Brocade Network OS Administrator’s Guide v4.1.1 - Manual (Page 38)

High performance and low latency are ensured because throughput is high and the hop count is low.
Throughput is high because multiple core switches share the load. Two hops get you from any edge
switch to any other edge switch. If you need greater throughput, simply add another core switch.
Scaling the topology also requires additional core switches and links. However, the number of
additional links you need is typically not as great as with, for example, a full mesh topology.
Ring topology
Ring topology connects each node to exactly two other nodes, forming a single continuous pathway.
Data travels from node to node, with each node along the path handling every packet of the data. The
following shows a ring topology.
FIGURE 9 Ring topology
This topology is highly scalable, yet susceptible to failures and traffic congestion. It is highly scalable
because of its efficient use of interswitch links and ports; an additional node requires only two ports to
connect to the ring. It is susceptible to failures because it provides only one path between any two
nodes. Throughput of the fabric is limited by the slowest link or node. Latency can be high because of
the potentially high number of hops it takes to communicates between two given switches. This
topology is useful where economy of port use is critical, but availability and throughput are less critical.
Full mesh topology
Full mesh topology connects each node to all other cluster nodes, as shown below.
Ring topology
38 Network OS Administrator’s Guide
53-1003225-04