null
> +++ b/tools/perf/tests/workloads/thloop.c
> @@ -0,0 +1,53 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#include <pthread.h>
> +#include <stdlib.h>
> +#include <signal.h>
> +#include <unistd.h>
> +#include <linux/compiler.h>
> +#include "../tests.h"
> +
> +static volatile int done;
> +static volatile unsigned count;
sig_atomic_t
> +/* We want to check this symbol in perf report */
> +noinline void test_loop(void);
> +
> +static void sighandler(int sig __maybe_unused)
> +{
> + done = 1;
> +}
> +
> +noinline void test_loop(void)
> +{
> + while (!done)
> + count++;
> +}
> +
> +static void *thfunc(void *arg)
> +{
> + void (*loop_fn)(void) = arg;
> +
> + loop_fn();
> + return NULL;
> +}
> +
> +static int thloop(int argc, const char **argv)
> +{
> + int sec = 1;
> + pthread_t th;
> +
> + if (argc > 0)
> + sec = atoi(argv[0]);
> +
> + signal(SIGINT, sighandler);
> + signal(SIGALRM, sighandler);
> + alarm(sec);
> +
> + pthread_create(&th, NULL, thfunc, test_loop);
> + test_loop();
> + pthread_join(th, NULL);
> +
> + return 0;
> +}
> +
> +DEFINE_WORKLOAD(thloop);
> --
> 2.38.1.431.g37b22c650d-goog
--
- Arnaldo
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH 04/12] perf test: Replace record test workload with thloop
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
` (2 preceding siblings ...)
2022-11-09 17:46 ` [PATCH 03/12] perf test: Add 'thloop' test workload Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-09 17:46 ` [PATCH 05/12] perf test: Add 'leafloop' test workload Namhyung Kim
` (7 subsequent siblings)
11 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
So that it can get rid of requirements for a compiler.
$ sudo ./perf test -v 92
92: perf record tests :
--- start ---
test child forked, pid 740204
Basic --per-thread mode test
Basic --per-thread mode test [Success]
Register capture test
Register capture test [Success]
Basic --system-wide mode test
Basic --system-wide mode test [Success]
Basic target workload test
Basic target workload test [Success]
test child finished with 0
---- end ----
perf record tests: Ok
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/shell/record.sh | 59 ++------------------------------
1 file changed, 3 insertions(+), 56 deletions(-)
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index e93b3a8871fe..4dff89e3a3fd 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -9,17 +9,13 @@ shelldir=$(dirname "$0")
err=0
perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
-testprog=$(mktemp /tmp/__perf_test.prog.XXXXXX)
+testprog="perf test -w thloop"
testsym="test_loop"
cleanup() {
rm -rf "${perfdata}"
rm -rf "${perfdata}".old
- if [ "${testprog}" != "true" ]; then
- rm -f "${testprog}"
- fi
-
trap - EXIT TERM INT
}
@@ -29,53 +25,6 @@ trap_cleanup() {
}
trap trap_cleanup EXIT TERM INT
-build_test_program() {
- if ! [ -x "$(command -v cc)" ]; then
- # No CC found. Fall back to 'true'
- testprog=true
- testsym=true
- return
- fi
-
- echo "Build a test program"
- cat <<EOF | cc -o ${testprog} -xc - -pthread
-#include <stdio.h>
-#include <stdlib.h>
-#include <pthread.h>
-
-void test_loop(void) {
- volatile int count = 1000000;
-
- while (count--)
- continue;
-}
-
-void *thfunc(void *arg) {
- int forever = *(int *)arg;
-
- do {
- test_loop();
- } while (forever);
-
- return NULL;
-}
-
-int main(int argc, char *argv[]) {
- pthread_t th;
- int forever = 0;
-
- if (argc > 1)
- forever = atoi(argv[1]);
-
- pthread_create(&th, NULL, thfunc, &forever);
- test_loop();
- pthread_join(th, NULL);
-
- return 0;
-}
-EOF
-}
-
test_per_thread() {
echo "Basic --per-thread mode test"
if ! perf record -o /dev/null --quiet ${testprog} 2> /dev/null
@@ -96,8 +45,8 @@ test_per_thread() {
return
fi
- # run the test program in background (forever)
- ${testprog} 1 &
+ # run the test program in background (for 30 seconds)
+ ${testprog} 30 &
TESTPID=$!
rm -f "${perfdata}"
@@ -205,8 +154,6 @@ test_workload() {
echo "Basic target workload test [Success]"
}
-build_test_program
-
test_per_thread
test_register_capture
test_system_wide
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH 05/12] perf test: Add 'leafloop' test workload
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
` (3 preceding siblings ...)
2022-11-09 17:46 ` [PATCH 04/12] perf test: Replace record test workload with thloop Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-09 17:46 ` [PATCH 06/12] perf test: Replace arm callgraph fp test workload with leafloop Namhyung Kim
` (6 subsequent siblings)
11 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
The leafloop workload is to run an infinite loop in the test_leaf
function. This is needed for the ARM fp callgraph test to verify if it
gets the correct callchains.
$ perf test -w leafloop
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/builtin-test.c | 1 +
tools/perf/tests/tests.h | 1 +
tools/perf/tests/workloads/Build | 3 +++
tools/perf/tests/workloads/leafloop.c | 34 +++++++++++++++++++++++++++
4 files changed, 39 insertions(+)
create mode 100644 tools/perf/tests/workloads/leafloop.c
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 161f38476e77..0ed5ac452f6e 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -121,6 +121,7 @@ static struct test_suite **tests[] = {
static struct test_workload *workloads[] = {
&workload__noploop,
&workload__thloop,
+ &workload__leafloop,
};
static int num_subtests(const struct test_suite *t)
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index e6edfeeadaeb..86804dd6452b 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -202,5 +202,6 @@ struct test_workload workload__##work = { \
/* The list of test workloads */
DECLARE_WORKLOAD(noploop);
DECLARE_WORKLOAD(thloop);
+DECLARE_WORKLOAD(leafloop);
#endif /* TESTS_H */
diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build
index b8964b1099c0..631596bdb2b3 100644
--- a/tools/perf/tests/workloads/Build
+++ b/tools/perf/tests/workloads/Build
@@ -2,3 +2,6 @@
perf-y += noploop.o
perf-y += thloop.o
+perf-y += leafloop.o
+
+CFLAGS_leafloop.o = -g -O0 -fno-inline -fno-omit-frame-pointer
diff --git a/tools/perf/tests/workloads/leafloop.c b/tools/perf/tests/workloads/leafloop.c
new file mode 100644
index 000000000000..1bf5cc97649b
--- /dev/null
+++ b/tools/perf/tests/workloads/leafloop.c
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+/* We want to check these symbols in perf script */
+noinline void leaf(volatile int b);
+noinline void parent(volatile int b);
+
+static volatile int a;
+
+noinline void leaf(volatile int b)
+{
+ for (;;)
+ a += b;
+}
+
+noinline void parent(volatile int b)
+{
+ leaf(b);
+}
+
+static int leafloop(int argc, const char **argv)
+{
+ int c = 1;
+
+ if (argc > 0)
+ c = atoi(argv[0]);
+
+ parent(c);
+ return 0;
+}
+
+DEFINE_WORKLOAD(leafloop);
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH 06/12] perf test: Replace arm callgraph fp test workload with leafloop
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
` (4 preceding siblings ...)
