A big ‘thank you’ to all of you who attended our webinar entitled “Trends in Tape: Looking beyond LTO-5 with LTO-6 and LTFS.”  We had the best attendance ever. This is clearly a topic of great interest to many of you out there.  Bob Cone hosted the call and the discussion was packed with a multitude of great information including LTO-6 and the overall LTO Roadmap.  But more importantly, Bob covered the implications of the roadmap and LTFS and how they fit into the overall storage picture. With so many technologies now available, storage hierarchies and designing and choosing the right building blocks for your environment continues to get more complex.  The presentation distilled much of the vast amount of available information on numerous storage alternatives into an easy-to-understand discussion. Tape, Disk and Solid State Disk / Flash were covered including where they fit now, and where they will fit in the future.  The session was recorded and is available at the link below:

Looking beyond LTO-5 with LTO-6 and LTFS

The webinar underscores how LTO-6 fits into the LTO Roadmap and its important performance and capacity improvements over past generations. It also points out the advantages of LTO-6, which is why you may be interested in Spectra’s LTO-6 Pre-Purchase program. 

How many times have you thought about buying a new car, computer, TV, or cell phone but when you found out a new technology was just around the corner, you waited?  Personally, I need to upgrade my iPhone and considered the current 4S, but am waiting for the iPhone 5. Like me, you hold off and limp along with the old technology, anxiously awaiting the new technology.  Well, when it comes to LTO technology, you don’t have to wait.  Spectra is offering our customers a cost-efficient path to get the latest LTO-5 tape drive technology available today, along with an LTO-6 option, where they will receive an LTO-6 drive to replace the -5, as soon as the LTO-6 is available. 

In addition, this is a great opportunity for customers currently on LTO-3 drives:  LTO-6 drives have read/write compatibility with one generation back (LTO-5) and read only with two generations back (LTO-4).  So, if you have LTO-3 drives and media and want to move to a new generation, you could upgrade to the LTO-6 Pre-Purchase option now, get LTO-5 drives now and replace ALL the LTO-3s, read and re-write the data to LTO-5 media.   Then, when LTO-6s are available through the pre-purchase program (with no additional cost), swap out the LTO-5 drives, and be able to read/write with the LTO-5 media.  Otherwise, if you wait and go straight to the LTO-6 drives, you will need some other way to migrate your LTO-3 media, as it will be unreadable with the LTO-6 drives.

Everything is handled at the time of ordering the LTO-5 drives, so when the LTO-6 is available, we would contact you and find out when you would like us to ship the new drives.  Then you just send the LTO-5 drives back.  And all this is done with no additional paperwork.  The new LTO-6 tape drive will double capacity and provide a 50% increase in performance over LTO-5.  With a larger compression history buffer, the expected compression ratio will go from 2:1 to 2.5:1, so LTO-6 will offer a compressed capacity of 8 TB and data transfer rates of up to 525 MB/second.  The sixth generation of LTO tape drives provides many positive implications for IT and business managers and we are excited to offer you our LTO-6 pre-purchase program: LTO-5 today and the ability to be one of the very first to get LTO-6 and all its advantages when it becomes generally available.
 

Unless tape is playing an important role in your storage strategy, you are probably stuck in the storage equivalent of the Ghost of Christmas Past.  

As noted in many industry forums, tape is playing an important role in archive as a reliable and efficient means to provide on-line access data.   Numerous recent Spectra Logic developments including T-Finity, Data Integrity Verification and CarbideClean^TMenhancement to Certified Media are specifically aimed at improving storage in archive and other ‘Big Data’ applications.

However, what often gets overlooked is the importance of tape as a cost-effective solution in the backup and disaster recovery markets.   If you think that dedup is the answer here, think again.  A recent ESG study shows that VTL/dedup solutions are 2 to 4x more expensive than LTO tape.   Once you’re ready to prepare for the future and make the most of your IT budget, check out the new ESG Lab video on Spectra’s T50e and T120 products for overviews of two efficient, scalable solutions in the 10TB to 200TB space with enterprise-class features.

 Den-si-ty (n.): The quantity per unit volume, unit area, or unit length. (From Merriam Webster)

Generally speaking, no one wants to pay more than is minimally required in order to store their stuff.  This is probably why so many American garages are filled with boxes and sports gear while the car sits out on the driveway.  It’s less expensive to keep grandma’s knick-knacks and the kids’ hand-me-downs in the garage than it is to pay the folks at U-Store-It to hold it for next spring’s neighborhood yard sale.

When it comes to storing electronic bits, the same premise holds true.  Administrators don’t want to pay more to store their data than is minimally necessary given various constraints around things like response times and availability.  As a result, buying storage gear that provides great density at low cost becomes highly important.  This is especially true given the length of time that bits have to be stored, which in some cases happens to be eternity. 

So what’s the most dense, cost-effective storage for the long-haul?  Tape.  Given proven technology and vendor roadmaps, the effort to extend tape density and cost effectiveness continues unabated.  In January, 2010, IBM and FUJIFILM demonstrated tape technology with a density 39 times greater than the best-in-class tape at that time.

Other notable tape density storylines include:

1) Hitachi and Maxell announced development of a 50 TB tape in May, 2010.

2) Oracle announced it was shipping a 5 TB tape drive in January, 2011.

3) The LTO consortium released a roadmap with a 12+ TB tape (LTO8) in April, 2010.

4) IBM announced shipment of a 4 TB tape drive in May, 2011.

Furthermore, the major tape drive vendors (IBM and Oracle) both specify that the cost per GB of disk is 5x to 10x more expensive than that of tape.  As the density advances noted above continue, the cost per GB will continue to decline going forward.  This means that the forecast for long-term, cost-effective storage on tape will continue to be attractive relative to that of disk.  This is particularly true for those customers facing significant active archive requirements.  Could this be the reason Why Tape Rolls On?

To learn more about Why Tape Rolls On, see part 3 of this series discussing the Speed of tape.

Speed (n.) Swiftness. Rapidity. Rate of motion or performance. (from Merriam Webster)

A trade show participant once told me he didn’t use tape because, “…it wasn’t fast enough”.  When asked how fast he needed to move data he said he needed to move it at about 200 MB/s for his backup purposes.  Furthermore, he believed only disk was fast enough to deliver.  When told a single LTO-4 tape drive could stream data at 120 MB/s and only 2 drives were needed to meet his requirement, he was shocked.  Unfortunately, his perception of tape is not exceptional given the marketing dollars spent “educating the masses” about the speed of disk versus tape.

So what is it about tape’s speed that storage buyers are missing?  If one looks only at random seek time, critical within on-line transaction processing environments for instance, then tape is indeed slower than disk.   But that’s not the only performance metric that’s important. 

Raw throughput can be a requirement in big data environments when moving huge files quickly from storage to application for processing.  Today’s tape drives are built to deliver speed in these areas.  For instance, LTO-5 tape drives move data at 280 MB/s compressed while enterprise tape drives from IBM are capable of slinging data around at 360 to 650+ MB/s compressed respectively.  This means it’s possible to reach transfer rates of upwards of 1PB per hour given today’s enterprise library configurations.  Believe it or not, there are HPC users currently pushing requirements for 1PB per hour data rates.  Tape can deliver that kind of speed on that kind of scale.

When it comes to transporting data between sites, the performance of physical tape movement becomes really interesting.  For example, electronically moving 10 TB of data via an OC-3 or OC-12 line can be expensive running from $10,000 to well over $100,000 per month respectively.  At these prices you have the distinct privilege of transporting that data in 6.1 days for an OC-3 and 1.5 days for an OC-12.  In contrast, you can put 10 TB of data on 2-4 tapes, depending on the type, drop them into a FedEx box and ship them overnight at a cost that’s little more than a rounding error relative to that of the cost of the digital pipes.  In other words, you can’t overestimate the bandwidth of a truck full of tapes – especially for the price!

Will you always have to move data this fast?  Maybe not, but when you do, tape can help you do it at a fraction of the cost of the alternatives.  Maybe that’s why tape rolls on.

To learn more about Why Tape Rolls On, see part  2 of this series discussing the Green Storage characteristics of tape.

by Matthew Star, CTO, Spectra Logic

LTFS, linear tape file system, is sometimes called long term filesytem. No matter what you call it; LTFS lets tape behave like removable disk. Having tested various LTFS applications, I can tell you it is shaping up to become the new standard in tape interchange, particularly in LTO-based archives. LTFS is an open standard that uses two partitions to split directory contents from its associated file data. But what about the other open formats like TAR (derived from “tape archive”), which are open and have compatibility across multiple platforms? How does LTFS stack up in comparison?

