neutron/doc/source/admin/config-sriov.rst
Radosław Piliszek a8fa085364 [nova][train] Docs: Remove deprecated RetryFilter
The default does not include it.

Nova docs:
RetryFilter - Deprecated since version 20.0.0 (Train)
Since the 17.0.0 (Queens) release, the scheduler has provided
alternate hosts for rescheduling so the scheduler does not need to
be called during a reschedule which makes the RetryFilter useless.

Change-Id: Ic7bfafce40b4025f6768121dec37c1d6f3b4c5fc
2019-10-18 12:47:47 +02:00

24 KiB

SR-IOV

The purpose of this page is to describe how to enable SR-IOV functionality available in OpenStack (using OpenStack Networking). This functionality was first introduced in the OpenStack Juno release. This page intends to serve as a guide for how to configure OpenStack Networking and OpenStack Compute to create SR-IOV ports.

The basics

PCI-SIG Single Root I/O Virtualization and Sharing (SR-IOV) functionality is available in OpenStack since the Juno release. The SR-IOV specification defines a standardized mechanism to virtualize PCIe devices. This mechanism can virtualize a single PCIe Ethernet controller to appear as multiple PCIe devices. Each device can be directly assigned to an instance, bypassing the hypervisor and virtual switch layer. As a result, users are able to achieve low latency and near-line wire speed.

The following terms are used throughout this document:

Term Definition
PF Physical Function. The physical Ethernet controller that supports SR-IOV.
VF Virtual Function. The virtual PCIe device created from a physical Ethernet controller.

SR-IOV agent

The SR-IOV agent allows you to set the admin state of ports, configure port security (enable and disable spoof checking), and configure QoS rate limiting and minimum bandwidth. You must include the SR-IOV agent on each compute node using SR-IOV ports.

Note

The SR-IOV agent was optional before Mitaka, and was not enabled by default before Liberty.

Note

The ability to control port security and QoS rate limit settings was added in Liberty.

Supported Ethernet controllers

The following manufacturers are known to work:

  • Intel
  • Mellanox
  • QLogic
  • Broadcom

For information on Mellanox SR-IOV Ethernet ConnectX cards, see:

For information on QLogic SR-IOV Ethernet cards, see:

For information on Broadcom NetXtreme-E Series Ethernet cards, see the Broadcom NetXtreme-C/NetXtreme-E User Guide.

For information on Broadcom NetXtreme-S Series Ethernet cards, see the Broadcom NetXtreme-S Product Page.

Using SR-IOV interfaces

In order to enable SR-IOV, the following steps are required:

  1. Create Virtual Functions (Compute)
  2. Whitelist PCI devices in nova-compute (Compute)
  3. Configure neutron-server (Controller)
  4. Configure nova-scheduler (Controller)
  5. Enable neutron sriov-agent (Compute)

We recommend using VLAN provider networks for segregation. This way you can combine instances without SR-IOV ports and instances with SR-IOV ports on a single network.

Note

Throughout this guide, eth3 is used as the PF and physnet2 is used as the provider network configured as a VLAN range. These ports may vary in different environments.

Create Virtual Functions (Compute)

Create the VFs for the network interface that will be used for SR-IOV. We use eth3 as PF, which is also used as the interface for the VLAN provider network and has access to the private networks of all machines.

Note

The steps detail how to create VFs using Mellanox ConnectX-4 and newer/Intel SR-IOV Ethernet cards on an Intel system. Steps may differ for different hardware configurations.

  1. Ensure SR-IOV and VT-d are enabled in BIOS.

  2. Enable IOMMU in Linux by adding intel_iommu=on to the kernel parameters, for example, using GRUB.

  3. On each compute node, create the VFs via the PCI SYS interface:

    # echo '8' > /sys/class/net/eth3/device/sriov_numvfs

    Note

    On some PCI devices, observe that when changing the amount of VFs you receive the error Device or resource busy. In this case, you must first set sriov_numvfs to 0, then set it to your new value.

    Note

    A network interface could be used both for PCI passthrough, using the PF, and SR-IOV, using the VFs. If the PF is used, the VF number stored in the sriov_numvfs file is lost. If the PF is attached again to the operating system, the number of VFs assigned to this interface will be zero. To keep the number of VFs always assigned to this interface, modify the interfaces configuration file adding an ifup script command.

