Data plane API in a distributed computing network

• US 10,432,450 B2
• Filed: 06/30/2016
• Issued: 10/01/2019
• Est. Priority Date: 06/30/2016
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Johnson, James Ernest, Suriyanarayanan, Guhan, Irun-Briz, Luis
• Primary Examiner(s): Chea, Philip J
• Assistant Examiner(s): McAdams, Robert B
• Application Number:
  US15/199,762
• Publication Number:
  US 20180006872A1
• Time in Patent Office: 1,188 Days
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455
• CPC Class Codes: H04L 41/0266 using meta-data, objects or commands for formatting management information, e.g. using eXtensible markup language [XML]
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

Embodiments are directed to a distributed computing system comprising a plurality of compute nodes for providing resources to users and a hierarchy of two or more layers of controllers coupling the compute nodes to a user interface via a control plane, wherein at least one compute node receives a local application program interface (API) call from an application running on the at least compute node, the local API call causing the at least one compute node to configure a local resource without requiring commands from the control plane.

Claims

1. A distributed computing system, comprising:

a plurality of compute nodes for providing resources to users; and

a hierarchy of two or more layers of controllers coupling the plurality of compute nodes to a user interface via a control plane;

wherein at least one compute node receives a local application program interface (API) call from code executing on the at least one compute node, the local API call causing the at least one compute node to configure a local resource without requiring commands from the control plane, the local API call being within parameters specified in a model, the parameters defining limits as to which local decisions are allowed.

2. The system of claim 1, wherein the local resource includes one or more containers specified by the model.

3. The system of claim 2, wherein the model defines virtual machines, specific applications, or operating systems.

4. The system of claim 2, wherein the local API call causes the at least one compute node to auto-clean a container running the code.

5. The system of claim 2, wherein the local API call causes the compute node to clean a second container on the compute node other than a container running the code.

6. The system of claim 2, wherein the local API call causes the compute node to start one or more new containers.

7. The system of claim 2, wherein the local API call causes the compute node to shut down one or more containers.

8. The system of claim 2, wherein the local API call causes the compute node to attach the containers to a communication network.

9. The system of claim 2, wherein the local API call causes the compute node to attach the containers to a disk.

10. The system of claim 2, wherein the local API call causes the compute node to resize a run space available for the container.

11. The system of claim 2, further comprising:

a cluster controller coupled to two or more compute nodes; and

wherein the local API call from a first container on a first compute node causes a second container on a second compute node to be cleaned.

12. The system of claim 2, further comprising:

a cluster controller coupled to two or more compute nodes; and

wherein the local API call from a first container on a first compute node causes a second container on a second compute node to start.

13. A computer-implemented method for controlling resources in a distributed computing system, comprising:

receiving, at a compute node in the distributed computing system, a local application program interface (API) call from an application running on the compute node; and

configuring a local resource in response to the local API call without requiring commands from a control plane, the local API call being within parameters specified in a model, the parameters defining limits as to which local decisions are allowed.

14. The method of claim 13, wherein the distributed computing system comprises a plurality of compute nodes for providing resources to users, and the distributed computing system comprises a hierarchy of two or more layers of controllers coupling the plurality of compute nodes to a user interface via the control plane.

15. The method of claim 13, wherein the resources comprise containers, and the application comprises code executing on a container.

16. The method of claim 15, further comprising:

in response to the API call, auto-cleaning the container.

17. The method of claim 15, further comprising:

in response to the local API call, starting one or more new containers or shutting down one or more containers.

18. The method of claim 14, further comprising:

in response to the local API call, attaching a virtual machine to a communication network or detaching the container to the communication network.

19. The method of claim 14, further comprising:

in response to the local API call, attaching the container to a disk or detaching the container from the disk.