Service-oriented infrastructure management

• US 20080123559A1
• Filed: 12/06/2006
• Published: 05/29/2008
• Est. Priority Date: 08/07/2006
• Status: Active Grant

• Current Assignee: Mellanox Technologies Limited (NVIDIA Corporation)
• Original Assignee: Voltaire Limited (NVIDIA Corporation)
• Inventors: Berlovitch, Albert, Haviv, Yaron
• Granted Patent: US 7,822,594 B2
• Time in Patent Office: Days
• US Class Current: 370/255
• CPC Class Codes: G06F 8/61 Installation
• CPC Class Codes: G06F 9/44505 Configuring for program initiating, e.g. using registry, configuration files
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: H04L 41/00 Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]

Abstract

A method for computing includes specifying a data processing system using a logical system definition, which defines logical system components having respective functionalities and a topology for interconnecting the logical system components. The logical system components are represented using respective logical objects in a hierarchical object model. Physical resources of a grid computer system are represented using physical objects in the hierarchical object model. The logical objects are automatically mapped to at least some of the physical objects, so as to allocate the physical resources to carry out the respective functionalities of the logical system components. The allocated physical resources are configured and activated so as to cause the grid computer system to function as the data processing system, in accordance with the logical system definition.

Claims

1. A method for computing, comprising:

specifying a data processing system using a logical system definition, which defines logical system components having respective functionalities and a topology for interconnecting the logical system components;

representing the logical system components using respective logical objects in a hierarchical object model;

representing physical resources of a grid computer system using physical objects in the hierarchical object model;

automatically mapping the logical objects to at least some of the physical objects, so as to allocate the physical resources to carry out the respective functionalities of the logical system components; and

configuring and activating the allocated physical resources so as to cause the grid computer system to function as the data processing system, in accordance with the logical system definition.

2. The method according to claim 1, wherein the logical system components comprise at least one component selected from a group of components consisting of logical servers, logical storage devices and logical networks.

3. The method according to claim 1, wherein the logical objects comprise hierarchical objects comprising at least one class selected from a group of classes consisting of a root class, an environment class, a users class, a logical server class, a compute node class, an image class, an attribute class, a service class, an interface class and a logical disk class.

4. The method according to claim 1, wherein specifying the data processing system comprises specifying a service running on one or more of the logical system components, and wherein configuring and activating the allocated physical resources comprises configuring and activating the service on the allocated physical resources.

5. The method according to claim 1, wherein the physical resources comprise at least one component selected from a group of components consisting of physical servers, virtual servers, physical storage devices, virtual storage devices and communication networks.

6. The method according to claim 1, wherein the physical objects comprise hierarchical objects comprising at least one class selected from a group of classes consisting of a root class, a site class, a users class, a system group class, a system class, an attribute class, a module class, an extent class and a port class.

7. The method according to claim 6, wherein the system class comprises at least one subclass selected from a group of subclasses consisting of a field replaceable unit (FRU) subclass, a group subclass, a switch/router subclass, a computer subclass and a storage device subclass.

8. The method according to claim 1, wherein specifying the data processing system comprises:

specifying two or more logical servers;

specifying logical network connections that interconnect the logical servers, so as to implement the specified topology; and

specifying logical storage devices to be used by the logical servers.

9. The method according to claim 1, wherein representing the physical resources comprises automatically identifying the physical resources in the grid computer system and learning attributes of the identified physical resources.

10. The method according to claim 1, wherein representing the logical system components and physical resources comprises arranging the logical and physical objects in multiple levels of hierarchy in the object model, and wherein automatically mapping the logical objects to the physical objects comprises pointing from the logical objects to the corresponding physical objects at the multiple levels of the hierarchy.

11. The method according to claim 10, wherein one of the logical system components comprises a logical network interface connection (NIC), wherein one of the physical resources allocated to the one of the logical system components comprises a physical port, and wherein pointing from the logical objects to the corresponding physical objects comprises pointing from a logical object representing the virtual NIC to a physical object representing the physical port.

12. The method according to claim 1, and comprising adaptively re-allocating the physical resources during operation of the grid computer system.

13. The method according to claim 12, wherein adaptively re-allocating the physical resources comprises detecting a configuration change in the grid computer system, and re-allocating the physical resources so as to continue carrying out the functionalities of the logical system components following the configuration change.

