tiered storage: An underlying principle of ILM (information lifecycle management), tiered storage is a networked storage method where data is stored on various types of media, based on performance, availability and recovery requirements. For example, data intended for restoration in the event of data loss or corruption could be stored locally, for fast recovery, while data for regulatory purposes could be archived to lower cost disks. Over the past five years data storage requirements have grown at an exponential rate. While, the emergence of new technologies such as SAN (storage area networks), iSCSI, CAS  (content addressed storage) and the enhancements to many proven technologies like NAS (network attached storage) have pushed the industry in pursuit of the holy grail -- ILM. Today, organizations can take full advantage of SRM (storage resource management) tools to determine the value of their data and thereby establish the ideal storage medium for maximum cost savings.  With the widespread use of ATA technology and the integration of fibre channel and ATA into common architecture, users are now able to more effectively classify and target data. But pervasive regulations such as Sarbanes-Oxley, HIPPA and the Patriot Act that require organizations to maintain or destroy data, and guarantee authenticity are adding to the complexity of the task. These regulatory and compliance requirements have given rise to technologies like CAS and new WORM (write once, read many) devices.

Key Terms To Understanding Tiered Storage: SAN Storage Area Network (SAN) is a high-speed subnetwork of shared storage devices. iSCSI Internet SCSI, an IP-based standard for linking data storage devices over a network and transferring data by carrying SCSI commands over IP networks. content addressed storage An object-oriented system for storing data that are not intended to be changed once they are stored. NAS A network-attached storage (NAS) device is a server that is dedicated to nothing more than file sharing.

The push to do more with less has accelerated the need for many end-users to begin developing advanced ILM strategies. Data is growing and organizations need to manage much larger infrastructures with little or no additional head count. Tiered storage infrastructures provide operational efficiencies, regulatory compliance, cost savings and cost avoidance.

RPO and RTO
Faced with explosive data growth, maintaining online data is just the tip of the iceberg when assessing infrastructure requirements. Organizations should be assessing recovery point objectives (RPO) and recovery time objectives (RTO) to assist in architecting the appropriate tiered storage infrastructure.

Understanding the amount of data loss that is acceptable and the amount of time it would take to recover to that point is critical to architecting a strategically relevant storage infrastructure. Once an organization has classified their data using RPOs, RTOs, and regulatory requirements they can begin architecting a tiered storage infrastructure.

Today's tiered storage infrastructures range from simple two-tier architecture consisting of SCSI or fibre channel attached disk and tape to more complex infrastructures, which in some cases are comprised of five-to-six tiers. Regardless of the number of tiers, organizations are looking to tiered storage and ILM to lower cost and improve operational efficiency.

Implementing tiered storage infrastructures can dramatically decrease the cost associated with achieving an RPO and RTO of zero. Classification of data can provide different RPOs and RTOs based on application and business requirements.  Policy-based data migration ensures that the right data is in the right place at the right time.

More Than Money
The implications of tiered storage go far beyond cost savings. Organizations that use policy-based archiving also benefit from dramatically reduced backup and restore times. Organizations with aggressive RTO are leveraging ATA disk technology and virtual tape libraries as the primary backup target. Leveraging disk based backup solutions eliminates the latency associated with tape.

With continually shrinking backup windows and growing data requirements, organizations require technologies that provide high-speed data transfer. The advent of ATA disk technology provides a media that is cost competitive with tape and provides unparalleled price/performance ratio.

Content Addressable Storage
Organizations with regulatory and compliance requirements may look to technologies like CAS and WORM technology for long term retention and guaranteed authenticity.

Since CAS solutions are being delivered to the market as hardware-based appliances and software-based solutions, organizations should investigate the pluses and minuses of both solutions. CAS offerings are primarily targeted at environments that require guaranteed authenticity and/or long term archiving. Vendors employ proprietary and/or open standards to provide robust features such as self healing, authenticity and single instance data storage.

When data is stored on a CAS solution the intelligence embedded in the solution performs an operation to generate a unique identifier. This identifier can guarantee authenticity and facilitate single-instance storage.

Network Attached Storage
Many organizations are facilitating server consolidation by deploying NAS. Traditionally organizations have deployed servers with DAS (direct attached storage) as file servers. While this provided a good solution at one time, the proliferation of servers to accommodate CIFS and NFS storage requirements is now a management and economic nightmare. NAS provides a single purpose device that can provide CIFS and NFS connected storage that can scale from gigabyte to petabytes. Organizations can now begin to leverage NAS devices as part of the tiered infrastructure.

Migrating CIFS and NFS data from captive server attached storage to network attached devices can dramatically reduce cost by increasing utilization and decreasing management. Many NAS devices in the market now support both fibre channel, ATA disk drives and enhanced functionality for backup and restore.

While there are many choices in the marketplace today, the key to implementing a successful tiered storage infrastructure is to understand the value of your data.  Most hardware and software vendors are willing to spend the time helping organizations classify their data. Building tiered infrastructures can greatly improve operational efficiencies and reduce cost. Investing in a SRM (storage resource management) tool may also be worthwhile when assessing the cost and operational savings that a tiered infrastructure may provide.

Did You Know... Tiered storage provides a way to reduce IT infrastructure costs, meet application service levels and simplify storage management. [Source]

Richard Bocchinfuso
Article courtesy of CIO Update
Last updated: July 21, 2006

Forsythe: How to Build a Tiered Storage Infrastructure
When it comes to choosing technology, storage and systems administrators know that one-size-fits-all storage is not cost-effective for the obvious reason that high-end, high-performance storage is not practical for older or less frequently accessed information; the ROI and TCO just don’t add up. The goal is to design a storage hierarchy, or tiered storage infrastructure, that best meets your company’s information requirements.

Tiered Storage Economics (PDF)
Defining and Calculating the Economic Benefit of Tiered Storage Solutions. A White Paper by David R. Merrill

IBM: Building successful ILM solutions on a strong foundation of tiered storage
One benefit of tiered storage is the ability to take advantage of cost-effective storage. This means that you can place data that is rarely accessed on lower-end storage devices than information that is accessed constantly and is critical to the daily workings of your business.

Seagate: Tiered Storage Knowledge Center
Articles and deployment strategies for tiered storage solutions.

Enterprise Storage Forum: University Graduates to Tiered Storage
When it came to solving its data storage problems, the Haas School of Business at the University of California's Berkeley campus hit the books. What it learned was that the solution to more affordable storage was to implement a complementary iSCSI-based storage area network (SAN).

Zycko Case Study: Architecting a Tiered Storage Network
In this scenario, we examine the implications of tiered storage in a consolidated server and storage network, and how network aware SAN switches can provide the appropriate level of visibility and control to uphold the end-to-end data requirements for each storage tier.