[tip:perf/core] perf bench: Add futex-requeue microbenchmark

From: tip-bot for Davidlohr Bueso
Date: Tue Mar 18 2014 - 04:39:15 EST


Commit-ID: 0fb298cf95c0d8119557b7d4657724a146e0622e
Gitweb: http://git.kernel.org/tip/0fb298cf95c0d8119557b7d4657724a146e0622e
Author: Davidlohr Bueso <davidlohr@xxxxxx>
AuthorDate: Sat, 14 Dec 2013 20:31:57 -0800
Committer: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Fri, 14 Mar 2014 11:20:44 -0300

perf bench: Add futex-requeue microbenchmark

Block a bunch of threads on a futex and requeue them on another, N at a
time.

This program is particularly useful to measure the latency of nthread
requeues without waking up any tasks -- thus mimicking a regular
futex_wait.

An example run:

$ perf bench futex requeue -r 100 -t 64
Run summary [PID 151011]: Requeuing 64 threads (from 0x7d15c4 to 0x7d15c8), 1 at a time.

[Run 1]: Requeued 64 of 64 threads in 0.0400 ms
[Run 2]: Requeued 64 of 64 threads in 0.0390 ms
[Run 3]: Requeued 64 of 64 threads in 0.0400 ms
...
[Run 100]: Requeued 64 of 64 threads in 0.0390 ms
Requeued 64 of 64 threads in 0.0399 ms (+-0.37%)

Signed-off-by: Davidlohr Bueso <davidlohr@xxxxxx>
Acked-by: Darren Hart <dvhart@xxxxxxxxxxxxxxx>
Cc: Aswin Chandramouleeswaran <aswin@xxxxxx>
Cc: Darren Hart <dvhart@xxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Jason Low <jason.low2@xxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Scott J Norton <scott.norton@xxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Waiman Long <Waiman.Long@xxxxxx>
Link: http://lkml.kernel.org/r/1387081917-9102-4-git-send-email-davidlohr@xxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/Makefile.perf | 1 +
tools/perf/bench/bench.h | 1 +
tools/perf/bench/{futex-wake.c => futex-requeue.c} | 108 +++++++++++----------
tools/perf/bench/futex.h | 13 +++
tools/perf/builtin-bench.c | 1 +
5 files changed, 75 insertions(+), 49 deletions(-)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 6fa5d8b..50d875d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -428,6 +428,7 @@ BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o

BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 6ac3f1d..eba4670 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -33,6 +33,7 @@ extern int bench_mem_memcpy(int argc, const char **argv,
extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
+extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);

#define BENCH_FORMAT_DEFAULT_STR "default"
#define BENCH_FORMAT_DEFAULT 0
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-requeue.c
similarity index 57%
copy from tools/perf/bench/futex-wake.c
copy to tools/perf/bench/futex-requeue.c
index d096169..a1625587 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -1,11 +1,11 @@
/*
* Copyright (C) 2013 Davidlohr Bueso <davidlohr@xxxxxx>
*
- * futex-wake: Block a bunch of threads on a futex and wake'em up, N at a time.
+ * futex-requeue: Block a bunch of threads on futex1 and requeue them
+ * on futex2, N at a time.
*
- * This program is particularly useful to measure the latency of nthread wakeups
- * in non-error situations: all waiters are queued and all wake calls wakeup
- * one or more tasks, and thus the waitqueue is never empty.
+ * This program is particularly useful to measure the latency of nthread
+ * requeues without waking up any tasks -- thus mimicking a regular futex_wait.
*/

#include "../perf.h"
@@ -21,14 +21,13 @@
#include <sys/time.h>
#include <pthread.h>

-/* all threads will block on the same futex */
-static u_int32_t futex1 = 0;
+static u_int32_t futex1 = 0, futex2 = 0;

/*
- * How many wakeups to do at a time.
+ * How many tasks to requeue at a time.
* Default to 1 in order to make the kernel work more.
*/
-static unsigned int nwakes = 1;
+static unsigned int nrequeue = 1;

/*
* There can be significant variance from run to run,
@@ -37,26 +36,39 @@ static unsigned int nwakes = 1;
*/
static unsigned int repeat = 10;

-pthread_t *worker;
+static pthread_t *worker;
static bool done = 0, silent = 0;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
-static struct stats waketime_stats, wakeup_stats;
+static struct stats requeuetime_stats, requeued_stats;
static unsigned int ncpus, threads_starting, nthreads = 0;

static const struct option options[] = {
- OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
- OPT_UINTEGER('w', "nwakes", &nwakes, "Specify amount of threads to wake at once"),
- OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"),
- OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
+ OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+ OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
+ OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"),
+ OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
OPT_END()
};

-static const char * const bench_futex_wake_usage[] = {
- "perf bench futex wake <options>",
+static const char * const bench_futex_requeue_usage[] = {
+ "perf bench futex requeue <options>",
NULL
};