Let’s look at both. TAR is a formatted data archive, usually written to tape and designed around sequential media. LTFS is a format used to make tape look more like random access media to the user or consumer of the storage. So, which is better? It depends on your needs and risks profile. TAR has been around for 30 some years and is available in source or binary format on nearly any operating system (OS) imaginable. LTFS currently only runs on about three OS's. TAR is self-describing, but must be accessed in sequence. You really cannot know the whole content of the archives on tape without reading, at a mimimum, the headers of each archive. In other words, TAR requires that you read the whole tape. LTFS, on the other hand, stores its directory, or header, information on a separate partition and thereby only loads a very small amount of data to be able to fully describe the contents of the entire tape.

There are some downsides to using tapes as a random access device. First and foremost, tape was not designed for a random access pattern. So, writing millions of small files to an LTFS formatted tape, then attempting to retrieve every other file on that tape can be a recipe for disaster, as the performance of the drive decreases significantly. This is where TAR works really well, because TAR bundles all of those millions of tiny files into one archive which is then stored as a single file on a single tape. Plus, TAR can restore data as fast as the drive can read it. If on the other hand you are writing hundreds of larger files to tape and want random access to any one of these files, LTFS may just be the trick you’re looking for.

The other advantage LTFS has over TAR is LTFS’s ease of use after the applications and drive stack are installed. LTFS makes the tape look just like a large USB key. TAR must be used with a command line interface (like tar -tvf /dev/tape1) just to get the contents of the one archive on a single tape.

So which one would I use? Both or either--depending on the environment and my needs. I don’t believe you should consider LTFS over TAR as a solution to your petabyte archive. But if you want an easy way to move data from place to place or are deploying a smaller archive, you should review LTFS’s features and benefits.

Well, apparently ‘Big Data’ organizations dealing with the data explosion care quite a bit about these topics.  

Numerous customers recently attended Spectra Logic’s 2011 TAP (T-Series Advisory Panel) meeting to discuss industry trends and roadmaps for archive, tape and overall storage.  The TAP consists of a select group of Spectra’s tape library users who convene annually to discuss their product experience and wish list for future developments and features. Attendees this year represented various HPC environments including national labs, genomics, cloud services, media and entertainment, financial services and manufacturing.

Customers gained insight on overall HPC storage trends from HPC analyst Addison Snell (@addisonsnell on Twitter), CEO of Intersect360.  Developers from IBM and FujiFilm demonstrated their commitment to tape technology by providing overviews of their LTO and enterprise tape roadmaps including their recent joint research demonstrating 35 TB tape capacity.  Finally, Spectra Logic executives held interactive sessions with customers on our storage roadmap.

Here are a few takeaways from customers at the August 2011 TAP meeting:

• Archive Matters.    Customers see archive solutions as a key element in cost-effectively managing data explosion.   They applaud Spectra Logic and other vendors’ leadership role in Active Archive.
• Tape Matters.    Customers are clear that tape will continue to play a crucial role well into the future by providing the safest, most cost-effective storage.  The LTO consortium agrees and has a committed LTO roadmap well into the future.
• Customer Relationships Matter.   Most importantly, as storage requirements evolve, customers need vendors who foster partnerships to help meet their evolving storage needs.   Customers need transparent dealings with sales, support and executives — and listed their personal relationships within Spectra Logic as one of the top reasons they selected us.  According to these TAP customers, Storage Magazine’s 2010 Quality Awards, and fiscal 2011 financial results, Spectra Logic is on the right track.

As I was bouncing around the country once again, I struck up a conversation with a complete stranger sitting next to me on the plane, which is my usual modus operandi.  Without knowing what industry I work in, he brought up the term "high performance computing" within the first minute of our friendly exchange.  Come to find out, the gentleman is a defense attorney to helicopter pilots involved in crashes. 

During the boarding process, he had his phone glued to his ear as he was engaged in a serious conversation with a couple of aeronautical engineers from Harvard. The engineers were conducting structural research on using multi-dimensional modeling techniques on super computers to help him build his case in determing why a helicopter recently crashed.  It became apparent to me that supercomputers continue to proliferate in our data-driven culture, and play a role in nearly every aspect of our everyday lives. 

