Research works on cluster computing and storage area network

ABSTRACT

Cluster Computing has attracted attention since the middle of 1990's. It has an advantage of outstanding scalability and cost/performance ratio, compared with the traditional parallel computers. We have constructed a prototype of large-scale PC cluster, making use of commoditized technologies in those days. Cluster Computing has become a mainstream of high-performance computing shortly after, especially for data-intensive applications.

Once the technique of constructing clusters has been established, the back-end of clusters, namely storage, has become a next essential research theme. When the number of nodes increases in clusters, the management cost of storage at each node becomes extremely high. Thus the storage area network (SAN) has been introduced in order to consolidate the back-end of clusters.

Currently, Fibre Channel (FC) SAN is dominant for the consolidation of high-performance servers that have cluster configuration. While FC-SAN is still growing, IP-SAN based on commoditized IP technologies is expected to be significant. We have investigated various techniques in terms of Cluster Computing and SAN until now. Some of those research topics are introduced in this paper.

REFERENCES

• 1: R. S. Nikhil , G. M. Papadopoulos , Arvind, T: a multithreaded massively parallel architecture, Proceedings of the 19th annual international symposium on Computer architecture, p.156-167, May 19-21, 1992, Queensland, Australia
• 2: M. A. Blumrich , K. Li , R. Alpert , C. Dubnicki , E. W. Felten , J. Sandberg, Virtual memory mapped network interface for the SHRIMP multicomputer, Proceedings of the 21st annual international symposium on Computer architecture, p.142-153, April 18-21, 1994, Chicago, Illinois, United States
• 3: D. E. Culler et al.: "Parallel Computing on the Berkeley NOW," Proc. Joint Symposium on Parallel Processing (JSPP '97), pp.237--247, May 1997.
• 4: T. Sterling , D. Savarese , D. J. Becker , B. Fryxell , K. Olson, Communication overhead for space science applications on the Beowulf parallel workstation, Proceedings of the 4th IEEE International Symposium on High Performance Distributed Computing, p.23, August 02-04, 1995
• 5: Russell Carter , John Laroco, Commodity Clusters: Performance Comparison Between PC's and Workstations, Proceedings of the 5th IEEE International Symposium on High Performance Distributed Computing, p.292, August 06-09, 1996
• 6: Takayuki Tamura , Masato Oguchi , Masaru Kitsuregawa, Parallel database processing on a 100 Node PC cluster: cases for decision support query processing and data mining, Proceedings of the 1997 ACM/IEEE conference on Supercomputing (CDROM), p.1-16, November 15-21, 1997, San Jose, CA [doi>10.1145/509593.509642]
• 7: Masato Oguchi , Takahiko Shintani , Takayuki Tamura , Masaru Kitsuregawa, Optimizing Protocol Parameters to Large Scale PC Cluster and Evaluation of its Effectiveness with Parallel Data Mining, Proceedings of the 7th IEEE International Symposium on High Performance Distributed Computing, p.34, July 28-31, 1998
• 8: Using Available Remote Memory Dynamically for Parallel Data Mining Application on ATM-Connected PC Cluster, Proceedings of the 14th International Symposium on Parallel and Distributed Processing, p.411, May 01-05, 2000
• 9: Rakesh Agrawal , Ramakrishnan Srikant, Fast Algorithms for Mining Association Rules in Large Databases, Proceedings of the 20th International Conference on Very Large Data Bases, p.487-499, September 12-15, 1994
• 10: Takahiko Shintani , Masaru Kitsuregawa, Hash based parallel algorithms for mining association rules, Proceedings of the fourth international conference on on Parallel and distributed information systems, p.19-30, December 18-20, 1996, Miami Beach, Florida, United States
• 11: ANSI: "Fibre Channel - Arbitrated Loop," Standard X3.272-1996, 1996.
• 12: ANSI: "Fibre Channel - Switch Fabric," Standard NCITS 320-1998, 1998.
• 13: Masato Oguchi and Masaru Kitsuregawa: "Data Mining on PC Cluster connected with Storage Area Network: Its Preliminary Experimental Results," Proc. IEEE International Conference on Communications (ICC2001), G51b.1, June 2001.
• 14: Runtime Data Declustering over SAN-Connected PC Cluster System, Proceedings of the 18th International Conference on Data Engineering, p.275, February 26-March 01, 2002
• 15: IETF IP Storage (ips) Charter, http://www.ietf.org/html.charters/ips-charter.html
• 16: iSCSI RFC: http://www.ietf.org/rfc/rfc3722.txt
• 17: Storage Networking Industry Association, http://www.snia.org/
• 18: Saneyasu Yamaguchi, Masato Oguchi and Masaru Kitsuregawa: "Trace System of iSCSI Storage Access and Perofrmance Improvement," Proc. International Conference on Database Systems for Advanced Applications 2005 (DASFAA2005), pp.487--497, April 2005.
• 19: Machiko Toyoda, Saneyasu Yamaguchi, and Masato Oguchi: "TCP congestion window controll on an iSCSI read access in a long latency environment," Proc. IASTED International Conference on Communication Systemd and Applications (CSA2005), pp.170--175, July 2005.
• 20: Nozomi Chishima, Saneyasu Yamaguchi, and Masato Oguchi: "Analysis of Multiple Target Network Stroage Access using Multi-routing VPN Connection," Proc. International Workshop on Advanced Storage Systems 2007 (ADSS2007) in conjunction with the 2nd IEEE International Conference on Digital Information Management (ICDIM2007), pp.526--531, October 2007.
• 21: Fujitsu IP access router GeoStream Si-R570· · http://fenics.fujitsu.com/products/sir/sir570/index.html
• 22: Kikuko Kamisaka , Saneyasu Yamaguchi , Masato Oguchi, Performance Analysis of iSCSI Middleware Optimized for Encryption Processing in a Long-Latency Environment, Proceedings of the 20th International Conference on Advanced Information Networking and Applications, p.947-952, April 18-20, 2006 [doi>10.1109/AINA.2006.265]
• 23: Kikuko Kamisaka, Saneyasu Yamaguchi, and Masato Oguchi: "Implementation and Evaluation of Secure and Optimized IP-SAN Mechanism," Proc. 14th IEEE International Conference On Telecommunications (ICT2007), No.228, May 2007.
• 24: Asuka Hara, Kikuko Kamisaka, Saneyasu Yamaguchi, and Masato Oguchi: "Analyzing characteristics of PC cluster consolidated with IP-SAN using data-intensive applications," Proc. 20th IASTED International Conference on Parallel and Distributed Computing and Systems (PDCS2008), pp.264--269, October 2008.
• 25: Rocks Cluster: http://www.rocksclusters.org/
• 26: Ganglia Monitoring System: http://www.ganglia.info/
• 27: Open-iSCSI: http://www.open-iscsi.org/
• 28: iSCSI-Enterprise Target: http://sourceforge.net/ projects/iscsitarget/
• 29: Bonnie++: http://www.coker.com.au/bonnie++/