Tip

SATA storage systems and the risk factor

Some of the main storage vendors have now begun offering serial ATA or parallel ATA based storage systems. There have been offerings from vendors less well known for a while but the offerings by the main vendors creates a higher comfort level for many customers, especially those in the enterprise data center space. The recent offerings for the main storage vendors include IBM and StorageTek with the new LSI Logic Storage Systems SATA storage. Previously released, EMC has offered ATA drive options in the CLARiiON product.

Probably one of the most important points to consider for these storage systems is the risk factor involved in deploying them. Certainly there's been quite a bit of discussion about reliability and performance and it is a simple fact that the drives don't have the same reliability or performance specifications as do the systems that use Fibre Channel drives.

There is also the concern of added administrative cost of managing an additional tier of disk storage. In this case, it is typically called secondary storage. The need for management of an additional tier is due to precisely the issues of performance and reliability. Having management software, specifically storage resource management software, controlling the placement of data on classes of storage based on policies is one of those developing areas that is seeing a great deal of activity.

The real risk factor to consider is one of stability of the product. A new storage system that

    Requires Free Membership to View

is a new implementation from the storage control standpoint takes a great deal of test time and invariably results in early field problems after it has been introduced. This is common and has been proven over and over again with new products. Quite simply, no test environment can reproduce all the possible customer usage cases so there will be problems after introduction. The problems decrease over time with the slope of the decline based on the complexity of the product and the number of resources the vendor applies to solving the problems.

The major vendors have addressed many of the risk factors with the introduction of the ATA-based storage systems by using the same controllers as their Fibre Channel-based storage systems. Generally, hardware control is added to convert from a Fibre Channel back end to serial or parallel ATA. Some additional code is required, usually for error isolation and recovery but the base functionality is the same as the products that have been shipping for some time. As examples, the IBM and STK products use the same controller functions as in the FASt and D-Series respectively which are provided by LSI Logic Storage Systems. EMC uses the same CLARiiON controller whether it has fibre channel drives or ATA drives. The other major storage vendors can be expected to have offerings soon.

By using the same controllers as in the Fibre Channel storage systems, the products should not have the same stability issues as a brand new implementation. That gives the customer greater confidence but also has value for the vendor as well. The engineering support costs should be much less with a common base. Subsequent development can be leveraged across both primary and secondary storage tiers. The component costs should be less with higher volumes that the combined base control function (and possibly drive module packaging) can produce.

All in all, using the Fibre Channel controllers as the starting point and translating the drive interface to ATA, whether serial or parallel, is a big win all the way around. The recent vendor announcements have confirmed that.


About the author: Randy Kerns is a partner at the Evaluator Group and is responsible for storage area network (SAN) and network-attached storage (NAS) analysis and education as well as company and product strategies. He has over twenty-eight years storage product development, including work for IBM, Fujitsu, Vice President of Engineering at the Array Technology subsidiary of Tandem Computers and Director of Engineering for Enterprise Disk at Storage Technology Corporation.

This was first published in December 2003

There are Comments. Add yours.

 
TIP: Want to include a code block in your comment? Use <pre> or <code> tags around the desired text. Ex: <code>insert code</code>

REGISTER or login:

Forgot Password?
By submitting you agree to receive email from TechTarget and its partners. If you reside outside of the United States, you consent to having your personal data transferred to and processed in the United States. Privacy
Sort by: OldestNewest

Forgot Password?

No problem! Submit your e-mail address below. We'll send you an email containing your password.

Your password has been sent to:

Disclaimer: Our Tips Exchange is a forum for you to share technical advice and expertise with your peers and to learn from other enterprise IT professionals. TechTarget provides the infrastructure to facilitate this sharing of information. However, we cannot guarantee the accuracy or validity of the material submitted. You agree that your use of the Ask The Expert services and your reliance on any questions, answers, information or other materials received through this Web site is at your own risk.