Design Guide
© 2008 Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information.
Page 14 of 28
●
Network Fault Tolerance (NFT)
●
Transmit Load Balancing (TLB)
●
Switch Assisted Load Balancing (server load balancing [SLB])
NFT teaming creates a virtual interface by grouping the blade-server network adapters into a team.
One adapter is the primary active interface and all other adapters are in a standby state. The virtual
adapter uses a single MAC address and a single Layer 3 address. NFT provides adapter fault
tolerance by monitoring the state of each team member’s network connection. The standby NICs
become active only if the primary NIC loses connectivity to the network.
TLB teaming supports adapter fault tolerance (NFT) and adds more functions in the server for load
balancing egress (transmit) traffic across the team. Note that a TLB team uses only one NIC to
receive traffic. The load-balancing algorithm is based on either the destination MAC or IP address.
This teaming method provides better use of the bandwidth available for egress traffic in the network
than NFT.
SLB teaming extends the functions of TLB by allowing the team to receive load-balanced traffic
from the network. This reception requires that the switch can load balance the traffic across the
ports connected to the server NIC team. The Cisco Catalyst Blade Switch 3020 supports the IEEE
802.3ad standard and Gigabit Ethernet port channels. SLB teaming can only be used on full-height
servers, because it requires that both NICS go to the same upstream switch.
For more information about NIC teaming, please visit:
http://h18000.www1.hp.com/products/servers/networking/whitepapers.html
Scalability
The capability of the data center to adapt to increased demands without compromising its
availability is a crucial design consideration. The aggregation layer infrastructure and the services it
provides must accommodate future growth in the number of servers or subnets it supports.
When deploying blade servers in the data center, two primary factors need to be considered:
●
Number of physical ports in the aggregation and access layers
●
Number of slots in the aggregation layer switches
Physical Port Count
The introduction of blade systems into the data center requires greater port density at the
aggregation layer. Blade systems, deployed with internal switches, provide their own access layer.
The cabling and maximum number of servers per enclosure are predetermined. Scaling the
aggregation layer ports to accommodate the blade-system uplinks is an area that requires
attention.
It is important to remember that aggregation switches provide data center services such as load
balancing, security, and network analysis that may require dedicated ports for appliances or slots
for integrated services. This situation directly affects the number of ports available for access layer
connectivity.
