Passive Identification of Under-Utilized CPUs in High Performance Cluster Grid Networks

In this paper we propose a passive approach to using network traffic to discover the availability of resources in local distributed networks (e.g., cluster grids, campus desktop grids, etc.). To our knowledge, this is the first approach of its kind. The ability to quickly identify resource availability is critical because the presence of available resources directly affects the job execution time of a distributed environment. The proposed method creates a delay sensitive profile generated by the analysis of monitored network traffic, which emulates high performance UDP based grid services such as file transfer applications (FOBS, Tsunami, UDT, SABUL, etc.), message passing platforms (MPICHG2/Score, etc.), and others. An energy value is derived from the delay sensitive profile, which represents the state (over-utilized CPU or under-utilized CPU) of the resource of interest. Then a simple threshold (derived from initial calibrations on the over-utilized resources.) is applied to the energy value to identify the state of the resource. This method could be used to enhance existing resource discovery algorithms used in local distributed networks because this approach is capable of passively determining a major dynamic resource attribute - CPU utilization. The main benefits are the reduction in the necessary complexity associated with the use of non-passive algorithms (e.g., flooding algorithm, name-dropper algorithm, distinctive awareness algorithm, etc.) and the reduction in the extra network traffic that results from the continual need to determine the availability of dynamic resources. Since this method is passive in nature, there is no need to query potential resources directly to determine their availability to complete distributed computing related jobs. Results suggest that once the CPU utilization approaches 70% (unavailable) the network traffic produced by that node exhibits different behavior than when the CPU utilization is less than 70% (available).

[1]  Richard Baraniuk,et al.  The dual-tree complex wavelet transform , 2005, IEEE Signal Processing Magazine.

[2]  Naixue Xiong,et al.  A resource-based admission control algorithm for grid computing systems , 2004, The Fourth International Conference onComputer and Information Technology, 2004. CIT '04..

[3]  John Sadowsky,et al.  Investigation of Signal Characteristics Using the Continuous Wavelet Transform , 1996 .

[4]  Wei Sun,et al.  CPU Load Predictions on the Computational Grid * , 2006, Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID'06).

[5]  Wei Sun,et al.  CPU Load Predictions on the Computational Grid , 2006, CCGRID.

[6]  Chao-Tung Yang,et al.  Apply cluster and grid computing on parallel 3D rendering , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[7]  R. Wolski,et al.  Predicting the CPU availability of time‐shared Unix systems on the computational grid , 1999, Proceedings. The Eighth International Symposium on High Performance Distributed Computing (Cat. No.99TH8469).

[8]  Richard Wolski,et al.  Predicting the CPU availability of time‐shared Unix systems on the computational grid , 2004, Cluster Computing.

[9]  S.J.E. Taylor,et al.  Using a desktop grid to support simulation modelling , 2006, 28th International Conference on Information Technology Interfaces, 2006..

[10]  Muthucumaru Maheswaran,et al.  A Parameter-Based Approach to Resource Discovery in Grid Computing System , 2000, GRID.

[11]  Motohiko Matsuda,et al.  Evaluation of MPI implementations on grid-connected clusters using an emulated WAN environment , 2003, CCGrid 2003. 3rd IEEE/ACM International Symposium on Cluster Computing and the Grid, 2003. Proceedings..

[12]  Bill Fenner,et al.  The sockets networking API , 2004 .

[13]  Vassilios V. Dimakopoulos,et al.  On the Performance of Flooding-Based Resource Discovery , 2006, IEEE Transactions on Parallel and Distributed Systems.

[14]  Cosimo Anglano,et al.  A comparative evaluation of high-performance file transfer systems for data-intensive grid applications , 2004, 13th IEEE International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprises.

[15]  Raheem A. Beyah,et al.  Using network traffic to passively detect under utilized resources in high performance cluster grid computing environments , 2007, GridNets '07.

[16]  Juan Li,et al.  A semantics-based routing scheme for grid resource discovery , 2005, First International Conference on e-Science and Grid Computing (e-Science'05).

[17]  Truong Q. Nguyen,et al.  Wavelets and filter banks , 1996 .

[18]  Peter A. Dinda,et al.  An evaluation of linear models for host load prediction , 1999, Proceedings. The Eighth International Symposium on High Performance Distributed Computing (Cat. No.99TH8469).

[19]  Lanier Watkins,et al.  Wavelet Transform Image Compression Prototype , 1999 .

[20]  Richard Baraniuk,et al.  The Dual-tree Complex Wavelet Transform , 2007 .

[21]  Ian T. Foster,et al.  Homeostatic and tendency-based CPU load predictions , 2003, Proceedings International Parallel and Distributed Processing Symposium.

[22]  Scott Rixner,et al.  Exploiting task-level concurrency in a programmable network interface , 2003, PPoPP '03.