Request and Server Consolidation Schemes for Cloud Energy Management

C Senthilkumar, A Gokilavani

Abstract


Cloud computing is used to access computing resources owned and operated by a third-party provider. Cloud computing is Internet-based computing to share resources, software and information. Both transactional and long-running analytic computations are comprised into workloads. Scientific simulations to multi-tier transactional applications are referred as workloads. Power management strategies have been proposed for enterprise servers based on Dynamic Voltage And Frequency Scaling (DVFS). DVFS allows the server to transition the processor from high-power states to low-power states. The processors are assigned to sleep states such as deep sleep to reduce energy consumption. In deep sleep the server can be configured to use Direct Memory Access (DMA) to place incoming packets into memory buffers for processing in the active state.

Request batching can be conducted to group received requests into batches and put the processor into sleep between the batches. Virtual Batching is a request batching solution for virtualized servers with primarily light workloads. The system dynamically allocates CPU resources with same performance level and peak values. Server consolidation is performed to fully utilize a small number of active servers in the data center. Static and dynamic server consolidation algorithms are used to assign data centers to the request batches. Static server consolidation algorithm is used for the offline mode in data centers. Online workload variations are managed by the dynamic server consolidation algorithms. Virtual batching is integrated with pMapper (power-aware application placement framework) to assign data centers for the workloads.

The Virtual Batching scheme is enhanced to manage resources with load balancing mechanism. The system is improved with optimization mechanism to manage relative response time. Resource levels and application requirements are integrated in the allocation process. The system is adopted to support Dynamic Random Access Memory(DRAM) and Dual in-line Memory Module(DIMM) components.

Keywords


DVFS, Virtual Batching, Request Batching, Server Consolidation CPU resource allocation.

References


. R. Nathuji, P. England, P. Sharma, and A. Singh, “Feedback Driven QoS-Aware Power Budgeting for Virtualized Servers,” Proc. Fourth Int’l Workshop Feedback Control Implementation and Design in Computing Systems and Networks (FeBID), 2009.

D. Meisner, B.T. Gold, and T.F. Wenisch, “PowerNap: Eliminating Server Idle Power,” Proc. 14th Int’l Conf. Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2009.

P. Padala, K.-Y. Hou, K.G. Shin, X. Zhu, M. Uysal, Z. Wang, S. Singhal, and A. Merchant, “Automated Control of Multiple Virtualized Resources,” Proc. Fourth ACM European Conf. Computer Systems (EuroSys), 2009.

X. Wang, M. Chen, C. Lefurgy, and T.W. Keller, “SHIP: Scalable Hierarchical Power Control for Large-Scale Data Centers,” Proc. Int’l Conf. Parallel Architectures and Compilation Techniques (PACT), 2009.

A. Verma, G. Dasgupta, T.K. Nayak, P. De, and R. Kothari, “Server Workload Analysis for Power Minimization Using Consolidation,” Proc. Conf. USENIX Ann. Technical Conf., 2009.

Intel. Intel 5500 Series Datasheet vol. 1, 2009.

Yefu Wang and Xiaorui Wang, “Virtual Batching: Request Batching for Server Energy Conservation in Virtualized Data Centers”, IEEE Transactions On Parallel And Distributed Systems, Vol. 24, No. 8, August 2013.

X. Zhu, D. Young, B.J. Watson, J. Rolia, S. Singhal, B. Mckee, C. Hyser, D. Gmach, R. Gardner, T. Christian, and L. Cherkasova, “1000 Islands: An Integrated Approach to Resource Management for Virtualized Data Centers,” Cluster Computing, vol. 12, pp. 45- 47, 2009.


Full Text: PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

.......................................................................................................................................................................................................................

ISSN  2279 – 0381 |  IST HOMEJOURNAL HOME | Copyright IST 2012-13

.......................................................................................................................................................................................................................