2 Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
5 Redistribution and use in source and binary forms, with or without
6 modification, are permitted provided that the following conditions
9 * Redistributions of source code must retain the above copyright
10 notice, this list of conditions and the following disclaimer.
11 * Redistributions in binary form must reproduce the above copyright
12 notice, this list of conditions and the following disclaimer in
13 the documentation and/or other materials provided with the
15 * Neither the name of Intel Corporation nor the names of its
16 contributors may be used to endorse or promote products derived
17 from this software without specific prior written permission.
19 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23 OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
31 VMDQ and DCB Forwarding Sample Application
32 ==========================================
34 The VMDQ and DCB Forwarding sample application is a simple example of packet processing using the DPDK.
35 The application performs L2 forwarding using VMDQ and DCB to divide the incoming traffic into 128 queues.
36 The traffic splitting is performed in hardware by the VMDQ and DCB features of the IntelĀ® 82599 10 Gigabit Ethernet Controller.
41 This sample application can be used as a starting point for developing a new application that is based on the DPDK and
42 uses VMDQ and DCB for traffic partitioning.
44 The VMDQ and DCB filters work on VLAN traffic to divide the traffic into 128 input queues on the basis of the VLAN ID field and
45 VLAN user priority field.
46 VMDQ filters split the traffic into 16 or 32 groups based on the VLAN ID.
47 Then, DCB places each packet into one of either 4 or 8 queues within that group, based upon the VLAN user priority field.
49 In either case, 16 groups of 8 queues, or 32 groups of 4 queues, the traffic can be split into 128 hardware queues on the NIC,
50 each of which can be polled individually by a DPDK application.
52 All traffic is read from a single incoming port (port 0) and output on port 1, without any processing being performed.
53 The traffic is split into 128 queues on input, where each thread of the application reads from multiple queues.
54 For example, when run with 8 threads, that is, with the -c FF option, each thread receives and forwards packets from 16 queues.
56 As supplied, the sample application configures the VMDQ feature to have 16 pools with 8 queues each as indicated in :numref:`figure_vmdq_dcb_example`.
57 The IntelĀ® 82599 10 Gigabit Ethernet Controller NIC also supports the splitting of traffic into 32 pools of 4 queues each and
58 this can be used by changing the NUM_POOLS parameter in the supplied code.
59 The NUM_POOLS parameter can be passed on the command line, after the EAL parameters:
61 .. code-block:: console
63 ./build/vmdq_dcb [EAL options] -- -p PORTMASK --nb-pools NP
65 where, NP can be 16 or 32.
67 .. _figure_vmdq_dcb_example:
69 .. figure:: img/vmdq_dcb_example.*
71 Packet Flow Through the VMDQ and DCB Sample Application
74 In Linux* user space, the application can display statistics with the number of packets received on each queue.
75 To have the application display the statistics, send a SIGHUP signal to the running application process, as follows:
77 where, <pid> is the process id of the application process.
79 The VMDQ and DCB Forwarding sample application is in many ways simpler than the L2 Forwarding application
80 (see Chapter 9 , "L2 Forwarding Sample Application (in Real and Virtualized Environments)")
81 as it performs unidirectional L2 forwarding of packets from one port to a second port.
82 No command-line options are taken by this application apart from the standard EAL command-line options.
86 Since VMD queues are being used for VMM, this application works correctly
87 when VTd is disabled in the BIOS or Linux* kernel (intel_iommu=off).
89 Compiling the Application
90 -------------------------
92 #. Go to the examples directory:
94 .. code-block:: console
96 export RTE_SDK=/path/to/rte_sdk cd ${RTE_SDK}/examples/vmdq_dcb
98 #. Set the target (a default target is used if not specified). For example:
100 .. code-block:: console
102 export RTE_TARGET=x86_64-native-linuxapp-gcc
104 See the *DPDK Getting Started Guide* for possible RTE_TARGET values.
106 #. Build the application:
108 .. code-block:: console
112 Running the Application
113 -----------------------
115 To run the example in a linuxapp environment:
117 .. code-block:: console
119 user@target:~$ ./build/vmdq_dcb -c f -n 4 -- -p 0x3 --nb-pools 16
121 Refer to the *DPDK Getting Started Guide* for general information on running applications and
122 the Environment Abstraction Layer (EAL) options.
127 The following sections provide some explanation of the code.
132 The EAL, driver and PCI configuration is performed largely as in the L2 Forwarding sample application,
133 as is the creation of the mbuf pool.
