Blogs

Data growth is clearly out of control. A stupendous 1.8 zettabytes of digitized information exists today –a 9x increase in stored data within the last 5 years alone. With data growing at ever-increasing rates, the question being asked is: How is all this data to be stored and moved around? Is current technology up to the task, or does it need a major overhaul?

Our CEO, Raj Kanaya, considers these questions in a phenomenal guest blog on Silicon Angle. The entire post is available here. Happy reading!

Ashwath Kakhandiki is Director of Marketing at Infineta Systems

I must confess - I was quite surprised when this deduplication (“dedupe”) related patent was granted barely two years after we filed it! That too in a field littered with patent applications – every other company seems to have filed one (and in some cases, many more).

2011 has been a memorable year here at Infineta. Here are a few things that come to the top of my mind:

• Gained significant traction in the Data Center networking industry – won the AlwaysOn Global 250 Award and the SiliconIndia 100 Award.
• Raised $15 million in Series B funding.
• Launched the industry’s first ever 10 Gbps WAN optimization system – the Data Mobility Switch.
• Established Infineta as a thought leader in the inter-data center WAN optimization space.
• Launched a pay-as-you-go service for WAN Optimization Service for Cloud and Data Center Migration Projects – the Data Mobility Accelerator.
• Received accolades from many industry analysts.
• Made many customers happy and beat our revenue goals for 2011.

Big Data implementations such as Hadoop are becoming more common, and as they do, organizations are discovering that Big Data drives Big Traffic. Ashish Shah has written a great piece on this subject, available here:  Wikibon.

Over the next five years, machine-to-machine traffic between data centers (over Data Center Interconnects, or DCIs) is expected to increase faster than traffic within data centers, forcing organizations to respond by implementing multiple 10 Gbps WAN links. In most cases, however, simply scaling up the WAN infrastructure is a weak long-term strategy. Instead, keeping pace with DCI traffic requires a new class of WAN optimization technologies that can scale to 10Gbps speeds while introducing minimum latency to the end-to-end workflow.

“Big Data” is one of the hottest buzzwords in IT today, with its promise of deriving previously-untapped business value from unstructured data stored throughout the enterprise. How Big Data’s unique scale-out architecture enables unprecedented pricing and storage is well understood, but what has not been understood as well are the implications for the WAN. Infineta worked with IRG to test the following hypothesis: The adoption of Big Data will bring the enterprise WAN to its knees. The research – announced today - led to a number of eye-opening findings around how companies are thinking about, and implementing, Big Data.

What a busy couple of weeks at Infineta! Between tons of analyst briefings and ongoing marketing programs, we sponsored two phenomenal technology conferences close to home – Storage Decisions in SF last week, and IT Roadmap in San Jose yesterday.

In talking to a number of attendees from some large enterprises at these conferences, I noticed a very interesting commonality: Even though these enterprises already use branch WAN optimization solutions, most of them are actively looking at alternative solutions to optimize their inter-data center WANs. These organizations had concluded that the same WAN opt solutions that are effective in accelerating branch traffic do a pretty poor job of accelerating inter-data center WAN traffic.

You are a key member of a network team managing a critical set of data centers, and are constantly dealing with replication, backup or virtualization related issues across the WAN. You would like to learn more about WAN optimization but simply don’t have time for some slick sales guy to come in and talk about “the importance of WAN optimization solution agility” or “how you can accelerate ALL your applications.” You just want something that addresses the inter-data center WAN issues you are dealing with today and want to ask very specific questions without all the “So when will you have budget for this project?” pressure.

If you live in the SF Bay Area, there are two awesome shows that Infineta will be participating in, where our technical experts will be present to answer all your questions. The events are:

I met with a prospective customer last week that happens to be one of the largest Internet portals in the world, with tens of data centers across the US as well as in Europe and Asia. One would think that with such an expansive infrastructure, some form of WAN optimization solution would already be in place across data centers.  When I asked which WAN optimization solution they had deployed to date, the chief network architect laughed at me and said: “We have over 100Gbps connectivity between most of our data centers. There’s no way we would deploy hundreds of 1Gbps-capable devices at each site!” He then went on to tell us his previous experience with other WAN optimization solutions, and how he bought a pair from a vendor and was using them to decorate the storage shelves in his lab.

A large healthcare firm we recently talked to had an upcoming data migration project, where the IT team planned on moving 800TB of data from a to-be-decommissioned data center to a larger data center 1,100 miles away. The WAN connectivity between the two sites consisted of 2x1Gbps MPLS links. The storage and network team concluded that the migration would take four months to complete, making it operationally cost-prohibitive. The network team considered leasing a 10Gbps WAN link, but came to the conclusion that the significantly higher WAN expenditure would in no way guarantee faster migration. Interestingly enough, one-time or periodic migrations are becoming quite common for medium to large enterprises.

Big Data is hot. A number of startups have been funded to explore Big Data opportunities. Even Oracle recently announced its entry into the Big Data ring.

Giants such as Oracle and EMC don’t enter a new category unless they can sell their solutions to large enterprises and make obscene profits. In return for all the money that enterprises pay out for these solutions, they expect them to scale and be highly available.