Simulating a production environment using distributed computing technologies

Patent metadata

Field	Value
Publication number	US-10496768-B2
Application number	US-201615254601-A
Country	US
Kind code	B2
Filing date	Sep 1, 2016
Priority date	Sep 1, 2016
Publication date	Dec 3, 2019
Grant date	Dec 3, 2019

Abstract

Systems and methods for query large database records are disclosed. An example method includes: selecting a user-specified test program for execution; determining one or more testing parameters associated with the user-specified test program; identifying, based on the one or more testing parameters, computing nodes within a distributed computing system; generating, based on the user-specified test program, a first plurality of computing tasks for execution by the computing nodes. The first plurality of computing tasks, when executed, generates a second plurality of computing requests to a server under test. The method also includes distributing execution of the first plurality of computing tasks across the computing nodes; and testing the server under test by causing the first plurality of computing tasks to be executed by the computing nodes.

First claim

What is claimed is:

1. A method, comprising:
selecting a user-specified test program for execution;
determining one or more testing parameters associated with the user-specified test program, wherein the one or more parameters indicate a load to a server under test;
identifying, based on the one or more testing parameters, computing nodes within a distributed computing system in a distributed testing environment;
generating, based on the user-specified test program, a first plurality of computing tasks for execution by the computing nodes, wherein the first plurality of computing tasks when executed generate a second plurality of computing requests that simulate the load on the server under test;
distributing execution of the first plurality of computing tasks across the computing nodes; and
testing the load on the server under test that executes the second plurality of computing requests in a production environment-by causing the first plurality of computing tasks to be executed by the computing nodes in the distributed testing environment.

2. The method of claim 1 , wherein the computing nodes include a name node and a plurality of data nodes managed by the name node.

3. The method of claim 2 , wherein distributing the execution of the first plurality of computing tasks comprises:
requesting the name node to distribute the execution of the plurality of computing tasks across the plurality of data nodes.

4. The method of claim 2 , wherein the plurality of computing requests, when executed, request responses from a first server application; and wherein the method further comprises:
detecting, using the name node, that the first server application is unresponsive; and
responsive to the detecting, automatically re-starting, using the name node, the first server application.

5. The method of claim 2 , wherein the plurality of computing requests, when executed, request responses from a first server application; and wherein the method further comprises:
detecting, using the name node, that the first server application provides a response time longer than a predefined response time; and
responsive to the detecting, automatically starting, using the name node, a second instance of the first server application.

6. The method of claim 5 , further comprising:
terminating an original instance of the first server application; and
measuring a response time of the second instance of the first server application.

7. The method of claim 6 , further comprising:
continuing the original instance of the first server application; and
determining a second response time of the first server application based on the response time of the original instance and a response time of the second instance.

8. The method of claim 1 , further comprising:
determining a performance indicator to be measured; and
generating the first plurality of computing tasks to provide a predefined number of computing requests.

9. The method of claim 1 , wherein causing the first plurality of computing tasks to be executed by the computing nodes comprises: causing the first plurality of computing tasks to be executed in a batch processing by the computing nodes.

10. The method of claim 1 , wherein the second plurality of computing requests comprises two or more types of computing tasks.

11. A system, comprising:
a non-transitory memory; and
one or more hardware processors coupled to the non-transitory memory and configured to execute instructions to perform operations comprising:
selecting a user-specified test program for execution to test a load on a server under test;
determining one or more testing parameters associated with the user-specified test program;
identifying, based on the one or more testing parameters, computing nodes within a distributed computing system used for testing a server under test;
distributing execution of the user-specified test program across the computing nodes; and
testing the load on the server under test using output generated by the user-specified test program by causing the user-specified test program to be executed by the computing nodes in the distributed computing system.

12. The system of claim 11 , wherein the operations further comprise:
measuring performance of the server under test based on execution of the user-specified test program by the computing nodes.

13. The system of claim 11 , wherein testing the server under test further comprises:
generating a predefined number of instances of the user-specified test program; and
causing the predefined number of instances of the user-specified test program to be executed by the computing nodes.

14. The system of claim 11 , wherein testing the server under test further comprises: causing the user-specified test program to be executed as part of a batch process job by the computing nodes.

15. The system of claim 11 , wherein the computing nodes include a name node and a plurality of data nodes managed by the name node.

16. The system of claim 15 , wherein distributing execution of the user-specified test program across the computing nodes comprises: requesting the name node to distribute the execution of a plurality of instances of the user-specified test program across the plurality of data nodes.

17. The system of claim 11 , wherein the distributed computing system includes a Hadoop distributed file system.

18. A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising:
selecting a user-specified test program for execution to test a load on a server under test;
determining one or more testing parameters associated with the user-specified test program;
identifying, based on the one or more testing parameters, computing nodes within a distributed computing system used for testing a server under test;
distributing execution of the user-specified test program across the computing nodes; and
testing the load on the server under test using output generated by the user-specified test program by causing the user-specified test program to be executed by the computing nodes in the distributed computing system.

19. The non-transitory machine-readable medium of claim 18 , wherein the computing nodes include a name node and a plurality of data nodes managed by the name node.

20. The non-transitory machine-readable medium of claim 19 , wherein distributing execution of the user-specified test program across the computing nodes comprises: requesting the name node to distribute the execution of a plurality of instances of the user-specified test program across the plurality of data nodes.

Assignees

• Paypal Inc

Inventors

• Zhang Pengshan
• Zhang Jun

Classifications

• H04L43/50 Primary

  Testing arrangements · CPC title

• G06F2111/02

  CAD in a network environment, e.g. collaborative CAD or distributed simulation · CPC title

• G06F30/20 Primary

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• G06F11/3414

  Workload generation, e.g. scripts, playback · CPC title

• 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