Administrator Guide

Flex hash APIs do not mask out unwanted byte values after extraction of the data from the Layer 4 headers for the offset
value.
2. Use the load-balance flexhash command to specify whether IPv4 or IPv6 packets must be subjected to the flex
hash functionality, a unique protocol number, the offset of hash fields from the start of the L4 header to be used for hash
calculation, and a meaningful description to associate the protocol number with the name.
CONFIGURATION mode
Dell(conf)# load-balance flexhash ipv4/ipv6 ip-proto <protocol number> <description
string> offset1 <offset1 value> [offset2 <offset2 value>]
To delete the configured flex hash setting, use the no version of the command.
LACP Fast Switchover
LACP Fast Switchover causes the physical ports to be aggregated faster when configured in a port-channel on both the nodes
that are members of a port-channel.
When LACP ‘fast-switchover’ is enabled on the system, two optimizations are performed to the LACP behavior:
● The wait-while timer is not started in the ‘waiting’ state of the MUX state machine. The port moves directly to the
‘attached’ state.
● The local system moves to the ‘collecting’ and ‘distributing’ states on the port in a single step without waiting for the partner
to set the ‘collecting’ bit.
Configuring LACP Fast Switchover
To configure the optimized booting time functionality, perform the following step:
● The lacp fast-switchover command applies to dynamic port-channel interfaces only. When applied on a static port-
channel, this command has no effect. If you configure the optimized booting-time capability and perform a reload of the
system, the LACP application sends PDUs across all the active LACP links immediately. INTERFACE (conf-if-po-number)
mode Dell(conf-if-po-number)#lacp fast-switchover
LACP
LACP Fast Switchover
When LACP ‘fast-switchover’ is enabled on the system, two optimizations are performed to the LACP behavior:
● The wait-while timer is not started in the ‘waiting’ state of the MUX state machine. The port moves directly to the
‘attached’ state.
● The local system moves to the ‘collecting’ and ‘distributing’ states on the port in a single step without waiting for the partner
to set the ‘collecting’ bit.
RDMA Over Converged Ethernet (RoCE) Overview
Remote direct memory access (RDMA) is a technology that a virtual machine (VM) uses to directly transfer information to
the memory of another VM, thus enabling VMs to be connected to storage networks. With RDMA over converged Ethernet
(RoCE), RDMA enables data to be forwarded without passing through the CPU and the main memory path of TCP/IP. In
a deployment that contains both the RoCE network and the normal IP network on two different networks, routable RoCE
(RRoCE) combines the RoCE and the IP networks and sends the RoCE frames over the IP network. RRoCE transmission results
in the encapsulation of RoCE packets in IP packets.
Flex Hash and Optimized Boot-Up
369