Add vhost code change before test Signed-off-by: Yinan Wang <yinan.wang@intel.com> --- test_plans/dpdk_gro_lib_test_plan.rst | 43 +++++++++++++++++---------- 1 file changed, 27 insertions(+), 16 deletions(-) diff --git a/test_plans/dpdk_gro_lib_test_plan.rst b/test_plans/dpdk_gro_lib_test_plan.rst index 410ae68..1ec8c23 100644 --- a/test_plans/dpdk_gro_lib_test_plan.rst +++ b/test_plans/dpdk_gro_lib_test_plan.rst @@ -84,12 +84,31 @@ Modify the testpmd code as following:: parse_ethernet(eth_hdr, &info); l3_hdr = (char *)eth_hdr + info.l2_len; +Also modify the dpdk code as following:: + + --- a/drivers/net/vhost/rte_eth_vhost.c + +++ b/drivers/net/vhost/rte_eth_vhost.c + @@ -1071,8 +1071,14 @@ eth_dev_info(struct rte_eth_dev *dev, + dev_info->min_rx_bufsize = 0; + dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS | + - DEV_TX_OFFLOAD_VLAN_INSERT; + - dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP; + + DEV_TX_OFFLOAD_VLAN_INSERT | + + DEV_TX_OFFLOAD_UDP_CKSUM | + + DEV_TX_OFFLOAD_TCP_CKSUM | + + DEV_TX_OFFLOAD_IPV4_CKSUM | + + DEV_TX_OFFLOAD_TCP_TSO; + + dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP | + + DEV_RX_OFFLOAD_TCP_CKSUM | + + DEV_RX_OFFLOAD_UDP_CKSUM | + + DEV_RX_OFFLOAD_IPV4_CKSUM | + + DEV_RX_OFFLOAD_TCP_LRO; + } + Test flow ========= -:: - - NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net +NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic ========================================================= @@ -121,9 +140,7 @@ Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic testpmd>port start 1 testpmd>start -3. Set up vm with virto device and using kernel virtio-net driver: - - :: +3. Set up vm with virto device and using kernel virtio-net driver:: taskset -c 13 \ qemu-system-x86_64 -name us-vhost-vm1 \ @@ -176,9 +193,7 @@ Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic testpmd>port start 1 testpmd>start -3. Set up vm with virto device and using kernel virtio-net driver: - - :: +3. Set up vm with virto device and using kernel virtio-net driver:: taskset -c 13 \ qemu-system-x86_64 -name us-vhost-vm1 \ @@ -231,9 +246,7 @@ Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic testpmd>port start 1 testpmd>start -3. Set up vm with virto device and using kernel virtio-net driver: - - :: +3. Set up vm with virto device and using kernel virtio-net driver:: taskset -c 13 \ qemu-system-x86_64 -name us-vhost-vm1 \ @@ -308,9 +321,7 @@ Vxlan topology testpmd>port start 1 testpmd>start -3. Set up vm with virto device and using kernel virtio-net driver: - - :: +3. Set up vm with virto device and using kernel virtio-net driver:: taskset -c 13 \ qemu-system-x86_64 -name us-vhost-vm1 \ @@ -335,4 +346,4 @@ Vxlan topology 5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log:: Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 2 -t 60 -f g -m - VM side: iperf -s -f g \ No newline at end of file + VM side: iperf -s -f g -- 2.17.1
Add cbdma enable case in dpdk gro lib test plan Signed-off-by: Yinan Wang <yinan.wang@intel.com> --- test_plans/dpdk_gro_lib_test_plan.rst | 60 ++++++++++++++++++++++++++- 1 file changed, 58 insertions(+), 2 deletions(-) diff --git a/test_plans/dpdk_gro_lib_test_plan.rst b/test_plans/dpdk_gro_lib_test_plan.rst index 1ec8c23..b71023e 100644 --- a/test_plans/dpdk_gro_lib_test_plan.rst +++ b/test_plans/dpdk_gro_lib_test_plan.rst @@ -275,8 +275,6 @@ Test Case4: DPDK GRO test with vxlan traffic Vxlan topology -------------- -:: - VM Host 50.1.1.2 50.1.1.1 | | @@ -347,3 +345,61 @@ Vxlan topology Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 2 -t 60 -f g -m VM side: iperf -s -f g + +Test Case5: DPDK GRO test with CBDMA enable using tcp/ipv4 traffic +================================================================== + +Test flow +========= + +NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net + +1. Connect two nic port directly, put nic2 into another namesapce and turn on the tso of this nic port by below cmds:: + + ip netns del ns1 + ip netns add ns1 + ip link set enp26s0f0 netns ns1 # [enp216s0f0] is the name of nic2 + ip netns exec ns1 ifconfig enp26s0f0 1.1.1.8 up + ip netns exec ns1 ethtool -K enp26s0f0 tso on + +2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1:: + + ./dpdk-devbind.py -b igb_uio xx:xx.x + ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-30 -n 4 \ + --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 + testpmd>set fwd csum + testpmd>stop + testpmd>port stop 0 + testpmd>port stop 1 + testpmd>csum set tcp hw 0 + testpmd>csum set ip hw 0 + testpmd>csum set tcp hw 1 + testpmd>csum set ip hw 1 + testpmd>set port 0 gro on + testpmd>set gro flush 1 + testpmd>port start 0 + testpmd>port start 1 + testpmd>start + +3. Set up vm with virto device and using kernel virtio-net driver:: + + taskset -c 31 /home/qemu-install/qemu-3.0/bin/qemu-system-x86_64 -name us-vhost-vm1 \ + -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu1910.img \ + -chardev socket,id=char0,path=./vhost-net \ + -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \ + -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \ + -vnc :10 -daemonize + +4. In vm, config the virtio-net device with ip and turn the kernel gro off:: + + ifconfig ens4 1.1.1.2 up # [ens3] is the name of virtio-net + ethtool -L ens4 combined 2 + ethtool -K ens4 gro off + +5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get better performance than case 1:: + + Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2 + VM side: iperf -s -- 2.17.1
Add 2 queue case for performance check Signed-off-by: Yinan Wang <yinan.wang@intel.com> --- test_plans/dpdk_gro_lib_test_plan.rst | 94 ++++++++++++++++++++++----- 1 file changed, 76 insertions(+), 18 deletions(-) diff --git a/test_plans/dpdk_gro_lib_test_plan.rst b/test_plans/dpdk_gro_lib_test_plan.rst index ea0244c..59ac0f1 100644 --- a/test_plans/dpdk_gro_lib_test_plan.rst +++ b/test_plans/dpdk_gro_lib_test_plan.rst @@ -130,7 +130,7 @@ Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic 2. Bind nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1:: ./dpdk-devbind.py -b igb_uio xx:xx.x - ./testpmd -l 2-4 -n 4 \ + ./testpmd -l 2-4 -n 4 --socket-mem 1024,1024 --legacy-mem \ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024 testpmd>set fwd csum testpmd>stop @@ -151,8 +151,8 @@ Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ - -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \ @@ -182,7 +182,7 @@ Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic 2. Bind nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 2:: ./dpdk-devbind.py -b igb_uio xx:xx.x - ./testpmd -l 2-4 -n 4 \ + ./testpmd -l 2-4 -n 4 --socket-mem 1024,1024 --legacy-mem \ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024 testpmd>set fwd csum testpmd>stop @@ -203,8 +203,8 @@ Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ - -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \ @@ -234,7 +234,7 @@ Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic 2. Bind nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 4:: ./dpdk-devbind.py -b igb_uio xx:xx.x - ./testpmd -l 2-4 -n 4 \ + ./testpmd -l 2-4 -n 4 --socket-mem 1024,1024 --legacy-mem \ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024 testpmd>set fwd csum testpmd>stop @@ -255,8 +255,8 @@ Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ - -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \ @@ -301,7 +301,7 @@ Vxlan topology 2. Bind nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 4:: ./dpdk-devbind.py -b igb_uio xx:xx.x - ./testpmd -l 2-4 -n 4 \ + ./testpmd -l 2-4 -n 4 --socket-mem 1024,1024 --legacy-mem \ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024 testpmd>set fwd csum testpmd>stop @@ -325,8 +325,8 @@ Vxlan topology taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ - -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \ @@ -346,8 +346,8 @@ Vxlan topology Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 2 -t 60 -f g -m VM side: iperf -s -f g -Test Case5: DPDK GRO test with CBDMA enable using tcp/ipv4 traffic -================================================================== +Test Case5: DPDK GRO test with 2 queues using tcp/ipv4 traffic +============================================================== Test flow ========= @@ -365,8 +365,8 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net 2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1:: ./dpdk-devbind.py -b igb_uio xx:xx.x - ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-30 -n 4 \ - --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 + ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-31 -n 4 \ + --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 --nb-cores=2 set fwd csum stop port stop 0 @@ -383,11 +383,11 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net 3. Set up vm with virto device and using kernel virtio-net driver:: - taskset -c 31 /home/qemu-install/qemu-3.0/bin/qemu-system-x86_64 -name us-vhost-vm1 \ + taskset -c 31 /home/qemu-install/qemu-4.2.1/bin/qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu1910.img \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \ @@ -403,3 +403,61 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2 VM side: iperf -s + +Test Case6: DPDK GRO test with CBDMA enable using tcp/ipv4 traffic +================================================================== + +Test flow +========= + +NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net + +1. Connect two nic port directly, put nic2 into another namesapce and turn on the tso of this nic port by below cmds:: + + ip netns del ns1 + ip netns add ns1 + ip link set enp26s0f0 netns ns1 # [enp216s0f0] is the name of nic2 + ip netns exec ns1 ifconfig enp26s0f0 1.1.1.8 up + ip netns exec ns1 ethtool -K enp26s0f0 tso on + +2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1:: + + ./dpdk-devbind.py -b igb_uio xx:xx.x + ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-31 -n 4 \ + --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 --nb-cores=2 + set fwd csum + stop + port stop 0 + port stop 1 + csum set tcp hw 0 + csum set ip hw 0 + csum set tcp hw 1 + csum set ip hw 1 + set port 0 gro on + set gro flush 1 + port start 0 + port start 1 + start + +3. Set up vm with virto device and using kernel virtio-net driver:: + + taskset -c 31 /home/qemu-install/qemu-4.2.1/bin/qemu-system-x86_64 -name us-vhost-vm1 \ + -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ + -chardev socket,id=char0,path=./vhost-net \ + -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \ + -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \ + -vnc :10 -daemonize + +4. In vm, config the virtio-net device with ip and turn the kernel gro off:: + + ifconfig ens4 1.1.1.2 up # [ens3] is the name of virtio-net + ethtool -L ens4 combined 2 + ethtool -K ens4 gro off + +5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get better performance than case5:: + + Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2 + VM side: iperf -s -- 2.25.1
> Add 2 queue case for performance check
>
> Signed-off-by: Yinan Wang <yinan.wang@intel.com>
Applied failed.
CONFLICT (content): Merge conflict in test_plans/dpdk_gro_lib_test_plan.rst
error: Failed to merge in the changes.
Patch failed at 0001 test_plans/dpdk_gro_lib_test_plan.rst
Add dpdk gro test with 2 queues. Signed-off-by: Yinan Wang <yinan.wang@intel.com> --- test_plans/dpdk_gro_lib_test_plan.rst | 141 ++++++++++++++++++-------- 1 file changed, 99 insertions(+), 42 deletions(-) diff --git a/test_plans/dpdk_gro_lib_test_plan.rst b/test_plans/dpdk_gro_lib_test_plan.rst index 60a0123..fac61aa 100644 --- a/test_plans/dpdk_gro_lib_test_plan.rst +++ b/test_plans/dpdk_gro_lib_test_plan.rst @@ -89,27 +89,27 @@ Modify the testpmd code as following:: Modify the dpdk code as following:: - diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c - index b38a4b6b1..573250dbe 100644 - --- a/drivers/net/vhost/rte_eth_vhost.c - +++ b/drivers/net/vhost/rte_eth_vhost.c - @@ -1071,8 +1071,14 @@ eth_dev_info(struct rte_eth_dev *dev, - dev_info->min_rx_bufsize = 0; - - dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS | - - DEV_TX_OFFLOAD_VLAN_INSERT; - - dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP; - + DEV_TX_OFFLOAD_VLAN_INSERT | - + DEV_TX_OFFLOAD_UDP_CKSUM | - + DEV_TX_OFFLOAD_TCP_CKSUM | - + DEV_TX_OFFLOAD_IPV4_CKSUM | - + DEV_TX_OFFLOAD_TCP_TSO; - + dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP | - + DEV_RX_OFFLOAD_TCP_CKSUM | - + DEV_RX_OFFLOAD_UDP_CKSUM | - + DEV_RX_OFFLOAD_IPV4_CKSUM | - + DEV_RX_OFFLOAD_TCP_LRO; - } +diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c +index b38a4b6b1..573250dbe 100644 +--- a/drivers/net/vhost/rte_eth_vhost.c ++++ b/drivers/net/vhost/rte_eth_vhost.c +@@ -1071,8 +1071,14 @@ eth_dev_info(struct rte_eth_dev *dev, + dev_info->min_rx_bufsize = 0; + + dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS | +- DEV_TX_OFFLOAD_VLAN_INSERT; +- dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP; ++ DEV_TX_OFFLOAD_VLAN_INSERT | ++ DEV_TX_OFFLOAD_UDP_CKSUM | ++ DEV_TX_OFFLOAD_TCP_CKSUM | ++ DEV_TX_OFFLOAD_IPV4_CKSUM | ++ DEV_TX_OFFLOAD_TCP_TSO; ++ dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP | ++ DEV_RX_OFFLOAD_TCP_CKSUM | ++ DEV_RX_OFFLOAD_UDP_CKSUM | ++ DEV_RX_OFFLOAD_IPV4_CKSUM | ++ DEV_RX_OFFLOAD_TCP_LRO; + } Test flow ========= @@ -148,11 +148,11 @@ Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic 3. Set up vm with virto device and using kernel virtio-net driver:: - taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ + taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ - -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \ @@ -200,11 +200,11 @@ Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic 3. Set up vm with virto device and using kernel virtio-net driver:: - taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ + taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ - -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \ @@ -252,11 +252,11 @@ Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic 3. Set up vm with virto device and using kernel virtio-net driver:: - taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ + taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ - -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \ @@ -278,11 +278,10 @@ Test Case4: DPDK GRO test with vxlan traffic Vxlan topology -------------- VM Host - 50.1.1.2 50.1.1.1 - \| | + | | 1.1.2.3 1.1.2.4 - \|------------Testpmd------------| + |------------Testpmd------------| 1. Connect two nic port directly, put nic2 into another namesapce and create Host VxLAN port:: @@ -323,11 +322,11 @@ Vxlan topology 3. Set up vm with virto device and using kernel virtio-net driver:: - taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ + taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ - -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \ @@ -347,8 +346,8 @@ Vxlan topology Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 2 -t 60 -f g -m VM side: iperf -s -f g -Test Case5: DPDK GRO test with CBDMA enable using tcp/ipv4 traffic -================================================================== +Test Case5: DPDK GRO test with 2 queues using tcp/ipv4 traffic +============================================================== Test flow ========= @@ -366,8 +365,8 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net 2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1:: ./dpdk-devbind.py -b igb_uio xx:xx.x - ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-30 -n 4 \ - --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 + ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-31 -n 4 \ + --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 --nb-cores=2 set fwd csum stop port stop 0 @@ -384,11 +383,11 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net 3. Set up vm with virto device and using kernel virtio-net driver:: - taskset -c 31 /home/qemu-install/qemu-3.0/bin/qemu-system-x86_64 -name us-vhost-vm1 \ + taskset -c 31 /home/qemu-install/qemu-4.2.1/bin/qemu-system-x86_64 -name us-vhost-vm1 \ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ -numa node,memdev=mem \ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \ - -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu1910.img \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ -chardev socket,id=char0,path=./vhost-net \ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \ @@ -404,3 +403,61 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2 VM side: iperf -s + +Test Case6: DPDK GRO test with two queues and two CBDMA channels using tcp/ipv4 traffic +======================================================================================= + +Test flow +========= + +NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net + +1. Connect two nic port directly, put nic2 into another namesapce and turn on the tso of this nic port by below cmds:: + + ip netns del ns1 + ip netns add ns1 + ip link set enp26s0f0 netns ns1 # [enp216s0f0] is the name of nic2 + ip netns exec ns1 ifconfig enp26s0f0 1.1.1.8 up + ip netns exec ns1 ethtool -K enp26s0f0 tso on + +2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1:: + + ./dpdk-devbind.py -b igb_uio xx:xx.x + ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-31 -n 4 \ + --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 --nb-cores=2 + set fwd csum + stop + port stop 0 + port stop 1 + csum set tcp hw 0 + csum set ip hw 0 + csum set tcp hw 1 + csum set ip hw 1 + set port 0 gro on + set gro flush 1 + port start 0 + port start 1 + start + +3. Set up vm with virto device and using kernel virtio-net driver:: + + taskset -c 31 /home/qemu-install/qemu-4.2.1/bin/qemu-system-x86_64 -name us-vhost-vm1 \ + -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem \ + -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \ + -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \ + -chardev socket,id=char0,path=./vhost-net \ + -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \ + -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \ + -vnc :10 -daemonize + +4. In vm, config the virtio-net device with ip and turn the kernel gro off:: + + ifconfig ens4 1.1.1.2 up # [ens3] is the name of virtio-net + ethtool -L ens4 combined 2 + ethtool -K ens4 gro off + +5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput, should be larger than 10Gbits/sec:: + + Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2 + VM side: iperf -s -- 2.25.1
> Add dpdk gro test with 2 queues.
>
> Signed-off-by: Yinan Wang <yinan.wang@intel.com>
Applied