Hivecell

Small servers for big data

We are building small servers for big data. It sounds counter-intuitive, but it is the next logical breakthrough.

hivecell-prototype

Hivecell® enables you to build a hive (cluster) of servers on your desktop. Learning and developing with big data technology such as Hadoop becomes much easier.

Hivecell provides twice the processing power for half the price and a third of the energy of traditional servers. Hivecell is green technology for Big Data.

More computing for half the price

A traditional server costs approximately $10,000, has 16 cores, 64 GB RAM and 12 TB hard drive storage. A minimum Hadoop cluster requires 4 servers, which would cost $40,000. For half that price, one could have 36 Hivecells which would provide more processors, more memory and more storage for less power and less space. The comparison of the clusters is shown in the following table.

traditional Hivecell
servers 1 x4 1 x36
price $10,000 $40,000 $550 $19,800
cores 16 64 4 144
memory (GB) 64 256 8 288
storage (TB) 12 48 2 72
energy (W) 460 1840 15 540

Big enough data

Big data is any data processing large enough that it cannot be easily executed or managed on traditional systems. The name “big data” is actually misleading. You do not need petabytes of data to have a big data problem. A better name might be “big enough data”. If data processing is taking hours to complete, then you could benefit from big data technology. A more accurate name still would be “massively distributed processing”. It’s not very catchy, but that is the essence of big data technology: what would take 24 hours to run on one server can be completed in less than an hour on 24 servers. Perhaps we should just call it Hadoop, which is the name of the open source projects that encompass most of what we call big data technology.

C5_IS_1-small_large (1)

Big barrier to learning big data

There is a big barrier to learning big data technology. With most new technology, a developer just downloads the software to his laptop and starts hacking. You can’t do that with Hadoop. It requires a minimum of four servers to work properly. Most developers do not have four servers lying around that they can play with to learn a new technology. Cloud is an option, but it is not cheap. For most people, it is not a place to comfortably experiment.

The barrier to learning is preventing the supply of developers from meeting the exploding demand for big data expertise. In a Gartner survey, companies said that their primary concern about using big data software is that “big data expertise is scarce and expensive.” Their second concern is that “data appliances platforms are expensive.”

Hive on your desktop

We believe that these two concerns are interdependent, that the cost of hardware is the barrier to learning. Hivecell removes that barrier. With Hivecell, a developer can affordably build a hive (or cluster) on his desktop. Each student can have his own hive for learning in the classroom.

C5_3view-crop_large

Our solution is a server designed for modern software that provides better computing power for less money, less energy and less space. For Hadoop, you want a processor with an Internet connection and a disk drive, as many of them as you can get. Why pay for all the other stuff? Hivecell is just that; a small, inexpensive, low-power server designed specifically for Apache Hadoop and big data processing.

C5_stacked-small_large

hivecell