1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright(c) 2010-2014 Intel Corporation.
4 Intel Virtual Function Driver
5 =============================
7 Supported Intel® Ethernet Controllers (see the *DPDK Release Notes* for details)
8 support the following modes of operation in a virtualized environment:
10 * **SR-IOV mode**: Involves direct assignment of part of the port resources to different guest operating systems
11 using the PCI-SIG Single Root I/O Virtualization (SR IOV) standard,
12 also known as "native mode" or "pass-through" mode.
13 In this chapter, this mode is referred to as IOV mode.
15 * **VMDq mode**: Involves central management of the networking resources by an IO Virtual Machine (IOVM) or
16 a Virtual Machine Monitor (VMM), also known as software switch acceleration mode.
17 In this chapter, this mode is referred to as the Next Generation VMDq mode.
19 SR-IOV Mode Utilization in a DPDK Environment
20 ---------------------------------------------
22 The DPDK uses the SR-IOV feature for hardware-based I/O sharing in IOV mode.
23 Therefore, it is possible to partition SR-IOV capability on Ethernet controller NIC resources logically and
24 expose them to a virtual machine as a separate PCI function called a "Virtual Function".
25 Refer to :numref:`figure_single_port_nic`.
27 Therefore, a NIC is logically distributed among multiple virtual machines (as shown in :numref:`figure_single_port_nic`),
28 while still having global data in common to share with the Physical Function and other Virtual Functions.
29 The DPDK fm10kvf, iavf, igbvf or ixgbevf as a Poll Mode Driver (PMD) serves for the Intel® 82576 Gigabit Ethernet Controller,
30 Intel® Ethernet Controller I350 family, Intel® 82599 10 Gigabit Ethernet Controller NIC,
31 Intel® Fortville 10/40 Gigabit Ethernet Controller NIC's virtual PCI function, or PCIe host-interface of the Intel Ethernet Switch
33 Meanwhile the DPDK Poll Mode Driver (PMD) also supports "Physical Function" of such NIC's on the host.
35 The DPDK PF/VF Poll Mode Driver (PMD) supports the Layer 2 switch on Intel® 82576 Gigabit Ethernet Controller,
36 Intel® Ethernet Controller I350 family, Intel® 82599 10 Gigabit Ethernet Controller,
37 and Intel® Fortville 10/40 Gigabit Ethernet Controller NICs so that guest can choose it for inter virtual machine traffic in SR-IOV mode.
39 For more detail on SR-IOV, please refer to the following documents:
41 * `SR-IOV provides hardware based I/O sharing <http://www.intel.com/network/connectivity/solutions/vmdc.htm>`_
43 * `PCI-SIG-Single Root I/O Virtualization Support on IA
44 <http://www.intel.com/content/www/us/en/pci-express/pci-sig-single-root-io-virtualization-support-in-virtualization-technology-for-connectivity-paper.html>`_
46 * `Scalable I/O Virtualized Servers <http://www.intel.com/content/www/us/en/virtualization/server-virtualization/scalable-i-o-virtualized-servers-paper.html>`_
48 .. _figure_single_port_nic:
50 .. figure:: img/single_port_nic.*
52 Virtualization for a Single Port NIC in SR-IOV Mode
55 Physical and Virtual Function Infrastructure
56 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
58 The following describes the Physical Function and Virtual Functions infrastructure for the supported Ethernet Controller NICs.
60 Virtual Functions operate under the respective Physical Function on the same NIC Port and therefore have no access
61 to the global NIC resources that are shared between other functions for the same NIC port.
63 A Virtual Function has basic access to the queue resources and control structures of the queues assigned to it.
64 For global resource access, a Virtual Function has to send a request to the Physical Function for that port,
65 and the Physical Function operates on the global resources on behalf of the Virtual Function.
66 For this out-of-band communication, an SR-IOV enabled NIC provides a memory buffer for each Virtual Function,
67 which is called a "Mailbox".
69 Intel® Ethernet Adaptive Virtual Function
70 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
71 Adaptive Virtual Function (IAVF) is a SR-IOV Virtual Function with the same device id (8086:1889) on different Intel Ethernet Controller.