2022-11-09 17:46 ` [PATCH 05/12] perf test: Add 'leafloop' test workload Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-10 11:20 ` Leo Yan
2022-11-09 17:46 ` [PATCH 07/12] perf test: Add 'sqrtloop' test workload Namhyung Kim
` (5 subsequent siblings)
11 siblings, 1 reply; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
So that it can get rid of requirement of a compiler.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
.../perf/tests/shell/test_arm_callgraph_fp.sh | 30 +------------------
1 file changed, 1 insertion(+), 29 deletions(-)
diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
index ec108d45d3c6..9d6d1b2d99c5 100755
--- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
@@ -4,44 +4,16 @@
lscpu | grep -q "aarch64" || exit 2
-if ! [ -x "$(command -v cc)" ]; then
- echo "failed: no compiler, install gcc"
- exit 2
-fi
-
PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
-TEST_PROGRAM_SOURCE=$(mktemp /tmp/test_program.XXXXX.c)
-TEST_PROGRAM=$(mktemp /tmp/test_program.XXXXX)
+TEST_PROGRAM="perf test -w leafloop"
cleanup_files()
{
rm -f $PERF_DATA
- rm -f $TEST_PROGRAM_SOURCE
- rm -f $TEST_PROGRAM
}
trap cleanup_files exit term int
-cat << EOF > $TEST_PROGRAM_SOURCE
-int a = 0;
-void leaf(void) {
- for (;;)
- a += a;
-}
-void parent(void) {
- leaf();
-}
-int main(void) {
- parent();
- return 0;
-}
-EOF
-
-echo " + Compiling test program ($TEST_PROGRAM)..."
-
-CFLAGS="-g -O0 -fno-inline -fno-omit-frame-pointer"
-cc $CFLAGS $TEST_PROGRAM_SOURCE -o $TEST_PROGRAM || exit 1
-
# Add a 1 second delay to skip samples that are not in the leaf() function
perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 --user-callchains -- $TEST_PROGRAM 2> /dev/null &
PID=$!
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH 06/12] perf test: Replace arm callgraph fp test workload with leafloop
2022-11-09 17:46 ` [PATCH 06/12] perf test: Replace arm callgraph fp test workload with leafloop Namhyung Kim
@ 2022-11-10 11:20 ` Leo Yan
2022-11-10 17:45 ` Namhyung Kim
0 siblings, 1 reply; 23+ messages in thread
From: Leo Yan @ 2022-11-10 11:20 UTC (permalink / raw)
To: Namhyung Kim
Cc: Arnaldo Carvalho de Melo, Jiri Olsa, Ingo Molnar, Peter Zijlstra,
LKML, Ian Rogers, Adrian Hunter, linux-perf-users, German Gomez,
Zhengjun Xing, James Clark
Hi Namyung,
On Wed, Nov 09, 2022 at 09:46:29AM -0800, Namhyung Kim wrote:
> So that it can get rid of requirement of a compiler.
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> .../perf/tests/shell/test_arm_callgraph_fp.sh | 30 +------------------
> 1 file changed, 1 insertion(+), 29 deletions(-)
>
> diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
> index ec108d45d3c6..9d6d1b2d99c5 100755
> --- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
> +++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
> @@ -4,44 +4,16 @@
>
> lscpu | grep -q "aarch64" || exit 2
>
> -if ! [ -x "$(command -v cc)" ]; then
> - echo "failed: no compiler, install gcc"
> - exit 2
> -fi
> -
> PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
> -TEST_PROGRAM_SOURCE=$(mktemp /tmp/test_program.XXXXX.c)
> -TEST_PROGRAM=$(mktemp /tmp/test_program.XXXXX)
> +TEST_PROGRAM="perf test -w leafloop"
>
> cleanup_files()
> {
> rm -f $PERF_DATA
> - rm -f $TEST_PROGRAM_SOURCE
> - rm -f $TEST_PROGRAM
> }
>
> trap cleanup_files exit term int
>
> -cat << EOF > $TEST_PROGRAM_SOURCE
> -int a = 0;
> -void leaf(void) {
> - for (;;)
> - a += a;
> -}
> -void parent(void) {
> - leaf();
> -}
> -int main(void) {
> - parent();
> - return 0;
> -}
> -EOF
> -
> -echo " + Compiling test program ($TEST_PROGRAM)..."
> -
> -CFLAGS="-g -O0 -fno-inline -fno-omit-frame-pointer"
> -cc $CFLAGS $TEST_PROGRAM_SOURCE -o $TEST_PROGRAM || exit 1
> -
> # Add a 1 second delay to skip samples that are not in the leaf() function
> perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 --user-callchains -- $TEST_PROGRAM 2> /dev/null &
> PID=$!
I need to append below changes, otherwise the test will fail on Arm64:
--- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
@@ -30,11 +30,11 @@ wait $PID
# program
# 728 leaf
# 753 parent
-# 76c main
+# 76c leafloop
# ...
perf script -i $PERF_DATA -F comm,ip,sym | head -n4
perf script -i $PERF_DATA -F comm,ip,sym | head -n4 | \
awk '{ if ($2 != "") sym[i++] = $2 } END { if (sym[0] != "leaf" ||
sym[1] != "parent" ||
- sym[2] != "main") exit 1 }'
+ sym[2] != "leafloop") exit 1 }'
With appending above change, this patch looks good to me:
Reviewed-by: Leo Yan <leo.yan@linaro.org>
German, James, would you have chance to review this change?