    On Ubuntu, modify the /etc/network/interfaces file:

    auto eth3
    iface eth3 inet dhcp
    pre-up echo '4' > /sys/class/net/eth3/device/sriov_numvfs

    On RHEL and derivatives, modify the /sbin/ifup-local file:

    #!/bin/sh
    if [[ "$1" == "eth3" ]]
    then
        echo '4' > /sys/class/net/eth3/device/sriov_numvfs
    fi

    Warning

    Alternatively, you can create VFs by passing the max_vfs to the kernel module of your network interface. However, the max_vfs parameter has been deprecated, so the PCI SYS interface is the preferred method.

    You can determine the maximum number of VFs a PF can support:

    # cat /sys/class/net/eth3/device/sriov_totalvfs
    63
  4. Verify that the VFs have been created and are in up state. For example:

    # lspci | grep Ethernet
    82:00.0 Ethernet controller: Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection (rev 01)
    82:00.1 Ethernet controller: Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection (rev 01)
    82:10.0 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
    82:10.2 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
    82:10.4 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
    82:10.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
    82:11.0 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
    82:11.2 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
    82:11.4 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
    82:11.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
    # ip link show eth3
    8: eth3: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT qlen 1000
       link/ether a0:36:9f:8f:3f:b8 brd ff:ff:ff:ff:ff:ff
       vf 0 MAC 00:00:00:00:00:00, spoof checking on, link-state auto
       vf 1 MAC 00:00:00:00:00:00, spoof checking on, link-state auto
       vf 2 MAC 00:00:00:00:00:00, spoof checking on, link-state auto
       vf 3 MAC 00:00:00:00:00:00, spoof checking on, link-state auto
       vf 4 MAC 00:00:00:00:00:00, spoof checking on, link-state auto
       vf 5 MAC 00:00:00:00:00:00, spoof checking on, link-state auto
       vf 6 MAC 00:00:00:00:00:00, spoof checking on, link-state auto
       vf 7 MAC 00:00:00:00:00:00, spoof checking on, link-state auto

    If the interfaces are down, set them to up before launching a guest, otherwise the instance will fail to spawn:

    # ip link set eth3 up
  5. Persist created VFs on reboot:

    # echo "echo '7' > /sys/class/net/eth3/device/sriov_numvfs" >> /etc/rc.local

    Note

    The suggested way of making PCI SYS settings persistent is through the sysfsutils tool. However, this is not available by default on many major distributions.

Whitelist PCI devices nova-compute (Compute)

  1. Configure which PCI devices the nova-compute service may use. Edit the nova.conf file:

    [pci]
    passthrough_whitelist = { "devname": "eth3", "physical_network": "physnet2"}

    This tells the Compute service that all VFs belonging to eth3 are allowed to be passed through to instances and belong to the provider network physnet2.

    Alternatively the [pci] passthrough_whitelist parameter also supports whitelisting by:

    • PCI address: The address uses the same syntax as in lspci and an asterisk (*) can be used to match anything.

      [pci]
      passthrough_whitelist = { "address": "[[[[<domain>]:]<bus>]:][<slot>][.[<function>]]", "physical_network": "physnet2" }

      For example, to match any domain, bus 0a, slot 00, and all functions:

      [pci]
      passthrough_whitelist = { "address": "*:0a:00.*", "physical_network": "physnet2" }
    • PCI vendor_id and product_id as displayed by the Linux utility lspci.

      [pci]
      passthrough_whitelist = { "vendor_id": "<id>", "product_id": "<id>", "physical_network": "physnet2" }

    If the device defined by the PCI address or devname corresponds to an SR-IOV PF, all VFs under the PF will match the entry. Multiple [pci] passthrough_whitelist entries per host are supported.

    In order to enable SR-IOV to request "trusted mode", the [pci] passthrough_whitelist parameter also supports a trusted tag.

    Note

    This capability is only supported starting with version 18.0.0 (Rocky) release of the compute service configured to use the libvirt driver.

    Important

    There are security implications of enabling trusted ports. The trusted VFs can be set into VF promiscuous mode which will enable it to receive unmatched and multicast traffic sent to the physical function.

