Results 101 to 110 of about 149 (130)

Throughput Scalability Analysis of Fork-Join Queueing Networks

Operations Research, 2018
Parallel and distributed processing systems have expanded in size as technology advances in cloud computing and big data analytics. A critical issue concerns throughput scalability: whether throughput decreases to zero as the systems scale in size and capabilities. We model parallel and distributed processing systems as fork and join queueing networks
Yun Zeng, Augustin Chaintreau, Don Towsley, Cathy H. Xia   +3 more
openaire   +2 more sources

Biased Processor Sharing in Fork-Join Queues

2018
We consider a fork-join system in which a fixed amount of computational resources has to be distributed among the K tasks forming the jobs. The queueing disciplines of the fork- and join- queues are First Come First Served. At each epoch, at most K tasks are in service while the others wait in the fork-queues. We propose an algorithm with a very simple
Andrea Marin, Sabina Rossi, Matteo Sottana   +2 more
openaire   +1 more source

Analysis of Fork/Join and Related Queueing Systems

ACM Computing Surveys, 2014
Fork/join (F/J) requests arise in contexts such as parallel computing, query processing in parallel databases, and parallel disk access in RAID. F/J requests spawnKtasks that are sent toKparallel servers, and the completion of allKtasks marks the completion of an F/J request.
openaire   +1 more source

Acyclic fork-join queuing networks

Journal of the ACM, 1989
In this paper the class of acyclic fork-join queuing networks that arise in various applications, including parallel processing and flexible manufacturing are studied. In such queuing networks, a fork describes the simultaneous creation of several new customers, which are sent to different queues.
François Baccelli, William A. Massey, Donald F. Towsley   +2 more
openaire   +2 more sources

A control policy for fork-join queueing network

Proceedings of 1995 34th IEEE Conference on Decision and Control, 2002
This paper considered the fork-join queueing network. A control policy was developed based on its max-algebra model. By controlling the epochs at which the external source tasks enter the system, this policy makes the network to operate at its ideal maximum output rate and at the same time, the buffers in the network have minimum capacity.
null Liu Ruihua, null Tu Fengsheng
openaire   +1 more source

Scalability of fork/join queueing networks with blocking

Proceedings of the 2007 ACM SIGMETRICS international conference on Measurement and modeling of computer systems, 2007
This paper investigates how the through put of a general fork-join queueing network with blocking behaves as the number of nodes increases to infinity while the processing speed and buffer space of each node stay unchanged. The problem is motivated by applications arising from distributed systems and computer networks.
Cathy H. Xia, Zhen Liu, Don Towsley, Marc Lelarge   +3 more
openaire   +1 more source

Analysis of balanced fork-join queueing networks

ACM SIGMETRICS Performance Evaluation Review, 1996
This paper presents an analysis of closed, balanced, fork-join queueing networks with exponential service time distributions. The fork-join queue is mapped onto two non-parallel networks, namely, a serial-join model and a state-dependent model. Using these models, it is proven that the proportion of the number of jobs in the different subsystems of the
Elizabeth Varki, Lawrence W. Dowdy
openaire   +1 more source

An optimal scheduling policy for fork/join queues

Proceedings of 32nd IEEE Conference on Decision and Control, 2002
We consider the problem of optimally scheduling an arriving job on a set of homogeneous single-server queues: (i) arriving jobs consist of a random number of tasks which can be executed independently of each other; (ii) a job is completed only after all of its component tasks have finished execution; and (iii) a central dispatcher schedules the tasks ...
A.M. Makowski, R. Nelson
openaire   +1 more source

A hybrid solution of fork/join synchronization in parallel queues

IEEE Transactions on Parallel and Distributed Systems, 2001
A new analysis technique, dynamic-bubblesort analysis, is introduced for general K-queue first-in-first-out HFJ (homogenous fork/join queuing) systems of K/spl ges/2 . The dynamic-bubblesort model dynamically sorts the branches of the queues based on the number of the tasks waiting for synchronization in each branch.
openaire   +1 more source

Equivalence relations in queueing models of Fork/Join networks with blocking

Performance Evaluation, 1989
Abstract Fork/join (F/J) networks can be used to model parallel processing computer systems.and manufacturing systems. In this paper, we present some fundamental equivalence properties that hold for F/J networks with blocking. Two networks that are equivalent may appear different, but their behavior is closely related.
Mostafa H. Ammar, Stanley B. Gershwin
openaire   +1 more source