All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
	Petr Mladek <pmladek@suse.com>,
	Andrey Zhizhikin <andrey.z@gmail.com>,
	Kefeng Wang <wangkefeng.wang@huawei.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Kan Liang <kan.liang@linux.intel.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Cc: Stephane Eranian <eranian@google.com>, Ian Rogers <irogers@google.com>
Subject: [PATCH 1/5] perf bench: add event synthesis benchmark
Date: Wed,  1 Apr 2020 16:39:41 -0700	[thread overview]
Message-ID: <20200401233945.133550-2-irogers@google.com> (raw)
In-Reply-To: <20200401233945.133550-1-irogers@google.com>

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.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/bench/Build        |   2 +-
 tools/perf/bench/bench.h      |   2 +-
 tools/perf/bench/synthesize.c | 101 ++++++++++++++++++++++++++++++++++
 tools/perf/builtin-bench.c    |   6 ++
 4 files changed, 109 insertions(+), 2 deletions(-)
 create mode 100644 tools/perf/bench/synthesize.c

diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index e4e321b6f883..042827385c87 100644
--- a/tools/perf/bench/Build
+++ b/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
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 4aa6de1aa67d..4d669c803237 100644
--- a/tools/perf/bench/bench.h
+++ b/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
diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c
new file mode 100644
index 000000000000..6291257bc9c9
--- /dev/null
+++ b/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;
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index c06fe21c8613..11c79a8d85d6 100644
--- a/tools/perf/builtin-bench.c
+++ b/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			}
 };
-- 
2.26.0.rc2.310.g2932bb562d-goog

  reply	other threads:[~2020-04-01 23:39 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-01 23:39 [PATCH 0/5] Benchmark and improve event synthesis performance Ian Rogers
2020-04-01 23:39 ` Ian Rogers [this message]
2020-04-02 13:41   ` [PATCH 1/5] perf bench: add event synthesis benchmark Jiri Olsa
2020-04-01 23:39 ` [PATCH 2/5] tools api fs: make xxx__mountpoint() more scalable Ian Rogers
2020-04-01 23:39 ` [PATCH 3/5] perf synthetic-events: save 4kb from 2 stack frames Ian Rogers
2020-04-01 23:39 ` [PATCH 4/5] tools api: add a lightweight buffered reading api Ian Rogers
2020-04-02 13:41   ` Jiri Olsa
2020-04-01 23:39 ` [PATCH 5/5] perf synthetic events: Remove use of sscanf from /proc reading Ian Rogers
2020-04-02 13:40   ` Jiri Olsa
2020-04-02 13:41   ` Jiri Olsa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200401233945.133550-2-irogers@google.com \
    --to=irogers@google.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=andrey.z@gmail.com \
    --cc=eranian@google.com \
    --cc=jolsa@redhat.com \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=pmladek@suse.com \
    --cc=tglx@linutronix.de \
    --cc=wangkefeng.wang@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.