Thanks,
Leo
^ permalink raw reply [flat|nested] 23+ messages in thread* Re: [PATCH 06/12] perf test: Replace arm callgraph fp test workload with leafloop
2022-11-10 11:20 ` Leo Yan
@ 2022-11-10 17:45 ` Namhyung Kim
0 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-10 17:45 UTC (permalink / raw)
To: Leo Yan
Cc: Arnaldo Carvalho de Melo, Jiri Olsa, Ingo Molnar, Peter Zijlstra,
LKML, Ian Rogers, Adrian Hunter, linux-perf-users, German Gomez,
Zhengjun Xing, James Clark
Hi Leo,
On Thu, Nov 10, 2022 at 3:20 AM Leo Yan <leo.yan@linaro.org> wrote:
>
> Hi Namyung,
>
> On Wed, Nov 09, 2022 at 09:46:29AM -0800, Namhyung Kim wrote:
> > So that it can get rid of requirement of a compiler.
> >
> > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > ---
> > .../perf/tests/shell/test_arm_callgraph_fp.sh | 30 +------------------
> > 1 file changed, 1 insertion(+), 29 deletions(-)
> >
> > diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
> > index ec108d45d3c6..9d6d1b2d99c5 100755
> > --- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
> > +++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
> > @@ -4,44 +4,16 @@
> >
> > lscpu | grep -q "aarch64" || exit 2
> >
> > -if ! [ -x "$(command -v cc)" ]; then
> > - echo "failed: no compiler, install gcc"
> > - exit 2
> > -fi
> > -
> > PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
> > -TEST_PROGRAM_SOURCE=$(mktemp /tmp/test_program.XXXXX.c)
> > -TEST_PROGRAM=$(mktemp /tmp/test_program.XXXXX)
> > +TEST_PROGRAM="perf test -w leafloop"
> >
> > cleanup_files()
> > {
> > rm -f $PERF_DATA
> > - rm -f $TEST_PROGRAM_SOURCE
> > - rm -f $TEST_PROGRAM
> > }
> >
> > trap cleanup_files exit term int
> >
> > -cat << EOF > $TEST_PROGRAM_SOURCE
> > -int a = 0;
> > -void leaf(void) {
> > - for (;;)
> > - a += a;
> > -}
> > -void parent(void) {
> > - leaf();
> > -}
> > -int main(void) {
> > - parent();
> > - return 0;
> > -}
> > -EOF
> > -
> > -echo " + Compiling test program ($TEST_PROGRAM)..."
> > -
> > -CFLAGS="-g -O0 -fno-inline -fno-omit-frame-pointer"
> > -cc $CFLAGS $TEST_PROGRAM_SOURCE -o $TEST_PROGRAM || exit 1
> > -
> > # Add a 1 second delay to skip samples that are not in the leaf() function
> > perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 --user-callchains -- $TEST_PROGRAM 2> /dev/null &
> > PID=$!
>
> I need to append below changes, otherwise the test will fail on Arm64:
Thanks for the fix, will add it to v2.
>
> --- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
> +++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
> @@ -30,11 +30,11 @@ wait $PID
> # program
> # 728 leaf
> # 753 parent
> -# 76c main
> +# 76c leafloop
> # ...
>
> perf script -i $PERF_DATA -F comm,ip,sym | head -n4
> perf script -i $PERF_DATA -F comm,ip,sym | head -n4 | \
> awk '{ if ($2 != "") sym[i++] = $2 } END { if (sym[0] != "leaf" ||
> sym[1] != "parent" ||
> - sym[2] != "main") exit 1 }'
> + sym[2] != "leafloop") exit 1 }'
>
> With appending above change, this patch looks good to me:
>
> Reviewed-by: Leo Yan <leo.yan@linaro.org>
Great, thanks a lot!
Namhyung
>
> German, James, would you have chance to review this change?
>
> Thanks,
> Leo
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH 07/12] perf test: Add 'sqrtloop' test workload
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
` (5 preceding siblings ...)
2022-11-09 17:46 ` [PATCH 06/12] perf test: Replace arm callgraph fp test workload with leafloop Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-10 14:49 ` German Gomez
2022-11-09 17:46 ` [PATCH 08/12] perf test: Replace arm spe fork test workload with sqrtloop Namhyung Kim
` (4 subsequent siblings)
11 siblings, 1 reply; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
The sqrtloop creates a child process to run an infinite loop calling
sqrt() with rand(). This is needed for ARM SPE fork test.
$ perf test -w sqrtloop
It can take an optional argument to specify how long it will run in
seconds (default: 1).
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/builtin-test.c | 1 +
tools/perf/tests/tests.h | 1 +
tools/perf/tests/workloads/Build | 1 +
tools/perf/tests/workloads/sqrtloop.c | 44 +++++++++++++++++++++++++++
4 files changed, 47 insertions(+)
create mode 100644 tools/perf/tests/workloads/sqrtloop.c
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 0ed5ac452f6e..9acb7a93eeb9 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -122,6 +122,7 @@ static struct test_workload *workloads[] = {
&workload__noploop,
&workload__thloop,
&workload__leafloop,
+ &workload__sqrtloop,
};
static int num_subtests(const struct test_suite *t)
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 86804dd6452b..18c40319e67c 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -203,5 +203,6 @@ struct test_workload workload__##work = { \
DECLARE_WORKLOAD(noploop);
DECLARE_WORKLOAD(thloop);
DECLARE_WORKLOAD(leafloop);
+DECLARE_WORKLOAD(sqrtloop);
#endif /* TESTS_H */
diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build
index 631596bdb2b3..1ca95cb0fdb5 100644
--- a/tools/perf/tests/workloads/Build
+++ b/tools/perf/tests/workloads/Build
@@ -3,5 +3,6 @@
perf-y += noploop.o
perf-y += thloop.o
perf-y += leafloop.o
+perf-y += sqrtloop.o
CFLAGS_leafloop.o = -g -O0 -fno-inline -fno-omit-frame-pointer
diff --git a/tools/perf/tests/workloads/sqrtloop.c b/tools/perf/tests/workloads/sqrtloop.c
new file mode 100644
index 000000000000..f7d1f8d4867b
--- /dev/null
+++ b/tools/perf/tests/workloads/sqrtloop.c
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <math.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+#include <sys/wait.h>
+#include "../tests.h"
+
+static volatile int done;
+
+static void sighandler(int sig __maybe_unused)
+{
+ done = 1;
+}
+
+static int __sqrtloop(int sec)
+{
+ signal(SIGALRM, sighandler);
+ alarm(sec);
+
+ while (!done)
+ sqrt(rand());
+ return 0;
+}
+
+static int sqrtloop(int argc, const char **argv)
+{
+ int sec = 1;
+
+ if (argc > 0)
+ sec = atoi(argv[0]);
+
+ switch (fork()) {
+ case 0:
+ return __sqrtloop(sec);
+ case -1:
+ return -1;
+ default:
+ wait(NULL);
+ }
+ return 0;
+}
+
+DEFINE_WORKLOAD(sqrtloop);
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH 07/12] perf test: Add 'sqrtloop' test workload
2022-11-09 17:46 ` [PATCH 07/12] perf test: Add 'sqrtloop' test workload Namhyung Kim
@ 2022-11-10 14:49 ` German Gomez
2022-11-10 17:48 ` Namhyung Kim
0 siblings, 1 reply; 23+ messages in thread
From: German Gomez @ 2022-11-10 14:49 UTC (permalink / raw)
To: Namhyung Kim, Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, Zhengjun Xing, James Clark
On 09/11/2022 17:46, Namhyung Kim wrote:
> The sqrtloop creates a child process to run an infinite loop calling
> sqrt() with rand(). This is needed for ARM SPE fork test.
