Earthweb
Images Events Jobs Premium Services Media Kit Network Map E-mail Offers Vendor Solutions Webcasts
   subjects:
EnterpriseStorageForum Webcasts:
Storage Is Changing Fast - Be Ready or Be Left Behind

more Webcasts...


Search EarthWeb Network


Find a Storage Term
 

internet.commerce
Be a Commerce Partner
Televisions
Promote Your Website
Web Design
Corporate Gifts
Online Education
Computer Hardware
Computer Deals
Web Hosting Directory
Best Price
Compare Prices
Auto Insurance Quote
Corporate Awards
Laptop Batteries
Domain registration

Download: Solaris 8 Migration Assistant Rapidly move your Solaris 8 application environments to new systems running Solaris 10 with the Solaris 8 Migration Assistant.
enterprisestorageforum.com : SANs/NAS : SANs/NAS Features: RAID Turns Rad

 
Putting the Data Center to the Test
Video: Watch as HP simulates a gas leak using real explosives to blow up a data center at a high-tech ballistics center. Every system failed-over after the explosion in less than two minutes including data on an HP StorageWorks XP12000 Disk Array, which failed over flawlessly to an HP StorageWorks XP24000 Disk Array. »
 
HP's Disaster Proof Solutions: Ensuring Application Availability
Whitepaper: Research indicates that 36 percent of enterprises indicate they will incur significant revenue loss or other adverse business impact if they have even an hour or less of downtime on their mission-critical applications. Almost 15 percent indicate they cannot tolerate any downtime. This whitepaper examines a field test of HP availability and recoverability solutions. »
 
Disaster-Proof Solutions E-Seminar
E-Seminar: Enterprise Strategy Group analyst Bob Laliberte takes a look HP's disaster-proof storage solutions and shares the results of the natural gas explosion test carried out at a high-tech ballistics center. »

Enterprise Storage Glossary
Fibre Channel
ILM
iSCSI
JBOD
NAS
RAID
SAN
SAS
SATA
Virtualization
Search for more storage terms ...
 
XML/RSS feeds

EarthWeb IT Management news and headlines
EnterpriseStorageForum Headlines
See more EarthWeb Network RSS feeds
FREE Tech Newsletters

RAID Turns Rad
March 12, 2008
By Jennifer Schiff

Last fall, Panasas, a developer of high-performance clustered storage solutions, unveiled a new "Tiered Parity" architecture that the company and some analysts said dramatically increases data reliability.

In addition to providing a more reliable solution to enterprises with large-scale data storage needs, Tiered Parity may also be heralding the beginning of the end to solutions based on "traditional," or single parity, RAID, and even those based on RAID 6, known as double parity RAID.

Classic RAID vs. New RAID

Tiered Parity renders old, non-Panasas RAID implementations obsolete, said Garth Gibson, the computer scientist and co-founder and CTO of Panasas, who pioneered RAID technology back in the late 1980s. That's because the original RAID technology mainly addressed the loss of complete disks, not media failures (also known as unrecoverable read errors or media faults) on one or more disks (see Gibson Discusses Learning from Storage Failures).

As Gibson explained, "RAID was a strategy for striping data over multiple fault domains and using inexpensive error-correcting codes across those fault domains so that we could recover from common storage failures, in particular the catastrophic loss of complete disks.

"In that era, the fault domain was a physical disk, and we striped the data logically one bit at a time across a fixed number of disks. What's happened since then is that we've realized that the simple striping one bit at a time across a fixed number of disks for all files in exactly the same pattern across storage is correct, but it is overspecialized."

It also doesn't address the problem of media failures, which grow proportionately with a disk's density. And with disks now 250 times denser than they were 20 years ago, when RAID first came on the scene, that's a big problem for enterprises and institutions that depend on high-performance computing and the secure storage and retrieval of terabytes of data. According to Panasas research, media failures occur approximately 30 times more often than disk failures, and a single media failure can cause a RAID reconstruction to fail.

Even powerful solutions such as RAID 6, said Gibson, are not up to the task.

"It [RAID 6] does a pretty good job of solving some of these problems, but it doubles the amount of parity and doubles the amount of work you do for small updates for particular classes of workloads," he said. "And it isn't as powerful as you'd like it to be because with RAID 6 if there are, in fact, two failed disks, you still have to deal with those media failures, because all RAID 6 really did was fix one failed disk and a media failure."

Put another way, RAID 6 treats the symptom of the failure, not the root cause — and can be expensive in terms of cost and lost performance.

Tiered Parity, on the hand, "is a set of novel solutions that ... improve the resistance to media failures, the silent hardware failures, and decrease the long reconstruction times that commercial commodity arrays are taking today," said Gibson.

