#include "../lib/pow2.h"
#include "../optgroup.h"
#include "../lib/memalign.h"
+#include "cmdprio.h"
-#ifndef IOCB_FLAG_HIPRI
-#define IOCB_FLAG_HIPRI (1 << 2)
+/* Should be defined in newest aio_abi.h */
+#ifndef IOCB_FLAG_IOPRIO
+#define IOCB_FLAG_IOPRIO (1 << 1)
#endif
-#ifndef IOCTX_FLAG_IOPOLL
-#define IOCTX_FLAG_IOPOLL (1 << 0)
+/* Hack for libaio < 0.3.111 */
+#ifndef CONFIG_LIBAIO_RW_FLAGS
+#define aio_rw_flags __pad2
#endif
static int fio_libaio_commit(struct thread_data *td);
+static int fio_libaio_init(struct thread_data *td);
struct libaio_data {
io_context_t aio_ctx;
unsigned int queued;
unsigned int head;
unsigned int tail;
+
+ bool use_cmdprio;
};
struct libaio_options {
- void *pad;
+ struct thread_data *td;
unsigned int userspace_reap;
- unsigned int hipri;
+ struct cmdprio cmdprio;
+ unsigned int nowait;
};
+static int str_cmdprio_bssplit_cb(void *data, const char *input)
+{
+ struct libaio_options *o = data;
+ struct thread_data *td = o->td;
+ struct cmdprio *cmdprio = &o->cmdprio;
+
+ return fio_cmdprio_bssplit_parse(td, input, cmdprio);
+}
+
static struct fio_option options[] = {
{
.name = "userspace_reap",
.category = FIO_OPT_C_ENGINE,
.group = FIO_OPT_G_LIBAIO,
},
+#ifdef FIO_HAVE_IOPRIO_CLASS
{
- .name = "hipri",
- .lname = "High Priority",
- .type = FIO_OPT_STR_SET,
- .off1 = offsetof(struct libaio_options, hipri),
- .help = "Use polled IO completions",
+ .name = "cmdprio_percentage",
+ .lname = "high priority percentage",
+ .type = FIO_OPT_INT,
+ .off1 = offsetof(struct libaio_options,
+ cmdprio.percentage[DDIR_READ]),
+ .off2 = offsetof(struct libaio_options,
+ cmdprio.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_LIBAIO,
+ },
+ {
+ .name = "cmdprio_class",
+ .lname = "Asynchronous I/O priority class",
+ .type = FIO_OPT_INT,
+ .off1 = offsetof(struct libaio_options,
+ cmdprio.class[DDIR_READ]),
+ .off2 = offsetof(struct libaio_options,
+ cmdprio.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_LIBAIO,
+ },
+ {
+ .name = "cmdprio",
+ .lname = "Asynchronous I/O priority level",
+ .type = FIO_OPT_INT,
+ .off1 = offsetof(struct libaio_options,
+ cmdprio.level[DDIR_READ]),
+ .off2 = offsetof(struct libaio_options,
+ cmdprio.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_LIBAIO,
+ },
+ {
+ .name = "cmdprio_bssplit",
+ .lname = "Priority percentage block size split",
+ .type = FIO_OPT_STR_ULL,
+ .cb = str_cmdprio_bssplit_cb,
+ .off1 = offsetof(struct libaio_options, cmdprio.bssplit),
+ .help = "Set priority percentages for different block sizes",
+ .category = FIO_OPT_C_ENGINE,
+ .group = FIO_OPT_G_LIBAIO,
+ },
+#else
+ {
+ .name = "cmdprio_percentage",
+ .lname = "high priority 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 = "nowait",
+ .lname = "RWF_NOWAIT",
+ .type = FIO_OPT_BOOL,
+ .off1 = offsetof(struct libaio_options, nowait),
+ .help = "Set RWF_NOWAIT for reads/writes",
.category = FIO_OPT_C_ENGINE,
.group = FIO_OPT_G_LIBAIO,
},
*val = (*val + add) % ld->entries;
}
-static int fio_libaio_prep(struct thread_data fio_unused *td, struct io_u *io_u)
+static int fio_libaio_prep(struct thread_data *td, struct io_u *io_u)
{
- struct fio_file *f = io_u->file;
struct libaio_options *o = td->eo;
- struct iocb *iocb;
-
- iocb = &io_u->iocb;
+ struct fio_file *f = io_u->file;
+ struct iocb *iocb = &io_u->iocb;
if (io_u->ddir == DDIR_READ) {
io_prep_pread(iocb, f->fd, io_u->xfer_buf, io_u->xfer_buflen, io_u->offset);
- if (o->hipri)