14. The method according to claim 12, wherein specifying the data processing system comprises specifying a performance level of at least one of the logical system components, and wherein adaptively re-allocating the physical resources comprises detecting a deviation from the specified performance level and re-allocating the physical resources so as to correct the deviation.

15. The method according to claim 12, wherein adaptively re-allocating the physical resources comprises accepting a modification of the logical system definition and re-allocating the physical resources responsively to the modified logical system definition.

16. The method according to claim 1, wherein specifying the data processing system comprises defining two or more alternative logical system definitions, wherein mapping the logical objects to the physical objects comprises determining two or more alternative allocations of the physical resources corresponding to the respective logical system definitions, and wherein configuring and activating the physical resources comprises alternating between the two or more alternative allocations.

17. The method according to claim 16, wherein alternating between the two or more alternative allocations comprises alternating between the allocations in accordance with a predefined time schedule.

18. The method according to claim 1, and comprising evaluating an equivalent status of a logical system component by detecting a resource status of the physical resources that are allocated to carry out the functionality of the logical system component, and converting the resource status to the equivalent status of the logical system component.

19. The method according to claim 18, wherein evaluating the equivalent status comprises performing at least one action selected from a group of actions consisting of declaring a virtual failure in the logical system component, detecting a deviation from a performance level specified for the logical system component, reporting the equivalent status to a user and reporting the equivalent status to an external application.

20. The method according to claim 1, wherein specifying the data processing system comprises accepting the logical system definition from one of a user and an external application.

21. A computing apparatus, comprising:

an interface, which is operative to communicate with a grid computer system; and

a processor, which is arranged to accept a specification of a data processing system using a logical system definition, which defines logical system components having respective functionalities and a topology for interconnecting the logical system components, to represent the logical system components using respective logical objects in a hierarchical object model, to represent physical resources of the grid computer system using physical objects in the hierarchical object model, to automatically map the logical objects to at least some of the physical objects, so as to allocate the physical resources to carry out the respective functionalities of the logical system components, and to configure and activate the allocated physical resources so as to cause the grid computer system to function as the data processing system, in accordance with the logical system definition.

22. The apparatus according to claim 21, wherein the logical system components comprise at least one component selected from a group of components consisting of logical servers, logical storage devices and logical networks.

23. The apparatus according to claim 21, wherein the logical objects comprise hierarchical objects comprising at least one class selected from a group of classes consisting of a root class, an environment class, a users class, a logical server class, a compute node class, a system class, and image class, an attribute class, a service class, an interface class and a logical disk class.

24. The apparatus according to claim 21, wherein the logical system definition comprises a specification of a service running on one or more of the logical system components, and wherein the processor is arranged to configure and activate the service on the allocated physical resources.

25. The apparatus according to claim 21, wherein the physical resources comprise at least one component selected from a group of components consisting of physical servers, virtual servers, physical storage devices, virtual storage devices and communication networks.

26. The apparatus according to claim 21, wherein the physical objects comprise hierarchical objects comprising at least one class selected from a group of classes consisting of a root class, a site class, a users class, a system group class, a system class, an attribute class, a module class, an extent class and a port class.

27. The apparatus according to claim 24, wherein the system class comprises at least one subclass selected from a group of subclasses consisting of a field replaceable unit (FRU) subclass, a group subclass, a switch/router subclass, a computer subclass and a storage device subclass.

28. The apparatus according to claim 21, wherein the processor is arranged to automatically identify the physical resources in the grid computer system and to learn attributes of the identified physical resources.

29. The apparatus according to claim 21, wherein the processor is arranged to arrange the logical and physical objects in multiple levels of hierarchy in the object model, and to automatically map the logical objects to the physical objects by pointing from the logical objects to the corresponding physical objects at the multiple levels of the hierarchy.

30. The apparatus according to claim 29, wherein one of the logical system components comprises a logical network interface connection (NIC), wherein one of the physical resources allocated to the one of the logical system components comprises a physical port, and wherein the processor is arranged to point from a logical object representing the virtual NIC to a physical object representing the physical port.

31. The apparatus according to claim 21, wherein the processor is arranged to adaptively re-allocate the physical resources during operation of the grid computer system.

