User's Guide

Planning the Fabric

Hyper Messaging Protocol (HMP)

Chapter 2

• Dynamic Resource Utilization (DRU): Partially Supported

When a new HyperFabric resource (node, cable or switch) is added to a cluster

running an HMP application, the HyperFabric subsystem will dynamically identify

the added resource and start using it. The same process takes place when a resource

is removed from a cluster. The distinction for HMP is that DRU is supported when a

node with adapters installed in it is added or removed from a cluster running an

HMP application, but DRU is not supported when an adapter is added or removed

from a node that is running an HMP application. This is consistent with the fact that

OLAR is not supported when an HMP application is running on HyperFabric.

• Load Balancing: Supported

When an HP 9000 node that has multiple HyperFabric adapter cards is running

HMP applications, the HyperFabric driver only balances the load across the nodes,

available adapter cards on that node, links and multiple links between switches.

• Switch Management: Not Supported

Switch Management is not supported. Switch management will not operate properly

if it is enabled on a HyperFabric cluster.

• Diagnostics: Supported

Diagnostics can be run to obtain information on many of the HyperFabric

components via the clic_diag, clic_probe and clic_stat commands, as well as

the Support Tools Manager (STM).

For more detailed information on HyperFabric diagnostics, see “Running

Diagnostics” on page 115 on page 149.

Conﬁguration Parameters

This section details, in general, the maximum limits for HMP HyperFabric

conﬁgurations. There are numerous variables that can impact the performance of any

particular HyperFabric conﬁguration. See the “HMP Supported Conﬁgurations” section

for guidance on speciﬁc HyperFabric conﬁgurations for HMP applications.

• HyperFabric is only supported on the HP 9000 series unix servers.

• The performance advantages HMP offers will not be fully realized unless it is used

with A6386A HF2 (ﬁbre) adapters and related ﬁbre hardware. The local failover

conﬁguration of HMP is supported only on the A6386AA HF2 adapters.

• Maximum Supported Nodes and Adapter Cards:

HyperFabric clusters running HMP applications are limited to supporting a

maximum of 64 adapter cards. However, in local failover conﬁgurations, a maximum

of only 52 adapters are supported.

In point to point conﬁgurations running HMP applications, the complexity and

performance limitations of having a large number of nodes in a cluster make it

necessary to include switching in the fabric. Typically, point to point conﬁgurations

consist of only 2 or 3 nodes.

In switched conﬁgurations running HMP applications, HyperFabric supports a

maximum of 64 interconnected adapter cards.