Data processing: measuring – calibrating – or testing – Measurement system – Time duration or rate
Reexamination Certificate
2000-01-10
2004-06-15
Bui, Bryan (Department: 2863)
Data processing: measuring, calibrating, or testing
Measurement system
Time duration or rate
C702S187000, C702S188000, C370S473000, C370S478000, C713S502000
Reexamination Certificate
active
06751573
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of Invention
The present invention pertains to the field of distributed systems. More particularly, this invention relates to performance monitoring in distributed systems using synchronized clocks and distributed event logs.
2. Art Background
Distributed systems are commonly employed in a variety of applications. A typical distributed system includes a set of nodes that communicate via a communication network. One or more of the nodes usually include processing resources that execute software for a distributed application. Examples of distributed applications include web client-server applications, groupware applications, and industrial and other types of control systems.
A distributed application may be viewed as a arrangement of software components that are distributed among the nodes of a distributed system. Examples of software components of a distributed application include processes, file systems, database servers, web servers, client applications, server applications, network components, and sensor, actuator, and controller applications. Such software components typically interact with one another using mechanisms such as function calls, messages, HTTP commands, etc., to name a few examples. An interaction between software components of a distributed application may be referred to as an event.
Events that are generated in one location of a distributed application typically cause events to occur at other locations in the distributed application. In a web-based application, for example, an end-user may click a button in a web browser. The click typically generates events in the form of HTTP commands. Each HTTP command in turn usually generates other events at other locations in the distributed application to communicate the HTTP command to a web server, for example via a TCP/IP link established by the protocol stacks in each node. In response, a web server as the remote portion of the distributed application typically generates events such as SQL statements for database access or events for file system access to carry out the HTTP command as well as events to return the appropriate information to the requesting web browser.
A capability to record the timing of events in a distributed application may be useful for a variety of system management tasks such as performance monitoring, diagnosis, and capacity planning. For example, a record of the timing of events may be useful for identifying bottlenecks in a distributed application that hinder overall performance. Unfortunately, prior methods for performance monitoring usually record the timing of events in a single node. Prior methods typically do not provide event timing across multiple nodes of a distributed application.
SUMMARY OF THE INVENTION
A distributed system is disclosed that provides performance monitoring capability across multiple nodes of a distributed application. A distributed system according to the present techniques includes a set of nodes that communicate via a network. A distributed application is performed by a set of cooperating node applications executing in the nodes. The distributed system implements techniques for generating time-stamp records for each of a set of significant events associated with one or more of the node applications. The time-stamp records provides a synchronized time base across the nodes for the significant events. This enables temporal ordering of the significant events.
Other features and advantages of the present invention will be apparent from the detailed description that follows.
REFERENCES:
patent: 5566180 (1996-10-01), Eidson et al.
patent: 5805442 (1998-09-01), Crater et al.
patent: 5828876 (1998-10-01), Fish et al.
patent: 6009530 (1999-12-01), Goatly
patent: 6205362 (2001-03-01), Eidson
patent: 0585479 (1992-08-01), None
Alan Mink et al—“Multiprocessor Performance-Measurement Instrumentation”; Computer, IEEE Computer Society, Los Alamitos., CA, U.S.; vol. 23, No. 9, Sep. 1990; pp. 63-75.
Paul Ashton et al—“A Tool For Visualizing The Execution Of Interactions On A Loosely-Coupled Distributed System”, Software—Practice and Experience, vol. 25, No. 10; Oct. 1995; pp. 1117-1140.
Agilent Technologie,s Inc.
Bui Bryan
LandOfFree
Performance monitoring in distributed systems using... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Performance monitoring in distributed systems using..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Performance monitoring in distributed systems using... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3333274