Granted Patent B1

US 10,298,681 · App. 15/014,046 · Granted May 21, 2019

Abstract

Claims (54)

1. A computer-implemented method for rerouting data sent between application containers and storage containers, at least a portion of the method being performed by a computing device comprising at least one processor, the method comprising:

identifying an application container, a storage container that stores data for the application container, and a host comprising physical hardware that hosts both the application container and the storage container;

configuring the application container and the storage container to share a namespace on the host, wherein at least one of the application container or the storage container is configured to share the namespace before deployment to the host, and wherein the application container and the storage container are independent of any namespace prior to being configured to share the namespace on the host;

creating, within the shared namespace on the host, a resource that enables the application container and the storage container to share data;

rerouting at least one item of data sent between the application container and the storage container to pass through the resource in the shared namespace rather than through a kernel of the host by:

loading a library that implements a library function comprising a portable operating system interface (POSIX) application programming interface (API) for a file system library, wherein the library is preloaded at a daemon level and hooks a plurality of child processes comprising the application container and the storage container to the library;

intercepting, by the library function, the at least one item of data as part of a write request intended for the storage container, the at least one item of data comprising one or more input/output (I/O) packets; and

redirecting, by the library, the I/O packets to a ring buffer accessible by the storage container, wherein the rerouting reduces a storage and hardware processing resource load on the host and enables the host to more efficiently run a greater number of application containers.

2. The computer-implemented method of claim 1 ,

further comprising identifying a write request initiated by the application container to write data to the storage container;

wherein rerouting the at least one item of data comprises rerouting the write request sent from the application container to the storage container.

3. The computer-implemented method of claim 1 ,

further comprising identifying a read request initiated by the application container to read data from the storage container;

wherein rerouting the at least one item of data comprises rerouting the data sent from the storage container to the application container in response to the read request.

4. The computer-implemented method of claim 1 , wherein the resource comprises a data structure in shared memory that is accessible by both the application container and the storage container.

5. The computer-implemented method of claim 1 , wherein the resource comprises an inter-process communication socket.

6. The computer-implemented method of claim 1 , wherein the ring buffer comprises an array of elements including at least a top element and a bottom element.

7. The computer-implemented method of claim 6 , wherein the bottom element in the array of elements points to the top element in the array of elements.

8. A system for rerouting data sent between application containers and storage containers, the system comprising:

an identification module, stored in memory, that identifies an application container, a storage container that stores data for the application container, and a host comprising physical hardware that hosts both the application container and the storage container;

a configuration module, stored in memory, that configures the application container and the storage container to share a namespace on the host, wherein at least one of the application container or the storage container is configured to share the namespace before deployment to the host, and wherein the application container and the storage container are independent of any namespace prior to being configured to share the namespace on the host;

a creation module, stored in memory, that creates, within the shared namespace on the host, a resource that enables the application container and the storage container to share data;

a rerouting module, stored in memory, that reroutes at least one item of data sent between the application container and the storage container to pass through the resource in the shared namespace rather than through a kernel of the host by:

loading a library that implements a library function comprising a portable operating system interface (POSIX) application programming interface (API) for a file system library, wherein the library is preloaded at a daemon level and hooks a plurality of child processes comprising the application container and the storage container to the library;

intercepting, by the library function, the at least one item of data as part of a write request intended for the storage container, the at least one item of data comprising one or more input/output (I/O) packets; and

redirecting, by the library, the I/O packets to a ring buffer accessible by the storage container, wherein the rerouting reduces a storage and hardware processing resource load on the host and enables the host to more efficiently run a greater number of application containers;

at least one physical processor configured to execute the identification module, the configuration module, the creation module, and the rerouting module.

9. The system of claim 8 , wherein:

the identification module identifies a write request initiated by the application container to write data to the storage container;

the rerouting module reroutes the at least one item of data by rerouting the write request sent from the application container to the storage container.

10. The system of claim 8 , wherein:

the identification module identifies a read request initiated by the application container to read data from the storage container;

the rerouting module reroutes the at least one item of data by rerouting the data sent from the storage container to the application container in response to the read request.

11. The system of claim 8 , wherein the resource comprises a data structure in shared memory that is accessible by both the application container and the storage container.

12. The system of claim 8 , wherein the resource comprises an inter-process communication socket.

13. The system of claim 8 , wherein the ring buffer comprises an array of elements including at least a top element and a bottom element.

14. The system of claim 13 , wherein the bottom element in the array of elements points to the top element in the array of elements.

15. A non-transitory computer-readable medium comprising one or more computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to:

identify an application container, a storage container that stores data for the application container, and a host comprising physical hardware that hosts both the application container and the storage container;

configure the application container and the storage container to share a namespace on the host, wherein at least one of the application container or the storage container is configured to share the namespace before deployment to the host, and wherein the application container and the storage container are independent of any namespace prior to being configured to share the namespace on the host;

create, within the shared namespace on the host, a resource that enables the application container and the storage container to share data;

reroute at least one item of data sent between the application container and the storage container to pass through the resource in the shared namespace rather than through a kernel of the host by:

loading a library that implements a library function comprising a portable operating system interface (POSIX) application programming interface (API) for a file system library, wherein the library is preloaded at a daemon level and hooks a plurality of child processes comprising the application container and the storage container to the library;

intercepting, by the library function, the at least one item of data as part of a write request intended for the storage container, the at least one item of data comprising one or more input/output (I/O) packets; and

redirecting, by the library, the I/O packets to a ring buffer accessible by the storage container, wherein the rerouting reduces a storage and hardware processing resource load on the host and enables the host to more efficiently run a greater number of application containers.

16. The non-transitory computer-readable medium of claim 15 , wherein the one or more computer-readable instructions cause the computing device to:

identify a write request initiated by the application container to write data to the storage container;

reroute the at least one item of data by rerouting the write request sent from the application container to the storage container.

17. The non-transitory computer-readable medium of claim 15 , wherein the one or more computer-readable instructions cause the computing device to:

identify a read request initiated by the application container to read data from the storage container;

reroute the at least one item of data by rerouting the data sent from the storage container to the application container in response to the read request.

18. The non-transitory computer-readable medium of claim 15 , wherein the resource comprises a data structure in shared memory that is accessible by both the application container and the storage container.

19. The non-transitory computer-readable medium of claim 15 , wherein the ring buffer comprises an array of elements including at least a top element and a bottom element.

20. The non-transitory computer-readable medium of claim 19 , wherein the bottom element in the array of elements points to the top element in the array of elements.

Assignments (14)

Cited By (1)

US 12,450,355