Method and system of an integrated simulation tool using business patterns and scripts

• US 6,768,968 B2
• Filed: 04/18/2002
• Issued: 07/27/2004
• Est. Priority Date: 04/18/2002
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Wadia, Noshir Cavas, Ignatowski, Michael
• Primary Examiner(s): Barlow, John
• Assistant Examiner(s): Walling, Meagan S
• Application Number:
  US10/126,245
• Publication Number:
  US 20030200059A1
• Time in Patent Office: 831 Days
• Field of Search: 702/186, 707/2, 707/4, 707/10, 707/100, 707/102, 706/49
• US Class Current: 702/186
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3438 monitoring of user actions tracking the activity of the user H04L67/535
• CPC Class Codes: G06F 11/3495 for systems
• CPC Class Codes: G06F 2201/87 Monitoring of transactions
• CPC Class Codes: G06F 2201/875 Monitoring of systems including the internet
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

A method, system and article of manufacture for estimating the performance of a computer system are provided. Initially, a business pattern representative of the expected usage of the computer system is identified. Then, for each parameter associated with each predefined script, which corresponds to the identified business pattern, a value is established. The computer system hardware characteristics and performance objectives are identified next. The performance estimate is then calculated utilizing the established parameter values, identified hardware characteristics and performance objectives. To calculate the performance estimate, the script measurements data is read from a table of previously measured values, and a weighted average number of page visits per user, a weighted average visit rate and a weighted average service time for each target device in the computer system are calculated. A total response time and a system throughput are calculated by varying each target device queue length and user arrival rate until the performance objectives are reached.

Claims

1. A method to be performed on a first computer system for estimating the performance of a second computer system comprising a plurality of target devices, said method comprising the steps of:

identifying a business pattern from a plurality of business patterns representative of the expected usage of said second computer system;

establishing a value for each parameter in a plurality of parameters associated with each script in a plurality of predefined scripts, wherein said plurality of predefined scripts corresponds to said identified business pattern;

identifying hardware characteristics and performance objectives of said second computer system; and

calculating a performance estimate for said second computer system utilizing said parameter values, said hardware characteristics and said performance objectives.

2. The method of claim 1, wherein said plurality of business patterns includes a business pattern selected from the group consisting of user-to-data, user-to-online-buying, user-to-business, and business-to-business business patterns.

3. The method of claim 2, wherein said plurality of parameters includes a script frequency parameter and a page visits per script parameter.

4. The method of claim 3, wherein said hardware characteristics comprise a plurality of types of devices associated with said plurality of target devices and the number of devices for each of said types of devices, said plurality of target devices comprises processors, disks, busses, and network connections.

5. The method of claim 4, wherein said performance objectives comprise a user arrival rate objective and a maximum allowed response time objective.

6. The method of claim 5, wherein said calculating step further comprises the steps of:

for each script in said plurality of predefined scripts, reading script measurements data from a table of previously measured values, and calculating a visit rate per page and a service time per visit for each target device in said plurality of target devices using said script measurements data;

calculating a weighted average number of page visits per user utilizing said script frequency parameter and said page visits per script parameter; and

for each target device in said plurality of target devices, calculating a weighted average visit rate based on said visit rates and a weighted average service time based on said service times.

7. The method of claim 6, wherein said script measurements data comprise a processor service time, a number of disk IO operations per page visit, and a number of bytes communicated over the network.

8. The method of claim 6, further comprising the steps of:

(a) initializing a queue length for each target device in said plurality of target devices and initializing a user arrival rate;

(b) calculating a target device response time for each target device in said plurality of target devices utilizing said weighted average service time and said queue length;

(c) calculating a total response time based on said target device response times and said weighted average visit rates;

(d) calculating a system throughput utilizing said weighted average number of page visits per user and said user arrival rate; and

(c) if said performance objectives are not reached, adjusting said queue lengths and said user arrival rate; and

repeating steps (b), (c) and (d) until said performance objectives are reached.

9. The method of claim 8, wherein said queue lengths are adjusted based on said calculated system throughput, said weighted average visit rates, and said target device response times.

10. The method of claim 1, wherein said second computer system is same as said first computer system.

11. A first computer system for estimating the performance of a second computer system comprising a plurality of target devices, said first computer system comprising:

a computer; and

one or more computer programs executed by said first computer system for performing the steps of;

identifying a business pattern from a plurality of business patterns representative of the expected usage of said second computer system;

establishing a value for each parameter in a plurality of parameters associated with each script in a plurality of predefined scripts, wherein said plurality of predefined scripts corresponds to said identified business pattern;

identifying hardware characteristics and performance objectives of said second computer system; and

calculating a performance estimate for said second computer system utilizing said parameter values, said hardware characteristics and said performance objectives.

12. The first computer system of claim 11, wherein said plurality of business patterns includes a business pattern selected from the group consisting of user-to-data, user-to-online-buying, user-to-business, and business-to-business business patterns.

13. The first computer system of claim 12, wherein said plurality of parameters includes a script frequency parameter and a page visits per script parameter.

