1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright(c) 2016 Intel Corporation.
7 The i40e PMD (librte_pmd_i40e) provides poll mode driver support for
8 10/25/40 Gbps Intel® Ethernet 700 Series Network Adapters based on
9 the Intel Ethernet Controller X710/XL710/XXV710 and Intel Ethernet
10 Connection X722 (only support part of features).
16 Features of the i40e PMD are:
18 - Multiple queues for TX and RX
19 - Receiver Side Scaling (RSS)
21 - Packet type information
25 - VLAN/QinQ stripping and inserting
29 - Port hardware statistics
31 - Link state information
33 - Mirror on port, VLAN and VSI
34 - Interrupt mode for RX
35 - Scattered and gather for TX and RX
36 - Vector Poll mode driver
41 - IEEE1588/802.1AS timestamping
42 - VF Daemon (VFD) - EXPERIMENTAL
43 - Dynamic Device Personalization (DDP)
44 - Queue region configuration
45 - Virtual Function Port Representors
50 - Identifying your adapter using `Intel Support
51 <http://www.intel.com/support>`_ and get the latest NVM/FW images.
53 - Follow the DPDK :ref:`Getting Started Guide for Linux <linux_gsg>` to setup the basic DPDK environment.
55 - To get better performance on Intel platforms, please follow the "How to get best performance with NICs on Intel platforms"
56 section of the :ref:`Getting Started Guide for Linux <linux_gsg>`.
58 - Upgrade the NVM/FW version following the `Intel® Ethernet NVM Update Tool Quick Usage Guide for Linux
59 <https://www-ssl.intel.com/content/www/us/en/embedded/products/networking/nvm-update-tool-quick-linux-usage-guide.html>`_ and `Intel® Ethernet NVM Update Tool: Quick Usage Guide for EFI <https://www.intel.com/content/www/us/en/embedded/products/networking/nvm-update-tool-quick-efi-usage-guide.html>`_ if needed.
61 Recommended Matching List
62 -------------------------
64 It is highly recommended to upgrade the i40e kernel driver and firmware to
65 avoid the compatibility issues with i40e PMD. Here is the suggested matching
66 list which has been tested and verified. The detailed information can refer
67 to chapter Tested Platforms/Tested NICs in release notes.
69 +--------------+-----------------------+------------------+
70 | DPDK version | Kernel driver version | Firmware version |
71 +==============+=======================+==================+
72 | 18.05 | 2.4.6 | 6.01 |
73 +--------------+-----------------------+------------------+
74 | 18.02 | 2.4.3 | 6.01 |
75 +--------------+-----------------------+------------------+
76 | 17.11 | 2.1.26 | 6.01 |
77 +--------------+-----------------------+------------------+
78 | 17.08 | 2.0.19 | 6.01 |
79 +--------------+-----------------------+------------------+
80 | 17.05 | 1.5.23 | 5.05 |
81 +--------------+-----------------------+------------------+
82 | 17.02 | 1.5.23 | 5.05 |
83 +--------------+-----------------------+------------------+
84 | 16.11 | 1.5.23 | 5.05 |
85 +--------------+-----------------------+------------------+
86 | 16.07 | 1.4.25 | 5.04 |
87 +--------------+-----------------------+------------------+
88 | 16.04 | 1.4.25 | 5.02 |
89 +--------------+-----------------------+------------------+
91 Pre-Installation Configuration
92 ------------------------------
97 The following options can be modified in the ``config`` file.
98 Please note that enabling debugging options may affect system performance.
100 - ``CONFIG_RTE_LIBRTE_I40E_PMD`` (default ``y``)
102 Toggle compilation of the ``librte_pmd_i40e`` driver.
104 - ``CONFIG_RTE_LIBRTE_I40E_DEBUG_*`` (default ``n``)
106 Toggle display of generic debugging messages.
108 - ``CONFIG_RTE_LIBRTE_I40E_RX_ALLOW_BULK_ALLOC`` (default ``y``)
110 Toggle bulk allocation for RX.
112 - ``CONFIG_RTE_LIBRTE_I40E_INC_VECTOR`` (default ``n``)
