Automated cloud resource trading system

• US 9,294,236 B1
• Filed: 03/27/2012
• Issued: 03/22/2016
• Est. Priority Date: 03/27/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Ward, David John Jr.
• Primary Examiner(s): Joo, Joshua
• Assistant Examiner(s): Naji, Younes
• Application Number:
  US13/431,355
• Time in Patent Office: 1,456 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06Q 30/0645 Rental transactions; Leasing transactions
• CPC Class Codes: H04L 1/20 using signal quality detector
• CPC Class Codes: H04L 5/00 Arrangements affording multiple use of the transmission path
• CPC Class Codes: H04L 5/0035 Resource allocation in a cooperative multipoint environment
• CPC Class Codes: H04L 65/40 Support for services or applications
• 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 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Methods and apparatus for an automated cloud resource trading system are disclosed. A system includes a plurality of resource instances, a resource manager, and a pricing optimizer. The resource manager receives an indication that a client has opted in for automated implementation of recommendations from the pricing optimizer. In response to the opt-in indication, and a recommendation generated by the pricing optimizer based at least in part on an analysis of the client'"'"'s resource usage and the pricing of instances reserved for the client, the resource manager includes a particular resource instance currently reserved for the client in a listing of instances available for reservation by other clients.

Claims

1. A system, comprising:

a plurality of computing devices configured to implement a plurality of resource instances of a provider network;

one or more computing devices configured to implement a pricing optimizer; and

one or more computing devices configured to implement a resource manager;

wherein the resource manager is configured to;

in response to an indication that a first client has opted in for automated implementation of a recommendation from the pricing optimizer and in response to a recommendation generated by the pricing optimizer based at least in part on an analysis of resource usage by the first client and at least in part on a pricing of a set of resource instances reserved for the first client;

include a particular resource instance of the set of resource instances reserved for the first client in a listing of resource instances available for reservation by other clients of the provider network; and

in response to a resell event, remove the particular resource instance from the set of resource instances reserved for the first client.

2. The system as recited in claim 1, wherein the resource manager is further configured to:

identify, based at least in part on the recommendation, a second resource instance of the plurality of resource instances usable by the first client in accordance with a pricing optimization goal of the first client; and

reserve the second resource instance for the first client.

3. The system as recited in claim 2, wherein each resource instance of the plurality of resource instances belongs to an availability zone of a plurality of availability zones of the provider network, and wherein the second resource instance belongs to a different availability zone than the particular resource instance.

4. The system as recited in claim 1, wherein the resell event comprises a reservation of the particular resource instance by a different client.

5. The system as recited in claim 1, further comprising one or more computing devices configured to implement an interface manager configured to:

implement a programmatic interface allowing a client to opt in for automated implementation of one or more recommendations from the pricing optimizer;

wherein the indication that the first client has opted in for automated implementation of the recommendation from the pricing optimizer is received in accordance with the programmatic interface.

6. The system as recited in claim 1, further comprising one or more computing devices configured to implement an interface manager configured to:

implement a programmatic interface allowing a client to specify an optimization goal comprising at least one of;

(a) a resource budget constraint or (b) an instance availability count goal;

wherein the recommendation is generated in accordance with a particular optimization goal specified by the first client via the programmatic interface.

7. The system as recited in claim 1, wherein the provider network comprises a service configured to provide the plurality of resource instances as virtual compute instances provisioned for requesting clients, wherein a given one of the plurality of computing devices is configured to host different virtual compute instances for different clients of the service, and wherein, in response to the resell event, the resource manager is configured to reserve the particular resource instance for another client.

10. The method as recited in claim 7, further comprising:

identifying, based at least in part on the notification, a second resource instance of the plurality of resource instances usable by the first client in accordance with an optimization goal of the first client; and

reserving the second resource instance for the first client.

11. The method as recited in claim 10, wherein each resource instance of the plurality of resource instances belongs to an availability zone of a plurality of availability zones of the provider network, and wherein the second resource instance belongs to a different availability zone than the particular resource instance.

8. A method, comprising:

receiving an indication that a first client of a provider network has sent an opt-in request that requests automated implementation of instance reservation actions recommended based at least in part on an analysis of resource usage by the first client, wherein the provider network comprises a plurality of resource instances;

receiving a notification of one or more instance reservation actions recommended for the first client;

in response to the notification and in response to the opt-in request, automatically implement the one or more instance reservation actions, comprising including a particular resource instance of a set of resource instances of the plurality of resource instances reserved for the first client in a listing of resource instances available for reservation by other clients of the provider network;

receive an opt-out request from a second client of the provider network that requests no automatic implementation of instance reservation recommendations that are based at least in part on an analysis of resource usage by the second client; and

after receiving the opt-out request, receive a request from the second client to reserve the particular resource instance.

