Abstract
Energy consumption is a primary concern for datacenters? management. Numerous datacenters are relying on virtualization, as it provides flexible resource management means such as virtual machine (VM) checkpoint/restart, migration and consolidation. However, one of the main hindrances to server consolidation is physical memory. In nowadays cloud, memory is generally statically allocated to VMs and wasted if not used. Techniques (such as ballooning) were introduced for dynamically reclaiming memory from VMs, such that only the needed memory is provisioned to each VM. However, the challenge is to precisely monitor the needed memory, i.e., the working set of each VM. In this paper, we thoroughly review the main techniques that were proposed for monitoring the working set of VMs. Additionally, we have implemented the main techniques in the Xen hypervisor and we have defined different metrics in order to evaluate their efficiency. Based on the evaluation results, we propose Badis, a system which combines several of the existing solutions, using the right solution at the right time. We also propose a consolidation extension which leverages Badis in order to pack the VMs based on the working set size and not the booked memory. The implementation of all techniques, our proposed system, and the benchmarks we have used are publicly available in order to support further research in this domain.
- https://github.com/papers02/working_set.gitGoogle Scholar
- U. Hölzle and L. André Barroso. The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines. Morgan and Claypool Publishers, 2009. Google Scholar
Digital Library
- America's Data Centers Are Wasting Huge Amounts of Energy. http://anthesisgroup.com/wp-content/uploads/2014/08/Data-Center-IB-final826.pdfGoogle Scholar
- C. Subramanian, A. Vasan, and A. Sivasubramaniam. Reducing data center power with server consolidation: Approximation and evaluation. HiPC, 2010.Google Scholar
Cross Ref
- L. André Barroso and U. Hölzle The Case for Energy-Proportional Computing. IEEE Computer 2007. Google Scholar
Digital Library
- C. Delimitrou and C. Kozyrakis Quasar: resource-efficient and QoS-aware cluster management. ASPLOS 2014. Google Scholar
Digital Library
- D. Meisner, B. T Gold, and T. F Wenisch The PowerNap Server Architecture. ACM Transaction on Computer Systems 2011. Google Scholar
Digital Library
- K. T. Lim, J. Chang, T. N. Mudge, P. Ranganathan, S. K. Reinhardt, T. F. Wenisch Disaggregated memory for expansion and sharing in blade servers. ISCA 2009.% Google Scholar
Digital Library
- %S. Barker, T. Wood, P. Shenoy, and R. Sitaraman. An Empirical Study of Memory Sharing in Virtual Machines.% ATC 2012. Google Scholar
Digital Library
- G. Milos, D. G. Murray, S. Hand, and M. A. Fetterman Satori: enlightened page sharing. ATC 2009. Google Scholar
Digital Library
- P. Barham, B. Dragovic, K. Fraser, S. Hand, T. Harris, A. Ho, R. Neugebauer, I. Pratt, A. Warfield Xen and the Art of Virtualization. SOSP 2003. Google Scholar
Digital Library
- Amazon Web Services, Inc. https://aws.amazon.com/ec2/Google Scholar
- C. A. Waldspurger Memory Resource Management in VMware ESX Server. OSDI 2002. Google Scholar
Digital Library
- https://blog.xenproject.org/2008/08/27/xen-33-feature-memory-overcommit/. visited on May 2017.Google Scholar
- https://access.redhat.com/documentation/en-US/Red_Hat_Enterprise_Linux/6/html/Deployment_Guide/s2-proc-meminfo.html. visited on May 2017.Google Scholar
- J. Chiang, L. Han-Lin, and C. Tzi-cker. Memory Working Set-based Physical Memory Ballooning. ICAC 2013.Google Scholar
- S. T. Jones, A. C. Arpaci-Dusseau, and R. H. Arpaci-Dusseau. Geiger: monitoring the buffer cache in a virtual machine environment. SIGARCH 2006. Google Scholar
Digital Library
- R. H. Patterson, G. A. Gibson, E. Ginting, D. Stodolsky, and J. Zelenka. Informed prefetching and caching. SOSP 1995. Google Scholar
