diff options
| author | Jens Axboe <axboe@kernel.dk> | 2021-10-12 09:28:46 -0600 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2021-10-18 14:40:46 -0600 |
| commit | b688f11e86c9a22169a0e522530982735d2db19b (patch) | |
| tree | e8a8c0f3d88d4194576c61993e056075e4029fb6 | |
| parent | c234a65392062504acf04afe0ae404cca61a8e1a (diff) | |
io_uring: utilize the io batching infrastructure for more efficient polled IO
Wire up using an io_comp_batch for f_op->iopoll(). If the lower stack
supports it, we can handle high rates of polled IO more efficiently.
This raises the single core efficiency on my system from ~6.1M IOPS to
~6.6M IOPS running a random read workload at depth 128 on two gen2
Optane drives.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
| -rw-r--r-- | fs/io_uring.c | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c index cd77a137f2d8..d4631a55a692 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2458,6 +2458,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, { struct io_kiocb *req, *tmp; unsigned int poll_flags = BLK_POLL_NOSLEEP; + DEFINE_IO_COMP_BATCH(iob); LIST_HEAD(done); /* @@ -2483,17 +2484,20 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, if (!list_empty(&done)) break; - ret = kiocb->ki_filp->f_op->iopoll(kiocb, NULL, poll_flags); + ret = kiocb->ki_filp->f_op->iopoll(kiocb, &iob, poll_flags); if (unlikely(ret < 0)) return ret; else if (ret) poll_flags |= BLK_POLL_ONESHOT; /* iopoll may have completed current req */ - if (READ_ONCE(req->iopoll_completed)) + if (!rq_list_empty(iob.req_list) || + READ_ONCE(req->iopoll_completed)) list_move_tail(&req->inflight_entry, &done); } + if (!rq_list_empty(iob.req_list)) + iob.complete(&iob); if (!list_empty(&done)) io_iopoll_complete(ctx, nr_events, &done); |