Distributed computing with multiple coordinated component collections

• US 8,650,270 B2
• Filed: 07/10/2008
• Issued: 02/11/2014
• Est. Priority Date: 07/10/2008
• Status: Expired due to Fees

• Current Assignee: Juniper Networks Incorporated
• Original Assignee: Juniper Networks Incorporated
• Inventors: Gerovac, Branko J., Carver, David C.
• Primary Examiner(s): Tiv, Backhean
• Application Number:
  US12/170,624
• Publication Number:
  US 20100011096A1
• Time in Patent Office: 2,042 Days
• Field of Search: 709/223, 709/224, 709/225
• US Class Current: 709/223
• CPC Class Codes: G06F 9/52 Program synchronisation; Mutual exclusion, e.g. by means of semaphores

Abstract

A system having components that collectively perform functions and services of the system. The components are managed as belonging to at least a first component collection and a second component collection. The components of the first component collection operate at a time scale that is substantially temporally independent of the components of the second component collection. The components of the first component collection have a first set of temporal requirements and the components of the second component collection have a second substantially different set of temporal requirements.

Claims

1. A system comprising:

one or more processors; and

one or more memories including a plurality of instructions that, when executed by the one or more processors, cause the one or more processors to;

group information regarding a plurality of components into a plurality of planes, based on one or more operations that are performed by the plurality of components, each of the plurality of components being implemented at least partially in hardware,

one or more first particular components, of the plurality of components, performing a same operation being grouped with one or more second particular components, of the plurality of components, that perform the same operation and not being grouped with one or more third particular components, of the plurality of components, that do not perform the same operation,

the plurality of components collectively performing functions of the system, the plurality of planes including;

a system plane,

a content plane,

a session plane,

an access plane, and

a transfer plane,

each of the plurality of planes being different from one another,

components, of each of the plurality of planes, operating at a time scale that is temporally independent of a time scale of the components of other ones of the plurality of planes,

the system plane, the content plane, and the session plane each being associated with one or more non-real-time operations,

the access plane and the transfer plane each being associated with one or more real-time operations,

the session plane bridging the non-real-time operations and the real-time operations, and

the components, of each of the plurality of planes, having temporal requirements that are different from temporal requirements of the components of other ones of the plurality of planes.

2. The system of claim 1, where the components of each plane, of the plurality of planes internally coordinate respective operations in accordance with a model.

3. The system of claim 1, where the components of the system plane collectively implement functions that provide overall visibility and management of the system, and

where the functions that provide overall visibility and management of the system include a function that maintains at least one of:

information identifying interconnections of each of the plurality of components, or

information identifying health and performance of each of the plurality of components.

4. The system of claim 1, where the components of the content plane collectively implement functions that organize and manage content storage on the system,

where the functions that organize and manage the content storage on the system include a function that at least one of allocates content to one or more storage devices associated with the system or assigns content to the one or more storage devices.

5. The system of claim 1, where the components of the session plane collectively implement session management functions.

6. The system of claim 5, where the session management functions include at least one of:

a session initiation function, a session termination function, or a session-specific resource allocation function.

7. The system of claim 1, where the components of the access plane collectively implement functions to enable data transfers associated with one or more storage resource elements of the system.

8. The system of claim 1, where the components of the transfer plane collectively implement functions to perform data transfers associated with one or more storage devices of the system.

9. The system of claim 1, where the plurality of components are hosted on a plurality of devices that are interconnected by a data network, and

where components of at least two of the plurality of planes are hosted on a single device.

10. The system of claim 1,

where the system plane comprises a first plurality of hardware components that are unique to the system plane,

where the content plane comprises a second plurality of hardware components that are unique to the content plane,

where the session plane comprises a third plurality of hardware components that are unique to the session plane,

where the access plane comprises a fourth plurality of hardware components that are unique to the access plane, and

where the transfer plane comprises a fifth plurality of hardware components that are unique to the transfer plane.

11. A system comprising:

one or more processors; and

one or more memories including a plurality of instructions that, when executed by the one or more processors, cause the one or more processors to;

group a plurality of components into a plurality of planes of based on one or more operations that are performed by the plurality of components, each of the plurality of planes being implemented at least partially in hardware and each plane, of the plurality of planes, including at least one of the plurality of components,

one or more first particular components, of the plurality of components, performing a same operation being grouped with one or more second particular components, of the plurality of components, that perform the same operation and not being grouped with one or more third particular components, of the plurality of components, that do not perform the same operation, and

components, of at least two of the plurality of planes, being hosted on a single node of a plurality of interconnected nodes; and

provide one or more interconnections between interfaces of the plurality of planes,

each plane, of the plurality of planes, independently implementing a consistency approach among distributed components of the plane,

each plane, of the plurality of planes, providing one or more interfaces to other planes, of the plurality of planes, at one or more computing platforms without guaranteeing, to the other planes, of the plurality of planes, an order of execution of requests, received at the interfaces, in an order in which the requests were received,

a first plurality of planes each being associated with one or more non-real-time operations,

a second plurality of planes each being associated with one or more real-time operations,

a plane, of the first plurality of planes, bridging the non-real-time operations and the real-time operations, and

the components of each plane, of the plurality of planes, operating at a time scale that is independent of a time scale of the components of other planes, of the plurality of planes.

12. The system of claim 11, where at least one of the plurality of planes implements a consistency approach for maintaining a shared state accessible to components of the at least one of the plurality of planes.

13. The system of claim 11, where external interfaces of the system are provided by multiple ones of the plurality of planes.

14. The system of claim 11, where the plurality of planes include:

a transfer plane that includes components for transfer of content between nodes of the plurality of interconnected nodes, and

a system plane that includes components for managing configuration information for the system,

where the configuration information includes information identifying health and performance of each of the plurality of components.

15. A method comprising:

grouping, by a device, a plurality of components into a plurality of planes based on one or more operations that are performed by the plurality of components,

one or more first particular components, of the plurality of components, performing a same operation being grouped with one or more second particular components, of the plurality of components, that perform the same operation and not being grouped with one or more third particular components, of the plurality of components, that do not perform the same operation, and

the plurality of planes including;

a content plane,

a session plane,

an access plane, and

a transfer plane,

managing, by the device and using one or more components of the content plane, storing of data on one or more storage resources associated with the device;

managing, by the device and using one or more components of the session plane, one or more sessions for accessing data stored on at least one of the one or more storage resources;

requesting, by the device and using one or more components of the access plane, transfer of data from the one or more storage resources; and

transferring, by the device and using one or more components of the transfer plane, data between the one or more storage resources,

the content plane and the session plane each being associated with one or more non-real-time operations,

the access plane and the transfer plane each being associated with one or more real-time operations,

the session plane bridging the non-real-time operations and the real-time operations, and

the one or more components of each plane, of the plurality of planes, operating at a time scale that is different than a time scale of the components of other planes, of the plurality of planes.

16. The method of claim 15, where a component, of the plurality of components, that is associated with transfer of data, operates at a time scale that is faster than a time scale of another component, of the plurality of components, that is associated with storing data.

17. The method of claim 15, where managing the one or more sessions includes:

creating a session based on a threshold workload associated with the device; and

allocating resources for the created session for a portion of a duration of the session.

18. The method of claim 15, further comprising:

arranging the plurality of planes in a linear sequence.

19. The method of claim 15, further comprising:

transmitting, from one of the plurality of planes, a request message to another one of the plurality of planes; and

receiving, by the one of the plurality of planes, an acknowledgement message, based on the transmitted request message, from the other one of the plurality of planes.

20. The method of claim 15, where the time scale is based on information regarding a data transfer from a first node to a second node.