A distributed programs monitor for berkeley UNIX

Abstract

Writing and debugging distributed programs can be difficult. When a program is working, it can be difficult to achieve reasonable execution performance. A major cause of these difficulties is a lack of tools for the programmer. We use a model of distributed computation and measurement to implement a program monitoring system for programs running on the Berkeley UNIX 4.2BSD operating system. The model of distributed computation describes the activities of the processes within a distributed program in terms of computation (internal events) and communication (external events). The measurement model focuses on external events and separates the detection of external events, event record selection and data analysis. The implementation of the measurement tools involved changes to the Berkeley UNIX kernel, and the addition of daemon processes to allow the monitoring activity to take place across machine boundaries. A user interface has also been implemented.

The Administration of Distributed Computations in a Networked Environment: An Interim Report

“…As a result of adoption, user processes are modified to contain specific tracing flags used thereafter by the kernel for event detection. This mechanism is much like that described in [15].…”

“…Another deficiency of existing systems has been the lack within process management facilities of historical information about the processing behavior of computations. Those event tracing tools that have existed in different computing environments [14][15] have not been incorporated into process management facilities in the corresponding systems. Multiple-process computations that span processors require for their appropriate management not only powerful and flexible mechanisms for process control but also historical processing information.…”

Debugging concurrent programs

“…The nested function calls can be hidden, giving a clearer picture of the highlevel activity (see Section 3.1). [LP85] ipc, sh mem [AP87] ipc, sh mem [BDV86] ipc [GB85] ipc [GGK84] n/s [GKY88] ipc, stmt [MMS86] ipc [Sno84] stmt …”

BRISK: a portable and flexible distributed instrumentation system

“…[2][3][4]), usually as components of larger software toolkits for analysis of parallel/distributed systems. Only a few have been ported to multiple platforms and made available to broader usage.…”