Apparatus and method for detecting resource consumption and preventing workload starvation

1. A method for detecting resource consumption and preventing workload starvation, the method comprising:

receiving a query for reading data from a data blocks set;

determining if the query will be classified as a resource intense query, wherein the determining is based on a number of read passes by a cache call over the data blocks set during a time window, wherein the determining further comprises comparing the number of read passes over the data blocks set with a pass threshold value during the time window, wherein a value of the time window is dependent on a data size of the data blocks set, and wherein the cache call is associated with the query; and

if the query is classified as a resource intense query, then responding to prevent workload starvation.

2. The method of claim 1 , wherein the comparing further comprises varying the pass threshold value.

3. The method of claim 1 , wherein the act of responding comprises generating a report that can be used to create rules to apply to the resource intense query.

4. The method of claim 1 , wherein the act of responding comprises reducing a data access priority of the resource intense query.

5. The method of claim 4 , further comprising: reducing the data access priority by a decrement value.

6. The method of claim 5 , further comprising: presetting the decrement value by a user.

7. The method of claim 5 , further comprising: dynamically adjusting the decrement value.

8. The method of claim 5 , further comprising: disabling the decrement value.

9. The method of claim 4 , further comprising: performing a throttle of the query if the data access priority falls to a minimum threshold value and contention of a resource is occurring.

10. The method of claim 9 , wherein the query will consume the resource during a share of a timeslice value, if the query is in a throttled state.

11. The method of claim 10 , wherein the share of the timeslice value is an adjustable value.

12. The method of claim 1 , wherein the responding to prevent the workload starvation further comprises: stopping an execution of the query if the query exceeds a resource limit.

13. An apparatus for detecting resource consumption and preventing workload starvation, the apparatus comprising:

a central processing unit;

a data access manager configured

to receive a query for reading data from a data blocks set,

to determine if the query will be classified as a resource intense query, wherein the determining is based on a number of read passes by a cache call over the data blocks set during a time window, wherein the determining further comprises comparing the number of read passes over the data blocks set with a pass threshold value during the time window, wherein a value of the time window is dependent on a data size of the data blocks set, and wherein the cache call is associated with the query, and

to respond to prevent workload starvation if the query is classified as a resource intense query.

14. The apparatus of claim 13 , wherein the pass threshold value may be varied in value.

15. The apparatus of claim 13 , wherein the data access manager is configured to generate a report that can be used to create rules to apply to the resource intense query.

16. The apparatus of claim 13 , wherein the data access manager is configured to reduce a data access priority of the resource intense query.

17. The apparatus of claim 16 , wherein the data access manager is configured to reduce the data access priority by a decrement value.

18. The apparatus of claim 17 , wherein the decrement value is preset by a user.

19. The apparatus of claim 17 , wherein the data access manager is configured to dynamically adjust the decrement value.

20. The apparatus of claim 17 , wherein the decrement value is disabled by a user.

21. The apparatus of claim 16 , wherein the data access manager is configured to perform a throttle of the query if the data access priority falls to a minimum threshold value and contention of a resource is occurring.

22. The apparatus of claim 21 , wherein the query will consume the resource during a share of a timeslice value, if the query is in a throttled state.

23. The apparatus of claim 22 , wherein the share of the timeslice value is an adjustable value.

24. The apparatus of claim 13 , wherein the data access manager is configured to stop an execution of the query if the query exceeds a resource limit as a part of the responding to prevent the workload starvation.

25. An article of manufacture comprising:

a non-transitory machine-readable medium having stored thereon instructions to:

receive a query for reading data from a data blocks set;

determine if the query will be classified as a resource intense query, wherein the determining is based on a number of read passes by a cache call over the data blocks set during a time window, wherein the determining further comprises comparing the number of read passes over the data blocks set with a pass threshold value during the time window, wherein a value of the time window is dependent on a data size of the data blocks set, and wherein the cache call is associated with the query; and

respond to prevent workload starvation, if the query is classified as a resource intense query.

26. An apparatus for detecting resource consumption and preventing workload starvation, the apparatus comprising:

a central processing unit;

means for receiving a query for reading data from a data blocks set;

means for determining if the query will be classified as a resource intense query, wherein the determining is based on a number of read passes by a cache call over the data blocks set during a time window, wherein the determining further comprises comparing the number of read passes over the data blocks set with a pass threshold value during the time window, wherein a value of the time window is dependent on a data size of the data blocks set, and wherein the cache call is associated with the query; and

means for responding to prevent workload starvation, if the query is classified as a resource intense query.