Management Science
Adaptive Optimal Load Balancing in a Nonhomogeneous Multiserver System with a Central Job Scheduler
IEEE Transactions on Computers
Optimal load balancing and scheduling in a distributed computer system
Journal of the ACM (JACM)
Queueing simulation in heavy traffic
Mathematics of Operations Research
On choosing a task assignment policy for a distributed server system
Journal of Parallel and Distributed Computing - Special issue on software support for distributed computing
Task assignment with unknown duration
Journal of the ACM (JACM)
Implementing Multiprocessor Scheduling Disciplines
IPPS '97 Proceedings of the Job Scheduling Strategies for Parallel Processing
Theory and Practice in Parallel Job Scheduling
IPPS '97 Proceedings of the Job Scheduling Strategies for Parallel Processing
Representative Traces for Processor Models with Infinite Cache
HPCA '96 Proceedings of the 2nd IEEE Symposium on High-Performance Computer Architecture
HPDC '00 Proceedings of the 9th IEEE International Symposium on High Performance Distributed Computing
Cycle stealing under immediate dispatch task assignment
Proceedings of the fifteenth annual ACM symposium on Parallel algorithms and architectures
A recursive analysis technique for multi-dimensionally infinite Markov chains
ACM SIGMETRICS Performance Evaluation Review
Stochastic analysis of multiserver systems
ACM SIGMETRICS Performance Evaluation Review
Why segregating short jobs from long jobs under high variability is not always a win
Allerton'09 Proceedings of the 47th annual Allerton conference on Communication, control, and computing
Optimal allocation of servers and processing time in a load balancing system
Computers and Operations Research
Review: Task assignment policies in distributed server systems: A survey
Journal of Network and Computer Applications
Task assignment based on prioritising traffic flows
OPODIS'04 Proceedings of the 8th international conference on Principles of Distributed Systems
Lookahead actions in dispatching to parallel queues
Performance Evaluation
Hi-index | 0.00 |
We consider the problem of task assignment in a distributedserver system, where short jobs are separated fromlong jobs, but short jobs may be run in the long job partitionif it is idle (cycle stealing). Jobs are assumed to be non-preemptible,where short and long jobs have generally-distributedservice requirements, and arrivals are Poisson.We consider two variants of this problem: a centralqueue model and an immediate dispatch model. This paperpresents the first analysis of cycle stealing under thecentral-queue model. (Cycle stealing under the immediatedispatch model is analyzed in [9]). The analysis usesa technique which we refer to as busy period transitions.Results show that cycle stealing can reduce mean responsetime for short jobs by orders of magnitude, while long jobsare only slightly penalized. Furthermore using a centralqueue yields significant performance improvement over immediatedispatch, both from the perspective of the benefit toshort jobs and the penalty to long jobs.