72 IAVF Driver is VF driver which supports for all future Intel devices without requiring a VM update. And since this happens to be an adaptive VF driver,
73 every new drop of the VF driver would add more and more advanced features that can be turned on in the VM if the underlying HW device supports those
74 advanced features based on a device agnostic way without ever compromising on the base functionality. IAVF provides generic hardware interface and
75 interface between IAVF driver and a compliant PF driver is specified.
77 Intel products starting Ethernet Controller 700 Series to support Adaptive Virtual Function.
79 The way to generate Virtual Function is like normal, and the resource of VF assignment depends on the NIC Infrastructure.
81 For more detail on SR-IOV, please refer to the following documents:
83 * `Intel® IAVF HAS <https://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/ethernet-adaptive-virtual-function-hardware-spec.pdf>`_
87 To use DPDK IAVF PMD on Intel® 700 Series Ethernet Controller, the device id (0x1889) need to specified during device
88 assignment in hypervisor. Take qemu for example, the device assignment should carry the IAVF device id (0x1889) like
89 ``-device vfio-pci,x-pci-device-id=0x1889,host=03:0a.0``.
91 When IAVF is backed by an Intel® E810 device, the "Protocol Extraction" feature which is supported by ice PMD is also
92 available for IAVF PMD. The same devargs with the same parameters can be applied to IAVF PMD, for detail please reference
93 the section ``Protocol extraction for per queue`` of ice.rst.
95 Quanta size configuration is also supported when IAVF is backed by an Intel® E810 device by setting ``devargs``
96 parameter ``quanta_size`` like ``-a 18:00.0,quanta_size=2048``. The default value is 1024, and quanta size should be
97 set as the product of 64 in legacy host interface mode.
99 The PCIE host-interface of Intel Ethernet Switch FM10000 Series VF infrastructure
100 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
102 In a virtualized environment, the programmer can enable a maximum of *64 Virtual Functions (VF)*
103 globally per PCIE host-interface of the Intel Ethernet Switch FM10000 Series device.
104 Each VF can have a maximum of 16 queue pairs.
105 The Physical Function in host could be only configured by the Linux* fm10k driver
106 (in the case of the Linux Kernel-based Virtual Machine [KVM]), DPDK PMD PF driver doesn't support it yet.
110 * Using Linux* fm10k driver:
112 .. code-block:: console
114 rmmod fm10k (To remove the fm10k module)
115 insmod fm0k.ko max_vfs=2,2 (To enable two Virtual Functions per port)
117 Virtual Function enumeration is performed in the following sequence by the Linux* pci driver for a dual-port NIC.
118 When you enable the four Virtual Functions with the above command, the four enabled functions have a Function#
119 represented by (Bus#, Device#, Function#) in sequence starting from 0 to 3.
122 * Virtual Functions 0 and 2 belong to Physical Function 0
124 * Virtual Functions 1 and 3 belong to Physical Function 1
128 The above is an important consideration to take into account when targeting specific packets to a selected port.
130 Intel® X710/XL710 Gigabit Ethernet Controller VF Infrastructure
131 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
133 In a virtualized environment, the programmer can enable a maximum of *128 Virtual Functions (VF)*
134 globally per Intel® X710/XL710 Gigabit Ethernet Controller NIC device.
135 The Physical Function in host could be either configured by the Linux* i40e driver
136 (in the case of the Linux Kernel-based Virtual Machine [KVM]) or by DPDK PMD PF driver.
137 When using both DPDK PMD PF/VF drivers, the whole NIC will be taken over by DPDK based application.
141 * Using Linux* i40e driver:
143 .. code-block:: console
145 rmmod i40e (To remove the i40e module)
146 insmod i40e.ko max_vfs=2,2 (To enable two Virtual Functions per port)
148 * Using the DPDK PMD PF i40e driver:
150 Kernel Params: iommu=pt, intel_iommu=on
152 .. code-block:: console
156 ./dpdk-devbind.py -b igb_uio bb:ss.f
157 echo 2 > /sys/bus/pci/devices/0000\:bb\:ss.f/max_vfs (To enable two VFs on a specific PCI device)
159 Launch the DPDK testpmd/example or your own host daemon application using the DPDK PMD library.
161 Virtual Function enumeration is performed in the following sequence by the Linux* pci driver for a dual-port NIC.
162 When you enable the four Virtual Functions with the above command, the four enabled functions have a Function#
163 represented by (Bus#, Device#, Function#) in sequence starting from 0 to 3.
