struct submitter {
pthread_t thread;
int ring_fd;
+ int index;
struct io_sq_ring sq_ring;
struct io_uring_sqe *sqes;
struct io_cq_ring cq_ring;
static int sq_thread_poll = 0; /* use kernel submission/poller thread */
static int sq_thread_cpu = -1; /* pin above thread to this CPU */
static int do_nop = 0; /* no-op SQ ring commands */
+static int nthreads = 1;
static int vectored = 1;
return NULL;
}
+static struct submitter *get_submitter(int offset)
+{
+ void *ret;
+
+ ret = submitter;
+ if (offset)
+ ret += offset * (sizeof(*submitter) + depth * sizeof(struct iovec));
+ return ret;
+}
+
static void sig_int(int sig)
{
+ int j;
+
printf("Exiting on signal %d\n", sig);
- submitter->finish = 1;
+ for (j = 0; j < nthreads; j++) {
+ struct submitter *s = get_submitter(j);
+ s->finish = 1;
+ }
finish = 1;
}
io_uring_probe(fd);
if (fixedbufs) {
+ struct rlimit rlim;
+
+ rlim.rlim_cur = RLIM_INFINITY;
+ rlim.rlim_max = RLIM_INFINITY;
+ /* ignore potential error, not needed on newer kernels */
+ setrlimit(RLIMIT_MEMLOCK, &rlim);
+
ret = io_uring_register_buffers(s);
if (ret < 0) {
perror("io_uring_register_buffers");
static void file_depths(char *buf)
{
- struct submitter *s = submitter;
+ bool prev = false;
char *p;
- int i;
+ int i, j;
buf[0] = '\0';
p = buf;
- for (i = 0; i < s->nr_files; i++) {
- struct file *f = &s->files[i];
+ for (j = 0; j < nthreads; j++) {
+ struct submitter *s = get_submitter(j);
- if (i + 1 == s->nr_files)
- p += sprintf(p, "%d", f->pending_ios);
- else
- p += sprintf(p, "%d, ", f->pending_ios);
+ for (i = 0; i < s->nr_files; i++) {
+ struct file *f = &s->files[i];
+
+ if (prev)
+ p += sprintf(p, " %d", f->pending_ios);
+ else
+ p += sprintf(p, "%d", f->pending_ios);
+ prev = true;
+ }
}
}
-static void usage(char *argv)
+static void usage(char *argv, int status)
{
printf("%s [options] -- [filenames]\n"
- " -d <int> : IO Depth, default %d\n"
- " -s <int> : Batch submit, default %d\n"
- " -c <int> : Batch complete, default %d\n"
- " -b <int> : Block size, default %d\n"
- " -p <bool> : Polled IO, default %d\n",
- argv, DEPTH, BATCH_SUBMIT, BATCH_COMPLETE, BS, polled);
- exit(0);
+ " -d <int> : IO Depth, default %d\n"
+ " -s <int> : Batch submit, default %d\n"
+ " -c <int> : Batch complete, default %d\n"
+ " -b <int> : Block size, default %d\n"
+ " -p <bool> : Polled IO, default %d\n"
+ " -B <bool> : Fixed buffers, default %d\n"
+ " -F <bool> : Register files, default %d\n"
+ " -n <int> : Number of threads, default %d\n"
+ " -O <bool> : Use O_DIRECT, default %d\n"
+ " -N <bool> : Perform just no-op requests, default %d\n",
+ argv, DEPTH, BATCH_SUBMIT, BATCH_COMPLETE, BS, polled,
+ fixedbufs, register_files, nthreads, !buffered, do_nop);
+ exit(status);
}
int main(int argc, char *argv[])
{
struct submitter *s;
unsigned long done, calls, reap;
- int err, i, flags, fd, opt;
+ int err, i, j, flags, fd, opt, threads_per_f, threads_rem = 0, nfiles;
+ struct file f;
char *fdepths;
void *ret;
- if (!do_nop && argc < 2) {
- printf("%s: filename [options]\n", argv[0]);
- return 1;
- }
+ if (!do_nop && argc < 2)
+ usage(argv[0], 1);
- while ((opt = getopt(argc, argv, "d:s:c:b:p:B:F:h?")) != -1) {
+ while ((opt = getopt(argc, argv, "d:s:c:b:p:B:F:n:N:O:h?")) != -1) {
switch (opt) {
case 'd':
depth = atoi(optarg);
case 'F':
register_files = !!atoi(optarg);
break;
+ case 'n':
+ nthreads = atoi(optarg);
+ if (!nthreads) {
+ printf("Threads must be non-zero\n");
+ usage(argv[0], 1);
+ }
+ break;
+ case 'N':
+ do_nop = !!atoi(optarg);
+ break;
+ case 'O':
+ buffered = !atoi(optarg);
+ break;
case 'h':
case '?':
default:
- usage(argv[0]);
+ usage(argv[0], 0);
break;
}
}
- submitter = malloc(sizeof(*submitter) + depth * sizeof(struct iovec));
- memset(submitter, 0, sizeof(*submitter) + depth * sizeof(struct iovec));
- s = submitter;
+ if (batch_complete > depth)
+ batch_complete = depth;
+ if (batch_submit > depth)
+ batch_submit = depth;
+
+ submitter = calloc(nthreads, sizeof(*submitter) +
+ depth * sizeof(struct iovec));
+ for (j = 0; j < nthreads; j++) {
+ s = get_submitter(j);
+ s->index = j;
+ s->done = s->calls = s->reaps = 0;
+ }
flags = O_RDONLY | O_NOATIME;
if (!buffered)
flags |= O_DIRECT;
+ j = 0;
i = optind;
+ nfiles = argc - i;
+ if (!do_nop) {
+ if (!nfiles) {
+ printf("No files specified\n");
+ usage(argv[0], 1);
+ }
+ threads_per_f = nthreads / nfiles;
+ /* make sure each thread gets assigned files */
+ if (threads_per_f == 0) {
+ threads_per_f = 1;
+ } else {
+ threads_rem = nthreads - threads_per_f * nfiles;
+ }
+ }
while (!do_nop && i < argc) {
- struct file *f;
+ int k, limit;
+
+ memset(&f, 0, sizeof(f));
- if (s->nr_files == MAX_FDS) {
- printf("Max number of files (%d) reached\n", MAX_FDS);
- break;
- }
fd = open(argv[i], flags);
if (fd < 0) {
perror("open");
return 1;
}
-
- f = &s->files[s->nr_files];
- f->real_fd = fd;
- if (get_file_size(f)) {
+ f.real_fd = fd;
+ if (get_file_size(&f)) {
printf("failed getting size of device/file\n");
return 1;
}
- if (f->max_blocks <= 1) {
+ if (f.max_blocks <= 1) {
printf("Zero file/device size?\n");
return 1;
}
- f->max_blocks--;
+ f.max_blocks--;
- printf("Added file %s\n", argv[i]);
- s->nr_files++;
- i++;
- }
+ limit = threads_per_f;
+ limit += threads_rem > 0 ? 1 : 0;
+ for (k = 0; k < limit; k++) {
+ s = get_submitter((j + k) % nthreads);
- if (fixedbufs) {
- struct rlimit rlim;
+ if (s->nr_files == MAX_FDS) {
+ printf("Max number of files (%d) reached\n", MAX_FDS);
+ break;
+ }
- rlim.rlim_cur = RLIM_INFINITY;
- rlim.rlim_max = RLIM_INFINITY;
- if (setrlimit(RLIMIT_MEMLOCK, &rlim) < 0) {
- perror("setrlimit");
- return 1;
+ memcpy(&s->files[s->nr_files], &f, sizeof(f));
+
+ printf("Added file %s (submitter %d)\n", argv[i], s->index);
+ s->nr_files++;
}
+ threads_rem--;
+ i++;
+ j += limit;
}
arm_sig_int();
- for (i = 0; i < depth; i++) {
- void *buf;
+ for (j = 0; j < nthreads; j++) {
+ s = get_submitter(j);
+ for (i = 0; i < depth; i++) {
+ void *buf;
- if (posix_memalign(&buf, bs, bs)) {
- printf("failed alloc\n");
- return 1;
+ if (posix_memalign(&buf, bs, bs)) {
+ printf("failed alloc\n");
+ return 1;
+ }
+ s->iovecs[i].iov_base = buf;
+ s->iovecs[i].iov_len = bs;
}
- s->iovecs[i].iov_base = buf;
- s->iovecs[i].iov_len = bs;
}
- err = setup_ring(s);
- if (err) {
- printf("ring setup failed: %s, %d\n", strerror(errno), err);
- return 1;
+ for (j = 0; j < nthreads; j++) {
+ s = get_submitter(j);
+
+ err = setup_ring(s);
+ if (err) {
+ printf("ring setup failed: %s, %d\n", strerror(errno), err);
+ return 1;
+ }
}
+ s = get_submitter(0);
printf("polled=%d, fixedbufs=%d, register_files=%d, buffered=%d", polled, fixedbufs, register_files, buffered);
printf(" QD=%d, sq_ring=%d, cq_ring=%d\n", depth, *s->sq_ring.ring_entries, *s->cq_ring.ring_entries);
- pthread_create(&s->thread, NULL, submitter_fn, s);
+ for (j = 0; j < nthreads; j++) {
+ s = get_submitter(j);
+ pthread_create(&s->thread, NULL, submitter_fn, s);
+ }
- fdepths = malloc(8 * s->nr_files);
+ fdepths = malloc(8 * s->nr_files * nthreads);
reap = calls = done = 0;
do {
unsigned long this_done = 0;
unsigned long this_reap = 0;
unsigned long this_call = 0;
unsigned long rpc = 0, ipc = 0;
+ unsigned long iops, bw;
sleep(1);
- this_done += s->done;
- this_call += s->calls;
- this_reap += s->reaps;
+ for (j = 0; j < nthreads; j++) {
+ this_done += s->done;
+ this_call += s->calls;
+ this_reap += s->reaps;
+ }
if (this_call - calls) {
rpc = (this_done - done) / (this_call - calls);
ipc = (this_reap - reap) / (this_call - calls);
} else
rpc = ipc = -1;
file_depths(fdepths);
- printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s)\n",
- this_done - done, rpc, ipc, s->inflight,
- fdepths);
+ iops = this_done - done;
+ if (bs > 1048576)
+ bw = iops * (bs / 1048576);
+ else
+ bw = iops / (1048576 / bs);
+ printf("IOPS=%lu, ", iops);
+ if (!do_nop)
+ printf("BW=%luMiB/s, ", bw);
+ printf("IOS/call=%ld/%ld, inflight=(%s)\n", rpc, ipc, fdepths);
done = this_done;
calls = this_call;
reap = this_reap;
} while (!finish);
- pthread_join(s->thread, &ret);
- close(s->ring_fd);
+ for (j = 0; j < nthreads; j++) {
+ s = get_submitter(j);
+ pthread_join(s->thread, &ret);
+ close(s->ring_fd);
+ }
free(fdepths);
+ free(submitter);
return 0;
}