From the Lab

Service Automation: First Results!

august 5, 2011

Our development team is currently testing a prototype that mixes BMC ProactiveNet Performance Management (BPPM) and BMC Atrium Orchestrator (BAO) to monitor the workload of the Web farm and adapt its number of nodes to the workload. The system computes the number of required nodes in the farm to handle the workload, analyzes the current state of the farm (how many nodes are currently on), and turns on or shuts down servers accordingly.

The first results are very encouraging!

These graphs represents the power consumption of a 3-servers’ chassis and the average load of these servers according to a load factor applied to the entire farm.


Without the solution, the power consumption remains significantly stable and above 300 watts, despite the load variation.

However, once the solution is activated, the overall power consumption of the system is adjusted and correlated to the workload: when the demand is low, the system consumes less power; when the workload is high, the system consumes the maximum power. We will publish soon a full article with thorough explanations on how this prototype was designed and how it could be scaled up to other architectures. Stay tuned!