DATA BASED SCHEDULING FOR HORIZONTALLY SCALABLE CLUSTERS

• US 20200133728A1
• Filed: 10/30/2018
• Published: 04/30/2020
• Est. Priority Date: 10/30/2018
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Nataraj, Pruthvi Panyam, Bhande, Ajay Vishwanath, Gupta, Amit Kumar
• Granted Patent: US 11,301,299 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/5033 considering data affinity
• CPC Class Codes: G06F 9/505 considering the load

Abstract

An apparatus comprising: a processing resource; a memory resource to store instructions executable by the processing resource to: associate a plurality of consumer containers with a data container, wherein the plurality of consumer containers accesses the data container; identify a node of a cloud computing system that hosts the data container; and schedule the plurality of consumer containers to execute on the node based on the association between the plurality of consumer containers and the data container.

Claims

1. An apparatus comprising:

a processing resource;

a memory resource to store instructions executable by the processing resource to;

associate a plurality of consumer containers with a data container, wherein the plurality of consumer containers accesses the data container;

identify a node of a horizontally scalable cluster that hosts the data container; and

schedule the plurality of consumer containers to execute on the node based on the association between the plurality of consumer containers and the data container.

2. The apparatus of claim 1, wherein the instructions are further executable to associate the plurality of consumer containers with a data segment of the data container.

3. The apparatus of claim 2, wherein the instructions are further executable to schedule the plurality of consumer containers to execute on the node based on the association between the data segment of the data container and the plurality of consumer containers.

4. The apparatus of claim 2, wherein the instructions are further executable to identify the node of the cloud computing system that hosts the data segment.

5. The apparatus of claim 1, wherein the node comprises at least one of a physical computing node and a virtual computing node.

6. The apparatus of claim 1, wherein the data container is a logical container for data segments of a same type.

8. The apparatus of claim 1, wherein the instructions are further executable to deploy the plurality of consumer containers and the data container on the node based on the schedule.

9. The apparatus of claim 1, wherein the instructions are further executable to identify the node of the cloud computing system that hosts the data container and is master of a data segment hosted by the data container.

10. The apparatus of claim 9, wherein instructions are further executable to schedule the plurality of consumer containers to execute on the node based on the association between the plurality of consumer containers and the data container and the node being master of the data segment.

7. The apparatus of claim 7, wherein each of the plurality of consumer containers is a logical container to access the data segments.

11. A non-transitory machine-readable medium storing instructions executable by a processing resource to:

receive a request to reschedule a consumer container previously hosted by a first node of a cloud computing system;

associate a data container and a data segment hosted by the data container with the consumer container;

identify a second node of the cloud computing system that is master of the data segment;

schedule the consumer container to execute on the second node based on the association; and

deploy the consumer container and on the second node based on the schedule.

12. The non-transitory machine-readable medium of claim 11, wherein the request is generated responsive to an unavailability of the data segment on the first node.

13. The non-transitory machine-readable medium of claim 11, wherein the request is generated responsive to restarting the consumer container.

14. The non-transitory machine-readable medium of claim 11, wherein the request is generated responsive to scaling the consumer container.

15. The non-transitory machine-readable medium of claim 11, wherein the request comprises an identification (ID) of the consumer container and an ID of the data container.

16. The non-transitory machine-readable medium of claim 11, further comprising instructions executable to receive the request from one of the first node and the second node.

17. A method, comprising:

deploying a first copy of the data container on a first node and a second copy of the data container on a second node of a horizontally scalable cluster;

deploying a consumer container on the first node of the horizontally scalable cluster, wherein the first node is master of a data segment hosted by the first copy of the data container;

labeling the second node as master of the data segment hosted by the second copy of the data container; and

scheduling the consumer container to execute on the second node responsive to assigning the second node as master of the data segment hosted by the second copy of the data container.

18. The method of claim 17, wherein the second node is labeled as master of the data segment hosted by the second copy of the data container responsive to an unavailability of the first node.

19. The method of claim 18, further comprising restarting the first node, wherein the first node is made unavailable responsive to restarting the first node.

20. The method of claim 17, further comprising scheduling a second consumer container to execute on the second node responsive to assigning the second node as master of the data segment hosted by the second copy of the data container.