diff mbox series

[19.11,V2,08/12] virtio: fix rx stats with vectorized functions

Message ID b639ae62e0f4be8864cb3969b1cbd26bfaf19c69.1565190405.git.thierry.herbelot@6wind.com (mailing list archive)
State Superseded, archived
Delegated to: Ferruh Yigit
Headers
Series Miscellaneous fixes |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/Intel-compilation fail Compilation issues

Commit Message

Thierry Herbelot Aug. 7, 2019, 3:09 p.m. UTC 
  From: Thibaut Collet <thibaut.collet@6wind.com>

With vectorized functions, only the rx stats for number of packets is
incremented.
Update also the other statistics.
Performance impact is about 2%

Fixes: fc3d66212fed ("virtio: add vector Rx")
Cc: stable@dpdk.org

Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
---
 drivers/net/virtio/virtio_rxtx.c             | 2 +-
 drivers/net/virtio/virtio_rxtx.h             | 2 ++
 drivers/net/virtio/virtio_rxtx_simple_neon.c | 6 ++++++
 drivers/net/virtio/virtio_rxtx_simple_sse.c  | 6 ++++++
 4 files changed, 15 insertions(+), 1 deletion(-)

Comments

Tiwei Bie Aug. 8, 2019, 5:15 a.m. UTC | #1 
On Wed, Aug 07, 2019 at 05:09:17PM +0200, Thierry Herbelot wrote:
> From: Thibaut Collet <thibaut.collet@6wind.com>
> 
> With vectorized functions, only the rx stats for number of packets is
> incremented.
> Update also the other statistics.
> Performance impact is about 2%

Could you share some details about your performance test?


> diff --git a/drivers/net/virtio/virtio_rxtx_simple_sse.c b/drivers/net/virtio/virtio_rxtx_simple_sse.c
> index af76708d66ae..c757e8c9d601 100644
> --- a/drivers/net/virtio/virtio_rxtx_simple_sse.c
> +++ b/drivers/net/virtio/virtio_rxtx_simple_sse.c
> @@ -48,6 +48,7 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
>  	struct vring_used_elem *rused;
>  	struct rte_mbuf **sw_ring;
>  	struct rte_mbuf **sw_ring_end;
> +	struct rte_mbuf **ref_rx_pkts;
>  	uint16_t nb_pkts_received = 0;
>  	__m128i shuf_msk1, shuf_msk2, len_adjust;
>  
> @@ -107,6 +108,7 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
>  			virtqueue_notify(vq);
>  	}
>  
> +	ref_rx_pkts = rx_pkts;
>  	for (nb_pkts_received = 0;
>  		nb_pkts_received < nb_used;) {
>  		__m128i desc[RTE_VIRTIO_DESC_PER_LOOP / 2];
> @@ -190,5 +192,9 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
>  	vq->vq_used_cons_idx += nb_pkts_received;
>  	vq->vq_free_cnt += nb_pkts_received;
>  	rxvq->stats.packets += nb_pkts_received;
> +	for (nb_used = 0; nb_used < nb_pkts_received; nb_used++) {
> +		rxvq->stats.bytes += ref_rx_pkts[nb_used]->pkt_len;
> +		virtio_update_packet_stats(&rxvq->stats, ref_rx_pkts[nb_used]);

The stats.bytes was updated twice by above code.

> +	}
>  	return nb_pkts_received;
>  }
> -- 
> 2.11.0
>
Thibaut Collet Aug. 8, 2019, 7:35 a.m. UTC | #2 
On Thu, Aug 8, 2019 at 7:17 AM Tiwei Bie <tiwei.bie@intel.com> wrote:
>
> On Wed, Aug 07, 2019 at 05:09:17PM +0200, Thierry Herbelot wrote:
> > From: Thibaut Collet <thibaut.collet@6wind.com>
> >
> > With vectorized functions, only the rx stats for number of packets is
> > incremented.
> > Update also the other statistics.
> > Performance impact is about 2%
>
> Could you share some details about your performance test?

The test has been done with a 6wind application based on dpdk and I
have not keep details. With test pmd impact is maybe a little bit
higher.

>
>
> > diff --git a/drivers/net/virtio/virtio_rxtx_simple_sse.c b/drivers/net/virtio/virtio_rxtx_simple_sse.c
> > index af76708d66ae..c757e8c9d601 100644
> > --- a/drivers/net/virtio/virtio_rxtx_simple_sse.c
> > +++ b/drivers/net/virtio/virtio_rxtx_simple_sse.c
> > @@ -48,6 +48,7 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
> >       struct vring_used_elem *rused;
> >       struct rte_mbuf **sw_ring;
> >       struct rte_mbuf **sw_ring_end;
> > +     struct rte_mbuf **ref_rx_pkts;
> >       uint16_t nb_pkts_received = 0;
> >       __m128i shuf_msk1, shuf_msk2, len_adjust;
> >
> > @@ -107,6 +108,7 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
> >                       virtqueue_notify(vq);
> >       }
> >
> > +     ref_rx_pkts = rx_pkts;
> >       for (nb_pkts_received = 0;
> >               nb_pkts_received < nb_used;) {
> >               __m128i desc[RTE_VIRTIO_DESC_PER_LOOP / 2];
> > @@ -190,5 +192,9 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
> >       vq->vq_used_cons_idx += nb_pkts_received;
> >       vq->vq_free_cnt += nb_pkts_received;
> >       rxvq->stats.packets += nb_pkts_received;
> > +     for (nb_used = 0; nb_used < nb_pkts_received; nb_used++) {
> > +             rxvq->stats.bytes += ref_rx_pkts[nb_used]->pkt_len;
> > +             virtio_update_packet_stats(&rxvq->stats, ref_rx_pkts[nb_used]);
>
> The stats.bytes was updated twice by above code.

