Big Blue introduces exabyte-capable tape libraries to handle massive data set backup and archiving
Perhaps it was coincidence, and perhaps not, but IBM just happened to come out this week with a major new Big Data storage product launch at exactly the same time as competing storage giant EMC is holding its big annual conference in Las Vegas: EMC World- Cloud Meets Big Data.
IBM has announced a set of new products involving tape storage backup, enhanced archiving, and deduplication that aim to help clients better store and extract business intelligence from massive amounts of data.
Something should be clarified before we go any further here: the increasingly-used term “Big Data” does not refer to volume alone. Big Data also signifies the wide number of data types that need to be stored, archived, protected and accessed, whether they be created by humans or generated from devices.
Tape Still an Important Asset
Tape may be a 1950s-era technology (IBM invented magnetic tape in 1952), but it is still a major player in enterprise data storage, no matter what the spinning disk hard drive storage makers say. Analysts who track such things generally agree that between 50 and 60 percent of all the world’s businesses that maintain digital records have tape in the mix somewhere.
“IBM has an edge over storage vendors like EMC that don’t support tape,” Doug Balog, general manager of IBM’s storage business unit, told eWEEK. “Tape and disk can be used together to deliver clients tiered storage that enables them to store data within the different tiers based on their data priorities.”
“For those of you who think tape has no future, please take note of the following quote from James Gleick’s very worthwhile new book The Information: ‘Hardly any information technology goes obsolete. Each new one throws its predecessors into relief’. In the context of IBM’s announcements, tape is likely to continue to play a key role in the backup process and to pick up new business, especially in providing bulk storage for active archiving,” wrote Mesabi Group analyst David Hill in Charles King’s May 11 Pund-IT report.
“All things considered, tape continues to be more cost effective for those processes than disk-based solutions, as has been shown by one or more studies for each area.”
We’re Talking Exabytes of Storage Here
IBM this week introduced the IT industry’s first tape library system that can provide more than 2.7 exabytes of automated storage, Balog said. An exabyte is rather a lot of capacity; an exabyte is represented by 1 followed by 18 zeroes. One of those is enough to store about three times all the mobile data generated in the U.S. in 2010, Balog said.
Suffice to say IBM is basically providing unlimited storage now in a single tape system, provided the user wants branch it out to its maximum size. Each of the cartridges in the new system hold 4TB of data, and this new library can hold multiple thousands of cartridges.
IBM’s System Storage TS3500 Tape Library, launched this week, can grow for Big Data workloads thanks to a newly developed shuttle addition — a mechanical attachment that connects multiple tape libraries to create a single, high capacity library complex (pictured).
Balog said the TS3500 offers a whopping 80 percent more capacity than a comparable Oracle tape library and is currently the highest-capacity library in the world.
To help users run this huge tape library, IBM also made available new file system access to select IBM tape libraries with the IBM Linear Tape File System Library Edition (LTFS LE). LTFS clients can now more efficiently index, search, retrieve and share data stored on Generation 5 LTO tape, an open tape storage format, Balog said.
What kinds of IT organisations need these humongous libraries? “There are more than you might think,” Balog told eWEEK. “Organisations studying genomics. CERN (the think tank in Switzerland), oil and gas exploration systems, weather-prediction systems — they all need to store, back up and archive huge amounts of data and be able to access it as needed.”
Clustering Secret Sauce Gets Upgrade, Too
IBM’s storage clustering IT, the Scale-out Network Attached Storage (SONAS) system and Information Archive, got an upgrade this week. SONAS, which can scale to more than 14 petabytes of clustered storage, now offers double the throughput of its predecessor, as well as faster response times. SONAS provides support for anti-virus applications to offer protection from malware with the ability to scan archived data and isolate or delete compromised files, Balog said.
SONAS also will can use an open standard protocol called NDMP, enabling clients to back up and protect large amounts of data in SONAS using ISV applications that support NDMP.
Balog said IBM has added a “many-to-many” replication feature to IBM System Storage TS7650 ProtecTIER Deduplication solutions that will allow enterprises with multiple data centers to automatically replicate backup data between locations, so that multiple copies of critical data can be stored and quickly restored if needed.
Finally, IBM TS7700 Virtual Tape Library product line has been upgraded to double the number of virtual tape cartridges it can contain to 2 million, Balog said.