Spectra Tape Plays to Cloud, Big Data, HPC Communities

By Tiffany Trader

November 4, 2011

In the past decade, the prevailing wisdom would have you believe that tape storage was a dead or dying breed, soon-to-be usurped by the sexier, speedier disk. Now that particular hype cycle has run its course and logic and common sense have returned to the storage conversation, prodded no doubt by a the latest buzzwords du jour, big data and cloud computing. At any rate, there’s no doubt that tape storage is as relevant as ever, and perhaps more relevant than ever. Indeed, this was the prevailing theme circulated by a group of prominent storage analysts at a recent Spectra Logic event in Boulder, Colo.

Spectra's expanded campusIn 2009 Spectra celebrated its 30-year anniversary, and like its storage capacity, Spectra is also expanding. Their fiscal 2011 figures reflected a 30 percent YoY growth overall and Spectra’s enterprise tape libraries posted revenue growth of 49 percent in the same period. Growth like that explains why the company recently outgrew their office, lab and manufacturing space for the second time in three years. But they won’t be cramped for long; they just purchased a 55,000-square-foot building in downtown Boulder next door to the 80,712-square-foot building they acquired in 2009.

It’s no surprise that data growth is exploding. In 1999, humankind had amassed 11 exabytes of digital information. By 2010 the figure had jumped to over 1 zettabyte. In light of this exponential growth, it’s imperative that data-intensive markets adopt storage solutions that demonstrate reliability, density, scalability and energy efficiency. They will also need tools to extract value from all this created and stored data.

Spectra Logic T-FinityOn the occasion of a big Spectra announcement earlier this week, Addison Snell, CEO of Intersect360 Research, explained that “the ‘Big Data’ trend is driving technology requirements in applications ranging from enterprise datacenters to academic supercomputing labs.” He went on to say that “the next generation of exascale data will require capabilities that not only provide sufficient capacity, but also deliver the speed, reliability, and data integrity features to match the needs of these environments.”

Consider these statistics (source: Making IT Matter – Chalfant/Toigo, 2009):

  • Up to 70 percent of capacity of every disk drive installed today is misused.
  • 40 percent of data is inert.
  • 15 percent is allocated but unused.
  • 10 percent is orphan data.
  • 5 percent is contraband data.

Currently, disk storage makes up between 33 and 70 cents of every dollar spent on IT hardware, and this trend is accelerating.

Before delving into tape’s role in the cloud space, it’s helpful to first review the major storage categories:

  • Backup: enables restoration of the most recent clean copy of the primary dataset available.

  • Archive: a repository designed to store, retain, and preserve data over time, regardless of its relation to the primary dataset.

  • Active Archive: An archive that manages both production and archive data in an online-accessible environment across multiple storage mediums including disk and tape.

It may seem obvious, but it’s important to point out that the value of data changes over time. With backup data, the information is more valuable today than it will be a month from now. Consider files stored on a computer that you will use to deliver a presentation five minutes from now. What if the data was lost or corrupted? With archive data, on the other hand, the value is measured over time. As our data habit grows, so does the need to prioritize it.

At the Spectra Logic event, which took place at the end of October, Chief Marketing Officer Molly Rector delivered a presentation on the state of the tape market, in which she shared the 2011 INSIC Tape Applications report. It looks at the ways tape is evolving to keep pace with the business realities of the 21st century:

“Tape has been shifting from its historical role of serving as a medium dedicated primarily to short-term backup, to a medium that addresses a much broader set of data storage goals, including:

Active archive (the most promising segment of market growth).

Regulatory compliance (approximately 20% – 25% of all business data created must be retained to meet compliance requirements for a specified and often lengthy period).

Disaster recovery, which continues in its traditional requirements as a significant use of tape.”

Rector explained that for practical reasons, a copy of all or most data stored in the cloud on disk is typically migrated to tape, if only for the extra reliability that tape provides. Tape is also used in cloud storage environments for the cost savings it confers.

