Programmatic instantiation, provisioning and management of fabric-backplane enterprise servers

• US 7,685,281 B1
• Filed: 02/12/2005
• Issued: 03/23/2010
• Est. Priority Date: 02/13/2004
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Habanero Holdings Incorporated
• Inventors: Mittur, Shyam, Ingrao, Fabio Onofrio, Saraiya, Nakul Pratap, Finkelstein, Yuri, Shah, Shreyas B., Collins, Curtis M., Lovett, Thomas Dean, Nicolaou, Cosmos
• Primary Examiner(s): Gilles, Jude J Jean
• Application Number:
  US11/057,048
• Time in Patent Office: 1,865 Days
• Field of Search: 709223-226, 709238-244
• US Class Current: 709/226
• CPC Class Codes: G06F 13/387 for adaptation of different data processing systems to different peripheral devices, e.g. protocol converters for incompatible systems, open system

Abstract

A system is taught in which a module having processing elements can access network and storage interfaces that are external to the module of the processing elements as though those interfaces were located internal to the module of the processing elements. The system may be operated as one or more provisioned servers, each of the provisioned servers including capabilities as identified by a corresponding set of specifications and attributes, according to various embodiments. Typically the specifications (or constraints) and attributes are specified with a Server Configuration File. An Enterprise Server system may be provisioned into any combination and number of servers according to needed processing and I/O capabilities. Each of these servers may include distinct compute, storage, and networking performance. Provisioned servers may be managed similar to conventional servers, including operations such as boot and shutting down.

Claims

1. A method comprising:

accessing a networked computing system template;

automatically instantiating a networked computing system according to the template; and

wherein

the template comprises a hardware manifest of required hardware primitives, and

the hardware manifest comprises a description of a required number of ways of a plurality of physically partitionable symmetric multiprocessors, and the automatically instantiating comprises configuring one or more of the physically partitionable symmetric multiprocessors as an N-way multiprocessor, where N is the required number of ways.

2. The method of claim 1, wherein:

the template is an instance of a server specification.

3. The method of claim 1, wherein:

the networked computing system is an instance of a provisioned server.

4. The method of claim 1, wherein:

the act of instantiating the networked computing system is an instance of forming a provisioned server.

5. The method of claim 1, wherein:

the hardware manifest is an instance of a hardware specification.

6. The method of claim 1, wherein:

the act of automatically instantiating comprises programmatically parsing the template.

7. The method of claim 6, wherein:

the act of automatically instantiating further comprises programmatically analyzing constraints determined from the parsed template.

8. The method of claim 1, wherein:

the act of automatically instantiating comprises programmatically managing a free primitives pool.

9. The method of claim 8, wherein:

the act of automatically instantiating further comprises programmatically allocating resources from the free primitives pool according to the template.

10. The method of claim 1, wherein:

the required hardware primitives are specified explicitly as minimum requirements.

11. The method of claim 1, wherein:

the required hardware primitives are specified implicitly as minimum requirements.

12. The method of claim 1, wherein:

the required hardware primitives are specified explicitly as exact requirements.

13. The method of claim 1, wherein:

the required hardware primitives are specified implicitly as exact requirements.

14. The method of claim 1, wherein:

the required hardware primitives are specified to comprise at least one of performance requirements, capacity requirements, bandwidth requirements, and hardware accelerator requirements.

15. The method of claim 1, wherein:

the partitions are physical partitions and the partitionable symmetric multiprocessors are physically-partitionable symmetric multiprocessors.

16. The method of claim 1, wherein:

each of the partitions couples to a switch fabric via a switch fabric interface.

17. The method of claim 16, wherein:

each of the partitions is designed to independently couple to the switch fabric.

18. The method of claim 16, wherein:

a first partition of the partitions communicates via the switch fabric with other partitions of the plurality of partitionable symmetric multiprocessors.

19. A method comprising:

via an instantiation process executing on a computing server, instantiating a networked computing system according to a networked computing system template; and

wherein

the template comprises a hardware manifest of required hardware primitives, and

the hardware manifest comprises a description of a required minimum number of ways of a plurality of physically partitionable symmetric multiprocessors, and the instantiating comprises configuring one or more of the physically partitionable symmetric multiprocessors as an N-way multiprocessor, where N is equal to or greater than the required minimum number of ways.

20. A method comprising:

receiving a networked computing system template;

programmatically instantiating a networked computing system according to the template; and

wherein

the template comprises a hardware manifest of required hardware primitives,

the hardware manifest includes comprises a description of a required number of ways of a plurality of physically partitionable symmetric multiprocessors, and the instantiating comprises configuring one or more of the physically partitionable symmetric multiprocessors as an N-way multiprocessor, where N is the required number of ways,

each of the partitions comprises a switch fabric interface designed to couple to a switch fabric, and

a first partition of the partitions communicates with other partitions of the plurality of partitionable symmetric multiprocessors via the switch fabric.