Data Center Network Throughput Analysis Using Queueing Petri Nets

In this paper, we contribute performance modeling and analysis approach in computer networks. We present a meta-model designed for the performance modeling of network infrastructures in modern data centers. Instances of our meta-model can be automatically transformed into stochastic simulation models for performance prediction. In this paper, we present a transformation to Queueing Petri Nets (QPNs). We show that despite the high level of abstraction of the QPN models, we are able to predict the utilization of resources with good accuracy within a short time.

[1]  Arun Prakash,et al.  Formal Methods for Modeling, Refining and Verifying Autonomic Components of Computer Networks , 2012, Trans. Comput. Sci..

[2]  Peter G. Harrison,et al.  A general performance model interchange format , 2006, valuetools '06.

[3]  Andreas Mitschele-Thiel,et al.  Performance engineering of SDL/MSC systems , 1999, Comput. Networks.

[4]  Gianfranco Ciardo,et al.  Modeling a fibre channel switch with stochastic Petri nets , 1995, SIGMETRICS '95/PERFORMANCE '95.

[5]  Falko Bause,et al.  Queueing Petri Nets-A formalism for the combined qualitative and quantitative analysis of systems , 1993, Proceedings of 5th International Workshop on Petri Nets and Performance Models.

[6]  Samuel Kounev,et al.  Architecture-level software performance abstractions for online performance prediction , 2014, Sci. Comput. Program..

[7]  Pieter S. Kritzinger,et al.  Using UML models for the performance analysis of network systems , 2005, Comput. Networks.

[8]  Ramón Puigjaner,et al.  Performance modelling of computer networks , 2003, LANC '03.

[9]  Samuel Kounev,et al.  A Methodology for Performance Modeling of Distributed Event-Based Systems , 2008, 2008 11th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing (ISORC).

[10]  Peter G. Harrison,et al.  Network traffic behaviour in switched Ethernet systems , 2004, Perform. Evaluation.

[11]  Samuel Kounev,et al.  QPME: a performance modeling tool based on queueing Petri Nets , 2009, PERV.

[12]  Lars Michael Kristensen,et al.  Specification and Validation of an Edge Router Discovery Protocol for Mobile Ad Hoc Networks , 2004, SoftSpez Final Report.

[13]  Peter G. Harrison,et al.  Performance modelling of communication networks and computer architectures , 1992, International computer science series.

[14]  Reinhard German,et al.  SYNTONY: network protocol simulation based on standard-conform UML 2 models , 2007, ValueTools '07.

[15]  David Evans,et al.  TIME: An Open Platform for Capturing, Processing and Delivering Transport-Related Data , 2008, 2008 5th IEEE Consumer Communications and Networking Conference.

[16]  Samuel Kounev,et al.  Automated simulation-based capacity planning for enterprise data fabrics , 2011, SimuTools.

[17]  Reinhard German,et al.  SYNTONY: network protocol simulation based on standard-conform UML 2 models , 2007, Valuetools 2007.

[18]  Piotr Rygielski,et al.  Model-based throughput prediction in data center networks , 2013, 2013 IEEE International Workshop on Measurements & Networking (M&N).

[19]  Piotr Rygielski,et al.  A meta-model for performance modeling of dynamic virtualized network infrastructures , 2013, ICPE '13.

[20]  Samuel Kounev,et al.  Evaluating and Modeling Virtualization Performance Overhead for Cloud Environments , 2011, CLOSER.

[21]  Dmitry A. Zaitsev,et al.  A Parametric Colored Petri Net Model of a Switched Network , 2011, Int. J. Commun. Netw. Syst. Sci..

[22]  Samuel Kounev,et al.  Stochastic Modeling and Analysis Using QPME: Queueing Petri Net Modeling Environment v2.0 , 2012, Petri Nets.

[23]  Steffen Becker,et al.  The Palladio component model for model-driven performance prediction , 2009, J. Syst. Softw..