Jump to: navigation, search

Difference between revisions of "Mellanox-Neutron-Kilo-Redhat-InfiniBand"

(Controller Node)
(Compute Nodes)
Line 180: Line 180:
2. Install Mellanox RPMs:  
2. Install Mellanox RPMs:  
  # yum install --nogpgcheck -y openstack-neutron-mellanox eswitchd mlnx-dnsmasq python-networking-mlnx
  # yum install --nogpgcheck -y openstack-neutron-mellanox eswitchd python-networking-mlnx

Revision as of 13:52, 10 September 2015


Mellanox Neutron ML2 Driver

Mellanox ML2 Mechanism Driver implements the ML2 Plugin Mechanism Driver API.

This driver supports Mellanox embedded switch functionality as part of the VPI (Ethernet/InfiniBand) HCA. Mellanox ML2 Mechanism Driver provides functional parity with Mellanox Neutron plugin.

Mellanox ML2 Mechanism Driver supports DIRECT (pci passthrough) vnic type. For vnic type configuration API details, please refer to configuration reference guide. Hardware vNICs mapped to the guest VMs allow higher performance and advanced features such as RDMA (remote direct memory access).

The driver supports VLAN network type to facilitate virtual networks either on Ethernet or InfiniBand fabrics.

  • Mellanox OpenStack Neutron Agent (L2 Agent) runs on each compute node.
  • Agent should apply VIF connectivity based on mapping between a VIF (VM vNIC) and Embedded Switch port.


  • A running OpenStack environment installed with the ML2 plugin on top of OpenVswitch or Linux Bridge.
  • All nodes equipped with Mellanox ConnectX®-3 Network Adapter [1]
  • Mellanox OFED 2.4 or greater installed on all nodes. Please refer to Mellanox website for the latest OFED: [2]
  • SR-IOV enabled on all compute nodes. For more information, please refer to Mellanox Community click [3].
  • The software package iproute2 [4] installed on all Compute nodes
  • Add repository
yum-config-manager --add-repo http://www.mellanox.com/repository/solutions/openstack/kilo/rhel7/

InfiniBand Network

The Mellanox Neutron Plugin use InfiniBand Partitions (PKeys) to separate Networks.

SM Node

OpenSM Provisioning with SDN Mechanism Driver

SDN Mechanism Driver allows OpenSM dynamically assign PKs in the IB network.

More details about applying SDN Mechanism Driver with NEO can be found here

Manual OpenSM Configuration

All the PKeys should be predefined in the partitions.conf file (/etc/opensm/partitions.conf) (Automatic cofiguration is planned in future phase)

Add/Change the following in the partitions.conf file

  management=0x7fff,ipoib, sl=0, defmember=full : ALL, ALL_SWITCHES=full,SELF=full;
  vlan1=0x1, ipoib, sl=0, defmember=full : ALL;
  vlan2=0x2, ipoib, sl=0, defmember=full : ALL;
  vlan3=0x3, ipoib, sl=0, defmember=full : ALL;
  vlan4=0x4, ipoib, sl=0, defmember=full : ALL;
  vlan5=0x5, ipoib, sl=0, defmember=full : ALL;
  vlan6=0x6, ipoib, sl=0, defmember=full : ALL;
  vlan7=0x7, ipoib, sl=0, defmember=full : ALL;
  vlan8=0x8, ipoib, sl=0, defmember=full : ALL;
  vlan9=0x9, ipoib, sl=0, defmember=full : ALL;
  vlan10=0xa, ipoib, sl=0, defmember=full : ALL;

For example: If we have 10 VLANs defined in configuration in /etc/neutron/plugins/mlnx/mlnx_conf.ini

  network_vlan_ranges = physnet1:1:10

Change the following in /etc/opensm/opensm.conf:

  allow_both_pkeys TRUE

4. Restart the OpenSM:

# systemctl restart opensmd.service

RDO installation

To install and configure packstack

1. Install packstack

# yum install -y https://repos.fedorapeople.org/repos/openstack/openstack-kilo/rdo-release-kilo-1.noarch.rpm
# yum install -y openstack-packstack

2. Prepare answer file

# packstack --gen-answer-file=packstack.sriov

3. Modify answer file


4. Run packstack

# packstack --answer-file=packstack.sriov

Controller Node

To configure the Controller node:

