IBM aims for better disaster recovery

IBM has enhanced its popular data pooling and storage virtualization software to include business continuity and disaster recovery capabilities, as well as faster performance and support for more storage platforms. The company also recently announced that more than 2,000 customers now use its storage virtualization software.

IBM is adding 4Gbps Fibre Channel support, increased interoperability with a variety of disk systems and asynchronous replication capability to its TotalStorage SAN Volume Controller (SVC), letting customers support faster Fibre Channel storage-area networks and protect data on storage systems.

The SVC software runs on a cluster of x86-based IBM computers attached to Brocade Communications, McData and Cisco Fibre Channel switches, where it can manage data on those storage systems. It creates pools of disks from those storage systems, which can be mapped to a set of virtual disks for use by host server applications. These applications may be the migration of data for information life-cycle management purposes or the replication of data for business continuity.

The new version, SVC 4.1, includes a global mirroring function that lets customers replicate data across locations of greater than 100 miles. Global Mirror, which has no distance limitations, is based on IBM’s synchronous Metro Mirror technology, which supports replication distances of only 100 miles. Because Global Mirror is asynchronous and supports longer latencies, longer-distance replication is possible.

“The latest version of IBM SVC brings good news to those who need to support data protection for business continuity and disaster recovery over long distances with asynchronous remote mirroring and replication,” says Greg Schulz, senior analyst for StorageIO.

“The support for asynchronous replication will enable SVC nodes to leverage IP and WAN network interfaces natively without having to rely upon external third-party asynchronous technologies such as McData’s UltraNet Edge Storage Router,” Schulz says.

IBM says global mirroring is important because of natural disasters such as Hurricane Katrina that can cause damage over more than 100 miles.

In addition, Global Mirror and Metro Mirror do not require the same storage arrays at both locations, allowing customers to deploy older storage at the secondary disaster recovery site. For instance, a customer may replicate data between an IBM TotalStorage DS4800 at the primary site and an older EMC Symmetrix at the secondary site.

SVC 4.1 also supports 4Gbps Fibre Channel environments and more than 80 disk systems, including Hitachi’s TagmaStore, the IBM DS4700 and the OpenVMS operating environment.

Further, SVC lets customers replace nodes in the SVC cluster with newer ones without disrupting access to data.

The use of storage virtualization products such as IBM’s SVC is on the rise. An IDC study shows that vendors such as IBM, FalconStor and EMC shipped more than 28 petabytes of virtualization software and appliances in 2005, a more than fourfold increase over 2004.

IBM’s SVC competes with EMC’s Invista and the built-in virtualization capabilities of Hitachi’s TagmaStore Universal Storage Platform. Although EMC’s Invista does not have asynchronous replication capability, the company is expected to build it in with its acquisition of Kashya, a remote replication vendor.

Related Download
3 reasons why Hyperconverged is the cost-efficient, simplified infrastructure for the modern data center Sponsor: Lenovo
3 reasons why Hyperconverged is the cost-efficient, simplified infrastructure for the modern data center
Find out how Hyperconverged systems can help you meet the challenges of the modern IT department. Click here to find out more.
Register Now