System specification language for resource management architecture and corresponding programs therefore

• US 7,171,654 B2
• Filed: 05/24/2001
• Issued: 01/30/2007
• Est. Priority Date: 05/25/2000
• Status: Active Grant

• Current Assignee: the united states of america as represented by the secretary of the navy
• Original Assignee: the united states of america as represented by the secretary of the navy
• Inventors: Fontenot, Larry A., Welch, Lonnie R., Werme, Paul V.
• Primary Examiner(s): Dam; Tuan
• Assistant Examiner(s): Kiss; Eric B.
• Application Number:
  US09/864,829
• Publication Number:
  US 20050055350A1
• Time in Patent Office: 2,077 Days
• Field of Search: 717/114, 717/117, 717/140, 717162-164, 717/130, 718/102, 718/104, 718/105, 709/223, 709/224, 709/226
• US Class Current: 717/130
• CPC Class Codes: G06F 11/3006 where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems multiprogramming arrangements G06F9/46; allocation of resources G06F9/50
• CPC Class Codes: G06F 11/3414 Workload generation, e.g. scripts, playback
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 11/3466 Performance evaluation by tracing or monitoring
• CPC Class Codes: G06F 11/349 for interfaces, buses
• CPC Class Codes: G06F 11/3495 for systems
• CPC Class Codes: G06F 2201/86 Event-based monitoring
• CPC Class Codes: G06F 2201/865 Monitoring of software
• CPC Class Codes: G06F 2209/482 Application
• CPC Class Codes: G06F 2209/508 Monitor
• CPC Class Codes: G06F 9/4856 resumption being on a different machine, e.g. task migration, virtual machine migration G06F9/5088 takes precedence
• CPC Class Codes: G06F 9/5038 considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration scheduling strategies G06F9/4881 and subgroups
• CPC Class Codes: G06F 9/5044 considering hardware capabilities
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: G06F 9/54 Interprogram communication
• CPC Class Codes: H04L 41/06 Management of faults, events, alarms or notifications
• CPC Class Codes: H04L 43/0811 by checking connectivity
• CPC Class Codes: H04L 43/0817 by checking functioning
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 : based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/101 : based on network conditions
• CPC Class Codes: H04L 9/40 : Network security protocols
• CPC Class Codes: H04N 21/2405 : Monitoring of the internal components or processes of the server, e.g. server load allocation of resources in multiprogramming arrangements G06F9/50; performance measurement of computer activity G06F11/34
• CPC Class Codes: H04N 21/25 : Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies maintenance or administration in data networks H04L41/00

Abstract

A method for distributing application, system and network specification information to functional elements controlling a plurality of hosts in a distributed environment, including steps for preparing specification files in a language providing a syntax adapted to describe application, system and network specification information, compiling the specification files to thereby generate specification objects, and providing an application programming interface (API) permitting the functional elements to access the specification information using API calls.

Claims

1. A method for distributing application, system and network specification information to a resource allocation function that controls an N-plurality of hosts in a distributed environment, each host instantiating up to M managed characteristic applications, the resource allocation function communicating with an application control function, the method comprising:

providing instrumentation information to the resource allocation function, the instrumentation information being associated with the N-plurality of hosts;

preparing system specification files to describe system and network specification information;

linking the system specification files to the characteristic applications;

producing quality-of-service (QoS) information by the resource allocation function based on the instrumentation information, the QoS information being associated with the characteristic applications on the N-plurality of hosts;

allocating assigned hosts for processing the characteristic applications as control orders by the resource allocation function based on the QoS information, the assigned hosts being among the N-plurality of hosts;

compiling commands for the respective characteristic applications by the application control function to the assigned hosts based on the control orders and the QoS information; and

providing an application programming interface (API) that enables the QoS managers to access the specification information using API calls, wherein producing the QoS information further comprises;

analyzing the instrumentation information from the N-plurality of hosts by a corresponding N-plurality of QoS managers; and

producing the QoS information by the QoS managers wherein providing the API further comprises;

providing a parser file that defines grammar, the parser file being compiled using yacc utility;

providing a lexical analyzer file that defines language tokens, the lexical analyzer file being compiled using a lex utility; and

providing a set of C++ System Specification classes for storing specification file information.

