Zinky, J. A. An example of automatically troubleshooting a throughput bottleneck using model based techniques. In Proceedings of the IEEE International Conference on Communications (1989), IEEE Communications Society, IEEE Communications Society Press, pp. 1448--1453.  Home/Search   Document Not in Database   Summary   Related Articles

....that requires only a limited number of testing interconnections between processors in the network. Each unit in the network forms a private opinion of the status of its neighboring units. The diagnosis algorithm consists of taking a majority vote among all neighboring units of a given unit. Zinky [63] discusses the problem of diagnosing and deciding what to do about a network throughput bottleneck. This type of diagnosis is typically very difficult due to the amount of data that must be collected and the number of system parameters that can be manipulated to affect the performance of the ....

....file. ffl Look for patterns in the messages. This approach is frequently taken in communications systems or message passing systems where message traces are voluminous. An expert system examining the messages can detect patterns that can indicate communications software errors [25] or bottlenecks [63] in a network. In the UNIX environment, the message logs are not that detailed or voluminous. However, simple patterns can still be detected. For example, 106 whenever the file system on which the accounting subsystem operates becomes full, accounting is suspended and a message to that effect is ....

Zinky, J. A. An example of automatically troubleshooting a throughput bottleneck using model based techniques. In Proceedings of the IEEE International Conference on Communications (1989), IEEE Communications Society, IEEE Communications Society Press, pp. 1448--1453.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC