Error detection/correction and fault detection/recovery – Data processing system error or fault handling – Reliability and availability
Reexamination Certificate
1999-10-21
2003-02-04
Beausoliel, Robert (Department: 2184)
Error detection/correction and fault detection/recovery
Data processing system error or fault handling
Reliability and availability
C714S006130
Reexamination Certificate
active
06516423
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Technical Field of the Invention
The present invention relates to providing redundant data storage devices, and particularly to a method and system for recreating a central queue in a distributed processing system without the expense of maintaining dual storage devices during normal operation of the system.
2. Background of the Invention
Today's computing networks often utilize central devices for handling data from a number of remote processing units. A central queue, for instance, is typically capable of receiving data from remote processing units, temporarily maintaining the data and providing the data for sequential processing thereof by a central processing unit. In order to prevent the distributed processing system from being halted upon the occurrence of one or more failures associated with the operation of the central queue, a backup central queue is typically provided. In existing systems, the contents of the backup central queue are updated in real time whenever the contents of the central queue are updated. In this way, an exact copy of the central queue is available for use as the central queue whenever the central queue fails.
A primary shortcoming in conventional distributed processing systems employing a backup central queue is the additional usage of system resources necessary to maintain and/or update a duplicate copy of the central queue in real time. Based upon the foregoing, there is a need for more efficiently providing multiple queue redundancy within a distributed processing system.
SUMMARY OF THE INVENTION
The present invention overcomes the shortcomings in prior systems and thereby satisfies a significant need for providing multiple queue redundancy without the expense of added system usage in maintaining the backup queue in real time. According to a preferred embodiment of the present invention, a distributed processing system or network includes a plurality of processing units, each of which includes a local queue. A first processing unit includes a central queue. Each processing unit includes system software and necessary hardware for transporting and/or sending data between processing units in the distributed network. The software and hardware also allows data that is intended to be centrally processed, such as by an electronic mail or print server, to be transported to the central queue from any processing unit. Data transported by a processing unit to the central queue is also maintained by the transporting processing unit, together with processing information relating to the data. The processing information may include a time stamp marking the time the corresponding data was transported to the central queue, or priority information indicating the level of priority for centrally processing the data. By maintaining the redundant data locally at each processing unit, system-level resources are not utilized during normal operation in order to maintain a second or backup central queue.
In the event the central queue fails or otherwise malfunctions, the system software and hardware at each processing unit recreates the central queue at another processing unit in the network. Specifically, data that was previously transported to the central queue is transported from each processing unit to the location of the new central queue, together with the processing information relating to the data. The system determines the order of data in the new central queue based upon the processing information (time stamp and/or priority information) transported with the data. In this way, the new central queue is created which substantially matches the original central queue prior to the failure thereof.
REFERENCES:
patent: 5566297 (1996-10-01), Devarakonda et al.
patent: 5590318 (1996-12-01), Zbikowski et al.
patent: 5649092 (1997-07-01), Price et al.
patent: 5796934 (1998-08-01), Bhanot et al.
patent: 5944838 (1999-08-01), Jantz
patent: 6185695 (2001-02-01), Murphy et al.
patent: 6278988 (2001-08-01), Lau et al.
patent: 6353834 (2002-03-01), Wong et al.
patent: 6385616 (2002-05-01), Gardner
Savela Orjan
Stenlund Bo
Beausoliel Robert
Duncan Marc
Ericsson Inc.
LandOfFree
System and method for providing multiple queue redundancy in... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for providing multiple queue redundancy in..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for providing multiple queue redundancy in... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3151766