User Manual

Rev 2.3-1.0.1
Mellanox Technologies
189
 To add a VLAN:
In the example below, the following state exist:
# cat /sys/class/net/eth5/vf0/vlan_set
oper: 0 1 2 3
admin: 0 1 2 3
Step 1. Make an operational VLAN set identical to the administration VLAN.
echo 2 3 4 5 6 > /sys/class/net/eth5/vf0/vlan_set
The delta will be added to the operational state immediately (4 5 6):
# cat /sys/class/net/eth5/vf0/vlan_set
oper: 0 1 2 3 4 5 6
admin: 2 3 4 5 6
Step 2. Reset the VF for changes to take effect.
3.4.2 VXLAN
3.4.2.1 Prerequisites
• HCA: ConnectX-3 Pro
• Firmware 2.31.5020 or higher
• RHEL7, Ubuntu 14.04 or upstream kernel 3.12.10 (or higher)
• DMFS enabled
3.4.2.2 Enabling VXLAN
To enable the vxlan offloads support load the
mlx4_core driver with Device-Managed Flow-
steering (DMFS) enabled. DMFS is the default steering mode.
To verify VXLAN is enabled, verify the Ethernet net-device created by the mlx4_en driver
advertises the
NETIF_F_GSO_UDP_TUNNEL feature, which can be seen by the "eththool -K $DEV
| grep udp"
For example:
$ ethtool -k eth0 | grep udp_tnl
tx-udp_tnl-segmentation: on
Make sure that the VXLAN tunnel is set over UDP port 4789, which is the ConnectX firmware
default. If using standard Linux bridge (and not open vswitch) set the following
/etc/mod-
probe.d/vxlan.conf
:
options vxlan udp_port=4789
3.4.2.3 Important Notes
• VXLAN tunneling adds 50 bytes (14-eth + 20-ip + 8-udp + 8-vxlan) to the VM Ethernet
frame. Please verify that either the MTU of the NIC who sends the packets, e.g. the
VM
virtio-net NIC or the host side veth device or the uplink takes into account the tunneling
overhead. Meaning, the MTU of the sending NIC has to be decremented by 50 bytes