diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index bbd27d89b50a..ddfb3e10e88c 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -82,7 +82,7 @@ Be multi thread instead of multi process
 Specify number of groups
 
 -l::
---loop=::
+--nr_loops=::
 Specify number of loops
 
 Example of *messaging*
@@ -149,8 +149,8 @@ Specify routine to copy (default: default).
 Available routines are depend on the architecture.
 On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
 
--i::
---iterations::
+-l::
+--nr_loops::
 Repeat memcpy invocation this number of times.
 
 -c::
@@ -173,8 +173,8 @@ Specify routine to set (default: default).
 Available routines are depend on the architecture.
 On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
 
--i::
---iterations::
+-l::
+--nr_loops::
 Repeat memset invocation this number of times.
 
 -c::
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 8d980d4a64e5..c5dfabdbd8d0 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -25,20 +25,20 @@
 
 static const char	*size_str	= "1MB";
 static const char	*routine_str	= "all";
-static int		iterations	= 1;
+static int		nr_loops	= 1;
 static bool		use_cycles;
 static int		cycles_fd;
 
 static const struct option options[] = {
-	OPT_STRING('l', "size", &size_str, "1MB",
+	OPT_STRING('s', "size", &size_str, "1MB",
 		    "Specify the size of the memory buffers. "
 		    "Available units: B, KB, MB, GB and TB (case insensitive)"),
 
 	OPT_STRING('r', "routine", &routine_str, "all",
 		    "Specify the routine to run, \"all\" runs all available routines, \"help\" lists them"),
 
-	OPT_INTEGER('i', "iterations", &iterations,
-		    "Repeat the function this number of times"),
+	OPT_INTEGER('l', "nr_loops", &nr_loops,
+		    "Specify the number of loops to run. (default: 1)"),
 
 	OPT_BOOLEAN('c', "cycles", &use_cycles,
 		    "Use a cycles event instead of gettimeofday() to measure performance"),
@@ -159,7 +159,7 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 		init_cycles();
 
 	size = (size_t)perf_atoll((char *)size_str);
-	size_total = (double)size * iterations;
+	size_total = (double)size * nr_loops;
 
 	if ((s64)size <= 0) {
 		fprintf(stderr, "Invalid size:%s\n", size_str);
@@ -222,7 +222,7 @@ static u64 do_memcpy_cycles(const struct routine *r, size_t size)
 	fn(dst, src, size);
 
 	cycle_start = get_cycles();
-	for (i = 0; i < iterations; ++i)
+	for (i = 0; i < nr_loops; ++i)
 		fn(dst, src, size);
 	cycle_end = get_cycles();
 
@@ -247,7 +247,7 @@ static double do_memcpy_gettimeofday(const struct routine *r, size_t size)
 	fn(dst, src, size);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
-	for (i = 0; i < iterations; ++i)
+	for (i = 0; i < nr_loops; ++i)
 		fn(dst, src, size);
 	BUG_ON(gettimeofday(&tv_end, NULL));
 
@@ -256,7 +256,7 @@ static double do_memcpy_gettimeofday(const struct routine *r, size_t size)
 	free(src);
 	free(dst);
 
-	return (double)(((double)size * iterations) / timeval2double(&tv_diff));
+	return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
 }
 
 struct routine memcpy_routines[] = {
@@ -313,7 +313,7 @@ static u64 do_memset_cycles(const struct routine *r, size_t size)
 	fn(dst, -1, size);
 
 	cycle_start = get_cycles();
-	for (i = 0; i < iterations; ++i)
+	for (i = 0; i < nr_loops; ++i)
 		fn(dst, i, size);
 	cycle_end = get_cycles();
 
@@ -337,14 +337,14 @@ static double do_memset_gettimeofday(const struct routine *r, size_t size)
 	fn(dst, -1, size);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
-	for (i = 0; i < iterations; ++i)
+	for (i = 0; i < nr_loops; ++i)
 		fn(dst, i, size);
 	BUG_ON(gettimeofday(&tv_end, NULL));
 
 	timersub(&tv_end, &tv_start, &tv_diff);
 
 	free(dst);
-	return (double)(((double)size * iterations) / timeval2double(&tv_diff));
+	return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
 }
 
 static const char * const bench_mem_memset_usage[] = {
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 870b7e665a20..492df2752a2d 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -164,8 +164,8 @@ static const struct option options[] = {
 	OPT_STRING('L', "mb_proc_locked", &p0.mb_proc_locked_str,"MB", "process serialized/locked memory access (MBs), <= process_memory"),
 	OPT_STRING('T', "mb_thread"	, &p0.mb_thread_str,	"MB", "thread  memory (MBs)"),
 
-	OPT_UINTEGER('l', "nr_loops"	, &p0.nr_loops,		"max number of loops to run"),
-	OPT_UINTEGER('s', "nr_secs"	, &p0.nr_secs,		"max number of seconds to run"),
+	OPT_UINTEGER('l', "nr_loops"	, &p0.nr_loops,		"max number of loops to run (default: unlimited)"),
+	OPT_UINTEGER('s', "nr_secs"	, &p0.nr_secs,		"max number of seconds to run (default: 5 secs)"),
 	OPT_UINTEGER('u', "usleep"	, &p0.sleep_usecs,	"usecs to sleep per loop iteration"),
 
 	OPT_BOOLEAN('R', "data_reads"	, &p0.data_reads,	"access the data via writes (can be mixed with -W)"),
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index d7f281c2828d..d4ff1b539cfd 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -33,7 +33,7 @@
 #define DATASIZE 100
 
 static bool use_pipes = false;
-static unsigned int loops = 100;
+static unsigned int nr_loops = 100;
 static bool thread_mode = false;
 static unsigned int num_groups = 10;
 
@@ -79,7 +79,7 @@ static void ready(int ready_out, int wakefd)
 		err(EXIT_FAILURE, "poll");
 }
 
-/* Sender sprays loops messages down each file descriptor */
+/* Sender sprays nr_loops messages down each file descriptor */
 static void *sender(struct sender_context *ctx)
 {
 	char data[DATASIZE];
@@ -88,7 +88,7 @@ static void *sender(struct sender_context *ctx)
 	ready(ctx->ready_out, ctx->wakefd);
 
 	/* Now pump to every receiver. */
-	for (i = 0; i < loops; i++) {
+	for (i = 0; i < nr_loops; i++) {
 		for (j = 0; j < ctx->num_fds; j++) {
 			int ret, done = 0;
 
@@ -213,7 +213,7 @@ static unsigned int group(pthread_t *pth,
 		/* Create the pipe between client and server */
 		fdpair(fds);
 
-		ctx->num_packets = num_fds * loops;
+		ctx->num_packets = num_fds * nr_loops;
 		ctx->in_fds[0] = fds[0];
 		ctx->in_fds[1] = fds[1];
 		ctx->ready_out = ready_out;
@@ -250,7 +250,7 @@ static const struct option options[] = {
 	OPT_BOOLEAN('t', "thread", &thread_mode,
 		    "Be multi thread instead of multi process"),
 	OPT_UINTEGER('g', "group", &num_groups, "Specify number of groups"),
-	OPT_UINTEGER('l', "loop", &loops, "Specify number of loops"),
+	OPT_UINTEGER('l', "nr_loops", &nr_loops, "Specify the number of loops to run (default: 100)"),
 	OPT_END()
 };