>
> $ perf test -w sqrtloop
>
> It can take an optional argument to specify how long it will run in
> seconds (default: 1).
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> tools/perf/tests/builtin-test.c | 1 +
> tools/perf/tests/tests.h | 1 +
> tools/perf/tests/workloads/Build | 1 +
> tools/perf/tests/workloads/sqrtloop.c | 44 +++++++++++++++++++++++++++
> 4 files changed, 47 insertions(+)
> create mode 100644 tools/perf/tests/workloads/sqrtloop.c
>
> diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
> index 0ed5ac452f6e..9acb7a93eeb9 100644
> --- a/tools/perf/tests/builtin-test.c
> +++ b/tools/perf/tests/builtin-test.c
> @@ -122,6 +122,7 @@ static struct test_workload *workloads[] = {
> &workload__noploop,
> &workload__thloop,
> &workload__leafloop,
> + &workload__sqrtloop,
> };
>
> static int num_subtests(const struct test_suite *t)
> diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
> index 86804dd6452b..18c40319e67c 100644
> --- a/tools/perf/tests/tests.h
> +++ b/tools/perf/tests/tests.h
> @@ -203,5 +203,6 @@ struct test_workload workload__##work = { \
> DECLARE_WORKLOAD(noploop);
> DECLARE_WORKLOAD(thloop);
> DECLARE_WORKLOAD(leafloop);
> +DECLARE_WORKLOAD(sqrtloop);
>
> #endif /* TESTS_H */
> diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build
> index 631596bdb2b3..1ca95cb0fdb5 100644
> --- a/tools/perf/tests/workloads/Build
> +++ b/tools/perf/tests/workloads/Build
> @@ -3,5 +3,6 @@
> perf-y += noploop.o
> perf-y += thloop.o
> perf-y += leafloop.o
> +perf-y += sqrtloop.o
>
> CFLAGS_leafloop.o = -g -O0 -fno-inline -fno-omit-frame-pointer
> diff --git a/tools/perf/tests/workloads/sqrtloop.c b/tools/perf/tests/workloads/sqrtloop.c
> new file mode 100644
> index 000000000000..f7d1f8d4867b
> --- /dev/null
> +++ b/tools/perf/tests/workloads/sqrtloop.c
> @@ -0,0 +1,44 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#include <math.h>
> +#include <signal.h>
> +#include <stdlib.h>
> +#include <linux/compiler.h>
> +#include <sys/wait.h>
> +#include "../tests.h"
> +
> +static volatile int done;
> +
> +static void sighandler(int sig __maybe_unused)
> +{
> + done = 1;
> +}
> +
> +static int __sqrtloop(int sec)
> +{
> + signal(SIGALRM, sighandler);
> + alarm(sec);
> +
> + while (!done)
> + sqrt(rand());
> + return 0;
> +}
I get some implicit declaration errors on x86 build
(gcc (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0)
. CC tests/workloads/sqrtloop.o
.tests/workloads/sqrtloop.c: In function ‘__sqrtloop’:
.tests/workloads/sqrtloop.c:19:2: error: implicit declaration of function ‘alarm’ [-Werror=implicit-function-declaration]
. 19 | alarm(sec);
. | ^~~~~
.tests/workloads/sqrtloop.c: In function ‘sqrtloop’:
.tests/workloads/sqrtloop.c:33:10: error: implicit declaration of function ‘fork’ [-Werror=implicit-function-declaration]
. 33 | switch (fork()) {
. | ^~~~
> +
> +static int sqrtloop(int argc, const char **argv)
> +{
> + int sec = 1;
> +
> + if (argc > 0)
> + sec = atoi(argv[0]);
> +
> + switch (fork()) {
> + case 0:
> + return __sqrtloop(sec);
> + case -1:
> + return -1;
> + default:
> + wait(NULL);
> + }
> + return 0;
> +}
> +
> +DEFINE_WORKLOAD(sqrtloop);
^ permalink raw reply [flat|nested] 23+ messages in thread* Re: [PATCH 07/12] perf test: Add 'sqrtloop' test workload
2022-11-10 14:49 ` German Gomez
@ 2022-11-10 17:48 ` Namhyung Kim
0 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-10 17:48 UTC (permalink / raw)
To: German Gomez
Cc: Arnaldo Carvalho de Melo, Jiri Olsa, Ingo Molnar, Peter Zijlstra,
LKML, Ian Rogers, Adrian Hunter, linux-perf-users, Leo Yan,
Zhengjun Xing, James Clark
Hello,
On Thu, Nov 10, 2022 at 6:49 AM German Gomez <german.gomez@arm.com> wrote:
>
> On 09/11/2022 17:46, Namhyung Kim wrote:
> > The sqrtloop creates a child process to run an infinite loop calling
> > sqrt() with rand(). This is needed for ARM SPE fork test.
> >
> > $ perf test -w sqrtloop
> >
> > It can take an optional argument to specify how long it will run in
> > seconds (default: 1).
