[dpdk-dev] [PATCH v2 2/2] vhost: introduce async enqueue for split ring

[Liu, Yong]

> 
> +#define VHOST_ASYNC_BATCH_THRESHOLD 8
> +

Not very clear about why batch number is 8. It is better to save it in rte_vhost_async_features if the value come from hardware requirement. 

> +
> +static __rte_noinline uint32_t
> +virtio_dev_rx_async_submit_split(struct virtio_net *dev,
> +	struct vhost_virtqueue *vq, uint16_t queue_id,
> +	struct rte_mbuf **pkts, uint32_t count)
> +{
> +	uint32_t pkt_idx = 0, pkt_burst_idx = 0;
> +	uint16_t num_buffers;
> +	struct buf_vector buf_vec[BUF_VECTOR_MAX];
> +	uint16_t avail_head, last_idx, shadow_idx;
> +
> +	struct rte_vhost_iov_iter *it_pool = vq->it_pool;
> +	struct iovec *vec_pool = vq->vec_pool;
> +	struct rte_vhost_async_desc tdes[MAX_PKT_BURST];
> +	struct iovec *src_iovec = vec_pool;
> +	struct iovec *dst_iovec = vec_pool + (VHOST_MAX_ASYNC_VEC >> 1);
> +	struct rte_vhost_iov_iter *src_it = it_pool;
> +	struct rte_vhost_iov_iter *dst_it = it_pool + 1;
> +	uint16_t n_free_slot, slot_idx;
> +	int n_pkts = 0;
> +
> +	avail_head = *((volatile uint16_t *)&vq->avail->idx);
> +	last_idx = vq->last_avail_idx;
> +	shadow_idx = vq->shadow_used_idx;
> +
> +	/*
> +	 * The ordering between avail index and
> +	 * desc reads needs to be enforced.
> +	 */
> +	rte_smp_rmb();
> +
> +	rte_prefetch0(&vq->avail->ring[vq->last_avail_idx & (vq->size - 1)]);
> +
> +	for (pkt_idx = 0; pkt_idx < count; pkt_idx++) {
> +		uint32_t pkt_len = pkts[pkt_idx]->pkt_len + dev->vhost_hlen;
> +		uint16_t nr_vec = 0;
> +
> +		if (unlikely(reserve_avail_buf_split(dev, vq,
> +						pkt_len, buf_vec,
> &num_buffers,
> +						avail_head, &nr_vec) < 0)) {
> +			VHOST_LOG_DATA(DEBUG,
> +				"(%d) failed to get enough desc from
> vring\n",
> +				dev->vid);
> +			vq->shadow_used_idx -= num_buffers;
> +			break;
> +		}
> +
> +		VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end
> index %d\n",
> +			dev->vid, vq->last_avail_idx,
> +			vq->last_avail_idx + num_buffers);
> +
> +		if (async_mbuf_to_desc(dev, vq, pkts[pkt_idx],
> +				buf_vec, nr_vec, num_buffers,
> +				src_iovec, dst_iovec, src_it, dst_it) < 0) {
> +			vq->shadow_used_idx -= num_buffers;
> +			break;
> +		}
> +
> +		slot_idx = (vq->async_pkts_idx + pkt_idx) & (vq->size - 1);
> +		if (src_it->count) {
> +			async_fill_des(&tdes[pkt_burst_idx], src_it, dst_it);
> +			pkt_burst_idx++;
> +			vq->async_pending_info[slot_idx] =
> +				num_buffers | (src_it->nr_segs << 16);
> +			src_iovec += src_it->nr_segs;
> +			dst_iovec += dst_it->nr_segs;
> +			src_it += 2;
> +			dst_it += 2;

Patrick, 
In my understanding, nr_segs type definition can follow nr_vec type definition (uint16_t). By that can short the data saved in async_pkts_pending from 64bit to 32bit. 
Since those information will be used in datapath, the smaller size will get the better perf. 

It is better to replace integer 2 with macro. 

Thanks,
Marvin