166 * Virtual Functions 0 and 2 belong to Physical Function 0
168 * Virtual Functions 1 and 3 belong to Physical Function 1
172 The above is an important consideration to take into account when targeting specific packets to a selected port.
174 For Intel® X710/XL710 Gigabit Ethernet Controller, queues are in pairs. One queue pair means one receive queue and
175 one transmit queue. The default number of queue pairs per VF is 4, and can be 16 in maximum.
177 Intel® 82599 10 Gigabit Ethernet Controller VF Infrastructure
178 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
180 The programmer can enable a maximum of *63 Virtual Functions* and there must be *one Physical Function* per Intel® 82599
181 10 Gigabit Ethernet Controller NIC port.
182 The reason for this is that the device allows for a maximum of 128 queues per port and a virtual/physical function has to
183 have at least one queue pair (RX/TX).
184 The current implementation of the DPDK ixgbevf driver supports a single queue pair (RX/TX) per Virtual Function.
185 The Physical Function in host could be either configured by the Linux* ixgbe driver
186 (in the case of the Linux Kernel-based Virtual Machine [KVM]) or by DPDK PMD PF driver.
187 When using both DPDK PMD PF/VF drivers, the whole NIC will be taken over by DPDK based application.
191 * Using Linux* ixgbe driver:
193 .. code-block:: console
195 rmmod ixgbe (To remove the ixgbe module)
196 insmod ixgbe max_vfs=2,2 (To enable two Virtual Functions per port)
198 * Using the DPDK PMD PF ixgbe driver:
200 Kernel Params: iommu=pt, intel_iommu=on
202 .. code-block:: console
206 ./dpdk-devbind.py -b igb_uio bb:ss.f
207 echo 2 > /sys/bus/pci/devices/0000\:bb\:ss.f/max_vfs (To enable two VFs on a specific PCI device)
209 Launch the DPDK testpmd/example or your own host daemon application using the DPDK PMD library.
211 * Using the DPDK PMD PF ixgbe driver to enable VF RSS:
213 Same steps as above to install the modules of uio, igb_uio, specify max_vfs for PCI device, and
214 launch the DPDK testpmd/example or your own host daemon application using the DPDK PMD library.
216 The available queue number (at most 4) per VF depends on the total number of pool, which is
217 determined by the max number of VF at PF initialization stage and the number of queue specified
220 * If the max number of VFs (max_vfs) is set in the range of 1 to 32:
222 If the number of Rx queues is specified as 4 (``--rxq=4`` in testpmd), then there are totally 32
223 pools (RTE_ETH_32_POOLS), and each VF could have 4 Rx queues;
225 If the number of Rx queues is specified as 2 (``--rxq=2`` in testpmd), then there are totally 32
226 pools (RTE_ETH_32_POOLS), and each VF could have 2 Rx queues;
228 * If the max number of VFs (max_vfs) is in the range of 33 to 64:
230 If the number of Rx queues in specified as 4 (``--rxq=4`` in testpmd), then error message is expected
231 as ``rxq`` is not correct at this case;
233 If the number of rxq is 2 (``--rxq=2`` in testpmd), then there is totally 64 pools (RTE_ETH_64_POOLS),
234 and each VF have 2 Rx queues;
236 On host, to enable VF RSS functionality, rx mq mode should be set as RTE_ETH_MQ_RX_VMDQ_RSS
237 or RTE_ETH_MQ_RX_RSS mode, and SRIOV mode should be activated (max_vfs >= 1).