> >
> > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > ---
> > tools/perf/tests/builtin-test.c | 1 +
> > tools/perf/tests/tests.h | 1 +
> > tools/perf/tests/workloads/Build | 1 +
> > tools/perf/tests/workloads/sqrtloop.c | 44 +++++++++++++++++++++++++++
> > 4 files changed, 47 insertions(+)
> > create mode 100644 tools/perf/tests/workloads/sqrtloop.c
> >
> > diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
> > index 0ed5ac452f6e..9acb7a93eeb9 100644
> > --- a/tools/perf/tests/builtin-test.c
> > +++ b/tools/perf/tests/builtin-test.c
> > @@ -122,6 +122,7 @@ static struct test_workload *workloads[] = {
> > &workload__noploop,
> > &workload__thloop,
> > &workload__leafloop,
> > + &workload__sqrtloop,
> > };
> >
> > static int num_subtests(const struct test_suite *t)
> > diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
> > index 86804dd6452b..18c40319e67c 100644
> > --- a/tools/perf/tests/tests.h
> > +++ b/tools/perf/tests/tests.h
> > @@ -203,5 +203,6 @@ struct test_workload workload__##work = { \
> > DECLARE_WORKLOAD(noploop);
> > DECLARE_WORKLOAD(thloop);
> > DECLARE_WORKLOAD(leafloop);
> > +DECLARE_WORKLOAD(sqrtloop);
> >
> > #endif /* TESTS_H */
> > diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build
> > index 631596bdb2b3..1ca95cb0fdb5 100644
> > --- a/tools/perf/tests/workloads/Build
> > +++ b/tools/perf/tests/workloads/Build
> > @@ -3,5 +3,6 @@
> > perf-y += noploop.o
> > perf-y += thloop.o
> > perf-y += leafloop.o
> > +perf-y += sqrtloop.o
> >
> > CFLAGS_leafloop.o = -g -O0 -fno-inline -fno-omit-frame-pointer
> > diff --git a/tools/perf/tests/workloads/sqrtloop.c b/tools/perf/tests/workloads/sqrtloop.c
> > new file mode 100644
> > index 000000000000..f7d1f8d4867b
> > --- /dev/null
> > +++ b/tools/perf/tests/workloads/sqrtloop.c
> > @@ -0,0 +1,44 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +#include <math.h>
> > +#include <signal.h>
> > +#include <stdlib.h>
> > +#include <linux/compiler.h>
> > +#include <sys/wait.h>
> > +#include "../tests.h"
> > +
> > +static volatile int done;
> > +
> > +static void sighandler(int sig __maybe_unused)
> > +{
> > + done = 1;
> > +}
> > +
> > +static int __sqrtloop(int sec)
> > +{
> > + signal(SIGALRM, sighandler);
> > + alarm(sec);
> > +
> > + while (!done)
> > + sqrt(rand());
> > + return 0;
> > +}
>
> I get some implicit declaration errors on x86 build
>
> (gcc (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0)
>
> . CC tests/workloads/sqrtloop.o
> .tests/workloads/sqrtloop.c: In function ‘__sqrtloop’:
> .tests/workloads/sqrtloop.c:19:2: error: implicit declaration of function ‘alarm’ [-Werror=implicit-function-declaration]
> . 19 | alarm(sec);
> . | ^~~~~
> .tests/workloads/sqrtloop.c: In function ‘sqrtloop’:
> .tests/workloads/sqrtloop.c:33:10: error: implicit declaration of function ‘fork’ [-Werror=implicit-function-declaration]
> . 33 | switch (fork()) {
> . | ^~~~
Oh, thanks for letting me know. I think it needs <unitstd.h>.
Will fix in v2.
Thanks,
Namhyung
>
> > +
> > +static int sqrtloop(int argc, const char **argv)
> > +{
> > + int sec = 1;
> > +
> > + if (argc > 0)
> > + sec = atoi(argv[0]);
> > +
> > + switch (fork()) {
> > + case 0:
> > + return __sqrtloop(sec);
> > + case -1:
> > + return -1;
> > + default:
> > + wait(NULL);
> > + }
> > + return 0;
> > +}
> > +
> > +DEFINE_WORKLOAD(sqrtloop);
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH 08/12] perf test: Replace arm spe fork test workload with sqrtloop
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
` (6 preceding siblings ...)
2022-11-09 17:46 ` [PATCH 07/12] perf test: Add 'sqrtloop' test workload Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-10 11:45 ` Leo Yan
2022-11-09 17:46 ` [PATCH 09/12] perf test: Add 'brstack' test workload Namhyung Kim
` (3 subsequent siblings)
11 siblings, 1 reply; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
So that it can get rid of requirement of a compiler. I've also removed
killall as it'll kill perf process now and run the test workload for 10
sec instead.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/shell/test_arm_spe_fork.sh | 44 +--------------------
1 file changed, 1 insertion(+), 43 deletions(-)
diff --git a/tools/perf/tests/shell/test_arm_spe_fork.sh b/tools/perf/tests/shell/test_arm_spe_fork.sh
index c920d3583d30..da810e1b2b9e 100755
--- a/tools/perf/tests/shell/test_arm_spe_fork.sh
+++ b/tools/perf/tests/shell/test_arm_spe_fork.sh
@@ -11,14 +11,7 @@ skip_if_no_arm_spe_event() {
skip_if_no_arm_spe_event || exit 2
-# skip if there's no compiler
-if ! [ -x "$(command -v cc)" ]; then
- echo "failed: no compiler, install gcc"
- exit 2
-fi
-
-TEST_PROGRAM_SOURCE=$(mktemp /tmp/__perf_test.program.XXXXX.c)
-TEST_PROGRAM=$(mktemp /tmp/__perf_test.program.XXXXX)
+TEST_PROGRAM="perf test -w sqrtloop 10"
PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
PERF_RECORD_LOG=$(mktemp /tmp/__perf_test.log.XXXXX)
@@ -27,43 +20,10 @@ cleanup_files()
echo "Cleaning up files..."
rm -f ${PERF_RECORD_LOG}
rm -f ${PERF_DATA}
- rm -f ${TEST_PROGRAM_SOURCE}
- rm -f ${TEST_PROGRAM}
}
trap cleanup_files exit term int
-# compile test program
-cat << EOF > $TEST_PROGRAM_SOURCE
-#include <math.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <sys/wait.h>
-
-int workload() {
- while (1)
- sqrt(rand());
- return 0;
-}
-
-int main() {
- switch (fork()) {
- case 0:
- return workload();
- case -1:
- return 1;
- default:
- wait(NULL);
- }
- return 0;
-}
-EOF
-
-echo "Compiling test program..."
