Skip to contentSkip to conversation

tools/perf-bench: Add basic syscall benchmark

PATCH In review Davidlohr Bueso 5 participants 6 messages Mar 7, 2019 – Jul 26, 2020 perf events

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 tools/perf-bench: Add basic syscall benchmark

The usefulness of having a standard way of testing syscall performance has come up from time to time[0]. Furthermore, some of our testing machinery (such as 'mmtests') already makes use of a simplified version of the microbenchmark. This patch mainly takes the same idea to measure syscall throughput compatible with 'perf-bench' via getppid(2), yet without any of the additional template stuff from Ingo's version (based on numa.c). The code is identical to what mmtests uses.

https://www.mail-archive.com/[email protected]/msg1067469.html

---
 tools/perf/bench/Build     |  1 +
 tools/perf/bench/bench.h   |  1 +
 tools/perf/bench/syscall.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/builtin-bench.c |  8 +++++
 4 files changed, 90 insertions(+)
 create mode 100644 tools/perf/bench/syscall.c
tools/perf/bench/Build +1 -0
index e4e321b6f883..839f9b790587 100644
@@ -1,5 +1,6 @@
 perf-y += sched-messaging.o
 perf-y += sched-pipe.o
+perf-y += syscall.o
 perf-y += mem-functions.o
 perf-y += futex-hash.o
 perf-y += futex-wake.o
tools/perf/bench/bench.h +1 -0
index fddb3ced9db6..31ad3283d41b 100644
@@ -29,6 +29,7 @@
 int bench_numa(int argc, const char **argv);
 int bench_sched_messaging(int argc, const char **argv);
 int bench_sched_pipe(int argc, const char **argv);
+int bench_syscall_basic(int argc, const char **argv);
 int bench_mem_memcpy(int argc, const char **argv);
 int bench_mem_memset(int argc, const char **argv);
 int bench_futex_hash(int argc, const char **argv);
tools/perf/bench/syscall.c new file +80 -0

80 lines not on this page · raw message

tools/perf/builtin-bench.c +8 -0
index 334c77ffc1d9..4e9dd0f4eced 100644
@@ -11,6 +11,7 @@
  * Available benchmark collection list:
  *
  *  sched ... scheduler and IPC performance
+ *  syscall ... System call performance
  *  mem   ... memory access performance
  *  numa  ... NUMA scheduling and MM performance
  *  futex ... Futex performance
@@ -50,6 +51,12 @@ static struct bench sched_benchmarks[] = {
 	{ NULL,		NULL,						NULL			}
 };
 
+static struct bench syscall_benchmarks[] = {
+	{ "basic",	"Benchmark for basic getppid() system calls",	bench_syscall_basic	},
+	{ "all",	"Run all syscall benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			},
+};
+
 static struct bench mem_benchmarks[] = {
 	{ "memcpy",	"Benchmark for memcpy() functions",		bench_mem_memcpy	},
 	{ "memset",	"Benchmark for memset() functions",		bench_mem_memset	},
@@ -85,6 +92,7 @@ struct collection {
 
 static struct collection collections[] = {
 	{ "sched",	"Scheduler and IPC benchmarks",			sched_benchmarks	},
+	{ "syscall",	"System call benchmarks",			syscall_benchmarks	},
 	{ "mem",	"Memory access benchmarks",			mem_benchmarks		},
 #ifdef HAVE_LIBNUMA_SUPPORT
 	{ "numa",	"NUMA scheduling and MM benchmarks",		numa_benchmarks		},
Signature · 1 line
2.16.4
#1 lore raw

Em Thu, Mar 07, 2019 at 10:52:53AM -0800, Davidlohr Bueso escreveu:

Quoted 7 lines

The usefulness of having a standard way of testing syscall performance has come up from time to time[0]. Furthermore, some of our testing machinery (such as 'mmtests') already makes use of a simplified version of the microbenchmark. This patch mainly takes the same idea to measure syscall throughput compatible with 'perf-bench' via getppid(2), yet without any of the additional template stuff from Ingo's version (based on numa.c). The code is identical to what mmtests uses.

You forgot to update tools/perf/Documentation/perf-bench.txt, and please take a look at tools/perf/util/pmu.c convert_scale() to see how to save the current locale, set the one you want, then restore the previous one, so that at the end of this benchmark the environment is back to where it was.

Thanks.

- Arnaldo

Quoted 155 lines

https://www.mail-archive.com/[email protected]/msg1067469.html

---
 tools/perf/bench/Build     |  1 +
 tools/perf/bench/bench.h   |  1 +
 tools/perf/bench/syscall.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/builtin-bench.c |  8 +++++
 4 files changed, 90 insertions(+)
 create mode 100644 tools/perf/bench/syscall.c
tools/perf/bench/Build +1 -0
index e4e321b6f883..839f9b790587 100644
@@ -1,5 +1,6 @@
 perf-y += sched-messaging.o
 perf-y += sched-pipe.o
+perf-y += syscall.o
 perf-y += mem-functions.o
 perf-y += futex-hash.o
 perf-y += futex-wake.o
tools/perf/bench/bench.h +1 -0
index fddb3ced9db6..31ad3283d41b 100644
@@ -29,6 +29,7 @@
 int bench_numa(int argc, const char **argv);
 int bench_sched_messaging(int argc, const char **argv);
 int bench_sched_pipe(int argc, const char **argv);
+int bench_syscall_basic(int argc, const char **argv);
 int bench_mem_memcpy(int argc, const char **argv);
 int bench_mem_memset(int argc, const char **argv);
 int bench_futex_hash(int argc, const char **argv);
tools/perf/bench/syscall.c new file +80 -0
new file mode 100644
index 000000000000..149129cca639
@@ -0,0 +1,80 @@
+/*
+ *
+ * syscall.c
+ *
+ * syscall: Benchmark for system call performance
+ */
+#include "../perf.h"
+#include "../util/util.h"
+#include <subcmd/parse-options.h>
+#include "../builtin.h"
+#include "bench.h"
+
+#include <stdio.h>
+#include <locale.h>
+#include <sys/time.h>
+#include <sys/syscall.h>
+
+#define LOOPS_DEFAULT 10000000
+static	int loops = LOOPS_DEFAULT;
+
+static const struct option options[] = {
+	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_syscall_usage[] = {
+	"perf bench syscall <options>",
+	NULL
+};
+
+int bench_syscall_basic(int argc, const char **argv)
+{
+	struct timeval start, stop, diff;
+	unsigned long long result_usec = 0;
+	int i;
+
+	argc = parse_options(argc, argv, options, bench_syscall_usage, 0);
+
+	gettimeofday(&start, NULL);
+
+	for (i = 0; i < loops; i++)
+		getppid();
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		setlocale(LC_NUMERIC, "");
+		printf("# Executed %'d getppid() calls\n", loops);
+
+		result_usec = diff.tv_sec * 1000000;
+		result_usec += diff.tv_usec;
+
+		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
+		       diff.tv_sec,
+		       (unsigned long) (diff.tv_usec/1000));
+
+		printf(" %14lf usecs/op\n",
+		       (double)result_usec / (double)loops);
+		printf(" %'14d ops/sec\n",
+		       (int)((double)loops /
+			     ((double)result_usec / (double)1000000)));
+		break;
+
+	case BENCH_FORMAT_SIMPLE:
+		printf("%lu.%03lu\n",
+		       diff.tv_sec,
+		       (unsigned long) (diff.tv_usec / 1000));
+		break;
+
+	default:
+		/* reaching here is something disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+		break;
+	}
+
+	return 0;
+}
tools/perf/builtin-bench.c +8 -0
index 334c77ffc1d9..4e9dd0f4eced 100644
@@ -11,6 +11,7 @@
  * Available benchmark collection list:
  *
  *  sched ... scheduler and IPC performance
+ *  syscall ... System call performance
  *  mem   ... memory access performance
  *  numa  ... NUMA scheduling and MM performance
  *  futex ... Futex performance
@@ -50,6 +51,12 @@ static struct bench sched_benchmarks[] = {
 	{ NULL,		NULL,						NULL			}
 };
 
+static struct bench syscall_benchmarks[] = {
+	{ "basic",	"Benchmark for basic getppid() system calls",	bench_syscall_basic	},
+	{ "all",	"Run all syscall benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			},
+};
+
 static struct bench mem_benchmarks[] = {
 	{ "memcpy",	"Benchmark for memcpy() functions",		bench_mem_memcpy	},
 	{ "memset",	"Benchmark for memset() functions",		bench_mem_memset	},
@@ -85,6 +92,7 @@ struct collection {
 
 static struct collection collections[] = {
 	{ "sched",	"Scheduler and IPC benchmarks",			sched_benchmarks	},
+	{ "syscall",	"System call benchmarks",			syscall_benchmarks	},
 	{ "mem",	"Memory access benchmarks",			mem_benchmarks		},
 #ifdef HAVE_LIBNUMA_SUPPORT
 	{ "numa",	"NUMA scheduling and MM benchmarks",		numa_benchmarks		},
Signature · 1 line
2.16.4
Signature · 1 line
- Arnaldo
#2 lore raw
Quoted 5 lines · Arnaldo Carvalho de Melo

You forgot to update tools/perf/Documentation/perf-bench.txt, and please take a look at tools/perf/util/pmu.c convert_scale() to see how to save the current locale, set the one you want, then restore the previous one, so that at the end of this benchmark the environment is back to where it was.

Here's an updated version with the corresponding docs, but I removed the setlocale() - doesn't seem worth it; I hope Mel has no strong objection.

Thanks.

-------8<---------------------------------------------------------- [PATCH v2] tools/perf-bench: Add basic syscall benchmark

The usefulness of having a standard way of testing syscall performance has come up from time to time[0]. Furthermore, some of our testing machinery (such as 'mmtests') already makes use of a simplified version of the microbenchmark. This patch mainly takes the same idea to measure syscall throughput compatible with 'perf-bench' via getppid(2), yet without any of the additional template stuff from Ingo's version (based on numa.c). The code is identical to what mmtests uses.

[0] https://lore.kernel.org/lkml/[email protected]/

---

tools/perf/Documentation/perf-bench.txt | 11 +++++
tools/perf/bench/Build                  |  1 +
tools/perf/bench/bench.h                |  1 +
tools/perf/bench/syscall.c              | 78 +++++++++++++++++++++++++++++++++
tools/perf/builtin-bench.c              |  8 ++++
5 files changed, 99 insertions(+)

create mode 100644 tools/perf/bench/syscall.c

tools/perf/Documentation/perf-bench.txt +0 -0
index 0921a3c67381..8093cafc530a 100644
@@ -49,6 +49,9 @@ SUBSYSTEM

'sched'::
Scheduler and IPC mechanisms.

+'syscall'::
+ System call performance (throughput).
+
'mem'::
Memory access performance.

