perf bench: Add futex-wake microbenchmark

Block a bunch of threads on a futex and wake them up, 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.

An example run:

  $ perf bench futex wake -t 512 -r 100
  Run summary [PID 27823]: blocking on 512 threads (at futex 0x7e10d4), waking up 1 at a time.

  [Run 1]: Wokeup 512 of 512 threads in 6.0080 ms
  [Run 2]: Wokeup 512 of 512 threads in 5.2280 ms
  [Run 3]: Wokeup 512 of 512 threads in 4.8300 ms
  ...
  [Run 100]: Wokeup 512 of 512 threads in 5.0100 ms
  Wokeup 512 of 512 threads in 5.0109 ms (+-2.25%)

Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Acked-by: Darren Hart <dvhart@linux.intel.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Darren Hart <dvhart@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <Waiman.Long@hp.com>
Link: http://lkml.kernel.org/r/1387081917-9102-3-git-send-email-davidlohr@hp.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 214 insertions, 0 deletions

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 54ae547b4bc4..6fa5d8b74635 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -427,6 +427,7 @@ endif
 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)builtin-diff.o
 BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 34edb5c34db3..6ac3f1d083cc 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -32,6 +32,7 @@ extern int bench_mem_memcpy(int argc, const char **argv,
                             const char *prefix __maybe_unused);
 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);
 
 #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-wake.c
new file mode 100644
index 000000000000..d096169b161e
--- /dev/null
+++ b/tools/perf/bench/futex-wake.c
@@ -0,0 +1,201 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-wake: Block a bunch of threads on a futex and wake'em up, 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.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+/* all threads will block on the same futex */
+static u_int32_t futex1 = 0;
+
+/*
+ * How many wakeups to do at a time.
+ * Default to 1 in order to make the kernel work more.
+ */
+static unsigned int nwakes = 1;
+
+/*
+ * There can be significant variance from run to run,
+ * the more repeats, the more exact the overall avg and
+ * the better idea of the futex latency.
+ */
+static unsigned int repeat = 10;
+
+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 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_END()
+};
+
+static const char * const bench_futex_wake_usage[] = {
+        "perf bench futex wake <options>",
+        NULL
+};
+
+static void *workerfn(void *arg __maybe_unused)
+{
+        pthread_mutex_lock(&thread_lock);
+        threads_starting--;
+        if (!threads_starting)
+                pthread_cond_signal(&thread_parent);
+        pthread_cond_wait(&thread_worker, &thread_lock);
+        pthread_mutex_unlock(&thread_lock);
+
+        futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+        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)
+{
+        cpu_set_t cpu;
+        unsigned int i;
+
+        threads_starting = nthreads;
+
+        /* create and block all threads */
+        for (i = 0; i < nthreads; i++) {
+                CPU_ZERO(&cpu);
+                CPU_SET(i % ncpus, &cpu);
+
+                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+                        err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+                if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+                        err(EXIT_FAILURE, "pthread_create");
+        }
+}
+
+static void toggle_done(int sig __maybe_unused,
+                        siginfo_t *info __maybe_unused,
+                        void *uc __maybe_unused)
+{
+        done = true;
+}
+
+int bench_futex_wake(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);
+        }
+
+        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+        sigfillset(&act.sa_mask);
+        act.sa_sigaction = toggle_done;
+        sigaction(SIGINT, &act, NULL);
+
+        if (!nthreads)
+                nthreads = ncpus;
+
+        worker = calloc(nthreads, sizeof(*worker));
+        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);
+
+        init_stats(&wakeup_stats);
+        init_stats(&waketime_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;
+                struct timeval start, end, runtime;
+
+                /* create, launch & block all threads */
+                block_threads(worker, thread_attr);
+
+                /* make sure all threads are already blocked */
+                pthread_mutex_lock(&thread_lock);
+                while (threads_starting)
+                        pthread_cond_wait(&thread_parent, &thread_lock);
+                pthread_cond_broadcast(&thread_worker);
+                pthread_mutex_unlock(&thread_lock);
+
+                usleep(100000);
+
+                /* Ok, all threads are patiently blocked, start waking folks up */
+                gettimeofday(&start, NULL);
+                while (nwoken != nthreads)
+                        nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG);
+                gettimeofday(&end, NULL);
+                timersub(&end, &start, &runtime);
+
+                update_stats(&wakeup_stats, nwoken);
+                update_stats(&waketime_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);
+                }
+
+                for (i = 0; i < nthreads; i++) {
+                        ret = pthread_join(worker[i], NULL);
+                        if (ret)
+                                err(EXIT_FAILURE, "pthread_join");
+                }
+
+        }
+
+        /* cleanup & report results */
+        pthread_cond_destroy(&thread_parent);
+        pthread_cond_destroy(&thread_worker);
+        pthread_mutex_destroy(&thread_lock);
+        pthread_attr_destroy(&thread_attr);
+
+        print_summary();
+
+        free(worker);
+        return ret;
+}
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index 7d0bda543e3d..6ac45093fac4 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -45,4 +45,14 @@ futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflag
         return futex(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags);
 }
 
+/**
+ * futex_wake() - wake one or more tasks blocked on uaddr
+ * @nr_wake:    wake up to this many tasks
+ */
+static inline int
+futex_wake(u_int32_t *uaddr, int nr_wake, int opflags)
+{
+        return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags);
+}
+
 #endif /* _FUTEX_H */
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index a8b0138fc6a0..743a30a8baa0 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -57,6 +57,7 @@ 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        },
         { "all",        "Test all futex benchmarks",                    NULL                    },
         { NULL,         NULL,                                           NULL                    }
 };