134 See Chapter 9, "L2 Forwarding Sample Application (in Real and Virtualized Environments)".
135 Where this example application differs is in the configuration of the NIC port for RX.
137 The VMDQ and DCB hardware feature is configured at port initialization time by setting the appropriate values in the
138 rte_eth_conf structure passed to the rte_eth_dev_configure() API.
139 Initially in the application,
140 a default structure is provided for VMDQ and DCB configuration to be filled in later by the application.
144 /* empty vmdq+dcb configuration structure. Filled in programmatically */
146 static const struct rte_eth_conf vmdq_dcb_conf_default = {
148 .mq_mode = ETH_VMDQ_DCB,
150 .header_split = 0, /**< Header Split disabled */
151 .hw_ip_checksum = 0, /**< IP checksum offload disabled */
152 .hw_vlan_filter = 0, /**< VLAN filtering disabled */
153 .jumbo_frame = 0, /**< Jumbo Frame Support disabled */
157 .mq_mode = ETH_DCB_NONE,
162 * should be overridden separately in code with
167 .nb_queue_pools = ETH_16_POOLS,
168 .enable_default_pool = 0,
171 .pool_map = {{0, 0},},
177 The get_eth_conf() function fills in an rte_eth_conf structure with the appropriate values,
178 based on the global vlan_tags array,
179 and dividing up the possible user priority values equally among the individual queues
180 (also referred to as traffic classes) within each pool, that is,
181 if the number of pools is 32, then the user priority fields are allocated two to a queue.
182 If 16 pools are used, then each of the 8 user priority fields is allocated to its own queue within the pool.
183 For the VLAN IDs, each one can be allocated to possibly multiple pools of queues,
184 so the pools parameter in the rte_eth_vmdq_dcb_conf structure is specified as a bitmask value.
188 const uint16_t vlan_tags[] = {
189 0, 1, 2, 3, 4, 5, 6, 7,
190 8, 9, 10, 11, 12, 13, 14, 15,
191 16, 17, 18, 19, 20, 21, 22, 23,
192 24, 25, 26, 27, 28, 29, 30, 31
196 /* Builds up the correct configuration for vmdq+dcb based on the vlan tags array
197 * given above, and the number of traffic classes available for use. */
200 get_eth_conf(struct rte_eth_conf *eth_conf, enum rte_eth_nb_pools num_pools)
202 struct rte_eth_vmdq_dcb_conf conf;
205 if (num_pools != ETH_16_POOLS && num_pools != ETH_32_POOLS ) return -1;
207 conf.nb_queue_pools = num_pools;
208 conf.enable_default_pool = 0;
209 conf.default_pool = 0; /* set explicit value, even if not used */
210 conf.nb_pool_maps = sizeof( vlan_tags )/sizeof( vlan_tags[ 0 ]);
212 for (i = 0; i < conf.nb_pool_maps; i++){
213 conf.pool_map[i].vlan_id = vlan_tags[ i ];
214 conf.pool_map[i].pools = 1 << (i % num_pools);
217 for (i = 0; i < ETH_DCB_NUM_USER_PRIORITIES; i++){
218 conf.dcb_queue[i] = (uint8_t)(i % (NUM_QUEUES/num_pools));
221 (void) rte_memcpy(eth_conf, &vmdq_dcb_conf_default, sizeof(\*eth_conf));
222 (void) rte_memcpy(ð_conf->rx_adv_conf.vmdq_dcb_conf, &conf, sizeof(eth_conf->rx_adv_conf.vmdq_dcb_conf));
227 Once the network port has been initialized using the correct VMDQ and DCB values,
228 the initialization of the port's RX and TX hardware rings is performed similarly to that
229 in the L2 Forwarding sample application.
230 See Chapter 9, "L2 Forwarding Sample Application (in Real and Virtualized Environments)" for more information.
235 When run in a linuxapp environment,
236 the VMDQ and DCB Forwarding sample application can display statistics showing the number of packets read from each RX queue.
237 This is provided by way of a signal handler for the SIGHUP signal,
238 which simply prints to standard output the packet counts in grid form.
239 Each row of the output is a single pool with the columns being the queue number within that pool.
241 To generate the statistics output, use the following command:
243 .. code-block:: console
245 user@host$ sudo killall -HUP vmdq_dcb_app
247 Please note that the statistics output will appear on the terminal where the vmdq_dcb_app is running,
248 rather than the terminal from which the HUP signal was sent.