From: Niklas Cassel <niklas.cassel@xxxxxxx>
Commit 7c70f506e438 ("engines/io_uring: move sqe clear out of hot path")
removed the memset of sqe from fio_ioring_prep().
Before this commit, fio_ioring_prio_prep() behaved properly, because
sqe->ioprio was always cleared by the memset in fio_ioring_prep().
cmdprio_percentage=20 is supposed to set the highest priority class for
20% of the total I/Os, however, because sqes got reused without clearing
the ioprio field, this meant that the number of I/Os sent with the highest
priority became 95% already after 10 seconds. Quite far off from the
intended 20%.
Fix this by explicitly clearing the priority in fio_ioring_prio_prep().
Note that prio/prioclass cannot be used together with cmdprio_percentage,
so we do not need to do an additional clear in fio_ioring_prep().
engines/libaio.c doesn't explicitly clear the ioprio, nor does it memset
the descriptor entry, this is because io_prep_pread()/io_prep_pwrite() in
libaio itself performs a memset.
Fixes: 7c70f506e438 ("engines/io_uring: move sqe clear out of hot path")
Signed-off-by: Niklas Cassel <niklas.cassel@xxxxxxx>
---
engines/io_uring.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/engines/io_uring.c b/engines/io_uring.c
index 2b65572d..b8d4cf91 100644
--- a/engines/io_uring.c
+++ b/engines/io_uring.c
@@ -384,6 +384,8 @@ static void fio_ioring_prio_prep(struct thread_data *td, struct io_u *io_u)
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;
+ } else {
+ ld->sqes[io_u->index].ioprio = 0;
}
return;
}
--
2.31.1
