HP Serviceguard Cluster Configuration for HP-UX 11i or Linux Partitioned Systems, April 2009

ManualsBrandsHP ManualsSoftwareHP Serviceguard for Linux ProLiant Cluster

Abstract........................................................................................................................................2

Partition Configurations ...................................................................................................................2

Serviceguard design assumptions......................................................................................................4

Hardware redundancy.................................................................................................................4

Cluster membership protocol.........................................................................................................4

Quorum arbitration......................................................................................................................5

Partition interactions........................................................................................................................6

Cluster configuration considerations...................................................................................................7

Quorum arbitration requirements...................................................................................................7

Cluster configuration and partitions................................................................................................9

Cluster in a box..........................................................................................................................9

I/O considerations....................................................................................................................10

Latency considerations for vPars ..................................................................................................11

Latency considerations for Integrity Virtual Machines.......................................................................12

Other Linux differences..................................................................................................................12

Summary and conclusion...............................................................................................................12

For more information.....................................................................................................................13

HP Serviceguard Cluster Configuration for

HP-UX 11i or Linux Partitioned Systems

April 2009

Summary of content (13 pages)

PAGE 1
HP Serviceguard Cluster Configuration for HP-UX 11i or Linux Partitioned Systems April 2009 Abstract ........................................................................................................................................ 2 Partition Configurations ................................................................................................................... 2 Serviceguard design assumptions ................................................................................................
PAGE 2
Abstract HP Serviceguard provides an infrastructure for the design and implementation of highly available HPUX or Linux clusters that can quickly restore mission-critical application services after hardware or software failures. To achieve the highest level of availability, clusters must be configured to eliminate all single points of failure (SPOFs). This requires a careful analysis of the hardware and software infrastructure used to build the cluster.
PAGE 3
The partitioning provided by nPartitions—available in HP-UX 11i v2 and HP-UX 11i v3—is done at a hardware level and each partition is isolated from both hardware and software failures of other partitions. vPars partitioning and Integrity VM are implemented at a software level. This provides greater flexibility in dividing hardware resources as shown in Figure 1. Figure 1.
PAGE 4
Figure 2. Sample of combined nPartitions and vPars configurations Serviceguard design assumptions To best understand issues related to using partitioning within the cluster, it is helpful to start with a review of the Serviceguard design philosophy and assumption, including hardware redundancy, cluster membership protocol, and quorum arbitrations. Hardware redundancy Serviceguard, like all other high-availability (HA) clustering products, uses hardware redundancy to maintain application availability.
PAGE 5
After a failure that results in loss of communication between the nodes, active cluster nodes execute a cluster re-formation algorithm that is used to determine the new cluster quorum. This new quorum, in conjunction with the previous quorum, is used to determine which nodes remain in the new active cluster. The algorithm for cluster re-formation generally requires a cluster quorum of a strict majority—more than 50% of the nodes that were previously running.
PAGE 6
• Through a quorum service, for Serviceguard clusters of any size or type. Quorum services are provided by a quorum server process running on a machine outside of the cluster. The quorum server listens to connection requests from the Serviceguard nodes on a known port. The server maintains a special area in memory for each cluster, and when a node obtains the cluster lock, this area is marked so that other nodes will recognize the lock as “taken.
PAGE 7
systems, while maintaining a third VM Host system for backup. Should one or more active applications fail, they can fail over to the backup VM Host system, which has the capacity to run all the guests at one time if necessary. The backup system might have limited performance but the applications would resume operation after a hardware failure. 3.
PAGE 8
the possibility of a complete cluster failure. This configuration is discussed in the section “Cluster in a box.” Figure 3. Unsupported configuration Rule 2. Configurations containing the potential for a loss of exactly 50% of the membership resulting from a single failure require the use of quorum arbitration.
PAGE 9
Figure 4. A 4—node cluster from two Superdomes with quorum server Cluster configuration and partitions Given the configuration requirements described in Rules1 and 2, a few interesting observations can be made of clusters utilizing partitioning: • If it is determined that a cluster lock is needed for a particular configuration, the cluster must be configured so the cluster lock is isolated from failures affecting the cluster nodes.
PAGE 10
up exclusively of nPartitions since an nPartition is isolated from hardware and software failures of other nPartitions. Figure 5. Cluster-in-a-box configuration I/O considerations Serviceguard does not treat OS instances running in a nPar or vPar any differently than those running on an independent node. Thus, partitions do not provide any exemptions from the normal Serviceguard connectivity rules (such as redundant paths for heartbeat networks, and to storage) nor do they impose any new requirements.
PAGE 11
interface cards for the heartbeat LANs. Assuming that combination Fibre Channel/network cards are not used, each partition would require a minimum of four interface cards. To support a 2 partition cluster-in-a-box the system would need to have a total of eight I/O slots. The use of “combination” cards that combine both network and storage can help in some situations.
PAGE 12
Latency considerations for Integrity Virtual Machines With Integrity Virtual Machines there is a risk that a heavy processing load will cause Serviceguard to lose cluster heartbeats and trigger a cluster-reformation or node failure. If you encounter this situation, adjust the Serviceguard NODE_TIMEOUT or MEMBER_TIMEOUT upwards. This can result in longer failover times.
PAGE 13
For more information To learn more about HP Serviceguard Solutions for HP-UX 11i, please visit: www.hp.com/go/serviceguardsolutions To learn more about HP Serviceguard Solutions for Linux, please visit: www.hp.com/go/sglx For technical documentation: www.docs.hp.com/hpux/ha © Copyright 2009 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice.