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/

Committer notes:

Add mising stdlib.h and unistd.h to get the prototypes for exit() and
getppid().

Committer testing:

  $ perf bench
  Usage:
  	perf bench [<common options>] <collection> <benchmark> [<options>]

          # List of all available benchmark collections:

           sched: Scheduler and IPC benchmarks
         syscall: System call benchmarks
             mem: Memory access benchmarks
            numa: NUMA scheduling and MM benchmarks
           futex: Futex stressing benchmarks
           epoll: Epoll stressing benchmarks
       internals: Perf-internals benchmarks
             all: All benchmarks

  $
  $ perf bench syscall

          # List of available benchmarks for collection 'syscall':

           basic: Benchmark for basic getppid(2) calls
             all: Run all syscall benchmarks

  $ perf bench syscall basic
  # Running 'syscall/basic' benchmark:
  # Executed 10000000 getppid() calls
       Total time: 3.679 [sec]

         0.367957 usecs/op
          2717708 ops/sec
  $ perf bench syscall all
  # Running syscall/basic benchmark...
  # Executed 10000000 getppid() calls
       Total time: 3.644 [sec]

         0.364456 usecs/op
          2743815 ops/sec

  $

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/20190308181747.l36zqz2avtivrr3c@linux-r8p5
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index bad1651..a0529c7 100644 (file)
--- 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.
 
@@ -137,6 +140,14 @@ 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 768e408..560eb97 100644 (file)
--- 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 61cae49..49bc8ed 100644 (file)
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -33,6 +33,7 @@ extern struct timeval bench__start, bench__end, bench__runtime;
 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 (file)
index 0000000..5fe621c
--- /dev/null
+++ b/tools/perf/bench/syscall.c
@@ -0,0 +1,81 @@
+/*
+ *
+ * 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>
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdlib.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 cad31b1..4094cbe 100644 (file)
--- 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
@@ -49,6 +50,12 @@ 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        },
@@ -90,6 +97,7 @@ 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         },