1.. BSD LICENSE 2 Copyright(c) 2010-2014 Intel Corporation. All rights reserved. 3 All rights reserved. 4 5 Redistribution and use in source and binary forms, with or without 6 modification, are permitted provided that the following conditions 7 are met: 8 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 14 distribution. 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. 18 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. 30 31Running the Application 32======================= 33 34EAL Command-line Options 35------------------------ 36 37The following are the EAL command-line options that can be used in conjunction with the testpmd, 38or any other DPDK application. 39See the DPDK Getting Started Guides for more information on these options. 40 41* ``-c COREMASK`` 42 43 Set the hexadecimal bitmask of the cores to run on. 44 45* ``-l CORELIST`` 46 47 List of cores to run on 48 49 The argument format is ``<c1>[-c2][,c3[-c4],...]`` 50 where ``c1``, ``c2``, etc are core indexes between 0 and 128. 51 52* ``--lcores COREMAP`` 53 54 Map lcore set to physical cpu set 55 56 The argument format is:: 57 58 <lcores[@cpus]>[<,lcores[@cpus]>...] 59 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. 64 65* ``--master-lcore ID`` 66 67 Core ID that is used as master. 68 69* ``-n NUM`` 70 71 Set the number of memory channels to use. 72 73* ``-b, --pci-blacklist domain:bus:devid.func`` 74 75 Blacklist a PCI devise to prevent EAL from using it. Multiple -b options are allowed. 76 77* ``-d LIB.so`` 78 79 Load an external driver. Multiple -d options are allowed. 80 81* ``-w, --pci-whitelist domain:bus:devid:func`` 82 83 Add a PCI device in white list. 84 85* ``-m MB`` 86 87 Memory to allocate. See also ``--socket-mem``. 88 89* ``-r NUM`` 90 91 Set the number of memory ranks (auto-detected by default). 92 93* ``-v`` 94 95 Display the version information on startup. 96 97* ``--xen-dom0`` 98 99 Support application running on Xen Domain0 without hugetlbfs. 100 101* ``--syslog`` 102 103 Set the syslog facility. 104 105* ``--socket-mem`` 106 107 Set the memory to allocate on specific sockets (use comma separated values). 108 109* ``--huge-dir`` 110 111 Specify the directory where the hugetlbfs is mounted. 112 113* ``--proc-type`` 114 115 Set the type of the current process. 116 117* ``--file-prefix`` 118 119 Prefix for hugepage filenames. 120 121* ``-vmware-tsc-map`` 122 123 Use VMware TSC map instead of native RDTSC. 124 125* ``--vdev`` 126 127 Add a virtual device using the format:: 128 129 <driver><id>[,key=val, ...] 130 131 For example:: 132 133 --vdev 'eth_pcap0,rx_pcap=input.pcap,tx_pcap=output.pcap' 134 135* ``--base-virtaddr`` 136 137 Specify base virtual address. 138 139* ``--create-uio-dev`` 140 141 Create ``/dev/uioX`` (usually done by hotplug). 142 143* ``--no-shconf`` 144 145 No shared config (mmap-ed files). 146 147* ``--no-pci`` 148 149 Disable pci. 150 151* ``--no-hpet`` 152 153 Disable hpet. 154 155* ``--no-huge`` 156 157 Use malloc instead of hugetlbfs. 158 159 160Testpmd Command-line Options 161---------------------------- 162 163The following are the command-line options for the testpmd applications. 164They must be separated from the EAL options, shown in the previous section, with a ``--`` separator: 165 166.. code-block:: console 167 168 sudo ./testpmd -c 0xF -n 4 -- -i --portmask=0x1 --nb-cores=2 169 170The commandline options are: 171 172* ``-i, --interactive`` 173 174 Run testpmd in interactive mode. 175 In this mode, the testpmd starts with a prompt that can be used to start and stop forwarding, 176 configure the application and display stats on the current packet processing session. 177 See :ref:`testpmd_runtime` for more details. 178 179 In non-interactive mode, 180 the application starts with the configuration specified on the command-line and 181 immediately enters forwarding mode. 182 183* ``-h, --help`` 184 185 Display a help message and quit. 186 187* ``-a, --auto-start`` 188 189 Start forwarding on initialization. 