Giovanni Pacifici
Mike Spreitzer
Asser Tantawi
ABSTRACT
Managing the resources in a large Web serving system requires knowledge of the resource needs for service request-s of various kinds, and these needs may change over time. Assessing resource needs is commonly performed using techniques such as offline profiling, application instrumentation, and kernel-based instrumentation. Little attention has been given to the dynamic estimation of dynamic resource needs, relying only on external and high-level measurements such as overall resource utilization and request rates. We consider the problem of dynamically estimating dynamic CPU demands of multiple kinds of requests using CPU utilization and throughput measurements. We formulate the problem as a linear regression problem and obtain its basic solution. However, in practice one is faced with issues such as insignificant flows, collinear flows, space and temporal variations, and background noise. In order to deal with such issues, we present several mechanisms such as data aging, flow rejection, flow combining, noise reduction, and smoothing. We implemented these techniques in a Work Profiler component that we delivered as part of a broader system management product. We present experimental results from using this component in scenarios inspired by real-world usage of that product; our technique produces estimates that are roughly within a factor of 2 of the right answer, for the request flows that draw significant CPU power.
- Application Resource Measurement - ARM. http://www.opengroup.org/tech/management/arm/.Google Scholar
- IBM WebSphere Extended Deployment. http://www.ibm.com/software/webservers/appserv/extend/.Google Scholar
- A. Hoerl and R. Kennard. Ridge regression: Biased estimation for non-orthogonal problems. Technometrics, 12, 1970.Google Scholar
- G. Pacifici, M. Spreitzer, A. Tantawi, and A. Youssef. Performance management for cluster based web services. IEEE Journal on Selected Areas in Communications, 23(12), December 2005. Google ScholarDigital Library
- J. O. Rawlings. Applied Regression Analysis: A Research Tool. Wadsworth & Brooks, Cole Advanced Books & Software, Pacific Grove, CA, 1988.Google Scholar
- J. Rolia, X. Zhu, and M. Arlitt. Resource access management for a utility hosting enterprise applications. In Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management, March 2003.Google ScholarCross Ref
- H. Senger and L. M. Sato. Load distribution for heterogeneous and non-dedicated clusters based on dynamic monitoring and differentiated services. In Proceedings of the International Conference on Computer Communication, 2003.Google ScholarCross Ref
- B. Urgaonkar and P. Shenoy. Sharc: Managing cpu and network bandwidth in shared clusters. IEEE Transactions on Parallel and Distributed Systems, 15(1), January 2004. Google ScholarDigital Library
- B. Urgaonkar, P. Shenoy, and T. Roscoe. Resource overbooking and application profiling in shared hosting platforms. In Proceedings of the Symposium on Operating Systems Design and Implementation, Boston, MA, December 2002. Google ScholarDigital Library
Index Terms
- Dynamic estimation of CPU demand of web traffic
Recommendations
CPU demand for web serving: Measurement analysis and dynamic estimation
Managing the resources in a large Web serving system requires knowledge of the resource needs for service requests of various types. In order to investigate the properties of Web traffic and its demand, we collected measurements of throughput and CPU ...
Dynamic Load Balancing in Web Cache Cluster
GCC '08: Proceedings of the 2008 Seventh International Conference on Grid and Cooperative ComputingIn Web Cache cluster, because task resource demand characteristic is shifting and task resource demand information is hard to obtain, existing dynamic load balancing strategy is inefficient or even inapplicable. In order to solve this problem, a novel ...
Dynamic buffer allocation in video-on-demand systems
In video-on-demand (VOD) systems, as the size of the buffer allocated to user requests increases, initial latency and memory requirements increase. Hence, the buffer size must be minimized. The existing static buffer allocation scheme, however, ...
Comments