Gallop: The Benefits of Wide-Area Computing for Parallel Processing

doi:10.1006/jpdc.1998.1487

Journal of Parallel and Distributed Computing

Volume 54, Issue 2, 1 November 1998, Pages 183-205

https://doi.org/10.1006/jpdc.1998.1487 Get rights and content

Abstract

Internet computing has emerged, as an attractive paradigm for many applications that require access to distributed resources such as telemedicine, collaboratories, and transaction systems. For applications that require high performance, the Internet is assumed to be inappropriate. However, it is possible to obtain high performance for parallel scientific applications in an Internet environment. A wide-area scheduling system called Gallop has been developed to exploit opportunities for high performance using remote Internet resources for these applications. This paper describes the Gallop architecture and scheduling model, and performance results obtained for three parallel applications. The initial results indicate that wide-area parallel processing can lead to better performance even with Internet technology, but that current Internet bandwidth is a major bottleneck for file and binary transfer. This overhead limits the class of suitable applications to those that are large-grained or that will be run multiple times to amortize the transfer cost.

References (25)

F. Berman, R. Wolski, Scheduling from the perspective of the application, Proceedings of the Fifth IEEE International...
A. Bestavros
Boston University Computer Science technical report
(March 1996)
S.H. Bokhari
Assignment Problems in Parallel and Distributed Computing
(1987)
S. Chatterjee
Requirements for success in gigabit networking
Comm. of the ACM
(1997)
K. M. Chandy, et al., A world-wide distributed system using java and the internet, Proceedings of the Fifth IEEE...
D.L. Eager et al.
Adaptive load sharing in homogeneous distributed systems
IEEE Trans. on Software Engrg.
(1986)
I. Foster, C. Kesselman, Globus: A metacomputing infrastructure toolkit, Intern. J. of Supercomputing...
P. A. Gray, V. S. Sunderam, IceT: Distributed computing and java, Cluster Computing Conference, Atlanta, GA,...
A.S. Grimshaw
Easy to use object-oriented parallel programming with mentat
IEEE Comput.
(1993)
A.S. Grimshaw et al.
No pain and gain! Experiences with mentat on biological application
Concurrency: Practice Experience
(1993)

A.S. Grimshaw et al.

The legion vision of a worldwide virtual computer

Comm. of the ACM

(1997)

A.K. Jain

Fundamentals of Digital Image Processing

(1989)

Cited by (17)

A self-organizing flock of Condors
2006, Journal of Parallel and Distributed Computing
Condor enables high throughput computing using off-the-shelf cost-effective components. It also supports flocking, a mechanism for sharing resources among Condor pools. Since Condor pools distributed over a wide area can have dynamically changing availability and sharing preferences, the current flocking mechanism based on static configurations can limit the potential of sharing resources across Condor pools. This paper presents a technique for resource discovery in distributed Condor pools using peer-to-peer mechanisms that are self-organizing, fault-tolerant, scalable, and locality-aware. Locality-awareness guarantees that applications are not shipped across long distances when nearby resources are available. Measurements using a synthetic job trace show that self-organized flocking reduces the maximum job wait time in queue for a heavily loaded pool by a factor of 10 compared to without flocking. Simulations of 1000 Condor pools are also presented and the results confirm that our technique discovers and utilizes nearby resources in the physical network.
Integrated scheduling: The best of both worlds
2003, Journal of Parallel and Distributed Computing
This paper presents a new paradigm for parallel job scheduling called integrated scheduling or iScheduling. The iScheduler is an application-aware job scheduler as opposed to a general-purpose system scheduler. It dynamically controls resource allocation among a set of competing applications, but unlike a traditional job scheduler, it can interact directly with an application during execution to optimize resource allocation. An iScheduler may add or remove resources from a running application to improve the performance of other applications. Such fluid resource management can support both improved application and system performance. We propose a framework for building iSchedulers and evaluate the concept on several workload traces obtained both from supercomputer centers and from a set of real parallel jobs. The results indicate that iScheduling can improve both waiting time and overall turnaround time substantially for these workload classes, outperforming standard policies such as backfilling and moldable job scheduling.
Predicting the cost and benefit of adapting data parallel applications in clusters
2002, Journal of Parallel and Distributed Computing
This paper examines the problem of adapting data parallel applications in a shared dynamic environment of PC or workstation clusters. We developed an analytic framework to compare and contrast a wide range of adaptation strategies: dynamic load balancing, migration, processor addition and removal. These strategies have been evaluated with respect to the cost and benefit they provide for three representative parallel applications: an iterative jacobi solver for Laplace's equation, gaussian elimination with partial pivoting, and a gene sequence comparison application. We found that the cost and benefit of each method can be predicted with high accuracy (within 10%) for all applications and show that the framework is applicable to a wide variety of parallel applications. We then show that accurate prediction allows the most appropriate method to be selected dynamically. Performance improvement for the three applications ranged from 25% to 45% using our adaptation library. In addition, we dispel the conventional wisdom that migration is too expensive, and show that it can be beneficial even for running parallel applications with non-trivial communication.
DistOpt: A Software Framework for Modeling and Evaluating Optimization Problem Solutions in Distributed Environments
2000, Journal of Parallel and Distributed Computing
We present a flexible software environment, named DistOpt, which is useful in building coarse-grain algorithms for solving optimization problems and simulating the solution of the resulting subproblems in multicomputer systems. It is based on a decomposition-coordination approach, by which large optimization problems can be split into subproblems, which are then easier to solve and can be solved in parallel. The object-oriented methodology on which DistOpt is based, and its graphical user interface, are well suited to modify, interface, and extend existing software modules with minimal impact. DistOpt is a flexible and innovative software environment that can be customized by the user in a short development time.
DT-RRNS: Routing Protocol Design for Secure and Reliable Distributed Smart Sensors Communication Systems †
2023, Sensors
SNS-Based Secret Sharing Scheme for Security of Smart City Communication Systems
2023, Communications in Computer and Information Science

View all citing articles on Scopus

^☆: This work was partially funded by NSF ASC-9625000.

^f1: E-mail: [email protected].

View full text

Regular ArticleGallop: The Benefits of Wide-Area Computing for Parallel Processing☆

Abstract

Boston University Computer Science technical report

Assignment Problems in Parallel and Distributed Computing

Requirements for success in gigabit networking

Comm. of the ACM

Adaptive load sharing in homogeneous distributed systems

IEEE Trans. on Software Engrg.

Easy to use object-oriented parallel programming with mentat

IEEE Comput.

No pain and gain! Experiences with mentat on biological application

Concurrency: Practice Experience

The legion vision of a worldwide virtual computer

Comm. of the ACM

Fundamentals of Digital Image Processing

Regular Article
Gallop: The Benefits of Wide-Area Computing for Parallel Processing☆