1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright(c) 2010-2014 Intel Corporation.
6 L2 Forwarding Eventdev Sample Application
7 =========================================
9 The L2 Forwarding eventdev sample application is a simple example of packet
10 processing using the Data Plane Development Kit (DPDK) to demonstrate usage of
11 poll and event mode packet I/O mechanism.
16 The L2 Forwarding eventdev sample application, performs L2 forwarding for each
17 packet that is received on an RX_PORT. The destination port is the adjacent port
18 from the enabled portmask, that is, if the first four ports are enabled (portmask=0x0f),
19 ports 1 and 2 forward into each other, and ports 3 and 4 forward into each other.
20 Also, if MAC addresses updating is enabled, the MAC addresses are affected as follows:
22 * The source MAC address is replaced by the TX_PORT MAC address
24 * The destination MAC address is replaced by 02:00:00:00:00:TX_PORT_ID
26 Application receives packets from RX_PORT using below mentioned methods:
30 * Eventdev mode (default)
32 This application can be used to benchmark performance using a traffic-generator,
33 as shown in the :numref:`figure_l2fwd_event_benchmark_setup`.
35 .. _figure_l2fwd_event_benchmark_setup:
37 .. figure:: img/l2_fwd_benchmark_setup.*
39 Performance Benchmark Setup (Basic Environment)
41 Compiling the Application
42 -------------------------
44 To compile the sample application see :doc:`compiling`.
46 The application is located in the ``l2fwd-event`` sub-directory.
48 Running the Application
49 -----------------------
51 The application requires a number of command line options:
53 .. code-block:: console
55 ./<build_dir>/examples/dpdk-l2fwd-event [EAL options] -- -p PORTMASK [-q NQ] --[no-]mac-updating --mode=MODE --eventq-sched=SCHED_MODE
59 * p PORTMASK: A hexadecimal bitmask of the ports to configure
61 * q NQ: A number of queues (=ports) per lcore (default is 1)
63 * --[no-]mac-updating: Enable or disable MAC addresses updating (enabled by default).
65 * --mode=MODE: Packet transfer mode for I/O, poll or eventdev. Eventdev by default.
67 * --eventq-sched=SCHED_MODE: Event queue schedule mode, Ordered, Atomic or Parallel. Atomic by default.
69 * --config: Configure forwarding port pair mapping. Alternate port pairs by default.
71 Sample usage commands are given below to run the application into different mode:
73 Poll mode with 4 lcores, 16 ports and 8 RX queues per lcore and MAC address updating enabled,
76 .. code-block:: console
78 ./<build_dir>/examples/dpdk-l2fwd-event -l 0-3 -n 4 -- -q 8 -p ffff --mode=poll
80 Eventdev mode with 4 lcores, 16 ports , sched method ordered and MAC address updating enabled,
83 .. code-block:: console
85 ./<build_dir>/examples/dpdk-l2fwd-event -l 0-3 -n 4 -- -p ffff --eventq-sched=ordered
89 .. code-block:: console
91 ./<build_dir>/examples/dpdk-l2fwd-event -l 0-3 -n 4 -- -q 8 -p ffff --mode=eventdev --eventq-sched=ordered
93 Refer to the *DPDK Getting Started Guide* for general information on running
94 applications and the Environment Abstraction Layer (EAL) options.
96 To run application with S/W scheduler, it uses following DPDK services:
99 * Rx adapter service function
100 * Tx adapter service function
102 Application needs service cores to run above mentioned services. Service cores
103 must be provided as EAL parameters along with the --vdev=event_sw0 to enable S/W
104 scheduler. Following is the sample command:
106 .. code-block:: console
108 ./<build_dir>/examples/dpdk-l2fwd-event -l 0-7 -s 0-3 -n 4 --vdev event_sw0 -- -q 8 -p ffff --mode=eventdev --eventq-sched=ordered
113 The following sections provide some explanation of the code.
115 .. _l2_fwd_event_app_cmd_arguments:
117 Command Line Arguments
118 ~~~~~~~~~~~~~~~~~~~~~~
120 The L2 Forwarding eventdev sample application takes specific parameters,
121 in addition to Environment Abstraction Layer (EAL) arguments.
122 The preferred way to parse parameters is to use the getopt() function,
123 since it is part of a well-defined and portable library.
125 The parsing of arguments is done in the **l2fwd_parse_args()** function for non
126 eventdev parameters and in **parse_eventdev_args()** for eventdev parameters.
127 The method of argument parsing is not described here. Refer to the
128 *glibc getopt(3)* man page for details.
130 EAL arguments are parsed first, then application-specific arguments.
131 This is done at the beginning of the main() function and eventdev parameters
132 are parsed in eventdev_resource_setup() function during eventdev setup:
134 .. literalinclude:: ../../../examples/l2fwd-event/main.c
136 :start-after: Init EAL. 8<
137 :end-before: >8 End of init EAL.
