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 Running the Application
32 =======================
34 EAL Command-line Options
35 ------------------------
37 The following are the EAL command-line options that can be used in conjunction with the testpmd,
38 or any other DPDK application.
39 See the DPDK Getting Started Guides for more information on these options.
43 Set the hexadecimal bitmask of the cores to run on.
47 List of cores to run on
49 The argument format is ``<c1>[-c2][,c3[-c4],...]``
50 where ``c1``, ``c2``, etc are core indexes between 0 and 128.
52 * ``--lcores COREMAP``
54 Map lcore set to physical cpu set
56 The argument format is::
58 <lcores[@cpus]>[<,lcores[@cpus]>...]
60 Lcore and CPU lists are grouped by ``(`` and ``)`` Within the group.
61 The ``-`` character is used as a range separator and ``,`` is used as a single number separator.
62 The grouping ``()`` can be omitted for single element group.
63 The ``@`` can be omitted if cpus and lcores have the same value.
65 * ``--master-lcore ID``
67 Core ID that is used as master.
71 Set the number of memory channels to use.
73 * ``-b, --pci-blacklist domain:bus:devid.func``
75 Blacklist a PCI device to prevent EAL from using it. Multiple -b options are allowed.
79 Load an external driver. Multiple -d options are allowed.
81 * ``-w, --pci-whitelist domain:bus:devid:func``
83 Add a PCI device in white list.
87 Memory to allocate. See also ``--socket-mem``.
91 Set the number of memory ranks (auto-detected by default).
95 Display the version information on startup.
99 Support application running on Xen Domain0 without hugetlbfs.
103 Set the syslog facility.
107 Set the memory to allocate on specific sockets (use comma separated values).
111 Specify the directory where the hugetlbfs is mounted.
113 * ``mbuf-pool-ops-name``:
115 Pool ops name for mbuf to use.
119 Set the type of the current process.
123 Prefix for hugepage filenames.
125 * ``-vmware-tsc-map``
127 Use VMware TSC map instead of native RDTSC.
131 Add a virtual device using the format::
133 <driver><id>[,key=val, ...]
137 --vdev 'net_pcap0,rx_pcap=input.pcap,tx_pcap=output.pcap'
139 * ``--base-virtaddr``
141 Specify base virtual address.
143 * ``--create-uio-dev``
145 Create ``/dev/uioX`` (usually done by hotplug).
149 No shared config (mmap-ed files).
161 Use malloc instead of hugetlbfs.
164 Testpmd Command-line Options
165 ----------------------------
167 The following are the command-line options for the testpmd applications.
168 They must be separated from the EAL options, shown in the previous section, with a ``--`` separator:
170 .. code-block:: console
172 sudo ./testpmd -l 0-3 -n 4 -- -i --portmask=0x1 --nb-cores=2
174 The commandline options are:
176 * ``-i, --interactive``
178 Run testpmd in interactive mode.
179 In this mode, the testpmd starts with a prompt that can be used to start and stop forwarding,
180 configure the application and display stats on the current packet processing session.
181 See :ref:`testpmd_runtime` for more details.
183 In non-interactive mode,
184 the application starts with the configuration specified on the command-line and
185 immediately enters forwarding mode.
189 Display a help message and quit.
191 * ``-a, --auto-start``
193 Start forwarding on initialization.
197 Start forwarding, after sending a burst of packets first.
201 This flag should be only used in non-interactive mode.
203 * ``--stats-period PERIOD``
205 Display statistics every PERIOD seconds, if interactive mode is disabled.
206 The default value is 0, which means that the statistics will not be displayed.
210 Set the number of forwarding cores,
211 where 1 <= N <= "number of cores" or ``CONFIG_RTE_MAX_LCORE`` from the configuration file.
212 The default value is 1.
216 Set the number of forwarding ports,
217 where 1 <= N <= "number of ports" on the board or ``CONFIG_RTE_MAX_ETHPORTS`` from the configuration file.
218 The default value is the number of ports on the board.
220 * ``--coremask=0xXX``
222 Set the hexadecimal bitmask of the cores running the packet forwarding test.
223 The master lcore is reserved for command line parsing only and cannot be masked on for packet forwarding.
225 * ``--portmask=0xXX``
227 Set the hexadecimal bitmask of the ports used by the packet forwarding test.
231 Enable NUMA-aware allocation of RX/TX rings and of RX memory buffers
232 (mbufs). [Default setting]
236 Disable NUMA-aware allocation of RX/TX rings and of RX memory buffers (mbufs).
238 * ``--port-numa-config=(port,socket)[,(port,socket)]``
240 Specify the socket on which the memory pool to be used by the port will be allocated.
242 * ``--ring-numa-config=(port,flag,socket)[,(port,flag,socket)]``
244 Specify the socket on which the TX/RX rings for the port will be allocated.
245 Where flag is 1 for RX, 2 for TX, and 3 for RX and TX.
249 Set the socket from which all memory is allocated in NUMA mode,
250 where 0 <= N < number of sockets on the board.
254 Set the data size of the mbufs used to N bytes, where N < 65536. The default value is 2048.
256 * ``--total-num-mbufs=N``
258 Set the number of mbufs to be allocated in the mbuf pools, where N > 1024.
260 * ``--max-pkt-len=N``
262 Set the maximum packet size to N bytes, where N >= 64. The default value is 1518.
264 * ``--eth-peers-configfile=name``
266 Use a configuration file containing the Ethernet addresses of the peer ports.
267 The configuration file should contain the Ethernet addresses on separate lines::
274 * ``--eth-peer=N,XX:XX:XX:XX:XX:XX``
276 Set the MAC address ``XX:XX:XX:XX:XX:XX`` of the peer port N,
277 where 0 <= N < ``CONFIG_RTE_MAX_ETHPORTS`` from the configuration file.
279 * ``--pkt-filter-mode=mode``
281 Set Flow Director mode where mode is either ``none`` (the default), ``signature`` or ``perfect``.
282 See :ref:`testpmd_flow_director` for more details.
284 * ``--pkt-filter-report-hash=mode``
286 Set Flow Director hash match reporting mode where mode is ``none``, ``match`` (the default) or ``always``.
288 * ``--pkt-filter-size=N``
290 Set Flow Director allocated memory size, where N is 64K, 128K or 256K.
291 Sizes are in kilobytes. The default is 64.
293 * ``--pkt-filter-flexbytes-offset=N``
295 Set the flexbytes offset.
296 The offset is defined in words (not bytes) counted from the first byte of the destination Ethernet MAC address,
297 where N is 0 <= N <= 32.
298 The default value is 0x6.
300 * ``--pkt-filter-drop-queue=N``
303 In perfect filter mode, when a rule is added with queue = -1, the packet will be enqueued into the RX drop-queue.
304 If the drop-queue does not exist, the packet is dropped. The default value is N=127.
306 * ``--disable-crc-strip``
308 Disable hardware CRC stripping.
312 Enable large receive offload.
314 * ``--enable-rx-cksum``
316 Enable hardware RX checksum offload.
318 * ``--enable-scatter``
320 Enable scatter (multi-segment) RX.
322 * ``--disable-hw-vlan``
324 Disable hardware VLAN.
326 * ``--disable-hw-vlan-filter``
328 Disable hardware VLAN filter.
330 * ``--disable-hw-vlan-strip``
332 Disable hardware VLAN strip.
334 * ``--disable-hw-vlan-extend``
336 Disable hardware VLAN extend.
338 * ``--enable-drop-en``
340 Enable per-queue packet drop for packets with no descriptors.
344 Disable RSS (Receive Side Scaling).
346 * ``--port-topology=mode``
348 Set port topology, where mode is ``paired`` (the default) or ``chained``.
350 In ``paired`` mode, the forwarding is between pairs of ports, for example: (0,1), (2,3), (4,5).
352 In ``chained`` mode, the forwarding is to the next available port in the port mask, for example: (0,1), (1,2), (2,0).
