Cloud Desktop Workload: a Characterization Study

被引：3
作者：
Casalicchio, Emiliano [1 ]
Iannucci, Stefano [1 ,2 ]
Silvestri, Luca [2 ]
机构：
[1] Univ Roma Tor Vergata, Dept Civil Engn & Comp Sci, Rome, Italy
[2] Grep Srl, Rome, Italy
来源：
2015 IEEE INTERNATIONAL CONFERENCE ON CLOUD ENGINEERING (IC2E 2015) | 2015年
关键词：
cloud computing; workload characterization; performance evaluation; cloud desktop; desktop-as-a-service; capacity planning; monitoring;
D O I：
10.1109/IC2E.2015.25
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Today the cloud-desktop service, or Desktop-as-a-Service (DaaS), is massively replacing Virtual Desktop Infrastructures (VDI), as confirmed by the importance of players entering the DaaS market. In this paper we study the workload of a DaaS provider, analyzing three months of real traffic and resource usage. What emerges from the study, the first on the subject at the best of our knowledge, is that the workload on CPU and disk usage are long-tail distributed (lognormal, weibull and pareto) and that the length of working sessions is exponentially distributed. These results are extremely important for: the selection of the appropriate performance model to be used in capacity planning or run-time resource provisioning; the setup of workload generators; and the definition of heuristic policies for resource provisioning. The paper provides an accurate distribution fitting for all the workload features considered and discusses the implications of results on performance analysis.
引用
收藏
页码：66 / 75
页数：10
相关论文
共 15 条
[1]   Cloud monitoring: A survey [J].
Aceto, Giuseppe ;
Botta, Alessio ;
de Donato, Walter ;
Pescape, Antonio .
COMPUTER NETWORKS, 2013, 57 (09) :2093-2115
[2]  
[Anonymous], ENT CLASS MON SOL EV
[3]  
Azmandian F., 2011, Proceedings of the 2011 IEEE 19th International Symposium on Modelling, Analysis & Simulation of Computer and Telecommunication Systems (MASCOTS 2011), P63, DOI 10.1109/MASCOTS.2011.63
[4]   Characterization and Comparison of Cloud versus Grid Workloads [J].
Di, Sheng ;
Kondo, Derrick ;
Cirne, Walfredo .
2012 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING (CLUSTER), 2012, :230-238
[5]  
Feitelson Dror G., 2015, WORKLOAD MODELING CO
[6]   Statistics-Driven Workload Modeling for the Cloud [J].
Ganapathi, Archana ;
Chen, Yanpei ;
Fox, Armando ;
Katz, Randy ;
Patterson, David .
2010 IEEE 26TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING WORKSHOPS (ICDE 2010), 2010, :87-92
[7]  
Grep, GREP RAINB CLOUD COM
[8]  
Khan A, 2012, IEEE IFIP NETW OPER, P1287, DOI 10.1109/NOMS.2012.6212065
[9]  
Menasce D. A., 2001, Capacity Planning for Web Services: Metrics, Models, and Methods
[10]   An Approach for Characterizing Workloads in Google Cloud to Derive Realistic Resource Utilization Models [J].
Moreno, Ismael Solis ;
Garraghan, Peter ;
Townend, Paul ;
Xu, Jie .
2013 IEEE SEVENTH INTERNATIONAL SYMPOSIUM ON SERVICE-ORIENTED SYSTEM ENGINEERING (SOSE 2013), 2013, :49-60
12