114 Toggle the use of Vector PMD instead of normal RX/TX path.
115 To enable vPMD for RX, bulk allocation for Rx must be allowed.
117 - ``CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC`` (default ``n``)
119 Toggle to use a 16-byte RX descriptor, by default the RX descriptor is 32 byte.
121 - ``CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_PF`` (default ``64``)
123 Number of queues reserved for PF.
125 - ``CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_VM`` (default ``4``)
127 Number of queues reserved for each VMDQ Pool.
129 Runtime Config Options
130 ~~~~~~~~~~~~~~~~~~~~~~
132 - ``Number of Queues per VF`` (default ``4``)
134 The number of queue per VF is determined by its host PF. If the PCI address
135 of an i40e PF is aaaa:bb.cc, the number of queues per VF can be configured
136 with EAL parameter like -w aaaa:bb.cc,queue-num-per-vf=n. The value n can be
137 1, 2, 4, 8 or 16. If no such parameter is configured, the number of queues
138 per VF is 4 by default.
140 - ``Support multiple driver`` (default ``disable``)
142 There was a multiple driver support issue during use of 700 series Ethernet
143 Adapter with both Linux kernel and DPDK PMD. To fix this issue, ``devargs``
144 parameter ``support-multi-driver`` is introduced, for example::
146 -w 84:00.0,support-multi-driver=1
148 With the above configuration, DPDK PMD will not change global registers, and
149 will switch PF interrupt from IntN to Int0 to avoid interrupt conflict between
150 DPDK and Linux Kernel.
152 - ``Support VF Port Representor`` (default ``not enabled``)
154 The i40e PF PMD supports the creation of VF port representors for the control
155 and monitoring of i40e virtual function devices. Each port representor
156 corresponds to a single virtual function of that device. Using the ``devargs``
157 option ``representor`` the user can specify which virtual functions to create
158 port representors for on initialization of the PF PMD by passing the VF IDs of
159 the VFs which are required.::
161 -w DBDF,representor=[0,1,4]
163 Currently hot-plugging of representor ports is not supported so all required
164 representors must be specified on the creation of the PF.
166 Driver compilation and testing
167 ------------------------------
169 Refer to the document :ref:`compiling and testing a PMD for a NIC <pmd_build_and_test>`
173 SR-IOV: Prerequisites and sample Application Notes
174 --------------------------------------------------
176 #. Load the kernel module:
178 .. code-block:: console
182 Check the output in dmesg:
184 .. code-block:: console
186 i40e 0000:83:00.1 ens802f0: renamed from eth0
188 #. Bring up the PF ports:
190 .. code-block:: console
194 #. Create VF device(s):
196 Echo the number of VFs to be created into the ``sriov_numvfs`` sysfs entry
201 .. code-block:: console
203 echo 2 > /sys/devices/pci0000:00/0000:00:03.0/0000:81:00.0/sriov_numvfs
206 #. Assign VF MAC address:
208 Assign MAC address to the VF using iproute2 utility. The syntax is:
210 .. code-block:: console
212 ip link set <PF netdev id> vf <VF id> mac <macaddr>
216 .. code-block:: console
218 ip link set ens802f0 vf 0 mac a0:b0:c0:d0:e0:f0
220 #. Assign VF to VM, and bring up the VM.
221 Please see the documentation for the *I40E/IXGBE/IGB Virtual Function Driver*.
225 Follow instructions available in the document
226 :ref:`compiling and testing a PMD for a NIC <pmd_build_and_test>`
231 .. code-block:: console
234 EAL: PCI device 0000:83:00.0 on NUMA socket 1
235 EAL: probe driver: 8086:1572 rte_i40e_pmd
236 EAL: PCI memory mapped at 0x7f7f80000000
237 EAL: PCI memory mapped at 0x7f7f80800000
238 PMD: eth_i40e_dev_init(): FW 5.0 API 1.5 NVM 05.00.02 eetrack 8000208a
239 Interactive-mode selected
240 Configuring Port 0 (socket 0)
243 PMD: i40e_dev_rx_queue_setup(): Rx Burst Bulk Alloc Preconditions are
244 satisfied.Rx Burst Bulk Alloc function will be used on port=0, queue=0.
247 Port 0: 68:05:CA:26:85:84
248 Checking link statuses...
249 Port 0 Link Up - speed 10000 Mbps - full-duplex
255 Sample Application Notes
256 ------------------------
261 Vlan filter only works when Promiscuous mode is off.
263 To start ``testpmd``, and add vlan 10 to port 0:
265 .. code-block:: console
267 ./app/testpmd -l 0-15 -n 4 -- -i --forward-mode=mac
270 testpmd> set promisc 0 off
271 testpmd> rx_vlan add 10 0
277 The Flow Director works in receive mode to identify specific flows or sets of flows and route them to specific queues.
278 The Flow Director filters can match the different fields for different type of packet: flow type, specific input set per flow type and the flexible payload.
280 The default input set of each flow type is::
282 ipv4-other : src_ip_address, dst_ip_address
283 ipv4-frag : src_ip_address, dst_ip_address
284 ipv4-tcp : src_ip_address, dst_ip_address, src_port, dst_port
285 ipv4-udp : src_ip_address, dst_ip_address, src_port, dst_port
286 ipv4-sctp : src_ip_address, dst_ip_address, src_port, dst_port,
288 ipv6-other : src_ip_address, dst_ip_address
289 ipv6-frag : src_ip_address, dst_ip_address
290 ipv6-tcp : src_ip_address, dst_ip_address, src_port, dst_port
291 ipv6-udp : src_ip_address, dst_ip_address, src_port, dst_port
292 ipv6-sctp : src_ip_address, dst_ip_address, src_port, dst_port,
294 l2_payload : ether_type
296 The flex payload is selected from offset 0 to 15 of packet's payload by default, while it is masked out from matching.
298 Start ``testpmd`` with ``--disable-rss`` and ``--pkt-filter-mode=perfect``:
300 .. code-block:: console
302 ./app/testpmd -l 0-15 -n 4 -- -i --disable-rss --pkt-filter-mode=perfect \
303 --rxq=8 --txq=8 --nb-cores=8 --nb-ports=1
305 Add a rule to direct ``ipv4-udp`` packet whose ``dst_ip=2.2.2.5, src_ip=2.2.2.3, src_port=32, dst_port=32`` to queue 1:
307 .. code-block:: console
309 testpmd> flow_director_filter 0 mode IP add flow ipv4-udp \
310 src 2.2.2.3 32 dst 2.2.2.5 32 vlan 0 flexbytes () \
311 fwd pf queue 1 fd_id 1
313 Check the flow director status:
315 .. code-block:: console
317 testpmd> show port fdir 0
319 ######################## FDIR infos for port 0 ####################
321 SUPPORTED FLOW TYPE: ipv4-frag ipv4-tcp ipv4-udp ipv4-sctp ipv4-other
322 ipv6-frag ipv6-tcp ipv6-udp ipv6-sctp ipv6-other
325 max_len: 16 payload_limit: 480
326 payload_unit: 2 payload_seg: 3
327 bitmask_unit: 2 bitmask_num: 2
330 src_ipv4: 0x00000000,
331 dst_ipv4: 0x00000000,
334 src_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000,
335 dst_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000
336 FLEX PAYLOAD SRC OFFSET:
337 L2_PAYLOAD: 0 1 2 3 4 5 6 ...
338 L3_PAYLOAD: 0 1 2 3 4 5 6 ...
339 L4_PAYLOAD: 0 1 2 3 4 5 6 ...
341 ipv4-udp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
342 ipv4-tcp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
343 ipv4-sctp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
344 ipv4-other: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
345 ipv4-frag: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
346 ipv6-udp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
347 ipv6-tcp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
348 ipv6-sctp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
349 ipv6-other: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
350 ipv6-frag: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
351 l2_payload: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
352 guarant_count: 1 best_count: 0
353 guarant_space: 512 best_space: 7168
360 Delete all flow director rules on a port:
362 .. code-block:: console
364 testpmd> flush_flow_director 0
369 The Intel® Ethernet 700 Series support a feature called
372 A Virtual Ethernet Bridge (VEB) is an IEEE Edge Virtual Bridging (EVB) term
373 for functionality that allows local switching between virtual endpoints within
374 a physical endpoint and also with an external bridge/network.
376 A "Floating" VEB doesn't have an uplink connection to the outside world so all
377 switching is done internally and remains within the host. As such, this
378 feature provides security benefits.
380 In addition, a Floating VEB overcomes a limitation of normal VEBs where they
381 cannot forward packets when the physical link is down. Floating VEBs don't need
382 to connect to the NIC port so they can still forward traffic from VF to VF
383 even when the physical link is down.
385 Therefore, with this feature enabled VFs can be limited to communicating with
386 each other but not an outside network, and they can do so even when there is
387 no physical uplink on the associated NIC port.
389 To enable this feature, the user should pass a ``devargs`` parameter to the
392 -w 84:00.0,enable_floating_veb=1
394 In this configuration the PMD will use the floating VEB feature for all the
395 VFs created by this PF device.
397 Alternatively, the user can specify which VFs need to connect to this floating
398 VEB using the ``floating_veb_list`` argument::
400 -w 84:00.0,enable_floating_veb=1,floating_veb_list=1;3-4
402 In this example ``VF1``, ``VF3`` and ``VF4`` connect to the floating VEB,
403 while other VFs connect to the normal VEB.
405 The current implementation only supports one floating VEB and one regular
406 VEB. VFs can connect to a floating VEB or a regular VEB according to the
407 configuration passed on the EAL command line.
409 The floating VEB functionality requires a NIC firmware version of 5.0
412 Dynamic Device Personalization (DDP)
413 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
415 The Intel® Ethernet 700 Series except for the Intel Ethernet Connection
416 X722 support a feature called "Dynamic Device Personalization (DDP)",
417 which is used to configure hardware by downloading a profile to support
418 protocols/filters which are not supported by default. The DDP
419 functionality requires a NIC firmware version of 6.0 or greater.
421 Current implementation supports GTP-C/GTP-U/PPPoE/PPPoL2TP,
422 steering can be used with rte_flow API.
424 GTPv1 package is released, and it can be downloaded from
425 https://downloadcenter.intel.com/download/27587.
427 Load a profile which supports GTP and store backup profile:
429 .. code-block:: console
431 testpmd> ddp add 0 ./gtp.pkgo,./backup.pkgo
433 Delete a GTP profile and restore backup profile:
435 .. code-block:: console
437 testpmd> ddp del 0 ./backup.pkgo
439 Get loaded DDP package info list:
441 .. code-block:: console
443 testpmd> ddp get list 0
445 Display information about a GTP profile:
447 .. code-block:: console
449 testpmd> ddp get info ./gtp.pkgo
451 Input set configuration
452 ~~~~~~~~~~~~~~~~~~~~~~~
453 Input set for any PCTYPE can be configured with user defined configuration,
454 For example, to use only 48bit prefix for IPv6 src address for IPv6 TCP RSS:
456 .. code-block:: console
458 testpmd> port config 0 pctype 43 hash_inset clear all
459 testpmd> port config 0 pctype 43 hash_inset set field 13
460 testpmd> port config 0 pctype 43 hash_inset set field 14
461 testpmd> port config 0 pctype 43 hash_inset set field 15
463 Queue region configuration
464 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
465 The Intel® Ethernet 700 Series supports a feature of queue regions
466 configuration for RSS in the PF, so that different traffic classes or
467 different packet classification types can be separated to different
468 queues in different queue regions. There is an API for configuration
469 of queue regions in RSS with a command line. It can parse the parameters
470 of the region index, queue number, queue start index, user priority, traffic
471 classes and so on. Depending on commands from the command line, it will call
472 i40e private APIs and start the process of setting or flushing the queue
473 region configuration. As this feature is specific for i40e only private
474 APIs are used. These new ``test_pmd`` commands are as shown below. For
475 details please refer to :doc:`../testpmd_app_ug/index`.
