This article can also be found in the Premium Editorial Download "Storage magazine: Distance: the new mantra for disaster recovery."
Download it now to read this article plus other related content.
Store objects on commodity hardware
Cluster File Systems, Inc., Mountain View, CA, is developing another new OO storage technology called Lustre (the name is a combination of Linux and Cluster) due out later this year. Lustre is an open-source high-performance cluster file system designed to store objects on commodity hardware.
Lustre handles files as objects, and separates its cluster file system operations from the actual storage of the object. The Lustre architecture is modular and consists of clients that interface over a network with both metadata servers (MDS) and object storage targets (OST). Metadata servers are responsible for managing all Lustre file system operations such as file creation and lookup and file metadata. When a new file is created, the MDS contacts an OST to create an object. The OSTs communicate with all clients and interface with the underlying physical storage devices to store information in object form.
According to Cluster File Systems, this design improves performance, data availability and system scalability. Additional storage devices may be added to the pool of available storage that an OST can access, and Lustre can accommodate new storage technologies as they become available. Lustre concurrently supports 10,000 clients and 1,000 of storage nodes. The initial implementations will scale to 100TB of storage capacity with data transfer rates of hundreds of
gigabytes per second.
Choosing a solution
With various fixed-content storage systems now available--and more to follow in the near future--storage managers face the challenge of choosing the right solution for their business requirements. Under standing how your information is used, accessed, shared and retained is the key to making the right decision. Typically, as with most IT decisions, users must not only consider how well the features and functions of a given solution address their individual needs, they must also consider system scalability, performance, ease of management and of course, price. Although the commercially available fixed-content storage solutions from EMC, Network Appliance, StorageTek and others are based on ATA disk arrays, they differ in approach and implementation.
Here's the Cliff Notes: IT managers willing to pay more for a content specific disk solution that offers flexible scalability and assurance of data immutability (non-erasable, non-rewriteable WORM) should consider EMC's Centera. Those interested in consolidating their fixed-content information on a low-cost storage repository should consider a Network Appliance NearStore system or StorageTek's BladeStore disk array. For policy-based management of information throughout its lifecycle--including integrated backup and long-term archive to secondary storage-- StorageTek's ASM/BladeStore solution. Alternatively, IT professionals should consider new storage technologies such as Lustre for building a flexible and scalable fixed-content storage repository, using low-cost commodity hardware, customized to meet their business requirements.
Robert Terdeman, CTO and senior VP of Rogers Medical Intelligence Solutions, New York, NY, implemented a fixed-content storage repository earlier this year. Rogers Medical publishes hundreds of custom reports per year that provide doctors with independent data and analysis on the latest clinical findings. "The savings in terms of business process time and energy by having a single consolidated content repository is huge," explains Terdeman. Terdeman's advice to others looking to implement a fixed-content solution is twofold: First, understand your data access characteristics and performance requirements. And secondly, ensure that all of the vendors involved completely understand your business requirements. Their solutions must be flexible and applications need to support a customized, integrated solution.
This was first published in May 2003