The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.12 - December (2011 vol.22)
pp: 2000-2007
L. Watkins , Appl. Phys. Lab., Johns Hopkins Univ., Laurel, MD, USA
ABSTRACT
We present the details of a novel method for passive resource discovery in cluster grid environments, where resources constantly utilize internode communication. Our method offers the ability to nonintrusively identify resources that have available CPU cycles; this is critical for lowering queue wait times in large cluster grid networks. The benefits include: 1) low message complexity, which facilitates low latency in distributed networks, 2) scalability, which provides support for very large networks, and 3) low maintainability, since no additional software is needed on compute resources. Using a 50-node (multicore) test bed (DETERlab), we demonstrate the feasibility of our method with experiments utilizing TCP, UDP, and ICMP network traffic. We use a simple but powerful technique that monitors the frequency of network packets emitted from the Network Interface Card (NIC) of local resources. We observed the correlation between CPU load and the timely response of network traffic. A highly utilized CPU will have numerous, active processes which require context switching. The latency associated with numerous context switches manifests as a delay signature within the packet transmission process. Our method detects that delay signature to determine the utilization of network resources. Results show that our method can consistently and accurately identify nodes with available CPU cycles (<;70 percent CPU utilization) through analysis of existing network traffic, including network traffic that has passed through a switch (noncongested). Also, in situations where there is no existing network traffic for nodes, ICMP ping replies can be used to ascertain this resource information.
INDEX TERMS
telecommunication traffic, communication complexity, grid computing, network interfaces, packet switching, queueing theory, resource information, passive solution, CPU resource discovery problem, cluster grid networks, cluster grid environments, internode communication, nonintrusively identify resources, CPU cycles, queue wait times, message complexity, distributed networks, scalability, very large networks, compute resources, multicore test bed, DETERlab, TCP network traffic, UDP network traffic, ICMP network traffic, network packets, network interface card, NIC, CPU load, context switching, delay signature, packet transmission process, network resources, network traffic analysis, ICMP ping reply, Decision support systems, Complexity theory, Clustering methods, Grid computing, Network interfaces, clustering algorithm., Cluster grid computing, passive resource discovery
CITATION
L. Watkins, "A Passive Solution to the CPU Resource Discovery Problem in Cluster Grid Networks", IEEE Transactions on Parallel & Distributed Systems, vol.22, no. 12, pp. 2000-2007, December 2011, doi:10.1109/TPDS.2011.89
REFERENCES
[1] V. Dimakopoulos and E. Pitoura, "On the Performance of Flooding-Based Resource Discovery," IEEE Trans. Parallel and Distributed Systems, vol. 17, no. 11, pp. 1242-1252, Nov. 2006.
[2] M. Harchol-Balter, T. Leighton, and D. Lewin, "Resource Discovery in Distributed Networks," Proc. ACM Symp. Principles of Distributed Computing, May 1999.
[3] B. Chen and F. Tobagi, "Network Topology Design to Optimize Link and Switching Costs," Proc. IEEE Int'l Conf. Comm. (ICC), 2007.
[4] C. Law and K. Siu, "An O(log n) Randomized Resource Discovery Algorithm," Proc. Int'l Symp. Distributed Computing, Oct. 2000.
[5] Z. Cao, K. Li, and Y. Liu, "A Multi-Level Super Peer Based P2P Architecture," Proc. Int'l Conf. Information Networking, Jan. 2008.
[6] C. Corbett, R. Beyah, and J. Copeland, "Using Active Scanning to Identify Wireless NICs," Proc. IEEE Information Assurance Workshop (IAW), pp. 239-246, 2006.
[7] C. Corbett, R. Beyah, and J. Copeland, "Passive Classification of Wireless NICs during Rate Switching," EURASIP J. Wireless Comm. and Networking, vol. 2008, p. 12, 2008, DOI 10.1155/2008/495070.
[8] L. Watkins, R. Beyah, and C. Corbett, "A Passive Approach to Rogue Access Point Detection," Proc. IEEE Global Comm. Conf. (GLOBECOM), 2007.
[9] L. Watkins, R. Beyah, and C. Corbett, "Passive Identification of under Utilized CPUs in High Performance Cluster Grid Networks," Proc. IEEE Int'l Conf. Comm. (ICC), May 2008.
[10] L. Watkins, R. Beyah, and C. Corbett, "Using Network Traffic to Passively Detect under Utilized Resources in High-Performance Cluster Grid Computing Environments," Proc. ACM Int'l Conf. Networks for Grid Applications (GRIDNETS), Oct. 2007.
[11] G. Müunz, S. Li, and G. Carle, "Traffic Anomaly Detection Using K-Means Clustering," Proc. GI/ITG Workshop MMBnet, 2007.
[12] R. Stevens, B. Fenner, and A. Rudoff, Unix Network Programming, Vol. 1: The Sockets Networking API, third ed. Addison-Wesley Professional, Oct. 2003.
[13] V. Strumpen and T. Casavant, "Exploiting Communication Latency Hiding for Parallel Network Computing: Model and Analysis," Proc. Int'l Conf. Parallel and Distributed Systems, Dec. 1994.
[14] DETERlab Website, http://www.isi.edudeter/, Nov. 2010.
[15] Mathworks Website, http://www.mathworks.com/ matlabcentral/ fileexchange6291, Nov. 2010.
[16] Berkeley College of Chemistry Rocks Cluster Website, http://dino.cchem.berkeley.edu/ganglia/addons/ rockstop.php?c= College%20of%20Chemistry&sortby=HOST&sortorder=down , Nov. 2010.
17 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool