ABSTRACT
Power estimation of software processes provides critical indicators to drive scheduling or power capping heuristics. State-of-the-art solutions can perform coarse-grained power estimation in virtualized environments, typically treating virtual machines (VMs) as a black box. Yet, VM-based systems are nowadays commonly used to host multiple applications for cost savings and better use of energy by sharing common resources and assets.
In this paper, we propose a fine-grained monitoring middleware providing real-time and accurate power estimation of software processes running at any level of virtualization in a system. In particular, our solution automatically learns an application-agnostic power model, which can be used to estimate the power consumption of applications.
Our middleware implementation, named BitWatts, builds on a distributed actor implementation to collect process usage and infer fine-grained power consumption without imposing any hardware investment (e.g., power meters). BitWatts instances use high-throughput communication channels to spread the power consumption across the VM levels and between machines. Our experiments, based on CPU- and memory-intensive benchmarks running on different hardware setups, demonstrate that BitWatts scales both in number of monitored processes and virtualization levels. This non-invasive monitoring solution therefore paves the way for scalable energy accounting that takes into account the dynamic nature of virtualized environments.
Supplemental Material
- SPECjbb2013 Design Document. Standard Performance Evaluation Corporation (SPEC) (2013).Google Scholar
- Ben-Yehuda, M., Day, M. D., Dubitzky, Z., Factor, M., Har'El, N., Gordon, A., Liguori, A., Wasserman, O., and Yassour, B.-A. The Turtles Project: Design and Implementation of Nested Virtualization. In Proc. of the USENIX Symposium on Operating Systems Design and Implementation (OSDI) (Oct. 2010), pp. 423--436. Google ScholarDigital Library
- Bertran, R., Becerra, Y., Carrera, D., Beltran, V., Gonzílez, M., Martorell, X., Navarro, N., Torres, J., and Ayguadé, E. Energy Accounting for Shared Virtualized Environments Under DVFS Using PMC-based Power Models. Future Generation Computer Systems 28, 2 (2012), pp. 457--468. Google ScholarDigital Library
- Bienia, C. Benchmarking Modern Multiprocessors. PhD thesis, Princeton University, Jan. 2011. Google ScholarDigital Library
- Bircher, W. L., and John, L. K. Complete System Power Estimation: A Trickle-Down Approach Based on Performance Events. In Proc. of IEEE International Symposium on Performance Analysis of Systems & Software (ISPASS) (Apr. 2007), pp. 158--168.Google Scholar
- Bohra, A., and Chaudhary, V. VMeter: Power Modelling for Virtualized Clouds. In Proc. of IEEE International Symposium on Parallel Distributed Processing (IPDPSW) (Apr. 2010), pp. 1--8.Google Scholar
- Contreras, G., and Martonosi, M. Power prediction for intel XScale® processors using performance monitoring unit events. In Proc. of IEEE International Symposium on Low Power Electronics and Design (ISLPED) (Aug. 2005), pp. 221--226. Google ScholarDigital Library
- Cook, G. How Clean is Your Cloud? Greenpeace, Apr. 2012.Google Scholar
- Hähnel, M., Döbel, B., Völp, M., and Härtig, H. Measuring Energy Consumption for Short Code Paths Using RAPL. ACM SIGMETRICS Performance Evaluation Review 40, 3 (Dec. 2012), pp. 13--17. Google ScholarDigital Library
- Janacek, S., Schroder, K., Schomaker, G., Nebel, W., Ruschen, M., and Pistoor, G. Modeling and approaching a cost transparent, specific data center power consumption. In Proc. of International Conference on Energy Aware Computing (ICEAC) (Dec. 2012), pp. 1--6.Google ScholarCross Ref
- Kansal, A., Zhao, F., Liu, J., Kothari, N., and Bhattacharya, A. A. Virtual Machine Power Metering and Provisioning. In Proc. of ACM Symposium on Cloud Computing (SoCC) (June 2010), pp. 39--50. Google ScholarDigital Library
- Kivity, A., Kamay, Y., Laor, D., Lublin, U., and Liguori, A. kvm: the Linux Virtual Machine Monitor. In Proc. of the Linux Symposium (June 2007), vol. 1, pp. 225--230.Google Scholar
- Knauth, T., and Fetzer, C. DreamServer: Truly On-Demand Cloud Services. In Proc. of ACM SIGOPS International Conference on Systems & Storage (SYSTOR) (June 2014), pp. 1--11. Google ScholarDigital Library
- Koller, R., Verma, A., and Neogi, A. WattApp: An Application Aware Power Meter for Shared Data Centers. In Proc. of ACM International Conference on Autonomic Computing (ICAC) (June 2010), pp. 31--40. Google ScholarDigital Library
- Krevat, E., Tucek, J., and Ganger, G. R. Disks Are Like Snowflakes: No Two Are Alike. In Proc. of USENIX conference on Hot topics in Operating Systems (HotOS) (May 2011), pp. 14--14. Google ScholarDigital Library