14. The first computer system of claim 13, wherein said hardware characteristics comprise a plurality of types of devices associated with said plurality of target devices and the number of devices for each of said types of devices, said plurality of target devices comprises processors, disks, busses, and network connections.

15. The first computer system of claim 14, wherein said performance objectives comprise a user arrival rate objective and a maximum allowed response time objective.

16. The first computer system of claim 15, wherein said calculating step further comprises the steps of:

for each script in said plurality of predefined scripts, reading script measurements data from a table of previously measured values, and calculating a visit rate per page and a service time per visit for each target device in said plurality of target devices using said script measurements data;

calculating a weighted average number of page visits per user utilizing said script frequency parameter and said page visits per script parameter; and

for each target device in said plurality of target devices, calculating a weighted average visit rate based on said visit rates and a weighted average service time based on said service times.

17. The first computer system of claim 16, wherein said script measurements data comprise a processor service time, a number of disk IO operations per page visit, and a number of bytes communicated over the network.

18. The first computer system of claim 16, further comprising the steps of:

(a) initializing a queue length for each target device in said plurality of target devices and initializing a user arrival rate;

(b) calculating a target device response time for each target device in said plurality of target devices utilizing said weighted average service time and said queue length;

(c) calculating a total response time based on said target device response times and said weighted average visit rates;

(d) calculating a system throughput utilizing said weighted average number of page visits per user and said user arrival rate; and

(c) if said performance objectives are not reached, adjusting said queue lengths and said user arrival rate; and

repeating steps (b), (c) and (d) until said performance objectives are reached.

19. The first computer system of claim 18, wherein said queue lengths are adjusted based on said calculated system throughput, said weighted average visit rates, and said target device response times.

20. The first computer system of claim 11, wherein said second computer system is same as said first computer system.

21. An article of manufacture comprising a program storage device readable by a first computer system and tangibly embodying one or more programs of instructions executable by said first computer system to perform method steps for estimating the performance of a second computer system comprising a plurality of target devices, said method steps comprising the steps of:

identifying a business pattern from a plurality of business patterns representative of the expected usage of said second computer system;

establishing a value for each parameter in a plurality of parameters associated with each script in a plurality of predefined scripts, wherein said plurality of predefined scripts corresponds to said identified business pattern;

identifying hardware characteristics and performance objectives of said second computer system; and

calculating a performance estimate for said second computer system utilizing said parameter values, said hardware characteristics and said performance objectives.

22. The article of manufacture according to claim 21, wherein said plurality of business patterns includes a business pattern selected from the group consisting of user-to-data, user-to-online-buying, user-to-business, and business-to-business business patterns.

23. The article of manufacture according to claim 22, wherein said plurality of parameters includes a script frequency parameter and a page visits per script parameter.

24. The article of manufacture according to claim 23, wherein said hardware characteristics comprise a plurality of types of devices associated with said plurality of target devices and the number of devices for each of said types of devices, said plurality of target devices comprises processors, disks, busses, and network connections.

25. The article of manufacture according to claim 24, wherein said performance objectives comprise a user arrival rate objective and a maximum allowed response time objective.

26. The article of manufacture according to claim 25, wherein said calculating step further comprises the steps of:

for each script in said plurality of predefined scripts, reading script measurements data from a table of previously measured values, and calculating a visit rate per page and a service time per visit for each target device in said plurality of target devices using said script measurements data;

calculating a weighted average number of page visits per user utilizing said script frequency parameter and said page visits per script parameter; and

for each target device in said plurality of target devices, calculating a weighted average visit rate based on said visit rates and a weighted average service time based on said service times.

27. The article of manufacture according to claim 26, wherein said script measurements data comprise a processor service time, a number of disk IO operations per page visit, and a number of bytes communicated over the network.

28. The article of manufacture according to claim 26, further comprising the steps of:

(a) initializing a queue length for each target device in said plurality of target devices and initializing a user arrival rate;

(b) calculating a target device response time for each target device in said plurality of target devices utilizing said weighted average service time and said queue length;

(c) calculating a total response time based on said target device response times and said weighted average visit rates;

(d) calculating a system throughput utilizing said weighted average number of page visits per user and said user arrival rate; and

(c) if said performance objectives are not reached, adjusting said queue lengths and said user arrival rate; and

repeating steps (b), (c) and (d) until said performance objectives are reached.

29. The article of manufacture according to claim 28, wherein said queue lengths are adjusted based on said calculated system throughput, said weighted average visit rates, and said target device response times.

30. The article of manufacture according to claim 21, wherein said second computer system is same as said first computer system.

31. A method for estimating the performance of a computer system comprising a plurality of target devices, said method comprising the steps of:

receiving a plurality of business patterns from a modeling tool for projecting system performance of said computer system;

selecting a business pattern from said plurality of business patterns representative of the expected usage of said computer system;

providing a value for each parameter in a plurality of parameters associated with each script in a plurality of predefined scripts, wherein said plurality of predefined scripts corresponds to said selected business pattern;

specifying hardware characteristics and performance objectives of said computer system; and

invoking said modeling tool to project system performance of said computer system, whereby said modeling tool utilizes said parameter values, said hardware characteristics and said performance objectives to calculate said system performance projection.