Automatic enforcement of service-level agreements for providing services over a network

• US 20040064557A1
• Filed: 09/30/2002
• Published: 04/01/2004
• Est. Priority Date: 09/30/2002
• Status: Active Grant

• Current Assignee: Snap, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Kumar, Arun, Chafle, Girish B., Karnik, Neeran M., Youssef, Alaa S., Arora, Ruby
• Granted Patent: US 7,305,431 B2
• Time in Patent Office: Days
• US Class Current: 709/225
• CPC Class Codes: G06F 9/5055 considering software capabilities, i.e. software resources associated or available to the machine
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: H04L 41/5029 Service quality level-based billing, e.g. dependent on measured service level customer is charged more or less
• CPC Class Codes: H04L 41/5032 Generating service level reports
• CPC Class Codes: H04L 41/508 based on type of value added network service under agreement
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level

Abstract

The invention deals with the enforcement of Service Level Agreement for the services provided over a client-server network. The invention discloses a method, system and a program product for automatic enforcement of SLAs. This is achieved by automatic metering of requests for service and allocation of resources of the server based on the SLA, current available resources and the needs of the customer.

Claims

1. A method enabling automatic enforcement of Service Level Agreements (SLAs) in a client-server arrangement over a network, between customers running an application utilizing services provided by a service provider, comprising the steps of:

automatically measuring the weighted service requirement of each service request,

queuing the service request,

controlling usage of services by dispatching the service requests from the queue to the server at a configurable dispatch rate,

aggregating the dispatched requests on per-application, per-customer basis, and

modifying the dispatch rate for each application of each customer, based on predefined events.

2. The method as claimed in claim 1, wherein the weighted service requirements are determined by analyzing the parameters of the service request.

3. The method as claimed in claim 1, wherein the service usage rate per application instance is defined by the SLA limits set for the customer for said application.

4. The method as claimed in claim 1, wherein events for triggering modification of dispatch rate include elapsing of predefined period of time, occurrence of system events and manual instigation of the trigger.

5. The method as claimed in claim 1, including the step of reporting the service usage statistics of each application for each customer to the server, at configurable intervals.

6. The method as claimed in claim 1, including optionally controlling the usage of service through manual intervention.

7. The method as claimed in claim 1, optionally including the step of modifying the SLA limits on the fly without having to restart the service.

8. The method as claimed in claim 2, wherein the usage parameters include distribution of requests, number of requests and frequency of requests.

9. The method as claimed in claim 5, wherein the configurable intervals include elapsing of fixed time intervals and processing of a fixed number of service requests.

10. The method as claimed in claim 1, wherein the policies for modifying dispatch rate include providing fair share of service capacity, maximizing revenue generation, ensuring high resource utilization and minimizing perturbation of the current allocation.

11. The method as claimed in claim 6, optionally including the step of overriding the system'"'"'s decisions and controlling the allocation by sending control messages and setting key parameters for allocation of resources.

12. The method as claimed in claim 10, including determining or dynamically updating the service capacity by benchmarking or on the basis of current configuration and the status of utilization of services.

13. The method as claimed in claim 10, including determining fair share of capacity on the basis of the guaranteed throughput and the available capacity of the system.

14. The method as claimed in claim 13, including allowing the customer to exceed the guaranteed throughput when the system is lightly loaded.

15. A system enabling automatic enforcement of Service Level Agreements (SLAs) in a client-server arrangement over a network, between customers running an application utilizing services provided by a service provider, comprising:

means for automatically measuring the weighted service requirement of each service request,

means for queuing the service request,

means for controlling usage of services by dispatching the service requests from the queue to the server at configurable dispatch rate,

means for aggregating the dispatched requests on per-application, per-customer basis, and

means for modifying the dispatch rate for each application of each customer, based on pre-defined events.

16. The system as claimed in claim 15, wherein means for measuring the weighted service requirements is a Metering module that analyses the parameters of the service request.

17. The system as claimed in claim 15, wherein the means for queuing each request and controlling the usage of service is a Throttling module comprising of a First-In First-Out (FIFO) buffer with configurable dispatch rate of service requests from the queue to the server by implementing a “

leaky”

bucket mechanism.

18. The system as claimed in claim 15, wherein means for aggregating the service request is an Aggregator module connected to an Allocator module, used for allocation of resources.

19. The system as claimed in claim 15, including means for reporting the service usage statistics of each application for each customer to the Allocator, at configurable intervals.

20. The system as claimed in claim 15, wherein means for modifying dispatch rate use predefined policies that include providing fair share of service capacity, maximizing revenue generation, ensuring high resource utilization and minimizing perturbation of the current allocation.