Scientists, engineers and generally smart people continue to leverage the power of massive and distributed processers for calculation-intensive tasks such as quantum physics problems, weather forecasting, climateresearch, molecular modeling (computing the structures and properties of chemical compounds, biological macromolecules, polymers and crystals), and physical simulations (such as simulation of airplanes or helicopters in wind tunnels, simulation of the detonation of nuclear weapons, and research into nuclear fusion). 

You might be asking, what is the significance of all of this to me, to storage and to Spectra?  The way I see it, as supercomputers become more common, more and more data will continue to be created!  It also begs a few questions: Where does all that data go and how can it be preserved?  How can it be archived in a manner that makes it searchable and useable into the foreseeable future? As I ask that seemingly rhetorical question, I feel sort of like the famous Sweathog, Arnold Horshack, in Welcome Back, Kotter with my hand raised high in the air saying, “Ooh-ooh-ooooh, pick me Mister Kotter!"  Knowing what I know, I am ecstatic about the supercomputing revolution that we are experiencing because a large majority of the data generated, according to just about any of the more educated storage analysts you talk to, is going to be on tape.  And again, knowing what I know about Spectra and our track record for growth, profitability, and more importantly innovation over the past 32 years, our name is becoming synonymous with "enterprise" tape since we have the world's most scalable, and feature-rich tape system!  Even though I just revealed my age with the reference to Welcome Back, Kotter, I couldn't be more excited about the continued growth of the HPC market and the subsequent growth of the data explosion as a direct result of HPC.  If you can’t see the HPC market being a tremendous opportunity for continued tape growth because of the inherent characteristics of the most reliable, dense and economical media type, then "up your nose with a rubber hose!"  Of course, that is a line from my favorite Sweathog, Vinnie Barbarino!  Sorry if you are offended...

We’ve all been privy to the countless articles hitting every technology journal around the world with predictions, forecasts, or trends for the upcoming year.  This is no different from any other year, and is virtually an industry ritual that sets the tone for the upcoming year. Amongst these trends, some were obvious, some were reasonable, and one in particular seemed to catch many people off guard: Tape is back, or more precisely, it never went anywhere.

From CNN’s shock at discovering that Google (GOOG) still uses tape backups as their final tier* , to Oracle announcing their latest 5TB Tape technology, tape has prevailed as one of the busier talking points so far this year. Obviously for Spectra Logic, this is neither a problem nor a surprise, but many people are probably asking themselves, "Why? Why Now?" or even "I thought Tape was Dead?" In order to understand this trend, let’s take a look at the other major trends forecasted for 2011: Cloud, Storage Virtualization, Acquisitions, and Overall cost reduction.

As far as cloud is concerned, whether it be a private, hybrid, or public cloud, tape is a logical tier for any hosting infrastructure. It is the strong silent partner, if you will, for two primary reasons: tape continues to be the most cost-effective format to store data on, and tape provides an offline copy of the data for added security. My college computer security professor used to refuse to plug his computer into the internet on the principle that nothing online is ever 100% secure. Unfortunately, in the era of viruses, worms, malicious attacks, and even software glitches, bugs and data corruption, this sentiment is all too true. I bet the Parish of Orleans Civil District Court will take a much closer look at their cloud service provider’s storage method moving forward after losing large amounts of data due to simultaneous disk crashes in a tapeless environment. Thankfully for the Court, they still have paper records to retrieve from**.

Our second case is that of storage virtualization. In 2010, the Active Archive Alliance was formed by Spectra Logic, FileTek, Qstar, SGI, and Compellent with the intention of educating and promoting the concept of active archiving, or extending a file system across multiple storage devices in a virtualized storage pool. With server virtualization dominating the market in 2010, it only makes sense that the virtualization trend would continue throughout the storage infrastructure. The Alliance, however, was not alone in their efforts to reintroduce the concept of seamlessly tiered storage. With data volumes growing in the Exabytes and floor space, power and cooling costs increasing, tape is the ideal resting point for generally inactive data.  Even in the era of deduplication, MAID, Thin Provisioning, and other power-saving technologies, tape continues to lead the charge for power efficiency and storage density. Why? Tape is designed to be stored offline, which consumes no power. Additionally, IBM and FUJIFILM have proven that tape is far from reaching its physical limitations for storage density with their 35TB prototype tape***. 

