Administrator's Guide

Overview of the HyperFabric Product

HyperFabric Concepts

Chapter 1 7

HyperFabric Concepts

This section brieﬂy describes some of the basic HyperFabric concepts and

terms.

The fabric is the physical conﬁguration that consists of all the

HyperFabric adapters, the HyperFabric switches (if any), and the

HyperFabric cables connecting them. The network software controls data

transfer over the fabric.

The HyperFabric conﬁguration contains two or more HP 9000 systems

and optional HyperFabric switches. Each HP 9000 acts as a node in the

conﬁguration. Each node has a minimum of one and a maximum of eight

HyperFabric adapters installed in it. (For information on the maximum

number of adapters that can be installed in each system, see Chapter 2,

“Planning the Fabric,” on page 9.) Each HF2 switch can be conﬁgured

with 12 or 16 ports. HyperFabric supports a maximum of 4 HyperFabric

switches. You can mesh HyperFabric switches and conﬁgurations with

up to four levels of meshed switches are supported.

You can plan a HyperFabric cluster as a High Availability (HA)

conﬁguration, when it is necessary to ensure that each node can always

participate in the fabric. This is done by using ServiceGuard (earlier

known as MC/ServiceGuard), ServiceGuard OPS Edition (earlier known

as MC/LockManager), and the Event Monitoring Service (EMS).

Conﬁgurations of up to 8 nodes are supported under ServiceGuard.

Beginning with HyperFabric software versions B.11.00.05 and

B.11.11.00,you can use relocatable IP addresses as part of an HA

conﬁguration. Relocatable IP addresses permit a client application to

reroute through an adapter on a remote node, allowing that application

to continue processing without interruption. The rerouting is

transparent. This function is associated with ServiceGuard (see

“Conﬁguring ServiceGuard for HyperFabric Relocatable IP Addresses”

on page 95). When the monitor for HyperFabric detects a failure and the

backup adapter takes over, the relocatable IP address is transparently

migrated to the backup adapter. Throughout this migration process, the

client application continues to execute normally.

When you start HyperFabric (with the clic_start command, through

SAM, or by booting the HP 9000 system), you start the management

process. This process must be active for HyperFabric to run. If the

HyperFabric management process on a node stops running for some