@@ -134,6 +137,14 @@ Example of *pipe*

                59004 ops/sec

---------------------

+SUITES FOR 'syscall'
+~~~~~~~~~~~~~~~~~~
+*basic*::
+Suite for evaluating performance of core system call throughput (both usecs/op and ops/sec metrics). +This uses a single thread simply doing getppid(2), which is a simple syscall where the result is not +cached by glibc.
+
+
SUITES FOR 'mem'
~~~~~~~~~~~~~~~~
*memcpy*::

tools/perf/bench/Build +0 -0
index e4e321b6f883..839f9b790587 100644
@@ -1,5 +1,6 @@

perf-y += sched-messaging.o
perf-y += sched-pipe.o
+perf-y += syscall.o
perf-y += mem-functions.o
perf-y += futex-hash.o
perf-y += futex-wake.o

tools/perf/bench/bench.h +0 -0
index fddb3ced9db6..31ad3283d41b 100644
@@ -29,6 +29,7 @@

int bench_numa(int argc, const char **argv); int bench_sched_messaging(int argc, const char **argv); int bench_sched_pipe(int argc, const char **argv); +int bench_syscall_basic(int argc, const char **argv); int bench_mem_memcpy(int argc, const char **argv); int bench_mem_memset(int argc, const char **argv); int bench_futex_hash(int argc, const char **argv);

tools/perf/bench/syscall.c new file +78 -0

78 lines not on this page · raw message

tools/perf/builtin-bench.c +1 -0
index 334c77ffc1d9..017029765404 100644
@@ -11,6 +11,7 @@
 * Available benchmark collection list:
 *
 *  sched ... scheduler and IPC performance
+ *  syscall ... System call performance
 *  mem   ... memory access performance
 *  numa  ... NUMA scheduling and MM performance
 *  futex ... Futex performance
@@ -50,6 +51,12 @@ static struct bench sched_benchmarks[] = {
	{ NULL,		NULL,						NULL			}
};

+static struct bench syscall_benchmarks[] = {
+ { "basic", "Benchmark for basic getppid(2) calls", bench_syscall_basic },
+ { "all", "Run all syscall benchmarks", NULL },
+ { NULL, NULL, NULL },
+};
+
static struct bench mem_benchmarks[] = {
{ "memcpy", "Benchmark for memcpy() functions", bench_mem_memcpy },
{ "memset", "Benchmark for memset() functions", bench_mem_memset },
@@ -85,6 +92,7 @@ struct collection {

static struct collection collections[] = {
{ "sched", "Scheduler and IPC benchmarks", sched_benchmarks },
+ { "syscall", "System call benchmarks", syscall_benchmarks },

	{ "mem",	"Memory access benchmarks",			mem_benchmarks		},

#ifdef HAVE_LIBNUMA_SUPPORT
{ "numa", "NUMA scheduling and MM benchmarks", numa_benchmarks },

Signature · 1 line
2.16.4
#3 lore raw
Quoted 10 lines · Davidlohr Bueso
Quoted 5 lines · Arnaldo Carvalho de Melo

You forgot to update tools/perf/Documentation/perf-bench.txt, and please take a look at tools/perf/util/pmu.c convert_scale() to see how to save the current locale, set the one you want, then restore the previous one, so that at the end of this benchmark the environment is back to where it was.

Here's an updated version with the corresponding docs, but I removed the setlocale() - doesn't seem worth it; I hope Mel has no strong objection.

No objection, thanks!

Signature · 2 lines
Mel Gorman
SUSE Labs
#4 lore raw
In reply to Davidlohr Bueso
Quoted 23 lines · Davidlohr Bueso
Quoted 5 lines · Arnaldo Carvalho de Melo

You forgot to update tools/perf/Documentation/perf-bench.txt, and please take a look at tools/perf/util/pmu.c convert_scale() to see how to save the current locale, set the one you want, then restore the previous one, so that at the end of this benchmark the environment is back to where it was.

Here's an updated version with the corresponding docs, but I removed the setlocale() - doesn't seem worth it; I hope Mel has no strong objection.

Thanks.

-------8<---------------------------------------------------------- [PATCH v2] tools/perf-bench: Add basic syscall benchmark

The usefulness of having a standard way of testing syscall performance has come up from time to time[0]. Furthermore, some of our testing machinery (such as 'mmtests') already makes use of a simplified version of the microbenchmark. This patch mainly takes the same idea to measure syscall throughput compatible with 'perf-bench' via getppid(2), yet without any of the additional template stuff from Ingo's version (based on numa.c). The code is identical to what mmtests uses.

Quoted 3 lines

[0] https://lore.kernel.org/lkml/[email protected]/

It would be nice to see this merged. I posted something very similar back in 2016.

Signature · 1 line
Josh
#5 lore raw

Em Thu, May 14, 2020 at 03:39:42PM -0500, Josh Poimboeuf escreveu:

Quoted 24 lines · Davidlohr Bueso
Quoted 23 lines · Arnaldo Carvalho de Melo
Quoted 5 lines

You forgot to update tools/perf/Documentation/perf-bench.txt, and please take a look at tools/perf/util/pmu.c convert_scale() to see how to save the current locale, set the one you want, then restore the previous one, so that at the end of this benchmark the environment is back to where it was.

Here's an updated version with the corresponding docs, but I removed the setlocale() - doesn't seem worth it; I hope Mel has no strong objection.

Thanks.

-------8<---------------------------------------------------------- [PATCH v2] tools/perf-bench: Add basic syscall benchmark

The usefulness of having a standard way of testing syscall performance has come up from time to time[0]. Furthermore, some of our testing machinery (such as 'mmtests') already makes use of a simplified version of the microbenchmark. This patch mainly takes the same idea to measure syscall throughput compatible with 'perf-bench' via getppid(2), yet without any of the additional template stuff from Ingo's version (based on numa.c). The code is identical to what mmtests uses.

Quoted 6 lines
Quoted 3 lines

[0] https://lore.kernel.org/lkml/[email protected]/

It would be nice to see this merged. I posted something very similar back in 2016.

So, I took this as an Acked-by: Josh, and the previous "no objection" from Mel as well, its now in my tmp.perf/core branch while it, together with other stuff goes thru build tests + 'perf test'.

Sorry for the long delay in processing it, I shoudl've noticed that my review comments were addressed in v2.

- Arnaldo