354 The ordering of the ports can be changed using the portlist testpmd runtime function.
356 * ``--forward-mode=mode``
358 Set the forwarding mode where ``mode`` is one of the following::
372 Set RSS functions for IPv4/IPv6 only.
376 Set RSS functions for IPv4/IPv6 and UDP.
380 Set the number of RX queues per port to N, where 1 <= N <= 65535.
381 The default value is 1.
385 Set the number of descriptors in the RX rings to N, where N > 0.
386 The default value is 128.
390 Set the number of TX queues per port to N, where 1 <= N <= 65535.
391 The default value is 1.
395 Set the number of descriptors in the TX rings to N, where N > 0.
396 The default value is 512.
400 Set the number of packets per burst to N, where 1 <= N <= 512.
401 The default value is 16.
405 Set the cache of mbuf memory pools to N, where 0 <= N <= 512.
406 The default value is 16.
410 Set the prefetch threshold register of RX rings to N, where N >= 0.
411 The default value is 8.
415 Set the host threshold register of RX rings to N, where N >= 0.
416 The default value is 8.
420 Set the free threshold of RX descriptors to N, where 0 <= N < value of --rxd.
421 The default value is 0.
425 Set the write-back threshold register of RX rings to N, where N >= 0.
426 The default value is 4.
430 Set the prefetch threshold register of TX rings to N, where N >= 0.
431 The default value is 36.
435 Set the host threshold register of TX rings to N, where N >= 0.
436 The default value is 0.
440 Set the write-back threshold register of TX rings to N, where N >= 0.
441 The default value is 0.
445 Set the transmit free threshold of TX rings to N, where 0 <= N <= value of ``--txd``.
446 The default value is 0.
450 Set the transmit RS bit threshold of TX rings to N, where 0 <= N <= value of ``--txd``.
451 The default value is 0.
453 * ``--txqflags=0xXXXXXXXX``
455 Set the hexadecimal bitmask of TX queue flags, where 0 <= N <= 0x7FFFFFFF.
456 The default value is 0.
460 When using hardware offload functions such as vlan or checksum
461 add ``txqflags=0`` to force the full-featured TX code path.
462 In some PMDs this may already be the default.
465 * ``--rx-queue-stats-mapping=(port,queue,mapping)[,(port,queue,mapping)]``
467 Set the RX queues statistics counters mapping 0 <= mapping <= 15.
469 * ``--tx-queue-stats-mapping=(port,queue,mapping)[,(port,queue,mapping)]``
471 Set the TX queues statistics counters mapping 0 <= mapping <= 15.
475 Don't flush the RX streams before starting forwarding. Used mainly with the PCAP PMD.
479 Set TX segment sizes or total packet length. Valid for ``tx-only``
480 and ``flowgen`` forwarding modes.
482 * ``--disable-link-check``
484 Disable check on link status when starting/stopping ports.
486 * ``--no-lsc-interrupt``
488 Disable LSC interrupts for all ports, even those supporting it.
490 * ``--no-rmv-interrupt``
492 Disable RMV interrupts for all ports, even those supporting it.
494 * ``--bitrate-stats=N``
496 Set the logical core N to perform bitrate calculation.
498 * ``--print-event <unknown|intr_lsc|queue_state|intr_reset|vf_mbox|macsec|intr_rmv|all>``
500 Enable printing the occurrence of the designated event. Using all will
503 * ``--mask-event <unknown|intr_lsc|queue_state|intr_reset|vf_mbox|macsec|intr_rmv|all>``
505 Disable printing the occurrence of the designated event. Using all will
508 * ``--flow-isolate-all``
510 Providing this parameter requests flow API isolated mode on all ports at
511 initialization time. It ensures all traffic is received through the
512 configured flow rules only (see flow command).
514 Ports that do not support this mode are automatically discarded.