Methods and systems for making effective use of system resources

• US 9,026,624 B2
• Filed: 10/19/2011
• Issued: 05/05/2015
• Est. Priority Date: 12/10/2010
• Status: Active Grant

• Current Assignee: Salesforce.com, Inc.
• Original Assignee: Salesforce.com, Inc.
• Inventors: Gusev, Andrey, Yang, Ronald, Hansma, Scott, Collins, Jesse, Arbizu, Alan
• Primary Examiner(s): DINH, KHANH Q
• Application Number:
  US13/276,531
• Publication Number:
  US 20120151062A1
• Time in Patent Office: 1,294 Days
• Field of Search: 709/220, 709/224, 709/228, 709/223
• US Class Current: 709/220
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 2209/5019 Workload prediction
• CPC Class Codes: G06F 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 47/125 by balancing the load, e.g. traffic engineering
• CPC Class Codes: H04L 49/90 Buffering arrangements
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/1014 based on the content of a request
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]

Abstract

Methods and systems for making effective use of system resources. A plurality of requests for access to a resource are received. Each request has an associated group of features. The group of features for each request is analyzed to collect observations about the plurality of requests. A function to predict an outcome of a subsequent request is generated based on the observations. Resources are allocated to service the subsequent request based on the function.

Claims

1. A method comprising:

receiving a plurality of requests for access to a resource with a training module of a database system, each request having an associated group of features to be mapped to classes in a database environment, wherein the database environment is provided by one or more server computing devices;

analyzing the group of features for each request with the training module to collect observations about the plurality of requests, wherein the training module generates a statistical model for each database instance within the database environment;

predicting an outcome of a subsequent request based on the observations with a learning module within the database system, wherein the prediction is based on the statistical model from the training module; and

allocating resources in the database environment to service the subsequent request based on the prediction.

2. The method of claim 1 wherein the plurality of requests comprises database queries.

3. The method of claim 1 wherein the group of features comprises:

a number of nested joins in the request;

a number of hash joins in the request; and

a sum of cardinalities for hash joins in the request.

4. The method of claim 1 wherein the group of features comprises:

a cardinality estimate of a main table;

a storage count of the main table; and

a selectivity estimate of the main table.

5. The method of claim 1 wherein the group of features comprises a number of secondary queries in the request.

6. The method of claim 1 wherein the group of features comprises:

an application server processor state; and

an application server memory state.

7. The method of claim 1 wherein the group of features comprises:

a database processor state; and

a number of tables used.

8. A non-transitory computer readable medium having stored there on instructions that, when executed, cause one or more processors to:

receive a plurality of requests for access to a resource, each request having an associated group of features to be mapped to classes in a database environment;

analyze the group of features for each request to collect observations about the plurality of requests;

predict an outcome of a subsequent request based on the observations with a learning module within the database system, wherein the prediction is based on the statistical model from a training module; and

allocate resources in the database environment to service the subsequent request based on the prediction.

9. The non-transitory computer-readable medium of claim 8 wherein the plurality of requests comprises database queries.

10. The non-transitory computer-readable medium of claim 8 wherein the group of features comprises:

a number of nested joins in the request;

a number of hash joins in the request; and

a sum of cardinalities for hash joins in the request.

11. The non-transitory computer-readable medium of claim 8 wherein the group of features comprises:

a cardinality estimate of a main table;

a storage count of the main table; and

a selectivity estimate of the main table.

12. The non-transitory computer-readable medium of claim 8 wherein the group of features comprises a number of secondary queries in the request.

13. The non-transitory computer-readable medium of claim 8 wherein the group of features comprises:

an application server processor state; and

an application server memory state.

14. The non-transitory computer-readable medium of claim 8 wherein the group of features comprises:

a database processor state; and

a number of tables used.

15. An apparatus comprising:

means for receiving a plurality of requests for access to a resource, each request having an associated group of features to be mapped to classes in a database environment;

means for analyzing the group of features for each request to collect observations about the plurality of requests;

means for predicting an outcome of a subsequent request based on the observations with a learning module within the database system, wherein the prediction is based on the statistical model from a training module; and

means for allocating resources in the database environment to service the subsequent request based on the prediction.

16. A system comprising:

one or more user systems;

one or more firewalls; and

one or more server systems communicatively coupled with the one or more user systems and the one or more firewalls, the server system to provide a multitenant environment, wherein the multitenant environment includes data for multiple client entities, each identified by a tenant identifier (ID) having one or more users associated with the tenant ID, users of each of multiple client identities can only access data identified by a tenant ID associated with the respective client entity, and the multitenant environment is at least a hosted database provided by an entity separate from the client entities, and provides on-demand database service to the client entities, the one or more server systems to receive a plurality of requests for access to a resource, each request having an associated group of features to be mapped to classes in a database environment, to analyze the group of features for each request to collect observations about the plurality of requests, to predict an outcome of a subsequent request based on the observations with a learning module within the database system, wherein the prediction is based on the statistical model from a training module, and to allocate resources in the database environment to service the subsequent request based on the prediction.

17. The system of claim 16 wherein the plurality of requests comprises database queries.

18. The system of claim 16 wherein the group of features comprises:

a number of nested joins in the request;

a number of hash joins in the request; and

a sum of cardinalities for hash joins in the request.

19. The system of claim 16 wherein the group of features comprises:

a cardinality estimate of a main table;

a storage count of the main table; and

a selectivity estimate of the main table.

20. The system of claim 16 wherein the group of features comprises a number of secondary queries in the request.

21. The system of claim 16 wherein the group of features comprises:

an application server processor state; and

an application server memory state.

22. The system of claim 16 wherein the group of features comprises:

a database processor state; and

a number of tables used.