Patch Detail
get:
Show a patch.
patch:
Update a patch.
put:
Update a patch.
GET /api/patches/110943/?format=api
{ "id": 110943, "url": "https://patches.dpdk.org/api/patches/110943/?format=api", "web_url": "https://patches.dpdk.org/project/dts/patch/20220510015050.327818-1-weix.ling@intel.com/", "project": { "id": 3, "url": "https://patches.dpdk.org/api/projects/3/?format=api", "name": "DTS", "link_name": "dts", "list_id": "dts.dpdk.org", "list_email": "dts@dpdk.org", "web_url": "", "scm_url": "git://dpdk.org/tools/dts", "webscm_url": "http://git.dpdk.org/tools/dts/", "list_archive_url": "https://inbox.dpdk.org/dts", "list_archive_url_format": "https://inbox.dpdk.org/dts/{}", "commit_url_format": "" }, "msgid": "<20220510015050.327818-1-weix.ling@intel.com>", "list_archive_url": "https://inbox.dpdk.org/dts/20220510015050.327818-1-weix.ling@intel.com", "date": "2022-05-10T01:50:50", "name": "[V3,2/3] test_plans/dpdk_gro_lib_cbdma_test_plan: add dpdk_gro_lib_cbdma testplan", "commit_ref": null, "pull_url": null, "state": "superseded", "archived": false, "hash": "416334884c0f273e33990a1cf8d06f802bd6b529", "submitter": { "id": 1828, "url": "https://patches.dpdk.org/api/people/1828/?format=api", "name": "Ling, WeiX", "email": "weix.ling@intel.com" }, "delegate": null, "mbox": "https://patches.dpdk.org/project/dts/patch/20220510015050.327818-1-weix.ling@intel.com/mbox/", "series": [ { "id": 22856, "url": "https://patches.dpdk.org/api/series/22856/?format=api", "web_url": "https://patches.dpdk.org/project/dts/list/?series=22856", "date": "2022-05-10T01:50:17", "name": "add dpdk_gro_lib_cbdma", "version": 3, "mbox": "https://patches.dpdk.org/series/22856/mbox/" } ], "comments": "https://patches.dpdk.org/api/patches/110943/comments/", "check": "pending", "checks": "https://patches.dpdk.org/api/patches/110943/checks/", "tags": {}, "related": [], "headers": { "Return-Path": "<dts-bounces@dpdk.org>", "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])\n\tby inbox.dpdk.org (Postfix) with ESMTP id 47962A034C;\n\tTue, 10 May 2022 03:51:43 +0200 (CEST)", "from [217.70.189.124] (localhost [127.0.0.1])\n\tby mails.dpdk.org (Postfix) with ESMTP id 428094113D;\n\tTue, 10 May 2022 03:51:43 +0200 (CEST)", "from mga11.intel.com (mga11.intel.com [192.55.52.93])\n by mails.dpdk.org (Postfix) with ESMTP id A256140DDA\n for <dts@dpdk.org>; Tue, 10 May 2022 03:51:41 +0200 (CEST)", "from orsmga007.jf.intel.com ([10.7.209.58])\n by fmsmga102.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384;\n 09 May 2022 18:51:40 -0700", "from unknown (HELO localhost.localdomain) ([10.239.251.222])\n by orsmga007-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384;\n 09 May 2022 18:51:38 -0700" ], "DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/simple;\n d=intel.com; i=@intel.com; q=dns/txt; s=Intel;\n t=1652147501; x=1683683501;\n h=from:to:cc:subject:date:message-id:mime-version:\n content-transfer-encoding;\n bh=pp97JLz2h/nAjQB1ALAsP/EMN0Xml8IkZtHJJLNIoJg=;\n b=d5p+cXl7VXpBqNn0fwabvOWyMX9e7vcCG4qodr/Mk8zHsQ77tOmMoKfi\n nVXkRMCFS6r5p7KvY4h59HKtTbzhfLBceBPmDGXg35cJKHHrNyxBLfT+i\n 9mnULc5+Hs2AaBFSoZ6w1gy1RH6WjMFmP57saMZFsz8DVDAo6oenAKLcg\n z39rRBJ2vjI0B1w0Wu70NU5/TXbDt4C+rdtpxKb9ONpDjkFU2E+DMc0LR\n pvlcyRFhCpc3ADk96y6HN5RwXtN/vGqsmzFMjp9eTunWFLzPxZf9sLrVb\n F0i4IyOBFoLvY6yw2c+e/FFaawZi6jeLE9VIL+kIZD5wGCaRkdSYzL6rE w==;", "X-IronPort-AV": [ "E=McAfee;i=\"6400,9594,10342\"; a=\"266817482\"", "E=Sophos;i=\"5.91,213,1647327600\"; d=\"scan'208\";a=\"266817482\"", "E=Sophos;i=\"5.91,213,1647327600\"; d=\"scan'208\";a=\"565388154\"" ], "From": "Wei Ling <weix.ling@intel.com>", "To": "dts@dpdk.org", "Cc": "Wei Ling <weix.ling@intel.com>", "Subject": "[dts][PATCH V3 2/3] test_plans/dpdk_gro_lib_cbdma_test_plan: add\n dpdk_gro_lib_cbdma testplan", "Date": "Mon, 9 May 2022 21:50:50 -0400", "Message-Id": "<20220510015050.327818-1-weix.ling@intel.com>", "X-Mailer": "git-send-email 2.25.1", "MIME-Version": "1.0", "Content-Type": "text/plain; charset=y", "Content-Transfer-Encoding": "8bit", "X-BeenThere": "dts@dpdk.org", "X-Mailman-Version": "2.1.29", "Precedence": "list", "List-Id": "test suite reviews and discussions <dts.dpdk.org>", "List-Unsubscribe": "<https://mails.dpdk.org/options/dts>,\n <mailto:dts-request@dpdk.org?subject=unsubscribe>", "List-Archive": "<http://mails.dpdk.org/archives/dts/>", "List-Post": "<mailto:dts@dpdk.org>", "List-Help": "<mailto:dts-request@dpdk.org?subject=help>", "List-Subscribe": "<https://mails.dpdk.org/listinfo/dts>,\n <mailto:dts-request@dpdk.org?subject=subscribe>", "Errors-To": "dts-bounces@dpdk.org" }, "content": "Add new testplan test_plans/dpdk_gro_lib_cbdma_test_plan.