238 It also needs config VF RSS information like hash function, RSS key, RSS key length.
242 The limitation for VF RSS on Intel® 82599 10 Gigabit Ethernet Controller is:
243 The hash and key are shared among PF and all VF, the RETA table with 128 entries is also shared
244 among PF and all VF; So it could not to provide a method to query the hash and reta content per
245 VF on guest, while, if possible, please query them on host for the shared RETA information.
247 Virtual Function enumeration is performed in the following sequence by the Linux* pci driver for a dual-port NIC.
248 When you enable the four Virtual Functions with the above command, the four enabled functions have a Function#
249 represented by (Bus#, Device#, Function#) in sequence starting from 0 to 3.
252 * Virtual Functions 0 and 2 belong to Physical Function 0
254 * Virtual Functions 1 and 3 belong to Physical Function 1
258 The above is an important consideration to take into account when targeting specific packets to a selected port.
260 Intel® 82576 Gigabit Ethernet Controller and Intel® Ethernet Controller I350 Family VF Infrastructure
261 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
263 In a virtualized environment, an Intel® 82576 Gigabit Ethernet Controller serves up to eight virtual machines (VMs).
264 The controller has 16 TX and 16 RX queues.
265 They are generally referred to (or thought of) as queue pairs (one TX and one RX queue).
266 This gives the controller 16 queue pairs.
268 A pool is a group of queue pairs for assignment to the same VF, used for transmit and receive operations.
269 The controller has eight pools, with each pool containing two queue pairs, that is, two TX and two RX queues assigned to each VF.
271 In a virtualized environment, an Intel® Ethernet Controller I350 family device serves up to eight virtual machines (VMs) per port.
272 The eight queues can be accessed by eight different VMs if configured correctly (the i350 has 4x1GbE ports each with 8T X and 8 RX queues),
273 that means, one Transmit and one Receive queue assigned to each VF.
277 * Using Linux* igb driver:
279 .. code-block:: console
281 rmmod igb (To remove the igb module)
282 insmod igb max_vfs=2,2 (To enable two Virtual Functions per port)
284 * Using DPDK PMD PF igb driver:
286 Kernel Params: iommu=pt, intel_iommu=on modprobe uio
288 .. code-block:: console
291 ./dpdk-devbind.py -b igb_uio bb:ss.f
292 echo 2 > /sys/bus/pci/devices/0000\:bb\:ss.f/max_vfs (To enable two VFs on a specific pci device)
294 Launch DPDK testpmd/example or your own host daemon application using the DPDK PMD library.
296 Virtual Function enumeration is performed in the following sequence by the Linux* pci driver for a four-port NIC.
297 When you enable the four Virtual Functions with the above command, the four enabled functions have a Function#
298 represented by (Bus#, Device#, Function#) in sequence, starting from 0 to 7.
301 * Virtual Functions 0 and 4 belong to Physical Function 0
303 * Virtual Functions 1 and 5 belong to Physical Function 1
305 * Virtual Functions 2 and 6 belong to Physical Function 2
307 * Virtual Functions 3 and 7 belong to Physical Function 3
311 The above is an important consideration to take into account when targeting specific packets to a selected port.
313 Validated Hypervisors
314 ~~~~~~~~~~~~~~~~~~~~~
316 The validated hypervisor is:
318 * KVM (Kernel Virtual Machine) with Qemu, version 0.14.0
320 However, the hypervisor is bypassed to configure the Virtual Function devices using the Mailbox interface,
321 the solution is hypervisor-agnostic.
322 Xen* and VMware* (when SR- IOV is supported) will also be able to support the DPDK with Virtual Function driver support.
324 Expected Guest Operating System in Virtual Machine
325 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
327 The expected guest operating systems in a virtualized environment are:
329 * Fedora* 14 (64-bit)
331 * Ubuntu* 10.04 (64-bit)
333 For supported kernel versions, refer to the *DPDK Release Notes*.
337 Setting Up a KVM Virtual Machine Monitor
338 ----------------------------------------
340 The following describes a target environment:
342 * Host Operating System: Fedora 14
344 * Hypervisor: KVM (Kernel Virtual Machine) with Qemu version 0.14.0
346 * Guest Operating System: Fedora 14
348 * Linux Kernel Version: Refer to the *DPDK Getting Started Guide*
350 * Target Applications: l2fwd, l3fwd-vf
352 The setup procedure is as follows:
354 #. Before booting the Host OS, open **BIOS setup** and enable **Intel® VT features**.
