| 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: <20190308181747.l36zqz2avtivrr3c@linux-r8p5>
Date: Fri, 8 Mar 2019 10:17:47 -0800
From: Davidlohr Bueso <dave@...olabs.net>
To: Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>
Cc: Ingo Molnar <mingo@...nel.org>, mgorman@...hsingularity.net,
linux-kernel@...r.kernel.org, Davidlohr Bueso <dbueso@...e.de>,
Namhyung Kim <namhyung@...nel.org>,
Jiri Olsa <jolsa@...nel.org>
Subject: Re: [PATCH] tools/perf-bench: Add basic syscall benchmark
On Thu, 07 Mar 2019, Arnaldo Carvalho de Melo wrote:
>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/20160201074156.GA27156@gmail.com/
Signed-off-by: Davidlohr Bueso <dbueso@...e.de>
---
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
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index 0921a3c67381..8093cafc530a 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -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*::
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index e4e321b6f883..839f9b790587 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -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
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index fddb3ced9db6..31ad3283d41b 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -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);
diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c
new file mode 100644
index 000000000000..409f84a4fe4f
--- /dev/null
+++ b/tools/perf/bench/syscall.c
@@ -0,0 +1,78 @@
+/*
+ *
+ * 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 <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:
+ 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;
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 334c77ffc1d9..017029765404 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -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 },
--
2.16.4
Powered by blists - more mailing lists