Currently, the dpdk-vhost side in ovs doesn't support tcp/udp tx cksum. So L4 packets's cksum were calculated in VM side but performance is not good. Implementing tcp/udp tx cksum in ovs-dpdk side improves throughput in VM->phy->phy->VM situation. And it makes virtio-net frontend-driver support NETIF_F_SG(feature scatter-gather) as well.
Signed-off-by: Zhenyu Gao <[email protected]> --- Here is some performance number: Setup: qperf client +---------+ | VM | +---------+ | | qperf server +--------------+ +------------+ | vswitch+dpdk | | bare-metal | +--------------+ +------------+ | | | | pNic---------PhysicalSwitch---- do cksum in ovs-dpdk: Applied this patch and execute 'ethtool -K eth0 tx on' in VM side. It offload cksum job to ovs-dpdk side. do cksum in VM: Applied this patch and execute 'ethtool -K eth0 tx off' in VM side. VM calculate cksum for tcp/udp packets. We can see huge improvment in TCP throughput if we leverage ovs-dpdk cksum. [root@localhost ~]# qperf -t 10 -oo msg_size:1:64K:*2 host-qperf-server01 tcp_bw tcp_lat udp_bw udp_lat do cksum in ovs-dpdk do cksum in VM without this patch tcp_bw: bw = 1.9 MB/sec bw = 1.92 MB/sec bw = 1.95 MB/sec tcp_bw: bw = 3.97 MB/sec bw = 3.99 MB/sec bw = 3.98 MB/sec tcp_bw: bw = 7.75 MB/sec bw = 7.79 MB/sec bw = 7.89 MB/sec tcp_bw: bw = 14.7 MB/sec bw = 14.7 MB/sec bw = 14.9 MB/sec tcp_bw: bw = 27.7 MB/sec bw = 27.4 MB/sec bw = 28 MB/sec tcp_bw: bw = 51.1 MB/sec bw = 51.3 MB/sec bw = 51.8 MB/sec tcp_bw: bw = 86.2 MB/sec bw = 84.4 MB/sec bw = 87.6 MB/sec tcp_bw: bw = 141 MB/sec bw = 142 MB/sec bw = 141 MB/sec tcp_bw: bw = 203 MB/sec bw = 201 MB/sec bw = 211 MB/sec tcp_bw: bw = 267 MB/sec bw = 250 MB/sec bw = 260 MB/sec tcp_bw: bw = 324 MB/sec bw = 295 MB/sec bw = 302 MB/sec tcp_bw: bw = 397 MB/sec bw = 363 MB/sec bw = 347 MB/sec tcp_bw: bw = 765 MB/sec bw = 510 MB/sec bw = 383 MB/sec tcp_bw: bw = 850 MB/sec bw = 710 MB/sec bw = 417 MB/sec tcp_bw: bw = 1.09 GB/sec bw = 860 MB/sec bw = 444 MB/sec tcp_bw: bw = 1.17 GB/sec bw = 979 MB/sec bw = 447 MB/sec tcp_bw: bw = 1.17 GB/sec bw = 1.07 GB/sec bw = 462 MB/sec tcp_lat: latency = 29.1 us latency = 28.7 us latency = 29.1 us tcp_lat: latency = 29 us latency = 28.8 us latency = 29 us tcp_lat: latency = 29 us latency = 28.8 us latency = 29 us tcp_lat: latency = 29 us latency = 28.9 us latency = 29 us tcp_lat: latency = 29.2 us latency = 28.9 us latency = 29.1 us tcp_lat: latency = 29.1 us latency = 29.1 us latency = 29.1 us tcp_lat: latency = 29.5 us latency = 29.5 us latency = 29.5 us tcp_lat: latency = 29.8 us latency = 29.8 us latency = 29.9 us tcp_lat: latency = 30.7 us latency = 30.7 us latency = 30.7 us tcp_lat: latency = 47.1 us latency = 46.2 us latency = 47.1 us tcp_lat: latency = 52.1 us latency = 52.3 us latency = 53.3 us tcp_lat: latency = 44 us latency = 43.8 us latency = 43.2 us tcp_lat: latency = 50 us latency = 46.6 us latency = 47.8 us tcp_lat: latency = 79.2 us latency = 77.9 us latency = 78.9 us tcp_lat: latency = 82.3 us latency = 81.7 us latency = 82.2 us tcp_lat: latency = 96.7 us latency = 90.8 us latency = 127 us tcp_lat: latency = 215 us latency = 177 us latency = 225 us udp_bw: send_bw = 422 KB/sec send_bw = 415 KB/sec send_bw = 405 KB/sec recv_bw = 402 KB/sec recv_bw = 404 KB/sec recv_bw = 403 KB/sec udp_bw: send_bw = 845 KB/sec send_bw = 835 KB/sec send_bw = 802 KB/sec recv_bw = 831 KB/sec recv_bw = 804 KB/sec recv_bw = 802 KB/sec udp_bw: send_bw = 1.69 MB/sec send_bw = 1.66 MB/sec send_bw = 1.62 MB/sec recv_bw = 1.45 MB/sec recv_bw = 1.63 MB/sec recv_bw = 1.6 MB/sec udp_bw: send_bw = 3.38 MB/sec send_bw = 3.33 MB/sec send_bw = 3.24 MB/sec recv_bw = 3.32 MB/sec recv_bw = 3.25 MB/sec recv_bw = 3.24 MB/sec udp_bw: send_bw = 6.76 MB/sec send_bw = 6.63 MB/sec send_bw = 6.47 MB/sec recv_bw = 6.42 MB/sec recv_bw = 5.59 MB/sec recv_bw = 6.45 MB/sec udp_bw: send_bw = 13.5 MB/sec send_bw = 13.3 MB/sec send_bw = 13 MB/sec recv_bw = 13.4 MB/sec recv_bw = 12.1 MB/sec recv_bw = 13 MB/sec udp_bw: send_bw = 27 MB/sec send_bw = 26.5 MB/sec send_bw = 25.9 MB/sec recv_bw = 26.4 MB/sec recv_bw = 21.5 MB/sec recv_bw = 25.9 MB/sec udp_bw: send_bw = 53.8 MB/sec send_bw = 52.9 MB/sec send_bw = 51.7 MB/sec recv_bw = 49.1 MB/sec recv_bw = 47.6 MB/sec recv_bw = 51.1 MB/sec udp_bw: send_bw = 108 MB/sec send_bw = 105 MB/sec send_bw = 102 MB/sec recv_bw = 91.1 MB/sec recv_bw = 101 MB/sec recv_bw = 100 MB/sec udp_bw: send_bw = 212 MB/sec send_bw = 208 MB/sec send_bw = 203 MB/sec recv_bw = 204 MB/sec recv_bw = 204 MB/sec recv_bw = 169 MB/sec udp_bw: send_bw = 414 MB/sec send_bw = 407 MB/sec send_bw = 398 MB/sec recv_bw = 403 MB/sec recv_bw = 312 MB/sec recv_bw = 343 MB/sec udp_bw: send_bw = 555 MB/sec send_bw = 561 MB/sec send_bw = 557 MB/sec recv_bw = 354 MB/sec recv_bw = 368 MB/sec recv_bw = 360 MB/sec udp_bw: send_bw = 877 MB/sec send_bw = 880 MB/sec send_bw = 868 MB/sec recv_bw = 551 MB/sec recv_bw = 542 MB/sec recv_bw = 562 MB/sec udp_bw: send_bw = 1.1 GB/sec send_bw = 1.08 GB/sec send_bw = 1.09 GB/sec recv_bw = 805 MB/sec recv_bw = 785 MB/sec recv_bw = 766 MB/sec udp_bw: send_bw = 1.21 GB/sec send_bw = 1.19 GB/sec send_bw = 1.22 GB/sec recv_bw = 899 MB/sec recv_bw = 715 MB/sec recv_bw = 700 MB/sec udp_bw: send_bw = 1.31 GB/sec send_bw = 1.31 GB/sec send_bw = 1.31 GB/sec recv_bw = 614 MB/sec recv_bw = 622 MB/sec recv_bw = 661 MB/sec udp_bw: send_bw = 0 bytes/sec send_bw = 0 bytes/sec send_bw = 0 bytes/sec recv_bw = 0 bytes/sec recv_bw = 0 bytes/sec recv_bw = 0 bytes/sec udp_lat: latency = 25.9 us latency = 26.5 us latency = 26.5 us udp_lat: latency = 26.3 us latency = 26.4 us latency = 26.5 us udp_lat: latency = 26 us latency = 26.4 us latency = 26.6 us udp_lat: latency = 26.1 us latency = 26.2 us latency = 26.4 us udp_lat: latency = 26.3 us latency = 26.5 us latency = 26.7 us udp_lat: latency = 26.3 us latency = 26.4 us latency = 26.5 us udp_lat: latency = 26.3 us latency = 26.7 us latency = 26.9 us udp_lat: latency = 27.1 us latency = 27.1 us latency = 27.2 us udp_lat: latency = 27.5 us latency = 27.8 us latency = 28.1 us udp_lat: latency = 28.7 us latency = 28.9 us latency = 29.1 us udp_lat: latency = 30.4 us latency = 30.5 us latency = 30.9 us udp_lat: latency = 41.2 us latency = 41.3 us latency = 41.1 us udp_lat: latency = 41.3 us latency = 41.5 us latency = 41.5 us udp_lat: latency = 64.4 us latency = 64.5 us latency = 64.2 us udp_lat: latency = 71.5 us latency = 71.5 us latency = 71.7 us udp_lat: latency = 120 us latency = 120 us latency = 120 us udp_lat: latency = 0 ns latency = 0 ns latency = 0 ns lib/netdev-dpdk.c | 79 ++++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 75 insertions(+), 4 deletions(-) diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c index f58e9be..0f91def 100644 --- a/lib/netdev-dpdk.c +++ b/lib/netdev-dpdk.c @@ -31,6 +31,7 @@ #include <rte_errno.h> #include <rte_eth_ring.h> #include <rte_ethdev.h> +#include <rte_ip.h> #include <rte_malloc.h> #include <rte_mbuf.h> #include <rte_meter.h> @@ -992,8 +993,7 @@ netdev_dpdk_vhost_construct(struct netdev *netdev) err = rte_vhost_driver_disable_features(dev->vhost_id, 1ULL << VIRTIO_NET_F_HOST_TSO4 - | 1ULL << VIRTIO_NET_F_HOST_TSO6 - | 1ULL << VIRTIO_NET_F_CSUM); + | 1ULL << VIRTIO_NET_F_HOST_TSO6); if (err) { VLOG_ERR("rte_vhost_driver_disable_features failed for vhost user " "port: %s\n", name); @@ -1455,6 +1455,76 @@ netdev_dpdk_rxq_dealloc(struct netdev_rxq *rxq) rte_free(rx); } +static inline void +netdev_dpdk_vhost_refill_l4_cksum(const char *data, struct dp_packet *pkt, + uint8_t l4_proto, bool is_ipv4) +{ + void *l3hdr = (void *)(data + pkt->mbuf.l2_len); + + if (l4_proto == IPPROTO_TCP) { + struct tcp_header *tcp_hdr = (struct tcp_header *)(data + + pkt->mbuf.l2_len + pkt->mbuf.l3_len); + + tcp_hdr->tcp_csum = 0; + if (is_ipv4) { + tcp_hdr->tcp_csum = rte_ipv4_udptcp_cksum(l3hdr, tcp_hdr); + } else { + tcp_hdr->tcp_csum = rte_ipv6_udptcp_cksum(l3hdr, tcp_hdr); + } + } else if (l4_proto == IPPROTO_UDP) { + struct udp_header *udp_hdr = (struct udp_header *)(data + + pkt->mbuf.l2_len + pkt->mbuf.l3_len); + /* do not recalculate udp cksum if it was 0 */ + if (udp_hdr->udp_csum != 0) { + udp_hdr->udp_csum = 0; + if (is_ipv4) { + /*do not calculate udp cksum if it was a fragment IP*/ + if (IP_IS_FRAGMENT(((struct ipv4_hdr *)l3hdr)-> + fragment_offset)) { + return; + } + + udp_hdr->udp_csum = rte_ipv4_udptcp_cksum(l3hdr, udp_hdr); + } else { + udp_hdr->udp_csum = rte_ipv6_udptcp_cksum(l3hdr, udp_hdr); + } + } + } + + pkt->mbuf.ol_flags &= ~PKT_TX_L4_MASK; +} + +static inline void +netdev_dpdk_vhost_tx_csum(struct dp_packet **pkts, int pkt_cnt) +{ + int i; + + for (i = 0; i < pkt_cnt; i++) { + ovs_be16 dl_type; + struct dp_packet *pkt = (struct dp_packet *)pkts[i]; + const char *data = dp_packet_data(pkt); + void *l3hdr = (char *)(data + pkt->mbuf.l2_len); + + if (!(pkt->mbuf.ol_flags & PKT_TX_L4_MASK)) { + /* DPDK vhost tags PKT_TX_L4_MASK if a L4 packet need cksum. */ + continue; + } + + if (OVS_UNLIKELY(pkt->mbuf.l2_len == 0 || pkt->mbuf.l3_len == 0)) { + continue; + } + + dl_type = *(ovs_be16 *)(data + pkt->mbuf.l2_len - sizeof dl_type); + if (dl_type == htons(ETH_TYPE_IP)) { + uint8_t l4_proto = ((struct ipv4_hdr *)l3hdr)->next_proto_id; + netdev_dpdk_vhost_refill_l4_cksum(data, pkt, l4_proto, true); + } else if (dl_type == htons(ETH_TYPE_IPV6)) { + uint8_t l4_proto = ((struct ipv6_hdr *)l3hdr)->proto; + netdev_dpdk_vhost_refill_l4_cksum(data, pkt, l4_proto, false); + } + } +} + /* Tries to transmit 'pkts' to txq 'qid' of device 'dev'. Takes ownership of * 'pkts', even in case of failure. * @@ -1646,6 +1716,8 @@ netdev_dpdk_vhost_rxq_recv(struct netdev_rxq *rxq, dp_packet_batch_init_cutlen(batch); batch->count = (int) nb_rx; + netdev_dpdk_vhost_tx_csum(batch->packets, batch->count); + return 0; } @@ -3288,8 +3360,7 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev) err = rte_vhost_driver_disable_features(dev->vhost_id, 1ULL << VIRTIO_NET_F_HOST_TSO4 - | 1ULL << VIRTIO_NET_F_HOST_TSO6 - | 1ULL << VIRTIO_NET_F_CSUM); + | 1ULL << VIRTIO_NET_F_HOST_TSO6); if (err) { VLOG_ERR("rte_vhost_driver_disable_features failed for vhost user " "client port: %s\n", dev->up.name); -- 1.8.3.1 _______________________________________________ dev mailing list [email protected] https://mail.openvswitch.org/mailman/listinfo/ovs-dev
