HP StorageWorks XPath OS 7.4.X Administrator Guide (AA-RVHDD-TE, February 2006)

XPath OS 7.4.x administrator guide 91
8 Using ISL trunking
This chapter provides information on HP Interswitch Link (ISL) trunking, and consists of the following
sections:
• How exchange-based trunking works, next
• Enabling trunking, page 92
• Managing trunking, page 92
• Trunking commands, page 93
How exchange-based trunking works
The MP Router exchange-based trunking feature increases overall bandwidth by distributing network traffic
across ISLs connecting pairs of switches. More precisely, load balancing occurs across all equal-cost paths
to a destination domain.
This functionality works in two situations:
• Between two MP Routers
• From an MP Router to any other Fabric OS-based switch
Exchange-based trunking also works across multiple EX_Ports when MP Router ports are configured as
Fibre Channel routers.
Exchange-based trunking is supported at both 1 Gbit/sec and 2 Gbit/sec link speeds. There is no
restriction on the port location/numbers that can be part of the trunk.
Exchange-based trunking is activated when you install the appropriate HP licensed feature bundle. To
create a trunk, use the trunkSet command.
NOTE: MP Router exchange-based trunking is not supported with Continuous Access EVA. For all
Continuous Access EVA configurations using FCIP, you must set trunking to SID_DID or none. See the FCIP
portcfgfcip command.
NOTE: Fibre Channel routing link-cost calculation uses a simple formula based only on link speed.
When exchange-based trunking is enabled, all equal-cost paths are used for sending traffic to the given
destination domain. Each ingress port contains a list of egress ports that can be used to reach a
destination domain. On receiving a frame at the ingress port, the following fields in the Fibre Channel
frame header are used to determine which egress port to use:
• Source ID (S_ID)
• Destination ID (D_ID)
• Originator Exchange ID (OX_ID)
This scheme guarantees in-order delivery within a given exchange.
Exchange-based trunking does not depend on having exchange-based trunking operating on the
destination switch; the routing decision for any given frame of data is made at the origin switch. Thus, the
choice of which ISL to take always occurs when an MP Router is the source switch and any other switch is
the destination switch. If the other switch is not an MP Router, the return traffic does not benefit from
exchange-based trunking load balancing.
MP Routers are compatible with other HP StorageWorks switches. However, they are not compatible with
trunk groups (groups of four ports) of HP ISL trunking in Fabric OS 4.2 and earlier. When an MP Router
has multiple ISLs to a different model HP StorageWorks switch, traffic from the MP Router to the other model
is load balanced using exchange-based trunking. Traffic from the other model to the MP Router is load
balanced at a granularity of initiator device, target device pair. That is, rather than at a