Generalized parallel-server fork-join queues with dynamic task scheduling

This paper introduces a generalization of the classical parallel-server fork-join queueing system in which arriving customers fork into multiple tasks, every task is uniquely assigned to one of the set of single-server queues, and each task consists of multiple iterations of different stages of execution, including task vacations and communication among sibling tasks. Several classes of dynamic polices are considered for scheduling multiple tasks at each of the single-server queues to maintain effective server utilization. The paper presents an exact matrix-analytic analysis of generalized parallel-server fork-join queueing systems, for small instances of the stochastic model, and presents an approximate matrix-analytic analysis and fixed-point solution, for larger instances of the model.

[1]  Vaidyanathan Ramaswami,et al.  A logarithmic reduction algorithm for quasi-birth-death processes , 1993, Journal of Applied Probability.

[2]  Warren Smith,et al.  Benchmarks and Standards for the Evaluation of Parallel Job Schedulers , 1999, JSSPP.

[3]  Mark S. Squillante,et al.  Stochastic analysis of multiserver systems , 2007, PERV.

[4]  Srinivas R. Chakravarthy,et al.  Matrix-Analytic Methods in Stochastic Models , 1996 .

[5]  Ray Jinzhu Chen.  A Hybrid Solution of Fork/Join Synchronization in Parallel Queues , 2001, IEEE Trans. Parallel Distributed Syst..

[6]  J. Little.  A Proof for the Queuing Formula: L = λW , 1961 .

[7]  F. Baccelli,et al.  The fork-join queue and related systems with synchronization constraints: stochastic ordering and computable bounds , 1989, Advances in Applied Probability.

[8]  B. Conolly.  Structured Stochastic Matrices of M/G/1 Type and Their Applications , 1991 .

[9]  Charles Knessl,et al.  A fork-join queueing model: Diffusion approximation, integral representations and asymptotics , 1996, Queueing Syst. Theory Appl..

[10]  Peter G. Taylor,et al.  Matrix-analytic methods: theory and applications , 2002 .

[11]  Patrick Sobalvarro,et al.  Demand-Based Coscheduling of Parallel Jobs on Multiprogrammed Multiprocessors , 1995, JSSPP.

[12]  L Bright,et al.  Equilibrium Distributions for Level-Dependent Quasi-Birth-and-Death Processes , 1996 .

[13]  Andrea C. Arpaci-Dusseau,et al.  Effective distributed scheduling of parallel workloads , 1996, SIGMETRICS '96.

[14]  J D Littler,et al.  A PROOF OF THE QUEUING FORMULA , 1961 .

[15]  Peter G. Taylor,et al.  Calculating the equilibrium distribution in level dependent quasi-birth-and-death processes , 1995 .

[16]  Mark S. Squillante,et al.  Dynamic Partitioning in Different Distributed-Memory Environments , 1996, JSSPP.

[17]  Anja Feldmann,et al.  Fitting mixtures of exponentials to long-tail distributions to analyze network performance models , 1997, Proceedings of INFOCOM '97.

[18]  Mark S. Squillante,et al.  Processor Allocation in Multiprogrammed Distributed-Memory Parallel Computer Systems , 1997, J. Parallel Distributed Comput..

[19]  Asser N. Tantawi,et al.  Approximate Analysis of Fork/Join Synchronization in Parallel Queues , 1988, IEEE Trans. Computers.

[20]  Alma Riska,et al.  An EM-based technique for approximating long-tailed data sets with PH distributions , 2004, Perform. Evaluation.

[21]  Chita R. Das,et al.  A closer look at coscheduling approaches for a network of workstations , 1999, SPAA '99.

[22]  R. Serfozo,et al.  Response times in M/M/s fork-join networks , 2004, Advances in Applied Probability.

[23]  Mark S. Squillante,et al.  Analysis of task migration in shared-memory multiprocessor scheduling , 1991, SIGMETRICS '91.

[24]  Vaidyanathan Ramaswami,et al.  Introduction to Matrix Analytic Methods in Stochastic Modeling , 1999, ASA-SIAM Series on Statistics and Applied Mathematics.

[25]  Armand M. Makowski,et al.  Interpolation Approximations for Symmetric Fork-Join Queues , 1994, Perform. Evaluation.

[26]  Mark S. Squillante,et al.  MATRIX-ANALYTIC ANALYSIS OF A MAP/PH/1 QUEUE FITTED TO WEB SERVER DATA , 2002 .

[27]  Chita R. Das,et al.  Alternatives to Coscheduling a Network of Workstations , 1999, J. Parallel Distributed Comput..

[28]  Anand Sivasubramaniam,et al.  A simulation-based study of scheduling mechanisms for a dynamic cluster environment , 2000, ICS '00.

[29]  Marcel F. Neuts,et al.  Matrix-geometric solutions in stochastic models - an algorithmic approach , 1982 .

[30]  Peter G. Taylor,et al.  Advances in Algorithmic Methods for Stochastic Models , 2000 .

[31]  Ren Asmussen,et al.  Fitting Phase-type Distributions via the EM Algorithm , 1996 .

[32]  S. Zachary,et al.  Loss networks , 2009, 0903.0640.