21. The system as claimed in claim 15, including means for optionally controlling the usage of service through manual intervention.

22. The system as claimed in claim 15, optionally including means for modifying the SLA limits on the fly without having to restart the service.

23. The system as claimed in claim 21, optionally including means for overriding the system'"'"'s decisions and controlling the allocation by sending control messages and setting key parameters for allocation of resources.

24. The system as claimed in claim 20, including means for determining or dynamically updating the service capacity by benchmarking or on the basis of current configuration and the status of utilization of services.

25. The system as claimed in claim 20, including determining fair share of capacity on the basis of the guaranteed throughput and the available capacity of the system.

27. The system as claimed in claim 23, wherein means for overriding the system'"'"'s decisions and controlling the allocation is a manual controller connected to the Allocator module.

28. The system as claimed in claim 15, wherein the customers run an application on a client computing systems comprising:

a system bus,

a communications unit connected to the system bus,

a memory including a set of instructions connected to the system bus, and

a control unit executing the instructions in the memory for generating service requests, connected to the system bus.

29. The system as claimed in claim 15, wherein the server providing the services comprises:

a system bus,

a communications unit connected to the system bus,

a memory connected to the system bus, wherein the memory includes a set of instructions, and

a processing unit connected to the system bus, wherein the control unit executes the set of instructions in the memory for acting on the service requests and ensuring that the SLA limits are adhered to.

30. The system as claimed in claim 15, wherein the application requests communicate to the server through a client end or server end Wrapper module that encompasses the Metering module and the Throttling module.

31. The system as claimed in claim 15, wherein the Allocator module resides at the server end and is further connected to a SLA database either local or remote, containing the details of the SLA limits of various applications run by various customers.

32. The system as claimed in claim 16, wherein the said client server network comprises of:

one or more clients forming one or more customers,

a server forming a service provider, and

a communication medium using a communicating protocol to interconnect the clients and the server.

33. A computer program product comprising computer readable program code stores on a computer readable storage medium embodied therein for enabling automatic enforcement of Service Level Agreements (SLAs) in a client-server arrangement over a network, between customers running an application utilizing services provided by a service, comprising:

computer readable program code means configured for automatically measuring the weighted service requirement of each service request,

computer readable program code means configured for queuing the service request,

computer readable program code means configured for controlling usage of services by dispatching the service requests from the queue to the server at a configurable dispatch rate,

computer readable program code means configured for aggregating the dispatched requests on per-application, per-customer basis, and

computer readable program code means configured for modifying the dispatch rate for each application of each customer, based on pre-defined events.

26. The system as claimed in claim 35, including means for allowing the customer to exceed the guaranteed throughput when the system is lightly loaded.

34. The computer program product as claimed in claim 33, including computer readable program code means configured for determining the weighted service requirements by analyzing the parameters of the service request.

35. The computer program product as claimed in claim 33, including computer readable program code means configured for defining the service usage rate per application instance as SLA limits set for the customer for said application.

36. The computer program product as claimed in claim 33, including computer readable program code means configured for triggering modification of dispatch rate on elapsing of pre-defined period of time, occurrence of system events and manual instigation of the trigger.

37. The computer program product as claimed in claim 33, including computer readable program code means configured for reporting the service usage statistics of each application for each customer to the server, at configurable intervals.

38. The computer program product as claimed in claim 33, including computer readable program code means configured for optionally controlling the usage of service through manual intervention.

39. The computer program product as claimed in claim 33, including computer readable program code means configured for optionally modifying the SLA limits on the fly without having to restart the service.

40. The computer program product as claimed in claim 37, including computer readable program code means configured for defining the intervals as elapsing of fixed time intervals and processing of a fixed number of service requests.

41. The computer program product as claimed in claim 33, including computer readable program code means configured for, defining the policies for modifying dispatch rate as providing fair share of service capacity, maximizing revenue generation, ensuring high resource utilization and minimizing perturbation of the current allocation.

42. The computer program product as claimed in claim 38, including computer readable program code means configured for optionally over riding the system'"'"'s decisions and controlling the allocation by sending control messages and setting key parameters for allocation of resources.

43. The computer program product as claimed in claim 33, including computer readable program code means configured for, including determining or dynamically updating the service capacity by benchmarking or on the basis of current configuration and the status of utilization of services.

44. The computer program product as claimed in claim 41, including computer readable program code means configured for determining fair share of capacity on the basis of the guaranteed throughput and the available capacity of the system.

45. The computer program product as claimed in claim 44, including computer readable program code means configured for allowing the customer to exceed the guaranteed throughput when the system is lightly loaded.