ABSTRACT
Energy consumption is a major cost of operating IT equipment in organizations and data centers. Hardware and software manufacturers are beginning to include power saving options in a range of products from processors to operating systems (OS). Previous work on power saving has focused mainly on OS control of the operating modes of laptop computers and mobile devices to maximize battery life. To take full advantage of these newly available energy saving features, we have developed a power management agent with a set of power control and monitoring interfaces which allows power saving features to be implemented on individual applications. We call these power saving capable applications Green Applications.
In this demonstration, we will discuss and show a web based Green Application which implements these newly introduced power saving features. This application runs on an IBM HS20 Blade Server with Linux OS and equipped with a processor (Intel Xeon 3 GHz) capable of power management. When the application runs, it continuously adjusts the power level (range from standby to maximum) of the server processor in accordance with the state and performance requirements of the application (expressed as policies or static user-defined control parameters) via the power management agent. The power management agent can manage multiple Green Applications and can set the power level of the processor according to the aggregate power requirement of the applications. Using an advanced monitoring tool, the IBM Tivoli Monitoring (ITM) System [1], we will show graphically the dynamic interactions of the state and performance of the application, including processor temperature, CPU utilization, power cap, and power usage in a single integrated view, and present the amount of energy used in comparison with running the same application with no power saving features included.
- IBM Tivoli Monitoring: http://publib.boulder.ibm.com/infocenter/tivihelp/v15r1/index.jsp?toc=/com.ibm.itm.doc/toc.xmlGoogle Scholar
- nWebsphere Extended Deployment: http://ibm.com/software/webservers/appserv/extend/Google Scholar
- C. Lefurgy, X.Wang, M.Ware. Server-level Power Control. ICAC 2007, Jacksonville, Florida Google ScholarDigital Library
- Workload generator (WSST, a component of IBM ETTK): http://alphaworks.ibm.com/tech./ettkwsGoogle Scholar
- J. Kephart, et al. Coordinating Multiple Autonomic Manager to Achieve Specified Power and Performance Tradeoff. ICAC 2007, Jacksonville, Florida. Google ScholarDigital Library
Index Terms
- Green applications: software applications that optimize energy usage
Recommendations
An experimental evaluation of real-time DVFS scheduling algorithms
SYSTOR '12: Proceedings of the 5th Annual International Systems and Storage ConferenceWe implement and experimentally evaluate the timeliness and energy consumption behaviors of fourteen Real-Time Dynamic Voltage and Frequency Scaling (RT-DVFS) schedulers on two hardware platforms. The schedulers include CC-EDF, LA-EDF, REUA, DRA, and ...
Koala: a platform for OS-level power management
EuroSys '09: Proceedings of the 4th ACM European conference on Computer systemsManaging the power consumption of computing platforms is a complicated problem thanks to a multitude of hardware configuration options and characteristics. Much of the academic research is based on unrealistic assumptions, and has, therefore, seen ...
System-wide leakage-aware energy minimization using dynamic voltage scaling and cache reconfiguration in multitasking systems
System optimization techniques are widely used to improve energy efficiency as well as overall performance. Dynamic voltage scaling (DVS) is well studied and known to be successful in reducing processor energy consumption. Due to the increasing ...
Comments