[PATCH] perf: add 'perf bench syscall'

[Josh Poimboeuf]

On Wed, Feb 03, 2016 at 11:22:47AM +0100, Ingo Molnar wrote:
> 
> * Andy Lutomirski <luto@xxxxxxxxxxxxxx> wrote:
> 
> > On Jan 31, 2016 11:42 PM, "Ingo Molnar" <mingo@xxxxxxxxxx> wrote:
> > >
> > >
> > > * riel@xxxxxxxxxx <riel@xxxxxxxxxx> wrote:
> > >
> > > > (v3: address comments raised by Frederic)
> > > >
> > > > Running with nohz_full introduces a fair amount of overhead.
> > > > Specifically, various things that are usually done from the
> > > > timer interrupt are now done at syscall, irq, and guest
> > > > entry and exit times.
> > > >
> > > > However, some of the code that is called every single time
> > > > has only ever worked at jiffy resolution. The code in
> > > > __acct_update_integrals was also doing some unnecessary
> > > > calculations.
> > > >
> > > > Getting rid of the unnecessary calculations, without
> > > > changing any of the functionality in __acct_update_integrals
> > > > gets us about an 11% win.
> > > >
> > > > Not calling the time statistics updating code more than
> > > > once per jiffy, like is done on housekeeping CPUs and on
> > > > all the CPUs of a non-nohz_full system, shaves off a
> > > > further 30%.
> > > >
> > > > I tested this series with a microbenchmark calling
> > > > an invalid syscall number ten million times in a row,
> > > > on a nohz_full cpu.
> > > >
> > > >     Run times for the microbenchmark:
> > > >
> > > > 4.4                           3.8 seconds
> > > > 4.5-rc1                               3.7 seconds
> > > > 4.5-rc1 + first patch         3.3 seconds
> > > > 4.5-rc1 + first 3 patches     3.1 seconds
> > > > 4.5-rc1 + all patches         2.3 seconds
> > >
> > > Another suggestion (beyond fixing the 32-bit build ;-), could you please stick
> > > your syscall microbenchmark into 'perf bench', so that we have a standardized way
> > > of checking such numbers?
> > >
> > > In fact I'd suggest we introduce an entirely new sub-tool for system call
> > > performance measurement - and this might be the first functionality of it.
> > >
> > > I've attached a quick patch that is basically a copy of 'perf bench numa' and
> > > which measures getppid() performance (simple syscall where the result is not
> > > cached by glibc).
> > >
> > > I kept the process, threading and memory allocation bits of numa.c, just in case
> > > we need them to measure more complex syscalls. Maybe we could keep the threading
> > > bits and remove the memory allocation parameters, to simplify the benchmark?
> > >
> > > Anyway, this could be a good base to start off on.
> > 
> > So much code...
> 
> Arguably 90% of that should be factored out, as it's now a duplicate between 
> bench/numa.c and bench/syscall.c.
> 
> Technically, for a minimum benchmark, something like this would already be 
> functional for tools/perf/bench/syscall.c:
> 
> #include "../perf.h"
> #include "../util/util.h"
> #include "../builtin.h"
> #include "bench.h"
> 
> static void run_syscall_benchmark(void)
> {
> 	[ .... your benchmark loop as-is ... ]
> }
> 
> int bench_syscall(int argc __maybe_unused, const char **argv __maybe_unused, const char *prefix __maybe_unused)
> {
> 	run_syscall_benchmark();
> 
>         switch (bench_format) {
>         case BENCH_FORMAT_DEFAULT:
>                 printf("print results in human-readable format\n");
>                 break;
>         case BENCH_FORMAT_SIMPLE:
>                 printf("print results in machine-parseable format\n");
>                 break;
>         default:
> 		BUG_ON(1);
>         }
> 
> 	return 0;
> }
> 
> Plus the small amount of glue for bench_sycall() I sent in the first patch.
> 
> Completely untested.
> 
> If the loop is long enough then even without any timing measurement this would be 
> usable via:
> 
> 	perf stat --null --repeat 10 perf bench syscall
> 
> as the 'perf stat' will do the timing and statistics.

How about this:

--------

From: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Subject: [PATCH] perf: add 'perf bench syscall'

Add a basic 'perf bench syscall' benchmark which does a getppid() system
call in a tight loop.

Suggested-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
---
 tools/perf/bench/Build     |  1 +
 tools/perf/bench/bench.h   |  1 +
 tools/perf/bench/syscall.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/builtin-bench.c | 18 ++++++++---
 4 files changed, 95 insertions(+), 5 deletions(-)
 create mode 100644 tools/perf/bench/syscall.c

diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 60bf119..0b7395d 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 579a592..bdd6cdc 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -28,6 +28,7 @@
 int bench_numa(int argc, const char **argv, const char *prefix);
 int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 int bench_sched_pipe(int argc, const char **argv, const char *prefix);
+int bench_syscall_basic(int argc, const char **argv, const char *prefix);
 int bench_mem_memcpy(int argc, const char **argv, const char *prefix);
 int bench_mem_memset(int argc, const char **argv, const char *prefix);
 int bench_futex_hash(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c
new file mode 100644
index 0000000..0dc782a
--- /dev/null
+++ b/tools/perf/bench/syscall.c
@@ -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, const char *prefix __maybe_unused)
+{
+	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;
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index a1cddc6..f32a503 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -9,10 +9,11 @@
 /*
  * Available benchmark collection list:
  *
- *  sched ... scheduler and IPC performance
- *  mem   ... memory access performance
- *  numa  ... NUMA scheduling and MM performance
- *  futex ... Futex performance
+ *  sched   ... Scheduler and IPC performance
+ *  syscall ... System call performance
+ *  mem     ... Memory access performance
+ *  numa    ... NUMA scheduling and MM performance
+ *  futex   ... Futex performance
  */
 #include "perf.h"
 #include "util/util.h"
@@ -44,10 +45,16 @@ static struct bench numa_benchmarks[] = {
 static struct bench sched_benchmarks[] = {
 	{ "messaging",	"Benchmark for scheduling and IPC",		bench_sched_messaging	},
 	{ "pipe",	"Benchmark for pipe() between two processes",	bench_sched_pipe	},
-	{ "all",	"Run all scheduler benchmarks",		NULL			},
+	{ "all",	"Run all scheduler benchmarks",			NULL			},
 	{ 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	},
@@ -74,6 +81,7 @@ 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		},
-- 
2.4.11