HP ProLiant Cluster HA/F500 for MA8000 Enhanced DT Supplement Guide

Introduction
The ProLiant server nodes in the cluster are connected or stretched over a distance.
Up to two storage subsystems for ATM connections and four storage subsystems for
non-ATM connections can be used at one site. These storage subsystems act as the
initiator sites for the DRM software and process disk subsystem requests for all nodes
in the cluster. The storage subsystems are connected to the server nodes by means of
redundant Fibre Channel connections that are managed by Secure Path. Additionally,
the initiator storage subsystems are connected by means of redundant longwave
fiber/ATM connections to the target site. As with standard ProLiant clusters using
Microsoft operating systems, MSCS manages failovers at the server and application
levels.
The DRM software functions at the redundant storage controller level in each of the
storage subsystems and performs synchronous mirroring from the initiator site to
the target site, creating an exact copy of the cluster-shared disk. A manual recovery
process performed at the target site allows access to the mirrored data in the event of
a disaster at the initiator site. The cluster is functional again within minutes, and
application processing can continue.
There are several types of failover scenarios in an HA/F500 Enhanced DT cluster.
Some are automatic and others require manual intervention. Because the nodes are
part of a standard MSCS cluster, many failures are recognized and corrected
automatically by MSCS, including server, application, and MSCS resource failures.
In addition, failover caused by Fibre Channel/ATM link failures and remote storage
failures are corrected automatically.
Failover scenarios that are not corrected automatically and that require manual
intervention include local storage and entire site failures. The failover and monitoring
logic that is required for a fully automated failover of these types of failures must be
very sophisticated to prevent false failover.
Most companies interested in HA/F500 Enhanced DT cluster configurations for
entire site failures still want the option of performing the site failover manually.
Additional operations can be performed remotely, using remote monitoring and
control features, such as those found in HP Remote Management products (Insight
Manager 7, HP Integrated Remote Console, and Remote Insight Board and Remote
Insight Lights-Out Edition).
HP ProLiant Cluster HA/F500 for MA8000 Enhanced DT Supplement Guide 1-3
HP CONFIDENTIAL
Writer: Bill Akers File Name: b-ch1 Introduction
Codename: Chargers II Part Number: 324547-001 Last Saved On: 4/7/03 10:30 AM