From patchwork Wed Sep 7 12:59:59 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Ling, WeiX" X-Patchwork-Id: 116045 Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 73CBAA054F; Wed, 7 Sep 2022 15:05:23 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 6EE194021F; Wed, 7 Sep 2022 15:05:23 +0200 (CEST) Received: from mga17.intel.com (mga17.intel.com [192.55.52.151]) by mails.dpdk.org (Postfix) with ESMTP id 369BA400D6 for ; Wed, 7 Sep 2022 15:05:21 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1662555921; x=1694091921; h=from:to:cc:subject:date:message-id:mime-version: content-transfer-encoding; bh=N21ssVt0R5LzpmP9BlCi3J6tNPlJN5TCnun4TeAB2wc=; b=nHYLVypCC3UuaoPNTa1NiUE5ny74OiFWkHgsRhJSNDaMX08Ok+LIqtw/ V+38iP6YucpfRo+N/S5iUUExI98+5VfLdEPVmutQp+1ODXsf1M7wo2+Uv 8OY/9Ka08XkascfdLuyLyk6D7DbRGsfTGDQAUTgYskXgZ/w9OOLKcr5v/ WkIc4gMzzyGXvq5bfn8hjv2QZkgLdvRsPlby+yFUZONw6EjkgZfYnSy+5 T3YLIEfOETKbY/asUvTgw1mH9u7Fz0oLul3NJdt62vbruvA1fWyMKxToU bYY26VGOjtzhIQgw3rau2OjkkKV61RmEvhIb4PL346vQ8GykO/9hb0tHD A==; X-IronPort-AV: E=McAfee;i="6500,9779,10462"; a="277257187" X-IronPort-AV: E=Sophos;i="5.93,296,1654585200"; d="scan'208";a="277257187" Received: from fmsmga008.fm.intel.com ([10.253.24.58]) by fmsmga107.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 07 Sep 2022 06:05:06 -0700 X-IronPort-AV: E=Sophos;i="5.93,296,1654585200"; d="scan'208";a="676176018" Received: from unknown (HELO localhost.localdomain) ([10.239.252.222]) by fmsmga008-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 07 Sep 2022 06:05:05 -0700 From: Wei Ling To: dts@dpdk.org Cc: Wei Ling Subject: [dts][PATCH V1 1/2] test_plans/dpdk_gro_lib_test_plan: add udp traffice testcase Date: Wed, 7 Sep 2022 08:59:59 -0400 Message-Id: <20220907125959.1728258-1-weix.ling@intel.com> X-Mailer: git-send-email 2.25.1 MIME-Version: 1.0 X-BeenThere: dts@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: test suite reviews and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dts-bounces@dpdk.org Add new udp traffic testcase 6-10 in dpdk_gro_lib testplan. Signed-off-by: Wei Ling --- test_plans/dpdk_gro_lib_test_plan.rst | 330 ++++++++++++++++++++++++-- 1 file changed, 307 insertions(+), 23 deletions(-) diff --git a/test_plans/dpdk_gro_lib_test_plan.rst b/test_plans/dpdk_gro_lib_test_plan.rst index e36550d2..e46f2487 100644 --- a/test_plans/dpdk_gro_lib_test_plan.rst +++ b/test_plans/dpdk_gro_lib_test_plan.rst @@ -16,12 +16,12 @@ be processed. To benefit DPDK-based applications, like Open vSwitch, DPDK also provides own GRO implementation. In DPDK, GRO is implemented as a standalone library. Applications explicitly use the GRO library to reassemble packets. - In the GRO library, there are many GRO types which are defined by packet types. One GRO type is in charge of process one kind of packets. For example, TCP/IPv4 GRO processes TCP/IPv4 packets. Each GRO type has a reassembly function, which defines own algorithm and + table structure to reassemble packets. We assign input packets to the corresponding GRO functions by MBUF->packet_type. @@ -95,7 +95,7 @@ Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic 5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get expected data:: - Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 1 + Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m VM side: iperf -s Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic @@ -147,7 +147,7 @@ Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic 5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get expected data:: - Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 1 + Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m VM side: iperf -s Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic @@ -199,11 +199,11 @@ Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic 5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get expected data:: - Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 1 + Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m VM side: iperf -s -Test Case4: DPDK GRO test with vxlan traffic -============================================ +Test Case4: DPDK GRO test with tcp/vxlan traffic +================================================ Vxlan topology -------------- @@ -274,8 +274,8 @@ Vxlan topology 5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get expected data:: - 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 + Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 2 -t 60 -f + VM side: iperf -s -f Test Case5: DPDK GRO test with 2 queues using tcp/ipv4 traffic ============================================================== @@ -288,24 +288,24 @@ Test Case5: DPDK GRO test with 2 queues using tcp/ipv4 traffic 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 vfio-pci, launch vhost-user with testpmd and set flush interval to 1:: +2. Bind nic1 to vfio-pci, launch vhost-user with testpmd and set flush interval to 1:: ./usertools/dpdk-devbind.py -b vfio-pci xx:xx.x ./x86_64-native-linuxapp-gcc/app/dpdk-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 - 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 + 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:: @@ -327,5 +327,289 @@ Test Case5: DPDK GRO test with 2 queues using tcp/ipv4 traffic 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 case1:: - Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2 + Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 + VM side: iperf -s + +Test Case6: DPDK GRO lightmode test with udp/ipv4 traffic +========================================================= + +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 [enp216s0f0] netns ns1 # [enp216s0f0] is the name of nic2 + ip netns exec ns1 ifconfig [enp216s0f0] 1.1.1.8 up + ip netns exec ns1 ethtool -K [enp216s0f0] tso on + +2. Bind nic1 to vfio-pci, launch vhost-user with testpmd and set flush interval to 1:: + + ./usertools/dpdk-devbind.py -b vfio-pci xx:xx.x + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 2-4 -n 4 \ + --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024 + 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 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,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,guest_ufo=on,guest_ecn=on \ + -vnc :10 -daemonize + +4. In vm, config the virtio-net device with ip and turn the kernel gro off:: + + ifconfig [ens3] 1.1.1.2 up # [ens3] is the name of virtio-net + ethtool -K [ens3] gro off + +5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get expected data:: + + Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -P 4 -u -b 10G -l 9000 + VM side: iperf -s + +Test Case7: DPDK GRO heavymode test with udp/ipv4 traffic +========================================================= + +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 [enp216s0f0] netns ns1 # [enp216s0f0] is the name of nic2 + ip netns exec ns1 ifconfig [enp216s0f0] 1.1.1.8 up + ip netns exec ns1 ethtool -K [enp216s0f0] tso on + +2. Bind nic1 to vfio-pci, launch vhost-user with testpmd and set flush interval to 2:: + + ./usertools/dpdk-devbind.py -b vfio-pci xx:xx.x + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 2-4 -n 4 \ + --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024 + 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 2 + 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 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,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,guest_ufo=on,guest_ecn=on \ + -vnc :10 -daemonize + +4. In vm, config the virtio-net device with ip and turn the kernel gro off:: + + ifconfig [ens3] 1.1.1.2 up # [ens3] is the name of virtio-net + ethtool -K [ens3] gro off + +5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get expected data:: + + Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -P 4 -u -b 10G -l 9000 + VM side: iperf -s + +Test Case8: DPDK GRO heavymode_flush4 test with udp/ipv4 traffic +================================================================ + +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 [enp216s0f0] netns ns1 # [enp216s0f0] is the name of nic2 + ip netns exec ns1 ifconfig [enp216s0f0] 1.1.1.8 up + ip netns exec ns1 ethtool -K [enp216s0f0] tso on + +2. Bind nic1 to vfio-pci, launch vhost-user with testpmd and set flush interval to 4:: + + ./usertools/dpdk-devbind.py -b vfio-pci xx:xx.x + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 2-4 -n 4 \ + --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024 + 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 4 + 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 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,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,guest_ufo=on,guest_ecn=on \ + -vnc :10 -daemonize + +4. In vm, config the virtio-net device with ip and turn the kernel gro off:: + + ifconfig [ens3] 1.1.1.2 up # [ens3] is the name of virtio-net + ethtool -K [ens3] gro off + +5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get expected data:: + + Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -P 4 -u -b 10G -l 9000 + VM side: iperf -s + +Test Case9: DPDK GRO test with udp/vxlan traffic +================================================ + +Vxlan topology +-------------- + VM Host + +50.1.1.2 50.1.1.1 + \| \| +1.1.2.3 1.1.2.4 + \|------------Testpmd------------| + +1. Connect two nic port directly, put nic2 into another namesapce and create Host VxLAN port:: + + ip netns del ns1 + ip netns add ns1 + ip link set [enp216s0f0] netns ns1 # [enp216s0f0] is the name of nic2 + ip netns exec ns1 ifconfig [enp216s0f0] 1.1.2.4/24 up + VXLAN_NAME=vxlan1 + VXLAN_IP=50.1.1.1 + IF_NAME=[enp216s0f0] + VM_IP=1.1.2.3 + ip netns exec t2 ip link add $VXLAN_NAME type vxlan id 42 dev $IF_NAME dstport 4789 + ip netns exec t2 bridge fdb append to 00:00:00:00:00:00 dst $VM_IP dev $VXLAN_NAME + ip netns exec t2 ip addr add $VXLAN_IP/24 dev $VXLAN_NAME + ip netns exec t2 ip link set up dev $VXLAN_NAME + +2. Bind nic1 to vfio-pci, launch vhost-user with testpmd and set flush interval to 4:: + + ./usertools/dpdk-devbind.py -b vfio-pci xx:xx.x + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 2-4 -n 4 \ + --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024 + 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 parse-tunnel on 0 + testpmd>csum parse-tunnel on 1 + testpmd>csum set outer-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 4 + 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 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,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,guest_ufo=on,guest_ecn=on \ + -vnc :10 -daemonize + +4. In vm, config the virtio-net device with ip and turn the kernel gro off:: + + ip link add vxlan0 type vxlan id 42 dev [ens3] dstport 4789 # [ens3] is the name of virtio-net + bridge fdb add to 00:00:00:00:00:00 dst 1.1.2.4 dev vxlan0 + ip addr add 50.1.1.2/24 dev vxlan0 + ip link set up dev vxlan0 + ifconfig [ens3] 1.1.2.3/24 up + ifconfig -a + +5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get expected data:: + + Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 1 -t 60 -P 4 -u -b 10G -l 9000 + VM side: iperf -s -f g + +Test Case10: DPDK GRO test with 2 queues using udp/ipv4 traffic +=============================================================== + +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 nic1 to vfio-pci, launch vhost-user with testpmd and set flush interval to 1:: + + ./usertools/dpdk-devbind.py -b vfio-pci xx:xx.x + ./x86_64-native-linuxapp-gcc/app/dpdk-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 + 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-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,,guest_ufo=on,guest_ecn=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 case1:: + + Host side : ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -P 4 -u -b 10G -l 9000 VM side: iperf -s