32. The apparatus according to claim 31, wherein the processor is arranged to detect a configuration change in the grid computer system, and to re-allocate the physical resources so as to continue carrying out the functionalities of the logical system components following the configuration change.

33. The apparatus according to claim 31, wherein the logical system definition comprises a specification of a performance level of at least one of the logical system components, and wherein the processor is arranged to detect a deviation from the specified performance level and to re-allocate the physical resources so as to correct the deviation.

34. The apparatus according to claim 31, wherein the processor is arranged to accept a modification of the logical system definition and to re-allocate the physical resources responsively to the modified logical system definition.

35. The apparatus according to claim 21, wherein the processor is arranged to accept two or more alternative logical system definitions, to determine two or more alternative allocations of the physical resources corresponding to the respective logical system definitions, and to alternate between the two or more alternative allocations.

36. The apparatus according to claim 35, wherein the processor is arranged to alternate between the allocations in accordance with a predefined time schedule.

37. The apparatus according to claim 21, wherein the processor is arranged to evaluate an equivalent status of a logical system component by detecting a resource status of the physical resources that are allocated to carry out the functionality of the logical system component, and converting the resource status to the equivalent status of the logical system component.

38. The apparatus according to claim 37, wherein the processor is arranged to perform at least one action selected from a group of actions consisting of declaring a virtual failure in the logical system component, detecting a deviation from a performance level specified for the logical system component, reporting the equivalent status to a user and reporting the equivalent status to an external application.

39. The apparatus according to claim 21, wherein the processor is arranged to store the hierarchical object model in a relational database.

40. The apparatus according to claim 21, and comprising a user terminal, which is arranged to interact with a user so as to enable the user to construct and enter the logical system definition.

41. The apparatus according to claim 40, wherein the user terminal is arranged to interact with the user using at least one interface type selected from a group of types consisting of a graphical user interface (GUI) and a command line interface (CLI).

42. The apparatus according to claim 21, and comprising an application interface, which is connected to the processor and is arranged to accept the logical system definition from an external application.

43. A computing system, comprising:

a grid computer system comprising physical resources; and

an infrastructure management (IM) server, which is arranged to accept a specification of a data processing system using a logical system definition, which defines logical system components having respective functionalities and a topology for interconnecting the logical system components, to represent the logical system components using respective logical objects in a hierarchical object model, to represent the physical resources of the grid computer system using physical objects in the hierarchical object model, to automatically map the logical objects to at least some of the physical objects, so as to allocate the physical resources to carry out the respective functionalities of the logical system components, and to configure and activate the allocated physical resources so as to cause the grid computer system to function as the data processing system, in accordance with the logical system definition.

44. The system according to claim 43, wherein the communication network comprises a remote direct memory access (RDMA)-capable network.

45. The system according to claim 43, wherein the IM server is arranged to accept the logical system definition from an external application.

46. The system according to claim 43, wherein the logical system components comprise at least one component selected from a group of components consisting of logical servers, logical storage devices and logical networks.

47. The system according to claim 43, wherein the physical resources comprise at least one component selected from a group of components consisting of physical servers, virtual servers, physical storage devices, virtual storage devices and communication networks.

48. The system according to claim 43, wherein the IM server is arranged to automatically identify the physical resources in the grid computer system and to learn attributes of the identified physical resources.

49. The system according to claim 43, wherein the IM server is arranged to adaptively re-allocate the physical resources during operation of the grid computer system.

50. The system according to claim 43, wherein the IM server is arranged to accept two or more alternative logical system definitions, to determine two or more alternative allocations of the physical resources corresponding to the respective logical system definitions, and to alternate between the two or more alternative allocations in accordance with a predetermined time schedule.

51. The system according to claim 43, wherein the IM server is arranged to evaluate a virtual status of a logical system component by detecting a resource status of the physical resources that are allocated to carry out the functionality of the logical system component, and converting the resource status to the virtual status of the logical system component.

52. A computer software product for controlling a grid computer system, the product comprising a computer-readable medium, in which program instructions are stored, which instructions, when read by a computer, cause the computer to accept a specification of a data processing system using a logical system definition, which defines logical system components having respective functionalities and a topology for interconnecting the logical system components, to represent the logical system components using respective logical objects in a hierarchical object model, to represent physical resources of the grid computer system using physical objects in the hierarchical object model, to automatically map the logical objects to at least some of the physical objects, so as to allocate the physical resources to carry out the respective functionalities of the logical system components, and to configure and activate the allocated physical resources so as to cause the grid computer system to function as the data processing system, in accordance with the logical system definition.

