System and method for determining how many servers of at least one server configuration to be included at a service provider's site for supporting an expected workload

• US 8,145,731 B2
• Filed: 12/17/2003
• Issued: 03/27/2012
• Est. Priority Date: 12/17/2003
• 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: Tang, Wenting, Cherkasova, Ludmila
• Primary Examiner(s): Patel, Haresh N
• Application Number:
  US10/738,273
• Publication Number:
  US 20050138170A1
• Time in Patent Office: 3,023 Days
• Field of Search: 709217-228, 713/300
• US Class Current: 709/220
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: H04L 41/5006 Creating or negotiating SLA contracts, guarantees or penalties

Abstract

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 the capacity planning system determining, for at least one server configuration, how many servers of the at least one server configuration to be included at the site for supporting the expected workload in a desired manner.

Claims

1. A method comprising:

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

said capacity planning system determining, for at least one server configuration, how many servers of said at least one server configuration to be included at said site for supporting the expected workload in a target manner, wherein said determining how many servers of said at least one server configuration to be included at said site for supporting the expected workload in the target manner comprises;

computing, for resources of a single server of said at least one server configuration, a first service demand under the expected workload;

determining from said first service demand if said single server has sufficient capacity for supporting the expected workload in the target manner; and

in response to determining that said single server does not have sufficient capacity for supporting the expected workload in the target manner, estimating from the first service demand a number of servers of said at least one server configuration that when clustered together in a cluster provide sufficient capacity for supporting the expected workload in the target manner; and

said capacity planning system selecting a type of load balancing strategy from among a plurality of types of load balancing strategies to use for the expected workload.

2. The method of claim 1 wherein said workload information includes identification of a number of concurrent client accesses of said streaming media files from said site over a period of time.

3. The method of claim 2 wherein said workload information further includes identification of a corresponding encoding bit rate of each of said streaming media files accessed.

4. The method of claim 1 further comprising:

receiving, into said capacity planning system, configuration information for said at least one server configuration.

5. The method of claim 1 wherein said determining how many servers of said at least one server configuration to be included at said site for supporting the expected workload in the target manner further comprises:

computing a cost corresponding to resources of said at least one server configuration that are consumed in supporting the expected workload.

6. The method of claim 5 wherein said computing said cost comprises:

computing a cost of consumed resources for a stream in said expected workload having a memory access to a streaming media file; and

computing a cost of consumed resources for a stream in said expected workload having a disk access to a streaming media file.

7. The method of claim 1 further comprising:

receiving at least one service parameter associated with a service level agreement, and

identifying plural server configurations that are able to support the expected workload in accordance with the service level agreement, wherein the at least one server configuration is one of the plural server configurations.

8. The method of claim 7 wherein said at least one service parameter comprises information identifying at least one performance criteria to be satisfied by said site in supporting the expected workload in the target manner.

9. The method of claim 7 wherein said determining how many servers of said at least one server configuration to be included at said site for supporting the expected workload in the target manner comprises:

determining how many servers of said at least one server configuration to be included at said site for supporting the expected workload in a manner that satisfies said at least one service parameter.

10. The method of claim 1, wherein said determining how many servers further comprises, in response to determining that said single server does not have sufficient capacity for supporting the expected workload in the target manner, computing for resources of the cluster of the number of servers, a second service demand under the expected workload, the method further comprising:

analyzing the second service demand to verify whether the number of servers estimated from the first service demand is accurate.

11. The method of claim 1, wherein the plural types of load balancing strategies include a round robin strategy and a locality-aware strategy.

12. The method of claim 1, wherein determining how many servers of said at least one server configuration to be included at said site for supporting the expected workload in the target manner comprises determining how many servers of said at least one server configuration to be included at said site for supporting the expected workload according to one or more service parameters.

13. The method of claim 1, wherein selecting the type of load balancing strategy from among the plurality of types of load balancing strategies is based on evaluating the plurality of types of load balancing strategies for the expected workload.

14. A method comprising:

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

said capacity planning system determining, for at least one server configuration, how many servers of said at least one server configuration to be included at said site for supporting the expected workload in a target manner; and

said capacity planning system selecting a type of load balancing strategy from among a plurality of types of load balancing strategies to use for the expected workload;

wherein said determining how many servers of said at least one server configuration to be included at said site for supporting the expected workload in the target manner comprises computing a service demand for said at least one server configuration in supporting said expected workload;

wherein said computing said service demand comprises computing;

15. The method of claim 14 further comprising:

said capacity planning system determining from said computed service demand how many servers of said at least one server configuration to be included at said site for supporting the expected workload in the target manner.

16. The method of claim 14 further comprising:

said capacity planning system determining from said computed service demand whether a single server of said at least one server configuration can support the expected workload in the target manner.

17. The method of claim 16 further comprising:

in response to said capacity planning system determining from said computed service demand that a single server of said at least one server configuration cannot support the expected workload in the target manner, said capacity planning system estimating from said computed service demand a number of servers of said at least one server configuration that can support the expected workload in the target manner.

18. The method of claim 17 further comprising:

said capacity planning system re-evaluating the expected workload for a cluster having the estimated number of servers of said at least one server configuration to compute a service demand for the cluster to determine whether the estimated number of servers is accurate.

19. The method of claim 18 wherein said re-evaluating includes considering a load balancing strategy used by said cluster in supporting the expected workload.