356 #. While booting the Host OS kernel, pass the intel_iommu=on kernel command line argument using GRUB.
357 When using DPDK PF driver on host, pass the iommu=pt kernel command line argument in GRUB.
359 #. Download qemu-kvm-0.14.0 from
360 `http://sourceforge.net/projects/kvm/files/qemu-kvm/ <http://sourceforge.net/projects/kvm/files/qemu-kvm/>`_
361 and install it in the Host OS using the following steps:
363 When using a recent kernel (2.6.25+) with kvm modules included:
365 .. code-block:: console
367 tar xzf qemu-kvm-release.tar.gz
369 ./configure --prefix=/usr/local/kvm
372 sudo /sbin/modprobe kvm-intel
374 When using an older kernel, or a kernel from a distribution without the kvm modules,
375 you must download (from the same link), compile and install the modules yourself:
377 .. code-block:: console
379 tar xjf kvm-kmod-release.tar.bz2
384 sudo /sbin/modprobe kvm-intel
386 qemu-kvm installs in the /usr/local/bin directory.
388 For more details about KVM configuration and usage, please refer to:
390 `http://www.linux-kvm.org/page/HOWTO1 <http://www.linux-kvm.org/page/HOWTO1>`_.
392 #. Create a Virtual Machine and install Fedora 14 on the Virtual Machine.
393 This is referred to as the Guest Operating System (Guest OS).
395 #. Download and install the latest ixgbe driver from
396 `intel.com <https://downloadcenter.intel.com/download/14687>`_.
400 When using Linux kernel ixgbe driver, unload the Linux ixgbe driver and reload it with the max_vfs=2,2 argument:
402 .. code-block:: console
405 modprobe ixgbe max_vfs=2,2
407 When using DPDK PMD PF driver, insert DPDK kernel module igb_uio and set the number of VF by sysfs max_vfs:
409 .. code-block:: console
413 ./dpdk-devbind.py -b igb_uio 02:00.0 02:00.1 0e:00.0 0e:00.1
414 echo 2 > /sys/bus/pci/devices/0000\:02\:00.0/max_vfs
415 echo 2 > /sys/bus/pci/devices/0000\:02\:00.1/max_vfs
416 echo 2 > /sys/bus/pci/devices/0000\:0e\:00.0/max_vfs
417 echo 2 > /sys/bus/pci/devices/0000\:0e\:00.1/max_vfs
421 You need to explicitly specify number of vfs for each port, for example,
422 in the command above, it creates two vfs for the first two ixgbe ports.
424 Let say we have a machine with four physical ixgbe ports:
435 The command above creates two vfs for device 0000:02:00.0:
437 .. code-block:: console
439 ls -alrt /sys/bus/pci/devices/0000\:02\:00.0/virt*
440 lrwxrwxrwx. 1 root root 0 Apr 13 05:40 /sys/bus/pci/devices/0000:02:00.0/virtfn1 -> ../0000:02:10.2
441 lrwxrwxrwx. 1 root root 0 Apr 13 05:40 /sys/bus/pci/devices/0000:02:00.0/virtfn0 -> ../0000:02:10.0
443 It also creates two vfs for device 0000:02:00.1:
445 .. code-block:: console
447 ls -alrt /sys/bus/pci/devices/0000\:02\:00.1/virt*
448 lrwxrwxrwx. 1 root root 0 Apr 13 05:51 /sys/bus/pci/devices/0000:02:00.1/virtfn1 -> ../0000:02:10.3
449 lrwxrwxrwx. 1 root root 0 Apr 13 05:51 /sys/bus/pci/devices/0000:02:00.1/virtfn0 -> ../0000:02:10.1
451 #. List the PCI devices connected and notice that the Host OS shows two Physical Functions (traditional ports)
452 and four Virtual Functions (two for each port).