Spectra slide - disk versus tape

Many people are naturally going to associate cloud storage with online storage, with spinning disks, but in reality most data that is created in or by the cloud will end up in a tape storage mechanism. In this video, Mark Peters, Senior Analyst for Enterprise Strategy Group, examines how tape’s role in the cloud parallels its importance in traditional IT. He details the following benefits:

  • Low CAPEX and OPEX cost per GB.
  • Reliable long-term storage with great media longevity and support for multiple media types.
  • It’s verifiable, searchable and scalable (with an active archive solution).

In Peters’ words, “[tape] remains the ultimate backup, and increasingly archival, device.” He goes on to note that tape is especially relevant for cloud in the areas of tiering and secure multi-tenancy, that is the sharing resources but not data. Keeping data secure is particularly important since privacy is cited as one of the major concerns with cloud. Portability is yet another plus for organizations looking to seed an offsite location, execute bulk DR restores, and even serves as an exit strategy to return data to a customer.

Active archiving is a major part of Spectra’s strategy to fulfill the requirements of an increasingly cloud-centered computing infrastructure. In an active archive, all production data, no matter how old or infrequently accessed, can still be retrieved online. According to company literature, Spectra’s Active Archive platform, announced in April 2010, offers cost-effective, online, file-based solutions that enable user access to all created data. With it, a petabyte of data can be presented as if it were a C drive. Additionally, management is simplified; business users simply set SLAs with their customers on the time to data, which may be 90-120 seconds coming from tape, or 2-3 seconds with a disk array.

Spectra slide - reduce overall data volumes
Spectra slide - before archiving
Spectra slide - after archiving
    Click on image to enlarge.

Archiving also reduces overall data volumes. It can turn 2.6 petabyte of data into 760 MB of managed data (as explained further in the set of slides on the right) and when you look at acquisition and energy costs, tape comes out ahead (as illustrated in the first slide). There are also financial and personnel costs involved with migration. Following best practices involves migrating data every 7 ½ years to new media in the same library with tape, or moving data to a new disk array every 3 – 4 years. As for portability, the quickest way to transport a petabyte of data is to send it through the air in a jumbo jet.

It certainly seems that Spectra is positioning itself as a big data storage provider, which it also refers to as exabyte storage. To that end, Spectra just announced a high-capacity T-Finity enterprise tape library capable of storing more than 3.6 exabytes of data. This represents the world’s largest data storage system – providing the highest capacity single library and the highest capacity library complex. A single T-Finity library will now expand to 40 frames for a capacity of up to 50,000 tape cartridges, and in a library complex, up to eight libraries can be clustered together for a capacity of up to 400,000 tape cartridges.

The jumbo storage solution will run the company’s recently-upgraded BlueScale management software, the latest version of which, BlueScale 12, delivers 35 to 60 percent faster robotic performance across Spectra’s enterprise and mid-range tape libraries, plus 15 to 20 times quicker library ‘power on’ times, as well as improved barcode scanning times. Another new advance, the Redundant Arrays of Independent Tapes (RAIT) architecture, developed with Spectra partner HPSS, “significantly improves data reliability in high performance, big data environments,” according to Jason Alt, senior software engineer, National Center for Supercomputing Applications.

Chairman, CEO and Founder Nathan C. Thompson originally designed Spectra’s storage systems for high-density, not speed, but customers were not willing to make that tradeoff, explains Rector. Active archiving strikes a balance between keeping data visible in online disk arrays and moving the data to more cost-effective near-line or off-line tape.

So who needs all that storage? Spectra sees this solution as a natural fit for a wide range of communities, from medicine and genomics to nuclear physics and petroleum exploration, in addition to supercomputing, media and entertainment, Internet storage, surveillance and, of course, cloud computing. As an interesting side note, when it comes to archiving data, Spectra notes that the general enterprise can archive about 80 percent of its data, but with HPC this figure is closer to 90-95 percent.

Spectra has well over 150 petascale-class customers, including Argonne National Laboratory, NCSA, NASA and Entertainment Tonight, as well as many that do not want to be named. Whether storing petabytes or exabytes, value and density are paramount. Organizations looking to meet their specific storage ought to be concerned with finding the right balance of speed, density and cost. Then there’s the long-term outlook: scalability. Tape libraries can stay active for 10 years, 15 years, or longer, incorporating new technologies as they become available.

