From patchwork Tue Sep 6 11:17:05 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "He, Xingguang" X-Patchwork-Id: 115970 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 38828A0542; Tue, 6 Sep 2022 13:17:17 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 349EC4021D; Tue, 6 Sep 2022 13:17:17 +0200 (CEST) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by mails.dpdk.org (Postfix) with ESMTP id 782E540695 for ; Tue, 6 Sep 2022 13:17:15 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1662463035; x=1693999035; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=R4Vdq5ih/H0eg7pDiQ4QKt4aTewiIutLFIB6kcpE/Hs=; b=caDO21Bb6/RRl1QcKkiS1DEz9M8AOP2bD4o8eyUGxWhULybU4a1O8NIT 8wz9Wmcw2Jcx0Iw54D4BYXMkpzbTOon0xglWNxEDLDbQgoj0BNiEQYc2E g87TGuJC0VA9HB8hCpKGIoF5Q1BUMrd4tvO9C7YNxOBr+TmZolPJyJ7Ke bkgDFYKmrxEJhRQiNsRWjFSUy7HFpAXe2mDyvfCoQSV+RpDg8SbpfDc5N 9STUPk8sfJcPNEpk0l6bSGBdqEWjuk5Ovgqi2gluHpgT+VQU6iqU3LJen +o4sCwBnE1rn4UtQlE/x6typkYEv6YIyui3eCEKcmZKr991SwL2J5mW1g w==; X-IronPort-AV: E=McAfee;i="6500,9779,10461"; a="358282806" X-IronPort-AV: E=Sophos;i="5.93,294,1654585200"; d="scan'208";a="358282806" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 06 Sep 2022 04:17:15 -0700 X-IronPort-AV: E=Sophos;i="5.93,294,1654585200"; d="scan'208";a="644130548" Received: from dpdk-xingguang-icelake.sh.intel.com ([10.67.119.147]) by orsmga008-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 06 Sep 2022 04:17:13 -0700 From: Xingguang He To: dts@dpdk.org Cc: Xingguang He Subject: [dts][PATCH V1 1/2] test_plans/index: add vm2vm_virtio_pmd_dsa test plan into test_plans/index Date: Tue, 6 Sep 2022 11:17:05 +0000 Message-Id: <20220906111706.1135805-2-xingguang.he@intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20220906111706.1135805-1-xingguang.he@intel.com> References: <20220906111706.1135805-1-xingguang.he@intel.com> 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 vm2vm_virtio_pmd_dsa into test_plans/index. Signed-off-by: Xingguang He --- test_plans/index.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/test_plans/index.rst b/test_plans/index.rst index cced285e..426f2cb1 100644 --- a/test_plans/index.rst +++ b/test_plans/index.rst @@ -211,6 +211,7 @@ The following are the test plans for the DPDK DTS automated test system. vm2vm_virtio_net_perfdsa_test_plan vm2vm_virtio_pmd_test_plan vm2vm_virtio_pmd_cbdma_test_plan + vm2vm_virtio_pmd_dsa_test_plan dpdk_gro_lib_test_plan dpdk_gro_lib_cbdma_test_plan dpdk_gso_lib_test_plan From patchwork Tue Sep 6 11:17:06 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: "He, Xingguang" X-Patchwork-Id: 115971 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 60C8AA0542; Tue, 6 Sep 2022 13:17:21 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 59FE14114A; Tue, 6 Sep 2022 13:17:21 +0200 (CEST) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by mails.dpdk.org (Postfix) with ESMTP id DCB90400D6 for ; Tue, 6 Sep 2022 13:17:18 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1662463039; x=1693999039; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=Oikx6GSjVYh3cPigWB72HC7y5DxAYx8byE0K/giK9vQ=; b=RJQlLg2JngFh5WZKK3JPeufQYz9+VDRJ+l8v8Oc7qX6GAqVdMW8j+Z6q howeGvHea/6X/0VI5pYLMBgMzb8pgzQUC93OC9AY4dS6txSLSr1zSEQ+h 7K/QKTJO4//kcZGFCa9AkAgGvS/YCxwsDADxF/1MsQMg5QI+i+gIfFteP DrbZ2qPrAq3T+TBbMKxX1KGNwCSwvnDI4kmYat1OmA9DPd/g0Ldh0GJPB bN1Hdiood6+gYPI6ye//gAlMCdbGlWV2Sxb7lw/uhNYye9yjj4ShjomJC hMxiQXDMRDz4EzQ4g+lp0CPy+FFUBfglKbEiDeeAM8mVSLoesQYgL6kM4 A==; X-IronPort-AV: E=McAfee;i="6500,9779,10461"; a="358282810" X-IronPort-AV: E=Sophos;i="5.93,294,1654585200"; d="scan'208";a="358282810" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 06 Sep 2022 04:17:17 -0700 X-IronPort-AV: E=Sophos;i="5.93,294,1654585200"; d="scan'208";a="644130560" Received: from dpdk-xingguang-icelake.sh.intel.com ([10.67.119.147]) by orsmga008-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 06 Sep 2022 04:17:16 -0700 From: Xingguang He To: dts@dpdk.org Cc: Xingguang He Subject: [dts][PATCH V1 2/2] test_plans/vm2vm_virtio_pmd_dsa_test_plan: add vm2vm_virtio_pmd_dsa_test_plan.rst into test_plans Date: Tue, 6 Sep 2022 11:17:06 +0000 Message-Id: <20220906111706.1135805-3-xingguang.he@intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20220906111706.1135805-1-xingguang.he@intel.com> References: <20220906111706.1135805-1-xingguang.he@intel.com> 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 test plan to test vhost async data-path with virito-pmd as front-end. Signed-off-by: Xingguang He --- test_plans/vm2vm_virtio_pmd_dsa_test_plan.rst | 930 ++++++++++++++++++ 1 file changed, 930 insertions(+) create mode 100644 test_plans/vm2vm_virtio_pmd_dsa_test_plan.rst diff --git a/test_plans/vm2vm_virtio_pmd_dsa_test_plan.rst b/test_plans/vm2vm_virtio_pmd_dsa_test_plan.rst new file mode 100644 index 00000000..afad2a1b --- /dev/null +++ b/test_plans/vm2vm_virtio_pmd_dsa_test_plan.rst @@ -0,0 +1,930 @@ +.. SPDX-License-Identifier: BSD-3-Clause + Copyright(c) 2022 Intel Corporation + +======================================================= +vm2vm vhost-user/virtio-pmd with dsa driver test plan +======================================================= + +This document provides the test plan for testing some basic functions with DSA driver(kernel IDXD driver and DPDK vfio-pci driver) +in vm2vm vhost-user/virtio-pmd topology environment. +1. vm2vm mergeable, non-mergebale path test with virtio 1.0 and virtio1.1 and check virtio-pmd tx chain packets in mergeable path. +2. dynamic change queue number. + +..Note: +1.For packed virtqueue virtio-net test, need qemu version > 4.2.0 and VM kernel version > 5.1, and packed ring multi-queues not support reconnect in qemu yet. +2.For split virtqueue virtio-net with multi-queues server mode test, better to use qemu version >= 5.2.0, dut to qemu(v4.2.0~v5.1.0) exist split ring multi-queues reconnection issue. +3.When DMA devices are bound to vfio driver, VA mode is the default and recommended. For PA mode, page by page mapping may +exceed IOMMU's max capability, better to use 1G guest hugepage. +4.DPDK local patch that about vhost pmd is needed when testing Vhost asynchronous data path with testpmd. + +For more about dpdk-testpmd sample, please refer to the DPDK docments: +https://doc.dpdk.org/guides/testpmd_app_ug/run_app.html +For more about qemu, you can refer to the qemu doc: https://qemu-project.gitlab.io/qemu/system/invocation.html + +Prerequisites +============= + +Topology +-------- + Test flow: Virtio-pmd-->Vhost-user-->Testpmd-->Vhost-user-->Virtio-pmd + +Software +-------- + iperf + +General set up +-------------- +1. Compile DPDK:: + + # CC=gcc meson --werror -Denable_kmods=True -Dlibdir=lib -Dexamples=all --default-library=static + # ninja -C -j 110 + For example: + CC=gcc meson --werror -Denable_kmods=True -Dlibdir=lib -Dexamples=all --default-library=static x86_64-native-linuxapp-gcc + ninja -C x86_64-native-linuxapp-gcc -j 110 + +2. Get the DMA device ID of DUT, for example, 0000:6a:01.0 is DMA device ID:: + + # ./usertools/dpdk-devbind.py -s + + DMA devices using kernel driver + =============================== + 0000:6a:01.0 'Device 0b25' drv=idxd unused=vfio-pci + 0000:6f:01.0 'Device 0b25' drv=idxd unused=vfio-pci + 0000:74:01.0 'Device 0b25' drv=idxd unused=vfio-pci + 0000:79:01.0 'Device 0b25' drv=idxd unused=vfio-pci + 0000:e7:01.0 'Device 0b25' drv=idxd unused=vfio-pci + 0000:ec:01.0 'Device 0b25' drv=idxd unused=vfio-pci + 0000:f1:01.0 'Device 0b25' drv=idxd unused=vfio-pci + 0000:f6:01.0 'Device 0b25' drv=idxd unused=vfio-pci + +Test case +========= + +Common steps +------------ +1.Bind DSA devices to DPDK vfio-pci driver:: + + # ./usertools/dpdk-devbind.py -b vfio-pci + For example, bind 2 DMA devices to vfio-pci driver: + # ./usertools/dpdk-devbind.py -b vfio-pci 0000:e7:01.0 0000:ec:01.0 + +.. note:: + + One DPDK DSA device can create 8 WQ at most. Below is an example, where DPDK DSA device will create one and + eight WQ for DSA deivce 0000:e7:01.0 and 0000:ec:01.0. The value of “max_queues” is 1~8: + # ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 4 -n 4 -a 0000:e7:01.0,max_queues=1 -- -i + # ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 4 -n 4 -a 0000:ec:01.0,max_queues=8 -- -i + +2. Bind DSA devices to kernel idxd driver, and configure Work Queue (WQ):: + + # ./usertools/dpdk-devbind.py -b idxd + # ./drivers/dma/dma/idxd/dpdk_idxd_cfg.py -q + +.. note:: + + Better to reset WQ when need operate DSA devices that bound to idxd drvier: + # ./drivers/dma/idxd/dpdk_idxd_cfg.py --reset + You can check it by 'ls /dev/dsa' + numDevices: number of devices, where 0<=numDevices<=7, corresponding to 0000:6a:01.0 - 0000:f6:01.0 + numWq: Number of workqueues per DSA endpoint, where 1<=numWq<=8 + + For example, bind 2 DMA devices to idxd driver and configure WQ: + + # ./usertools/dpdk-devbind.py -b idxd 6a:01.0 6f:01.0 + # ./drivers/dma/idxd/dpdk_idxd_cfg.py -q 1 0 + # ./drivers/dma/idxd/dpdk_idxd_cfg.py -q 4 1 + Check WQ by 'ls /dev/dsa' and can find "wq0.0 wq1.0 wq1.1 wq1.2 wq1.3" + +Test Case 1: VM2VM virtio-pmd split ring mergeable path dynamic queue size with dsa dpdk driver and server mode +----------------------------------------------------------------------------------------------------------------- +This case tests split ring mergeable path in VM2VM vhost-user/virtio-pmd topology when vhost uses the asynchronous operations with dsa dpdk driver, +check that it can tx chain packets normally after dynamically changing queue number from vhost, reconnection has also been tested. + +1. Bind 2 dsa device to vfio-pci, then launch the testpmd with 2 vhost ports below commands:: + + # ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost -a 0000:f1:01.0,max_queues=4 -a 0000:f6:01.0,max_queues=4 \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=4 --txq=4 \ + --lcore-dma=[lcore2@0000:f1:01.0-q0,lcore2@0000:f1:01.0-q1,lcore3@0000:f1:01.0-q2,lcore3@0000:f1:01.0-q3,lcore4@0000:f6:01.0-q0,lcore4@0000:f6:01.0-q1,lcore5@0000:f6:01.0-q2,lcore5@0000:f6:01.0-q3] + testpmd>start + +2. Launch VM1 and VM2 using qemu:: + + taskset -c 6-16 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04.img \ + -chardev socket,path=/tmp/vm1_qga0.sock,server,nowait,id=vm1_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm1_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm1_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6002-:22 \ + -chardev socket,id=char0,path=./vhost-net0,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=on,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :10 + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=on,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :12 + +3. On VM1 and VM2, bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +4. Launch testpmd in VM1:: + + # ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 --max-pkt-len=9600 --rx-offloads=0x00002000 + testpmd>set fwd mac + testpmd>start + +5. Launch testpmd in VM2 and send imix pkts, check imix packets can looped between two VMs for 1 mins and 4 queues (queue0 to queue3) have packets rx/tx:: + + # ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 --max-pkt-len=9600 --rx-offloads=0x00002000 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512,1024,2000,64,256,512,1024,2000 + testpmd>start tx_first 32 + testpmd>show port stats all + +6. Check vhost use the asynchronous data path(funtion like virtio_dev_rx_async_xxx/virtio_dev_tx_async_xxx):: + + perf top + +7. Stop vhost, check that both 4 queues can rx/tx queues:: + + testpmd>stop + +8. On host, dynamic change queue numbers:: + + testpmd>stop + testpmd>port stop all + testpmd>port config all rxq 8 + testpmd>port config all txq 8 + testpmd>port start all + testpmd>start + +9. Send packets by testpmd in VM2:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + +10. Check vhost testpmd RX/TX can work normally, packets can looped between two VMs and both 8 queues can RX/TX traffic. + +11. Rerun step 6. + +12. Relaunch and start vhost side testpmd with 8 queues:: + + # ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost -a 0000:f1:01.0,max_queues=8 \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;txq4;txq5;rxq2;rxq3;rxq4;rxq5;rxq6;rxq7]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;txq4;txq5;rxq2;rxq3;rxq4;rxq5;rxq6;rxq7]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=8 --txq=8 \ + --lcore-dma=[lcore2@0000:f1:01.0-q0,lcore2@0000:f1:01.0-q1,lcore3@0000:f1:01.0-q2,lcore3@0000:f1:01.0-q3,lcore4@0000:f1:01.0-q4,lcore4@0000:f1:01.0-q5,lcore5@0000:f1:01.0-q6,lcore5@0000:f1:01.0-q7] + testpmd>start + +13. Send packets by testpmd in VM2, check imix packets can looped between two VMs for 1 mins and 8 queues all have packets rx/tx:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + testpmd>stop + +14. Rerun step 12-13 for 3 times. + +Test Case 2: VM2VM virtio-pmd split ring non-mergeable path dynamic queue size with dsa dpdk driver and server mode +---------------------------------------------------------------------------------------------------------------------- +This case tests split ring non-mergeable path in VM2VM vhost-user/virtio-pmd topology when vhost uses the asynchronous operations with dsa dpdk driver, +check that it can work normally after dynamically changing queue number at virtio-pmd side, reconnection has also been tested. + +1. Bind 2 dsa device to vfio-pci, then launch the testpmd with 2 vhost ports below commands:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost -a 0000:f1:01.0,max_queues=4 -a 0000:f6:01.0,max_queues=4 \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=8 --txq=8 \ + --lcore-dma=[lcore2@0000:f1:01.0-q0,lcore2@0000:f1:01.0-q1,lcore3@0000:f1:01.0-q2,lcore3@0000:f1:01.0-q3,lcore4@0000:f6:01.0-q0,lcore4@0000:f6:01.0-q1,lcore5@0000:f6:01.0-q2,lcore5@0000:f6:01.0-q3] + testpmd>start + +2. Launch