author: John Yocum date: December 29, 2014 transition: fade
http://github.com/brianhigh/research-computing
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.- Capacity Planning
- System Resources
- CPU
- RAM
- Disk
- Optimization
- Parallel Processing
- Monitoring Utilization
- CPU: Central Processing Unit
- Clock Speed
- Processor Cores
- RAM: Random Access Memory
- Insertable modules
- Relatively Cheap
- Fast
- Disk
- Sizes and types
- Arrays
- Network
- Monitor Utilization
- Windows
- Performance Monitor
- Mac
- Activity Monitor
- Linux
- htop
- iostat
- Windows
- Find bottlenecks
- Reduce bottlenecks
Source: [Used with permission from Microsoft](http://en.wikipedia.org/wiki/File:Performance_Monitor_-_Windows_7.png)
Some applications read all data into RAM by default:
- R
- MATLAB
- Excel
- Stata
In each of these cases, there are some tools or methods to help reduce consumption.
- "Divide and Conquer"
- Break down tasks into many small ones
- Maximize CPU core utilization
- MapReduce
- Open source framework for parallel processing
- GNU Parallel
- Open source tool for managing parallel tasks
- Examples:
- Climate data