Aug 7 ’14
CIO Perspective: Game-Changing Technology—Elastic Storage
We’re in an era of game-changing insights and it’s transforming the personality of storage as we know it.
There are two fundamental shifts IBM is seeing among Big Data clients. First are the increasing data challenges organizations face with Big Data analytics and new application workloads such as mobile and social. Second is the increasing adoption of our software defined automation technologies, which were born in high-performance computing, to meet these new challenges.
As a result, organizations are looking for new software defined solutions that help them create a flexible foundation of storage services in support of faster performance and better Big Data economics.
Breakthrough Software Defined Storage Technology for the Era of Big Data
IBM Storage innovations helped IBM Watson get the right answers—fast—in the “Jeopardy!” Challenge. With each question, the system instantly scoured 4 terabytes of content using advanced storage and memory pairings, providing the most probable response within seconds.
Systems such as Watson demonstrate how commercial clients can manage this explosive growth of data that has put a strain on the IT infrastructure and data management operations. That’s why IBM is expanding its Software Defined Storage portfolio by making Elastic Storage used in Watson commercially available.
Elastic Storage is a proven, scalable, high-performance data and file management solution that’s being used extensively across multiple industries worldwide. USAA, a provider of healthcare and financials services, had multiple lines of business deploying Big Data and analytics, bringing significant infrastructure and storage cost challenges. The efficiency, performance and unique capabilities of IBM's software defined storage enabled a 30:1 consolidation of production applications and accelerated Hadoop workloads by four times.
Elastic Storage provides simplified data management and integrated information lifecycle tools capable of managing thousands of yottabytes of data and billions of files, in order to arrest the growing cost of exploding data.
Contrary to urban legend, a yottabyte isn’t a snack for the Jedi master, Yoda. A yottabyte is 1 billion petabytes, or the equivalent of data centers running traditional hard drives that occupy 1 million city blocks, about the size of the states of Delaware and Rhode Island combined!
Optimized for Big Data and a new generation of applications and cloud environments, this storage software builds on the leading technology of IBM global file system. Elastic Storage is open for businesses with new applications for the cloud where community innovation on OpenStack is critical. It supports open standard access such as POSIX, NFS, OpenStack Cinder and Swift, and Hadoop.
An IBM CFO and CIO study found 71 percent of CFOs identify technology changes as the most important external factor impacting their organizations and 78 percent report that pressure remains high to control costs and increase efficiency.
A key component of Elastic Storage is its ability to automatically and intelligently move data to the most strategic and economic storage system available. Through policy-driven features and real-time analytics, for example, Elastic Storage can automatically move infrequently used data to less expensive, low-cost tape drives, while storing more frequently accessed data on high-speed Flash systems (see http://www-03.ibm.com/systems/storage/flash/) for quicker access. And what makes CFOs happy is these features can provide cost savings of up to 90 percent.
While traditional storage systems must move data to separate, designated systems for transaction processing and analytics, Elastic Storage can automatically balance resources to support all types of application workloads, including Hadoop-based analytics. This dramatically speeds analysis and eliminates the costly and time-consuming process of producing duplicate copies of data.
Almost every discussion today about Big Data leads to conversations about infrastructure resources, especially storage. As Big Data and analytics evolve, companies will ask for faster insights from sophisticated computations that occur in storage resources and are quicker, more flexible and far less expensive.
IBM is leading the charge in the IT industry to deliver infrastructure value defined by software. We’ve entered a new era where IT infrastructure isn’t only about the physical CPUs, networks and storage devices. IBM researchers in Haifa, Israel, have been working on prototyping a software defined mechanism called “storlets” that hold the promise of greatly increasing the value we get out of storage and the speed at which we can access what we need.
I invite you to join in the conversation about the new generation of IBM Storage through hubs such as IBM Storage Experience (see http://ibmstorageexperience.tumblr.com/).
And if you ever find yourself on “Jeopardy!” and are presented with a clue such as, “Can successfully scan 10 billion files on a single system in just 43 minutes,” just know the answer is “What is Elastic Storage?”