Yang Hu
ABSTRACT
The functional scope of today's software-defined data centers (SDDC) has expanded to such an extent that servers face a growing amount of critical background operational tasks like load monitoring, logging, migration, and duplication, etc. These ancillary operations, which we refer to as management operations, often nibble the stringent data center power envelope and exert a tremendous amount of pressure on front-end user tasks. However, existing power capping, peak shaving, and time shifting mechanisms mainly focus on managing data center power demand at the "macro level" -- they do not distinguish ancillary background services from user tasks, and therefore often incur significant performance degradation and energy overhead.
In this study we explore "micro-level" power management in SDDC: tuning a specific set of critical loads for the sake of overall system efficiency and performance. Specifically, we look at management operations that can often lead to resource contention and energy overhead in an IaaS SDDC. We assess the feasibility of this new power management paradigm by characterizing the resource and power impact of various management operations. We propose HOPE, a new system optimization framework for eliminating the potential efficiency bottleneck caused by the management operations in the SDDC. HOPE is implemented on a customized OpenStack cloud environment with heavily instrumented power infrastructure. We thoroughly validate HOPE models and optimization efficacy under various user workload scenarios. Our deployment experiences show that the proposed technique allows SDDC to reduce energy consumption by 19%, reduce management operation execution time by 25.4%, and in the meantime improve workload performance by 30%.
- Alvarez, C. 2011. NetApp deduplication for FAS and V-Series deployment and implementation guide. Technical ReportTR-3505. January (2011).Google Scholar
- Amazon EC2: http://aws.amazon.com/ec2/.Google Scholar
- Arzuaga, E. and Kaeli, D.R. 2010. Quantifying Load Imbalance on Virtualized Enterprise Servers. Proceedings of the First Joint WOSP/SIPEW International Conference on Performance Engineering (New York, NY, USA, 2010), 235--242. Google ScholarDigital Library
- Cidon, A., Rumble, S.M., Stutsman, R., Katti, S., Ousterhout, J. and Rosenblum, M. 2013. Copysets: Reducing the Frequency of Data Loss in Cloud Storage. Proceedings of the 2013 USENIX Conference on Annual Technical Conference (Berkeley, CA, USA, 2013), 37--48. Google ScholarDigital Library
- Delimitrou, C. and Kozyrakis, C. 2013. Paragon: QoS-aware Scheduling for Heterogeneous Datacenters. Proceedings of the eighteenth international conference on Architectural support for programming languages and operating systems - ASPLOS '13. (2013), 77--88. Google ScholarDigital Library
- Delimitrou, C. and Kozyrakis, C. 2014. Quasar: Resource-efficient and QoS-aware Cluster Management. Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems (New York, NY, USA, 2014), 127--144. Google ScholarDigital Library
- Dirolf, K.C.& M. 2011. MongoDB: The Definitive Guide.Google Scholar
- Ferdman, M., Adileh, A., Kocberber, O., Volos, S., Alisafaee, M., Jevdjic, D., Kaynak, C., Popescu, A.D., Ailamaki, A. and Falsafi, B. 2012. Clearing the clouds: a study of emerging scale-out workloads on modern hardware. Proceedings of the seventeenth international conference on Architectural Support for Programming Languages and Operating Systems (New York, NY, USA, 2012), 37--48. Google ScholarDigital Library
- Goiri, Í., Katsak, W., Le, K., Nguyen, T.D. and Bianchini, R. 2013. Parasol and GreenSwitch: Managing Datacenters Powered by Renewable Energy. Proceedings of the Eighteenth International Conference on Architectural Support for Programming Languages and Operating Systems (New York, NY, USA, 2013), 51--64. Google ScholarDigital Library
- Govindan, S., Liu, J., Kansal, A. and Sivasubramaniam, A. 2011. Cuanta: Quantifying Effects of Shared On-chip Resource Interference for Consolidated Virtual Machines. Proceedings of the 2Nd ACM Symposium on Cloud Computing (New York, NY, USA, 2011), 22:1--22:14. Google ScholarDigital Library