140 Mbuf Pool Initialization
141 ~~~~~~~~~~~~~~~~~~~~~~~~
143 Once the arguments are parsed, the mbuf pool is created.
144 The mbuf pool contains a set of mbuf objects that will be used by the driver
145 and the application to store network packet data:
147 .. literalinclude:: ../../../examples/l2fwd-event/main.c
149 :start-after: Create the mbuf pool. 8<
150 :end-before: >8 End of creation of mbuf pool.
153 The rte_mempool is a generic structure used to handle pools of objects.
154 In this case, it is necessary to create a pool that will be used by the driver.
155 The number of allocated pkt mbufs is NB_MBUF, with a data room size of
156 RTE_MBUF_DEFAULT_BUF_SIZE each.
157 A per-lcore cache of 32 mbufs is kept.
158 The memory is allocated in NUMA socket 0,
159 but it is possible to extend this code to allocate one mbuf pool per socket.
161 The rte_pktmbuf_pool_create() function uses the default mbuf pool and mbuf
162 initializers, respectively rte_pktmbuf_pool_init() and rte_pktmbuf_init().
163 An advanced application may want to use the mempool API to create the
164 mbuf pool with more control.
166 .. _l2_fwd_event_app_drv_init:
168 Driver Initialization
169 ~~~~~~~~~~~~~~~~~~~~~
171 The main part of the code in the main() function relates to the initialization
172 of the driver. To fully understand this code, it is recommended to study the
173 chapters that related to the Poll Mode and Event mode Driver in the
174 *DPDK Programmer's Guide* - Rel 1.4 EAR and the *DPDK API Reference*.
176 .. literalinclude:: ../../../examples/l2fwd-event/main.c
178 :start-after: Reset l2fwd_dst_ports. 8<
179 :end-before: >8 End of reset l2fwd_dst_ports.
182 The next step is to configure the RX and TX queues. For each port, there is only
183 one RX queue (only one lcore is able to poll a given port). The number of TX
184 queues depends on the number of available lcores. The rte_eth_dev_configure()
185 function is used to configure the number of queues for a port:
187 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_common.c
189 :start-after: Configure RX and TX queue. 8<
190 :end-before: >8 End of configuration RX and TX queue.
193 RX Queue Initialization
194 ~~~~~~~~~~~~~~~~~~~~~~~
196 The application uses one lcore to poll one or several ports, depending on the -q
197 option, which specifies the number of queues per lcore.
199 For example, if the user specifies -q 4, the application is able to poll four
200 ports with one lcore. If there are 16 ports on the target (and if the portmask
201 argument is -p ffff ), the application will need four lcores to poll all the
204 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_common.c
206 :start-after: Using lcore to poll one or several ports. 8<
207 :end-before: >8 End of using lcore to poll one or several ports.
210 The list of queues that must be polled for a given lcore is stored in a private
211 structure called struct lcore_queue_conf.
213 .. literalinclude:: ../../../examples/l2fwd/main.c
215 :start-after: List of queues to be polled for a given lcore. 8<
216 :end-before: >8 End of list of queues to be polled for a given lcore.
218 The values n_rx_port and rx_port_list[] are used in the main packet processing
219 loop (see :ref:`l2_fwd_event_app_rx_tx_packets`).
221 .. _l2_fwd_event_app_tx_init:
223 TX Queue Initialization
224 ~~~~~~~~~~~~~~~~~~~~~~~
226 Each lcore should be able to transmit on any port. For every port, a single TX
227 queue is initialized.
229 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_common.c
231 :start-after: Init one TX queue on each port. 8<
232 :end-before: >8 End of init one TX queue on each port.
235 To configure eventdev support, application setups following components:
243 .. _l2_fwd_event_app_event_dev_init:
245 Event device Initialization
246 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
247 Application can use either H/W or S/W based event device scheduler
248 implementation and supports single instance of event device. It configures event
249 device as per below configuration
251 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_event_generic.c
253 :start-after: Configures event device as per below configuration. 8<
254 :end-before: >8 End of configuration event device as per below configuration.
257 In case of S/W scheduler, application runs eventdev scheduler service on service
258 core. Application retrieves service id and finds the best possible service core to
261 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_event.c
263 :start-after: Running eventdev scheduler service on service core. 8<
264 :end-before: >8 End of running eventdev scheduler service on service core.
267 Event queue Initialization
268 ~~~~~~~~~~~~~~~~~~~~~~~~~~
269 Each Ethernet device is assigned a dedicated event queue which will be linked
270 to all available event ports i.e. each lcore can dequeue packets from any of the
273 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_event_generic.c
275 :start-after: Event queue initialization. 8<
276 :end-before: >8 End of event queue initialization.
279 In case of S/W scheduler, an extra event queue is created which will be used for
280 Tx adapter service function for enqueue operation.
282 .. _l2_fwd_app_event_port_init:
284 Event port Initialization
285 ~~~~~~~~~~~~~~~~~~~~~~~~~
286 Each worker thread is assigned a dedicated event port for enq/deq operations
287 to/from an event device. All event ports are linked with all available event
290 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_event_generic.c
292 :start-after: Event port initialization. 8<
293 :end-before: >8 End of event port initialization.
