Mark polled IO as being safe for dipping into the bio allocation cache, in case the targeted bio_set has it enabled. This brings an IOPOLL gen2 Optane QD=128 workload from ~3.0M IOPS to ~3.3M IOPS. Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 6c65c90131cb..ea387b0741b8 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2736,7 +2736,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) !kiocb->ki_filp->f_op->iopoll) return -EOPNOTSUPP; - kiocb->ki_flags |= IOCB_HIPRI; + kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; kiocb->ki_complete = io_complete_rw_iopoll; req->iopoll_completed = 0; } else { -- 2.32.0