- iocb->u.c.flags |= IOCB_FLAG_HIPRI;
+ if (o->nowait)
+ iocb->aio_rw_flags |= RWF_NOWAIT;
} else if (io_u->ddir == DDIR_WRITE) {
io_prep_pwrite(iocb, f->fd, io_u->xfer_buf, io_u->xfer_buflen, io_u->offset);
- if (o->hipri)
- iocb->u.c.flags |= IOCB_FLAG_HIPRI;
+ if (o->nowait)
+ iocb->aio_rw_flags |= RWF_NOWAIT;
} else if (ddir_sync(io_u->ddir))
io_prep_fsync(iocb, f->fd);
return 0;
}
+static void fio_libaio_prio_prep(struct thread_data *td, struct io_u *io_u)
+{
+ struct libaio_options *o = td->eo;
+ struct cmdprio *cmdprio = &o->cmdprio;
+ enum fio_ddir ddir = io_u->ddir;
+ unsigned int p = fio_cmdprio_percentage(cmdprio, io_u);
+ unsigned int cmdprio_value =
+ ioprio_value(cmdprio->class[ddir], cmdprio->level[ddir]);
+
+ if (p && rand_between(&td->prio_state, 0, 99) < p) {
+ io_u->ioprio = cmdprio_value;
+ io_u->iocb.aio_reqprio = cmdprio_value;
+ io_u->iocb.u.c.flags |= IOCB_FLAG_IOPRIO;
+ if (!td->ioprio || cmdprio_value < td->ioprio) {
+ /*
+ * The async IO priority is higher (has a lower value)
+ * than the default context priority.
+ */
+ io_u->flags |= IO_U_F_HIGH_PRIO;
+ }
+ } else if (td->ioprio && td->ioprio < cmdprio_value) {
+ /*
+ * The IO will be executed with the default context priority,
+ * and this priority is higher (has a lower value) than the
+ * async IO priority.
+ */
+ io_u->flags |= IO_U_F_HIGH_PRIO;
+ }
+}
+
static struct io_u *fio_libaio_event(struct thread_data *td, int event)
{
struct libaio_data *ld = td->io_ops_data;
} else {
/* There is another completion to reap */
events[i] = ring->events[head];
- read_barrier();
- ring->head = (head + 1) % ring->nr;
+ atomic_store_release(&ring->head,
+ (head + 1) % ring->nr);
i++;
}
}
return FIO_Q_COMPLETED;
}
+ if (ld->use_cmdprio)
+ fio_libaio_prio_prep(td, io_u);
+
ld->iocbs[ld->head] = &io_u->iocb;
ld->io_us[ld->head] = io_u;
ring_inc(ld, &ld->head, 1);
}
}
-static int fio_libaio_old_queue_init(struct libaio_data *ld, unsigned int depth,
- bool hipri)
-{
- if (hipri) {
- log_err("fio: polled aio not available on your platform\n");
- return 1;
- }
-
- return io_queue_init(depth, &ld->aio_ctx);
-}
-
-static int fio_libaio_queue_init(struct libaio_data *ld, unsigned int depth,
- bool hipri)
-{
-#ifdef __NR_sys_io_setup2
- int ret, flags = 0;
-
- if (hipri)
- flags |= IOCTX_FLAG_IOPOLL;
-
- ret = syscall(__NR_sys_io_setup2, depth, flags, NULL, NULL,
- &ld->aio_ctx);
- if (!ret)
- return 0;
- /* fall through to old syscall */
-#endif
- return fio_libaio_old_queue_init(ld, depth, hipri);
-}
-
static int fio_libaio_post_init(struct thread_data *td)
{
struct libaio_data *ld = td->io_ops_data;
- struct libaio_options *o = td->eo;
- int err = 0;
+ int err;
- err = fio_libaio_queue_init(ld, td->o.iodepth, o->hipri);
+ err = io_queue_init(td->o.iodepth, &ld->aio_ctx);
if (err) {
td_verror(td, -err, "io_queue_init");
return 1;
static int fio_libaio_init(struct thread_data *td)
{
struct libaio_data *ld;
+ struct libaio_options *o = td->eo;
+ struct cmdprio *cmdprio = &o->cmdprio;
+ int ret;
ld = calloc(1, sizeof(*ld));
ld->io_us = calloc(ld->entries, sizeof(struct io_u *));
td->io_ops_data = ld;
+
+ ret = fio_cmdprio_init(td, cmdprio, &ld->use_cmdprio);
+ if (ret) {
+ td_verror(td, EINVAL, "fio_libaio_init");
+ return 1;
+ }
+
return 0;
}
-static struct ioengine_ops ioengine = {
+FIO_STATIC struct ioengine_ops ioengine = {
.name = "libaio",
.version = FIO_IOOPS_VERSION,
.flags = FIO_ASYNCIO_SYNC_TRIM,