1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright(c) 2010-2014 Intel Corporation.
4 Running the Application
5 =======================
7 EAL Command-line Options
8 ------------------------
10 Please refer to :doc:`EAL parameters (Linux) <../linux_gsg/linux_eal_parameters>`
11 or :doc:`EAL parameters (FreeBSD) <../freebsd_gsg/freebsd_eal_parameters>` for
12 a list of available EAL command-line options.
15 Testpmd Command-line Options
16 ----------------------------
18 The following are the command-line options for the testpmd applications.
19 They must be separated from the EAL options, shown in the previous section, with a ``--`` separator:
21 .. code-block:: console
23 sudo ./testpmd -l 0-3 -n 4 -- -i --portmask=0x1 --nb-cores=2
25 The command line options are:
27 * ``-i, --interactive``
29 Run testpmd in interactive mode.
30 In this mode, the testpmd starts with a prompt that can be used to start and stop forwarding,
31 configure the application and display stats on the current packet processing session.
32 See :ref:`testpmd_runtime` for more details.
34 In non-interactive mode,
35 the application starts with the configuration specified on the command-line and
36 immediately enters forwarding mode.
40 Display a help message and quit.
42 * ``-a, --auto-start``
44 Start forwarding on initialization.
48 Start forwarding, after sending a burst of packets first.
52 This flag should be only used in non-interactive mode.
54 * ``--stats-period PERIOD``
56 Display statistics every PERIOD seconds, if interactive mode is disabled.
57 The default value is 0, which means that the statistics will not be displayed.
61 Set the number of forwarding cores,
62 where 1 <= N <= "number of cores" or ``CONFIG_RTE_MAX_LCORE`` from the configuration file.
63 The default value is 1.
67 Set the number of forwarding ports,
68 where 1 <= N <= "number of ports" on the board or ``CONFIG_RTE_MAX_ETHPORTS`` from the configuration file.
69 The default value is the number of ports on the board.
73 Set the hexadecimal bitmask of the cores running the packet forwarding test.
74 The master lcore is reserved for command line parsing only and cannot be masked on for packet forwarding.
78 Set the hexadecimal bitmask of the ports used by the packet forwarding test.
82 Enable NUMA-aware allocation of RX/TX rings and of RX memory buffers
83 (mbufs). [Default setting]
87 Disable NUMA-aware allocation of RX/TX rings and of RX memory buffers (mbufs).
89 * ``--port-numa-config=(port,socket)[,(port,socket)]``
91 Specify the socket on which the memory pool to be used by the port will be allocated.
93 * ``--ring-numa-config=(port,flag,socket)[,(port,flag,socket)]``
95 Specify the socket on which the TX/RX rings for the port will be allocated.
96 Where flag is 1 for RX, 2 for TX, and 3 for RX and TX.
100 Set the socket from which all memory is allocated in NUMA mode,
101 where 0 <= N < number of sockets on the board.
105 Set the data size of the mbufs used to N bytes, where N < 65536. The default value is 2048.
107 * ``--total-num-mbufs=N``
109 Set the number of mbufs to be allocated in the mbuf pools, where N > 1024.
111 * ``--max-pkt-len=N``
113 Set the maximum packet size to N bytes, where N >= 64. The default value is 1518.
115 * ``--max-lro-pkt-size=N``
117 Set the maximum LRO aggregated packet size to N bytes, where N >= 64.
119 * ``--eth-peers-configfile=name``
121 Use a configuration file containing the Ethernet addresses of the peer ports.
122 The configuration file should contain the Ethernet addresses on separate lines::
128 * ``--eth-peer=N,XX:XX:XX:XX:XX:XX``
130 Set the MAC address ``XX:XX:XX:XX:XX:XX`` of the peer port N,
131 where 0 <= N < ``CONFIG_RTE_MAX_ETHPORTS`` from the configuration file.
133 * ``--tx-ip=SRC,DST``
135 Set the source and destination IP address used when doing transmit only test.
136 The defaults address values are source 198.18.0.1 and
137 destination 198.18.0.2. These are special purpose addresses
138 reserved for benchmarking (RFC 5735).
