Redundancy device

Patent metadata

Field	Value
Publication number	US-9491228-B2
Application number	US-201113979788-A
Country	US
Kind code	B2
Filing date	Dec 7, 2011
Priority date	Mar 10, 2011
Publication date	Nov 8, 2016
Grant date	Nov 8, 2016

Abstract

A computing unit computes a computed value for input data. A comparing unit compares the computed value of the computing unit with a computed value of another node which is included in an input/output set. An output unit outputs the computed value as output data of a node itself when the result of the comparison by the comparing unit shows that the computed value matches either one of computed values. When the computed value does not match any one of the computed values of other nodes, a transferring unit adds the computed value of the node itself to the input/output set, and transfers the input/output set to another node.

First claim

The invention claimed is:

1. A redundancy device that implements redundancy by grouping a plurality of nodes connected to a network, and enabling nodes within each group to exchange input and output data with one another within the group, the redundancy device comprising:
the plurality of nodes, wherein
each of said nodes includes:
a computing unit, implemented by circuitry and configured to receive either input data or an input/output set including said input data and a computed value of another node within the group, and carry out a computation on said input data,
a comparing unit, implemented by the circuitry and configured to, when said input/output set is inputted thereto, compare a computed value of said computing unit with the computed value of said other node,
an output unit, implemented by the circuitry and configured to, when a result of the comparison by said comparing unit shows that the computed value of said computing unit matches either one of computed values, output said computed value as output data of the node itself, and
a transferring unit, implemented by the circuitry and configured to, when the result of the comparison by said comparing unit shows that the input/output set does not include any computed value matching the computed value of said computing unit, add the computed value of said computing unit to the input/output set and then transfer this input/output set to another node.

2. The redundancy device according to claim 1 , wherein when the result of the comparison by the comparing unit shows that the input/output set includes a computed value matching the computed value of the computing unit and a computed value not matching the computed value of the computing unit, said redundancy device determines that a node which has transferred said computed value not matching the computed value of the computing unit is faulty, and notifies a node within the group to that effect.

3. The redundancy device according to claim 1 , wherein the transferring unit transfers the input/output set to which the computed value of the computing unit is added to another node before a predetermined response time period has elapsed.

4. The redundancy device according to claim 1 , wherein said redundancy device outputs a default value or a previous value when not finding out a computed value matching the computed value of the computing unit before a predetermined response time period has elapsed.

5. The redundancy device according to claim 1 , wherein when computed values of N nodes (N is an arbitrary integer) match one another, said redundancy device outputs said matching computed value as output data.

6. The redundancy device according to claim 1 , wherein said redundancy device defines a maximum number of times that said redundancy device carries out a transfer of data when no computed value matching any other computed value is acquired, and the transferring unit carries out a transfer of data until the number of times that said redundancy device has carried out a transfer of data reaches said maximum number of times.

7. A redundancy device that implements redundancy by grouping a plurality of nodes connected to a network, and enabling nodes within each group to exchange input and output data with one another within the group, the redundancy device comprising:
the plurality of nodes, wherein
each of said nodes includes:
a computing unit, implemented by circuitry and configured to receive either input data or an input/output set including said input data and a computed value of another node within the group, and carry out a computation on said input data,
a transferring unit, implemented by the circuitry and configured to add a computed value of said computing unit to said input/output set, and transfer said input/output set to another node within said group until a number of times that said redundancy device has carried out a transfer of data reaches a predetermined number of times, and
an output unit, implemented by the circuitry and configured to selectively output a most frequently computed value from the computed value of said computing unit and the computed value of said other node which are acquired through the transferring operation which has been carried out said predetermined number of times.

8. A redundancy device that implements redundancy by grouping a plurality of nodes connected to a network, and enabling nodes within each group to exchange input and output data with each other within the group, the redundancy device comprising:
the plurality of nodes, wherein
each of said nodes includes:
a computing unit, implemented by circuitry and configured to receive either input data or an input/output set including said input data and a computed value of another node within the group, and carry out a computation on said input data,
a transferring unit, implemented by the circuitry and configured to add the computed value of said computing unit to said input/output set, and carry out a transfer of said input/output set to another node in said group until a predetermined deadline has been reached within a cycle, and
an output unit, implemented by the circuitry and configured to selectively output a most frequently computed value from the computed value of said computing unit and the computed value of said other node which have been acquired until said predetermined deadline.

Assignees

• Sasaki Kenichi
• Mitsubishi Electric Corp

Inventors

• Sasaki Kenichi

Classifications

• H04L67/10 Primary

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title

• G06F11/181

  Eliminating the failing redundant component · CPC title

• G06F11/182 Primary

  based on mutual exchange of the output between redundant processing components · CPC title

• G06F11/187

  Voting techniques · CPC title