2. The method as recited in claim 1, wherein preparing the system specification files is performed in a language that provides syntax adapted to describe the system and network specification information.

3. The method as recited in claim 1, wherein providing the instrumentation information further comprises:

reporting application events of the applications from the N-plurality of hosts;

collecting the application events as compiled events by an instrumentation collector;

correlating the compiled events as application metrics for the instrumentation information; and

providing the instrumentation information to the QoS managers.

4. The method as recited in claim 1, producing the QoS information further comprises:

copying a characteristic application of the M plurality of managed characteristic applications by the QoS managers as a copy for an additional host among the N-plurality of hosts.

5. The method as recited in claim 4, wherein copying the characteristic application comprises:

transmitting a scale request associated with the copy to the resource allocation function.

6. The method as recited in claim 1, wherein allocating the assigned hosts further comprises:

analyzing the instrumentation information and the system specification files by a resource manager to assign priorities to the characteristic applications; and

distributing the characteristic applications to the assigned hosts based on the priorities.

7. The method as recited in claim 6, further comprising:

determining respective loads of the N-plurality of hosts by a hardware broker, the loads corresponding to computation requirements by the hosts and the network; and

providing the loads to the resource manager.

8. The method as recited in claim 7, wherein determining the respective loads further comprises:

receiving respective operational statuses of the N-plurality of hosts to the hardware broker from history servers associated with the hosts;

assigning fitness scores associated with the respective operational statuses by the hardware broker; and

determining the loads based on the fitness scores by the hardware broker.

9. The method as recited in claim 1, wherein compiling the commands further comprises:

creating an instruction by a program control based on the control orders and the QoS information, the instruction being associated with a characteristic application of the M plurality of managed characteristic applications;

compiling the instruction by the program control; and

submitting the compiled instruction to the assigned hosts.

10. The method as recited in claim 9, wherein creating the instruction further includes creating a process startup order in response to a notification of Qos violation from the resource allocation function.

11. The method as recited in claim 9, wherein creating the instruction further includes creating a process shutdown order in response to a notification of QoS violation from the resource allocation function.

12. A method for distributing application, system and network specification information to a resource allocation function that controls an N-plurality of hosts in a distributed environment, each host instantiating up to M managed characteristic applications, the resource allocation function communicating with an application control function, the method comprising:

providing instrumentation information to an N-plurality of quality-of-service (QoS) managers of the resource allocation function, the instrumentation information being associated with the N-plurality of hosts, the QoS managers being associated with the N-plurality of hosts;

preparing system specification files to describe system and network specification information;

linking the system specification files to the characteristic applications;

producing QoS information by the QoS managers based on the instrumentation information, the QoS information being associated with the characteristic applications on the N-plurality of hosts;

analyzing the instrumentation information and the system specification files by a resource manager of the resource allocation function;

allocating assigned hosts for processing the characteristic applications as control orders by the resource manager based on the QoS information, the assigned hosts being among the N-plurality of hosts;

compiling commands for the respective characteristic applications by a program controller of the application control function to the assigned hosts based on the control orders and the QoS information; and

providing an application programming interface (API) that enables the QoS managers to access the specification information using API calls, wherein the API further comprises;

a parser file that defines grammar, the parser file being compiled using a yacc utility;

a lexical analyzer file that defines language tokens, the lexical analyzer file being compiler using a lex utility; and

a set of C++ System Specification classes for storing specification file information.

13. The method as recited in claim 12, wherein allocating the assigned hosts further comprises:

analyzing the instrumentation information and the system specification files by the resource manager to assign priorities to the characteristic applications; and

distributing the characteristic applications to the assigned hosts based on the priorities.