- Hossain, M.M., Huang, J.-C. and Lee, H.-H.S. 2012. Migration Energy-Aware Workload Consolidation in Enterprise Clouds. 2012 IEEE 4th International Conference on Cloud Computing Technology and Science. (2012), 405-- 410. Google ScholarDigital Library
- Koh, Y., Knauerhase, R., Brett, P., Bowman, M., Wen, Z. and Pu, C. 2007. An Analysis of Performance Interference Effects in Virtual Environments. 2007 IEEE International Symposium on Performance Analysis of Systems & Software. (2007), 200--209.Google Scholar
- Li, C., Hu, Y., Liu, L., Gu, J., Song, M., Liang, X., Yuan, J. and Li, T. 2015. Towards sustainable in-situ server systems in the big data era. Proceedings of the 42nd Annual International Symposium on Computer Architecture - ISCA '15. (2015), 14--26. Google ScholarDigital Library
- Li, C., Hu, Y., Zhou, R., Liu, M., Liu, L., Yuan, J. and Li, T. 2013. Enabling datacenter servers to scale out economically and sustainably. Proceedings of the 46th Annual IEEE/ACM International Symposium on Microarchitecture - MICRO-46. (2013), 322--333. Google ScholarDigital Library
- Li, C., Qouneh, A. and Li, T. 2012. iSwitch: Coordinating and optimizing renewable energy powered server clusters. Proceedings - International Symposium on Computer Architecture (2012), 512--523. Google ScholarDigital Library
- Li, C., Wang, R., Hu, Y., Zhou, R., Liu, M., Liu, L.J., Yuan, J.L., Li, T. and Qian, D.P. 2014. Towards automated provisioning and emergency handling in renewable energy powered datacenters. Journal of Computer Science and Technology. 29, 4 (2014), 618--630.Google ScholarCross Ref
- Li, C., Wang, R., Li, T., Qian, D. and Yuan, J. 2014. Managing Green Datacenters Powered by Hybrid Renewable Energy Systems. Proc. of 11th Int. Conf. on Automatic Computing. (2014), 261--272.Google Scholar
- Liu, L., Li, C., Sun, H., Hu, Y., Gu, J., Li, T., Xin, J. and Zheng, N. 2015. HEB: Deploying and Managing Hybrid Energy Buffers for Improving Datacenter Efficiency and Economy. Proceedings of the 42nd Annual International Symposium on Computer Architecture - ISCA '15 (2015), 463--475. Google ScholarDigital Library
- Liu, L., Li, C., Sun, H., Hu, Y., Xin, J., Zheng, N. and Li, T. 2015. Leveraging heterogeneous power for improving datacenter efficiency and resiliency. IEEE Computer Architecture Letters. 14, 1 (2015), 41--45.Google ScholarCross Ref
- Liu, L., Sun, H., Li, C., Hu, Y., Xin, J., Zheng, N. and Li, T. 2016. RE-UPS: an adaptive distributed energy storage system for dynamically managing solar energy in green datacenters. The Journal of Supercomputing. 72, 1 (2016), 295--316. Google ScholarDigital Library
- Liu, L., Sun, H., Li, C., Hu, Y., Zheng, N. and Li, T. 2016. Towards an Adaptive Multi-Power-Source Datacenter. Proceedings of the 30th ACM on International Conference on Supercomputing - ICS '16 (2016). Google ScholarDigital Library
- Moshref, M., Yu, M., Sharma, A. and Govindan, R. 2013. Scalable Rule Management for Data Centers. NSDI'13 Proceedings of the 10th USENIX conference on Networked Systems Design and Implementation. (2013), 157--170. Google ScholarDigital Library
- Mysql 2011. MySQL Workbench.Google Scholar
- Nathuji, R. and Schwan, K. 2007. VirtualPower: coordinated power management in virtualized enterprise systems. Proceedings of twenty-first ACM SIGOPS symposium on Operating systems principles - SOSP '07. (2007), 265. Google ScholarDigital Library
- Novakovic, D., Vasic, N. and Novakovic, S. 2013. Deepdive: Transparently identifying and managing performance interference in virtualized environments. USENIX ATC'13 Proceedings of the 2013 USENIX conference on Annual Technical Conference. (2013), 219--230. Google ScholarDigital Library
- OpenStack Ceilometer: https://wiki.openstack.org/wiki/Ceilometer.Google Scholar
- OpenStack Cloud Software: www.openstack.org.Google Scholar
- OpenStack Kwapi: https://github.com/openstack/kwapi.Google Scholar
- OpenStack Rally: https://github.com/openstack/rally.Google Scholar