Of course tape is not an all or nothing proposition, in most instances, a tiered storage approach provides an optimal cost/benefit profile, a concept summarized by Chris Marsh, Spectra’s IT market and development manager:

Cloud storage providers often implement a tiered storage approach that provides upfront performance to customers via performance disk, while relying on tape storage on the back end. This is an effective way of meeting their customers’ requirements and driving more profitability for their organization. So, regardless of whether it’s a business or technology decision, tape adds value to cloud storage and should be considered when reviewing any specific cloud storage service provider.

Marsh wrote an in-depth 3-part feature on the value of tape for cloud storage providers. In it, he lists the key characteristics for a cloud service, including multi-tenancy, security, data integrity verification, retrieval expectations, and exit strategies.

For anyone wondering why this shift is happening now and not sooner, the simple answer is there wasn’t this much data before! There is a belief that data is growing faster than storage capacity, so we need a shift, one that includes more optimal efficiencies that give users access to the data they need, when they need it, and does so in a reliable, cost-effective, and energy-efficient manner.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Geospatial Data Research Leverages GPUs

August 17, 2017

MapD Technologies, the GPU-accelerated database specialist, said it is working with university researchers on leveraging graphics processors to advance geospatial analytics. The San Francisco-based company is collabor Read more…

By George Leopold

Intel, NERSC and University Partners Launch New Big Data Center

August 17, 2017

A collaboration between the Department of Energy’s National Energy Research Scientific Computing Center (NERSC), Intel and five Intel Parallel Computing Centers (IPCCs) has resulted in a new Big Data Center (BDC) that Read more…

By Linda Barney

Google Releases Deeplearn.js to Further Democratize Machine Learning

August 17, 2017

Spreading the use of machine learning tools is one of the goals of Google’s PAIR (People + AI Research) initiative, which was introduced in early July. Last week the cloud giant released deeplearn.js as part of that in Read more…

By John Russell

HPE Extreme Performance Solutions

Leveraging Deep Learning for Fraud Detection

Advancements in computing technologies and the expanding use of e-commerce platforms have dramatically increased the risk of fraud for financial services companies and their customers. Read more…

Spoiler Alert: Glimpse Next Week’s Solar Eclipse Via Simulation from TACC, SDSC, and NASA

August 17, 2017

Can’t wait to see next week’s solar eclipse? You can at least catch glimpses of what scientists expect it will look like. A team from Predictive Science Inc. (PSI), based in San Diego, working with Stampede2 at the Read more…

By John Russell

Microsoft Bolsters Azure With Cloud HPC Deal

August 15, 2017

Microsoft has acquired cloud computing software vendor Cycle Computing in a move designed to bring orchestration tools along with high-end computing access capabilities to the cloud. Terms of the acquisition were not disclosed. Read more…

By George Leopold

HPE Ships Supercomputer to Space Station, Final Destination Mars

August 14, 2017

With a manned mission to Mars on the horizon, the demand for space-based supercomputing is at hand. Today HPE and NASA sent the first off-the-shelf HPC system i Read more…

By Tiffany Trader

AMD EPYC Video Takes Aim at Intel’s Broadwell

August 14, 2017

Let the benchmarking begin. Last week, AMD posted a YouTube video in which one of its EPYC-based systems outperformed a ‘comparable’ Intel Broadwell-based s Read more…

By John Russell

Deep Learning Thrives in Cancer Moonshot

August 8, 2017

The U.S. War on Cancer, certainly a worthy cause, is a collection of programs stretching back more than 40 years and abiding under many banners. The latest is t Read more…

By John Russell

IBM Raises the Bar for Distributed Deep Learning

August 8, 2017

IBM is announcing today an enhancement to its PowerAI software platform aimed at facilitating the practical scaling of AI models on today’s fastest GPUs. Scal Read more…

