Predictive analytics on database wait events

1. A machine learning system for performing predictive analytics on database wait events, the machine learning system including:

a processor;

a memory; and

one or more modules stored in the memory and executable by a processor to perform operations including:

receive database wait event data indicative of an individual wait time for one of a plurality of wait states associated with a database processing query running on a monitored database, wherein the database wait event data is collected and monitored by a plurality of agents running on remote devices;

receive database performance data indicative of performance of the monitored database;

correlate, by a machine learning algorithm, the received database wait event data with the received database performance data to obtain a correlation result;

receiving additional database wait event data and database performance data;

continuously update the machine learning algorithm based on the additional received database call wait event data and database performance data;

predict a performance issue with the monitored database based on the correlation result; and

provide the predicted performance issue to a user interface to display the predicted performance issue.

2. The system of claim 1 , wherein the one or more modules are executable by a processor to provide the user interface to display the predicted performance issue including providing an alert before the performance issue actually occurs.

3. The system of claim 1 , wherein the one or more modules are executable by a processor to provide the user interface to display the predicted performance issue including providing a recommendation on how to avoid the performance issue.

4. The system of claim 3 , wherein the recommendation includes a recommendation that a specific process should be removed or fixed.

5. The system of claim 1 , wherein the database performance data include performance metric data.

6. A method for performing predictive analytics on database wait events, the method including:

receiving, at a learning machine in a computer network, database wait event data indicative of an individual wait time for one of a plurality of wait states associated with a database processing query running on a monitored database, wherein the database wait event data is collected and monitored by a plurality of agents running on remote devices;

receiving database performance data indicative of performance of the monitored database;

correlating the received database wait event data with the received database performance data to obtain a correlation result;

receiving additional database wait event data and database performance data;

continuously updating the machine learning algorithm based on the additional database call wait event data and database performance data;

predicting a performance issue with the monitored database based on the correlation result; and

providing the predicted performance issue to a user interface to display the predicted performance issue.

7. The method of claim 6 , wherein providing the user interface to display the predicted performance issue include providing an alert before the performance issue actually occurs.

8. The method of claim 6 , wherein providing the user interface to display the predicted performance issue include providing a recommendation on how to avoid the performance issue.

9. The method of claim 8 , wherein the recommendation includes a recommendation that a specific process should be removed or fixed.

10. A non-transitory computer readable storage medium embodying instructions when executed by a processor to cause operations to be performed including:

receiving database wait event data indicative of an individual wait time for one of a plurality of wait states associated with a database processing query running on a monitored database, wherein the database wait event data is collected and monitored by a plurality of agents running on remote devices;

receiving database performance data indicative of performance of the monitored database;

correlating the received database wait event data with the received database performance data to obtain a correlation result;

receiving additional database wait event data and database performance data;

continuously update the machine learning algorithm based on the additional received database call wait event data and database performance data;

predicting a performance issue with the monitored database based on the correlation result; and

providing the predicted performance issue to a user interface to display the predicted performance issue.

11. The non-transitory computer readable storage medium of claim 10 , wherein providing the user interface to display the predicted performance issue include providing an alert before the performance issue actually occurs.

12. The non-transitory computer readable storage medium of claim 10 , wherein providing the user interface to display the predicted performance issue include providing a recommendation on how to avoid the performance issue.

13. The non-transitory computer readable storage medium of claim 10 , wherein the individual wait time is a central processing unit wait time during the database processing query, an Input/Output wait time of the database processing query or a memory wait time associated with the database processing query.

14. The method of claim 6 , wherein the individual wait time is a central processing unit wait time during the database processing query, an Input/Output wait time of the database processing query or a memory wait time associated with the database processing query.

15. The system of claim 1 , wherein the individual wait time is a central processing unit wait time during the database processing query, an Input/Output wait time of the database processing query or a memory wait time associated with the database processing query.