    For example, to allow users to request SR-IOV devices with trusted capabilities on device eth3:

    [pci]
    passthrough_whitelist = { "devname": "eth3", "physical_network": "physnet2", "trusted":"true" }

    The ports will have to be created with a binding profile to match the trusted tag, see Launching instances with SR-IOV ports.

  2. Restart the nova-compute service for the changes to go into effect.

Configure neutron-server (Controller)

  1. Add sriovnicswitch as mechanism driver. Edit the ml2_conf.ini file on each controller:

    [ml2]
    mechanism_drivers = openvswitch,sriovnicswitch
  2. Ensure your physnet is configured for the chosen network type. Edit the ml2_conf.ini file on each controller:

    [ml2_type_vlan]
    network_vlan_ranges = physnet2
  3. Add the plugin.ini file as a parameter to the neutron-server service. Edit the appropriate initialization script to configure the neutron-server service to load the plugin configuration file:

    --config-file /etc/neutron/neutron.conf
    --config-file /etc/neutron/plugin.ini
  4. Restart the neutron-server service.

Configure nova-scheduler (Controller)

  1. On every controller node running the nova-scheduler service, add PciPassthroughFilter to [filter_scheduler] enabled_filters to enable this filter. Ensure [filter_scheduler] available_filters is set to the default of nova.scheduler.filters.all_filters:

    [filter_scheduler]
    enabled_filters = AvailabilityZoneFilter, ComputeFilter, ComputeCapabilitiesFilter, ImagePropertiesFilter, ServerGroupAntiAffinityFilter, ServerGroupAffinityFilter, PciPassthroughFilter
    available_filters = nova.scheduler.filters.all_filters
  2. Restart the nova-scheduler service.

Enable neutron-sriov-nic-agent (Compute)

  1. Install the SR-IOV agent, if necessary.

  2. Edit the sriov_agent.ini file on each compute node. For example:

    [securitygroup]
    firewall_driver = neutron.agent.firewall.NoopFirewallDriver
    
    [sriov_nic]
    physical_device_mappings = physnet2:eth3
    exclude_devices =

    Note

    The physical_device_mappings parameter is not limited to be a 1-1 mapping between physical networks and NICs. This enables you to map the same physical network to more than one NIC. For example, if physnet2 is connected to eth3 and eth4, then physnet2:eth3,physnet2:eth4 is a valid option.

    The exclude_devices parameter is empty, therefore, all the VFs associated with eth3 may be configured by the agent. To exclude specific VFs, add them to the exclude_devices parameter as follows:

    exclude_devices = eth1:0000:07:00.2;0000:07:00.3,eth2:0000:05:00.1;0000:05:00.2
  3. Ensure the SR-IOV agent runs successfully:

    # neutron-sriov-nic-agent \
      --config-file /etc/neutron/neutron.conf \
      --config-file /etc/neutron/plugins/ml2/sriov_agent.ini
  4. Enable the neutron SR-IOV agent service.

    If installing from source, you must configure a daemon file for the init system manually.

(Optional) FDB L2 agent extension

Forwarding DataBase (FDB) population is an L2 agent extension to OVS agent or Linux bridge. Its objective is to update the FDB table for existing instance using normal port. This enables communication between SR-IOV instances and normal instances. The use cases of the FDB population extension are:

  • Direct port and normal port instances reside on the same compute node.
  • Direct port instance that uses floating IP address and network node are located on the same host.

For additional information describing the problem, refer to: Virtual switching technologies and Linux bridge.

  1. Edit the ovs_agent.ini or linuxbridge_agent.ini file on each compute node. For example:

    [agent]
    extensions = fdb
  2. Add the FDB section and the shared_physical_device_mappings parameter. This parameter maps each physical port to its physical network name. Each physical network can be mapped to several ports:

    [FDB]
    shared_physical_device_mappings = physnet1:p1p1, physnet1:p1p2

Launching instances with SR-IOV ports

Once configuration is complete, you can launch instances with SR-IOV ports.

  1. If it does not already exist, create a network and subnet for the chosen physnet. This is the network to which SR-IOV ports will be attached. For example:

    $ openstack network create --provider-physical-network physnet2 \
        --provider-network-type vlan --provider-segment 1000 \
        sriov-net
    
    $ openstack subnet create --network sriov-net \
        --subnet-pool shared-default-subnetpool-v4 \
        sriov-subnet
  2. Get the id of the network where you want the SR-IOV port to be created:

    $ net_id=$(openstack network show sriov-net -c id -f value)
  3. Create the SR-IOV port. vnic-type=direct is used here, but other options include normal, direct-physical, and macvtap:

    $ openstack port create --network $net_id --vnic-type direct \
        sriov-port

    Alternatively, to request that the SR-IOV port accept trusted capabilities, the binding profile should be enhanced with the trusted tag.

    $ openstack port create --network $net_id --vnic-type direct \
        --binding-profile trusted=true \
        sriov-port
  4. Get the id of the created port:

    $ port_id=$(openstack port show sriov-port -c id -f value)
  5. Create the instance. Specify the SR-IOV port created in step two for the NIC:

    $ openstack server create --flavor m1.large --image ubuntu_18.04 \
        --nic port-id=$port_id \
        test-sriov

    Note

    There are two ways to attach VFs to an instance. You can create an SR-IOV port or use the pci_alias in the Compute service. For more information about using pci_alias, refer to nova-api configuration__.

    __ https://docs.openstack.org/nova/latest/admin/pci-passthrough.html#configure-nova-api-controller

SR-IOV with ConnectX-3/ConnectX-3 Pro Dual Port Ethernet

In contrast to Mellanox newer generation NICs, ConnectX-3 family network adapters expose a single PCI device (PF) in the system regardless of the number of physical ports. When the device is dual port and SR-IOV is enabled and configured we can observe some inconsistencies in linux networking subsystem.

Note

In the example below enp4s0 represents PF net device associated with physical port 1 and enp4s0d1 represents PF net device associated with physical port 2.

Example: A system with ConnectX-3 dual port device and a total of four VFs configured, two VFs assigned to port one and two VFs assigned to port two.

$ lspci | grep Mellanox
04:00.0 Network controller: Mellanox Technologies MT27520 Family [ConnectX-3 Pro]
04:00.1 Network controller: Mellanox Technologies MT27500/MT27520 Family [ConnectX-3/ConnectX-3 Pro Virtual Function]
04:00.2 Network controller: Mellanox Technologies MT27500/MT27520 Family [ConnectX-3/ConnectX-3 Pro Virtual Function]
04:00.3 Network controller: Mellanox Technologies MT27500/MT27520 Family [ConnectX-3/ConnectX-3 Pro Virtual Function]
04:00.4 Network controller: Mellanox Technologies MT27500/MT27520 Family [ConnectX-3/ConnectX-3 Pro Virtual Function]

Four VFs are available in the system, however,

$ ip link show
31: enp4s0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop master ovs-system state DOWN mode DEFAULT group default qlen 1000
    link/ether f4:52:14:01:d9:e1 brd ff:ff:ff:ff:ff:ff
    vf 0 MAC 00:00:00:00:00:00, vlan 4095, spoof checking off, link-state auto
    vf 1 MAC 00:00:00:00:00:00, vlan 4095, spoof checking off, link-state auto
    vf 2 MAC 00:00:00:00:00:00, vlan 4095, spoof checking off, link-state auto
    vf 3 MAC 00:00:00:00:00:00, vlan 4095, spoof checking off, link-state auto
32: enp4s0d1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
    link/ether f4:52:14:01:d9:e2 brd ff:ff:ff:ff:ff:ff
    vf 0 MAC 00:00:00:00:00:00, vlan 4095, spoof checking off, link-state auto
    vf 1 MAC 00:00:00:00:00:00, vlan 4095, spoof checking off, link-state auto
    vf 2 MAC 00:00:00:00:00:00, vlan 4095, spoof checking off, link-state auto
    vf 3 MAC 00:00:00:00:00:00, vlan 4095, spoof checking off, link-state auto

ip command identifies each PF associated net device as having four VFs each.

Note

Mellanox mlx4 driver allows ip commands to perform configuration of all VFs from either PF associated network devices.