9. The method as recited in claim 8, further comprising:

in response to a resell event comprising the request from the second client to reserve the particular resource instance, removing the particular resource instance from the set of resource instances reserved for the first client.

12. The method as recited in claim 8, further comprising:

implementing a programmatic interface allowing a client to opt in for automated implementation of one or more recommendations;

wherein the indication that the first client has requested automated implementation of instance reservation actions is received in accordance with the interface.

13. The method as recited in claim 8, further comprising:

implementing a programmatic interface allowing a client to specify one or more optimization goals including at least one of (a) a resource budget constraint or (b) an instance count availability goal;

wherein the one or more instance reservation actions recommended for the first client are determined based at least in part on an optimization goal specified via the programmatic interface.

14. The method as recited in claim 8, further comprising:

receiving an indication of one or more availability zone preferences of the first client;

wherein the one or more instance reservation actions recommended for the first client are determined based at least in part on the one or more availability zone preferences.

15. The method as recited in claim 8, further comprising:

implementing a programmatic interface allowing a client to specify a scheduling preference for automated implementation of instance reservation actions; and

performing one or more recommended instance reservation actions in accordance with a scheduling preference specified by the first client via the programmatic interface.

16. The method as recited in claim 8, further comprising:

in response to a second notification of one or more instance reservation actions recommended for the first client, removing the particular resource instance from the listing of resource instances available for reservation by other clients of the provider network.

17. A non-transitory computer-accessible storage medium storing program instructions, that when executed on one or more processors, cause the one or more processors to:

receive an opt-in request from a first client of a provider network that requests automated implementation of instance reservation recommendations that are based at least in part on an analysis of resource usage by the first client, wherein the provider network comprises a plurality of resource instances;

after receiving the opt-in request, receive a notification of one or more instance reservation recommendations for the first client;

in response to the notification and in response to the opt-in request, automatically implement the one or more instance reservation recommendations, comprising reserving a first instance of the plurality of resource instances for the first client;

receive an opt-out request from a second client of the provider network that requests no automatic implementation of instance reservation recommendations that are based at least in part on an analysis of resource usage by the second client; and

after receiving the opt-out request, receive a request from the second client to reserve one or more instances of the plurality of resource instances.

18. The storage medium as recited in claim 17, wherein automatically implementing the one or more instance reservation recommendations further comprises:

including a second resource instance reserved for the first client in a listing of resource instances available for reservation by other clients of the provider network.

19. The storage medium as recited in claim 18, wherein automatically implementing the one or more instance reservation recommendations further comprises:

in response to a resell event, removing the second resource instance from a set of resource instances reserved for the first client.

20. The storage medium as recited in claim 19, wherein the resell event comprises a reservation of the second resource instance by a different client.

21. The storage medium as recited in claim 18, wherein each resource instance of the plurality of resource instances belongs to an availability zone of a plurality of availability zones of the provider network, and wherein the second resource instance belongs to a different availability zone than the first resource instance.

22. The storage medium as recited in claim 17, wherein the instructions, when executed on the one or more processors, cause the one or more processors to:

implement a programmatic interface allowing a client to opt in for automated implementation of one or more recommendations;

wherein the opt-in request is received in accordance with the interface.

23. The storage medium as recited in claim 17, wherein the instructions, when executed on the one or more processors, cause the one or more processors to:

implement a programmatic interface allowing a client to specify one or more optimization goals including at least one of;

a resource budget constraint or an instance count availability goal;

wherein the one or more instance reservation recommendations are determined based at least in part on an optimization goal specified via the programmatic interface.

24. The storage medium as recited in claim 17, wherein the instructions, when executed on the one or more processors, cause the one or more processors to:

implement a programmatic interface allowing a client to specify a scheduling preference for automated implementation of instance reservation recommendations,

wherein the one or more instance reservation recommendations are implemented in accordance with a scheduling preference specified by the client via the programmatic interface.

25. The storage medium as recited in claim 17, wherein the instructions when executed on the one or more processors, cause the one or more processors to:

in response to a second notification of a reservation recommendation for the first client, remove a particular resource instance from a listing of resource instances available for reservation by other clients of the provider network, wherein the particular resource instance was placed on the listing in accordance with an other notification of a reservation recommendation for the first client.