REAL-TIME COMPUTING RESOURCE MONITORING

• US 20120110582A1
• Filed: 10/29/2010
• Published: 05/03/2012
• Est. Priority Date: 10/29/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ferdous, Rashed, Meyer, Arthur J. III, Sosa, Carlos P.
• Granted Patent: US 8,621,477 B2
• Time in Patent Office: Days
• US Class Current: 718/101
• CPC Class Codes: G06F 11/004 Error avoidance G06F11/07 and subgroups take precedence
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3442 for planning or managing the needed capacity
• CPC Class Codes: G06F 11/3452 Performance evaluation by statistical analysis
• CPC Class Codes: G06F 2209/503 Resource availability
• CPC Class Codes: G06F 2209/508 Monitor
• CPC Class Codes: G06F 9/5044 considering hardware capabilities
• CPC Class Codes: G06F 9/505 considering the load

Abstract

Techniques used to enhance the execution of long-running or complex software application instances and jobs on computing systems are disclosed herein. In one embodiment, a real time, self-predicting job resource monitor is employed to predict inadequate system resources on the computing system and failure of a job execution on the computing system. This monitor may not only determine if inadequate resources exist prior to execution of the job, but may also detect in real time if inadequate resources will be encountered during the execution of the job for cases where resource availability has unexpectedly decreased. If a resource deficiency is predicted on the executing computer system, the system may pause the job and automatically take corrective action or alert a user. The job may resume after the resource deficiency is met. Additional embodiments also integrate this resource monitoring capability with the adaptive selection of a computer system or application execution environment based on resource capability predictions and benchmarks.

Claims

1. A method for real time job resource monitoring in a computing system, comprising:

analyzing input for a job, the job provided to the computing system for a job execution with one or more application instances on the computing system, and the job execution consuming processing resources of the computing system;

estimating total resource requirements of the job execution on the computing system based on the analysis of the input;

monitoring usage of the processing resources throughout the job execution on the computing system, including repeatedly verifying future resource availability for the job during the job execution by;

measuring cumulative resource consumption for the job and available resource levels in the computing system;

estimating future resource requirements of the execution of the job based on the total resource requirements of the job and cumulative resource consumption for the job;

comparing the future resource requirements of the execution of the job with the available resource levels in the computing system; and

predicting a resource deficiency if the future resource requirements exceed the available resource levels in the computing system; and

implementing one or more actions to prevent failure of the job execution on the computing system responsive to prediction of the resource deficiency.

2. The method of claim 1, wherein the actions include pausing the job.

3. The method of claim 1, wherein the actions include alerting a user of the resource deficiency.

4. The method of claim 1, further comprising estimating a total amount of time required to execute the job on the computing system, wherein monitoring usage of the processing resources throughout the job execution factors remaining execution time from the total amount of time required to execute the job on the computing system.

5. The method of claim 1, further comprising automatically selecting the computing system from a plurality of computing systems for execution of the job based on the input and the total resource requirements of the job.

6. The method of claim 5, further comprising factoring currently executing or scheduled jobs on the computing system and resource usage thresholds to select the computing system.

7. The method of claim 1, wherein the processing resources include one or more of disk space, memory, and CPU cycles.

8. The method of claim 1, wherein the computing system comprises a massively parallel processing computer architecture.

9. The method of claim 1, wherein the computing system comprises a single-processor computer system.

10. The method of claim 1, wherein analyzing the input of the job comprises obtaining a series of application performance benchmarks against the computing system and determining the resource consumption rate of the job based on the application performance benchmarks.

11. The method of claim 1, wherein repeatedly verifying future resource availability includes repeating the monitoring steps at a predefined interval, the predefined interval correlating to one or both of the input and the total resource requirements of the job.

12. The method of claim 1, wherein the job is a batch job and contains a plurality of jobs for execution in a plurality of application instances.

13. A method for real time job resource monitoring in a computing environment, comprising:

calculating application processing capabilities of a plurality of computing systems;

analyzing job input of a job to be executed with one or more application instances on the plurality of computing systems;

estimating total resource requirements of the job execution on each of the plurality of computing systems based on the analysis of the job input;

selecting one or more computer systems from the plurality of computing systems based on the analysis of the job input and available resources on the computer systems;

providing the job to the selected computer systems;

monitoring resource usage of the job execution on the selected computer systems throughout the job execution, including repeatedly verifying future resource availability for continued execution of the job within the selected computer systems, thereby providing a prediction of any resource deficiency; and

implementing one or more corrective actions to prevent failure of the job execution on the selected computer systems responsive to prediction of a resource deficiency.

14. The method of claim 13, wherein monitoring resource usage of the job execution on the selected computer systems throughout the job execution includes:

measuring cumulative resource consumption for the job and available resource levels in the selected computer systems;

estimating future resource requirements of the execution of the job based on the total resource requirements of the job and cumulative resource consumption for the job;

comparing the future resource requirements of the execution of the job with the available resource levels in the selected computer systems; and

predicting a resource deficiency if the future resource requirements exceed the available resource levels in the computing system.

15. The method of claim 14, wherein the steps of monitoring resource usage of the job execution on the selected computer systems throughout the job execution are repeated during each of a plurality of predefined time intervals.

16. The method of claim 15, wherein length of the predefined time intervals correlates to one or both of the job input and the total resource requirements of the job.

17. The method of claim 13, wherein analyzing the job input comprises obtaining a series of application performance benchmarks against the plurality of computing systems and determining the resource consumption rate of the job based on the application performance benchmarks.

18. A system for providing real time job resource monitoring of a computer system, comprising:

a resource estimator configured for analyzing input of a job provided to the computer system and estimating adequate levels of processing resources in the computer system needed for successful execution of the job;

a resource monitor configured for monitoring adequate processing resources of the computer system throughout execution of the job within the computer system, by;

measuring cumulative resource consumption for the job and available resource levels in the computer system;

estimating future resource requirements of the execution of the job based on total resource requirements of the job and the cumulative resource consumption for the job; and

comparing the future resource requirements of the execution of the job with the available resource levels in the computer system to predict any resource deficiency; and

a resource manager configured for implementing one or more corrective actions to prevent failure of the job execution on the computer system responsive to prediction of a resource deficiency.

19. The system of claim 18, wherein monitoring adequate processing resources of the computer system throughout execution of the job occurs during each of a plurality of predefined time intervals.

20. The system of claim 19, wherein length of the predefined time intervals correlates to one or both of the job input and the total resource requirements of the job.