| By Bill McColl |
Article Rating: |
|
| September 4, 2010 10:45 AM EDT |
Reads: |
3,207 |
Databases, Data Warehouses, Map Reduce, Hadoop, Realtime Data Warehouses,... What is the right technology for your "big data" analytics challenges? The best fit will depend on your specific requirements on three fronts:
- Speed (How long can you afford to wait for the results of your big data processing? Is latency of several hours acceptable, or do you need analytics insight at the speed of your business transactions and events, i.e. in seconds?)
- Scale (How much data are you gathering? How much do you need to process per second, per minute, or per hour?)
- Power (How complex do your analytics algorithms need to be? Do you need only simple summaries and statistics, or do you need powerful algorithms that can carry out deep analytics? Is simple batch processing enough, or do you need the power of continuous, always-on analytics?)
Cloud supercomputing is all about big data. Knowing where you need to be on these three axes is the key step in figuring out the right technology solution for your needs.
Watch the video here.
Bill McColl left Oxford University to found Cloudscale. At Oxford he was Professor of Computer Science, Head of the Parallel Computing Research Center, and Chairman of the Computer Science Faculty. Along with Les Valiant of Harvard, he developed the BSP approach to parallel programming. He has led research, product, and business teams, in a number of areas: massively parallel algorithms and architectures, parallel programming languages and tools, datacenter virtualization, realtime stream processing, big data analytics, and cloud computing. He lives in Palo Alto, CA.
Subscribe to Virtualization Journal Email News Alerts
Subscribe via RSS