- Krishnan, B., Amur, H., Gavrilovska, A., and Schwan, K. VM Power Metering: Feasibility and Challenges. ACM SIGMETRICS Performance Evaluation Review 38, 3 (Jan. 2011), pp. 56--60. Google ScholarDigital Library
- Li, T., and John, L. K. Run-time Modeling and Estimation of Operating System Power Consumption. ACM SIGMETRICS Performance Evaluation Review 31, 1 (June 2003), pp. 160--171. Google ScholarDigital Library
- Lim, M. Y., Porterfield, A., and Fowler, R. J. Soft-Power: Fine-Grain Power Estimations Using Performance Counters. In Proc. of ACM International Symposium on High Performance Distributed Computing (HPDC) (June 2010), pp. 308--311. Google ScholarDigital Library
- McCullough, J. C., Agarwal, Y., Chandrashekar, J., Kuppuswamy, S., Snoeren, A. C., and Gupta, R. K. Evaluating the Effectiveness of Model-Based Power Characterization. In Proc. of USENIX Annual Technical Conference (ATC) (June 2011), pp. 12--12. Google ScholarDigital Library
- Noureddine, A., Bourdon, A., Rouvoy, R., and Seinturier, L. Runtime Monitoring of Software Energy Hotspots. In Proc. of the IEEE/ACM International Conference on Automated Software Engineering (ASE) (Sept. 2012), pp. 160--169. Google ScholarDigital Library
- Noureddine, A., Rouvoy, R., and Seinturier, L. Unit Testing of Energy Consumption of Software Libraries. In Proc. of ACM Symposium On Applied Computing (Mar. 2014), pp. 1200--1205. Google ScholarDigital Library
- Orgerie, A.-C., Assuncao, M. D. d., and Lefevre, L. A Survey on Techniques for Improving the Energy Efficiency of Large-scale Distributed Systems. ACM Computing Surveys (CSUR) 46, 4 (Apr. 2014), pp. 47:1--47:31. Google ScholarDigital Library
- Powell, M. D., Biswas, A., Emer, J. S., Mukherjee, S. S., Sheikh, B. R., and Yardi, S. CAMP: A Technique to Estimate Per-Structure Power at Run-time using a Few Simple Parameters. In Proc. of IEEE International Symposium on High Performance Computer Architecture (HPCA) (Feb. 2009), pp. 289--300.Google ScholarCross Ref
- Sanderson, D. Programming Google App Engine: Build and Run Scalable Web Apps on Google's Infrastructure. O'Reilly Media, Inc., Dec. 2009. Google ScholarDigital Library
- Shen, K., Shriraman, A., Dwarkadas, S., Zhang, X., and Chen, Z. Power Containers: An OS Facility for Fine-grained Power and Energy Management on Multicore Servers. In Proc. of International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) (Apr. 2013), pp. 65--76. Google ScholarDigital Library
- Sterling, C. Energy Consumption tool in Visual Studio 2013, July 2013.Google Scholar
- Stoess, J., Lang, C., and Bellosa, F. Energy Management for Hypervisor-Based Virtual Machines. In Proc. of USENIX Annual Technical Conference (ATC) (June 2007), pp. 1--14. Google ScholarDigital Library
- The Climate Group. SMART 2020: Enabling the low carbon economy in the information age, 2008.Google Scholar
- Verma, A., Ahuja, P., and Neogi, A. pMapper: Power and Migration Cost Aware Application Placement in Virtualized Systems. In Proc. of ACM/IFIP/USENIX Middleware Conference (Dec. 2008), Springer, pp. 243--264. Google ScholarDigital Library
- Versick, D., Wassmann, I., and Tavangarian, D. Power Consumption Estimation of CPU and Peripheral Components in Virtual Machines. ACM SIGAPP Applied Computing Review 13, 3 (Sept. 2013), pp. 17--25. Google ScholarDigital Library
- Wang, S., Chen, H., and Shi, W. SPAN: A software power analyzer for multicore computer systems. Sustainable Computing: Informatics and Systems 1, 1 (2011), pp. 23--34.Google ScholarCross Ref
- Zhai, Y., Zhang, X., Eranian, S., Tang, L., and Mars, J. HaPPy: Hyperthread-aware Power Profiling Dynamically. In Proc. of USENIX Annual Technical Conference (ATC) (June 2014), pp. 211--217. Google ScholarDigital Library
Index Terms
- Process-level power estimation in VM-based systems
Recommendations
VM consolidation
In recent years, Cloud computing has been emerging as the next big revolution in both computer networks and Web provisioning. Because of raised expectations, several vendors, such as Amazon and IBM, started designing, developing, and deploying Cloud ...
Network-centric Performance Improvement for Live VM Migration
CLOUD '15: Proceedings of the 2015 IEEE 8th International Conference on Cloud ComputingLive Virtual Machine (VM) migrations are an important tool that is used in modern data centers in order to e.g. Consolidate server racks for maintenance or optimize VM placements across physical hosts. However, live VM migration causes a lot of network ...
Virtual Device Passthrough for High Speed VM Networking
ANCS '15: Proceedings of the Eleventh ACM/IEEE Symposium on Architectures for networking and communications systemsSupporting network I/O at high packet rates in virtual machines is fundamental for the deployment of Cloud data centers and Network Function Virtualization. Historically, SR-IOV and hardware passthrough were thought as the only viable solution to reduce ...
Comments