IBM Storage Scale cluster configurations

An IBM Storage Scale cluster can be configured in various ways. The cluster can be a heterogeneous mix of hardware platforms and operating systems.

IBM Storage Scale clusters can contain a mix of all supported node types including Linux®, AIX®, and Windows Server and these operating systems can run on various hardware platforms, such as IBM® POWER®, x86-based servers, and IBM Z®. These nodes can all be attached to a common set of SAN storage or through a mix of SAN and network attached nodes. Nodes can all be in a single cluster, or data can be shared across multiple clusters. A cluster can be contained in a single data center or spread across geographical locations. To determine which cluster configuration is best for your application, start by determining the following:
  • Application I/O performance and reliability requirements.
  • Properties of the underlying storage hardware.
  • Administration, security, and ownership considerations.

Understanding these requirements helps you determine which nodes require direct access to the disks and which nodes must access the disks over a network connection through an NSD server.

There are four basic IBM Storage Scale configurations:
  • When all nodes are attached to a common set of Logical Unit Numbers (LUNs).
  • When some nodes are NSD clients.
  • When a cluster is spread across multiple sites.
  • When data is shared between clusters.

All nodes attached to a common set of LUNs

In this type of configuration, all of the nodes in the cluster are connected to a common set of LUNs (for example, over a SAN). The following factors must be considered while defining this configuration:
  • The maximum number of nodes accessing a LUN that you want to support.
  • You cannot mix different operating systems with IBM Storage Scale to directly access the same set of LUNs on SAN.
For example, see Figure 1.
Figure 1. A cluster with disks that are SAN-attached to all nodes
This figure shows a cluster with four nodes that have direct SAN attachment to a common set of disks.

Some nodes are NSD clients

In this type of configuration, only some nodes are connected to disks. Other nodes access the disks using the NSD path.

For an example, see Figure 2.
Figure 2. A cluster with some nodes connected to disks
This figure shows a cluster with some nodes connected to disks.

IBM Storage Scale servers and clients

You can configure an IBM Storage Scale cluster in which some nodes have a direct attachment to the disks and others access the disks through other IBM Storage Scale nodes. This configuration is often used in large clusters or to provide a cost effective and high-performance solution.

When an IBM Storage Scale node is providing access to a disk for another IBM Storage Scale node, the node that provides access is called an NSD server. The node that accesses the data through an NSD server is called an IBM Storage Scale client.

Sharing data across multiple IBM Storage Scale clusters

IBM Storage Scale allows you to share data across multiple IBM Storage Scale clusters. After a file system is mounted in another IBM Storage Scale cluster, all access to the data is the same as if you were in the host cluster. You can connect multiple clusters within the same data center or across long distances over a WAN. In a multicluster configuration, each cluster can be placed in a separate administrative group simplifying administration or provide a common view of data across multiple organizations.
Figure 3. A multicluster configuration
This figure shows a multicluster configuration.
Note: For more information, see Accessing a remote GPFS file system.