\n\nSigned-off-by: Wei Ling <weix.ling@intel.com>\n---\n test_plans/dpdk_gro_lib_cbdma_test_plan.rst | 185 ++++++++++++++++++++\n 1 file changed, 185 insertions(+)\n create mode 100644 test_plans/dpdk_gro_lib_cbdma_test_plan.rst", "diff": "diff --git a/test_plans/dpdk_gro_lib_cbdma_test_plan.rst b/test_plans/dpdk_gro_lib_cbdma_test_plan.rst\nnew file mode 100644\nindex 00000000..445540a6\n--- /dev/null\n+++ b/test_plans/dpdk_gro_lib_cbdma_test_plan.rst\n@@ -0,0 +1,185 @@\n+.. Copyright (c) <2022>, Intel Corporation\n+ All rights reserved.\n+\n+ Redistribution and use in source and binary forms, with or without\n+ modification, are permitted provided that the following conditions\n+ are met:\n+\n+ - Redistributions of source code must retain the above copyright\n+ notice, this list of conditions and the following disclaimer.\n+\n+ - Redistributions in binary form must reproduce the above copyright\n+ notice, this list of conditions and the following disclaimer in\n+ the documentation and/or other materials provided with the\n+ distribution.\n+\n+ - Neither the name of Intel Corporation nor the names of its\n+ contributors may be used to endorse or promote products derived\n+ from this software without specific prior written permission.\n+\n+ THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS\n+ \"AS IS\" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT\n+ LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS\n+ FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE\n+ COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,\n+ INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES\n+ (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR\n+ SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)\n+ HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,\n+ STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)\n+ ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED\n+ OF THE POSSIBILITY OF SUCH DAMAGE.\n+\n+=================================\n+DPDK GRO lib with cbdma test plan\n+=================================\n+\n+Description\n+===========\n+\n+Generic Receive Offload (GRO) is a widely used SW-based offloading\n+technique to reduce per-packet processing overheads. By reassembling\n+small packets into larger ones, GRO enables applications to process\n+fewer large packets directly, thus reducing the number of packets to\n+be processed. To benefit DPDK-based applications, like Open vSwitch,\n+DPDK also provides own GRO implementation. In DPDK, GRO is implemented\n+as a standalone library. Applications explicitly use the GRO library to\n+reassemble packets.\n+\n+In the GRO library, there are many GRO types which are defined by packet\n+types. One GRO type is in charge of process one kind of packets. For\n+example, TCP/IPv4 GRO processes TCP/IPv4 packets.\n+\n+Each GRO type has a reassembly function, which defines own algorithm and\n+table structure to reassemble packets. We assign input packets to the\n+corresponding GRO functions by MBUF->packet_type.\n+\n+The GRO library doesn't check if input packets have correct checksums and\n+doesn't re-calculate checksums for merged packets. The GRO library\n+assumes the packets are complete (i.e., MF==0 && frag_off==0), when IP\n+fragmentation is possible (i.e., DF==0). Additionally, it complies RFC\n+6864 to process the IPv4 ID field.\n+\n+Currently, the GRO library provides GRO supports for TCP/IPv4 packets and\n+VxLAN packets which contain an outer IPv4 header and an inner TCP/IPv4\n+packet.\n+\n+This test plan includes dpdk gro lib test with TCP/IPv4 traffic with CBDMA.\n+\n+..Note:\n+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.