This patch supports mq_ops->queue_rqs() hook. It has an advantage of
batch submission to virtio-blk driver. It also helps polling I/O because
polling uses batched completion of block layer. Batch submission in
queue_rqs() can boost polling performance.
In queue_rqs(), it iterates plug->mq_list, collects requests that
belong to same HW queue and adds requests into virtqueue until it
encounters a request from other HW queue or sees the end of the list.
Then, virtio-blk kicks virtqueue to submit requests.
If there is an error, it inserts error request to requeue_list and
passes it to ordinary block layer path.
For verification, I did fio test.
(io_uring, randread, direct=1, bs=4K, iodepth=64 numjobs=N)
I set 4 vcpu and 2 virtio-blk queues for VM and run fio test 5 times.
It shows about 1-4% improvement.
| numjobs=2 | numjobs=4
-----------------------------------------------------------
fio without queue_rqs() | 282K IOPS | 245K IOPS
-----------------------------------------------------------
fio with queue_rqs() | 294K IOPS | 249K IOPS
For polling I/O performance, I also did fio test as below.
(io_uring, hipri, randread, direct=1, bs=512, iodepth=64 numjobs=4)
I set 4 vcpu and 2 poll queues for VM.
It shows upto 7% improvement in polling I/O.
| IOPS | avg latency
-----------------------------------------------------------
fio poll without queue_rqs() | 413K | 619.72 usec
-----------------------------------------------------------
fio poll with queue_rqs() | 445K | 581.2 usec
Signed-off-by: Suwan Kim <suwan.kim027@xxxxxxxxx>
---
drivers/block/virtio_blk.c | 93 ++++++++++++++++++++++++++++++++++----
1 file changed, 84 insertions(+), 9 deletions(-)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 3d16f8b753e7..4a0a3b2d9caf 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -311,6 +311,28 @@ static void virtio_commit_rqs(struct blk_mq_hw_ctx *hctx)
virtqueue_notify(vq->vq);
}
+static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
+ struct virtio_blk *vblk,
+ struct request *req,
+ struct virtblk_req *vbr, int *num)
+{
+ blk_status_t status;
+
+ status = virtblk_setup_cmd(vblk->vdev, req, vbr);
+ if (unlikely(status))
+ return status;
+
+ blk_mq_start_request(req);
+
+ *num = virtblk_map_data(hctx, req, vbr);
+ if (unlikely(*num < 0)) {
+ virtblk_cleanup_cmd(req);
+ return BLK_STS_RESOURCE;
+ }
+
+ return BLK_STS_OK;
+}
+
static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
@@ -324,18 +346,10 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
blk_status_t status;
int err;
- status = virtblk_setup_cmd(vblk->vdev, req, vbr);
+ status = virtblk_prep_rq(hctx, vblk, req, vbr, &num);
if (unlikely(status))
return status;
- blk_mq_start_request(req);
-
- num = virtblk_map_data(hctx, req, vbr);
- if (unlikely(num < 0)) {
- virtblk_cleanup_cmd(req);
- return BLK_STS_RESOURCE;
- }
-
spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg_table.sgl, num);
if (err) {
@@ -367,6 +381,66 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
return BLK_STS_OK;
}
+static bool virtblk_prep_rq_batch(struct virtio_blk_vq *vq, struct request *req)
+{
+ struct virtio_blk *vblk = req->mq_hctx->queue->queuedata;
+ struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+ unsigned long flags;
+ int num, err;
+
+ req->mq_hctx->tags->rqs[req->tag] = req;
+
+ if (virtblk_prep_rq(req->mq_hctx, vblk, req, vbr, &num) != BLK_STS_OK)
+ return false;
+
+ spin_lock_irqsave(&vq->lock, flags);
+ err = virtblk_add_req(vq->vq, vbr, vbr->sg_table.sgl, num);
+ if (err) {
+ spin_unlock_irqrestore(&vq->lock, flags);
+ virtblk_unmap_data(req, vbr);
+ virtblk_cleanup_cmd(req);
+ return false;
+ }
+ spin_unlock_irqrestore(&vq->lock, flags);
+
+ return true;
+}
+
+static void virtio_queue_rqs(struct request **rqlist)
+{
+ struct request *req, *next, *prev = NULL;
+ struct request *requeue_list = NULL;
+
+ rq_list_for_each_safe(rqlist, req, next) {
+ struct virtio_blk_vq *vq = req->mq_hctx->driver_data;
+ unsigned long flags;
+ bool kick;
+
+ if (!virtblk_prep_rq_batch(vq, req)) {
+ rq_list_move(rqlist, &requeue_list, req, prev);
+ req = prev;
+
+ if (!req)
+ continue;
+ }
+
+ if (!next || req->mq_hctx != next->mq_hctx) {
+ spin_lock_irqsave(&vq->lock, flags);
+ kick = virtqueue_kick_prepare(vq->vq);
+ spin_unlock_irqrestore(&vq->lock, flags);
+ if (kick)
+ virtqueue_notify(vq->vq);
+
+ req->rq_next = NULL;
+ *rqlist = next;
+ prev = NULL;
+ } else
+ prev = req;
+ }
+
+ *rqlist = requeue_list;
+}
+
/* return id (s/n) string for *disk to *id_str
*/
static int virtblk_get_id(struct gendisk *disk, char *id_str)
@@ -823,6 +897,7 @@ static int virtblk_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
static const struct blk_mq_ops virtio_mq_ops = {
.queue_rq = virtio_queue_rq,
+ .queue_rqs = virtio_queue_rqs,
.commit_rqs = virtio_commit_rqs,
.init_hctx = virtblk_init_hctx,
.complete = virtblk_request_done,
--
2.26.3