140 * ``--tx-udp=SRC[,DST]``
142 Set the source and destination UDP port number for transmit test only test.
143 The default port is the port 9 which is defined for the discard protocol
146 * ``--pkt-filter-mode=mode``
148 Set Flow Director mode where mode is either ``none`` (the default), ``signature`` or ``perfect``.
149 See :ref:`testpmd_flow_director` for more details.
151 * ``--pkt-filter-report-hash=mode``
153 Set Flow Director hash match reporting mode where mode is ``none``, ``match`` (the default) or ``always``.
155 * ``--pkt-filter-size=N``
157 Set Flow Director allocated memory size, where N is 64K, 128K or 256K.
158 Sizes are in kilobytes. The default is 64.
160 * ``--pkt-filter-flexbytes-offset=N``
162 Set the flexbytes offset.
163 The offset is defined in words (not bytes) counted from the first byte of the destination Ethernet MAC address,
164 where N is 0 <= N <= 32.
165 The default value is 0x6.
167 * ``--pkt-filter-drop-queue=N``
170 In perfect filter mode, when a rule is added with queue = -1, the packet will be enqueued into the RX drop-queue.
171 If the drop-queue does not exist, the packet is dropped. The default value is N=127.
173 * ``--disable-crc-strip``
175 Disable hardware CRC stripping.
179 Enable large receive offload.
181 * ``--enable-rx-cksum``
183 Enable hardware RX checksum offload.
185 * ``--enable-scatter``
187 Enable scatter (multi-segment) RX.
189 * ``--enable-hw-vlan``
191 Enable hardware VLAN.
193 * ``--enable-hw-vlan-filter``
195 Enable hardware VLAN filter.
197 * ``--enable-hw-vlan-strip``
199 Enable hardware VLAN strip.
201 * ``--enable-hw-vlan-extend``
203 Enable hardware VLAN extend.
205 * ``--enable-hw-qinq-strip``
207 Enable hardware QINQ strip.
209 * ``--enable-drop-en``
211 Enable per-queue packet drop for packets with no descriptors.
215 Disable RSS (Receive Side Scaling).
217 * ``--port-topology=mode``
219 Set port topology, where mode is ``paired`` (the default), ``chained`` or ``loop``.
221 In ``paired`` mode, the forwarding is between pairs of ports, for example: (0,1), (2,3), (4,5).
223 In ``chained`` mode, the forwarding is to the next available port in the port mask, for example: (0,1), (1,2), (2,0).
225 The ordering of the ports can be changed using the portlist testpmd runtime function.
227 In ``loop`` mode, ingress traffic is simply transmitted back on the same interface.
229 * ``--forward-mode=mode``
231 Set the forwarding mode where ``mode`` is one of the following::
247 Set RSS functions for IPv4/IPv6 only.
251 Set RSS functions for IPv4/IPv6 and UDP.
255 Set the number of RX queues per port to N, where 1 <= N <= 65535.
256 The default value is 1.
260 Set the number of descriptors in the RX rings to N, where N > 0.
261 The default value is 128.
265 Set the number of TX queues per port to N, where 1 <= N <= 65535.
266 The default value is 1.
270 Set the number of descriptors in the TX rings to N, where N > 0.
271 The default value is 512.
275 Set the number of hairpin queues per port to N, where 1 <= N <= 65535.
276 The default value is 0. The number of hairpin queues are added to the
277 number of TX queues and to the number of RX queues. then the first
278 RX hairpin is binded to the first TX hairpin, the second RX hairpin is
279 binded to the second TX hairpin and so on. The index of the first
280 RX hairpin queue is the number of RX queues as configured using --rxq.
281 The index of the first TX hairpin queue is the number of TX queues
282 as configured using --txq.
286 Set the number of packets per burst to N, where 1 <= N <= 512.
287 The default value is 32.
288 If set to 0, driver default is used if defined. Else, if driver
289 default is not defined, default of 32 is used.