190 191* ``--nb-cores=N`` 192 193 Set the number of forwarding cores, 194 where 1 <= N <= "number of cores" or ``CONFIG_RTE_MAX_LCORE`` from the configuration file. 195 The default value is 1. 196 197* ``--nb-ports=N`` 198 199 Set the number of forwarding ports, 200 where 1 <= N <= "number of ports" on the board or ``CONFIG_RTE_MAX_ETHPORTS`` from the configuration file. 201 The default value is the number of ports on the board. 202 203* ``--coremask=0xXX`` 204 205 Set the hexadecimal bitmask of the cores running the packet forwarding test. 206 The master lcore is reserved for command line parsing only and cannot be masked on for packet forwarding. 207 208* ``--portmask=0xXX`` 209 210 Set the hexadecimal bitmask of the ports used by the packet forwarding test. 211 212* ``--numa`` 213 214 Enable NUMA-aware allocation of RX/TX rings and of RX memory buffers (mbufs). 215 216* ``--port-numa-config=(port,socket)[,(port,socket)]`` 217 218 Specify the socket on which the memory pool to be used by the port will be allocated. 219 220* ``--ring-numa-config=(port,flag,socket)[,(port,flag,socket)]`` 221 222 Specify the socket on which the TX/RX rings for the port will be allocated. 223 Where flag is 1 for RX, 2 for TX, and 3 for RX and TX. 224 225* ``--socket-num=N`` 226 227 Set the socket from which all memory is allocated in NUMA mode, 228 where 0 <= N < number of sockets on the board. 229 230* ``--mbuf-size=N`` 231 232 Set the data size of the mbufs used to N bytes, where N < 65536. The default value is 2048. 233 234* ``--total-num-mbufs=N`` 235 236 Set the number of mbufs to be allocated in the mbuf pools, where N > 1024. 237 238* ``--max-pkt-len=N`` 239 240 Set the maximum packet size to N bytes, where N >= 64. The default value is 1518. 241 242* ``--eth-peers-configfile=name`` 243 244 Use a configuration file containing the Ethernet addresses of the peer ports. 245 The configuration file should contain the Ethernet addresses on separate lines:: 246 247 XX:XX:XX:XX:XX:01 248 XX:XX:XX:XX:XX:02 249 ... 250 251 252* ``--eth-peer=N,XX:XX:XX:XX:XX:XX`` 253 254 Set the MAC address ``XX:XX:XX:XX:XX:XX`` of the peer port N, 255 where 0 <= N < ``CONFIG_RTE_MAX_ETHPORTS`` from the configuration file. 256 257* ``--pkt-filter-mode=mode`` 258 259 Set Flow Director mode where mode is either ``none`` (the default), ``signature`` or ``perfect``. 260 See :ref:`testpmd_flow_director` for more details. 261 262* ``--pkt-filter-report-hash=mode`` 263 264 Set Flow Director hash match reporting mode where mode is ``none``, ``match`` (the default) or ``always``. 265 266* ``--pkt-filter-size=N`` 267 268 Set Flow Director allocated memory size, where N is 64K, 128K or 256K. 269 Sizes are in kilobytes. The default is 64. 270 271* ``--pkt-filter-flexbytes-offset=N`` 272 273 Set the flexbytes offset. 274 The offset is defined in words (not bytes) counted from the first byte of the destination Ethernet MAC address, 275 where N is 0 <= N <= 32. 276 The default value is 0x6. 277 278* ``--pkt-filter-drop-queue=N`` 279 280 Set the drop-queue. 281 In perfect filter mode, when a rule is added with queue = -1, the packet will be enqueued into the RX drop-queue. 282 If the drop-queue does not exist, the packet is dropped. The default value is N=127. 283 284* ``--crc-strip`` 285 286 Enable hardware CRC stripping. 287 288* ``--enable-rx-cksum`` 289 290 Enable hardware RX checksum offload. 291 292* ``--enable-scatter`` 293 294 Enable scatter (multi-segment) RX. 295 296* ``--disable-hw-vlan`` 297 298 Disable hardware VLAN. 299 300* ``--disable-hw-vlan-filter`` 301 302 Disable hardware VLAN filter. 303 304* ``--disable-hw-vlan-strip`` 305 306 Disable hardware VLAN strip. 307 308* ``--disable-hw-vlan-extend`` 309 310 Disable hardware VLAN extend. 