Sign up for our newsletter and get the latest big data news and analysis.

The Hidden Costs of Open Source

big-data-picClusters based on open-source software and the Linux® operating system have come to dominate high performance computing (HPC). This is due in part to their superior performance, cost-effectiveness and flexibility. The same factors that make open-source software the choice of HPC professionals have also made it less accessible to smaller centers. The complexity and associated cost of deploying and managing open-source clusters threatens to erode the very cost benefits that have made them compelling in the first place. The following graphic shows a range of deployment choices for HPC along with associated Total Cost of Ownership (TCO).

OpenSource_TCOAs customers choose between open-source and commercial alternatives, there are many different costs related to administration and productivity that should be considered. These are explored in a new IBM technical white paper,  “The Hidden Costs of Open Source,” in order to give a true cost perspective. The paper also examines how a commercial management product, such as IBM® Platform™ HPC, enables HPC customers to side-step many overhead cost and support issues that often plague open-source environments and enable them to deploy powerful, easy to use clusters.

Download this whitepaper today to learn best practices for addressing the following topics:

  • HPC: Why this debate is different?
  • Accounting for real costs
  • Real TCO: More like calculus
  • A pragmatic approach
  • Introducing Platform HPC
  • Sources of savings
  • Comparing the costs

While Linux clusters dominate HPC, there are many issues related to cost and complexity that can make open-source solutions challenging. In addition, determining real costs can be complex because every environment is different, and organizations will assess costs using their own methodologies and based on their own requirements and capabilities.

For many organizations, the most practical and cost-effective approach is to deploy a commercially supported cluster management product on a Linux platform. Platform HPC represents an attractive solution because it is a complete product that preserves the many benefits of open-source software while avoiding the headaches and management costs of open-source software.

Because it is a complete, integrated product, Platform HPC allows analysts, engineers and scientists to focus on their work rather than on less productive pursuits such as deploying, managing and supporting open-source clusters.

Download this white paper from the insideBIGDATA White Paper Library.

 

 

Leave a Comment

*

Resource Links: