System and method for evaluating a heterogeneous cluster for supporting expected workload in compliance with at least one service parameter

• US 20050278453A1
• Filed: 06/14/2004
• Published: 12/15/2005
• Est. Priority Date: 06/14/2004
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Cherkasova, Ludmila
• Granted Patent: US 7,953,843 B2
• Time in Patent Office: Days
• US Class Current: 709/231
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 65/1101 Session protocols
• CPC Class Codes: H04L 65/613 for the control of the source by the destination control signals issued by the client directed to the server or network components specially adapted for selective content distribution H04N21/637
• CPC Class Codes: H04L 65/752 adapting media to network capabilities
• CPC Class Codes: H04L 65/80 Responding to QoS
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network
• CPC Class Codes: H04L 67/14 Session management for real-time applications in data packet communications networks H04L65/1066
• CPC Class Codes: H04L 67/61 taking into account QoS or priority requirements

Abstract

According to at least one embodiment, a method comprises receiving, into a capacity planning system, workload information representing an expected workload of client accesses of streaming media files from a site. The method further comprises receiving, into the capacity planning system, at least one service parameter that defines a desired service characteristic to be provided by a heterogeneous cluster of servers under the expected workload. The capacity planning system evaluates whether the heterogeneous cluster, having a plurality of different server configurations included therein, is capable of supporting the expected workload in compliance with the at least one service parameter.

Claims

1. A method comprising:

receiving, into a capacity planning system, workload information representing an expected workload of client accesses of streaming media files from a site;

receiving, into said capacity planning system, at least one service parameter that defines a desired service characteristic to be provided by a heterogeneous cluster of servers under the expected workload; and

said capacity planning system evaluating whether said heterogeneous cluster, having a plurality of different server configurations included therein, is capable of supporting the expected workload in compliance with said at least one service parameter.

2. The method of claim 1 wherein said at least one service parameter comprises at least one performability parameter that defines a desired service characteristic to be provided by said heterogeneous cluster during periods of degraded service under the expected workload.

3. The method of claim 2 wherein said at least one performability parameter specifies a limit on the amount of degradation of service encountered during said periods of degraded service.

4. The method of claim 2 wherein said at least one performability parameter comprises at least one selected from the group consisting of:

a regular-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods of performance degradation under regular system operation of said heterogeneous cluster, and

a node-failure-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods in which one or more nodes of said heterogeneous cluster have failed.

5. The method of claim 1 wherein said at least one service parameter comprises at least one performability parameter that defines a desired service characteristic to be provided by at least one of said plurality of different server configurations included in said heterogeneous cluster during periods of degraded service under the expected workload.

6. The method of claim 5 wherein said at least one performability parameter specifies a limit on the amount of degradation of service encountered during said periods of degraded service.

7. The method of claim 5 wherein said at least one performability parameter comprises at least one selected from the group consisting of:

a regular-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods of performance degradation under regular system operation of said at least one of said plurality of different server configurations, and

a node-failure-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods in which one or more nodes of said at least one of said plurality of different server configurations have failed.

8. The method of claim 1 wherein said at least one service parameter comprises at least one basic capacity parameter.

9. The method of claim 8 wherein said at least one basic capacity parameter comprises at least one selected from the group consisting of:

a statistical demand guarantee that specifies a desired limit on the percentage of time that said heterogeneous cluster is overloaded under the expected workload, and

a utilization constraint that specifies a desired limit on the percentage of time that said heterogeneous cluster is at or near its capacity under the expected workload.

10. The method of claim 8 wherein said at least one basic capacity parameter comprises a statistical demand guarantee that specifies a desired limit on the percentage of time that said heterogeneous cluster is overloaded under the expected workload, and a utilization constraint that specifies a desired limit on the percentage of time that said heterogeneous cluster is at or near its capacity under the expected workload.

11. The method of claim 8 wherein said at least one service parameter further comprises at least one performability parameter that defines a desired limit on the amount of degradation of service encountered during said percentage of time that said heterogeneous cluster is overloaded under the expected workload.

12. The method of claim 8 wherein said at least one service parameter further comprises at least one performability parameter that defines a desired limit on the amount of continuous overload encountered at any given time by said heterogeneous cluster under the expected workload.

13. A method comprising:

receiving, into a capacity planning system, workload information representing an expected workload of client accesses of streaming media files from a site;

receiving, into said capacity planning system, at least one service parameter that defines a desired service characteristic to be provided by a heterogeneous cluster of servers under the expected workload; and

determining, by said capacity planning system, for each of a plurality of different types of server configurations included in said heterogeneous cluster, how many servers to be included in said heterogeneous cluster for supporting the expected workload in compliance with said at least one service parameter.

14. The method of claim 13 wherein said at least one service parameter comprises at least one performability parameter that defines a desired service characteristic to be provided by said heterogeneous cluster during periods of degraded service under the expected workload.

15. The method of claim 14 wherein said at least one performability parameter specifies a limit on the amount of degradation of service encountered during said periods of degraded service.

16. The method of claim 14 wherein said at least one performability parameter comprises at least one selected from the group consisting of:

a regular-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods of performance degradation under regular system operation of said heterogeneous cluster, and

a node-failure-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods in which one or more nodes of said heterogeneous cluster have failed.

17. The method of claim 13 wherein said at least one service parameter comprises at least one performability parameter that defines a desired service characteristic to be provided by each of said plurality of different types of server configurations included in said heterogeneous cluster during periods of degraded service under the expected workload.

18. The method of claim 17 wherein said at least one performability parameter specifies a limit on the amount of degradation of service encountered during said periods of degraded service.

19. The method of claim 17 wherein said at least one performability parameter comprises at least one selected from the group consisting of:

a regular-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods of performance degradation under regular system operation of a selected one of said plurality of different types of server configurations included in said heterogeneous cluster, and

a node-failure-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods in which one or more nodes of said selected one of said plurality of different types of server configurations have failed.

20. A method comprising:

receiving, into a capacity planning tool, information about a first server configuration;

receiving, into said capacity planning tool, information about a second server configuration;

receiving, into said capacity planning tool, workload information representing an expected workload of client accesses of streaming media files from a site;

receiving, into said capacity planning system, at least one performability parameter that defines a desired service characteristic to be provided, during non-compliant periods of operation under the expected workload, by a heterogeneous cluster that includes at least one node of said first server configuration and at least one node of said second server configuration; and

said capacity planning tool evaluating whether said heterogeneous cluster is capable of supporting the expected workload in compliance with said at least one performability parameter.

21. The method of claim 20 wherein said non-compliant periods of operation comprise periods of degraded performance in servicing said expected workload.

22. The method of claim 21 wherein said degraded performance is performance in which said heterogeneous cluster is unable to satisfy real-time constraints of at least one stream being served.

23. The method of claim 21 wherein said degraded performance is performance in which said heterogeneous cluster is unable to serve at least one stream so as to avoid interruptions in the presentation of such stream.

24. The method of claim 21 wherein said degraded performance results from overload of said heterogeneous cluster.

25. The method of claim 20 wherein said non-compliant periods of operation comprise periods of at least one node failure of said heterogeneous cluster.

26. The method of claim 20 further comprising:

receiving, into said capacity planning system, at least one basic capacity parameter that defines a desired service characteristic to be provided by said heterogeneous cluster during compliant periods of operation under the expected workload.

27. The method of claim 26 wherein said compliant periods of operation comprise periods in which said heterogeneous cluster is not overloaded under the expected workload.

28. The method of claim 26 further comprising:

said capacity planning tool performing basic capacity planning to determine how many servers of said first server configuration and how many servers of said second server configuration to be included in said heterogeneous cluster for supporting the expected workload in compliance with said at least one basic capacity parameter.

29. The method of claim 28 further comprising:

said capacity planning tool determining how many servers of said first server configuration and how many servers of said second server configuration to be included in said heterogeneous cluster for supporting the expected workload in compliance with said at least one basic capacity parameter and said at least one performability parameter.

