perf bench: Harmonize all the -l/--nr_loops options

We have three benchmarking subsystems that specify some sort of 'number
of loops' parameter - but all of them do it inconsistently:

numa: -l/--nr_loops
sched messaging: -l/--loops
mem memset/memcpy: -i/--iterations

Harmonize them to -l/--nr_loops by picking the numa variant - which is
also the most likely one to have existing scripting which we don't want
to break.

Plus improve the parameter help texts to indicate the default value for
the nr_loops variable to keep users from guessing ...

Also propagate the naming to internal variables.

Signed-off-by: Ingo Molnar <[e-mail]>
Cc: David Ahern <[e-mail]>
Cc: Hitoshi Mitake <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
[ Let the harmonisation reach the perf-bench man page as well ]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/Documentation/perf-bench.txt

···
 Specify number of groups
 
 -l::
---loop=::
+--nr_loops=::
 Specify number of loops
 
 Example of *messaging*
···
 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::
···
 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::

tools/perf/bench/mem-functions.c

···
 
 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"),
···
 		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);
···
 	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();
 
···
 	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));
 
···
 	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[] = {
···
 	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();
 
···
 	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[] = {

tools/perf/bench/numa.c

···
 	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)"),

tools/perf/bench/sched-messaging.c

···
 #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;
 
···
 		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];
···
 	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;
 
···
 		/* 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;
···
 	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()
 };