So does this mean that the father of RAID has abandoned his first born? Yes and no. Tiered Parity, which makes use of RAID (specifically Panasas's ObjectRAID), is really "new and improved RAID," a fully grown, mature RAID, said Gibson, designed to address today's enterprise and institutional large-scale storage reliability needs.

So What Exactly Is 'Tiered Parity'?

Tiered Parity is a combination of three independent tiers, or solutions — Horizontal Parity, Vertical Parity and Network Parity — aimed at detecting and correcting problems before they cause a disk failure.

  • Horizontal Parity uses Panasas's ObjectRAID to provide protection from disk failure across the entire storage array. It also provides scalable RAID recovery, parallel reconstruction and per-file fault isolation.
  • Vertical Parity, a new technology from Panasas that can also be thought of as RAID within an individual drive, detects and fixes media errors on disks — the leading cause of failed RAID recovery operations — before the failure can interfere with RAID recovery.
  • Network Parity, which provides the industry's first end-to-end data integrity capability, detects errors introduced outside of an enterprise or institution's storage system.
According to Panasas, when used together (although sold bundled, tiers can be turned off or enabled, depending on the customer's needs), Tiered Parity, which is sold under the Panasas ActiveScale label, provides 10,000 times the protection of traditional RAID 5 — with no major performance hit.

Put another way, Tiered Parity is RAID, only better.

Back to Enterprise Storage Forum

Tools:
Add www.enterprisestorageforum.com to your favorites
Add www.enterprisestorageforum.com to your browser search box
IE 7 | Firefox 2.0 | Firefox 1.5.x
Receive news via our XML/RSS feed

SANs/NAS Features Archives

HP eBook: Using Business Service Management (BSM) to Manage Your Business Applications
Quest Whitepaper: Improving Oracle Database Performance Using Real-Time Visual Diagnostics
Best Practices: Make the Case for IT Investments. Complimentary Independent Report. Download Now!
Five Trends for Application Development & Program Management. Download Complimentary Report Now.
Whitepaper: HP Integrated Citrix XenServer for HP ProLiant Servers. Sponsored by HP, Citrix, and Intel.



JupiterOnlineMedia

internet.comearthweb.comDevx.commediabistro.comGraphics.com

Search:

Jupitermedia Corporation has two divisions: Jupiterimages and JupiterOnlineMedia

Jupitermedia Corporate Info


Legal Notices, Licensing, Reprints, & Permissions, Privacy Policy.

Advertise | Newsletters | Tech Jobs | Shopping | E-mail Offers

Solutions
Whitepapers and eBooks
Microsoft Article: HyperV-The Killer Feature in WinServer ‘08
Avaya Article: How to Feed Data into the Avaya Event Processor
Microsoft Article: Install What You Need with Win Server ‘08
HP eBook: Putting the Green into IT
Whitepaper: HP Integrated Citrix XenServer for HP ProLiant Servers
Intel Go Parallel Portal: Interview with C++ Guru Herb Sutter, Part 1
Intel Go Parallel Portal: Interview with C++ Guru Herb Sutter, Part 2--The Future of Concurrency
Avaya Article: Setting Up a SIP A/S Development Environment
IBM Article: How Cool Is Your Data Center?
Microsoft Article: Managing Virtual Machines with Microsoft System Center
HP eBook: Storage Networking , Part 1
Microsoft Article: Solving Data Center Complexity with Microsoft System Center Configuration Manager 2007
MORE WHITEPAPERS, EBOOKS, AND ARTICLES
Webcasts
Intel Video: Are Multi-core Processors Here to Stay?
On-Demand Webcast: Five Virtualization Trends to Watch
HP Video: Page Cost Calculator
Intel Video: APIs for Parallel Programming
HP Webcast: Storage Is Changing Fast - Be Ready or Be Left Behind
Microsoft Silverlight Video: Creating Fading Controls with Expression Design and Expression Blend 2
MORE WEBCASTS, PODCASTS, AND VIDEOS
Downloads and eKits
Sun Download: Solaris 8 Migration Assistant
Sybase Download: SQL Anywhere Developer Edition
Red Gate Download: SQL Backup Pro and free DBA Best Practices eBook
Red Gate Download: SQL Compare Pro 6
Iron Speed Designer Application Generator
MORE DOWNLOADS, EKITS, AND FREE TRIALS
Tutorials and Demos
How-to-Article: Preparing for Hyper-Threading Technology and Dual Core Technology
eTouch PDF: Conquering the Tyranny of E-Mail and Word Processors
IBM Article: Collaborating in the High-Performance Workplace
HP Demo: StorageWorks EVA4400
Microsoft How-to Article: Get Going with Silverlight and Windows Live
MORE TUTORIALS, DEMOS AND STEP-BY-STEP GUIDES