Server array capacity management calculator

• US 8,484,340 B2
• Filed: 06/14/2010
• Issued: 07/09/2013
• Est. Priority Date: 06/14/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Hogan, Grant, Ma, Roy Y.
• Primary Examiner(s): Keehn, Richard G
• Application Number:
  US12/815,270
• Publication Number:
  US 20110307601A1
• Time in Patent Office: 1,121 Days
• Field of Search: 709/224
• US Class Current: 709/224
• 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 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 67/1031 Controlling of the operation of servers by a load balancer, e.g. adding or removing servers that serve requests
• CPC Class Codes: H04L 67/131 Protocols for games, networked simulations or virtual reality

Abstract

Server array capacity calculator systems and methods are provided for estimating capacity based on diagnostic data. For example, a system comprising a database and an estimator computing device comprising a graphical user interface (GUI) and a capacity management module stored in memory and executed on a processor comprising instructions to receive diagnostic data from a plurality of servers of different server types, receive user input via the GUI, and in response to the user input, and for each of the server types, compute a current reference number of servers from current server efficiency estimates and a current number of utilized servers; calculate a growth multiplier from a ratio of the projected number of users and a count of the current concurrent users; generate a projected number of servers by multiplying the current reference number of servers with the growth multiplier, and display the projected number of servers on the GUI.

Claims

1. An estimating system for calculating server array capacity, comprising:

a database for storing diagnostic data detected by work counter modules and resource monitoring modules executed on each server of a server array; and

an estimator computing device comprising a graphical user interface and a capacity management module executed by a processor using portions of memory and comprising instructions to;

receive diagnostic data from a plurality of servers of different server types in a server array, the diagnostic data including, for each server type, a current number of utilized servers and a count of current concurrent users, wherein the diagnostic data further includes current processor utilization data, and wherein the diagnostic data is detected by work counter modules and resource monitoring modules executed on each of the servers in the server array and stored in a database;

receive user input via the graphical user interface, the user input including a projected number of users and a processor threshold input; and

in response to the user input, and for each of the server types;

compute an estimated current server efficiency based on the current processor utilization data and the processor threshold input,

estimate a current server transaction rate threshold based on the estimated current server efficiency and on current server transaction rate data included in the diagnostic data,

compute a current reference number of servers based on the current number of utilized servers, the current server transaction rate data, and the current server transaction rate threshold,

calculate a growth multiplier based on a ratio of the projected number of users and the count of the current concurrent users,

generate a projected number of servers to be deployed in the server array for the projected number of users by multiplying the current reference number of servers with the growth multiplier, and

display the projected number of servers on the graphical user interface.

2. The system of claim 1, wherein the current server transaction rate data includes a count of the number of transactions requested per unit time and/or a count of the number of transactions served per unit time.

3. The system of claim 1, wherein the server types in the server array include two or more of avatar servers, game servers, marketplace servers, or movie servers or other type of server to client connected array.

4. The system of claim 1, the capacity management module further comprising instructions to, for each of the server types:

calculate a maximum number of concurrent users that can be served for each of the different server types in the server array based on the processor threshold input included in the user input, on the projected number of users, and on a growth-modified processor estimation; and

display the maximum number of concurrent users on the graphical user interface.

5. The system of claim 4, wherein the growth-modified processor estimation is generated based on average current processor maximum load data for each server type and the growth multiplier, the average current processor maximum load data included in the diagnostic data.

6. The system of claim 1, the capacity management module further comprising instructions to receive a date range input, a day of week input, and/or a time of day input via the graphical user interface and wherein receiving the diagnostic data includes filtering the diagnostic data for the date range input, day of week input, and/or time of day input.

7. A method for use in calculating server array capacity, comprising, at a capacity management module executed on an estimator computing device:

receiving diagnostic data from a plurality of servers of different server types in a server array, the diagnostic data including, for each server type, a current number of utilized servers and a count of current concurrent users, wherein the diagnostic data further includes current processor utilization data, and wherein the diagnostic data is detected by work counter modules and resource monitoring modules executed on each of the servers in the server array and stored in a database,

receiving user input via a graphical user interface, the user input including a projected number of users and a processor threshold input; and

in response to the user input, and for each of the server types;

computing an estimated current server efficiency based on the current processor utilization data and the processor threshold input,

estimating a current server transaction rate threshold based on the estimated current server efficiency and on current server transaction rate data included in the diagnostic data,

computing a current reference number of servers based on and the current number of utilized servers, the current server transaction rate data, and the current server transaction rate threshold,

calculating a growth multiplier based on a ratio of the projected number of users and the count of current concurrent users,

generating a projected number of servers to be deployed in the server array for the projected number of users by multiplying the current reference number of servers with the growth multiplier, and

displaying the projected number of servers on the graphical user interface.

8. The method of claim 7, wherein the current transaction rate data includes a count of the number of transactions requested per unit time and/or a count of the number of transactions served per unit time.

9. The method of claim 7, further comprising, for each of the server types:

calculating a maximum number of concurrent users that can be served for each of the different server types in the server array based on the processor threshold input included in the user input, on the projected number of users, and on a growth-modified processor estimation; and

displaying the maximum number of concurrent users on the graphical user interface.

10. The method of claim 9, wherein the growth-modified processor estimation is generated based on average current processor maximum load data for each server type and the growth multiplier, the average current processor maximum load data included in the diagnostic data.

11. The method of claim 7, further comprising receiving a date range input, a day of week input, and/or a time of day input via the graphical user interface and wherein receiving the diagnostic data includes filtering the diagnostic data for the date range input, day of week input, and/or time of day input.

12. The method of claim 7, wherein the server types in the server array include two or more of avatar servers, game servers, marketplace servers, or movie servers.

13. A method for use in calculating server array capacity, comprising, at an estimator program executed on an estimator computing device:

receiving diagnostic data from a plurality of servers of different server types in a server array, the server types including two or more of avatar servers, game servers, marketplace servers, or movie servers, the diagnostic data including, for each server type, a current number of utilized servers and a count of current concurrent users, wherein the diagnostic data further includes current processor utilization data, and wherein the diagnostic data is detected by work counter modules and resource monitoring modules executed on each of the servers in the server array and stored in a database,

receiving user input via a graphical user interface, the user input including a projected number of users and a processor threshold input; and

in response to the user input, and for each of the server types;

computing an estimated current server efficiency based on the current processor utilization data and the processor threshold input,

estimating a current server transaction rate threshold based on the estimated current server efficiency and on current server transaction rate data included in the diagnostic data,

computing a current reference number of servers based on the current number of utilized servers, the current server transaction rate data, and the current server transaction rate threshold,

calculating a growth multiplier based on a ratio of the projected number of users and the count of current concurrent users,

generating a projected number of servers to be deployed in the server array for the projected number of users by multiplying the current reference number of servers with the growth multiplier,

calculating a maximum number of concurrent users that can be served for each of the different server types in the server array based on the processor threshold input included in the user input, on the projected number of users, and on a growth-modified processor estimation, and

displaying the projected number of servers and the maximum number of concurrent users on the graphical user interface.

14. The method of claim 13, wherein the current server transaction rate data includes a count of the number of transactions requested per unit time and/or a count of the number of transactions served per unit time.

15. The method of claim 13, further comprising receiving a date range input, a day of week input, and/or a time of day input via the graphical user interface and wherein receiving the diagnostic data includes filtering the diagnostic data for the date range input, day of week input, and/or time of day input.