TU Darmstadt / ULB / TUbiblio

Provisioning and Performance Evaluation of Parallel 1 Systems with Output Synchronization

KhudaBukhsh, W. R. and Kar, S. and Koeppl, H. and Rizk, A. :
Provisioning and Performance Evaluation of Parallel 1 Systems with Output Synchronization.
[Online-Edition: https://dl.acm.org/citation.cfm?id=3300142]
In: ACM Transactions on Modeling and Performance Evaluation of Computing Systems (TOMPECS), 4 (1) Art. 6. ISSN 2376-3639
[Article] , (2019)

Official URL: https://dl.acm.org/citation.cfm?id=3300142

Abstract

Parallel server frameworks are widely deployed in modern large-data processing applications. Intuitively, splitting and parallel processing of the workload provides accelerated application response times and scaling flexibility. Examples of such frameworks include MapReduce, Hadoop, and Spark. For many applications, the dynamics of such systems are naturally captured by a Fork-Join (FJ) queuing model, where incoming jobs are split into tasks each of which is mapped to exactly one server. When all the tasks that belong to one job are executed, the job is reassembled and leaves the system. We consider this behavior at the output as a synchronization constraint. In this article, we study the performance of such parallel systems for different server properties, i.e., work-conservingness, phase-type behavior, and as suggested by recent evidence, for bursty input job arrivals. We establish a Large Deviations Principle for the steady-state job waiting times in an FJ system based on Markov-additive processes. Building on that,we present a performance analysis framework for FJ systems and provide computable bounds on the tail probabilities of the steady-state waiting times. We validate our bounds using estimates obtained through simulations. In addition, we define and analyze provisioning, a flexible division of jobs into tasks, in FJ systems. Finally, we use this framework together with real-world traces to show the benefits of an adaptive provisioning system that adjusts the service within an FJ system based on the arrival intensity.

Item Type: Article
Erschienen: 2019
Creators: KhudaBukhsh, W. R. and Kar, S. and Koeppl, H. and Rizk, A.
Title: Provisioning and Performance Evaluation of Parallel 1 Systems with Output Synchronization
Language: English
Abstract:

Parallel server frameworks are widely deployed in modern large-data processing applications. Intuitively, splitting and parallel processing of the workload provides accelerated application response times and scaling flexibility. Examples of such frameworks include MapReduce, Hadoop, and Spark. For many applications, the dynamics of such systems are naturally captured by a Fork-Join (FJ) queuing model, where incoming jobs are split into tasks each of which is mapped to exactly one server. When all the tasks that belong to one job are executed, the job is reassembled and leaves the system. We consider this behavior at the output as a synchronization constraint. In this article, we study the performance of such parallel systems for different server properties, i.e., work-conservingness, phase-type behavior, and as suggested by recent evidence, for bursty input job arrivals. We establish a Large Deviations Principle for the steady-state job waiting times in an FJ system based on Markov-additive processes. Building on that,we present a performance analysis framework for FJ systems and provide computable bounds on the tail probabilities of the steady-state waiting times. We validate our bounds using estimates obtained through simulations. In addition, we define and analyze provisioning, a flexible division of jobs into tasks, in FJ systems. Finally, we use this framework together with real-world traces to show the benefits of an adaptive provisioning system that adjusts the service within an FJ system based on the arrival intensity.

Journal or Publication Title: ACM Transactions on Modeling and Performance Evaluation of Computing Systems (TOMPECS)
Volume: 4
Number: 1
Publisher: Association for Computing Machinery ACM
Uncontrolled Keywords: Mathematics of computing, Queueing theory, Theory of computation, Performance evaluation, queuing systems, Fork-Join queues, Markov 22 additive processes, Parallel systems
Divisions: 18 Department of Electrical Engineering and Information Technology
18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications > Bioinspired Communication Systems
18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications
DFG-Collaborative Research Centres (incl. Transregio)
DFG-Collaborative Research Centres (incl. Transregio) > Collaborative Research Centres
DFG-Collaborative Research Centres (incl. Transregio) > Collaborative Research Centres > CRC 1053: MAKI – Multi-Mechanisms Adaptation for the Future Internet
DFG-Collaborative Research Centres (incl. Transregio) > Collaborative Research Centres > CRC 1053: MAKI – Multi-Mechanisms Adaptation for the Future Internet > B: Adaptation Mechanisms
DFG-Collaborative Research Centres (incl. Transregio) > Collaborative Research Centres > CRC 1053: MAKI – Multi-Mechanisms Adaptation for the Future Internet > B: Adaptation Mechanisms > Subproject B4: Planning
Date Deposited: 26 Feb 2019 08:50
Official URL: https://dl.acm.org/citation.cfm?id=3300142
Identification Number: TOMPECS0401-06
Export:

Optionen (nur für Redakteure)

View Item View Item