Adding userspace_libaio_reap option

When a single thread is reading from a libaio io_context_t object
in a non-blocking polling manner (that is, with the minimum number
of events to return being 0), then it is possible to safely read
events directly from user-space, taking advantage of the fact that
the io_context_t object is a pointer to memory with a certain layout.
This patch adds an option, userspace_libaio_reap, which allows
reading events in this manner when the libaio engine is used.

You can observe its effect by setting iodepth_batch_complete=0
and seeing the change in distribution of system/user time based on
whether this new flag is set. If userspace_libaio_reap=1, then
busy polling takes place in userspace, and there is a larger amount of
usr CPU. If userspace_libaio_reap=0 (the default), then there is a
larger amount of sys CPU from the polling in the kernel.

Polling from a queue in this manner is several times faster. In my
testing, it took less than an eighth as much time to execute a
polling operation in user-space than with the io_getevents syscall.

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

diff --git a/HOWTO b/HOWTO
index a1b2e8c0bf7a6f51bceb8016618acb32e7dae01e..ad4e45402172f04a4563b2974c5e997462b4d30d 100644 (file)
--- a/HOWTO
+++ b/HOWTO
@@ -1187,6 +1187,13 @@ uid=int          Instead of running as the invoking user, set the user ID to
 
 gid=int                Set group ID, see uid.
 
+userspace_libaio_reap=bool  Normally, with the libaio engine in use, fio
+               will use the io_getevents system call to reap newly returned
+               events. With this flag turned on, the AIO ring will be read
+               directly from user-space to reap events. The reaping mode is
+               only enabled when polling for a minimum of 0 events (eg when
+               iodepth_batch_complete=0).
+
 6.0 Interpreting the output
 ---------------------------
 

diff --git a/engines/libaio.c b/engines/libaio.c
index c837ab6bb9e4e9af10553bff980cc318e7274821..ea05c63c689b43de1f18116a1c04c62bf5af12a6 100644 (file)
--- a/engines/libaio.c
+++ b/engines/libaio.c
@@ -58,6 +58,47 @@ static struct io_u *fio_libaio_event(struct thread_data *td, int event)
        return io_u;
 }
 
+struct aio_ring {
+       unsigned id;             /** kernel internal index number */
+       unsigned nr;             /** number of io_events */
+       unsigned head;
+       unsigned tail;
+ 
+       unsigned magic;
+       unsigned compat_features;
+       unsigned incompat_features;
+       unsigned header_length; /** size of aio_ring */
+
+       struct io_event events[0];
+};
+
+#define AIO_RING_MAGIC 0xa10a10a1
+
+static int user_io_getevents(io_context_t aio_ctx, unsigned int max,
+                       struct io_event *events)
+{
+       long i = 0;
+       unsigned head;
+       struct aio_ring *ring = (struct aio_ring*)aio_ctx;
+
+       while (i < max) {
+               head = ring->head;
+
+               if (head == ring->tail) {
+                       /* There are no more completions */
+                       break;
+               } else {
+                       /* There is another completion to reap */
+                       events[i] = ring->events[head];
+                       read_barrier();
+                       ring->head = (head + 1) % ring->nr;
+                       i++;
+               }
+       }
+
+       return i;
+}
+
 static int fio_libaio_getevents(struct thread_data *td, unsigned int min,
                                unsigned int max, struct timespec *t)
 {
@@ -66,7 +107,16 @@ static int fio_libaio_getevents(struct thread_data *td, unsigned int min,
        int r, events = 0;
 
        do {
-               r = io_getevents(ld->aio_ctx, actual_min, max, ld->aio_events + events, t);
+               if (td->o.userspace_libaio_reap == 1
+                   && actual_min == 0
+                   && ((struct aio_ring *)(ld->aio_ctx))->magic
+                               == AIO_RING_MAGIC) {
+                       r = user_io_getevents(ld->aio_ctx, max,
+                               ld->aio_events + events);
+               } else {
+                       r = io_getevents(ld->aio_ctx, actual_min,
+                               max, ld->aio_events + events, t);
+               }
                if (r >= 0)
                        events += r;
                else if (r == -EAGAIN)

diff --git a/fio.h b/fio.h
index 9d2a61ccedb2883aa00414ce84b80864af9af0c4..0c86f2882053e6bb37e74ff181e83eea426d9041 100644 (file)
--- a/fio.h
+++ b/fio.h
@@ -413,6 +413,8 @@ struct thread_options {
        unsigned int gid;
 
        unsigned int sync_file_range;
+
+       unsigned int userspace_libaio_reap;
 };
 
 #define FIO_VERROR_SIZE        128

diff --git a/options.c b/options.c
index 6a87e98fda6134f52167667225e69bd5757b296d..6f7c41ed1d3df25a07b0f08c932220f752ca553f 100644 (file)
--- a/options.c
+++ b/options.c
@@ -2069,6 +2069,15 @@ static struct fio_option options[FIO_MAX_OPTS] = {
                .off1   = td_var_offset(gid),
                .help   = "Run job with this group ID",
        },
+#ifdef FIO_HAVE_LIBAIO
+       {
+               .name   = "userspace_libaio_reap",
+               .type   = FIO_OPT_BOOL,
+               .off1   = td_var_offset(userspace_libaio_reap),
+               .help   = "When using the libaio engine with iodepth_batch_complete=0, enable userspace reaping",
+               .def    = "0",
+       },
+#endif
        {
                .name = NULL,
        },