293 Set the cache of mbuf memory pools to N, where 0 <= N <= 512.
294 The default value is 16.
298 Set the prefetch threshold register of RX rings to N, where N >= 0.
299 The default value is 8.
303 Set the host threshold register of RX rings to N, where N >= 0.
304 The default value is 8.
308 Set the free threshold of RX descriptors to N, where 0 <= N < value of --rxd.
309 The default value is 0.
313 Set the write-back threshold register of RX rings to N, where N >= 0.
314 The default value is 4.
318 Set the prefetch threshold register of TX rings to N, where N >= 0.
319 The default value is 36.
323 Set the host threshold register of TX rings to N, where N >= 0.
324 The default value is 0.
328 Set the write-back threshold register of TX rings to N, where N >= 0.
329 The default value is 0.
333 Set the transmit free threshold of TX rings to N, where 0 <= N <= value of ``--txd``.
334 The default value is 0.
338 Set the transmit RS bit threshold of TX rings to N, where 0 <= N <= value of ``--txd``.
339 The default value is 0.
341 * ``--rx-queue-stats-mapping=(port,queue,mapping)[,(port,queue,mapping)]``
343 Set the RX queues statistics counters mapping 0 <= mapping <= 15.
345 * ``--tx-queue-stats-mapping=(port,queue,mapping)[,(port,queue,mapping)]``
347 Set the TX queues statistics counters mapping 0 <= mapping <= 15.
351 Don't flush the RX streams before starting forwarding. Used mainly with the PCAP PMD.
355 Set TX segment sizes or total packet length. Valid for ``tx-only``
356 and ``flowgen`` forwarding modes.
358 * ``--txonly-multi-flow``
360 Generate multiple flows in txonly mode.
362 * ``--disable-link-check``
364 Disable check on link status when starting/stopping ports.
366 * ``--disable-device-start``
368 Do not automatically start all ports. This allows testing
369 configuration of rx and tx queues before device is started
372 * ``--no-lsc-interrupt``
374 Disable LSC interrupts for all ports, even those supporting it.
376 * ``--no-rmv-interrupt``
378 Disable RMV interrupts for all ports, even those supporting it.
380 * ``--bitrate-stats=N``
382 Set the logical core N to perform bitrate calculation.
384 * ``--print-event <unknown|intr_lsc|queue_state|intr_reset|vf_mbox|macsec|intr_rmv|dev_probed|dev_released|all>``
386 Enable printing the occurrence of the designated event. Using all will
389 * ``--mask-event <unknown|intr_lsc|queue_state|intr_reset|vf_mbox|macsec|intr_rmv|dev_probed|dev_released|all>``
391 Disable printing the occurrence of the designated event. Using all will
394 * ``--flow-isolate-all``
396 Providing this parameter requests flow API isolated mode on all ports at
397 initialization time. It ensures all traffic is received through the
398 configured flow rules only (see flow command).
400 Ports that do not support this mode are automatically discarded.
402 * ``--tx-offloads=0xXXXXXXXX``
404 Set the hexadecimal bitmask of TX queue offloads.
405 The default value is 0.
407 * ``--rx-offloads=0xXXXXXXXX``
409 Set the hexadecimal bitmask of RX queue offloads.
410 The default value is 0.
414 Enable device event monitor mechanism for hotplug.
416 * ``--vxlan-gpe-port=N``
418 Set the UDP port number of tunnel VXLAN-GPE to N.
419 The default value is 4790.
423 Enable locking all memory.
427 Disable locking all memory.
429 * ``--mp-alloc <native|anon|xmem|xmemhuge>``
431 Select mempool allocation mode:
433 * native: create and populate mempool using native DPDK memory
434 * anon: create mempool using native DPDK memory, but populate using
436 * xmem: create and populate mempool using externally and anonymously
438 * xmemhuge: create and populate mempool using externally and anonymously
439 allocated hugepage area
441 * ``--noisy-tx-sw-buffer-size``
443 Set the number of maximum elements of the FIFO queue to be created
444 for buffering packets. Only available with the noisy forwarding mode.
445 The default value is 0.
447 * ``--noisy-tx-sw-buffer-flushtime=N``
449 Set the time before packets in the FIFO queue is flushed.
450 Only available with the noisy forwarding mode. The default value is 0.
452 * ``--noisy-lkup-memory=N``
454 Set the size of the noisy neighbor simulation memory buffer in MB to N.
455 Only available with the noisy forwarding mode. The default value is 0.
458 * ``--noisy-lkup-num-reads=N``
460 Set the number of reads to be done in noisy neighbor simulation memory buffer to N.
461 Only available with the noisy forwarding mode. The default value is 0.
463 * ``--noisy-lkup-num-writes=N``
465 Set the number of writes to be done in noisy neighbor simulation memory buffer to N.
466 Only available with the noisy forwarding mode. The default value is 0.
468 * ``--noisy-lkup-num-reads-writes=N``
470 Set the number of r/w accesses to be done in noisy neighbor simulation memory buffer to N.
471 Only available with the noisy forwarding mode. The default value is 0.
473 * ``--no-iova-contig``
475 Enable to create mempool which is not IOVA contiguous. Valid only with --mp-alloc=anon.
476 The default value is 0.