\n+2.For split virtqueue virtio-net with multi-queues server mode test, need qemu version >= 5.2.0, dut to old qemu exist reconnect issue when multi-queues test.\n+3.DPDK local patch that about vhost pmd is needed when testing Vhost asynchronous data path with testpmd.\n+\n+Prerequisites\n+=============\n+\n+Modify the testpmd code as following::\n+\n+ --- a/app/test-pmd/csumonly.c\n+ +++ b/app/test-pmd/csumonly.c\n+ @@ -693,10 +693,12 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)\n+ * and inner headers */\n+ \n+ eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);\n+ +#if 0\n+ ether_addr_copy(&peer_eth_addrs[fs->peer_addr],\n+ ð_hdr->d_addr);\n+ ether_addr_copy(&ports[fs->tx_port].eth_addr,\n+ ð_hdr->s_addr);\n+ +#endif\n+ parse_ethernet(eth_hdr, &info);\n+ l3_hdr = (char *)eth_hdr + info.l2_len;\n+\n+Modify the dpdk code as following::\n+\n+ diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c\n+ index b38a4b6b1..573250dbe 100644\n+ --- a/drivers/net/vhost/rte_eth_vhost.c\n+ +++ b/drivers/net/vhost/rte_eth_vhost.c\n+ @@ -1071,8 +1071,14 @@ eth_dev_info(struct rte_eth_dev *dev,\n+ dev_info->min_rx_bufsize = 0;\n+\n+ dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS |\n+ - DEV_TX_OFFLOAD_VLAN_INSERT;\n+ - dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP;\n+ + DEV_TX_OFFLOAD_VLAN_INSERT |\n+ + DEV_TX_OFFLOAD_UDP_CKSUM |\n+ + DEV_TX_OFFLOAD_TCP_CKSUM |\n+ + DEV_TX_OFFLOAD_IPV4_CKSUM |\n+ + DEV_TX_OFFLOAD_TCP_TSO;\n+ + dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP |\n+ + DEV_RX_OFFLOAD_TCP_CKSUM |\n+ + DEV_RX_OFFLOAD_UDP_CKSUM |\n+ + DEV_RX_OFFLOAD_IPV4_CKSUM |\n+ + DEV_RX_OFFLOAD_TCP_LRO;\n+ }\n+\n+Compile DPDK as following::\n+\n+ CC=gcc meson --werror -Denable_kmods=True -Dlibdir=lib --default-library=static x86_64-native-linuxapp-gcc\n+ ninja -C x86_64-native-linuxapp-gcc -j 110\n+\n+Test flow\n+=========\n+\n+NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net\n+\n+\n+Test Case1: DPDK GRO test with two queues and two CBDMA channels using tcp/ipv4 traffic\n+=======================================================================================\n+\n+Test flow\n+=========\n+\n+\n+1. Connect two nic port directly, put nic2 into another namesapce and turn on the tso of this nic port by below cmds::\n+\n+ ip netns del ns1\n+ ip netns add ns1\n+ ip link set enp26s0f0 netns ns1 # [enp216s0f0] is the name of nic2\n+ ip netns exec ns1 ifconfig enp26s0f0 1.1.1.8 up\n+ ip netns exec ns1 ethtool -K enp26s0f0 tso on\n+\n+2. Bind cbdma port and nic1 to vfio-pci, launch vhost-user with testpmd and set flush interval to 1::\n+\n+ ./usertools/dpdk-devbind.py -b vfio-pci xx:xx.x\n+ ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 29-31 -n 4 \\\n+ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1]' \\\n+ -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 --nb-cores=2\n+ testpmd> set fwd csum\n+ testpmd> stop\n+ testpmd> port stop 0\n+ testpmd> port stop 1\n+ testpmd> csum set tcp hw 0\n+ testpmd> csum set ip hw 0\n+ testpmd> csum set tcp hw 1\n+ testpmd> csum set ip hw 1\n+ testpmd> set port 0 gro on\n+ testpmd> set gro flush 1\n+ testpmd> port start 0\n+ testpmd> port start 1\n+ testpmd> start\n+\n+3. Set up vm with virto device and using kernel virtio-net driver::\n+\n+ taskset -c 31 /home/qemu-install/qemu-4.2.1/bin/qemu-system-x86_64 -name us-vhost-vm1 \\\n+ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \\\n+ -numa node,memdev=mem \\\n+ -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 \\\n+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \\\n+ -chardev socket,id=char0,path=./vhost-net \\\n+ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \\\n+ -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 \\\n+ -vnc :10 -daemonize\n+\n+4. In vm, config the virtio-net device with ip and turn the kernel gro off::\n+\n+ ifconfig ens4 1.1.1.2 up # [ens3] is the name of virtio-net\n+ ethtool -L ens4 combined 2\n+ ethtool -K ens4 gro off\n+\n+5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput, should be larger than 10Gbits/sec::\n+\n+ Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2\n+ VM side: iperf -s\n", "prefixes": [ "V3", "2/3" ] }