VM1 and VM2 using qemu:: + + taskset -c 6-16 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04.img \ + -chardev socket,path=/tmp/vm1_qga0.sock,server,nowait,id=vm1_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm1_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm1_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6002-:22 \ + -chardev socket,id=char0,path=./vhost-net0,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=off,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :10 + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=off,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :12 + +3. On VM1 and VM2, bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +4. Launch testpmd in VM1:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 + testpmd>set fwd mac + testpmd>start + +5. Launch testpmd in VM2 and send imix pkts, check imix packets can looped between two VMs for 1 mins and 4 queues (queue0 to queue3) have packets rx/tx:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512 + testpmd>start tx_first 32 + testpmd>show port stats all + +6. Check vhost use the asynchronous data path(funtion like virtio_dev_rx_async_xxx/virtio_dev_tx_async_xxx):: + + perf top + +7. Stop vhost, check that both 8 queues can rx/tx queues, then start the vhost. + + testpmd>stop + testpmd>start + +8. On VM2, dynamic change queue numbers at virtio-pmd side from 8 queues to 4 queues:: + + testpmd>stop + testpmd>port stop all + testpmd>port config all rxq 4 + testpmd>port config all txq 4 + testpmd>port start all + testpmd>start + +9. Send packets by testpmd in VM2, check Check virtio-pmd RX/TX can work normally and imix packets can looped between two VMs for 1 mins:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + +10. Rerun step 6. + +11. Stop testpmd in VM2, and check that 4 queues can RX/TX traffic. + +Test Case 3: VM2VM virtio-pmd packed ring mergeable path dynamic queue size with dsa dpdk driver and server mode +----------------------------------------------------------------------------------------------------------------- +This case tests packed ring mergeable path in VM2VM vhost-user/virtio-pmd topology when vhost uses the asynchronous operations with dsa dpdk driver, +check that it can tx chain packets normally after dynamically changing queue number. + +1. Bind 2 dsa device to vfio-pci, then launch the testpmd with 2 vhost ports below commands:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost -a 0000:f1:01.0,max_queues=4 -a 0000:f6:01.0,max_queues=4 \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=4 --txq=4 \ + --lcore-dma=[lcore2@0000:f1:01.0-q0,lcore2@0000:f1:01.0-q1,lcore3@0000:f1:01.0-q2,lcore3@0000:f1:01.0-q3,lcore4@0000:f6:01.0-q0,lcore4@0000:f6:01.0-q1,lcore5@0000:f6:01.0-q2,lcore5@0000:f6:01.0-q3] + testpmd>start + +2. Launch VM1 and VM2 using qemu:: + + taskset -c 6-16 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04.img \ + -chardev socket,path=/tmp/vm1_qga0.sock,server,nowait,id=vm1_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm1_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm1_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6002-:22 \ + -chardev socket,id=char0,path=./vhost-net0,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=on,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on,packed=on -vnc :10 + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=on,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on,packed=on -vnc :12 + +3. On VM1 and VM2, bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +4. Launch testpmd in VM1:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 --max-pkt-len=9600 --rx-offloads=0x00002000 + testpmd>set fwd mac + testpmd>start + +5. Launch testpmd in VM2 and send imix pkts, check imix packets can looped between two VMs for 1 mins and 4 queues (queue0 to queue3) have packets rx/tx:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 --max-pkt-len=9600 --rx-offloads=0x00002000 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512,1024,2000,64,256,512,1024,2000 + testpmd>start tx_first 32 + testpmd>show port stats all + testpmd>stop + +6. Quit VM2 and relaunch VM2 with split ring:: + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=on,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :12 + +7. Bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +8. Launch testpmd in VM2 and send imix pkts from VM2:: + + # ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 --max-pkt-len=9600 --rx-offloads=0x00002000 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512,1024,2000,64,256,512,1024,2000 + testpmd>start