53. The product according to claim 52, wherein the logical system components comprise at least one component selected from a group of components consisting of logical servers, logical storage devices and logical networks.

54. The product according to claim 52, wherein the logical objects comprise hierarchical objects comprising at least one class selected from a group of classes consisting of a root class, an environment class, a users class, a logical server class, a compute node class, a system class, an image class, an attribute class, a service class, an interface class and a logical disk class.

55. The product according to claim 52, wherein the logical system definition comprises a specification of a service running on one or more of the logical system components, and wherein the instructions cause the computer to configure and activate the service on the allocated physical resources.

56. The product according to claim 52, wherein the physical resources comprise at least one component selected from a group of components consisting of physical servers, virtual servers, physical storage devices, virtual storage devices and communication networks.

57. The product according to claim 52, wherein the physical objects comprise hierarchical objects comprising at least one class selected from a group of classes consisting of a root class, a site class, a users class, a system group class, a system class, an attribute class, a module class, an extent class and a port class.

58. The product according to claim 57, wherein the system class comprises at least one subclass selected from a group of subclasses consisting of a field replaceable unit (FRU) subclass, a group subclass, a switch/router subclass, a computer subclass and a storage device subclass.

59. The product according to claim 52, wherein the instructions cause the computer to automatically identify the physical resources in the grid computer system and to learn attributes of the identified physical resources.

60. The product according to claim 52, wherein the instructions cause the computer to arrange the logical and physical objects in multiple levels of hierarchy in the object model, and to automatically map the logical objects to the physical objects by pointing from the logical objects to the corresponding physical objects at the multiple levels of the hierarchy.

61. The product according to claim 60, wherein one of the logical system components comprises a logical network interface connection (NIC), wherein one of the physical resources allocated to the one of the logical system components comprises a physical port, and wherein the instructions cause the computer to point from a logical object representing the virtual NIC to a physical object representing the physical port.

62. The product according to claim 52, wherein the instructions cause the computer to adaptively re-allocate the physical resources during operation of the grid computer system.

63. The product according to claim 62, wherein the instructions cause the computer to detect a configuration change in the grid computer system, and to re-allocate the physical resources so as to continue carrying out the functionalities of the logical system components following the configuration change.

64. The product according to claim 62, wherein the logical system definition comprises a specification of a performance level of at least one of the logical system components, and wherein the instructions cause the computer to detect a deviation from the specified performance level and to re-allocate the physical resources so as to correct the deviation.

65. The product according to claim 62, wherein the instructions cause the computer to accept a modification of the logical system definition and to re-allocate the physical resources responsively to the modified logical system definition.

66. The product according to claim 52, wherein the instructions cause the computer to accept two or more alternative logical system definitions, to determine two or more alternative allocations of the physical resources corresponding to the respective logical system definitions, and to alternate between the two or more alternative allocations.

67. The product according to claim 66, wherein the instructions cause the computer to alternate between the allocations in accordance with a predefined time schedule.

68. The product according to claim 52, wherein the instructions cause the computer to evaluate an equivalent status of a logical system component by detecting a resource status of the physical resources that are allocated to carry out the functionality of the logical system component, and converting the resource status to the equivalent status of the logical system component.

69. The product according to claim 68, wherein the instructions cause the computer to perform at least one action selected from a group of actions consisting of declaring a virtual failure in the logical system component, detecting a deviation from a performance level specified for the logical system component, reporting the equivalent status to a user and reporting the equivalent status to an external application.

70. The product according to claim 52, wherein the instructions cause the computer to store the hierarchical object model in a relational database.

71. The product according to claim 52, wherein the instructions cause the computer to interact with a user so as to enable the user to construct and enter the logical system definition.

72. The product according to claim 71, wherein the instructions cause the computer to interact with the user using at least one interface type selected from a group of types consisting of a graphical user interface (GUI) and a command line interface (CLI).

73. The product according to claim 52, wherein the instructions cause the computer to accept the logical system definition from an external application.