Agree. My correction is an old one, done on the old 18.11 dpdk, and so
done before patch
https://git.dpdk.org/dpdk/commit/drivers/net/virtio/virtio_rxtx.c?id=81e5cdf19e583c742040d3be83b8cc79b451e243.
So the line
 +             rxvq->stats.bytes += ref_rx_pkts[nb_used]->pkt_len;
must be removed to be compliant with Ilya Maximets patch.

>
> > +     }
> >       return nb_pkts_received;
> >  }
> > --
> > 2.11.0
> >
diff mbox series

Patch

diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
index 27ead19fbe81..6dd62bf51863 100644
--- a/drivers/net/virtio/virtio_rxtx.c
+++ b/drivers/net/virtio/virtio_rxtx.c
@@ -1083,7 +1083,7 @@  virtio_discard_rxbuf_inorder(struct virtqueue *vq, struct rte_mbuf *m)
 	}
 }
 
-static inline void
+void
 virtio_update_packet_stats(struct virtnet_stats *stats, struct rte_mbuf *mbuf)
 {
 	uint32_t s = mbuf->pkt_len;
diff --git a/drivers/net/virtio/virtio_rxtx.h b/drivers/net/virtio/virtio_rxtx.h
index 685cc4f8104c..1eb8dae227ee 100644
--- a/drivers/net/virtio/virtio_rxtx.h
+++ b/drivers/net/virtio/virtio_rxtx.h
@@ -59,5 +59,7 @@  struct virtnet_ctl {
 };
 
 int virtio_rxq_vec_setup(struct virtnet_rx *rxvq);
+void virtio_update_packet_stats(struct virtnet_stats *stats,
+				struct rte_mbuf *mbuf);
 
 #endif /* _VIRTIO_RXTX_H_ */
diff --git a/drivers/net/virtio/virtio_rxtx_simple_neon.c b/drivers/net/virtio/virtio_rxtx_simple_neon.c
index cdc2a4d28ed5..e4b18cba0ce5 100644
--- a/drivers/net/virtio/virtio_rxtx_simple_neon.c
+++ b/drivers/net/virtio/virtio_rxtx_simple_neon.c
@@ -47,6 +47,7 @@  virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 	struct vring_used_elem *rused;
 	struct rte_mbuf **sw_ring;
 	struct rte_mbuf **sw_ring_end;
+	struct rte_mbuf **ref_rx_pkts;
 	uint16_t nb_pkts_received = 0;
 
 	uint8x16_t shuf_msk1 = {
@@ -105,6 +106,7 @@  virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 			virtqueue_notify(vq);
 	}
 
+	ref_rx_pkts = rx_pkts;
 	for (nb_pkts_received = 0;
 		nb_pkts_received < nb_used;) {
 		uint64x2_t desc[RTE_VIRTIO_DESC_PER_LOOP / 2];
@@ -204,5 +206,9 @@  virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 	vq->vq_used_cons_idx += nb_pkts_received;
 	vq->vq_free_cnt += nb_pkts_received;
 	rxvq->stats.packets += nb_pkts_received;
+	for (nb_used = 0; nb_used < nb_pkts_received; nb_used++) {
+		rxvq->stats.bytes += ref_rx_pkts[nb_used]->pkt_len;
+		virtio_update_packet_stats(&rxvq->stats, ref_rx_pkts[nb_used]);
+	}
 	return nb_pkts_received;
 }
diff --git a/drivers/net/virtio/virtio_rxtx_simple_sse.c b/drivers/net/virtio/virtio_rxtx_simple_sse.c
index af76708d66ae..c757e8c9d601 100644
--- a/drivers/net/virtio/virtio_rxtx_simple_sse.c
+++ b/drivers/net/virtio/virtio_rxtx_simple_sse.c
@@ -48,6 +48,7 @@  virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 	struct vring_used_elem *rused;
 	struct rte_mbuf **sw_ring;
 	struct rte_mbuf **sw_ring_end;
+	struct rte_mbuf **ref_rx_pkts;
 	uint16_t nb_pkts_received = 0;
 	__m128i shuf_msk1, shuf_msk2, len_adjust;
 
@@ -107,6 +108,7 @@  virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 			virtqueue_notify(vq);
 	}
 
+	ref_rx_pkts = rx_pkts;
 	for (nb_pkts_received = 0;
 		nb_pkts_received < nb_used;) {
 		__m128i desc[RTE_VIRTIO_DESC_PER_LOOP / 2];
@@ -190,5 +192,9 @@  virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 	vq->vq_used_cons_idx += nb_pkts_received;
 	vq->vq_free_cnt += nb_pkts_received;
 	rxvq->stats.packets += nb_pkts_received;
+	for (nb_used = 0; nb_used < nb_pkts_received; nb_used++) {
+		rxvq->stats.bytes += ref_rx_pkts[nb_used]->pkt_len;
+		virtio_update_packet_stats(&rxvq->stats, ref_rx_pkts[nb_used]);
+	}
 	return nb_pkts_received;
 }