311 312* ``--enable-drop-en`` 313 314 Enable per-queue packet drop for packets with no descriptors. 315 316* ``--disable-rss`` 317 318 Disable RSS (Receive Side Scaling). 319 320* ``--port-topology=mode`` 321 322 Set port topology, where mode is ``paired`` (the default) or ``chained``. 323 324 In ``paired`` mode, the forwarding is between pairs of ports, for example: (0,1), (2,3), (4,5). 325 326 In ``chained`` mode, the forwarding is to the next available port in the port mask, for example: (0,1), (1,2), (2,0). 327 328 The ordering of the ports can be changed using the portlist testpmd runtime function. 329 330* ``--forward-mode=mode`` 331 332 Set the forwarding mode where ``mode`` is one of the following:: 333 334 io (the default) 335 mac 336 mac_retry 337 mac_swap 338 flowgen 339 rxonly 340 txonly 341 csum 342 icmpecho 343 ieee1588 344 345* ``--rss-ip`` 346 347 Set RSS functions for IPv4/IPv6 only. 348 349* ``--rss-udp`` 350 351 Set RSS functions for IPv4/IPv6 and UDP. 352 353* ``--rxq=N`` 354 355 Set the number of RX queues per port to N, where 1 <= N <= 65535. 356 The default value is 1. 357 358* ``--rxd=N`` 359 360 Set the number of descriptors in the RX rings to N, where N > 0. 361 The default value is 128. 362 363* ``--txq=N`` 364 365 Set the number of TX queues per port to N, where 1 <= N <= 65535. 366 The default value is 1. 367 368* ``--txd=N`` 369 370 Set the number of descriptors in the TX rings to N, where N > 0. 371 The default value is 512. 372 373* ``--burst=N`` 374 375 Set the number of packets per burst to N, where 1 <= N <= 512. 376 The default value is 16. 377 378* ``--mbcache=N`` 379 380 Set the cache of mbuf memory pools to N, where 0 <= N <= 512. 381 The default value is 16. 382 383* ``--rxpt=N`` 384 385 Set the prefetch threshold register of RX rings to N, where N >= 0. 386 The default value is 8. 387 388* ``--rxht=N`` 389 390 Set the host threshold register of RX rings to N, where N >= 0. 391 The default value is 8. 392 393* ``--rxfreet=N`` 394 395 Set the free threshold of RX descriptors to N, where 0 <= N < value of --rxd. 396 The default value is 0. 397 398* ``--rxwt=N`` 399 400 Set the write-back threshold register of RX rings to N, where N >= 0. 401 The default value is 4. 402 403* ``--txpt=N`` 404 405 Set the prefetch threshold register of TX rings to N, where N >= 0. 406 The default value is 36. 407 408* ``--txht=N`` 409 410 Set the host threshold register of TX rings to N, where N >= 0. 411 The default value is 0. 412 413* ``--txwt=N`` 414 415 Set the write-back threshold register of TX rings to N, where N >= 0. 416 The default value is 0. 417 418* ``--txfreet=N`` 419 420 Set the transmit free threshold of TX rings to N, where 0 <= N <= value of ``--txd``. 421 The default value is 0. 422 423* ``--txrst=N`` 424 425 Set the transmit RS bit threshold of TX rings to N, where 0 <= N <= value of ``--txd``. 426 The default value is 0. 427 428* ``--txqflags=0xXXXXXXXX`` 429 430 Set the hexadecimal bitmask of TX queue flags, where 0 <= N <= 0x7FFFFFFF. 431 The default value is 0. 432 433 .. note:: 434 435 When using hardware offload functions such as vlan or checksum 436 add ``txqflags=0`` to force the full-featured TX code path. 437 In some PMDs this may already be the default. 438 439 440* ``--rx-queue-stats-mapping=(port,queue,mapping)[,(port,queue,mapping)]`` 441 442 Set the RX queues statistics counters mapping 0 <= mapping <= 15. 443 444* ``--tx-queue-stats-mapping=(port,queue,mapping)[,(port,queue,mapping)]`` 445 446 Set the TX queues statistics counters mapping 0 <= mapping <= 15. 447 448* ``--no-flush-rx`` 449 450 Don't flush the RX streams before starting forwarding. Used mainly with the PCAP PMD. 451 452* ``--txpkts=X[,Y]`` 453 454 Set TX segment sizes. 455 456* ``--disable-link-check`` 457 458 Disable check on link status when starting/stopping ports. 459