453 This is the result of the previous step.
455 #. Insert the pci_stub module to hold the PCI devices that are freed from the default driver using the following command
456 (see http://www.linux-kvm.org/page/How_to_assign_devices_with_VT-d_in_KVM Section 4 for more information):
458 .. code-block:: console
460 sudo /sbin/modprobe pci-stub
462 Unbind the default driver from the PCI devices representing the Virtual Functions.
463 A script to perform this action is as follows:
465 .. code-block:: console
467 echo "8086 10ed" > /sys/bus/pci/drivers/pci-stub/new_id
468 echo 0000:08:10.0 > /sys/bus/pci/devices/0000:08:10.0/driver/unbind
469 echo 0000:08:10.0 > /sys/bus/pci/drivers/pci-stub/bind
471 where, 0000:08:10.0 belongs to the Virtual Function visible in the Host OS.
473 #. Now, start the Virtual Machine by running the following command:
475 .. code-block:: console
477 /usr/local/kvm/bin/qemu-system-x86_64 -m 4096 -smp 4 -boot c -hda lucid.qcow2 -device pci-assign,host=08:10.0
481 — -m = memory to assign
483 — -smp = number of smp cores
485 — -boot = boot option
487 — -hda = virtual disk image
489 — -device = device to attach
493 — The pci-assign,host=08:10.0 value indicates that you want to attach a PCI device
494 to a Virtual Machine and the respective (Bus:Device.Function)
495 numbers should be passed for the Virtual Function to be attached.
497 — qemu-kvm-0.14.0 allows a maximum of four PCI devices assigned to a VM,
498 but this is qemu-kvm version dependent since qemu-kvm-0.14.1 allows a maximum of five PCI devices.
500 — qemu-system-x86_64 also has a -cpu command line option that is used to select the cpu_model
501 to emulate in a Virtual Machine. Therefore, it can be used as:
503 .. code-block:: console
505 /usr/local/kvm/bin/qemu-system-x86_64 -cpu ?
507 (to list all available cpu_models)
509 /usr/local/kvm/bin/qemu-system-x86_64 -m 4096 -cpu host -smp 4 -boot c -hda lucid.qcow2 -device pci-assign,host=08:10.0
511 (to use the same cpu_model equivalent to the host cpu)
513 For more information, please refer to: `http://wiki.qemu.org/Features/CPUModels <http://wiki.qemu.org/Features/CPUModels>`_.
515 #. If use vfio-pci to pass through device instead of pci-assign, steps 8 and 9 need to be updated to bind device to vfio-pci and
516 replace pci-assign with vfio-pci when start virtual machine.
518 .. code-block:: console
520 sudo /sbin/modprobe vfio-pci
522 echo "8086 10ed" > /sys/bus/pci/drivers/vfio-pci/new_id
523 echo 0000:08:10.0 > /sys/bus/pci/devices/0000:08:10.0/driver/unbind
524 echo 0000:08:10.0 > /sys/bus/pci/drivers/vfio-pci/bind
526 /usr/local/kvm/bin/qemu-system-x86_64 -m 4096 -smp 4 -boot c -hda lucid.qcow2 -device vfio-pci,host=08:10.0
528 #. Install and run DPDK host app to take over the Physical Function. Eg.
530 .. code-block:: console
532 ./<build_dir>/app/dpdk-testpmd -l 0-3 -n 4 -- -i
534 #. Finally, access the Guest OS using vncviewer with the localhost:5900 port and check the lspci command output in the Guest OS.
535 The virtual functions will be listed as available for use.
537 #. Configure and install the DPDK on the Guest OS as normal, that is, there is no change to the normal installation procedure.
541 If you are unable to compile the DPDK and you are getting "error: CPU you selected does not support x86-64 instruction set",
542 power off the Guest OS and start the virtual machine with the correct -cpu option in the qemu- system-x86_64 command as shown in step 9.
543 You must select the best x86_64 cpu_model to emulate or you can select host option if available.
547 Run the DPDK l2fwd sample application in the Guest OS with Hugepages enabled.
548 For the expected benchmark performance, you must pin the cores from the Guest OS to the Host OS (taskset can be used to do this) and
549 you must also look at the PCI Bus layout on the board to ensure you are not running the traffic over the QPI Interface.
