Specifications

DATA CENTER BEST PRACTICES
SAN Design and Best Practices 9 of 84
The ClearLink diagnostic capability provides an opportunity to measure and thoroughly test ISLs before they are
put into production. It is recommended that diagnostics be conducted prior to deployment or when there are
CRC errors that could be caused by physical layer issues.
ClearLink D_Port guidelines and restrictions:
•Supported only on the Gen 5 Fibre Channel platforms with Brocade branded 10 Gbps or
16 Gbps transceivers
•Supported on E_Port and ports on both ends of the ISL must be in ClearLink D_Port mode
•Brocade FOS v7.1 provides ClearLink D_Port support on Gen 5 Fibre Channel switches running in Access
Gateway mode as well as on links between Gen 5 Fibre Channel switches and Brocade fabric adapters running
at 16 Gbps speed
•Brocade FOS v7.1 provides ClearLink D_Port support on UltraScale ICLs on the Brocade DCX® 8510
Backbone. The ClearLink D_Port on UltraScale ICLs skips the electrical and optical loopback tests, as the
Quad Small Form-factor Pluggable (QSFP) used does not support it.
•If Brocade Inter-Switch Link (ISL) Trunking is deployed, use a minimum of 2 ports for the trunk. This enables
the user to take down one of the links for diagnostic testing without disrupting the trafc on the remaining
trunk members.
•Make sure there are at least two ISLs prior to taking a port ofine for diagnostic testing. This ensures
redundancy and prevents fabric segmentation in case a link is taken down for diagnostics.
SAN DESIGN BASICS
This section provides high-level guidelines necessary to implement a typical SAN installation. The focus is on
best practices for core-edge or edge-core-edge fabrics. The discussion starts at the highest level, the data
center, and works down to the port level, providing recommendations at each point along the way.
Topologies
A typical SAN design comprises devices on the edge of the network, switches in the core of the network,
and the cabling that connects it all together. Topology is usually described in terms of how the switches are
interconnected, such as ring, core-edge, and edge-core-edge or fully meshed. At this point the focus is on
switch topology with SLs—device connectivity is discussed in later sections. The recommended SAN topology
to optimize performance, management, and scalability is a tiered, core-edge topology (sometimes called core-
edge or tiered core edge). This approach provides good performance without unnecessary interconnections. At
a high level, the tiered topology has a large number of edge switches used for device connectivity, and a smaller
number of core switches used for routing trafc between the edge switches, as shown in Figure 1.
fig01_SAN_Design
Scenario A
No hop
Scenario B
1 hops
Scenario C
2 hops
Server
Storage
Server
Storage
Server
Scenario D
1 hops
Server
StorageStorage
ICLICL
ICL
Storage
Figure 1. Four scenarios of tiered network topologies (hops shown in heavier, orange connections).