Managing operational throughput for shared resources

Patent metadata

Field	Value
Publication number	US-9374243-B1
Application number	US-201213620251-A
Country	US
Kind code	B1
Filing date	Sep 14, 2012
Priority date	Sep 14, 2010
Publication date	Jun 21, 2016
Grant date	Jun 21, 2016

Abstract

Usage of shared resources can be managed by enabling users to obtain different types of guarantees at different times for various types and/or levels of resource capacity. A user can select to have an amount or rate of capacity dedicated to that user. A user can also select reserved capacity for at least a portion of the requests, tasks, or program execution for that user, where the user has priority to that capacity but other users can utilize the excess capacity during other periods. Users can alternatively specify to use the excess capacity or other variable, non-guaranteed capacity. The capacity can be for any appropriate functional aspect of a resource, such as computational capacity, throughput, latency, bandwidth, and storage. Users can submit bids for various types and combinations of excess capacity, and winning bids can receive dedicated use of the excess capacity for at least a period of time.

First claim

What is claimed is:

1. A computer-implemented method for managing shared resources, comprising:
receiving an instance request that includes a request parameter, the instance request associated with a user of a multi-tenant computing environment, the multi-tenant computing environment including a plurality of client devices in communication via a network with one or more servers and storage devices, the instance request indicating a data set and a performance specification for responding to data requests for the data set, the performance specification indicating a latency target to be met for responding to at least one of the data requests for the data set;
determining an amount of latency of processing at least one of the data requests;
determining that the amount of latency is greater than the latency target as indicated by the performance specification;
identifying another storage device having additional capacity, the another storage device being associated with a resource usage request for the additional capacity;
determining whether the request parameter satisfies the resource usage request;
in response to determining that the request parameter satisfies the resource usage request, moving at least a subset of the data set from a current storage device to the another storage device; and
in response to determining that the request parameter does not satisfy the resource usage request, denying the instance request.

2. The computer-implemented method of claim 1 , wherein the another storage device comprises a solid state drive.

3. The computer-implemented method of claim 2 , wherein determining hardware further includes identifying a hardware device.

4. The computer-implemented method of claim 1 , wherein:
the current storage device and the another storage device are from a set of storage devices managed by a program execution service; and
the instance request originated from a customer computing device from a customer of the program execution service.

5. The computer-implemented method of claim 4 , wherein the receiving an instance request is received by an application programming interface call.

6. The computer-implemented method of claim 1 , wherein:
the current storage device comprises a magnetic storage medium; and
the another storage device uses a non-magnetic storage medium.

7. A computer system for managing shared resources, comprising:
one or more processors; and
memory, including instructions executable by the one or more processors to cause the computer system to at least:
receive an instance request that includes a request parameter, the instance request associated with a user of a multi-tenant computing environment, the multi-tenant computing environment including a plurality of client devices in communication via a network with one or more servers and storage devices, the instance request indicating a data set and a user-specified performance requirement for responding to data requests for the data set;
determine, based at least in part on the user-specified performance requirement for responding to the data requests in connection with the data set, whether one or more current data resources collectively storing the data set respond to the data requests in accordance with the user-specified performance requirement, the user-specified performance requirement indicating a latency target to be met for responding to the data requests;
determine that the one or more current data resource fail to respond to the data requests in accordance with the user-specified performance requirement based at least in part on the latency target as indicated by the user-specified performance requirement;
identify another storage device having additional capacity, the another storage device being associated with a resource usage request for the additional capacity;
determine whether the request parameter satisfies the resource usage request;
in response to determining that the request parameter satisfies the resource usage request, transfer data from at least one of the one or more current data resources to at least one second data resource; and
in response to determining that the request parameter does not satisfy the resource usage request, deny the instance request.

8. The computer system of claim 7 , further comprising receiving the user-specified performance requirement by application programming interface call.

9. The computer system of claim 7 , wherein transferring data from the at least one of the one or more current data resources to at least one second data resource further comprises transferring data from non-solid state media to solid state media.

10. The computer system of claim 7 , wherein transferring data from the at least one of the one or more current data resources to at least one second data resource further comprises provisioning at least a portion of the second data resource to hold a data set transferred from the current data resource.

11. The computer system of claim 7 , wherein the instance request further comprises a request for a particular hardware storage medium.

12. The computer system of claim 11 , wherein the particular hardware storage medium is solid state storage.

13. A non-transitory computer-readable storage media having collectively stored thereon executable instructions that, when executed by one or more processors of a computer system, cause the computer system to at least:
receive an instance request that includes a request parameter, the instance request associated with a user of a multi-tenant computing environment, the multi-tenant computing environment including a plurality of client devices in communication via a network with one or more servers and storage devices, the instance request indicating a performance specification for responding to data requests, the performance specification indicating a latency target to be met for responding to the data requests;
determine whether a current storage resource processing the data requests meets the performance specification based at least in part on an amount of latency of processing the data requests;
identifying another storage device having additional capacity, the another storage device being associated with a resource usage request for the additional capacity;
determining whether the request parameter satisfies the resource usage request;
in response to determining that the request parameter satisfies the resource usage request, transfer responsibility for processing the data requests from the current storage resource to a second storage resource after determining the current storage resource fails to meet the performance specification, the second storage resource determined to meet the performance specification; and
in response to determining that the request parameter does not satisfy the resource usage request, denying the instance request.

14. The non-transitory computer-readable storage media of claim 13 , wherein:
the current storage resource and the at least one second data resource are from a set of storage devices managed by a control plane; and
the instance request is received by the control plane.

15. The non-transitory computer-readable storage media of claim 14 , wherein receiving an instance request further includes receiving the instance request by the control plane through an application programming interface call.

16. The non-transitory computer-readable storage media of claim 15 , wherein the instructions further comprise instructions that, when executed, cause the computer system to at least determine whether the performance specification indicates use of a so

Assignees

• Certain Tate Andrew
• Jain Sachin
• Marshall Bradley E
• Maniscalco Nicholas J
• Sivasubramanian Swaminathan
• Garman Matthew S
• Amazon Tech Inc

Inventors

• Certain Tate Andrew
• Jain Sachin
• Marshall Bradley E
• Maniscalco Nicholas J
• Sivasubramanian Swaminathan
• Garman Matthew S

Classifications

• G06Q40/06

  Asset management; Financial planning or analysis · CPC title

• G06T15/20

  Perspective computation · CPC title

• G06Q30/08

  Auctions · CPC title

• G06Q30/00 Primary

  Commerce · CPC title

• H04L15/16 Primary

  with keyboard co-operating with code discs · CPC title