To allow neutron SR-IOV agent to properly identify the VFs that belong to the correct PF network device (thus to the correct network port) Admin is required to provide the exclude_devices configuration option in sriov_agent.ini

Step 1: derive the VF to Port mapping from mlx4 driver configuration file: /etc/modprobe.d/mlnx.conf or /etc/modprobe.d/mlx4.conf

$ cat /etc/modprobe.d/mlnx.conf | grep "options mlx4_core"
options mlx4_core port_type_array=2,2 num_vfs=2,2,0 probe_vf=2,2,0 log_num_mgm_entry_size=-1

Where:

num_vfs=n1,n2,n3 - The driver will enable n1 VFs on physical port 1, n2 VFs on physical port 2 and n3 dual port VFs (applies only to dual port HCA when all ports are Ethernet ports).

probe_vfs=m1,m2,m3 - the driver probes m1 single port VFs on physical port 1, m2 single port VFs on physical port 2 (applies only if such a port exist) m3 dual port VFs. Those VFs are attached to the hypervisor. (applies only if all ports are configured as Ethernet).

The VFs will be enumerated in the following order:

  1. port 1 VFs
  2. port 2 VFs
  3. dual port VFs

In our example:

04:00.0 : PF associated to both ports.
04:00.1 : VF associated to port 1
04:00.2 : VF associated to port 1
04:00.3 : VF associated to port 2
04:00.4 : VF associated to port 2

Step 2: Update exclude_devices configuration option in sriov_agent.ini with the correct mapping

Each PF associated net device shall exclude the other port's VFs

[sriov_nic]
physical_device_mappings = physnet1:enp4s0,physnet2:enp4s0d1
exclude_devices = enp4s0:0000:04:00.3;0000:04:00.4,enp4s0d1:0000:04:00.1;0000:04:00.2

SR-IOV with InfiniBand

The support for SR-IOV with InfiniBand allows a Virtual PCI device (VF) to be directly mapped to the guest, allowing higher performance and advanced features such as RDMA (remote direct memory access). To use this feature, you must:

  1. Use InfiniBand enabled network adapters.

  2. Run InfiniBand subnet managers to enable InfiniBand fabric.

    All InfiniBand networks must have a subnet manager running for the network to function. This is true even when doing a simple network of two machines with no switch and the cards are plugged in back-to-back. A subnet manager is required for the link on the cards to come up. It is possible to have more than one subnet manager. In this case, one of them will act as the master, and any other will act as a slave that will take over when the master subnet manager fails.

  3. Install the ebrctl utility on the compute nodes.

    Check that ebrctl is listed somewhere in /etc/nova/rootwrap.d/*:

    $ grep 'ebrctl' /etc/nova/rootwrap.d/*

    If ebrctl does not appear in any of the rootwrap files, add this to the /etc/nova/rootwrap.d/compute.filters file in the [Filters] section.

    [Filters]
    ebrctl: CommandFilter, ebrctl, root

Known limitations

  • When using Quality of Service (QoS), max_burst_kbps (burst over max_kbps) is not supported. In addition, max_kbps is rounded to Mbps.

  • Security groups are not supported when using SR-IOV, thus, the firewall driver must be disabled. This can be done in the neutron.conf file.

    [securitygroup]
    firewall_driver = neutron.agent.firewall.NoopFirewallDriver
  • SR-IOV is not integrated into the OpenStack Dashboard (horizon). Users must use the CLI or API to configure SR-IOV interfaces.

  • Live migration support has been added to the Libvirt Nova virt-driver in the Train release for instances with neutron SR-IOV ports. Indirect mode SR-IOV interfaces (vnic-type: macvtap or virtio-forwarder) can now be migrated transparently to the guest. Direct mode SR-IOV interfaces (vnic-type: direct or direct-physical) are detached before the migration and reattached after the migration so this is not transparent to the guest. To avoid loss of network connectivy when live migrating with direct mode sriov the user should create a failover bond in the guest with a transparently live migration port type e.g. vnic-type normal or indirect mode SR-IOV.

    Note

    SR-IOV features may require a specific NIC driver version, depending on the vendor. Intel NICs, for example, require ixgbe version 4.4.6 or greater, and ixgbevf version 3.2.2 or greater.

  • Attaching SR-IOV ports to existing servers is not currently supported, see bug 1708433 for details.