-CFLAGS="-lm"
-cc $TEST_PROGRAM_SOURCE $CFLAGS -o $TEST_PROGRAM || exit 1
-
echo "Recording workload..."
perf record -o ${PERF_DATA} -e arm_spe/period=65536/ -vvv -- $TEST_PROGRAM > ${PERF_RECORD_LOG} 2>&1 &
PERFPID=$!
@@ -78,8 +38,6 @@ echo Log lines after 1 second = $log1
kill $PERFPID
wait $PERFPID
-# test program may leave an orphan process running the workload
-killall $(basename $TEST_PROGRAM)
if [ "$log0" = "$log1" ];
then
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH 08/12] perf test: Replace arm spe fork test workload with sqrtloop
2022-11-09 17:46 ` [PATCH 08/12] perf test: Replace arm spe fork test workload with sqrtloop Namhyung Kim
@ 2022-11-10 11:45 ` Leo Yan
0 siblings, 0 replies; 23+ messages in thread
From: Leo Yan @ 2022-11-10 11:45 UTC (permalink / raw)
To: Namhyung Kim
Cc: Arnaldo Carvalho de Melo, Jiri Olsa, Ingo Molnar, Peter Zijlstra,
LKML, Ian Rogers, Adrian Hunter, linux-perf-users, German Gomez,
Zhengjun Xing, James Clark
On Wed, Nov 09, 2022 at 09:46:31AM -0800, Namhyung Kim wrote:
> So that it can get rid of requirement of a compiler. I've also removed
> killall as it'll kill perf process now and run the test workload for 10
> sec instead.
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The patch looks good to me and I tested on Arm64 machine:
Tested-by: Leo Yan <leo.yan@linaro.org>
> ---
> tools/perf/tests/shell/test_arm_spe_fork.sh | 44 +--------------------
> 1 file changed, 1 insertion(+), 43 deletions(-)
>
> diff --git a/tools/perf/tests/shell/test_arm_spe_fork.sh b/tools/perf/tests/shell/test_arm_spe_fork.sh
> index c920d3583d30..da810e1b2b9e 100755
> --- a/tools/perf/tests/shell/test_arm_spe_fork.sh
> +++ b/tools/perf/tests/shell/test_arm_spe_fork.sh
> @@ -11,14 +11,7 @@ skip_if_no_arm_spe_event() {
>
> skip_if_no_arm_spe_event || exit 2
>
> -# skip if there's no compiler
> -if ! [ -x "$(command -v cc)" ]; then
> - echo "failed: no compiler, install gcc"
> - exit 2
> -fi
> -
> -TEST_PROGRAM_SOURCE=$(mktemp /tmp/__perf_test.program.XXXXX.c)
> -TEST_PROGRAM=$(mktemp /tmp/__perf_test.program.XXXXX)
> +TEST_PROGRAM="perf test -w sqrtloop 10"
> PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
> PERF_RECORD_LOG=$(mktemp /tmp/__perf_test.log.XXXXX)
>
> @@ -27,43 +20,10 @@ cleanup_files()
> echo "Cleaning up files..."
> rm -f ${PERF_RECORD_LOG}
> rm -f ${PERF_DATA}
> - rm -f ${TEST_PROGRAM_SOURCE}
> - rm -f ${TEST_PROGRAM}
> }
>
> trap cleanup_files exit term int
>
> -# compile test program
> -cat << EOF > $TEST_PROGRAM_SOURCE
> -#include <math.h>
> -#include <stdio.h>
> -#include <stdlib.h>
> -#include <unistd.h>
> -#include <sys/wait.h>
> -
> -int workload() {
> - while (1)
> - sqrt(rand());
> - return 0;
> -}
> -
> -int main() {
> - switch (fork()) {
> - case 0:
> - return workload();
> - case -1:
> - return 1;
> - default:
> - wait(NULL);
> - }
> - return 0;
> -}
> -EOF
> -
> -echo "Compiling test program..."
> -CFLAGS="-lm"
> -cc $TEST_PROGRAM_SOURCE $CFLAGS -o $TEST_PROGRAM || exit 1
> -
> echo "Recording workload..."
> perf record -o ${PERF_DATA} -e arm_spe/period=65536/ -vvv -- $TEST_PROGRAM > ${PERF_RECORD_LOG} 2>&1 &
> PERFPID=$!
> @@ -78,8 +38,6 @@ echo Log lines after 1 second = $log1
>
> kill $PERFPID
> wait $PERFPID
> -# test program may leave an orphan process running the workload
> -killall $(basename $TEST_PROGRAM)
>
> if [ "$log0" = "$log1" ];
> then
> --
> 2.38.1.431.g37b22c650d-goog
>
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH 09/12] perf test: Add 'brstack' test workload
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
` (7 preceding siblings ...)
2022-11-09 17:46 ` [PATCH 08/12] perf test: Replace arm spe fork test workload with sqrtloop Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-09 17:46 ` [PATCH 10/12] perf test: Replace brstack " Namhyung Kim
` (2 subsequent siblings)
11 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
The brstack is to run different kinds of branches repeatedly. This is
necessary for brstack test case to verify if it has correct branch info.