1. Configure yum with Mellanox OpenStack Kilo repository

# yum-config-manager --add-repo http://www.mellanox.com/repository/solutions/openstack/kilo/rhel7

2. Install Mellanox RPMs:

# yum install -y --no gpgcheck openstack-neutron-mellanox python-networking-mlnx 

3. Make sure ML2 is the current Neutron plugin by checking the core_plugin parameter in /etc/neutron/neutron.conf:

core_plugin = neutron.plugins.ml2.plugin.Ml2Plugin

4. Make sure /etc/neutron/plugin.ini is pointing to /etc/neutron/plugins/ml2/ml2_conf.ini (symbolic link)

5. Modify /etc/neutron/plugins/ml2/ml2_conf.ini by adding the following:

type_drivers = vlan,flat
tenant_network_types = vlan
mechanism_drivers = mlnx, openvswitch
# or mechanism_drivers = mlnx, linuxbridge
network_vlan_ranges = physnet1:1:10
# (StrOpt) Type of Network Interface to allocate for VM:
# mlnx_direct or hostdev according to libvirt terminology
vnic_type = hostdev

6. Start (or restart) the Neutron server:

# systemctl restart neutron-server.service

Network Node

To configure the Network node:


E_IPoIB port is configured and up

1. Make sure that eIPoIB module is up and configured in /etc/infiniband/openib.conf: For more information, please refer to eIPoIB configuration in Mellanox OFED User Manual.


2. Restart openibd:

# service openibd restart

3. Modify the network bridge configuration according to the use of OpenVswitch or LinuxBridge

  • 3.1 OpenVswitch /etc/neutron/plugins/openvswitch/ovs_neutron_plugin.ini
bridge_mappings = physnet1:br-<eIPoIB interface>
  • 3.2 LinuxBridge file /etc/neutron/plugins/linuxbridge/linuxbridge_conf.ini:
physical_interface_mappings = physnet1:<eIPoIB interface>

NOTE: In order to obtain the eIPoIB interface name, run the ethtool tool command (see below) and check that driver name is eth_ipoib:

# ethtool -i <eIPoIB_interface> 
driver: eth_ipoib

4. Restart network bridge and neutron-dhcp-agent:

# service neutron-dhcp-agent restart
  • 4.1 OpenVswitch
# service neutron-openvswitch-agent restart
  • 4.2 LinuxBridge
# service neutron-linuxbridge-agent restart

NOTE: For DHCP support, the Network node should use the Mellanox Dnsmasq driver as the DHCP driver.

DHCP Server (Usually part of the Network node)

1. Modify /etc/neutron/dhcp_agent.ini as follows and according to OVS or Linuxbridge:

dhcp_driver = mlnx_dhcp.MlnxDnsmasq
dhcp_broadcast_reply = True
1.1 For OVS
    interface_driver = neutron.agent.linux.interface.OVSInterfaceDriver
1.2 For Linux Bridge
     interface_driver =  neutron.agent.linux.interface.BridgeInterfaceDriver

2. Start DHCP server:

# systemctl restart neutron-dhcp-agent.service

Compute Nodes

To configure the Compute Node:

1.Configure yum with Mellanox OpenStack Kilo repository

# yum-config-manager --add-repo http://www.mellanox.com/repository/solutions/openstack/kilo/rhel7

2. Install Mellanox RPMs:

# yum install --nogpgcheck -y openstack-neutron-mellanox eswitchd  python-networking-mlnx

3. Edit the following file: /usr/lib/systemd/system/neutron-mlnx-agent.service

Change the /etc/neutron/plugins/mlnx/mlnx.ini to /etc/neutron/plugins/mlnx/mlnx_conf.ini

4. Run:

# systemctl enable neutron-mlnx-agent.service

5. Run:

# systemctl daemon-reload

6. Apply MLNX patch for Kilo:

# pushd /usr/lib/python2.7/site-packages/nova/virt/libvirt/ 
# wget http://www.mellanox.com/repository/solutions/openstack/kilo/rhel7/patch/mlnx_kilo.patch
# patch < mlnx_kilo.patch
# popd

7. Create the file /etc/modprobe.d/mlx4_ib.conf and add the following:

options mlx4_ib sm_guid_assign=0

8. Restart Nova:

# systemctl restart openstack-nova-compute

9. Restart the driver:

# /bin/systemctl restart opensm.service
# /etc/init.d/openibd restart

10. In the file /etc/neutron/plugins/mlnx/mlnx_conf.ini, the parameters tenant_network_type , and network_vlan_ranges should be configured as the controllers:

physical_interface_mappings = physnet1:<ib_interface>(for example physnet1:ib0)

11. Modify the file /etc/eswitchd/eswitchd.conf as follows:

fabrics = physnet1:<ib_interface> (for example physnet1:ib0)

12. Start eSwitchd:

# systemctl restart eswitchd

13. Start the Neutron agent:

# systemctl restart neutron-mlnx-agent

Known issues and Troubleshooting

For known issues and troubleshooting options refer to Mellanox OpenStack Troubleshooting