- Pelley, S., Meisner, D., Zandevakili, P., Wenisch, T.F. and Underwood, J. 2010. Power Routing: Dynamic Power Provisioning in the Data Center. Proceedings of the Fifteenth Edition of ASPLOS on Architectural Support for Programming Languages and Operating Systems (New York, NY, USA, 2010), 231--242. Google ScholarDigital Library
- Shen, K., Shriraman, A., Dwarkadas, S., Zhang, X. and Chen, Z. 2013. Power Containers: An OS Facility for Fine-Grained Power and Energy Management on Multicore Servers. Proceedings of the 16th international conference on Architectural Support for Programming Languages and Operating Systems. (2013), 65--76. Google ScholarDigital Library
- Soundararajan, V. and Anderson, J.M. 2010. The Impact of Management Operations on the Virtualized Datacenter. Proceedings of the 37th Annual International Symposium on Computer Architecture (New York, NY, USA, 2010), 326--337. Google ScholarDigital Library
- Splunk: http://www.splunk.com/product.Google Scholar
- SumoLogic: http://www.sumologic.com/.Google Scholar
- The Software-Defined Data Center: 2015. http://www.vmware.com/software-defined-datacenter/index.html.Google Scholar
- Vasić, N., Novaković, D., Miučin, S., Kostić, D. and Bianchini, R. 2012. DejaVu: accelerating resource allocation in virtualized environments. ACM SIGARCH Computer Architecture News. 40, 1 (2012), 423. Google ScholarDigital Library
- vRealize Log Insight 3.0 Documentation Center: http://pubs.vmware.com/log-insight-30/index.jsp?topic=%2Fcom.vmware.log-insight.getting-started.doc%2FGUID-4E3853AA-EFBF-4004-B182-DF5F6DC3826F.html.Google Scholar
- vRealize Operations IT Operations Management: VMware: http://www.vmware.com/ap/products/vrealize-operations. Accessed: 2015-12-13.Google Scholar
- Wang, C., Rayan, I.A., Eisenhauer, G., Schwan, K., Talwar, V., Wolf, M. and Huneycutt, C. 2012. VScope: Middleware for Troubleshooting Time-sensitive Data Center Applications. Proceedings of the 13th International Middleware Conference (New York, NY, USA, 2012), 121--141. Google ScholarDigital Library
- Wang, D., Ren, C. and Sivasubramaniam, A. 2013. Virtualizing Power Distribution in Datacenters. Proceedings of the 40th Annual International Symposium on Computer Architecture (New York, NY, USA, 2013), 595--606. Google ScholarDigital Library
- Zabbix: The Ultimate Enterprise-class Monitoring Platform: http://www.zabbix.com/.Google Scholar
- ZFS Filesystem: http://zfsonlinux.org/.Google Scholar
- Zhang, I., Denniston, T., Baskakov, Y. and Garthwaite, A. 2013. Optimizing VM Checkpointing for Restore Performance in VMware ESXi. Proceedings of the 2013 USENIX Conference on Annual Technical Conference (Berkeley, CA, USA, 2013), 1--12. Google ScholarDigital Library
- Zhou, R., Liu, M. and Li, T. 2013. Characterizing the efficiency of data deduplication for big data storage management. Workload Characterization (IISWC), 2013 IEEE International Symposium on.Google Scholar
Recommendations
Vpm tokens: virtual machine-aware power budgeting in datacenters
HPDC '08: Proceedings of the 17th international symposium on High performance distributed computingPower consumption and cooling overheads are becoming increasingly significant for large scale machines, affecting overall costs and the ability to extend resource capacities and performance capabilities. To help mitigate these issues, active power ...
VPM tokens: virtual machine-aware power budgeting in datacenters
Power consumption and cooling overheads are becoming increasingly significant for enterprise datacenters, affecting overall costs and the ability to extend resource capacities. To help mitigate these issues, active power management technologies are ...
VIP: Virtual Performance-State for Efficient Power Management of Virtual Machines
SoCC '18: Proceedings of the ACM Symposium on Cloud ComputingA power management policy aims to improve energy efficiency by choosing an appropriate performance (voltage/frequency) state for a given core. In current virtualized environments, multiple virtual machines (VMs) running on the same core must follow a ...
Comments