From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>, Thomas Gleixner <tglx@linutronix.de>
Cc: Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
Clark Williams <williams@redhat.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
Ian Rogers <irogers@google.com>, Jiri Olsa <jolsa@redhat.com>,
Arnaldo Carvalho de Melo <acme@redhat.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Andrey Zhizhikin <andrey.z@gmail.com>,
Kan Liang <kan.liang@linux.intel.com>,
Kefeng Wang <wangkefeng.wang@huawei.com>,
Mark Rutland <mark.rutland@arm.com>,
Peter Zijlstra <peterz@infradead.org>,
Petr Mladek <pmladek@suse.com>,
Stephane Eranian <eranian@google.com>
Subject: [PATCH 18/60] perf bench: Add event synthesis benchmark
Date: Mon, 20 Apr 2020 08:52:34 -0300 [thread overview]
Message-ID: <20200420115316.18781-19-acme@kernel.org> (raw)
In-Reply-To: <20200420115316.18781-1-acme@kernel.org>
From: Ian Rogers <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.
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 | 8 ++
tools/perf/bench/Build | 2 +-
tools/perf/bench/bench.h | 2 +-
tools/perf/bench/synthesize.c | 101 ++++++++++++++++++++++++
tools/perf/builtin-bench.c | 6 ++
5 files changed, 117 insertions(+), 2 deletions(-)
create mode 100644 tools/perf/bench/synthesize.c
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index 0921a3c67381..bad16512c48d 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/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]
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 }
};
--
2.21.1
next prev parent reply other threads:[~2020-04-20 11:55 UTC|newest]
Thread overview: 70+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-20 11:52 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 01/60] perf stat: Honour --timeout for forked workloads Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 02/60] perf tools: Synthesize bpf_trampoline/dispatcher ksymbol event Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 03/60] perf machine: Set ksymbol dso as loaded on arrival Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 04/60] perf annotate: Add basic support for bpf_image Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 05/60] capabilities: Introduce CAP_PERFMON to kernel and user space Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 06/60] perf/core: Open access to the core for CAP_PERFMON privileged process Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 07/60] perf/core: open access to probes " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 08/60] perf tools: Support CAP_PERFMON capability Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 09/60] drm/i915/perf: Open access for CAP_PERFMON privileged process Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 10/60] trace/bpf_trace: " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 11/60] powerpc/perf: open " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 12/60] parisc/perf: " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 13/60] drivers/perf: Open " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 14/60] drivers/oprofile: " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 15/60] doc/admin-guide: Update perf-security.rst with CAP_PERFMON information Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 16/60] doc/admin-guide: update kernel.rst " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 17/60] perf script: Simplify auxiliary event printing functions Arnaldo Carvalho de Melo
2020-04-20 11:52 ` Arnaldo Carvalho de Melo [this message]
2020-04-20 11:52 ` [PATCH 19/60] tools api fs: Make xxx__mountpoint() more scalable Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 20/60] perf synthetic-events: save 4kb from 2 stack frames Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 21/60] perf expr: Add expr_ prefix for parse_ctx and parse_id Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 22/60] perf expr: Add expr_scanner_ctx object Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 23/60] perf metrictroup: Split the metricgroup__add_metric function Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 24/60] perf script: Add flamegraph.py script Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 25/60] perf auxtrace: Add ->evsel_is_auxtrace() callback Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 26/60] perf intel-pt: Implement " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 27/60] perf intel-bts: " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 28/60] perf arm-spe: " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 29/60] perf cs-etm: " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 30/60] perf s390-cpumsf: " Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 31/60] perf auxtrace: For reporting purposes, un-group AUX area event Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 32/60] perf auxtrace: Add an option to synthesize callchains for regular events Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 33/60] perf thread-stack: Add thread_stack__sample_late() Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 34/60] perf evsel: Be consistent when looking which evsel PERF_SAMPLE_ bits are set Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 35/60] perf evsel: Add support for synthesized sample type Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 36/60] perf intel-pt: Add support for synthesizing callchains for regular events Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 37/60] perf evsel: Move and globalize perf_evsel__find_pmu() and perf_evsel__is_aux_event() Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 38/60] perf evlist: Move leader-sampling configuration Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 39/60] perf evsel: Rearrange perf_evsel__config_leader_sampling() Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 40/60] perf evlist: Allow multiple read formats Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 41/60] perf tools: Add support for leader-sampling with AUX area events Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 42/60] perf stat: Force error in fallback on :k events Arnaldo Carvalho de Melo
2020-04-20 11:52 ` [PATCH 43/60] tools lib traceevent: Take care of return value of asprintf Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 44/60] perf pmu: Add support for PMU capabilities Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 45/60] perf doc: allow ASCIIDOC_EXTRA to be an argument Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 46/60] perf parser: Add support to specify rXXX event with pmu Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 47/60] perf header: Support CPU PMU capabilities Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 48/60] perf machine: Remove the indent in resolve_lbr_callchain_sample Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 49/60] perf machine: Refine the function for LBR call stack reconstruction Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 50/60] perf machine: Factor out lbr_callchain_add_kernel_ip() Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 51/60] perf machine: Factor out lbr_callchain_add_lbr_ip() Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 52/60] perf thread: Add a knob for LBR stitch approach Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 53/60] perf thread: Save previous sample for LBR stitching approach Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 54/60] perf callchain: Save previous cursor nodes " Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 55/60] perf callchain: Stitch LBR call stack Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 56/60] perf report: Add option to enable the LBR stitching approach Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 57/60] perf script: " Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 58/60] perf top: " Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 59/60] perf c2c: " Arnaldo Carvalho de Melo
2020-04-20 11:53 ` [PATCH 60/60] perf hist: Add fast path for duplicate entries check Arnaldo Carvalho de Melo
2020-04-22 12:09 ` [GIT PULL] perf/core improvements and fixes Ingo Molnar
2020-04-23 21:28 ` Daniel Díaz
2020-04-24 13:07 ` Arnaldo Carvalho de Melo
2020-04-24 14:10 ` Andreas Gerstmayr
2020-05-04 19:07 ` Daniel Díaz
2020-05-05 16:37 ` Arnaldo Carvalho de Melo
2020-05-05 16:57 ` Daniel Díaz
2020-05-05 17:03 ` Arnaldo Carvalho de Melo
2020-05-08 13:04 ` [tip: perf/core] perf flamegraph: Use /bin/bash for report and record scripts tip-bot2 for Arnaldo Carvalho de Melo
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=20200420115316.18781-19-acme@kernel.org \
--to=acme@kernel.org \
--cc=acme@redhat.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=andrey.z@gmail.com \
--cc=eranian@google.com \
--cc=irogers@google.com \
--cc=jolsa@kernel.org \
--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@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=pmladek@suse.com \
--cc=tglx@linutronix.de \
--cc=wangkefeng.wang@huawei.com \
--cc=williams@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).