296 In case of S/W scheduler, an extra event port is created by DPDK library which
297 is retrieved by the application and same will be used by Tx adapter service.
299 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_event_generic.c
301 :start-after: Extra port created. 8<
302 :end-before: >8 End of extra port created.
305 Rx/Tx adapter Initialization
306 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
307 Each Ethernet port is assigned a dedicated Rx/Tx adapter for H/W scheduler. Each
308 Ethernet port's Rx queues are connected to its respective event queue at
309 priority 0 via Rx adapter configuration and Ethernet port's tx queues are
310 connected via Tx adapter.
312 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_event_internal_port.c
314 :start-after: Assigned ethernet port. 8<
315 :end-before: >8 End of assigned ethernet port.
318 For S/W scheduler instead of dedicated adapters, common Rx/Tx adapters are
319 configured which will be shared among all the Ethernet ports. Also DPDK library
320 need service cores to run internal services for Rx/Tx adapters. Application gets
321 service id for Rx/Tx adapters and after successful setup it runs the services
322 on dedicated service cores.
324 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_event.c
326 :start-after: Gets service ID for RX/TX adapters. 8<
327 :end-before: >8 End of get service ID for RX/TX adapters.
330 .. _l2_fwd_event_app_rx_tx_packets:
332 Receive, Process and Transmit Packets
333 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
335 In the **l2fwd_main_loop()** function, the main task is to read ingress packets from
336 the RX queues. This is done using the following code:
338 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_poll.c
340 :start-after: Reading ingress packets. 8<
341 :end-before: >8 End of reading ingress packets.
344 Packets are read in a burst of size MAX_PKT_BURST. The rte_eth_rx_burst()
345 function writes the mbuf pointers in a local table and returns the number of
346 available mbufs in the table.
348 Then, each mbuf in the table is processed by the l2fwd_simple_forward()
349 function. The processing is very simple: process the TX port from the RX port,
350 then replace the source and destination MAC addresses if MAC addresses updating
353 During the initialization process, a static array of destination ports
354 (l2fwd_dst_ports[]) is filled such that for each source port, a destination port
355 is assigned that is either the next or previous enabled port from the portmask.
356 If number of ports are odd in portmask then packet from last port will be
357 forwarded to first port i.e. if portmask=0x07, then forwarding will take place
358 like p0--->p1, p1--->p2, p2--->p0.
360 Also to optimize enqueue operation, l2fwd_simple_forward() stores incoming mbufs
361 up to MAX_PKT_BURST. Once it reaches up to limit, all packets are transmitted to
364 .. literalinclude:: ../../../examples/l2fwd/main.c
366 :start-after: Simple forward. 8<
367 :end-before: >8 End of simple forward.
369 For this test application, the processing is exactly the same for all packets
370 arriving on the same RX port. Therefore, it would have been possible to call
371 the rte_eth_tx_buffer() function directly from the main loop to send all the
372 received packets on the same TX port, using the burst-oriented send function,
373 which is more efficient.
375 However, in real-life applications (such as, L3 routing),
376 packet N is not necessarily forwarded on the same port as packet N-1.
377 The application is implemented to illustrate that, so the same approach can be
378 reused in a more complex application.
380 To ensure that no packets remain in the tables, each lcore does a draining of TX
381 queue in its main loop. This technique introduces some latency when there are
382 not many packets to send, however it improves performance:
384 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_poll.c
386 :start-after: Draining TX queue in main loop. 8<
387 :end-before: >8 End of draining TX queue in main loop.
390 In the **l2fwd_event_loop()** function, the main task is to read ingress
391 packets from the event ports. This is done using the following code:
393 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_event.c
395 :start-after: Read packet from eventdev. 8<
396 :end-before: >8 End of reading packets from eventdev.
400 Before reading packets, deq_len is fetched to ensure correct allowed deq length
402 The rte_event_dequeue_burst() function writes the mbuf pointers in a local table
403 and returns the number of available mbufs in the table.
405 Then, each mbuf in the table is processed by the l2fwd_eventdev_forward()
406 function. The processing is very simple: process the TX port from the RX port,
407 then replace the source and destination MAC addresses if MAC addresses updating
410 During the initialization process, a static array of destination ports
411 (l2fwd_dst_ports[]) is filled such that for each source port, a destination port
412 is assigned that is either the next or previous enabled port from the portmask.
413 If number of ports are odd in portmask then packet from last port will be
414 forwarded to first port i.e. if portmask=0x07, then forwarding will take place
415 like p0--->p1, p1--->p2, p2--->p0.
417 l2fwd_eventdev_forward() does not stores incoming mbufs. Packet will forwarded
418 be to destination ports via Tx adapter or generic event dev enqueue API
419 depending H/W or S/W scheduler is used.
421 .. literalinclude:: ../../../examples/l2fwd-event/l2fwd_event.c
423 :start-after: Read packet from eventdev. 8<
424 :end-before: >8 End of reading packets from eventdev.