Abstract
Implicit coscheduling techniques applied to non-dedicated homogeneous Networks Of Workstations (NOWs) have shown they can perform well when many local users compete with a single parallel job. Implicit coscheduling deals with minimizing the communication waiting time of parallel processes by identifying the processes in need of coscheduling through gathering and analyzing implicit runtime information, basically communication events. Unfortunately, implicit coscheduling techniques do not guarantee the performance of local and parallel jobs, when the number of parallel jobs competing against each other is increased. Thus, a low efficiency use of the idle computational resources is achieved.
In order to solve these problems, a new technique, named Cooperating CoScheduling (CCS), is presented in this work. Unlike traditional implicit coscheduling techniques, under CCS, each node takes its scheduling decisions from the occurrence of local events, basically communication, memory, Input/Output and CPU, together with foreign events received from cooperating nodes. This allows CCS to provide a social contract based on reserving a percentage of CPU and memory resources to ensure the progress of parallel jobs without disturbing the local users, while coscheduling of communicating tasks is ensured. Besides, the CCS algorithm uses status information from the cooperating nodes to balance the resources across the cluster when necessary. Experimental results in a non-dedicated heterogeneous NOW reveal that CCS allows the idle resources to be exploited efficiently, thus obtaining a satisfactory speedup and provoking an overhead that is imperceptible to the local user.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Acharya A, Edjlali G, Saltz J. The utility of exploiting idle workstations for parallel computations. In Proc. the ACM SIGMETRICS/PERFORMANCE, USA, 1997, pp.225–236.
Acharya A, Setia S. Availability and utility of idle memory in workstation clusters. In Proc. the ACM SIGMETRICS/PERFORMANCE, USA, 1999, pp.35–46.
Carriero N, Freedman E, Gelernter D, Kaminsky D. Adaptive parallelism and piranha. Computer, 1995, 28(1): 40–49.
Litzkow M, Livny M, Mutka M. Condor — A hunter of idle workstations. In Proc. the 8th Int. Conf. Distributed Computing Systems, USA, 1988, pp.104–111.
Ousterhout J. Scheduling strategies for concurrent systems. In Proc. the 3rd Int. Conf. Distributed Computing Systems, USA, 1982, pp.22–30.
Feitelson D. Packing schemes for gang scheduling. Lecture Notes in Computer Science, 1996, 1162: 89–110.
Sobalvarro P, Weihl W. Demand-based coscheduling of parallel jobs on multiprogrammed multiprocessors. Lecture Notes in Computer Science, 1995, 949: 106–126.
Anglano C. A comparative evaluation of implicit coscheduling strategies for networks of workstations. In Proc. the 9th Int. Symp. High Performance Distributed Computing, Japan, 2000, pp.221–228.
Sobalvarro P, Pakin S, Weihl W, Chien A. Dynamic coscheduling on workstation clusters. Lecture Notes in Computer Science, 1998, 1459: 231–256.
Frachtenberg E, Feitelson D, Petrini F, Fernandez J. Flexible CoScheduling: Mitigating load imbalance and improving utilization of heterogeneous resources. In Proc. the Int. Parallel and Distributed Processing Symposium (IPDPS), France, 2003.
Hanzich M, Giné F, Hernández P et al. Coscheduling and multiprogramming level in a non-dedicated cluster. Lecture Notes in Computer Science, 2004, 3241: 327–336.
Sodan A. Loosely coordinated coscheduling in the context of other approaches for dynamic job scheduling: A survey. Concurrency and Computation: Practice and Experience, 2005, 17(16): 1725–1781.
Petrini F, Feng W. Buffered coscheduling: A new methodology for multitasking parallel jobs on distributed systems. In Proc. the Int. Parallel and Distributed Processing Symposium (IPDPS), Mexico, 2000.
Solsona F. Coscheduling techniques for non-dedicated cluster computing [Dissertation]. Dept. Computer Science, Universitat Autonoma de Barcelona, Spain, 2002.
Dusseau A. Implicit coscheduling: Coordinated scheduling with implicit information in distributed systems. ACM Transactions on Computer Systems, 2001, 19(3): 283–331.
Nagar S, Banerjee A, Sivasubramaniam A, Das C. Alternatives to coscheduling a network of workstations. J. Parallel and Distributed Computing, 1999, 59: 302–327.
Choi G, Agarwal S, Kim J, Yoo A, Das C. Impact of job allocation strategies on communication-driven coscheduling in clusters. Lecture Notes in Computer Science, 2003, 2790: 160–169.
Frachtenberg E, Petrini F, Feitelson D, Fernandez J. Adaptive parallel job scheduling with flexible coscheduling. IEEE Trans. Parallel and Distributed Systems, 2005, 16(11): 1066–1077.
Yu J, Azougagh D, Kim J, Maeng S. Impact of exploiting load imbalance on coscheduling in workstation clusters. In Proc. the Int. Conference on Parallel Processing (ICPP), Norway, 2005, pp.595–602.
Du X, Zhang X. Coordinating parallel processes on networks of workstations. J. Parallel and Distributed Computing, 1997, 46(2): 125–135.
Giné F, Solsona F, Hernández P, Luque E. Dealing with memory constraints in a non-dedicated linux cluster. International Journal of High Performance Computing Applications, 2003, 17(1): 39–48.
Nikolopoulos D, Polychronopoulos C. Adaptive scheduling under memory constraints on a non-dedicated computational farms. Future Generation Computer Systems, 2003, 19(4): 505–519.
Ryu K, Pachapurkar N, Fong L. Adaptive memory paging for efficient gang scheduling of parallel applications. In Proc. the Int. Parallel and Distributed Processing Symposium (IPDPS), Mexico, 2004, pp.30–40.
Giné F, Solsona F, Hernández P, Luque E. Cooperating CoScheduling in a non-dedicated cluster. Lecture Notes in Computer Science, 2004, 2790: 212–218.
Zhang X, Yan Y. Modeling and characterizing parallel computing performance on heterogeneous NOW. In Proc. the Seventh IEEE Symposium on Parallel and Distributed Processing, USA, 1995, pp.25–34.
Mutka M, Livny M. The available capacity of a privately owned workstation environment. J. Performance Evaluation, 1991, 12(4): 269–284.
Nielsen J. Designing Web Usability: The Practice of Simplicity. New Riders Publishing, 2000.
Batat A, Feitelson D. Gang scheduling with memory considerations. In Proc. the 14th Int. Parallel Distributed Processing Symposium (IPDPS), Mexico, 2000, pp.109–114.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the MEyC under Grant No. TIN 2004-03388.
Electronic supplementary material
Rights and permissions
About this article
Cite this article
Giné, F., Solsona, F., Hanzich, M. et al. Cooperating CoScheduling: A Coscheduling Proposal Aimed at Non-Dedicated Heterogeneous NOWs. J Comput Sci Technol 22, 695–710 (2007). https://doi.org/10.1007/s11390-007-9082-y
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11390-007-9082-y