Using multicast to pre-load jobs on the ParPar cluster

Abstract The ParPar system is a high-performance cluster environment supporting a multiuser parallel workload. Its design follows a master-nodes structure, where the master controls all aspects of system activity using a dedicated control network. As nearly all control messages are multicast to a set of nodes, we implemented a reliable multicast protocol for this network based on UDP. This was then used to pre-load executable files to the nodes, rather than using demand paging via NFS. Such pre-loading leads to significant reductions in job startup times in most cases. It is also more scalable than an asymmetrical hardware approach giving the master higher bandwidth, which can be used for small clusters.

[1]  Alexander V. Veidenbaum,et al.  Scalability of the Cedar system , 1994, Proceedings of Supercomputing '94.

[2]  Louise E. Moser,et al.  Totem: a fault-tolerant multicast group communication system , 1996, CACM.

[3]  M. Gerla,et al.  Multicasting protocols for high-speed, wormhole-routing local area networks , 1996, SIGCOMM '96.

[4]  Douglas E. Comer,et al.  Internetworking with TCP/IP - Principles, Protocols, and Architectures, Fourth Edition , 1988 .

[5]  Eric A. Brewer,et al.  How to get good performance from the CM-5 data network , 1994, Proceedings of 8th International Parallel Processing Symposium.

[6]  Danny Dolev,et al.  The Transis approach to high availability cluster communication , 1996, CACM.

[7]  George Kingsley Zipf,et al.  Human behavior and the principle of least effort , 1949 .

[8]  Gheith A. Abandah,et al.  Modeling the communication performance of the IBM SP2 , 1996, Proceedings of International Conference on Parallel Processing.

[9]  Rajkumar Buyya,et al.  High Performance Cluster Computing , 1999 .

[10]  Wolfgang Schröder-Preikschat,et al.  Performance considerations in software multicasts , 1997, ICS '97.

[11]  Dror G. Feitelson,et al.  Job Characteristics of a Production Parallel Scientivic Workload on the NASA Ames iPSC/860 , 1995, JSSPP.

[12]  Douglas Comer,et al.  Principles, protocols, and architecture , 1995 .

[13]  Charles L. Seitz,et al.  Myrinet: A Gigabit-per-Second Local Area Network , 1995, IEEE Micro.

[14]  David Scott,et al.  A TeraFLOP supercomputer in 1996: the ASCI TFLOP system , 1996, Proceedings of International Conference on Parallel Processing.

[15]  Kenneth P. Birman,et al.  The ISIS project: real experience with a fault tolerant programming system , 1990, EW 4.

[16]  Jon A. Solworth,et al.  Increasing network bandwidth on meshes , 1994, SPAA '94.

[17]  Dror G. Feitelson,et al.  The ParPar System: A Software MPP , 1999 .