Digital Library
- P. Lu and K. She. Virtual machine memory access tracing with hypervisor exclusive cache. ATC 2007. Google Scholar
Digital Library
- Blackburn, S. M., Garner, R., Hoffman, C., Khan, A. M., McKinley, K. S., Bentzur, R., Diwan, A., Feinberg, D., Frampton, D., Guyer, S. Z., Hirzel, M., Hosking, A., Jump, M., Lee, H., Moss, J. E. B., Phansalkar, A., Stefanovic, D., VanDrunen, T., von Dincklage, D., and Wiedermann, B. The DaCapo Benchmarks: Java Benchmarking Development and Analysis. OOPSLA '06: Proceedings of the 21st annual ACM SIGPLAN conference on Object-Oriented Programing, Systems, Languages, and Applications, (Portland, OR, USA, October 22--26, 2006) Google Scholar
Digital Library
- CloudSuite. http://cloudsuite.ch/. visited on May 2017.Google Scholar
- T. G. Armstrong, V. Ponnekanti, D. Borthakur, and M. Callaghan LinkBench: a database benchmark based on the Facebook social graph. SIGMOD 2013. Google Scholar
Digital Library
- W. Zhao and Z. Wang Dynamic memory balancing for virtual machines. VEE 2009. Google Scholar
Digital Library
- W. Zhao, X. Jin, Z. Wang, X. Wang, Y. Luo, and X. Li Low cost working set size tracking. ATC 2011. Google Scholar
Digital Library
- Melekhova A, Markeeva L. Estimating Working Set Size by Guest OS Performance Counters Means. The Sixth International Conference on Cloud Computing, GRIDs, and Virtualization 2015.Google Scholar
- E. Bugnion, S. Devine, K. Govil, and M. Rosenblum Disco: Running Commodity Operating Systems on Scalable Multiprocessors. ACM Trans. Computer Systems, vol. 15, no. 4, pp. 412--447, 1997. Google Scholar
Digital Library
- Gupta D, Lee S, Vrable M, Savage S, Snoeren C A, Varghese G, Voelker M. G, Vahdat A Difference Engine: Harnessing Memory Redundancy in Virtual Machines OSDI 2008.% Google Scholar
Digital Library
- %Weiming Zhao and Zhenlin Wang% Dynamic Memory Balancing for Virtual Machines.% VEE 2009.% Google Scholar
Digital Library
- %D. Magenheimer, C. Mason, D. McCracken, and K. Hackel,% Paravirtualized Paging.% Workshop I/O Virtualization 2008 Google Scholar
Digital Library
- Tudor-Ioan Salomie, Gustavo Alonso, Timothy Roscoe, and Kevin Elphinstone. Application level ballooning for efficient server consolidation. EuroSys 2013.% Google Scholar
Digital Library
- %Hwanju Kim, Heeseung Jo, and Joonwon LeeJ% XHive: Efficient Cooperative Caching for Virtual Machines.% IEEE TRANSACTIONS ON COMPUTERS 2011.% Google Scholar
Digital Library
- %Woomin Hwang, Yangwoo Roh, Youngwoo Park, Ki-Woong Park, and Kyu Ho Par.% HyperDealer: Reference-pattern-aware Instant Memory Balancing for Consolidated Virtual Machines.% Cloud 2010. Google Scholar
Digital Library
- Weiming Zhao Zhenlin Wang. Dynamic Memory Balancing for Virtualization. TACO 2016.Google Scholar
- Dan Magenheimer, Chris Mason, Dave McCracken, Kurt Hackel. Transcendent Memory and Linux. Ottawa Linux Symposium (OLS) 2009Google Scholar
- Irina Chihaia Tuduce and Thomas Gross. Adaptive Main Memory Compression. ATC 2005.Google Scholar
- Gennady Pekhimenko, Todd C. Mowry, and Onur Mutlu. Linearly Compressed Pages: A Main Memory Compression Framework with Low Complexity and Low Latency. PACT 2012. Google Scholar
Digital Library
- Lei Yang Haris Lekatsas Robert P. Dick. High-Performance Operating System Controlled Memory Compression. DAC 2006. Google Scholar
Digital Library
- Pin Zhou, Vivek Pandey, Jagadeesan Sundaresan, Anand Raghuraman, Yuanyuan Zhou and Sanjeev Kumar. Dynamic tracking of page miss ratio curve for memory management. ASPLOS 2004. Google Scholar
Digital Library
- Carl A. Waldspurger, Nohhyun Park, Alexander Garthwaite, and Irfan Ahmad. Efficient MRC Construction with SHARDS. FAST 2015.% Google Scholar
Digital Library
- %Anna Melekhova.% Machine Learning in Virtualization: Estimate a Virtual Machine's Working Set Size.% CLOUD 2013. Google Scholar
Digital Library
- Haikun Liu, Cheng-Zhong Xu, Hai Jin, Jiayu Gong, Xiaofei Liao Energy modeling for live migration of virtual machines. Cluster Computingi. Google Scholar
Digital Library
- William Voorsluys, James Broberg, Srikumar Venugopal, Rajkumar Buyya Cost of Virtual Machine Live Migration in Clouds: A Performance Evaluation. CloudCom. Google Scholar
Digital Library
- Anton Beloglazov, Rajkumar Buyya OpenStack Neat: a framework for dynamic and energy-efficient consolidation of virtual machines in OpenStack clouds. Concurrency and Computation: Practice and Experience. Google Scholar
Digital Library
- Omar Sefraoui, Mohammed Aissaoui, Mohsine Eleuldj Openstack: Toward an open-source solution for cloud computing. International Journal of Computer Applications.Google Scholar
- Sheng Di, Franck Cappello. GloudSim: Google trace based cloud simulator with virtual machines. SPE 2015. Google Scholar
Digital Library
- Google Traces. https://github.com/google/cluster-data/blob/master/ClusterData2011_2.mdGoogle Scholar
- Meng, Xiaoqiao and Isci, Canturk and Kephart, Jeffrey and Zhang, Li and Bouillet, Eric and Pendarakis, Dimitrios. Efficient Resource Provisioning in Compute Clouds via VM Multiplexing. ICAC 2010. Google Scholar
Digital Library
- A. Karve, T. Kimbrel, G. Pacifici, M. Spreitzer, M. Sviridenko, and A. Tantawi. Dynamic placement for clustered web applications. In WWW, 2006. Google Scholar
Digital Library
- K.H.Kim, A.Beloglazov, R.Buyya. Power-aware provisioning of cloud resources for real-time services. MGC 2009. Google Scholar
Digital Library
- A.Beloglazov, R.Buyya. Energy efficient resource management in virtualized cloud datacenters. Cloud and Grid Computing 2010. Google Scholar
Digital Library
- H.S. Abdelsalam, K. Maly, R. Mukkamala, M. Zubair, D. Kaminsky. Analysis of energy efficiency in Clouds. Computation World: Future Computing, Service Computation, Cognitive, Adaptive, Content, Patterns, 2009. Google Scholar
Digital Library
- G.Jung, M.A.Hiltunen, K.R.Joshi, R.D.Schlichting, C.Pu Mistral:dynamically managing power, performance, and adaptation cost in Cloud infrastructures. ICDCS 2010. Google Scholar
Digital Library
- Feller E, Rilling L, Morin C. Snooze: a scalable and autonomic virtual machine management framework for private clouds. CCGrid 2012. Google Scholar
Digital Library
- Jinchun Kim, Viacheslav Fedorov, Paul V. Gratz, A. L. Narasimha Reddy Dynamic Memory Pressure Aware Ballooning. MEMSYS 2015. Google Scholar
Digital Library
- Eolas cloud provider. https://www.eolas.fr/Google Scholar
Index Terms
Working Set Size Estimation Techniques in Virtualized Environments: One Size Does not Fit All
Recommendations
Working Set Size Estimation Techniques in Virtualized Environments: One Size Does not Fit All
SIGMETRICS '18Energy consumption is a primary concern for datacenters' management. Numerous datacenters are relying on virtualization, as it provides flexible resource management means such as virtual machine (VM) checkpoint/restart, migration and consolidation. ...
Working Set Size Estimation Techniques in Virtualized Environments: One Size Does not Fit All
SIGMETRICS '18: Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer SystemsEnergy consumption is a primary concern for datacenters' management. Numerous datacenters are relying on virtualization, as it provides flexible resource management means such as virtual machine (VM) checkpoint/restart, migration and consolidation. ...
Transparently bridging semantic gap in CPU management for virtualized environments
Consolidated environments are progressively accommodating diverse and unpredictable workloads in conjunction with virtual desktop infrastructure and cloud computing. Unpredictable workloads, however, aggravate the semantic gap between the virtual ...






Comments