Optimized deployment based upon customer locality

• US 10,467,042 B1
• Filed: 01/29/2019
• Issued: 11/05/2019
• Est. Priority Date: 04/27/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Mercier, Benjamin W., Fitzgerald, Joseph E., Brandwine, Eric J., Theimer, Marvin M.
• Primary Examiner(s): Rashid, Wissam
• Application Number:
  US16/261,401
• Time in Patent Office: 280 Days
• Field of Search: None
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2009/45595 Network integration; Enabling network access in virtual machine instances
• CPC Class Codes: G06F 8/60 Software deployment
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• 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 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/34 involving the movement of software or configuration parameters network booting or remote initial program loading [RIPL] G06F9/4416
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal

Abstract

The deployment of content and computing resources for implementing a distributed software application can be optimized based upon customer location. The volume and geographic origin of incoming requests for a distributed software application are determined. Based upon the volume and geographic origin of the incoming requests, content and/or one or more instances of the distributed software application may be deployed to a geographic region generating a significant volume of requests for the distributed software application. Content and/or instances of a distributed software application might also be speculatively deployed to a geographic region in an attempt to optimize the performance, cost, or other attribute of a distributed software application.

Claims

1. A computer-implemented method for optimizing deployment of one or more virtual machine instances of a network-based application over a distributed network, the computer-implemented method comprising:

determining a number of requests for communication with a network-based application by one or more computers over a network, wherein the network-based application is one of a plurality of distributed software applications executed by at least one of a plurality of virtual machine instances at a data center in a network-based environment;

determining a geographic location from which each of the requests originates;

determining a first geographic region meeting a predetermined number of requests for the network-based application based upon the number of the requests and the geographic location from which each of the requests originates;

determining a cost associated with deploying one or more instances of the network-based application to the first geographic region meeting the predetermined number of requests;

determining whether to deploy the one or more instances of the network-based application to the first geographic region meeting the predetermined number of requests based upon the determined cost and the number of incoming requests;

responsive to determining the first geographic region meeting the predetermined number of requests for the network-based application, deploying the one or more instances of the network-based application to the first geographic region;

determining an updated number of requests received for the network-based application from the first geographic region; and

terminating at least one of the instances of the network-based application deployed to the first geographic region based upon the updated number of requests received for the network-based application from the first geographic region.

2. The computer-implemented method of claim 1, wherein deploying one or more instances of the network-based application comprises deploying one or more virtual machine instances executing the network-based application to the first geographic region meeting the predetermined number of requests.

3. The computer-implemented method of claim 2 further comprising causing the deployed virtual machine instances to execute in the first geographic region meeting the predetermined number of requests and to handle requests for the network-based application generated from within the first geographic region.

4. The computer-implemented method of claim 1, wherein deploying one or more instances of the network-based application comprises deploying content served by the network-based application together with the one or more instances of the network-based application to the first geographic region meeting the predetermined number of requests.

5. The computer-implemented method of claim 4, wherein deploying one or more instances of the network-based application further comprises deploying one or more virtual machine instances configured to serve the content to the first geographic region meeting the predetermined number of requests.

6. The computer-implemented method of claim 5 further comprising causing the deployed virtual machine instances to execute in the first geographic region meeting the predetermined number of requests and to handle requests for the content generated from within the first geographic region.

7. The computer-implemented method of claim 6, wherein causing the deployed virtual machine instances to handle requests for the content generated from within the first geographic region comprises modifying settings in one or more load balancers.

8. The computer-implemented method of claim 6, wherein causing the deployed virtual machine instances to handle requests for the content generated from within the first geographic region comprises modifying entries in one or more domain name servers.

9. The computer-implemented method of claim 6, wherein causing the deployed virtual machine instances to handle requests for the content generated from within the first geographic region comprises modifying one or more hyperlinks.

10. The computer-implemented method of claim 1, wherein the geographic location from which each of the requests originates is determined based upon an Internet Protocol (IP) address associated with each of the incoming requests.

11. The computer-implemented method of claim 1, wherein the deployment of the one or more instances of the network-based application is further based upon a network route of the incoming requests for the network-based application.

12. A computer system comprising:

a plurality of server computers executing a distributed software application on a plurality of virtual machine instances at a data center in a networked-based environment; and

a computer in communication with the plurality of server computers over a network, wherein the computer executes a deployment component configured to;

determine a first geographic region meeting a predetermined number of requests for communication with the distributed software application over a network;

determine a cost associated with deploying one or more instances of the network-based application to the first geographic region meeting the predetermined number of requests;

responsive to determining the first geographic region, deploy the one or more instances of the distributed software application to the first geographic region based upon the determined cost and the number of incoming requests;

determine an updated number of requests received for the distributed software application from the first geographic region; and

terminate at least one of the instances of the distributed software application deployed to the first geographic region based upon the updated number of requests.

13. The computer system of claim 12, wherein determining a first geographic region meeting a predetermined number of requests for communication with the distributed software application comprises:

determining a number of incoming requests for the distributed software application;

determining a geographic location from which each of the incoming requests originates; and

determining a first geographic region meeting a predetermined number of requests for communication with the distributed software application based upon the number of the incoming requests and the geographic location from which each of the incoming requests originates.

14. The computer system of claim 12, wherein the determination as to whether to terminate at least one of the instances of the distributed software application deployed to the first geographic region is further based upon a cost of terminating the at least one of the instances.

15. The computer system of claim 12, wherein the deployment component is further configured to:

determine a cost associated with deploying the one or more instances of the distributed software application to the first geographic region meeting the predetermined number of requests; and

determine whether to deploy the one or more instances of the distributed software application to the first geographic region meeting the predetermined number of requests based upon the determined cost and the number of incoming requests.

16. The computer system of claim 12, wherein the deployment component is further configured to:

deploy one or more instances of the distributed software application to a second geographic region;

measure an impact of the speculative deployment of the one or more instances of the distributed software application to the second geographic region;

maintain the instances of the distributed software application deployed to the second geographic region in response to measuring a first impact; and

terminate the instances of the distributed software application deployed to the second geographic region in response to measuring a second impact.

17. A non-transitory computer-readable storage medium having computer-executable instructions stored thereupon which, when executed by a computer, cause the computer to:

determine a first geographic region meeting a predetermined number of requests for a network-based application based upon a number of requests received over a network for the network-based application and a geographic location from which each of the requests originates, wherein the network-based application is one of a plurality of distributed software applications executed by at least one of a plurality of virtual machine instances at a data center in a network-based environment;

determine a cost associated with deploying the one or more instances of the network-based application to the first geographic region meeting the predetermined number of requests;

determine whether to deploy the one or more instances of the network-based application to the first geographic region meeting the predetermined number of requests based upon the determined cost and the number of incoming requests; and

cause one or more instances of the network-based application to be deployed to the first geographic region.

18. The computer-readable storage medium of claim 17, wherein causing one or more instances of the application to be deployed comprises deploying, over a network, one or more virtual machine instances executing the network-based application to the first geographic region.

19. The computer-readable storage medium of claim 17, having further computer-executable instructions stored thereupon which, when executed by the computer, cause the computer to:

periodically determine an updated number of requests for the network-based application received from the first geographic region; and

terminate at least one of the instances of the network-based application deployed to the first geographic region based upon the updated number of requests received for the network-based application from the first geographic region.