Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S934858AbcJQPdy convert rfc822-to-8bit (ORCPT <rfc822;w@1wt.eu>);
        Mon, 17 Oct 2016 11:33:54 -0400
Received: from Galois.linutronix.de ([146.0.238.70]:37581 "EHLO
        Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S933824AbcJQPdn (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 17 Oct 2016 11:33:43 -0400
Date: Mon, 17 Oct 2016 17:33:31 +0200
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>, Jiri Olsa <jolsa@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>,
        linux-kernel@vger.kernel.org, Davidlohr Bueso <dbueso@suse.de>
Subject: [PATCH 2/2 v2] perf bench futex: add NUMA support
Message-ID: <20161017153331.pkzaij5a3ma5c5s5@linutronix.de>
References: <20161016190803.3392-1-bigeasy@linutronix.de>
 <20161016190803.3392-2-bigeasy@linutronix.de>
 <20161017143821.GO12815@kernel.org>
 <20161017150123.GA18595@krava>
 <20161017150442.GQ12815@kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8BIT
In-Reply-To: <20161017150442.GQ12815@kernel.org>
User-Agent: NeoMutt/20161014 (1.7.1)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Length: 5360
Lines: 175

By default the application uses malloc() and all available CPUs. This
patch introduces NUMA support which means:
- memory is allocated node local via numa_alloc_local()
- all CPUs of the specified NUMA node are used. This is also true if the
  number of threads set is greater than the number of CPUs available on
  this node.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1…v2: use HAVE_LIBNUMA_SUPPORT instead the custom variant

 tools/perf/bench/futex-hash.c | 87 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 77 insertions(+), 10 deletions(-)

diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index d9e5e80bb4d0..17d38ce829f8 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -25,6 +25,9 @@
 
 #include <err.h>
 #include <sys/time.h>
+#ifdef HAVE_LIBNUMA_SUPPORT
+#include <numa.h>
+#endif
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 10;
@@ -32,6 +35,7 @@ static unsigned int nsecs    = 10;
 static unsigned int nfutexes = 1024;
 static bool fshared = false, done = false, silent = false;
 static int futex_flag = 0;
+static int numa_node = -1;
 
 struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
@@ -55,9 +59,28 @@ static const struct option options[] = {
 	OPT_UINTEGER('f', "futexes", &nfutexes, "Specify amount of futexes per threads"),
 	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
 	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
+#ifdef HAVE_LIBNUMA_SUPPORT
+	OPT_INTEGER( 'n', "numa",   &numa_node,  "Specify the NUMA node"),
+#endif
 	OPT_END()
 };
 
+#ifndef HAVE_LIBNUMA_SUPPORT
+static int numa_run_on_node(int node __maybe_unused) { return 0; }
+static int numa_node_of_cpu(int node __maybe_unused) { return 0; }
+static void *numa_alloc_local(size_t size) { return malloc(size); }
+static void numa_free(void *p, size_t size __maybe_unused) { return free(p); }
+#endif
+
+static bool cpu_is_local(int cpu)
+{
+	if (numa_node < 0)
+		return true;
+	if (numa_node_of_cpu(cpu) == numa_node)
+		return true;
+	return false;
+}
+
 static const char * const bench_futex_hash_usage[] = {
 	"perf bench futex hash <options>",
 	NULL
@@ -123,6 +146,8 @@ int bench_futex_hash(int argc, const char **argv,
 	unsigned int i, ncpus;
 	pthread_attr_t thread_attr;
 	struct worker *worker = NULL;
+	char *node_str = NULL;
+	unsigned int cpunum;
 
 	argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
 	if (argc) {
@@ -136,18 +161,50 @@ int bench_futex_hash(int argc, const char **argv,
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	if (!nthreads) /* default to the number of CPUs */
-		nthreads = ncpus;
+	if (!nthreads) {
+		/* default to the number of CPUs per NUMA node */
+		if (numa_node < 0) {
+			nthreads = ncpus;
+		} else {
+			for (i = 0; i < ncpus; i++) {
+				if (cpu_is_local(i))
+					nthreads++;
+			}
+			if (!nthreads)
+				err(EXIT_FAILURE, "No online CPUs for this node");
+		}
+	} else {
+		int cpu_available = 0;
 
-	worker = calloc(nthreads, sizeof(*worker));
+		for (i = 0; i < ncpus && !cpu_available; i++) {
+			if (cpu_is_local(i))
+				cpu_available = 1;
+		}
+		if (!cpu_available)
+			err(EXIT_FAILURE, "No online CPUs for this node");
+	}
+
+	if (numa_node >= 0) {
+		ret = numa_run_on_node(numa_node);
+		if (ret < 0)
+			err(EXIT_FAILURE, "numa_run_on_node");
+		ret = asprintf(&node_str, " on node %d", numa_node);
+		if (ret < 0)
+			err(EXIT_FAILURE, "numa_node, asprintf");
+	}
+
+	worker = numa_alloc_local(nthreads * sizeof(*worker));
 	if (!worker)
 		goto errmem;
 
 	if (!fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
-	printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
-	       getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs);
+	printf("Run summary [PID %d]: %d threads%s, each operating on %d [%s] futexes for %d secs.\n\n",
+	       getpid(), nthreads,
+	       node_str ? : "",
+	       nfutexes, fshared ? "shared":"private",
+	       nsecs);
 
 	init_stats(&throughput_stats);
 	pthread_mutex_init(&thread_lock, NULL);
@@ -157,14 +214,24 @@ int bench_futex_hash(int argc, const char **argv,
 	threads_starting = nthreads;
 	pthread_attr_init(&thread_attr);
 	gettimeofday(&start, NULL);
-	for (i = 0; i < nthreads; i++) {
+	for (cpunum = 0, i = 0; i < nthreads; i++, cpunum++) {
+
+		do {
+			if (cpu_is_local(cpunum))
+				break;
+			cpunum++;
+			if (cpunum > ncpus)
+				cpunum = 0;
+		} while (1);
+
 		worker[i].tid = i;
-		worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex));
+		worker[i].futex = numa_alloc_local(nfutexes *
+						   sizeof(*worker[i].futex));
 		if (!worker[i].futex)
 			goto errmem;
 
 		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_SET(cpunum % ncpus, &cpu);
 
 		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu);
 		if (ret)
@@ -211,12 +278,12 @@ int bench_futex_hash(int argc, const char **argv,
 				       &worker[i].futex[nfutexes-1], t);
 		}
 
-		free(worker[i].futex);
+		numa_free(worker[i].futex, nfutexes * sizeof(*worker[i].futex));
 	}
 
 	print_summary();
 
-	free(worker);
+	numa_free(worker, nthreads * sizeof(*worker));
 	return ret;
 errmem:
 	err(EXIT_FAILURE, "calloc");
-- 
2.9.3