US 6,618,819 B1 · Sparing system and method to accommodate equipment failures in critical systems

Abstract

A sparing system and method of accommodating failure of equipment in critical systems comprises, in one embodiment, 1:n sparing where an equipment spare is provided for every n pieces of equipment in the system. The spare equipment includes journal memory wherein an image of the operating system, applications and state of each piece of equipment being spared for can be maintained. The image information is updated at appropriate intervals when the equipment is operating without a failure and, in the event of a piece of equipment failing, the spare equipment loads the state of failed equipment from the corresponding image and commences executing the software in the corresponding image, thus resuming performance of the activities of the failed equipment. In a second embodiment, m:n sparing is provided wherein m pieces of spare equipment are provided for n pieces of equipment to accommodate m failures of the equipment.

Claims11

Dependent claims

A sparing method of accommodating equipment failures in a critical system comprising n pieces of equipment and at least one spare piece of equipment for said n pieces of equipment, comprising the steps of:

(i) loading software onto each of said n pieces of equipment;
(ii) commencing execution of said loaded software with said respective piece of equipment;
(iii) transferring an image of information on each of said n pieces of equipment to a memory on said at least one spare piece of equipment when commencing the execution, said information including said loaded software and a hardware state;
(iv) detecting a failure of one of said n pieces of equipment;
(v) causing said at least one spare piece of equipment to replace said detected one piece of equipment by commencing execution of said image corresponding to said detected one piece of equipment, which is stored in the memory, to employ said at least one spare piece of equipment in place of said detected one piece of equipment.

2 more elements

A sparing system to accommodate equipment failures in a critical system comprising:

n pieces of equipment, each of equipment including a memory to maintain software to be executed by said piece of equipment and state information for said piece of equipment, said state information including a hardware state;
at least one spare piece of equipment including a journal memory to store an image of said software and said state information maintained in said memory of each of said n pieces of equipment;
a communication path between each of said n pieces of equipment and said at least one piece of equipment to allow transfer of the image of each said piece of equipment to said journal memory when each said piece of equipment commences execution of the software, each of said n pieces of equipment operable to transfer the image maintained in a corresponding memory to said journal memory;
wherein upon determination that one of said n pieces of equipment has experienced a failure, said at least one spare piece of equipment loads said image corresponding to said one piece of equipment and operates to execute said image to replace said one piece of equipment.

1 more element

Dependencies are inferred from the claim text.

Sparing system and method to accommodate equipment failures in critical systems

Life of this patent

Sparing system and method to accommodate equipment failures in critical systems

Life of this patent

Abstract

Claims11