Electrical computers and digital processing systems: multicomput – Computer network managing – Computer network monitoring
Reexamination Certificate
1998-10-14
2001-10-09
Wiley, David (Department: 2155)
Electrical computers and digital processing systems: multicomput
Computer network managing
Computer network monitoring
C709S200000, C709S220000, C707S793000
Reexamination Certificate
active
06301615
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates generally to computer systems and more specifically to a method and system for monitoring the performance of a cluster of computers as measured by a variety of preexisting monitoring utilities.
2. Description of the Relevant Art
As a result of the increased power and reduced cost of personal computers, they have become increasingly common in homes and businesses. While individual computers enable users to accomplish computational tasks which would otherwise be impossible by the user alone, the capabilities of the individual computer can be multiplied by using it in conjunction with one or more other computers. Individual computers are therefore commonly coupled together to form a computer network.
Computer networks may be interconnected according to various topologies. For example, several computers may each be connected to a single bus, they may be connected to adjacent computers to form a ring, or they may be connected to a central hub to form a star configuration. These networks may themselves serve as nodes in a larger network. While the individual computers in the network are no more powerful than they were when they stood alone, they can share the capabilities of the computers with which they are connected. The individual computers therefore have access to more information and more resources than standalone systems. Computer networks can therefore be a very powerful tool for business, research or other applications.
Computer networks have become fundamental to the functioning of many businesses. The networks facilitate the distribution and tracking of information throughout the office(s) and allow centralized administration of the computer resources. In order to properly administer the functions of the computer network, it may be necessary to monitor the performance of the network. It may also be useful to have means to monitor the performance or resource usage of individual machines on the network. It is therefore preferable that this monitoring of the computers can be done at the level of the network or at the level of the individual computers on the network. Although the individual computers on the network must communicate using a common protocol, the individual machines may be of several different types and may, for example, even use different operating systems. Similarly, the individual computers may each have different performance monitoring utilities which are resident within the respective computers. These utilities obtain performance data from the operating systems and make the data available to the user, usually by displaying this information on a computer's monitor. A network administrator may thereby access various performance measures for each of the machines.
When the network administrator accesses the performance data for the individual machines, it is often the case that there is not a single performance monitoring utility which is common to all the machines. The different utilities may not even output the same type of data (e.g., CPU utilization.) The network administrator may be presented with a jumble of individual and possibly unrelated pieces of information. It may therefore be difficult to determine the overall performance of a particular cluster or the network as a whole.
A network administrator who wishes to consolidate performance information for a cluster of computers may encounter difficulties in obtaining suitably formatted data. Because non-identical computers may have different performance monitoring utilities, the data available from the different computers may be different, or the utilities may generate the same data in different formats. Even different version of the same utilities may have several formats. It is therefore difficult, if not impossible, to simply combine the outputs of the utilities. It is also difficult to develop new utilities for the purpose of monitoring the computers because of the cost of developing the code. Further, different versions of operating systems may rename data variables or make other changes which would prevent the new utility from functioning properly. Utilities designed to extract data from all possible types of computers would therefore have to be updated almost continuously in order to match the updates of the various computers' operating systems.
SUMMARY OF THE INVENTION
One or more of the problems outlined above may be solved by the system and method of the present invention. The invention utilizes preexisting performance monitoring utilities. The output of these utilities is filtered to provide information to a client in a standardized format which facilitates the assessment of performance in both individual computers and selected groups of computers The standardized format of the data allows the client to selectively view particular performance indicators for individual computers or clusters of computers on the network
In one embodiment, the system is implemented on a network of computers. One or more performance monitoring utilities is executed on each of several computers of interest. The performance monitoring utilities extract data from the respective computers and output the data to the standard output. A run command server is also executed on each of these computers. The run command server accepts the data output by the performance monitoring utilities and directs the data to a superserver which is concurrently executed on one of the computers connected to the network. The superserver takes data from each of the performance monitoring utilities on each of the machines and filters it. Each performance monitoring utility has a particular filter associated with it. The filter converts the output of the respective performance monitoring utility into a format which consists of a series of key-value pairs. The keys are predefined and are incorporated into the filters. The set of key-value pairs generated by a filter for a particular performance monitoring utility may include only a subset of all the available keys. The key-value pairs generated for the performance monitoring utilities are then made available to a client which can use selected ones to determine the performance of the computers. The client can select data for individual computers or for clusters of computers. The client can view data corresponding to individual keys, consolidate data relating to particular performance parameters, or otherwise manipulate the data to gauge system performance.
REFERENCES:
patent: 5621892 (1997-04-01), Cook
patent: 5696701 (1997-12-01), Burgess et al.
patent: 5742762 (1998-04-01), Scholl et al.
patent: 5758071 (1998-05-01), Burgess et al.
patent: 5771274 (1998-06-01), Harris
patent: 5796633 (1998-08-01), Burgess et al.
patent: 5819028 (1998-10-01), Manghirmalani et al.
patent: 5835705 (1998-11-01), Larsen et al.
patent: 5875420 (1999-02-01), Piety et al.
patent: 5878420 (1999-03-01), Salle
patent: 6115393 (2000-09-01), Engel et al.
“Performance Toolbox Version 1.2 and 2 for AIX: Guide and Reference (PowerPC Platform Only)”, IBM.
Backer Firmin
Conley Rose & Tayon PC
Kivlin B. Noäl
Sun Microsystems Inc.
Wiley David
LandOfFree
Cluster performance monitoring utility does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Cluster performance monitoring utility, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Cluster performance monitoring utility will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2616008