Deployment rule system

Patent metadata

Field	Value
Publication number	US-9836298-B2
Application number	US-201615082366-A
Country	US
Kind code	B2
Filing date	Mar 28, 2016
Priority date	Mar 28, 2016
Publication date	Dec 5, 2017
Grant date	Dec 5, 2017

Abstract

One embodiment provides an apparatus. The apparatus includes a deployment recipe generator to generate a plurality of deployment recipes; a deployment test engine to test each of a plurality of deployment configurations, each deployment configuration corresponding to a respective deployment recipe; and data analysis logic to determine a deployment rule based, at least in part, on deployment heuristics.

First claim

What is claimed is:

1. An apparatus comprising:
at least one memory to store program instructions; and
at least one processor to execute the program instructions from the at least one memory, the program instructions causing the at least one processor to programmatically implement:
a deployment recipe generator to generate a plurality of deployment recipes identifying physical and virtual resources usable to implement a plurality of deployment configurations to test a workload configured based on an intended use of the resources, and determine test intervals specific to each of the plurality of deployment configurations based on the test intervals based on at least one type of resource included in each of the plurality of deployment configurations;
a deployment test engine to test each of the plurality of deployment configurations utilizing at least the identified resources to process the workload over the interval;
metrics collection logic to collect telemetry data for each deployment configuration; and
data analysis logic to determine deployment heuristics utilizing performance parameters determined based at least on the telemetry data, and determine a deployment rule based, at least in part, on the deployment heuristics.

2. The apparatus of claim 1 , wherein the deployment test engine is to allocate each of the plurality of deployment configurations in a resource pool.

3. The apparatus of claim 1 , further comprising efficiency logic to determine an efficiency value for each deployment rule of a plurality of deployment rules.

4. The apparatus of claim 3 , wherein the efficiency logic is further to rank each deployment rule based, at least in part, on respective efficiency values.

5. The apparatus of claim 1 , further comprising an orchestrator to determine a first deployment recipe based, at least in part, on a target performance value and based, at least in part, on a first deployment rule associated with a workload.

6. The apparatus of claim 5 , wherein the orchestrator is to allocate resources specified by the first deployment recipe and to place the workload.

7. The apparatus of claim 6 , further comprising metrics collection logic to monitor performance, the data analysis logic further to update the first deployment rule if a performance parameter is not at the target performance value.

8. A method comprising:
generating, by a deployment recipe generator, a plurality of deployment recipes identifying physical and virtual resources usable to implement a plurality of deployment configurations to test a workload configured based on an intended use of the resources, and determining test intervals specific to each of the plurality of deployment configurations based on the test intervals based on at least one type of resource included in each of the plurality of deployment configurations;
testing, by a deployment test engine, each of the plurality of deployment configurations utilizing at least the identified resources to process the workload over the interval;
collecting, by metrics collection logic, telemetry data for each deployment configuration;
determining, by data analysis logic, deployment heuristics utilizing performance parameters determined based at least on the telemetry data; and
determining, by the data analysis logic, a deployment rule based, at least in part, on the deployment heuristics.

9. The method of claim 8 , further comprising allocating, by the deployment test engine, each of the plurality of deployment configurations in a resource pool.

10. The method of claim 8 , further comprising determining, by efficiency logic, an efficiency value for each deployment rule of a plurality of deployment rules.

11. The method of claim 10 , further comprising ranking, by the efficiency logic, each deployment rule based, at least in part, on respective efficiency values.

12. The method of claim 8 , further comprising determining, by an orchestrator, a first deployment recipe based, at least in part, on a target performance value and based, at least in part, on a first deployment rule associated with a workload.

13. The method of claim 12 , further comprising allocating, by the orchestrator, resources specified by the first deployment recipe; and placing, by the orchestrator, the workload.

14. The method of claim 13 , further comprising monitoring, by metrics collection logic, performance; and updating, by the data analysis logic, the first deployment rule if a performance parameter is not at the target performance value.

15. A non-transitory computer readable storage device having stored thereon instructions that when executed by one or more processors result in the following operations comprising:
generating a plurality of deployment recipes identifying physical and virtual resources usable to implement a plurality of deployment configurations to test a workload configured based on an intended use of the resources, and determining test intervals specific to each of the plurality of deployment configurations based on the test intervals based on at least one type of resource included in each of the plurality of deployment configurations;
testing each of a plurality of deployment configurations utilizing at least the identified resources to process the workload over the interval;
collecting telemetry data for each deployment configuration;
determining deployment heuristics utilizing performance parameters determined based at least on the telemetry data; and
determining a deployment rule based, at least in part, on the deployment heuristics.

16. The device of claim 15 , wherein the instructions that when executed by one or more processors results in the following additional operations comprising allocating each of the plurality of deployment configurations in a resource pool.

17. The device of claim 15 , wherein the instructions that when executed by one or more processors results in the following additional operations comprising determining an efficiency value for each deployment rule of a plurality of deployment rules.

18. The device of claim 17 , wherein the instructions that when executed by one or more processors results in the following additional operations comprising ranking each deployment rule based, at least in part, on respective efficiency values.

19. The device of claim 15 , wherein the instructions that when executed by one or more processors results in the following additional operations comprising determining a first deployment recipe based, at least in part, on a target performance value and based, at least in part, on a first deployment rule associated with a workload.

20. The device of claim 19 , wherein the instructions that when executed by one or more processors results in the following additional operations comprising allocating resources specified by the first deployment recipe; and placing the workload.

21. The device of claim 20 , wherein the instructions that when executed by one or more processors results in the following additional operations comprising monitoring performance; and updating the first deployment rule if a performance parameter is not at the target performance value.

Assignees

• Intel Corp

Inventors

• Mcgrath Michael J
• Riccobene Vincenzo M

Classifications

• G06F9/50 Primary

  Allocation of resources, e.g. of the central processing unit [CPU] · CPC title

• G06F11/36

  Prevention of errors by analysis, debugging or testing of software · CPC title

• G06F9/44505

  Configuring for program initiating, e.g. using registry, configuration files · CPC title

• G06F9/5055

  considering software capabilities, i.e. software resources associated or available to the machine · CPC title

• G06F9/5083

  Techniques for rebalancing the load in a distributed system · CPC title