Generation of resource-usage profiles for application sessions of a number of client computing devices

• US 20070150599A1
• Filed: 12/22/2005
• Published: 06/28/2007
• Est. Priority Date: 12/22/2005
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Neogi, Anindya, Kothari, Ravi, Rohit, Jain
• Application Number:
  US11/315,821
• Publication Number:
  US 20070150599A1
• Time in Patent Office: Days
• US Class Current: 709/227
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3495 for systems
• CPC Class Codes: G06F 16/217 Database tuning G06F16/2282 takes precedence; database performance monitoring G06F11/3409
• CPC Class Codes: G06F 2209/508 Monitor
• CPC Class Codes: G06F 9/5061 Partitioning or combining of resources

Abstract

Resource-usage profiles for application sessions of a number of client computing devices are generated, by aggregating profiles generated from application sessions running on the client computing devices. In particular, resource-usage information for application sessions is generated as the application sessions are generated within each client computing device of a number of client computing devices. Resource-usage profiles for application programs or application categories are then created based on this resource-usage information. Thus, at least one of the resource-usage profiles is based upon the resource-usage information generated by more than one of the client computing devices. Furthermore, a user may query the resource-usage profiles, so that the user is able to retrieve information regarding a desired application program as run on a number of the client computing devices. Additionally or alternatively, a computer program running on a client computing device may query the resource-usage profiles.

Claims

1. A method comprising:

by each client computing device of a plurality of client computing devices,

as application sessions are generated within the client computing device, generating resource-usage information for the application sessions;

creating resource-usage profiles for application programs based on the resource-usage information generated within the client computing devices, such that at least one of the resource-usage profiles is based upon the resource-usage information generated by more than one of the client computing devices;

at least one of;

a user querying the resource-usage profiles, such that the user is able to retrieve information regarding a desired application program as run on a number of the client computing devices; and

,

a computer program running on one of the client computing devices querying the resource-usage profiles for a desired application program to retrieve information regarding the desired application program.

2. The method of claim 1, further comprising:

by each client computing device of the plurality of client computing devices, transmitting the resource-usage information for the application sessions to a central repository; and

,

storing the resource-usage information for the application sessions generated by the client computing devices at the central repository, such that the user or the computer program queries the resource-usage profiles at the central repository.

3. The method of claim 2, wherein the resource-usage profiles are generated and stored using a predetermined schema.

4. The method of claim 1, further comprising storing the resource-usage information for the application sessions generated by the client computing devices in a distributed manner among the client computing devices.

5. The method of claim 4, wherein the resource-usage information is stored in a distributed manner among the client computing devices using a predetermined schema.

6. The method of claim 1, wherein the resource-usage information for the application sessions are generated by an agent running on the client computing device and monitoring the invocation and termination of application programs.

7. The method of claim 1, wherein each resource-usage information comprises static information comprising at least one of:

a name of an executable file used to launch an application program;

a version number of the application program; and

,

one or more attributes of the executable file.

8. The method of claim 1, wherein each resource-usage information comprises dynamic information.

9. The method of claim 8, wherein the dynamic information of each resource-usage information comprises a resource-usage trace having a set of 5-tupes, each of the form {(c_i,n_i,d_i,m_i,t_i)}_i=1^N, where c_i denotes processor usage, n_i denotes network usage, d_i denotes disk usage, and m_i denotes memory usage within a time interval t_i−

t<sub>i−

1</sub>, for each time interval t_i, i=1 . . . N.

10. The method of claim 8, wherein the dynamic information of each resource-usage information further comprises user feedback.

11. The method of claim 10, wherein the user feedback having a set of 4-types, each of the form {(s_c,s_n,s_d,s_m)}, where s_c, s_n, s_d, and s_m are binary feedback values indicating whether a user is satisfied with processor usage, network usage, disk usage, and memory usage, respectively.

12. The method of claim 8, wherein the dynamic information of each resource-usage information is stored in accordance with a clustering approach, such that the dynamic information of all the resource-usage information generated by all the client computing devices is combined on a per-application program or on an application category basis.

13. The method of claim 12, wherein the dynamic information is combined on the application category basis using a plurality of application categories, the application categories named based on an ontology obtained from external sources and stored in a repository.

14. The method of claim 12, further comprising, for each application program or application category for which resource-usage information have been generated, filtering the dynamic information of the resource-usage information for the application program or application category to provide a prototypical representation of a resource-usage profile for the application program or application category.

15. The method of claim 14, further comprising updating the prototypical representation of the resource-usage profile for the application program or application category as additional resource-usage information is generated for the application program or application category.

16. A computerizing system comprising:

a plurality of client computing devices, each client computing device running an agent to monitor invocation, resource usage, and termination of application programs; and

,

a repository to store the resource-usage information generated within the client computing devices and to store resource-usage profiles for the application programs and application categories created based on the resource-usage information generated within the client computing devices, such that at least one of the resource-usage profiles is based upon the resource-usage information generated by more than one of the client computing devices, the repository queryable by at least one of;

a user, in order to retrieve information regarding a desired application program as run on a number of the client computing devices; and

,

computer program running on one of the client computing devices.

17. The system of claim 16, wherein the repository comprises a central storage, to which the agent of each client computing device transmits the resource-usage information for the application sessions generated thereby.

18. The system of claim 16, wherein the repository is distributed over the client computing devices.

19. The system of claim 16, wherein each resource-usage information comprises a resource-usage trace having a set of 5-tupes, each of the form {(c_i,n_i,d_i,m_i,t_i)}_i=1^N, where c_i denotes processor usage, n_i denotes network usage, d_i denotes disk usage, and m_i denotes memory usage within a time interval t_i−

t<sub>i−

i</sub>, for each time interval t_i, i=1 . . . N.

20. An article of manufacture comprising:

a computer-readable medium;

tangibly embodying a computer program for executing a method comprising;

collecting resource-usage information generated for application sessions by and within a plurality of client computing devices;

creating resource-usage profiles for application programs based on the resource-usage information generated within the client computing devices; and

enabling querying of the resource-usage profiles by at least one of;

a user, in order to retrieve information regarding a desired application program as run on a number of the client computing devices, and,

a computer program running on one of the client computing devices.