perf bench: Add event synthesis benchmark

Event synthesis may occur at the start or end (tail) of a perf command.
In system-wide mode it can scan every process in /proc, which may add
seconds of latency before event recording. Add a new benchmark that
times how long event synthesis takes with and without data synthesis.

An example execution looks like:

 $ perf bench internals synthesize
 # Running 'internals/synthesize' benchmark:
 Average synthesis took: 168.253800 usec
 Average data synthesis took: 208.104700 usec

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrey Zhizhikin <andrey.z@gmail.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lore.kernel.org/lkml/20200402154357.107873-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-bench.txt

@@ -61,6 +61,9 @@ SUBSYSTEM
 'epoll'::
 	Eventpoll (epoll) stressing benchmarks.
 
+'internals'::
+	Benchmark internal perf functionality.
+
 'all'::
 	All benchmark subsystems.
 
@@ -214,6 +217,11 @@ Suite for evaluating concurrent epoll_wait calls.
 *ctl*::
 Suite for evaluating multiple epoll_ctl calls.
 
+SUITES FOR 'internals'
+~~~~~~~~~~~~~~~~~~~~~~
+*synthesize*::
+Suite for evaluating perf's event synthesis performance.
+
 SEE ALSO
 --------
 linkperf:perf[1]

tools/perf/bench/Build

@@ -6,9 +6,9 @@ perf-y += futex-wake.o
 perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 perf-y += futex-lock-pi.o
-
 perf-y += epoll-wait.o
 perf-y += epoll-ctl.o
+perf-y += synthesize.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o

tools/perf/bench/bench.h

@@ -41,9 +41,9 @@ int bench_futex_wake_parallel(int argc, const char **argv);
 int bench_futex_requeue(int argc, const char **argv);
 /* pi futexes */
 int bench_futex_lock_pi(int argc, const char **argv);
-
 int bench_epoll_wait(int argc, const char **argv);
 int bench_epoll_ctl(int argc, const char **argv);
+int bench_synthesize(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0

tools/perf/bench/synthesize.c

@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Benchmark synthesis of perf events such as at the start of a 'perf
+ * record'. Synthesis is done on the current process and the 'dummy' event
+ * handlers are invoked that support dump_trace but otherwise do nothing.
+ *
+ * Copyright 2019 Google LLC.
+ */
+#include <stdio.h>
+#include "bench.h"
+#include "../util/debug.h"
+#include "../util/session.h"
+#include "../util/synthetic-events.h"
+#include "../util/target.h"
+#include "../util/thread_map.h"
+#include "../util/tool.h"
+#include <linux/err.h>
+#include <linux/time64.h>
+#include <subcmd/parse-options.h>
+
+static unsigned int iterations = 10000;
+
+static const struct option options[] = {
+	OPT_UINTEGER('i', "iterations", &iterations,
+		"Number of iterations used to compute average"),
+	OPT_END()
+};
+
+static const char *const usage[] = {
+	"perf bench internals synthesize <options>",
+	NULL
+};
+
+
+static int do_synthesize(struct perf_session *session,
+			struct perf_thread_map *threads,
+			struct target *target, bool data_mmap)
+{
+	const unsigned int nr_threads_synthesize = 1;
+	struct timeval start, end, diff;
+	u64 runtime_us;
+	unsigned int i;
+	double average;
+	int err;
+
+	gettimeofday(&start, NULL);
+	for (i = 0; i < iterations; i++) {
+		err = machine__synthesize_threads(&session->machines.host,
+						target, threads, data_mmap,
+						nr_threads_synthesize);
+		if (err)
+			return err;
+	}
+
+	gettimeofday(&end, NULL);
+	timersub(&end, &start, &diff);
+	runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec;
+	average = (double)runtime_us/(double)iterations;
+	printf("Average %ssynthesis took: %f usec\n",
+		data_mmap ? "data " : "", average);
+	return 0;
+}
+
+int bench_synthesize(int argc, const char **argv)
+{
+	struct perf_tool tool;
+	struct perf_session *session;
+	struct target target = {
+		.pid = "self",
+	};
+	struct perf_thread_map *threads;
+	int err;
+
+	argc = parse_options(argc, argv, options, usage, 0);
+
+	session = perf_session__new(NULL, false, NULL);
+	if (IS_ERR(session)) {
+		pr_err("Session creation failed.\n");
+		return PTR_ERR(session);
+	}
+	threads = thread_map__new_by_pid(getpid());
+	if (!threads) {
+		pr_err("Thread map creation failed.\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+	perf_tool__fill_defaults(&tool);
+
+	err = do_synthesize(session, threads, &target, false);
+	if (err)
+		goto err_out;
+
+	err = do_synthesize(session, threads, &target, true);
+
+err_out:
+	if (threads)
+		perf_thread_map__put(threads);
+
+	perf_session__delete(session);
+	return err;
+}

tools/perf/builtin-bench.c

@@ -76,6 +76,11 @@ static struct bench epoll_benchmarks[] = {
 };
 #endif // HAVE_EVENTFD
 
+static struct bench internals_benchmarks[] = {
+	{ "synthesize", "Benchmark perf event synthesis",	bench_synthesize	},
+	{ NULL,		NULL,					NULL			}
+};
+
 struct collection {
 	const char	*name;
 	const char	*summary;
@@ -92,6 +97,7 @@ static struct collection collections[] = {
 #ifdef HAVE_EVENTFD
 	{"epoll",       "Epoll stressing benchmarks",                   epoll_benchmarks        },
 #endif
+	{ "internals",	"Perf-internals benchmarks",			internals_benchmarks	},
 	{ "all",	"All benchmarks",				NULL			},
 	{ NULL,		NULL,						NULL			}
 };