1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright(c) 2020 Intel Corporation.
4 VMDq Forwarding Sample Application
5 ==========================================
7 The VMDq Forwarding sample application is a simple example of packet processing using the DPDK.
8 The application performs L2 forwarding using VMDq to divide the incoming traffic into queues.
9 The traffic splitting is performed in hardware by the VMDq feature of the Intel® 82599 and X710/XL710 Ethernet Controllers.
14 This sample application can be used as a starting point for developing a new application that is based on the DPDK and
15 uses VMDq for traffic partitioning.
17 VMDq filters split the incoming packets up into different "pools" - each with its own set of RX queues - based upon
18 the MAC address and VLAN ID within the VLAN tag of the packet.
20 All traffic is read from a single incoming port and output on another port, without any processing being performed.
21 With Intel® 82599 NIC, for example, the traffic is split into 128 queues on input, where each thread of the application reads from
22 multiple queues. When run with 8 threads, that is, with the -c FF option, each thread receives and forwards packets from 16 queues.
24 As supplied, the sample application configures the VMDq feature to have 32 pools with 4 queues each.
25 The Intel® 82599 10 Gigabit Ethernet Controller NIC also supports the splitting of traffic into 16 pools of 2 queues.
26 While the Intel® X710 or XL710 Ethernet Controller NICs support many configurations of VMDq pools of 4 or 8 queues each.
27 And queues numbers for each VMDq pool can be changed by setting CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_VM
28 in config/common_* file.
29 The nb-pools and enable-rss parameters can be passed on the command line, after the EAL parameters:
31 .. code-block:: console
33 ./build/vmdq_app [EAL options] -- -p PORTMASK --nb-pools NP --enable-rss
35 where, NP can be 8, 16 or 32, rss is disabled by default.
37 In Linux* user space, the application can display statistics with the number of packets received on each queue.
38 To have the application display the statistics, send a SIGHUP signal to the running application process.
40 The VMDq Forwarding sample application is in many ways simpler than the L2 Forwarding application
41 (see :doc:`l2_forward_real_virtual`)
42 as it performs unidirectional L2 forwarding of packets from one port to a second port.
43 No command-line options are taken by this application apart from the standard EAL command-line options.
45 Compiling the Application
46 -------------------------
48 To compile the sample application see :doc:`compiling`.
50 The application is located in the ``vmdq`` sub-directory.
52 Running the Application
53 -----------------------
55 To run the example in a Linux environment:
57 .. code-block:: console
59 user@target:~$ ./build/vmdq_app -l 0-3 -n 4 -- -p 0x3 --nb-pools 16
61 Refer to the *DPDK Getting Started Guide* for general information on running applications and
62 the Environment Abstraction Layer (EAL) options.
67 The following sections provide some explanation of the code.
72 The EAL, driver and PCI configuration is performed largely as in the L2 Forwarding sample application,
73 as is the creation of the mbuf pool.
74 See :doc:`l2_forward_real_virtual`.
75 Where this example application differs is in the configuration of the NIC port for RX.
77 The VMDq hardware feature is configured at port initialization time by setting the appropriate values in the
78 rte_eth_conf structure passed to the rte_eth_dev_configure() API.
79 Initially in the application,
80 a default structure is provided for VMDq configuration to be filled in later by the application.
84 /* empty vmdq configuration structure. Filled in programmatically */
85 static const struct rte_eth_conf vmdq_conf_default = {
87 .mq_mode = ETH_MQ_RX_VMDQ_ONLY,
92 .mq_mode = ETH_MQ_TX_NONE,
96 * should be overridden separately in code with
100 .nb_queue_pools = ETH_8_POOLS,
101 .enable_default_pool = 0,
104 .pool_map = {{0, 0},},
109 The get_eth_conf() function fills in an rte_eth_conf structure with the appropriate values,
110 based on the global vlan_tags array.
111 For the VLAN IDs, each one can be allocated to possibly multiple pools of queues.
112 For destination MAC, each VMDq pool will be assigned with a MAC address. In this sample, each VMDq pool
113 is assigned to the MAC like 52:54:00:12:<port_id>:<pool_id>, that is,
114 the MAC of VMDq pool 2 on port 1 is 52:54:00:12:01:02.
118 const uint16_t vlan_tags[] = {
119 0, 1, 2, 3, 4, 5, 6, 7,
120 8, 9, 10, 11, 12, 13, 14, 15,
121 16, 17, 18, 19, 20, 21, 22, 23,
122 24, 25, 26, 27, 28, 29, 30, 31,
123 32, 33, 34, 35, 36, 37, 38, 39,
124 40, 41, 42, 43, 44, 45, 46, 47,
125 48, 49, 50, 51, 52, 53, 54, 55,
126 56, 57, 58, 59, 60, 61, 62, 63,
129 /* pool mac addr template, pool mac addr is like: 52 54 00 12 port# pool# */
130 static struct rte_ether_addr pool_addr_template = {
131 .addr_bytes = {0x52, 0x54, 0x00, 0x12, 0x00, 0x00}
135 * Builds up the correct configuration for vmdq based on the vlan tags array
136 * given above, and determine the queue number and pool map number according to
140 get_eth_conf(struct rte_eth_conf *eth_conf, uint32_t num_pools)
142 struct rte_eth_vmdq_rx_conf conf;
145 conf.nb_queue_pools = (enum rte_eth_nb_pools)num_pools;
146 conf.nb_pool_maps = num_pools;
147 conf.enable_default_pool = 0;
148 conf.default_pool = 0; /* set explicit value, even if not used */
150 for (i = 0; i < conf.nb_pool_maps; i++) {
151 conf.pool_map[i].vlan_id = vlan_tags[i];
152 conf.pool_map[i].pools = (1UL << (i % num_pools));
155 (void)(rte_memcpy(eth_conf, &vmdq_conf_default, sizeof(*eth_conf)));
156 (void)(rte_memcpy(ð_conf->rx_adv_conf.vmdq_rx_conf, &conf,
157 sizeof(eth_conf->rx_adv_conf.vmdq_rx_conf)));
164 * Set mac for each pool.
165 * There is no default mac for the pools in i40.
166 * Removes this after i40e fixes this issue.
168 for (q = 0; q < num_pools; q++) {
169 struct rte_ether_addr mac;
170 mac = pool_addr_template;
171 mac.addr_bytes[4] = port;
172 mac.addr_bytes[5] = q;
173 printf("Port %u vmdq pool %u set mac %02x:%02x:%02x:%02x:%02x:%02x\n",
175 mac.addr_bytes[0], mac.addr_bytes[1],
176 mac.addr_bytes[2], mac.addr_bytes[3],
177 mac.addr_bytes[4], mac.addr_bytes[5]);
178 retval = rte_eth_dev_mac_addr_add(port, &mac,
181 printf("mac addr add failed at pool %d\n", q);
186 Once the network port has been initialized using the correct VMDq values,
187 the initialization of the port's RX and TX hardware rings is performed similarly to that
188 in the L2 Forwarding sample application.
189 See :doc:`l2_forward_real_virtual` for more information.
194 When run in a Linux environment,
195 the VMDq Forwarding sample application can display statistics showing the number of packets read from each RX queue.
196 This is provided by way of a signal handler for the SIGHUP signal,
197 which simply prints to standard output the packet counts in grid form.
198 Each row of the output is a single pool with the columns being the queue number within that pool.
200 To generate the statistics output, use the following command:
202 .. code-block:: console
204 user@host$ sudo killall -HUP vmdq_app
206 Please note that the statistics output will appear on the terminal where the vmdq_app is running,
207 rather than the terminal from which the HUP signal was sent.