20. A method comprising:

receiving, into a capacity planning tool executed by a computer, information relating to a service level agreement;

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

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

said capacity planning tool determining how many servers of said first server configuration to be included at said site for supporting the expected workload in a manner that complies with the service level agreement; and

said capacity planning tool selecting a type of load balancing strategy from among a plurality of types of load balancing strategies to use for the expected workload,

wherein said determining how many servers of said first server configuration to be included at said site for supporting the expected workload in the manner that complies with the service level agreement comprises;

computing a cost corresponding to resources of said first server configuration that are consumed in supporting the expected workload;

using the computed cost to compute a service demand for said first server configuration in supporting said expected workload, wherein said computing said service demand comprises computing;

21. The method of claim 20 wherein said computing said cost comprises:

computing a cost of consumed resources for a stream in said workload having a memory access to a streaming media file; and

computing a cost of consumed resources for a stream in said workload having a disk access to a streaming media file.

22. The method of claim 20 further comprising:

generating a workload profile for a single server of said first server configuration under the expected workload, wherein said workload profile identifies client accesses in the expected workload that are served from memory of the single server of said first server configuration and client accesses in the expected workload that are served from disk of the single server.

23. A method comprising:

receiving, into a capacity planning tool executed by a computer, information relating to a service level agreement;

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

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

said capacity planning tool determining how many servers of said first server configuration to be included at said site for supporting the expected workload in a manner that complies with the service level agreement; and

said capacity planning tool selecting a type of load balancing strategy from among a plurality of types of load balancing strategies to use for the expected workload,

wherein said determining how many servers of said first server configuration to be included at said site for supporting the expected workload in the manner that complies with the service level agreement comprises;

computing a service demand for resources of a single server of said first server configuration under the expected workload;

determining from said service demand if said single server has sufficient capacity for supporting the expected workload in the manner that complies with the service level agreement; and

in response to determining that said single server does not have sufficient capacity for supporting the expected workload in the manner that complies with the service level agreement, estimating from the service demand a number of servers of said first server configuration that when clustered together provide sufficient capacity for supporting the expected workload in the manner that complies with the service level agreement.

24. The method of claim 23, wherein selecting the type of load balancing strategy from among the plurality of types of load balancing strategies is based on evaluating the plurality of types of load balancing strategies for the expected workload.

25. The method of claim 23 further comprising:

computing a second service demand for resources of the cluster of the number of servers under the expected workload.

26. The method of claim 25 further comprising:

analyzing the second service demand to verify whether the estimated number of servers is accurate.

27. A method comprising:

receiving, into a capacity planning tool executed by a computer, information relating to a service level agreement;

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

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

said capacity planning tool determining how many servers of said first server configuration to be included at said site for supporting the expected workload in a manner that complies with the service level agreement;

said capacity planning tool selecting a type of load balancing strategy from among a plurality of types of load balancing strategies to use for the expected workload; and

generating a workload profile for a single server of said first server configuration under the expected workload, wherein said workload profile identifies client accesses in the expected workload that are served from memory of the single server of said first server configuration and client accesses in the expected workload that are served from disk of the single server;

wherein said determining how many servers of said first server configuration to be included at said site for supporting the expected workload in the manner that complies with the service level agreement comprises;

using the generated workload profile to evaluate the capacity of said single server of said first server configuration to determine whether said single server of said first server configuration has sufficient capacity for supporting the expected workload in the manner that complies with the service level agreement.

28. The method of claim 27 further comprising:

in response to determining that said single server of the said first server configuration does not have sufficient capacity for supporting the expected workload in the manner that complies with the service level agreement, estimating a number of servers of said first server configuration that when clustered together in a cluster provide sufficient capacity for supporting the expected workload in the manner that complies with the service level agreement and generating a second workload profile for the cluster under the expected workload, wherein said second workload profile identifies client accesses in the expected workload that are served from memory of the cluster of servers of said first server configuration and client accesses in the expected workload that are served from disk of the cluster of servers of said first server configuration.

29. The method of claim 28 wherein said generating said second workload profile comprises determining for each of said number of servers in the cluster the client accesses of the expected workload that are assigned to such server under a load balancing strategy.

30. The method of claim 28 further comprising:

using the generated second workload profile to evaluate the capacity of said cluster of servers of said first server configuration to determine whether said cluster has sufficient capacity for supporting the expected workload in the manner that complies with the service level agreement.

31. A capacity planning system comprising:

at least one central processing unit (CPU);

a capacity planning tool executable on the at least one CPU to;

receive workload information representing an expected workload of client accesses of streaming media files from a site, wherein the workload information identifies a number of concurrent client accesses of said streaming media files from said site over a period of time, and the workload information further identifies types of the client accesses;

determine a number of servers of a given configuration type to be implemented at said site for supporting the expected workload as defined by the workload information according to a service level agreement, wherein the determining is based on;

computing, for resources of a single server of the given configuration type, a service demand under the expected workload,

determining from the service demand if the single server has sufficient capacity for supporting the expected workload according to the service level agreement, and

in response to determining that the single server does not have sufficient capacity for supporting the expected workload according to the service level agreement, estimating from the service demand the number of servers of the given configuration type that when clustered together in a cluster provide sufficient capacity for supporting the expected workload according to the service level agreement; and

select a type of load balancing strategy from among a plurality of types of load balancing strategies to use for the expected workload.

32. The capacity planning system of claim 31, wherein the number of servers of the given configuration type to be implemented at said site for supporting the expected workload comprises a number of the servers of the given configuration type to be implemented at said site for supporting the expected workload according to one or more service parameters.

33. The capacity planning system of claim 31, wherein the type of load balancing strategy selected from among the plurality of types of load balancing strategies is based on evaluating the plurality of types of load balancing strategies for the expected workload.