Error detection/correction and fault detection/recovery – Data processing system error or fault handling – Reliability and availability
Reexamination Certificate
1998-07-31
2001-12-04
Le, Dieu-Minh (Department: 2184)
Error detection/correction and fault detection/recovery
Data processing system error or fault handling
Reliability and availability
C714S004110
Reexamination Certificate
active
06327675
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates to fault tolerant systems, and more particularly to modular computing and communications systems having at least one redundant module.
BACKGROUND OF THE INVENTION
Fault tolerant computing and communications systems having redundant or spare components are known. One or more active primary data processing components are shadowed by one or more spare components, ready to take the place of the primary components in the event of failure.
Typically, the systems are adapted to effect a switch-over from a failed active component to a spare component in real time, and as quickly as possible to avoid possible data losses at the failed component.
Such fault tolerant systems, however, are premised largely on the assumption that failures of components are caused by hardware failures which are typically permanent. In many systems, computing resources are distributed among modules, with each module having its own processor under software control. Such systems are prone to software faults within the modules, as well as traditional hardware faults. Software faults, unlike hardware faults, are often aberrant, occurring rarely under special circumstances. Moreover, software faults are typically not remedied by replacing one active module with an identical spare module having the same software deficiency.
Accordingly, a fault tolerant system that more effectively recognizes and handles recoverable faults is desirable.
SUMMARY OF THE INVENTION
In accordance with an aspect of the present invention, there is provided, in a modular computing system comprising at least one primary module processing data under software control, and one spare module capable of processing data under software control, a method of switching data at the primary module to the spare module, comprising the steps of: a) sensing failure of the primary module; b) resetting the primary module in response to sensing the failure; c) waiting a determined time interval for successful reset of the primary module; d) if reset in step b. is not successful in the determined time interval, switching the data from the primary module to the spare module, and processing the data at the spare module.
In accordance with another aspect of the present invention, there is provided, in a modular computing system, comprising at least one primary module for processing data, and one redundant module capable of processing data, a method of switching data from the primary module to the redundant module, comprising the steps of: a) sensing failure of the primary module; b) determining if the failure is recoverable; c) if the failure is not recoverable, switching the data from the primary module to the redundant module, and processing the data at the spare module.
In accordance with a further aspect of the present invention, there is provided a modular computing system comprising: a) at least one primary processing module, operable to process data at the primary processing module; b) a spare processing module, capable of processing data at the spare module c) a control processor interconnected with the spare processing module and the primary processing module to switch data between the primary module and the spare module; the control processor operable to i) sense failure of the primary module; ii) determine if the failure is recoverable; iii) if the failure is not recoverable, switch the data from the primary module to the spare module for processing of the data at the spare module.
In accordance with yet a further aspect of the present invention, there is provided a modular computing system comprising: a) at least one primary processing module, operable to process data at the primary processing module; b) a spare processing module, capable of processing data at the spare module; c) means for sensing failure of the primary module; d) means for determining if the failure is recoverable; and e) means for switching the data from the primary module to the spare module for processing of the data at the spare module, in the event of the failure is not recoverable.
REFERENCES:
patent: 4276451 (1981-06-01), Beebe
patent: 4881227 (1989-11-01), Buhren
patent: 5291494 (1994-03-01), Bruckert et al.
patent: 5367665 (1994-11-01), Koch
patent: 6145089 (2000-11-01), Le
patent: 6161193 (2000-12-01), Garg
Burdett Gregory P.
Imbeau Rene
O'Neill John
Paquet Michel
Stubberfield Mark
Bonzo Bryce P.
Le Dieu-Minh
Millard Allan P.
Nortel Networks Limited
LandOfFree
Fault tolerant system and method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Fault tolerant system and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fault tolerant system and method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2587936