tx_first 32 + +9. On host, Check imix packets can looped between two VMs and 4 queues all have packets rx/tx:: + + testpmd>show port stats all + testpmd>stop + testpmd>start + +10. Check vhost use the asynchronous data path(funtion like virtio_dev_rx_async_xxx/virtio_dev_tx_async_xxx):: + + perf top + +11. On host, dynamic change queue numbers:: + + testpmd>stop + testpmd>port stop all + testpmd>port config all rxq 8 + testpmd>port config all txq 8 + testpmd>port start all + testpmd>start + +12. Send packets by testpmd in VM2:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + +13. Check vhost testpmd RX/TX can work normally, packets can looped between two VMs and both 8 queues can RX/TX traffic. + +14. Rerun step 10. + +Test Case 4: VM2VM virtio-pmd packed ring non-mergeable path dynamic queue size with dsa dpdk driver and server mode +----------------------------------------------------------------------------------------------------------------------- +This case tests packed ring non-mergeable path in VM2VM vhost-user/virtio-pmd topology when vhost uses the asynchronous operations with dsa dpdk driver, +check that it can work normally after dynamically changing queue number at virtio-pmd side. + +1. Bind 2 dsa device to vfio-pci, then launch the testpmd with 2 vhost ports below commands:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost -a 0000:f1:01.0,max_queues=4 -a 0000:f6:01.0,max_queues=4 \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;txq4]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;txq4]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=8 --txq=8 \ + --lcore-dma=[lcore2@0000:f1:01.0-q0,lcore2@0000:f1:01.0-q1,lcore3@0000:f1:01.0-q2,lcore3@0000:f1:01.0-q3,lcore4@0000:f6:01.0-q0,lcore4@0000:f6:01.0-q1,lcore5@0000:f6:01.0-q2,lcore5@0000:f6:01.0-q3] + testpmd>start + +2. Launch VM1 and VM2 using qemu:: + + taskset -c 6-16 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04.img \ + -chardev socket,path=/tmp/vm1_qga0.sock,server,nowait,id=vm1_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm1_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm1_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6002-:22 \ + -chardev socket,id=char0,path=./vhost-net0,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=off,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on,packed=on -vnc :10 + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=off,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on,packed=on -vnc :12 + +3. On VM1 and VM2, bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +4. Launch testpmd in VM1:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 + testpmd>set fwd mac + testpmd>start + +5. Launch testpmd in VM2 and send imix pkts, check imix packets can looped between two VMs for 1 mins:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512 + testpmd>start tx_first 32 + testpmd>show port stats all + +6. Check vhost use the asynchronous data path(funtion like virtio_dev_rx_async_xxx/virtio_dev_tx_async_xxx):: + + perf top + +7. On VM2, stop the testpmd, check that both 8 queues have packets rx/tx:: + + testpmd>stop + +8. On VM2, dynamic change queue numbers at virtio-pmd side from 8 queues to 4 queues:: + + testpmd>stop + testpmd>port stop all + testpmd>port config all rxq 4 + testpmd>port config all txq 4 + testpmd>port start all + testpmd>start + +9. Send packets by testpmd in VM2, check Check virtio-pmd RX/TX can work normally and imix packets can looped between two VMs for 1 mins:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + +10. Rerun step 6. + +11. Stop testpmd in VM2, and check that 4 queues can RX/TX traffic. + +Test Case 5: VM2VM virtio-pmd split ring mergeable path dynamic queue size with dsa kernel driver and server mode +------------------------------------------------------------------------------------------------------------------- +This case tests split ring mergeable path in VM2VM vhost-user/virtio-pmd topology when vhost uses the asynchronous operations with dsa kernel driver, +check that it can tx chain packets normally after dynamically changing queue number at vhost side, reconnection has also been tested. + +1. Bind 2 dsa device to idxd:: + + ls /dev/dsa #check wq configure, reset if exist + ./usertools/dpdk-devbind.py -u 6a:01.0 6f:01.0 + ./usertools/dpdk-devbind.py -b idxd 6a:01.0 6f:01.0 + ./drivers/raw/ioat/dpdk_idxd_cfg.py -q 8 0 + ./drivers/raw/ioat/dpdk_idxd_cfg.py -q 8 1 + ls /dev/dsa #check wq configure success + +2. Launch the testpmd with 2 vhost ports below commands:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=4 --txq=4 \ + --lcore-dma=[lcore2@wq0.0,lcore2@wq0.1,lcore3@wq0.2,lcore3@wq0.3,lcore4@wq0.4,lcore4@wq0.5,lcore5@wq0.6,lcore5@wq0.7] + testpmd>start + +3. Launch VM1 and VM2 using qemu:: + + taskset -c 6-16 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04.img \ + -chardev socket,path=/tmp/vm1_qga0.sock,server,nowait,id=vm1_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm1_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm1_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6002-:22 \ + -chardev socket,id=char0,path=./vhost-net0,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=on,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :10 + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=on,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :12 + +4. On VM1 and VM2, bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +5. Launch testpmd in VM1:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 --max-pkt-len=9600 --rx-offloads=0x00002000 + testpmd>set fwd mac + testpmd>start + +6. Launch testpmd in VM2 and send imix pkts, check imix packets can looped between two VMs for 1 mins and 4 queues (queue0 to queue3) have packets rx/tx:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 --max-pkt-len=9600 --rx-offloads=0x00002000 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512,1024,2000,64,256,512,1024,2000 + testpmd>start tx_first 32 + testpmd>show port stats all + +7. Check vhost use the asynchronous data path(funtion like virtio_dev_rx_async_xxx/virtio_dev_tx_async_xxx):: + + perf top + +8. Stop vhost, check that both 4 queues can rx/tx queues. + +9. On host, dynamic change queue numbers:: + + testpmd>stop + testpmd>port stop all + testpmd>port config all rxq 8 + testpmd>port config all txq 8 + testpmd>port start all + testpmd>start + +10. Send packets by testpmd in VM2:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + +11. Check vhost testpmd RX/TX can work normally, packets can looped between two VMs and both 8 queues can RX/TX traffic. + +12. Rerun step 7. + +13. Relaunch and start vhost side testpmd with 8 queues:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;txq4;txq5;rxq2;rxq3;rxq4;rxq5;rxq6;rxq7]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;txq4;txq5;rxq2;rxq3;rxq4;rxq5;rxq6;rxq7]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=8 --txq=8 \ + --lcore-dma=[lcore2@wq0.0,lcore2@wq0.1,lcore3@wq0.2,lcore3@wq0.3,lcore4@wq1.0,lcore4@wq1.1,lcore5@wq1.2,lcore5@wq1.3] + testpmd>start + +14. Send packets by testpmd in VM2, check imix packets can looped between two VMs for 1 mins and 8 queues all have packets rx/tx:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + testpmd>stop + +15. Rerun step 13-14 for 3 times. + +Test Case 6: VM2VM virtio-pmd split ring non-mergeable path dynamic queue size with dsa kernel driver and server mode +----------------------------------------------------------------------------------------------------------------------- +This case tests split ring non-mergeable path in VM2VM vhost-user/virtio-pmd topology when vhost uses the asynchronous operations with dsa kernel driver, +check that it can work normally after dynamically changing queue number at virtio-pmd side, reconnection has also been tested. + +1. Bind 2 dsa device to idxd:: + + ls /dev/dsa #check wq configure, reset if exist + ./usertools/dpdk-devbind.py -u 6a:01.0 6f:01.0 + ./usertools/dpdk-devbind.py -b idxd 6a:01.0 6f:01.0 + ./drivers/raw/ioat/dpdk_idxd_cfg.py -q 8 0 + ./drivers/raw/ioat/dpdk_idxd_cfg.py -q 8 1 + ls /dev/dsa #check wq configure success + +2. Launch the testpmd with 2 vhost ports below commands:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;rxq0;rxq1;rxq2;rxq3]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=8 --txq=8 \ + --lcore-dma=[lcore2@wq0.0,lcore2@wq0.1,lcore3@wq0.2,lcore3@wq0.3,lcore4@wq0.4,lcore4@wq0.5,lcore5@wq0.6,lcore5@wq0.7] + testpmd>start + +3. Launch VM1 and VM2 using qemu:: + + taskset -c 6-16 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04.img \ + -chardev socket,path=/tmp/vm1_qga0.sock,server,nowait,id=vm1_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm1_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm1_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6002-:22 \ + -chardev socket,id=char0,path=./vhost-net0,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=off,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :10 + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=off,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :12 + +4. On VM1 and VM2, bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +5. Launch testpmd in