Ultimately, our final two trends answer tape’s role in the prior. Oracle now has an investment in tape technology through their acquisition of Sun, and thereby StorageTek’s, tape technologies. IBM, HP, Dell, and Quantum similarly have made an investment in tape technology.  Additionally, many of the loudest voices against the tape market have been acquired, some by companies with tape interests, leaving only one large player still beating the "Tape is Dead" drum: EMC.  So ask yourself... why would a marketing powerhouse spend such energy on anti-tape promotions, if it weren’t a threat on their radar?

These acquisitions have opened the airwaves for the pro-tape messaging to once again make its way into everyday dialog. Why? Because, like our final trend, it's about overall cost reduction. With tape remaining the leader in both low-cost capital expense and low-cost operational expense storage, and the integration of other technologies with tape, it is once again being discussed as a viable, valuable tier within any datacenter design. 

*http://tech.fortune.cnn.com/2011/02/28/google-goes-to-the-tape-to-get-lost-emails-back/

**http://itknowledgeexchange.techtarget.com/storage-soup/i365-involved-in-new-orleans-backup-failure/

***http://www.engadget.com/2010/01/23/ibm-and-fujifilm-develop-35tb-magnetic-tape-cartridges-unveil-i/

CTO Insight: Big Data: Why Tape?

 By Matt Starr, Spectra Logic’s CTO

I have watched the tape market’s growth over the last two years, which seems mostly due to the increasing number of archive installations.  With much larger system implementations projected through 2014, this growth will continue for the foreseeable future.  Military low-altitude and high-altitude video surveillance in countries like Afghanistan, the media and entertainment industry’s drive to 4K file data and the growth in PACS data are just a few of the many market segments driving the implementation of large archives. 

These are areas where dedupe and disk, in general, fall down, precisely because of the raw quantity of data involved--the disk resources required would be enormous, and use enormous quantities of power-- and the delays in time to deduplicate, then reduplicate is unacceptable.   

EMC’s recent “Big Data” news splash did not mention tape, which kind of shocked me!   (It’s only kind of shocking, as EMC is tape-hostile.) Tape is Big Data:  80% of the world’s data is stored on tape[1]and tape is the only media that can scale to exabyte(s) and still be cost effective.  In fact, tape is the only cost-effective method of storing Big Data.   Tape storage is denser than disk storage, costs less up-front and is ten times less expensive to operate over time than a disk-based solution.  I am not implying that disk does not have a play in the Big Data world; it is just not well suited as the “meat” of a storage environment.  

So, where does disk belong in this Big Data world?  First, disk works very well as the cache system that interacts directly with the user via a Filesystem, WebDAV, FTP or other front-end system.   Second, disk is the right platform for meta-data storage.  For far too long, users have been saving data as file names and not objects with meta-data.  As archives grow, object storage and meta-data will take the front seat in how data is stored.   Lastly, disk has an important role in helping to make stored data searchable: why would you store data if you cannot get it when you need it?   In my opinion, roughly 10% of the total archive space should be dedicated to meta-data and search.   Add another 10% of the total archive as disk space for cache, and the picture starts to come together.   Roughly 20% of your total archive should be disk, with the other 80% consisting of long lived, reliable, cost-effective tape.

Reliable? Yes. The facts are absolute and irrefutable-- tape is extremely reliable—more reliable than disk.  Tape’s error correction is 10 to -17^thup to 10 to the -19^thbits, which blows disk’s reliability[2]statistics out of the water.   Additionally, modern tape libraries have features like Spectra Logic’s Media Lifecycle Management that predictively informs the user about the health status of the tape as it being used. Features like this layer on reliability even beyond tape’s already high reliability.   Through MLM and other features (stay tuned for a few upcoming announcements this spring), Spectra’s T-Series libraries ensure that the data on the tape is intact and recoverable from the archive.

The architects and developers of data archives will continue to build systems based on disk and tape, not just disk.  When Big Data archives are based on disk alone, then one or more of the following scenarios is true:  1.) They are not a Big Data environment, but want to be (or think they are) 2.) They are wasting money and should be answering to their shareholders or voters.   3.) They have been mis-educated on tape.  In the end, tape is far from dead and will continue to prove itself as the ideal medium in the Big Data world.