Modified consensus protocol for eliminating heartbeat network traffic

Patent metadata

Field	Value
Publication number	US-2017366451-A1
Application number	US-201615184173-A
Country	US
Kind code	A1
Filing date	Jun 16, 2016
Priority date	Jun 16, 2016
Publication date	Dec 21, 2017
Grant date	—

Abstract

A computing system in data communication with a plurality of nodes that make up a distributed computing cluster can detect an absence of communication from a node of the plurality of nodes over a time period that exceeds a predefined threshold time period. The computing system can query an instance of a central topology manager for the plurality of nodes regarding liveness of the node from which the absence of communication was detected and can attempting to re-initiate communication with the node when the instance of the central topology manager indicates that the node is live.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
detecting, by a computing system in data communication with a plurality of nodes that make up a distributed computing cluster, an absence of communication from a node of the plurality of nodes over a time period that exceeds a predefined threshold time period; querying, by the computing system, an instance of a central topology manager for the plurality of nodes regarding liveness of the node from which the absence of communication was detected; and attempting, by the computing system, to re-initiate communication with the node when the instance of the central topology manager indicates that the node is live.

2 . A computer-implemented method as in claim 1 , wherein the computing system comprises another node of the plurality of nodes.

3 . A computer-implemented method as in claim 1 , wherein the computing system comprises a client machine in communication with the cluster.

4 . A computer-implemented method as in claim 1 , wherein the re-initiating comprises retrying a failed communication with the node.

5 . A computer-implemented method as in claim 1 , wherein the re-initiating comprises ceasing the communication from the master node of the cluster to a follower node of the cluster.

6 . A computer-implemented method as in claim 1 , wherein the re-initiating comprises starting a new master election process on a follower node of the plurality of nodes.

7 . A computer program product comprising a non-transitory machine-readable medium storing instructions that, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:
detecting, by a computing system in data communication with a plurality of nodes that make up a distributed computing cluster, an absence of communication from a node of the plurality of nodes over a time period that exceeds a predefined threshold time period; querying, by the computing system, an instance of a central topology manager for the plurality of nodes regarding liveness of the node from which the absence of communication was detected; and attempting, by the computing system, to re-initiate communication with the node when the instance of the central topology manager indicates that the node is live.

8 . A computer program product as in claim 7 , wherein the computing system comprises another node of the plurality of nodes.

9 . A computer program product as in claim 7 , wherein the computing system comprises a client machine in communication with the cluster.

10 . A computer program product as in claim 7 , wherein the re-initiating comprises retrying a failed communication with the node.

11 . A computer program product as in claim 7 , wherein the re-initiating comprises ceasing the communication from the master node of the cluster to a follower node of the cluster.

12 . A computer program product as in claim 7 , wherein the re-initiating comprises starting a new master election process on a follower node of the plurality of nodes.

13 . A system comprising:
computer hardware configured to perform operations comprising:
detecting, by a computing system in data communication with a plurality of nodes that make up a distributed computing cluster, an absence of communication from a node of the plurality of nodes over a time period that exceeds a predefined threshold time period;
querying, by the computing system, an instance of a central topology manager for the plurality of nodes regarding liveness of the node from which the absence of communication was detected; and
attempting, by the computing system, to re-initiate communication with the node when the instance of the central topology manager indicates that the node is live.

14 . A system as in claim 13 , wherein the computing system comprises another node of the plurality of nodes.

15 . A system as in claim 13 , wherein the computing system comprises a client machine in communication with the cluster.

16 . A system as in claim 13 , wherein the re-initiating comprises retrying a failed communication with the node.

17 . A system as in claim 13 , wherein the re-initiating comprises ceasing the communication from the master node of the cluster to a follower node of the cluster.

18 . A system as in claim 13 , wherein the re-initiating comprises starting a new master election process on a follower node of the plurality of nodes.

19 . A system as in claim 13 , wherein the computer hardware comprises
a programmable processor; and a machine-readable medium storing instructions that, when executed by the processor, cause the at least one programmable processor to perform at least some of the operations.

Assignees

• Sap Se

Inventors

• Schreter Ivan

Classifications

• H04L43/16

  Threshold monitoring · CPC title

• H04L45/28 Primary

  using route fault recovery · CPC title

• H04L43/0811 Primary

  by checking connectivity · CPC title

• H04L45/46

  Cluster building · CPC title

• H04L67/10

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