477 .. code-block:: console
479 testpmd> set port (port_id) queue-region region_id (value) \
480 queue_start_index (value) queue_num (value)
481 testpmd> set port (port_id) queue-region region_id (value) flowtype (value)
482 testpmd> set port (port_id) queue-region UP (value) region_id (value)
483 testpmd> set port (port_id) queue-region flush (on|off)
484 testpmd> show port (port_id) queue-region
486 Limitations or Known issues
487 ---------------------------
489 MPLS packet classification
490 ~~~~~~~~~~~~~~~~~~~~~~~~~~
492 For firmware versions prior to 5.0, MPLS packets are not recognized by the NIC.
493 The L2 Payload flow type in flow director can be used to classify MPLS packet
494 by using a command in testpmd like:
496 testpmd> flow_director_filter 0 mode IP add flow l2_payload ether \
497 0x8847 flexbytes () fwd pf queue <N> fd_id <M>
499 With the NIC firmware version 5.0 or greater, some limited MPLS support
500 is added: Native MPLS (MPLS in Ethernet) skip is implemented, while no
501 new packet type, no classification or offload are possible. With this change,
502 L2 Payload flow type in flow director cannot be used to classify MPLS packet
503 as with previous firmware versions. Meanwhile, the Ethertype filter can be
504 used to classify MPLS packet by using a command in testpmd like:
506 testpmd> ethertype_filter 0 add mac_ignr 00:00:00:00:00:00 ethertype \
509 16 Byte RX Descriptor setting on DPDK VF
510 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
512 Currently the VF's RX descriptor mode is decided by PF. There's no PF-VF
513 interface for VF to request the RX descriptor mode, also no interface to notify
514 VF its own RX descriptor mode.
515 For all available versions of the i40e driver, these drivers don't support 16
516 byte RX descriptor. If the Linux i40e kernel driver is used as host driver,
517 while DPDK i40e PMD is used as the VF driver, DPDK cannot choose 16 byte receive
518 descriptor. The reason is that the RX descriptor is already set to 32 byte by
519 the i40e kernel driver. That is to say, user should keep
520 ``CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC=n`` in config file.
521 In the future, if the Linux i40e driver supports 16 byte RX descriptor, user
522 should make sure the DPDK VF uses the same RX descriptor mode, 16 byte or 32
523 byte, as the PF driver.
525 The same rule for DPDK PF + DPDK VF. The PF and VF should use the same RX
526 descriptor mode. Or the VF RX will not work.
528 Receive packets with Ethertype 0x88A8
529 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
531 Due to the FW limitation, PF can receive packets with Ethertype 0x88A8
532 only when floating VEB is disabled.
534 Incorrect Rx statistics when packet is oversize
535 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
537 When a packet is over maximum frame size, the packet is dropped.
538 However, the Rx statistics, when calling `rte_eth_stats_get` incorrectly
539 shows it as received.
541 VF & TC max bandwidth setting
542 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
544 The per VF max bandwidth and per TC max bandwidth cannot be enabled in parallel.
545 The behavior is different when handling per VF and per TC max bandwidth setting.
546 When enabling per VF max bandwidth, SW will check if per TC max bandwidth is
547 enabled. If so, return failure.
548 When enabling per TC max bandwidth, SW will check if per VF max bandwidth
549 is enabled. If so, disable per VF max bandwidth and continue with per TC max
552 TC TX scheduling mode setting
553 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
555 There're 2 TX scheduling modes for TCs, round robin and strict priority mode.
556 If a TC is set to strict priority mode, it can consume unlimited bandwidth.
557 It means if APP has set the max bandwidth for that TC, it comes to no
559 It's suggested to set the strict priority mode for a TC that is latency
560 sensitive but no consuming much bandwidth.
562 VF performance is impacted by PCI extended tag setting
563 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
565 To reach maximum NIC performance in the VF the PCI extended tag must be
566 enabled. The DPDK i40e PF driver will set this feature during initialization,
567 but the kernel PF driver does not. So when running traffic on a VF which is
568 managed by the kernel PF driver, a significant NIC performance downgrade has
569 been observed (for 64 byte packets, there is about 25% line-rate downgrade for
570 a 25GbE device and about 35% for a 40GbE device).
572 For kernel version >= 4.11, the kernel's PCI driver will enable the extended
573 tag if it detects that the device supports it. So by default, this is not an
574 issue. For kernels <= 4.11 or when the PCI extended tag is disabled it can be
575 enabled using the steps below.
