Method, management node and processing node for continuous availability in cloud environment

Patent metadata

Field	Value
Publication number	US-11456934-B2
Application number	US-201716762123-A
Country	US
Kind code	B2
Filing date	Nov 9, 2017
Priority date	Nov 9, 2017
Publication date	Sep 27, 2022
Grant date	Sep 27, 2022

Abstract

Method, management node and processing node are disclosed for continuous availability in a cloud environment. According to an embodiment, the cloud environment comprises a plurality of layers and each layer includes at least two processing nodes. Each processing node in a layer can pull job(s) from the processing nodes in the upper layer if any and prepare job(s) for the processing nodes in the under layer if any. A method implemented at a management node comprises receiving measurement reports from the plurality of layers. The measurement report of each processing node comprises information about job(s) pulled from the upper layer if any and job(s) pulled by the under layer if any. The method further comprises determining information about failure in the cloud environment based on the measurement reports.

First claim

What is claimed is:

1. A method, comprising:
receiving measurement reports at a management node in a cloud environment comprising a plurality of layers, each layer of the plurality of layers comprising at least two processing nodes, each processing node in a layer of the plurality of layers operable to pull jobs from the processing nodes in an upper layer of the plurality of layers and prepare jobs for the processing nodes in an under layer of the plurality of layers, wherein the measurement report of said each processing node comprises information about any jobs pulled from the upper layer and any jobs pulled by the under layer; and
determining information about failure in the cloud environment based on the measurement reports.

2. The method according to claim 1 , wherein the information about jobs pulled from the upper layer comprises at least identification information of the processing nodes from which the jobs have been pulled; and
wherein the information about jobs pulled by the under layer comprises at least identification information of the processing nodes that have pulled the jobs.

3. The method according to claim 1 , wherein the plurality of layers comprises at least a first layer and its upper and under layers, and the first layer includes at least a first and a second processing nodes; wherein determining the information about failure comprises:
checking whether no measurement report has been received from the first processing node for a first predetermined period;
checking whether the first processing node has pulled jobs from the upper layer;
checking whether the under layer has pulled jobs from the first processing node; and
determining the information about failure based on the checking results.

4. The method according to claim 3 , wherein determining the information about failure comprises:
when no measurement report has been received from the first processing node, the first processing node has pulled no jobs from the upper layer, and the under layer has pulled no jobs from the first processing node, determining that the first processing node fails;
when no measurement report has been received from the first processing node, the first processing node has pulled jobs from the upper layer, and the under layer has pulled jobs from the first processing node, determining that the connection between the first processing node and the management node breaks;
when a measurement report has been received from the first processing node, the first processing node has pulled no jobs from the upper layer, and the under layer has pulled no jobs from the first processing node, determining that the connection between the first processing node and the under layer breaks; and
when a measurement report has been received from the first processing node, the first processing node has pulled jobs from the upper layer, and only a third processing node in the under layer has pulled no jobs from the first processing node, determining that the connection between the first and third processing nodes breaks.

5. The method according to claim 1 , wherein the plurality of layers comprises at least a first layer and its under layer, and the first layer is the uppermost layer including at least a first and a second processing nodes; wherein determining the information about failure comprises:
checking whether no measurement report has been received from the first processing node for a first predetermined period;
checking whether the under layer has pulled jobs from the first processing node; and
determining the information about failure based on the checking results.

6. The method according to claim 5 , wherein determining the information about failure comprises:
when no measurement report has been received from the first processing node, and the under layer has pulled no jobs from the first processing node, determining that the first processing node fails;
when no measurement report has been received from the first processing node, and the under layer has pulled jobs from the first processing node, determining that the connection between the first processing node and the management node breaks;
when a measurement report has been received from the first processing node, and the under layer has pulled no jobs from the first processing node, determining that the connection between the first processing node and the under layer breaks; and
when a measurement report has been received from the first processing node, and only a third processing node in the under layer has pulled no jobs from the first processing node, determining that the connection between the first and third processing nodes breaks.

7. The method according to claim 1 , wherein the plurality of layers comprises at least a first layer and its upper layer, and the first layer is the undermost layer including at least a first and a second processing nodes; and
wherein determining the information about failure comprises:
checking whether no measurement report has been received from the first processing node for a first predetermined period;
checking whether the first processing node has pulled jobs from the upper layer; and
determining the information about failure based on the checking results.

8. The method according to claim 7 , wherein determining the information about failure comprises:
when no measurement report has been received from the first processing node, and the first processing node has pulled no jobs from the upper layer, determining that the first processing node fails;
when no measurement report has been received from the first processing node, and the first processing node has pulled jobs from the upper layer, determining that the connection between the first processing node and the management node breaks;
when a measurement report has been received from the first processing node, and the first processing node has pulled no jobs from the upper layer, determining that the connection between the first processing node and the upper layer breaks; and
when a measurement report has been received from the first processing node, and the first processing node has pulled no jobs from only a third processing node in the upper layer, determining that the connection between the first and third processing nodes breaks.

9. The method according to claim 1 , wherein the management node can be configured to act as a backup management node for another management node; and
wherein the method further comprises:
checking whether the another management node has not synchronized with the backup management node for a second predetermined period;
in response to a positive checking result, initiating a vote about the alive/dead status of the another management node to the processing nodes in the plurality of layers;
receiving vote data from the processing nodes in the plurality of layers; and
determining failure information related to the another management node based on the vote data.

10. The method according to claim 9 , wherein determining the failure information related to the another management node comprises:
when all the processing nodes vote that the another management node is dead, determining that the another management node fails; and
when all the processing nodes vote that the another management node is alive, determining that the connection between the another management node and the backup management node breaks.

11. A management node for use in a cloud environment, wherein the cloud environment comprises a plurality of layers, each layer of the plurality of layers includes at least two processing nodes, and each processing node in a layer of the plurality of layers is operable to pull jobs from the processing

Assignees

• Nokia Shanghai Bell Co Ltd

Inventors

• Wang Bi

Classifications

• H04L41/0695

  the faulty arrangement being the maintenance, administration or management system · CPC title

• G06F11/2038

  with a single idle spare processing component · CPC title

• G06F11/079

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• H04L67/1036

  Load balancing of requests to servers for services different from user content provisioning, e.g. load balancing across domain name servers · CPC title

• G06F11/0757

  by exceeding a time limit, i.e. time-out, e.g. watchdogs · CPC title