US 7,480,827 B2 · Fault tolerance and failover using active copy-cat

Abstract

Fault tolerant operation is disclosed for a primary instance, such as a process, thread, application, processor, etc., using an active copy-cat instance, a.k.a. backup instance, that mirrors operations in the primary instance, but only after those operations have successfully completed in the primary instance. Fault tolerant logic monitors inputs and outputs of the primary instance and gates those inputs to the backup instance once a given input has been processed. The outputs of the backup instance are then compared with the outputs of the primary instance to ensure correct operation. The disclosed embodiments further relate to fault tolerant failover mechanism allowing the backup instance to take over for the primary instance in a fault situation wherein the primary and backup instances are loosely coupled, i.e. they need not be aware that they are operating in a fault tolerant environment. As such, the primary instance need not be specifically designed or programmed to interact with the fault tolerant mechanisms. Instead, the primary instance need only be designed to adhere to specific basic operating guidelines and shut itself down when it cannot do so. By externally controlling the ability of the primary instance to successfully adhere to its operating guidelines, the fault tolerant mechanisms of the disclosed embodiments can recognize error conditions and easily failover from the primary instance to the backup instance.

Claims13

Dependent claims

A method of providing fault tolerance to a primary instance, the method comprising:

receiving a copy of a first input transmitted to the primary instance;
receiving a copy of a second input transmitted to the primary instance, the copy of the second input being received subsequent to the copy of the first input;
waiting, in response to the receiving of the copy of the first input, for the primary instance to transmit a first primary result based on the first input;
waiting, in response to the receiving of the copy of the second input, for the primary instance to transmit a second primary result based on the second input;
forwarding the copy of the first input to a backup instance operative to generate a first backup result based on the forwarded copy of the first input upon the transmission of the first and second primary results by the primary instance, the first primary result having been transmitted prior to the second primary result;
forwarding the copy of the second input to the backup instance operative to generate a second backup result based on the forwarded copy of the second input upon the transmission of the first and second primary results by the primary instance, the second primary result having transmitted prior to the first primary result;
determining that the first primary result is not likely to be transmitted;
preventing, based on the determination that the first primary result is not likely to be transmitted, the primary instance from completing a transaction that the primary instance is supposed to complete to continue operating;
and
transmitting the first backup result when the first primary result is not likely to be transmitted.

7 more elements

A system for providing fault tolerance to a primary instance, the system comprising:

a processor;
a memory coupled with the processor;
first logic stored in the memory and executable by the processor to receive a copy of a first input transmitted to the primary instance, the first logic being further executable by the processor to receive a copy of a second input transmitted to the primary instance, the copy of the second input being received subsequent to the copy of the first input;
fourth logic stored in the memory, coupled with the first logic and executable by the processor to wait, in response to the receiving of the copy of the first input, for the primary instance to transmit a first primary result based on the first input, the fourth logic being further executable by the processor to wait, in response to the receiving of the copy of the second input, for the primary instance to transmit a second primary result based on the second input, wherein the fourth logic is further executable by the processor to determine that the first primary result is not likely to be transmitted;
second logic stored in the memory, coupled with the first logic and executable by the processor to forward the copy of the first input to a backup instance upon the transmission of the first and second primary results by the primary instance, the first primary result having been transmitted prior to the second primary result, the backup instance being operative to generate a first backup result based on the forwarded copy of the first input, the second logic being further executable by the processor to forward the copy of the second input to the backup instance upon the transmission of the first and second primary results by the primary instance, the second primary result having been transmitted prior to the first primary result, the backup instance being operative to generate a second backup result based on the forwarded copy of the second input;
fifth logic stored in the memory, coupled with the fourth logic and executable by the processor to prevent, based on the fourth logic determining that the first primary result is not likely to be transmitted, the primary instance from completing a transaction that the primary instance is supposed to complete to continue operating;
and
sixth logic stored in the memory, coupled with the backup instance and the fourth logic and executable by the processor to transmit the first backup result when the first primary result is not likely to be transmitted.

5 more elements

Dependencies are inferred from the claim text.

Fault tolerance and failover using active copy-cat

Life of this patent

Fault tolerance and failover using active copy-cat

Life of this patent

Abstract

Claims13