By Tiffany Trader

IBM Storage Breakthrough Paves Way for 330TB Tape Cartridges

August 3, 2017

IBM announced yesterday a new record for magnetic tape storage that it says will keep tape storage density on a Moore's law-like path far into the next decade. Read more…

By Tiffany Trader

AMD Stuffs a Petaflops of Machine Intelligence into 20-Node Rack

August 1, 2017

With its Radeon “Vega” Instinct datacenter GPUs and EPYC “Naples” server chips entering the market this summer, AMD has positioned itself for a two-head Read more…

By Tiffany Trader

Cray Moves to Acquire the Seagate ClusterStor Line

July 28, 2017

This week Cray announced that it is picking up Seagate's ClusterStor HPC storage array business for an undisclosed sum. "In short we're effectively transitioning the bulk of the ClusterStor product line to Cray," said CEO Peter Ungaro. Read more…

By Tiffany Trader

Nvidia’s Mammoth Volta GPU Aims High for AI, HPC

May 10, 2017

At Nvidia's GPU Technology Conference (GTC17) in San Jose, Calif., this morning, CEO Jensen Huang announced the company's much-anticipated Volta architecture a Read more…

By Tiffany Trader

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

Quantum Bits: D-Wave and VW; Google Quantum Lab; IBM Expands Access

March 21, 2017

For a technology that’s usually characterized as far off and in a distant galaxy, quantum computing has been steadily picking up steam. Just how close real-wo Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

Russian Researchers Claim First Quantum-Safe Blockchain

May 25, 2017

The Russian Quantum Center today announced it has overcome the threat of quantum cryptography by creating the first quantum-safe blockchain, securing cryptocurrencies like Bitcoin, along with classified government communications and other sensitive digital transfers. Read more…

By Doug Black

HPC Compiler Company PathScale Seeks Life Raft

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its a Read more…

By Tiffany Trader

Trump Budget Targets NIH, DOE, and EPA; No Mention of NSF

March 16, 2017

President Trump’s proposed U.S. fiscal 2018 budget issued today sharply cuts science spending while bolstering military spending as he promised during the cam Read more…

By John Russell

Leading Solution Providers

Groq This: New AI Chips to Give GPUs a Run for Deep Learning Money

April 24, 2017

CPUs and GPUs, move over. Thanks to recent revelations surrounding Google’s new Tensor Processing Unit (TPU), the computing world appears to be on the cusp of Read more…

By Alex Woodie

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

In this contributed perspective piece, Intel’s Jim Jeffers makes the case that CPU-based visualization is now widely adopted and as such is no longer a contrarian view, but is rather an exascale requirement. Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

Google Debuts TPU v2 and will Add to Google Cloud

May 25, 2017

Not long after stirring attention in the deep learning/AI community by revealing the details of its Tensor Processing Unit (TPU), Google last week announced the Read more…

By John Russell

MIT Mathematician Spins Up 220,000-Core Google Compute Cluster

April 21, 2017

On Thursday, Google announced that MIT math professor and computational number theorist Andrew V. Sutherland had set a record for the largest Google Compute Engine (GCE) job. Sutherland ran the massive mathematics workload on 220,000 GCE cores using preemptible virtual machine instances. Read more…

By Tiffany Trader

Six Exascale PathForward Vendors Selected; DoE Providing $258M

June 15, 2017

The much-anticipated PathForward awards for hardware R&D in support of the Exascale Computing Project were announced today with six vendors selected – AMD Read more…

By John Russell

Top500 Results: Latest List Trends and What’s in Store

June 19, 2017

Greetings from Frankfurt and the 2017 International Supercomputing Conference where the latest Top500 list has just been revealed. Although there were no major Read more…

By Tiffany Trader

IBM Clears Path to 5nm with Silicon Nanosheets

June 5, 2017

Two years since announcing the industry’s first 7nm node test chip, IBM and its research alliance partners GlobalFoundries and Samsung have developed a proces Read more…

By Tiffany Trader

Messina Update: The US Path to Exascale in 16 Slides

April 26, 2017

Paul Messina, director of the U.S. Exascale Computing Project, provided a wide-ranging review of ECP’s evolving plans last week at the HPC User Forum. Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Share This