30. The method of claim 20 wherein said at least one performability parameter comprises at least one selected from the group consisting of:

a regular-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods of performance degradation under regular system operation of said heterogeneous cluster, and

a node-failure-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods in which one or more nodes of said heterogeneous cluster have failed.

31. A method comprising:

receiving, into a capacity planning tool, workload information representing an expected workload of client accesses of streaming media files over a period of time T;

said capacity planning tool determining, for each of a plurality of different types of server configurations included in a heterogeneous cluster under evaluation, an amount of overload encountered by such type of server configuration during each of a plurality of time intervals of said expected workload.

32. The method of claim 31 where each of said plurality of time intervals have a size I where I<

T.

33. The method of claim 31 wherein beginning points of each of said plurality of time intervals are separated by a Step amount.

34. The method of claim 33 wherein said Step <

I.

35. The method of claim 33 wherein each of said intervals has a duration of 1 hour and said Step is 1 minute.

36. The method of claim 31 wherein said capacity planning tool receives at least one performability parameter that defines a desired limit on the amount of continuous overload encountered by any of the plurality of different types of server configurations included in the heterogeneous cluster under the expected workload.

37. The method of claim 36 wherein said capacity planning tool evaluates said amount of overload encountered by each of said plurality of different types of server configurations during each of said plurality of time intervals to determine whether the plurality of different types of server configurations satisfy said at least one performability parameter.

38. The method of claim 36 wherein said at least one performability parameter comprises at least one selected from the group consisting of:

a regular-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods of performance degradation under regular system operation of at least one of said plurality of different types of server configuration, and

a node-failure-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods in which one or more nodes of at least one of said plurality of different types of server configuration have failed.

39. A system comprising:

means for receiving workload information representing an expected workload of client accesses of streaming media files from a site over a period of time T; and

means for determining, for a heterogeneous clustered media server configuration under evaluation, an amount of overload encountered by said heterogeneous clustered media server configuration during servicing each of a plurality of time intervals of said expected workload.

40. The system of claim 39 further comprising:

means for receiving information specifying duration of each of said time intervals.

41. The system of claim 39 where each of said plurality of time intervals have a duration I where I<

T.

42. The system of claim 39 wherein beginning points of each of said plurality of time intervals are separated by a Step amount.

43. The system of claim 42 wherein said Step is smaller in duration than a duration I of each of said intervals.

44. The system of claim 39 further comprising:

means for receiving at least one performability parameter that defines a desired limit on the amount of continuous overload encountered by said heterogeneous clustered media server configuration under evaluation under the expected workload.

45. The system of claim 44 further comprising:

means for evaluating the determined amount of overload encountered by said heterogeneous clustered media server configuration under evaluation for each of said plurality of time intervals to determine whether said heterogeneous clustered media server configuration under evaluation satisfies said at least one performability parameter.

46. The system of claim 44 wherein said at least one performability parameter comprises at least one selected from the group consisting of:

a regular-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods of performance degradation under regular system operation of said heterogeneous clustered media server configuration under evaluation, and

a node-failure-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods in which one or more nodes of said heterogeneous clustered media server configuration under evaluation have failed.

47. A system comprising:

a media profiler operable to receive workload information for a service provider'"'"'s site and generate a workload profile for each of a plurality of different types of server configurations included in a heterogeneous cluster under consideration for supporting the service provider'"'"'s site; and

a capacity planner operable to receive the generated workload profiles for the server configurations of the heterogeneous cluster under consideration and evaluate whether the heterogeneous cluster provides sufficient capacity for supporting the site'"'"'s workload in compliance with defined performability parameters that specify a desired limit on degradation of quality of service provided by said heterogeneous cluster during periods of degraded service.

48. The system of claim 47 wherein said periods of degraded service is periods in which said heterogeneous cluster is unable to serve at least one stream so as to avoid interruptions in the presentation of such stream.

49. The system of claim 47 wherein said defined performability parameters comprise at least one selected from the group consisting of:

a regular-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods of degraded service under regular system operation of said heterogeneous cluster, and

a node-failure-mode overload constraint that specifies a desired limit on the amount of degradation in service that is encountered during periods in which one or more nodes of said heterogeneous cluster have failed.