Predictive analytics on database wait events

Patent metadata

Field	Value
Publication number	US-10452463-B2
Application number	US-201615224560-A
Country	US
Kind code	B2
Filing date	Jul 31, 2016
Priority date	Jul 31, 2016
Publication date	Oct 22, 2019
Grant date	Oct 22, 2019

Abstract

In one aspect, a machine learning system for performing predictive analytics on database wait events is disclosed. The machine learning system includes 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 wait events associated with database calls running on a monitored database; receive database performance data indicative of performance of the monitored database; correlate the received database wait event data with the received database performance data to obtain a correlation result; predict a performance issue with the monitored database based on the correlation result; and provide a user interface to display the predicted performance issue.

First claim

What is claimed is:

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.

Assignees

• Appdynamics Llc
• Cisco Tech Inc

Inventors

• Hiran Apun
• Carmel Ido
• Nagaraj Sanjay

Classifications

• G06F11/3006

  where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems (multiprogramming arrangements G06F9/46; allocation of resources G06F9/50) · CPC title

• G06F11/3447

  Performance evaluation by modeling · CPC title

• G06F11/079 Primary

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• G06F2201/86

  Event-based monitoring · CPC title

• G06F2201/80

  Database-specific techniques · CPC title