HPCwire: Active Archives: A Way to Tame the Data Monster

Since 1986 - Covering the Fastest Computers in the World and the People Who Run Them

HPCwire >> Features

April 28, 2010

Active Archives: A Way to Tame the Data Monster

by Michael Feldman, HPCwire Editor

Page: 1 of 2
1 | 2 All »

It seems like every information technology has its own industry trade group these days. The latest one to join the herd is the Active Archive Alliance, a group dedicated to pushing active archive solutions into the mainstream. The Alliance was announced this week with its founding members Compellent Technologies, FileTek, QStar Technologies, and Spectra Logic.

According to the latest IDC numbers, external storage is growing at an annual rate of 58 percent and estimated to reach a whopping 1610 exabytes by 2011. As a result, companies are scrambling to find places to keep their data, and keep it accessible. This is certainly true in HPC, where the size of datasets is growing in parallel with the computational power of supercomputers. In the enterprise, storage growth is just as epidemic. Between email, structured data of all types, multimedia files, and regulations that mandate new storage requirements, organizations are being overwhelmed.

The result is that datacenters are turning into spinning disk warehouses, with storage infrastructure gobbling up floor space, power, and IT budgets. One saving grace is that most of the data on primary storage -- perhaps as much as 75 to 85 percent of it -- does not need to be accessed frequently. That suggests that much of the data currently sitting on high-end disk drives can be migrated to much denser, less expensive, and less power-hungry storage systems. And that's where active archives come in.

The definition of an active archive is a little fluid, but the Alliance defines it as a storage system that contains production data, no matter how old or infrequently accessed, that can still be retrieved online. Essentially, it's a storage tier than sits between offline backup and primary storage. It could be based on tape or disk, but in either case the archive should be accessible through a file system, like NFS or CIFS.

It's this last feature that is at the center of the value proposition for active archives. Mounting a file system atop such a solution makes file access transparent to users, scripts, and applications. And even if access times are greater than the millisecond-level response you get from primary storage, the underlying software and the interface is still the same.

File systems, of course, are old technology, but not in the archive arena, especially for tape-based systems. "What is new is that there are applications now available that can extend the file system to tape, whereas historically file systems have relied on disk technologies," explains Molly Rector, vice president of marketing and product management at storage vendor Spectra Logic.

Spectra is one of the four founding members of the Active Archive Alliance and is positioning itself as the premier vendor for active archive solutions in the tape storage domain. Rector says a tape library five to 10 years ago would not have been an appropriate solution for this application, but scalability, performance, and reliability and data integrity have advanced to the point where tape-based active archives are now commercially viable.

The large HPC labs have actually been at the forefront of this technology and are leading the charge on archive tape libraries with a file system front-end. NASA Ames, for example, installed two Spectra tape libraries and increased its active archive storage capacity from 12 PB to 32 PB, recouping 1,400 square feet of datacenter space in the process. The future (2011) Blue Waters supercomputer at NCSA is also slated to include a 500 PB tape archive, fronted by a GPFS-HPSS interface.

But according to Rector, most other industries, and the majority of HPC users, are not even aware that such a capability exists. The Alliance's mission is to drive these solutions into the mainstream datacenter, and not just for petabyte-sized datasets either. There are plenty of organizations with terabytes of infrequently accessed files, but who have run out of room on their primary storage. In genomic research environments, for example, raw genetic data is being accumulated at a rate that outpaces any reasonable NAS or SAN deployment scheme. Since much of this data is not in constant use, it would seem to be an ideal app for a tape-based archive.

Archives are not just the tale of the tape, however. The other founding Alliance members -- Compellent Technologies, FileTek, and QStar Technologies -- offer a mix of disk-based and tape-based archiving solutions. Even Spectra has a disk-based product set, although for now the company is focused on its tape-based offerings for active archives. Panasas, although not part of the Alliance, recently launched, PAS HC, its disk-based NAS solution for archiving and scratch storage.

Page: 1 of 2
1 | 2 All »

Article Tools

Share Options

(Digg, Technorati, more)

Subscribe

Subscribe to HPCwire

Discussion

There are 0 discussion items posted.

RSS Feeds

Feeds by Topic

Feeds by Industry

Feeds by Content Type

Around the Web

The Mainstreaming of HPC

Sep 08 | Closing the gap between HPC and mainstream IT. Read more...

Data Mined for Love Connection

Sep 07 | Clues left on social media sites help singles find love. Read more...

Picking the Right Processor

Sep 03 | Should engineers take advantage of GPU computing? Read more...

HP, Hynix Start Memristor on Path to Commercialization

Sep 02 | Could see first products in three years. Read more...

TED Talks for the IT Crowd

Sep 01 | A hand-picked selection of video presentations from the TED conference -- because the next big thing has to start somewhere. Read more...

Read more headlines...

Featured Whitepapers

Breaking Through Real World Storage Barriers in Next Generation Sequencing

Jul 20 | | BlueArc's network storage systems are compelling solutions for the evolving and unpredictable needs of an NGS environment. They offer significant performance, scalability, utilization and cost benefits, while catering to the manageability needs of various users in a research organization.

Effective Backup and Restore

Jul 29 | | Panasas storage solutions deliver high throughput with many concurrent backup IO streams to standard backup applications such as Veritas NetBackup™ or EMC® NetWorker™. Download this whitepaper to understand the essential elements for effective backup and restore: the tape subsystem, networking, file system workload and administrative policy.

View the White Paper Library

Multimedia

Webcast: Are you drowning in data?

In this webinar you will hear about the current storage challenges facing the HPC community, how Panasas storage solutions provide exceptional performance, scalability, and manageability, and how you can achieve the lowest total Cost of Ownership with a system that installs and configures in 15 minutes.

Webcast: Virtualized Data Center Roundtable

Join this online panel discussion for live Q&A with leading industry experts, analysts, and end-users to discuss the latest innovations, best practices, barriers to implementation, and measurable benefits of server virtualization with a particular focus on today's real world solutions.

Webcast: Watch SC09 Birds of a Feather Video: Scalable Fault-Tolerant HPC Supercomputers

Learn about scalable fault-tolerant architectures and examples of energy efficient and scalable supercomputing clusters using dual QDR InfiniBand to combine capacity computing with network failover capabilities with the help of programming languages such as MPI and a robust Linux cluster management package.