+static void print_summary(void)
+{
+ double requeuetime_avg = avg_stats(&requeuetime_stats);
+ double requeuetime_stddev = stddev_stats(&requeuetime_stats);
+ unsigned int requeued_avg = avg_stats(&requeued_stats);
+
+ printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
+ requeued_avg,
+ nthreads,
+ requeuetime_avg/1e3,
+ rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
+}
+
static void *workerfn(void *arg __maybe_unused)
{
pthread_mutex_lock(&thread_lock);
@@ -70,19 +82,6 @@ static void *workerfn(void *arg __maybe_unused)
return NULL;
}

-static void print_summary(void)
-{
- double waketime_avg = avg_stats(&waketime_stats);
- double waketime_stddev = stddev_stats(&waketime_stats);
- unsigned int wakeup_avg = avg_stats(&wakeup_stats);
-
- printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n",
- wakeup_avg,
- nthreads,
- waketime_avg/1e3,
- rel_stddev_stats(waketime_stddev, waketime_avg));
-}
-
static void block_threads(pthread_t *w,
pthread_attr_t thread_attr)
{
@@ -111,19 +110,17 @@ static void toggle_done(int sig __maybe_unused,
done = true;
}

-int bench_futex_wake(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int bench_futex_requeue(int argc, const char **argv,
+ const char *prefix __maybe_unused)
{
int ret = 0;
unsigned int i, j;
struct sigaction act;
pthread_attr_t thread_attr;

- argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
- if (argc) {
- usage_with_options(bench_futex_wake_usage, options);
- exit(EXIT_FAILURE);
- }
+ argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
+ if (argc)
+ goto err;

ncpus = sysconf(_SC_NPROCESSORS_ONLN);

@@ -138,19 +135,19 @@ int bench_futex_wake(int argc, const char **argv,
if (!worker)
err(EXIT_FAILURE, "calloc");

- printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
- "waking up %d at a time.\n\n",
- getpid(), nthreads, &futex1, nwakes);
+ printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
+ "%d at a time.\n\n",
+ getpid(), nthreads, &futex1, &futex2, nrequeue);

- init_stats(&wakeup_stats);
- init_stats(&waketime_stats);
+ init_stats(&requeued_stats);
+ init_stats(&requeuetime_stats);
pthread_attr_init(&thread_attr);
pthread_mutex_init(&thread_lock, NULL);
pthread_cond_init(&thread_parent, NULL);
pthread_cond_init(&thread_worker, NULL);

for (j = 0; j < repeat && !done; j++) {
- unsigned int nwoken = 0;
+ unsigned int nrequeued = 0;
struct timeval start, end, runtime;

/* create, launch & block all threads */
@@ -165,21 +162,31 @@ int bench_futex_wake(int argc, const char **argv,

usleep(100000);

- /* Ok, all threads are patiently blocked, start waking folks up */
+ /* Ok, all threads are patiently blocked, start requeueing */
gettimeofday(&start, NULL);
- while (nwoken != nthreads)
- nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG);
+ for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+ /*
+ * Do not wakeup any tasks blocked on futex1, allowing
+ * us to really measure futex_wait functionality.
+ */
+ futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
+ FUTEX_PRIVATE_FLAG);
gettimeofday(&end, NULL);
timersub(&end, &start, &runtime);

- update_stats(&wakeup_stats, nwoken);
- update_stats(&waketime_stats, runtime.tv_usec);
+ update_stats(&requeued_stats, nrequeued);
+ update_stats(&requeuetime_stats, runtime.tv_usec);

if (!silent) {
- printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n",
- j + 1, nwoken, nthreads, runtime.tv_usec/1e3);
+ printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
+ j + 1, nrequeued, nthreads, runtime.tv_usec/1e3);
}

+ /* everybody should be blocked on futex2, wake'em up */
+ nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+ if (nthreads != nrequeued)
+ warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
+
for (i = 0; i < nthreads; i++) {
ret = pthread_join(worker[i], NULL);
if (ret)
@@ -198,4 +205,7 @@ int bench_futex_wake(int argc, const char **argv,

free(worker);
return ret;
+err:
+ usage_with_options(bench_futex_requeue_usage, options);
+ exit(EXIT_FAILURE);
}
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index 6ac4509..71f2844 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -55,4 +55,17 @@ futex_wake(u_int32_t *uaddr, int nr_wake, int opflags)
return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags);
}

+/**
+* futex_cmp_requeue() - requeue tasks from uaddr to uaddr2
+* @nr_wake: wake up to this many tasks
+* @nr_requeue: requeue up to this many tasks
+*/
+static inline int
+futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake,
+ int nr_requeue, int opflags)
+{
+ return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
+ val, opflags);
+}
+
#endif /* _FUTEX_H */
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 743a30a..f600b74 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -58,6 +58,7 @@ static struct bench mem_benchmarks[] = {
static struct bench futex_benchmarks[] = {
{ "hash", "Benchmark for futex hash table", bench_futex_hash },
{ "wake", "Benchmark for futex wake calls", bench_futex_wake },
+ { "requeue", "Benchmark for futex requeue calls", bench_futex_requeue },
{ "all", "Test all futex benchmarks", NULL },
{ NULL, NULL, NULL }
};
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/