553 * The Virtual Machine Manager (the Fedora package name is virt-manager) is a utility for virtual machine management
554 that can also be used to create, start, stop and delete virtual machines.
555 If this option is used, step 2 and 6 in the instructions provided will be different.
557 * virsh, a command line utility for virtual machine management,
558 can also be used to bind and unbind devices to a virtual machine in Ubuntu.
559 If this option is used, step 6 in the instructions provided will be different.
561 * The Virtual Machine Monitor (see :numref:`figure_perf_benchmark`) is equivalent to a Host OS with KVM installed as described in the instructions.
563 .. _figure_perf_benchmark:
565 .. figure:: img/perf_benchmark.*
567 Performance Benchmark Setup
570 DPDK SR-IOV PMD PF/VF Driver Usage Model
571 ----------------------------------------
573 Fast Host-based Packet Processing
574 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
576 Software Defined Network (SDN) trends are demanding fast host-based packet handling.
577 In a virtualization environment,
578 the DPDK VF PMD performs the same throughput result as a non-VT native environment.
580 With such host instance fast packet processing, lots of services such as filtering, QoS,
581 DPI can be offloaded on the host fast path.
583 :numref:`figure_fast_pkt_proc` shows the scenario where some VMs directly communicate externally via a VFs,
584 while others connect to a virtual switch and share the same uplink bandwidth.
586 .. _figure_fast_pkt_proc:
588 .. figure:: img/fast_pkt_proc.*
590 Fast Host-based Packet Processing
593 SR-IOV (PF/VF) Approach for Inter-VM Communication
594 --------------------------------------------------
596 Inter-VM data communication is one of the traffic bottle necks in virtualization platforms.
597 SR-IOV device assignment helps a VM to attach the real device, taking advantage of the bridge in the NIC.
598 So VF-to-VF traffic within the same physical port (VM0<->VM1) have hardware acceleration.
599 However, when VF crosses physical ports (VM0<->VM2), there is no such hardware bridge.
600 In this case, the DPDK PMD PF driver provides host forwarding between such VMs.
602 :numref:`figure_inter_vm_comms` shows an example.
603 In this case an update of the MAC address lookup tables in both the NIC and host DPDK application is required.
605 In the NIC, writing the destination of a MAC address belongs to another cross device VM to the PF specific pool.
606 So when a packet comes in, its destination MAC address will match and forward to the host DPDK PMD application.
608 In the host DPDK application, the behavior is similar to L2 forwarding,
609 that is, the packet is forwarded to the correct PF pool.
610 The SR-IOV NIC switch forwards the packet to a specific VM according to the MAC destination address
611 which belongs to the destination VF on the VM.
613 .. _figure_inter_vm_comms:
615 .. figure:: img/inter_vm_comms.*
617 Inter-VM Communication
623 * IAVF PMD currently is supported only inside Windows guest created on Linux host.
625 * Physical PCI resources are exposed as virtual functions
626 into Windows VM using SR-IOV pass-through feature.
628 * Create a Windows guest on Linux host using KVM hypervisor.
629 Refer to the steps mentioned in the above section: :ref:`intel_vf_kvm`.
631 * In the Host machine, download and install the kernel Ethernet driver
632 for `i40e <https://downloadcenter.intel.com/download/24411>`_
633 or `ice <https://downloadcenter.intel.com/download/29746>`_.
635 * For Windows guest, install NetUIO driver
636 in place of existing built-in (inbox) Virtual Function driver.
638 * To load NetUIO driver, follow the steps mentioned in `dpdk-kmods repository
639 <https://git.dpdk.org/dpdk-kmods/tree/windows/netuio/README.rst>`_.
645 * IAVF PMD supports inline crypto processing depending on the underlying
646 hardware crypto capabilities. IPsec Security Gateway Sample Application
647 supports inline IPsec processing for IAVF PMD. For more details see the
648 IPsec Security Gateway Sample Application and Security library