577 #. Get the current value of the PCI configure register::
579 setpci -s <XX:XX.X> a8.w
583 value = value | 0x100
585 #. Set the PCI configure register with new value::
587 setpci -s <XX:XX.X> a8.w=<value>
592 The VF vlan strip function is only supported in the i40e kernel driver >= 2.1.26.
597 DCB works only when RSS is enabled.
599 Global configuration warning
600 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
602 I40E PMD will set some global registers to enable some function or set some
603 configure. Then when using different ports of the same NIC with Linux kernel
604 and DPDK, the port with Linux kernel will be impacted by the port with DPDK.
605 For example, register I40E_GL_SWT_L2TAGCTRL is used to control L2 tag, i40e
606 PMD uses I40E_GL_SWT_L2TAGCTRL to set vlan TPID. If setting TPID in port A
607 with DPDK, then the configuration will also impact port B in the NIC with
608 kernel driver, which don't want to use the TPID.
609 So PMD reports warning to clarify what is changed by writing global register.
611 High Performance of Small Packets on 40GbE NIC
612 ----------------------------------------------
614 As there might be firmware fixes for performance enhancement in latest version
615 of firmware image, the firmware update might be needed for getting high performance.
616 Check the Intel support website for the latest firmware updates.
617 Users should consult the release notes specific to a DPDK release to identify
618 the validated firmware version for a NIC using the i40e driver.
620 Use 16 Bytes RX Descriptor Size
621 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
623 As i40e PMD supports both 16 and 32 bytes RX descriptor sizes, and 16 bytes size can provide helps to high performance of small packets.
624 Configuration of ``CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC`` in config files can be changed to use 16 bytes size RX descriptors.
626 Example of getting best performance with l3fwd example
627 ------------------------------------------------------
629 The following is an example of running the DPDK ``l3fwd`` sample application to get high performance with a
630 server with Intel Xeon processors and Intel Ethernet CNA XL710.
632 The example scenario is to get best performance with two Intel Ethernet CNA XL710 40GbE ports.
633 See :numref:`figure_intel_perf_test_setup` for the performance test setup.
635 .. _figure_intel_perf_test_setup:
637 .. figure:: img/intel_perf_test_setup.*
639 Performance Test Setup
642 1. Add two Intel Ethernet CNA XL710 to the platform, and use one port per card to get best performance.
643 The reason for using two NICs is to overcome a PCIe v3.0 limitation since it cannot provide 80GbE bandwidth
644 for two 40GbE ports, but two different PCIe v3.0 x8 slot can.
645 Refer to the sample NICs output above, then we can select ``82:00.0`` and ``85:00.0`` as test ports::
647 82:00.0 Ethernet [0200]: Intel XL710 for 40GbE QSFP+ [8086:1583]
648 85:00.0 Ethernet [0200]: Intel XL710 for 40GbE QSFP+ [8086:1583]
650 2. Connect the ports to the traffic generator. For high speed testing, it's best to use a hardware traffic generator.
652 3. Check the PCI devices numa node (socket id) and get the cores number on the exact socket id.
653 In this case, ``82:00.0`` and ``85:00.0`` are both in socket 1, and the cores on socket 1 in the referenced platform
655 Note: Don't use 2 logical cores on the same core (e.g core18 has 2 logical cores, core18 and core54), instead, use 2 logical
656 cores from different cores (e.g core18 and core19).
658 4. Bind these two ports to igb_uio.
660 5. As to Intel Ethernet CNA XL710 40GbE port, we need at least two queue pairs to achieve best performance, then two queues per port
661 will be required, and each queue pair will need a dedicated CPU core for receiving/transmitting packets.
663 6. The DPDK sample application ``l3fwd`` will be used for performance testing, with using two ports for bi-directional forwarding.
664 Compile the ``l3fwd sample`` with the default lpm mode.
666 7. The command line of running l3fwd would be something like the following::
668 ./l3fwd -l 18-21 -n 4 -w 82:00.0 -w 85:00.0 \
669 -- -p 0x3 --config '(0,0,18),(0,1,19),(1,0,20),(1,1,21)'
671 This means that the application uses core 18 for port 0, queue pair 0 forwarding, core 19 for port 0, queue pair 1 forwarding,
672 core 20 for port 1, queue pair 0 forwarding, and core 21 for port 1, queue pair 1 forwarding.
674 8. Configure the traffic at a traffic generator.
676 * Start creating a stream on packet generator.
678 * Set the Ethernet II type to 0x0800.