Electrical computers and digital processing systems: multicomput – Computer-to-computer data routing – Least weight routing
Reexamination Certificate
1998-11-04
2001-04-24
Vu, Viet D. (Department: 2154)
Electrical computers and digital processing systems: multicomput
Computer-to-computer data routing
Least weight routing
C709S241000, C709S241000, C709S241000
Reexamination Certificate
active
06223203
ABSTRACT:
COPYRIGHT NOTICE
A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent file or records, but otherwise reserves all copyright rights whatsoever.
BACKGROUND
1. Field of the Invention
The present invention relates to computer systems and networks of computer systems, and, more particularly, to efficient, parallel execution of computer processes over multiple computer systems.
2. Description of the Related Art
Computer systems have attained widespread use in providing computing power to businesses and institutions. Some important fields in which computer systems have become common include manufacturing monitoring and control; electrical, mechanical, and chemical system design and simulation; and network management and service. Productive processing time is of great importance to the users of computer systems in these and other fields because computer system down time can result in significant costs.
Computer systems are designed to provide a degree of system availability that is necessitated by the applications for which the computer system is intended. High availability (HA) computer systems, as their name implies, are required to be available, or “on,” virtally all of the time. Such computer systems (or networks of such computer systems) should be substantially error free or should be capable of recovery from errors. Also, consumption of resources and down time in such systems due to maintenance tasks should be minimized.
For example, in a 24×7 manufacturing system, time is extremely critical. Performance of management/maintenance operations as quickly and efficiently as possible is extremely important. In such a manufacturing system, downtime for such operations can be very limited. For example, in one such manufacturing system, scheduled downtime may be as little as one hour per quarter. Therefore, the operations performed during these downtime periods must be optimized to run as quickly and efficiently as possible.
In an environment where scheduled downtime is extremely limited, it is imperative that operations be performed as quickly and accurately as possible. Also, in a client/server environment where hundreds of systems may be involved, the ability to execute the same command across all systems with minimal effort and in the shortest time possible is extremely important. When a common operation is to be performed across a group of systems, one of two methods is typically used. For example, management operations to be performed across many computer systems in a client/server environment are typically performed either manually on each system, one-by-one, or sequentially using a script. Manual execution on each system involves logging into each system and performing the command manually. This is time consuming and can result in errors and/or omissions. Sequential script execution typically includes bundling the work to be done into a script and then sequentially executing the scripted commands on all systems. If hundreds of systems are involved, this sequential method can also be very time consuming.
SUMMARY
It has been discovered that a method and software application may be used to facilitate dynamic, substantially parallel execution of operations on multiple computer systems over a distributed computing system such as a semiconductor processing system. The application and method thereof defines a set of systems upon which each operation is to be executed and then performs each operation in a substantially parallel fashion. Such an application and method thereof allow system administrators to execute operations across a set of systems substantially in parallel and without writing sequentially executed scripts of the operations. Consequently, system management operations are performed across a multitude of systems in a fast and efficient manner, thereby decreasing system down time.
In one embodiment, a method of minimizing the time required for executing a function over a network of computer systems in a high availability system is provided. A list of computer systems is provided by a parent process. The list includes a plurality of computer systems upon which a first function is to be performed. The first function is received by the parent process. A plurality of child processes is sequentially created. Each of the child processes corresponds to one of the computer systems on the list. Each of the child processes executes in parallel with at least one other of the child processes. Each of the child processes remotely executes the first function on the computer system corresponding to the respective child process.
In another embodiment of the invention, a computer program product encoded in computer readable media is provided. The computer program product includes first, second, third and fourth instructions executable on a computer system. The first instructions are for providing a list of computer systems by a parent process. The list includes computer systems upon which a first function is to be performed. The second instructions are for receiving the fist function by the parent process. The third instructions are for sequentially creating child processes. The fourth instructions are for executing each of the child processes in parallel with at least one other of the child processes. Each of the child processes remotely execute the first function on a computer system corresponding to the respective child process.
REFERENCES:
patent: 5193186 (1993-03-01), Tamaki et al.
patent: 5615127 (1997-03-01), Beatty et al.
patent: 5692193 (1997-11-01), Jagannathan et al.
patent: 5887166 (1999-03-01), Mallick et al.
John S. Gray, “Interprocess Communications in UNIX® The Nooks and Crannies,” Prentice Hall PTR, New Jersey, 1997, pp. 15-18, 53-68 (22 pages).
Gross Danny B.
O'Donnell Michael D.
Toomey Gene R.
Advanced Micro Devices , Inc.
Skjerven Morrill & MacPherson LLP
Terrile Stephen A.
Vu Viet D.
LandOfFree
Method for performing parallel management operations... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for performing parallel management operations..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for performing parallel management operations... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2453982