#include "../lib/types.h"
#include "../os/linux/io_uring.h"
+#include "cmdprio.h"
struct io_sq_ring {
unsigned *head;
int queued;
int cq_ring_off;
unsigned iodepth;
- bool ioprio_class_set;
- bool ioprio_set;
int prepped;
struct ioring_mmap mmap[3];
+
+ struct cmdprio cmdprio;
};
struct ioring_options {
- void *pad;
+ struct thread_data *td;
unsigned int hipri;
- unsigned int cmdprio_percentage;
+ struct cmdprio_options cmdprio_options;
unsigned int fixedbufs;
unsigned int registerfiles;
unsigned int sqpoll_thread;
.name = "cmdprio_percentage",
.lname = "high priority percentage",
.type = FIO_OPT_INT,
- .off1 = offsetof(struct ioring_options, cmdprio_percentage),
- .minval = 1,
+ .off1 = offsetof(struct ioring_options,
+ cmdprio_options.percentage[DDIR_READ]),
+ .off2 = offsetof(struct ioring_options,
+ cmdprio_options.percentage[DDIR_WRITE]),
+ .minval = 0,
.maxval = 100,
.help = "Send high priority I/O this percentage of the time",
.category = FIO_OPT_C_ENGINE,
.group = FIO_OPT_G_IOURING,
},
+ {
+ .name = "cmdprio_class",
+ .lname = "Asynchronous I/O priority class",
+ .type = FIO_OPT_INT,
+ .off1 = offsetof(struct ioring_options,
+ cmdprio_options.class[DDIR_READ]),
+ .off2 = offsetof(struct ioring_options,
+ cmdprio_options.class[DDIR_WRITE]),
+ .help = "Set asynchronous IO priority class",
+ .minval = IOPRIO_MIN_PRIO_CLASS + 1,
+ .maxval = IOPRIO_MAX_PRIO_CLASS,
+ .interval = 1,
+ .category = FIO_OPT_C_ENGINE,
+ .group = FIO_OPT_G_IOURING,
+ },
+ {
+ .name = "cmdprio",
+ .lname = "Asynchronous I/O priority level",
+ .type = FIO_OPT_INT,
+ .off1 = offsetof(struct ioring_options,
+ cmdprio_options.level[DDIR_READ]),
+ .off2 = offsetof(struct ioring_options,
+ cmdprio_options.level[DDIR_WRITE]),
+ .help = "Set asynchronous IO priority level",
+ .minval = IOPRIO_MIN_PRIO,
+ .maxval = IOPRIO_MAX_PRIO,
+ .interval = 1,
+ .category = FIO_OPT_C_ENGINE,
+ .group = FIO_OPT_G_IOURING,
+ },
+ {
+ .name = "cmdprio_bssplit",
+ .lname = "Priority percentage block size split",
+ .type = FIO_OPT_STR_STORE,
+ .off1 = offsetof(struct ioring_options,
+ cmdprio_options.bssplit_str),
+ .help = "Set priority percentages for different block sizes",
+ .category = FIO_OPT_C_ENGINE,
+ .group = FIO_OPT_G_IOURING,
+ },
#else
{
.name = "cmdprio_percentage",
.type = FIO_OPT_UNSUPPORTED,
.help = "Your platform does not support I/O priority classes",
},
+ {
+ .name = "cmdprio_class",
+ .lname = "Asynchronous I/O priority class",
+ .type = FIO_OPT_UNSUPPORTED,
+ .help = "Your platform does not support I/O priority classes",
+ },
+ {
+ .name = "cmdprio",
+ .lname = "Asynchronous I/O priority level",
+ .type = FIO_OPT_UNSUPPORTED,
+ .help = "Your platform does not support I/O priority classes",
+ },
+ {
+ .name = "cmdprio_bssplit",
+ .lname = "Priority percentage block size split",
+ .type = FIO_OPT_UNSUPPORTED,
+ .help = "Your platform does not support I/O priority classes",
+ },
#endif
{
.name = "fixedbufs",
sqe->flags = IOSQE_FIXED_FILE;
} else {
sqe->fd = f->fd;
+ sqe->flags = 0;
}
if (io_u->ddir == DDIR_READ || io_u->ddir == DDIR_WRITE) {
sqe->len = 1;
}
}
+ sqe->rw_flags = 0;
if (!td->o.odirect && o->uncached)
- sqe->rw_flags = RWF_UNCACHED;
+ sqe->rw_flags |= RWF_UNCACHED;
if (o->nowait)
sqe->rw_flags |= RWF_NOWAIT;
- if (ld->ioprio_class_set)
- sqe->ioprio = td->o.ioprio_class << 13;
- if (ld->ioprio_set)
- sqe->ioprio |= td->o.ioprio;
+
+ /*
+ * Since io_uring can have a submission context (sqthread_poll)
+ * that is different from the process context, we cannot rely on
+ * the IO priority set by ioprio_set() (option prio/prioclass)
+ * to be inherited.
+ * td->ioprio will have the value of the "default prio", so set
+ * this unconditionally. This value might get overridden by
+ * fio_ioring_cmdprio_prep() if the option cmdprio_percentage or
+ * cmdprio_bssplit is used.
+ */
+ sqe->ioprio = td->ioprio;
sqe->off = io_u->offset;
- sqe->rw_flags = 0;
} else if (ddir_sync(io_u->ddir)) {
sqe->ioprio = 0;
if (io_u->ddir == DDIR_SYNC_FILE_RANGE) {
return r < 0 ? r : events;
}
-static void fio_ioring_prio_prep(struct thread_data *td, struct io_u *io_u)
+static inline void fio_ioring_cmdprio_prep(struct thread_data *td,
+ struct io_u *io_u)
{
- struct ioring_options *o = td->eo;
struct ioring_data *ld = td->io_ops_data;
- if (rand_between(&td->prio_state, 0, 99) < o->cmdprio_percentage) {
- ld->sqes[io_u->index].ioprio = IOPRIO_CLASS_RT << IOPRIO_CLASS_SHIFT;
- io_u->flags |= IO_U_F_PRIORITY;
- }
- return;
+ struct cmdprio *cmdprio = &ld->cmdprio;
+
+ if (fio_cmdprio_set_ioprio(td, cmdprio, io_u))
+ ld->sqes[io_u->index].ioprio = io_u->ioprio;
}
static enum fio_q_status fio_ioring_queue(struct thread_data *td,
{
struct ioring_data *ld = td->io_ops_data;
struct io_sq_ring *ring = &ld->sq_ring;
- struct ioring_options *o = td->eo;
unsigned tail, next_tail;
fio_ro_check(td, io_u);
if (next_tail == atomic_load_acquire(ring->head))
return FIO_Q_BUSY;
- if (o->cmdprio_percentage)
- fio_ioring_prio_prep(td, io_u);
+ if (ld->cmdprio.mode != CMDPRIO_MODE_NONE)
+ fio_ioring_cmdprio_prep(td, io_u);
+
ring->array[tail & ld->sq_ring_mask] = io_u->index;
atomic_store_release(ring->tail, next_tail);
{
int i;
- for (i = 0; i < ARRAY_SIZE(ld->mmap); i++)
+ for (i = 0; i < FIO_ARRAY_SIZE(ld->mmap); i++)
munmap(ld->mmap[i].ptr, ld->mmap[i].len);
close(ld->ring_fd);
}
if (!(td->flags & TD_F_CHILD))
fio_ioring_unmap(ld);
+ fio_cmdprio_cleanup(&ld->cmdprio);
free(ld->io_u_index);
free(ld->iovecs);
free(ld->fds);
}
}
+ /*
+ * Clamp CQ ring size at our SQ ring size, we don't need more entries
+ * than that.
+ */
+ p.flags |= IORING_SETUP_CQSIZE;
+ p.cq_entries = depth;
+
+retry:
ret = syscall(__NR_io_uring_setup, depth, &p);
- if (ret < 0)
+ if (ret < 0) {
+ if (errno == EINVAL && p.flags & IORING_SETUP_CQSIZE) {
+ p.flags &= ~IORING_SETUP_CQSIZE;
+ goto retry;
+ }
return ret;
+ }
ld->ring_fd = ret;
err = fio_ioring_queue_init(td);
if (err) {
- td_verror(td, errno, "io_queue_init");
+ int init_err = errno;
+
+ if (init_err == ENOSYS)
+ log_err("fio: your kernel doesn't support io_uring\n");
+ td_verror(td, init_err, "io_queue_init");
return 1;
}
{
struct ioring_options *o = td->eo;
struct ioring_data *ld;
- struct thread_options *to = &td->o;
-
- if (to->io_submit_mode == IO_MODE_OFFLOAD) {
- log_err("fio: io_submit_mode=offload is not compatible (or "
- "useful) with io_uring\n");
- return 1;
- }
+ int ret;
/* sqthread submission requires registered files */
if (o->sqpoll_thread)
td->io_ops_data = ld;
- /*
- * Check for option conflicts
- */
- if ((fio_option_is_set(to, ioprio) || fio_option_is_set(to, ioprio_class)) &&
- o->cmdprio_percentage != 0) {
- log_err("%s: cmdprio_percentage option and mutually exclusive "
- "prio or prioclass option is set, exiting\n", to->name);
- td_verror(td, EINVAL, "fio_io_uring_init");
+ ret = fio_cmdprio_init(td, &ld->cmdprio, &o->cmdprio_options);
+ if (ret) {
+ td_verror(td, EINVAL, "fio_ioring_init");
return 1;
}
- if (fio_option_is_set(&td->o, ioprio_class))
- ld->ioprio_class_set = true;
- if (fio_option_is_set(&td->o, ioprio))
- ld->ioprio_set = true;
-
return 0;
}