$ perf test -w brstack
I renamed the internal functions to have brstack_ prefix as it's too
generic name.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/builtin-test.c | 1 +
tools/perf/tests/tests.h | 1 +
tools/perf/tests/workloads/Build | 2 ++
tools/perf/tests/workloads/brstack.c | 39 ++++++++++++++++++++++++++++
4 files changed, 43 insertions(+)
create mode 100644 tools/perf/tests/workloads/brstack.c
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 9acb7a93eeb9..69fa56939309 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -123,6 +123,7 @@ static struct test_workload *workloads[] = {
&workload__thloop,
&workload__leafloop,
&workload__sqrtloop,
+ &workload__brstack,
};
static int num_subtests(const struct test_suite *t)
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 18c40319e67c..dc96f59cac2e 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -204,5 +204,6 @@ DECLARE_WORKLOAD(noploop);
DECLARE_WORKLOAD(thloop);
DECLARE_WORKLOAD(leafloop);
DECLARE_WORKLOAD(sqrtloop);
+DECLARE_WORKLOAD(brstack);
#endif /* TESTS_H */
diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build
index 1ca95cb0fdb5..c933cdcf91d1 100644
--- a/tools/perf/tests/workloads/Build
+++ b/tools/perf/tests/workloads/Build
@@ -4,5 +4,7 @@ perf-y += noploop.o
perf-y += thloop.o
perf-y += leafloop.o
perf-y += sqrtloop.o
+perf-y += brstack.o
CFLAGS_leafloop.o = -g -O0 -fno-inline -fno-omit-frame-pointer
+CFLAGS_brstack.o = -g -O0 -fno-inline
diff --git a/tools/perf/tests/workloads/brstack.c b/tools/perf/tests/workloads/brstack.c
new file mode 100644
index 000000000000..61c9a9f24b43
--- /dev/null
+++ b/tools/perf/tests/workloads/brstack.c
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+#include "../tests.h"
+
+
+#define BENCH_RUNS 999999
+
+static volatile int cnt;
+
+static void brstack_bar(void) {
+} /* return */
+
+static void brstack_foo(void) {
+ brstack_bar(); /* call */
+} /* return */
+
+static void brstack_bench(void) {
+ void (*brstack_foo_ind)(void) = brstack_foo;
+
+ if ((cnt++) % 3) /* branch (cond) */
+ brstack_foo(); /* call */
+ brstack_bar(); /* call */
+ brstack_foo_ind(); /* call (ind) */
+}
+
+static int brstack(int argc, const char **argv)
+{
+ if (argc > 0)
+ cnt = atoi(argv[0]);
+
+ while (1) {
+ if ((cnt++) > BENCH_RUNS)
+ break;
+ brstack_bench();/* call */
+ } /* branch (uncond) */
+ return 0;
+}
+
+DEFINE_WORKLOAD(brstack);
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH 10/12] perf test: Replace brstack test workload
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
` (8 preceding siblings ...)
2022-11-09 17:46 ` [PATCH 09/12] perf test: Add 'brstack' test workload Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-09 17:46 ` [PATCH 11/12] perf test: Add 'datasym' " Namhyung Kim
2022-11-09 17:46 ` [PATCH 12/12] perf test: Replace data symbol test workload with datasym Namhyung Kim
11 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
So that it can get rid of requirement of a compiler. Also rename the
symbols to match with the perf test workload.
Cc: German Gomez <german.gomez@arm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/shell/test_brstack.sh | 66 +++++---------------------
1 file changed, 12 insertions(+), 54 deletions(-)
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index ec801cffae6b..a8a182dea25f 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -4,18 +4,12 @@
# SPDX-License-Identifier: GPL-2.0
# German Gomez <german.gomez@arm.com>, 2022
-# we need a C compiler to build the test programs
-# so bail if none is found
-if ! [ -x "$(command -v cc)" ]; then
- echo "failed: no compiler, install gcc"
- exit 2
-fi
-
# skip the test if the hardware doesn't support branch stack sampling
# and if the architecture doesn't support filter types: any,save_type,u
perf record -b -o- -B --branch-filter any,save_type,u true > /dev/null 2>&1 || exit 2
TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
+TESTPROG="perf test -w brstack"
cleanup() {
rm -rf $TMPDIR
@@ -23,57 +17,24 @@ cleanup() {
trap cleanup exit term int
-gen_test_program() {
- # generate test program
- cat << EOF > $1
-#define BENCH_RUNS 999999
-int cnt;
-void bar(void) {
-} /* return */
-void foo(void) {
- bar(); /* call */
-} /* return */
-void bench(void) {
- void (*foo_ind)(void) = foo;
- if ((cnt++) % 3) /* branch (cond) */
- foo(); /* call */
- bar(); /* call */
- foo_ind(); /* call (ind) */
-}
-int main(void)
-{
- int cnt = 0;
- while (1) {
- if ((cnt++) > BENCH_RUNS)
- break;
- bench(); /* call */
- } /* branch (uncond) */
- return 0;
-}
-EOF
-}
-
test_user_branches() {
echo "Testing user branch stack sampling"
- gen_test_program "$TEMPDIR/program.c"
- cc -fno-inline -g "$TEMPDIR/program.c" -o $TMPDIR/a.out
-
- perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- $TMPDIR/a.out > /dev/null 2>&1
+ perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1
perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script
# example of branch entries:
- # foo+0x14/bar+0x40/P/-/-/0/CALL
+ # brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL
set -x
- egrep -m1 "^bench\+[^ ]*/foo\+[^ ]*/IND_CALL$" $TMPDIR/perf.script
- egrep -m1 "^foo\+[^ ]*/bar\+[^ ]*/CALL$" $TMPDIR/perf.script
- egrep -m1 "^bench\+[^ ]*/foo\+[^ ]*/CALL$" $TMPDIR/perf.script
- egrep -m1 "^bench\+[^ ]*/bar\+[^ ]*/CALL$" $TMPDIR/perf.script
- egrep -m1 "^bar\+[^ ]*/foo\+[^ ]*/RET$" $TMPDIR/perf.script
- egrep -m1 "^foo\+[^ ]*/bench\+[^ ]*/RET$" $TMPDIR/perf.script
- egrep -m1 "^bench\+[^ ]*/bench\+[^ ]*/COND$" $TMPDIR/perf.script
- egrep -m1 "^main\+[^ ]*/main\+[^ ]*/UNCOND$" $TMPDIR/perf.script
+ egrep -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL$" $TMPDIR/perf.script
+ egrep -m1 "^brstack_foo\+[^ ]*/brstack_bar\+[^ ]*/CALL$" $TMPDIR/perf.script
+ egrep -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/CALL$" $TMPDIR/perf.script
+ egrep -m1 "^brstack_bench\+[^ ]*/brstack_bar\+[^ ]*/CALL$" $TMPDIR/perf.script
+ egrep -m1 "^brstack_bar\+[^ ]*/brstack_foo\+[^ ]*/RET$" $TMPDIR/perf.script
+ egrep -m1 "^brstack_foo\+[^ ]*/brstsack_bench\+[^ ]*/RET$" $TMPDIR/perf.script
+ egrep -m1 "^brstack_bench\+[^ ]*/brstack_bench\+[^ ]*/COND$" $TMPDIR/perf.script
+ egrep -m1 "^brstack\+[^ ]*/brstack\+[^ ]*/UNCOND$" $TMPDIR/perf.script
set +x
# some branch types are still not being tested:
@@ -88,10 +49,7 @@ test_filter() {
echo "Testing branch stack filtering permutation ($filter,$expect)"
- gen_test_program "$TEMPDIR/program.c"
- cc -fno-inline -g "$TEMPDIR/program.c" -o $TMPDIR/a.out
-
- perf record -o $TMPDIR/perf.data --branch-filter $filter,save_type,u -- $TMPDIR/a.out > /dev/null 2>&1
+ perf record -o $TMPDIR/perf.data --branch-filter $filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1
perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script
# fail if we find any branch type that doesn't match any of the expected ones
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH 11/12] perf test: Add 'datasym' test workload
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
` (9 preceding siblings ...)
