static int parse_cpus_opt(const struct option *opt, const char *arg, int unset);
static int parse_nodes_opt(const struct option *opt, const char *arg, int unset);
struct params p0;
static const struct option options[] = {
OPT_INTEGER('p', "nr_proc" , &p0.nr_proc, "number of processes"),
OPT_INTEGER('t', "nr_threads" , &p0.nr_threads, "number of threads per process"),
OPT_STRING('G', "mb_global" , &p0.mb_global_str, "MB", "global memory (MBs)"),
OPT_STRING('P', "mb_proc" , &p0.mb_proc_str, "MB", "process memory (MBs)"),
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('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)"),
OPT_BOOLEAN('W', "data_writes" , &p0.data_writes, "access the data via writes (can be mixed with -R)"),
OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards, "access the data backwards as well"),
OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"),
OPT_BOOLEAN('r', "data_rand_walk", &p0.data_rand_walk, "access the data with random (32bit LFSR) walk"),
OPT_BOOLEAN('z', "init_zero" , &p0.init_zero, "bzero the initial allocations"),
OPT_BOOLEAN('I', "init_random" , &p0.init_random, "randomize the contents of the initial allocations"),
OPT_BOOLEAN('0', "init_cpu0" , &p0.init_cpu0, "do the initial allocations on CPU#0"),
OPT_INTEGER('x', "perturb_secs", &p0.perturb_secs, "perturb thread 0/0 every X secs, to test convergence stability"),
static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
{
int rec_argc, i = 0, j;
const char **rec_argv;
int ret;
bool all_user = false, all_kernel = false;
struct option options[] = {
OPT_CALLBACK('e', "event", &mem, "event",
"event selector. use 'perf mem record -e list' to list available events",
parse_record_events),
OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_BOOLEAN('U', "all-user", &all_user, "collect only user level data"),
OPT_BOOLEAN('K', "all-kernel", &all_kernel, "collect only kernel level data"),
OPT_END()
};
argc = parse_options(argc, argv, options, record_mem_usage,
PARSE_OPT_KEEP_UNKNOWN);
rec_argc = argc + 9; /* max number of arguments */
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (!rec_argv)
return -1;
rec_argv[i++] = "record";
if (mem->operation & MEM_OPERATION_LOAD)
perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
if (mem->operation & MEM_OPERATION_STORE)
perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
rec_argv[i++] = "-W";
rec_argv[i++] = "-d";
if (mem->phys_addr)
rec_argv[i++] = "--phys-data";
for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
if (!perf_mem_events[j].record)
continue;
if (!perf_mem_events[j].supported) {
pr_err("failed: event '%s' not supported\n",
perf_mem_events__name(j));
free(rec_argv);
return -1;
}
rec_argv[i++] = "-e";
rec_argv[i++] = perf_mem_events__name(j);
};
if (all_user)
rec_argv[i++] = "--all-user";
if (all_kernel)
rec_argv[i++] = "--all-kernel";
for (j = 0; j < argc; j++, i++)
rec_argv[i] = argv[j];
if (verbose > 0) {
pr_debug("calling: record ");
while (rec_argv[j]) {
pr_debug("%s ", rec_argv[j]);
j++;
}
pr_debug("\n");
}
ret = cmd_record(i, rec_argv);
free(rec_argv);
return ret;
}
/*
* How many tasks to requeue at a time.
* Default to 1 in order to make the kernel work more.
*/
static unsigned int nrequeue = 1;
static pthread_t *worker;
static bool done = false, silent = false, fshared = false;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
static struct stats requeuetime_stats, requeued_stats;
static unsigned int ncpus, threads_starting, nthreads = 0;
static int futex_flag = 0;
static const struct option options[] = {
OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
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);
struct timeval start, end, runtime;
static pthread_mutex_t thread_lock;
static unsigned int threads_starting;
static struct stats throughput_stats;
static pthread_cond_t thread_parent, thread_worker;
struct worker {
int tid;
u_int32_t *futex;
pthread_t thread;
unsigned long ops;
};
static const struct option options[] = {
OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"),
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"),
OPT_BOOLEAN( 'a', "attached", &attached, "Use attached futexes"),
OPT_END()
};
static const char * const bench_futex_hash_usage[] = {
"perf bench futex hash <options>",
NULL
};
static void *workerfn(void *arg)
{
static unsigned int nwakes = 1;
/* all threads will block on the same futex -- hash bucket chaos ;) */
static u_int32_t futex = 0;
static pthread_t *blocked_worker;
static bool done = false, silent = false, fshared = false;
static unsigned int nblocked_threads = 0, nwaking_threads = 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;
static int futex_flag = 0;
static const struct option options[] = {
OPT_UINTEGER('t', "threads", &nblocked_threads, "Specify amount of threads"),
OPT_UINTEGER('w', "nwakers", &nwaking_threads, "Specify amount of waking 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"),
OPT_END()
};
static const char * const bench_futex_wake_parallel_usage[] = {
"perf bench futex wake-parallel <options>",
NULL
};
static void *waking_workerfn(void *arg)
{
struct thread_data *waker = (struct thread_data *) arg;
struct timeval start, end;
/*
* How many wakeups to do at a time.
* Default to 1 in order to make the kernel work more.
*/
static unsigned int nwakes = 1;
pthread_t *worker;
static bool done = false, silent = false, fshared = false;
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 int futex_flag = 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_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"),
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--;
/* Close the fds we have left */
if (!thread_mode)
for (i = 0; i < num_fds; i++)
close(snd_ctx->out_fds[i]);
/* Return number of children to reap */
return num_fds * 2;
}
static const struct option options[] = {
OPT_BOOLEAN('p', "pipe", &use_pipes,
"Use pipe() instead of socketpair()"),
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_END()
};
static const char * const bench_sched_message_usage[] = {
"perf bench sched messaging <options>",
NULL
};
int bench_sched_messaging(int argc, const char **argv,
const char *prefix __maybe_unused)
{
unsigned int i, total_children;
struct timeval start, stop, diff;
unsigned int num_fds = 20;
for_each_bench(coll, bench)
printf("%14s: %s\n", bench->name, bench->summary);
printf("\n");
}
static const char *bench_format_str;
/* Output/formatting style, exported to benchmark modules: */
int bench_format = BENCH_FORMAT_DEFAULT;
unsigned int bench_repeat = 10; /* default number of times to repeat the run */
static const struct option bench_options[] = {
OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"),
OPT_UINTEGER('r', "repeat", &bench_repeat, "Specify amount of times to repeat the run"),
OPT_END()
};
static const char * const bench_usage[] = {
"perf bench [<common options>] <collection> <benchmark> [<options>]",
NULL
};
static void print_usage(void)
{
struct collection *coll;
int i;
printf("Usage: \n");
for (i = 0; bench_usage[i]; i++)
static u_int32_t global_futex = 0;
static struct worker *worker;
static unsigned int nsecs = 10;
static bool silent = false, multi = false;
static bool done = false, fshared = false;
static unsigned int ncpus, nthreads = 0;
static int futex_flag = 0;
struct timeval start, end, runtime;
static pthread_mutex_t thread_lock;
static unsigned int threads_starting;
static struct stats throughput_stats;
static pthread_cond_t thread_parent, thread_worker;
static const struct option options[] = {
OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"),
OPT_BOOLEAN( 'M', "multi", &multi, "Use multiple futexes"),
OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
static const char * const bench_futex_lock_pi_usage[] = {
"perf bench futex requeue <options>",
NULL
};
static void print_summary(void)
{
unsigned long avg = avg_stats(&throughput_stats);
