DocumentCode :
2376502
Title :
Analysis and Simulation for a Mean Response Time Hybrid Solution to Homogeneous Fork/Join Queues
Author :
Chen, Ray Jinzhu ; Tong, Muchenxuan
Author_Institution :
Software Sch., Xiamen Univ., Xiamen, China
fYear :
2010
fDate :
17-19 Nov. 2010
Firstpage :
322
Lastpage :
327
Abstract :
In this paper, we simulate and analyze general K-queue HFJ (Homogeneous Fork/Join) systems with 100 thousand parallel queues for the mean response time, which we denote by TK. Jobs arrive with mean rate λ and a general arrival distribution. Upon arrival, a job forks into K tasks. Task k, k = 1, 2, ..., K, is assigned to the kth queuing system, which is a first-in-first-out server with a general service distribution and an infinite capacity queue. A job leaves the HFJ system as soon as all its tasks complete their service. In other words, tasks corresponding to the same job are joined before departing the HFJ system. We use the huge-scale simulation to analyze the tightness and the trend of a mean response time hybrid solution as K grows. The hybrid solution is consistent for huge-scale systems with max absolute offset <; 0.5%. In general, the max offsets and the min offsets do not change significantly as the scale (the number of queues) increases.
Keywords :
queueing theory; statistical distributions; K-queue homogeneous fork-join system; arrival distribution; first-in-first-out server; huge-scale simulation; huge-scale system; mean rate; mean response time hybrid solution; parallel queues; service distribution; HFJ; dynamic-bubblesort analysis; fork/join queuing system; fork/join simulation; hybrid solution;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Modeling and Simulation (EMS), 2010 Fourth UKSim European Symposium on
Conference_Location :
Pisa
Print_ISBN :
978-1-4244-9313-5
Electronic_ISBN :
978-0-7695-4308-6
Type :
conf
DOI :
10.1109/EMS.2010.59
Filename :
5703704
Link To Document :
بازگشت