Data centers

11:15 PM
Connect Directly
RSS
E-Mail
50%
50%

Atrato Enhances Data Analysis to Boost Storage Performance

Velocity array includes support for SSDs, and self-healing and data migration capabilities

Atrato, a relatively new storage array vendor, has upgraded its Velocity1000 multi-tier system to include support for solid-state disks, and enhanced its virtualization software to more effectively migrate data between tiers to improve performance.

Atrato is starting off supporting SSDs from Intel, but says it will support other vendors in the future. The array can support up to eight SSDs with up to 1.2 TB of data in the controller and can also support commodity Flash drives in a JBOF, or Just a Bunch of Flash, system that holds 10 SSDs that can scale over a SAN to 1.6 TB in a 1U expansion unit. The goal is to reduce the need for conventional RAM-based cache, which "is too small and too costly," says company chief technology officer Sam Siewert. "Scaling to a half terabyte of RAM would cost a fortune, and the management of RAM cache is not very precise or fast."

The company has enhanced its Atrato Virtualization Software to move data between Tier 0 SSDs and Tier 1 hard disks to improve performance -- by as much as 2X to 8X, Siewert says, adding that the system can deliver 60,000 IOPS. The software also can move data to archives to lower the cost per terabyte. The key, he says, is the ability to identify data that is frequently accessed and most recently accessed and to move that data to SSDs.

"By getting an accurate view of the workloads you can now size the Tier 0 Flash accurately so you can replicate high-access content into that tier. The software provides that analysis for you automatically," he says. "The integration of Flash allows the customer to scale performance without adding more spindles." Other data is stored on SAID, or a self-maintaining array of identical disks, that has 160 2.5-inch drives from Seagate and provides the Tier 1 storage.

Arun Taneja, founder of consulting firm Taneja Group says Atrato's ability to determine data usage patterns from seemingly random data could help in sorting data for placement on the various storage tiers to reduce latency. He also says the addition of self-healing and self-maintenance is a requirement in the current market.

Previous
1 of 3
Next
Comment  | 
Print  | 
More Insights
Cartoon
Hot Topics
7
VMware NSX Banks On Security
Marcia Savage, Managing Editor, Network Computing,  8/28/2014
5
How To Survive In Networking
Susan Fogarty, Editor in Chief,  8/28/2014
White Papers
Register for Network Computing Newsletters
Current Issue
2014 Private Cloud Survey
2014 Private Cloud Survey
Respondents are on a roll: 53% brought their private clouds from concept to production in less than one year, and 60% ­extend their clouds across multiple datacenters. But expertise is scarce, with 51% saying acquiring skilled employees is a roadblock.
Video
Slideshows
Twitter Feed