VM1:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 + testpmd>set fwd mac + testpmd>start + +6. Launch testpmd in VM2 and send imix pkts, check imix packets can looped between two VMs for 1 mins and 4 queues (queue0 to queue3) have packets rx/tx:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512 + testpmd>start tx_first 32 + testpmd>show port stats all + +7. Check vhost use the asynchronous data path(funtion like virtio_dev_rx_async_xxx/virtio_dev_tx_async_xxx):: + + perf top + +8. Stop testpmd in host, and check that 8 queues can RX/TX traffic. + +8. On VM, dynamic change queue numbers at virtio-pmd side from 8 queues to 4 queues:: + + testpmd>stop + testpmd>port stop all + testpmd>port config all rxq 4 + testpmd>port config all txq 4 + testpmd>port start all + testpmd>start + +9. Send packets by testpmd in VM2, check Check virtio-pmd RX/TX can work normally and imix packets can looped between two VMs for 1 mins:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + +10. Rerun step 7. + +11. Stop testpmd in host, and check that 4 queues can RX/TX traffic. + +Test Case 7: VM2VM virtio-pmd packed ring mergeable path dynamic queue size with dsa kernel driver and server mode +------------------------------------------------------------------------------------------------------------------- +This case tests packed ring mergeable path in VM2VM vhost-user/virtio-pmd topology when vhost uses the asynchronous operations with dsa kernel driver, +check that it can tx chain packets normally after dynamically changing queue number. + +1. Bind 1 dsa device to idxd:: + + ls /dev/dsa #check wq configure, reset if exist + ./usertools/dpdk-devbind.py -u 6a:01.0 + ./usertools/dpdk-devbind.py -b idxd 6a:01.0 + ./drivers/raw/ioat/dpdk_idxd_cfg.py -q 8 0 + ls /dev/dsa #check wq configure success + +2. Launch the testpmd with 2 vhost ports below commands:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=4 --txq=4 \ + --lcore-dma=[lcore2@wq0.0,lcore2@wq0.1,lcore3@wq0.2,lcore3@wq0.3,lcore4@wq0.4,lcore4@wq0.5,lcore5@wq0.6,lcore5@wq0.7] + testpmd>start + +3. Launch VM1 and VM2 using qemu:: + + taskset -c 6-16 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04.img \ + -chardev socket,path=/tmp/vm1_qga0.sock,server,nowait,id=vm1_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm1_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm1_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6002-:22 \ + -chardev socket,id=char0,path=./vhost-net0,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=on,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on,packed=on -vnc :10 + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=on,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on,packed=on -vnc :12 + +4. On VM1 and VM2, bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +5. Launch testpmd in VM1:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 --max-pkt-len=9600 --rx-offloads=0x00002000 + testpmd>set fwd mac + testpmd>start + +6. Launch testpmd in VM2 and send imix pkts, check imix packets can looped between two VMs for 1 mins and 4 queues (queue0 to queue3) have packets rx/tx:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 --max-pkt-len=9600 --rx-offloads=0x00002000 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512,1024,2000,64,256,512,1024,2000 + testpmd>start tx_first 32 + testpmd>show port stats all + testpmd>stop + +7. Quit VM2 and relaunch VM2 with split ring:: + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=off,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on -vnc :12 + +8. Bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +9. Launch testpmd in VM2 and send imix pkts from VM2:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512 + testpmd>start tx_first 32 + +10. Check vhost use the asynchronous data path(funtion like virtio_dev_rx_async_xxx/virtio_dev_tx_async_xxx):: + + perf top + +11. On host, check imix packets can looped between two VMs and 4 queues all have packets rx/tx:: + + testpmd>show port stats all + testpmd>stop + +12. On host, dynamic change queue numbers:: + + testpmd>stop + testpmd>port stop all + testpmd>port config all rxq 8 + testpmd>port config all txq 8 + testpmd>port start all + testpmd>start + +13. Send packets by testpmd in VM2:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + +14. Check vhost testpmd RX/TX can work normally, packets can looped between two VMs and both 8 queues can RX/TX traffic. + +15. Rerun step 10. + +Test Case 8: VM2VM virtio-pmd packed ring non-mergeable path dynamic queue size with dsa kernel driver and server mode +------------------------------------------------------------------------------------------------------------------------ +This case tests packed ring non-mergeable path in VM2VM vhost-user/virtio-pmd topology when vhost uses the asynchronous operations with dsa kernel driver, +check that it can work normally after dynamically changing queue number at virtio-pmd side. + +1. Bind 2 dsa device to idxd:: + + ls /dev/dsa #check wq configure, reset if exist + ./usertools/dpdk-devbind.py -u 6a:01.0 6f:01.0 + ./usertools/dpdk-devbind.py -b idxd 6a:01.0 6f:01.0 + ./drivers/raw/ioat/dpdk_idxd_cfg.py -q 8 0 + ./drivers/raw/ioat/dpdk_idxd_cfg.py -q 8 1 + ls /dev/dsa #check wq configure success + +1. Launch the testpmd with 2 vhost ports below commands:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-5 -n 4 --file-prefix=vhost \ + --vdev 'net_vhost0,iface=vhost-net0,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;txq4;txq5;rxq2;rxq3;rxq4;rxq5;rxq6;rxq7]' \ + --vdev 'net_vhost1,iface=vhost-net1,client=1,queues=8,dmas=[txq0;txq1;txq2;txq3;txq4;txq5;rxq2;rxq3;rxq4;rxq5;rxq6;rxq7]' \ + -- -i --nb-cores=4 --txd=1024 --rxd=1024 --rxq=8 --txq=8 \ + --lcore-dma=[lcore2@wq0.0,lcore2@wq0.1,lcore3@wq0.2,lcore3@wq0.3,lcore4@wq1.0,lcore4@wq1.1,lcore5@wq1.2,lcore5@wq1.3] + testpmd>start + +2. Launch VM1 and VM2 using qemu:: + + taskset -c 6-16 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04.img \ + -chardev socket,path=/tmp/vm1_qga0.sock,server,nowait,id=vm1_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm1_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm1_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6002-:22 \ + -chardev socket,id=char0,path=./vhost-net0,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=off,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on,packed=on -vnc :10 + + taskset -c 17-27 /usr/local/qemu-7.0.0/bin/qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 9 -m 4096 \ + -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \ + -numa node,memdev=mem -mem-prealloc -drive file=/home/xingguang/osimg/ubuntu20-04-2.img \ + -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \ + -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \ + -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \ + -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \ + -chardev socket,id=char0,path=./vhost-net1,server \ + -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce,queues=8 \ + -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=off,mq=on,vectors=40,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,guest_ufo=on,host_ufo=on,packed=on -vnc :12 + +3. On VM1 and VM2, bind virtio device with vfio-pci driver:: + + modprobe vfio + modprobe vfio-pci + echo 1 > /sys/module/vfio/parameters/enable_unsafe_noiommu_mode + ./usertools/dpdk-devbind.py --force --bind=vfio-pci 0000:00:05.0 + +4. Launch testpmd in VM1:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 + testpmd>set fwd mac + testpmd>start + +5. Launch testpmd in VM2 and send imix pkts, check imix packets can looped between two VMs for 1 mins:: + + ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -c 0x3 -n 4 -- -i --tx-offloads=0x00 --enable-hw-vlan-strip --txq=8 --rxq=8 --txd=1024 --rxd=1024 + testpmd>set fwd mac + testpmd>set txpkts 64,256,512 + testpmd>start tx_first 32 + testpmd>show port stats all + +6. Check vhost use the asynchronous data path(funtion like virtio_dev_rx_async_xxx/virtio_dev_tx_async_xxx):: + + perf top + +7. On VM2, stop the testpmd, check that both 8 queues have packets rx/tx:: + + testpmd>stop + +8. On VM2, dynamic change queue numbers at virtio-pmd side from 8 queues to 4 queues:: + + testpmd>stop + testpmd>port stop all + testpmd>port config all rxq 4 + testpmd>port config all txq 4 + testpmd>port start all + testpmd>start + +9. Send packets by testpmd in VM2, check Check virtio-pmd RX/TX can work normally and imix packets can looped between two VMs for 1 mins:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + +10. Rerun step 6. + +11. Stop testpmd in VM2, and check that 4 queues can RX/TX traffic. + +12. On VM2, dynamic change queue numbers at virtio-pmd side from 4 queues to 8 queues:: + + testpmd>stop + testpmd>port stop all + testpmd>port config all rxq 8 + testpmd>port config all txq 8 + testpmd>port start all + testpmd>start + +13. Send packets by testpmd in VM2, check Check virtio-pmd RX/TX can work normally and imix packets can looped between two VMs for 1 mins:: + + testpmd>stop + testpmd>start tx_first 32 + testpmd>show port stats all + +14. Rerun step 6. + +15. Stop testpmd in VM2, and check that 8 queues can RX/TX traffic.