2022-11-09 17:46 ` [PATCH 10/12] perf test: Replace brstack " Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
2022-11-09 17:46 ` [PATCH 12/12] perf test: Replace data symbol test workload with datasym Namhyung Kim
11 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
The datasym workload is to check if perf mem command gets the data
addresses precisely. This is needed for data symbol test.
$ perf test -w datasym
I had to keep the buf1 in the data section, otherwise it could end
up in the BSS and was mmaped as a separate //anon region, then it
was not symbolized at all. It needs to be fixed separately.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/builtin-test.c | 1 +
tools/perf/tests/tests.h | 1 +
tools/perf/tests/workloads/Build | 2 ++
tools/perf/tests/workloads/datasym.c | 24 ++++++++++++++++++++++++
4 files changed, 28 insertions(+)
create mode 100644 tools/perf/tests/workloads/datasym.c
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 69fa56939309..4c6ae59a4dfd 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -124,6 +124,7 @@ static struct test_workload *workloads[] = {
&workload__leafloop,
&workload__sqrtloop,
&workload__brstack,
+ &workload__datasym,
};
static int num_subtests(const struct test_suite *t)
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index dc96f59cac2e..e15f24cfc909 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -205,5 +205,6 @@ DECLARE_WORKLOAD(thloop);
DECLARE_WORKLOAD(leafloop);
DECLARE_WORKLOAD(sqrtloop);
DECLARE_WORKLOAD(brstack);
+DECLARE_WORKLOAD(datasym);
#endif /* TESTS_H */
diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build
index c933cdcf91d1..ec3cb10c52ae 100644
--- a/tools/perf/tests/workloads/Build
+++ b/tools/perf/tests/workloads/Build
@@ -5,6 +5,8 @@ perf-y += thloop.o
perf-y += leafloop.o
perf-y += sqrtloop.o
perf-y += brstack.o
+perf-y += datasym.o
CFLAGS_leafloop.o = -g -O0 -fno-inline -fno-omit-frame-pointer
CFLAGS_brstack.o = -g -O0 -fno-inline
+CFLAGS_datasym.o = -g -O0 -fno-inline
diff --git a/tools/perf/tests/workloads/datasym.c b/tools/perf/tests/workloads/datasym.c
new file mode 100644
index 000000000000..ddd40bc63448
--- /dev/null
+++ b/tools/perf/tests/workloads/datasym.c
@@ -0,0 +1,24 @@
+#include <linux/compiler.h>
+#include "../tests.h"
+
+typedef struct _buf {
+ char data1;
+ char reserved[55];
+ char data2;
+} buf __attribute__((aligned(64)));
+
+static buf buf1 = {
+ /* to have this in the data section */
+ .reserved[0] = 1,
+};
+
+static int datasym(int argc __maybe_unused, const char **argv __maybe_unused)
+{
+ for (;;) {
+ buf1.data1++;
+ buf1.data2 += buf1.data1;
+ }
+ return 0;
+}
+
+DEFINE_WORKLOAD(datasym);
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH 12/12] perf test: Replace data symbol test workload with datasym
2022-11-09 17:46 [PATCHSET 00/12] perf test: Add test workloads (v1) Namhyung Kim
` (10 preceding siblings ...)
2022-11-09 17:46 ` [PATCH 11/12] perf test: Add 'datasym' " Namhyung Kim
@ 2022-11-09 17:46 ` Namhyung Kim
11 siblings, 0 replies; 23+ messages in thread
From: Namhyung Kim @ 2022-11-09 17:46 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Ian Rogers, Adrian Hunter,
linux-perf-users, Leo Yan, German Gomez, Zhengjun Xing,
James Clark
So that it can get rid of requirement of a compiler.
$ sudo ./perf test -v 109
109: Test data symbol :
--- start ---
test child forked, pid 844526
Recording workload...
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.354 MB /tmp/__perf_test.perf.data.GFeZO (4847 samples) ]
Cleaning up files...
test child finished with 0
---- end ----
Test data symbol: Ok
Cc: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/tests/shell/test_data_symbol.sh | 29 +---------------------
1 file changed, 1 insertion(+), 28 deletions(-)
diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh
index cd6eb54d235d..d871e6c743ef 100755
--- a/tools/perf/tests/shell/test_data_symbol.sh
+++ b/tools/perf/tests/shell/test_data_symbol.sh
@@ -11,13 +11,7 @@ skip_if_no_mem_event() {
skip_if_no_mem_event || exit 2
-# skip if there's no compiler
-if ! [ -x "$(command -v cc)" ]; then
- echo "skip: no compiler, install gcc"
- exit 2
-fi
-
-TEST_PROGRAM=$(mktemp /tmp/__perf_test.program.XXXXX)
+TEST_PROGRAM="perf test -w datasym"
PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
check_result() {
@@ -45,31 +39,10 @@ cleanup_files()
{
echo "Cleaning up files..."
rm -f ${PERF_DATA}
- rm -f ${TEST_PROGRAM}
}
trap cleanup_files exit term int
-# compile test program
-echo "Compiling test program..."
-cat << EOF | cc -o ${TEST_PROGRAM} -x c -
-typedef struct _buf {
- char data1;
- char reserved[55];
- char data2;
-} buf __attribute__((aligned(64)));
-
-static buf buf1;
-
-int main(void) {
- for (;;) {
- buf1.data1++;
- buf1.data2 += buf1.data1;
- }
- return 0;
-}
-EOF
-
echo "Recording workload..."
# perf mem/c2c internally uses IBS PMU on AMD CPU which doesn't support
--
2.38.1.431.g37b22c650d-goog
^ permalink raw reply related [flat|nested] 23+ messages in thread