Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd...

13
ADAPTIVE PERFORMANCE CONTROL OF COMPUTING SYSTEMS VIA DISTRIBUTED COOPERATIVE CONTROL: APPLICATION TO POWER MANAGEMENT IN COMPUTING CLUSTERS Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006, Dublin, Ireland Presenter: Ramya Pradhan, Fall 2012, UCF.

Transcript of Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd...

Page 1: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

ADAPTIVE PERFORMANCE CONTROL OF COMPUTING SYSTEMS

VIA DISTRIBUTED COOPERATIVE CONTROL:

APPLICATION TO POWER MANAGEMENT IN COMPUTING

CLUSTERSAuthors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3rd International Conference on Autonomic Computing,

ICAC 2006, Dublin, Ireland

Presenter: Ramya Pradhan,

Fall 2012, UCF.

Page 2: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Outline

Research problem Proposed solution Evaluation of proposed solution Strengths Limitations Proposed extensions

Page 3: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Research ProblemServer cluster Clients

Power Consumption

How to balance power consumption with time-varying workload and QoS?

Page 4: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Proposed solution

Fully decentralized and cooperative control framework using optimal control theorybalance cluster operating frequency and

average response timescalable due to problem decompositionfault-tolerant due to cooperative controlno intra-cluster communication

Page 5: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Proposed solution using optimal control

Optimal control“uses predictive approach that generates sequence

of control inputs over a specified lookahead horizon while estimating changes in operating conditions.”

System ModelSystem state: queue sizeConstrained control input: operating frequencyOutput: average response time

Page 6: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Distributed control framework

Server cluster Global request buffer ClientsDynamic

Controllers

Page 7: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Evaluation

System settingse-commerce

○ Virtual store consisting of 10000 objects○ response time uniformly chosen between

(4,11) msrequest distribution

○ popularity○ temporal locality

cluster of four servers

Page 8: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

EvaluationAdaptive power consumption

Page 9: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

EvaluationAdaptive power consumption during processors’ failure

Page 10: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Strengths

Development of a communication-less framework for distributed optimization

Implementation of the framework of power consumption and guarantee QoS

Usage of distributed frameworkautonomous controllersno single point of failurecapable of self-* properties

Page 11: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Limitations Main concept: decomposing power

management into optimal control problems for each server, based on the assumption that resource provisioning and allocation can also be decomposed into such problems; this may not always be possible.

Adding new servers adds to the overhead in predicting its behavior by all other servers. Results for adding servers is not presented.

Page 12: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Possible extensions

Study the system under dynamic adding and removing of servers

Experiment with perturbations when servers are optimally performingremove servers that almost always

guanrantee QoS and see how other servers respond

add more servers to observe how estimating the other servers’ behavior affects guarantee of QoS

Page 13: Authors: Mianyu Wang, Nagarajan Kandasamy, Allon Guez, and Moshe Kam Proceedings of the 3 rd International Conference on Autonomic Computing, ICAC 2006,

Thank You!