IBM eserver Cluster 1350, Installation And Service Manual

Page: 53 / 122

Chapter 8. Troubleshooting hardware and software problems
This chapter includes information to diagnose problems associated with the Cluster
1350. The Cluster 1350 is an integrated Linux cluster that includes IBM and third
party hardware and software components like server nodes and associated
firmware, storage and networking subsystems, plus Cluster Systems Management
(CSM) software and General Parallel File System (GPFS) software.
Problem resolution involves identifying the problem cluster component and following
the applicable problem resolution procedure for that component.
This chapter includes information for the diagnosis of problems down to the
component level. When a failing component is identified you can review the specific
product documentation for further actions. Links to applicable product Web sites
and online product documentation are provided in this chapter.
Diagnosing hardware and software problems in a cluster environment requires a
basic understanding of how the components of the Cluster 1350 function together.
The cluster consists of:
v One or more 19
″
racks.
v From 4 to 512 cluster nodes. The nodes are configured to execute customer
applications or provide other services required by the customer, such as, file
server, network gateway, or storage server.
v One management node (xSeries 345 or
Eserver
325) for cluster systems
management and administration.
v
A management Ethernet VLAN used for secure traffic for hardware control.
The management Ethernet VLAN is used for management traffic only. It is
logically isolated for security using the VLAN capability of the Cisco Ethernet
switches, and is only accessible from the management node. The cluster VLAN
and management VLANs share the same physical Cisco switches.
v A cluster VLAN used for other management traffic and user traffic. Cisco
switches integrated with the cluster are used for the management Ethernet VLAN
and the cluster Ethernet VLAN.
v Service processor networks. All nodes in the cluster are connected through serial
service processors (xSeries 335) and/or Remote Supervisor Adapter (RSA)
devices. The first node in a serial connection must have a Remote Supervisor
Adapter which is connected through the Ethernet to the management-Ethernet
VLAN.
v
A terminal server network for remote console, using the In-Reach LX-4000
(32-port, 48-port) terminal server. Optionally, the customer might elect to include
an additional network.
v
A high-performance Myrinet 2000 cluster interconnect, or an additional 10/100
Ethernet.
v
The customer can elect to configure a subset of cluster nodes with additional
external storage. This can also be a Fibre Channel solution (using a FAStT
storage subsystem).
v
A supported distribution of the Linux operating system.
v
Cluster management software, such as, CSM.
CSM maintains a database of configuration information (tab files) about the nodes
that are configured in the Cluster 1350. To display the node configuration
information, use the following CSM command on the management server console:
Isnode -Al
© Copyright IBM Corp. 2004
37