Enhanced Stretched Cluster Architecture for Continuous Availability Platform

Business continuity and continuous application availability are among the top requirements for many organizations today. Advances in virtualization, storage, and networking make enhanced business continuity possible. Information technology solutions can now be designed to manage both planned and unplanned outages, and to take advantage of the flexibility, efficient use of resources, and cost savings that are available from cloud computing…

PowerM Solution : IBM SAN Volume Controller /IBM Spectrum Virtualize

1. IBM Spectrum Virtualize:

IBM Spectrum Virtualize and SAN Volume Controller is a storage virtualization system that enables a single point of control for storage resources. It helps improve business application availability and greater resource use. The objective is to manage storage resources in your IT infrastructure and to ensure that they are used to the advantage of your business. These processes take place quickly, efficiently, and in real time, while avoiding increases in administrative costs.

IBM Spectrum Virtualize and SAN Volume Controller supports attachment to servers through Fibre Channel (FC) protocols and Internet Small Computer System Interface (iSCSI) protocols over IP networks at 1 Gbps and 10 Gbps speeds. These configurations can help reduce costs and simplify server configuration. Spectrum Virtualize also supports Fibre Channel over Ethernet (FCoE) protocol.

IBM Spectrum Virtualize and SAN Volume Controller combines hardware and software in an integrated, modular solution that is highly scalable. An I/O group is formed by combining a redundant pair of storage engines that are based on IBM System x server technology. Highly available I/O groups are the basic configuration element of a Spectrum Virtualize cluster.

The configuration flexibility means that your implementation can start small and grow with your business to manage very large storage environments. The scalable architecture and tight integration enable your business to take advantage of the high throughput of solid-state drives (SSDs). This configuration supports high performance for critical applications.

Figure 1: Overview of SVC clustered system with I/O Group

Improving data value

  • Improves efficiency of your storage, increasing utilization up to double
  • Increases amount of data you can store, enabling up to 5x as much data to be stored in the same space
  • Improves storage performance so you can get more done with your data
  • Optimizes storage use by moving data to the most appropriate type of storage based on policies you define with IBM Spectrum Control

Increasing data security

  • Improves data security with software based encryption
  • Improves data protection with 5-10x faster rebuild of data following a drive failure
  • Improves data availability with fully duplexed copies of data and automatic switchover across data centers
  • Eliminates storage downtime with nondisruptive movement of data from one type of storage to another

Enhancing data simplicity

  • Improves agility with automated provisioning of storage as it is required by applications, integration with virtualization tools such as VMware vCenter, and easy deployment of new storage technologies
  • Consolidates all your storage – no matter the vendor – for simplified management, consistent functionality, and greater efficiency
  • Enables flexibility in storage acquisition by supporting common capability across all types of storage so you can mix vendors with ease

2. Enhanced Stretched Cluster:

The stretched cluster is an extended High Availability (HA) method supported by SAN Volume Controller to enable I/O operations to continue after the loss of half of the system. This is also sometimes referred to as a split cluster because one half of the cluster and I/O group is usually in a geographically distant location from the other; often 10 kilometers or more. A third site is required to host a controller that provides a quorum disk.

The main benefits of using stretched clusters are the following:

  • In addition to the automatic failover that occurs when a site fails in a standard stretched cluster configuration, an enhanced stretched cluster provides an additional manual override that can be used to choose which of two sites continues operation.
  • Enhanced stretched clusters intelligently route I/O traffic between nodes and controllers to reduce the amount of I/O traffic between sites, and to minimize the impact to host application I/O latency
  • Enhanced stretched clusters include an implementation of additional policing rules to ensure the correct configuration of a standard stretched cluster

Combining stretched cluster configurations with the Volume Mirroring capability provides a continuous availability platform whereby host access is maintained during the loss of any single location.

With the stretched cluster configurations, the two nodes in an I/O group are separated by the distance between two locations. If a copy of the volume is stored at each location, you can lose either the SAN or power at one location, and access to the disks remains available at the alternate location. Using this behavior requires clustering software at the application and server layer to fail over to a server at the alternate location and resume access to the disks.

Figure 2: Spectrum Virtualize Enhanced Stretched Cluster: No ISL configuration (with WDM)

6. Detailed reference architecture:

Need more information about this reference architecture? Send us email : refarchitect@powerm.ma


7. Reference

  • IBM System Storage SAN Volume Controller and Storwize V7000 Best Practices and Performance Guidelines SG24-7521-04
  • Implementing the IBM System Storage SAN Volume Controller with IBM Spectrum Virtualize V7.8 SG24-7933-05