System high availability

A system has several features that can be used to deploy a high-availability storage system with no single point of failure.

Volume mirroring provides protection against a storage system failure by mirroring data across storage systems. For example, for disaster recovery, the Metro Mirror and Global Mirror features can be used to mirror data between systems at different physical locations.

Each I/O group within a system consists of a pair of node canisters. If a node fails within an I/O group, the other node canister in the I/O group assumes the I/O responsibilities of the failed node canister.

The control enclosure contains a pair of node canisters. If one node canister fails, then the other node canister assumes the I/O and management responsibilities of the failed node canister.

Each node canister has redundant host attachment ports. For high availability, use these ports to make at least two independent connections between each host system and each node canister. Systems support the following host attachment options.

For example, when you use Fibre Channel SAN-attached hosts, attach the node canisters to at least two SAN fabrics, and attach each host system to both fabrics.

Configure any Fibre Channel host systems to use multipathing software. If a SAN fabric fault or node canister failure occurs, then I/O operations among Fibre Channel host systems and the node canisters are tried again. Subsystem Device Driver (SDD) multipathing software is available from IBM at no additional charge for use with the system. For additional information about Subsystem Device Driver (SDD), go to the Support for IBM Systems website.

Each node has four optionalFibre Channel ports, which can be used to attach the node to multiple SAN fabrics. The system software incorporates multipathing software to communicate with the nodes. This software is also used for I/O operations among the node and storage systems. If a SAN fabric fault disrupts communication or I/O operations, the multipathing software recovers and tries the operation again through an alternative communication path. For high availability, configure your Fibre Channel host systems to use multipathing software. If a SAN fabric fault or node failure occurs, I/O operations among Fibre Channel host systems andnode are tried again. Subsystem Device Driver (SDD) multipathing software is available from IBM at no additional charge for use withthe system. For more information about Subsystem Device Driver (SDD), go to the Support for IBM Systems website and enter the product name in the Product Finder field.

ibm.co/U06Fbb

SAS and iSCSI-attached hosts connect to the system through node Ethernet ports. If a node fails, the system fails over the IP addresses to the partner node in the I/O group to maintain access to the volumes.