14. The method as recited in claim 12, wherein compiling the commands further comprises:

creating an instruction by a program control based on the control orders and the QoS information, the instruction being associated with a characteristic application of the M plurality of managed characteristic applications;

compiling the instruction by the program control; and

submitting the compiled instruction to the assigned hosts.

15. The method as recited in claim 12, further comprising:

determining respective loads of the N-plurality of hosts by a hardware broker, the loads corresponding to computation requirements by the hosts and the network; and

providing the loads to the resource manager.

16. The method as recited in claim 15, wherein determining the respective loads further comprises:

receiving respective operational statuses of the N-plurality of hosts to the hardware broker from history servers associated with the hosts;

assigning fitness scores associated with the respective operational statuses by the hardware broker; and

determining the loads based on the fitness scores by the hardware broker.

17. The method as recited in claim 12, wherein producing the QoS information further comprises:

copying a characteristic application of the M plurality of managed characteristic applications by the QoS managers as a copy for an additional host among the N-plurality of hosts.

18. The method as recited in claim 17, wherein copying the characteristic application further comprises:

transmitting a scale request associated with the copy to the resource manager.

19. A process control system controlling an N-plurality of hosts in a distributed environment, each host instantiating up to M managed characteristic applications, the system comprising:

a plurality of quality-of-service (QoS) managers corresponding to the N-plurality of hosts, the QoS managers receiving instrumentation information from the respective hosts and producing QoS information based on the instrumentation information, the instrumentation information being associated with the N-plurality of hosts, the QoS information being associated with the characteristic applications on the N-plurality of hosts;

a library that links system specification files that describe system and network specification information, the library linking the specification files to the characteristic applications;

a resource manager that allocates assigned hosts for processing the characteristic applications as control orders based on the QoS information, the assigned hosts being among the N-plurality of hosts;

a program controller that compiles commands for the respective characteristic applications to the assigned hosts based on the control orders and the QoS information; and

an application programming interface (API) that enables the QoS managers to access the specification information using API calls, wherein the API further comprises;

a parser file that defines grammar, the parser file being compiled using a yacc utility;

a lexical analyzer file that defines language tokens, the lexical analyzer file being compiled using a lex utility; and

a set of C++ System Specification classes for storing specification file information.

20. The system as recited in claim 19, further comprising:

an instrumentation collector that receives application events as compiled events, the application events being reported from the N-plurality of hosts; and

an instrumentation correlator that correlates the compiled events as application metrics for the instrumentation information.

21. The system as recited in claim 19, further comprising:

a hardware broker that analyzes history server information and provides respective loads of the N-plurality of hosts to the resource manager, the loads corresponding to computation requirements by the hosts and the network.

22. The system as recited in claim 21, further comprising

history servers associated with the N-plurality of hosts,the history servers providing operational statuses of the hosts to the hardware broker determining the respective loads.

23. The system Ms recited in claim 22, wherein the loads are determined from fitness scores, and the fitness scores are determined from the operational statuses.

24. The system as recited in claim 19, wherein the program controller communicates with the hosts using operating systems.

25. The system as recited in claim 19, wherein at least one of the up to M managed characteristic applications comprises a scalable application.

26. The system as recited in claim 19, wherein at least one of the up to M managed characteristic applications comprises a fault tolerant application, where the degree of fault tolerance is user selectable.

27. The system as recited in claim 19, wherein the instrumentation information provides condition metrics of the characteristic applications, the conditions including at least one of execution status, computation cycles, running duration and memory usage.

28. The system as recited in claim 19, further comprising:

an N-plurality of program control displays corresponding to the hosts and communicating with the program controller, the displays displaying information from the resource manager.

29. The system as recited in claim 19, wherein the QoS managers copy a characteristic application of the M plurality of managed characteristic applications as a copy for an additional host among the N-plurality of hosts.

30. The system as recited in claim 29, wherein the QoS managers transmit a scale request associated with the copy to the resource manager.