Managing committed processing rates for shared resources

Patent metadata

Field	Value
Publication number	US-9342801-B2
Application number	US-74945110-A
Country	US
Kind code	B2
Filing date	Mar 29, 2010
Priority date	Mar 29, 2010
Publication date	May 17, 2016
Grant date	May 17, 2016

Abstract

Commitments against various resources can be dynamically adjusted for customers in a shared-resource environment. A customer can provision a data volume with a committed rate of Input/Output Operations Per Second (IOPS) and pay only for that commitment (plus any overage), for example, as well as the amount of storage requested. The customer can subsequently adjust the committed rate of IOPS by submitting an appropriate request, or the rate can be adjusted automatically based on any of a number of criteria. Data volumes for the customer can be migrated, split, or combined in order to provide the adjusted rate. The interaction of the customer with the data volume does not need to change, independent of adjustments in rate or changes in the data volume, other than the rate at which requests are processed.

First claim

What is claimed is:

1. A computer-implemented method of adjusting committed rates for customers of shared resources, comprising:
receiving a request to adjust a committed rate of input/output operations per second (IOPS) guaranteed to a customer in a data environment, wherein the IOPS are executed using guaranteed server capacity, wherein a portion of the guaranteed server capacity that is unused by the customer is available to at least one other customer, the request capable of specifying an adjusted committed rate, the request being received as a Web service request to at least one application programming interface (API);
when the request relates to decreasing the committed rate of IOPS:
reducing an amount of the guaranteed server capacity for the customer;

when the request relates to increasing the committed rate of TOPS:
committing at least an additional portion of server capacity to the customer; and
storing information for the adjusted committed rate to a non-transitory data store, wherein the adjusted committed request rate is capable of being supplied by a single determined instance of the type of server or a plurality of determined instances of the type of server, each of the plurality of determined instances of the type of server providing at least a portion of the requested committed request rate, and wherein each determined instances of the type of server is capable of having additional users sharing the determined instance of the type of server when request capacity for the determined instance of the type of server allows for the additional users.

2. The computer-implemented method of claim 1 , further comprising:
analyzing commitment information for a plurality of servers in the data environment as stored in a management data store.

3. The computer-implemented method of claim 1 , wherein if the data environment is unable to provide the adjusted committed rate, the request to adjust the committed rate of IOPS is denied.

4. A computer-implemented method of adjusting usage of shared servers, comprising:
receiving a request for an adjusted committed request rate guaranteed to a customer with respect to a type of server, the customer having a current committed request rate for servers of the type of server, wherein a portion of a capacity of the servers that is guaranteed to the customer and unused by the customer is available to at least one other customer, the request capable of specifying a committed request rate;
when the adjusted committed request rate is less than the current committed request rate, reduce the committed request rate for at least one instance of the type of server for the customer;
when the request relates to increasing the committed request rate,
commit at least a portion of an available committable rate capacity of at least one instance of the type of server to obtain the adjusted committed request rate; and

storing information for the adjusted committed request rate for the customer for use in managing a rate of request handling for the customer, wherein the adjusted committed request rate is capable of being supplied by a single determined instance of the type of server or a plurality of determined instances of the type of server, each of the plurality of determined instances of the type of server providing at least a portion of the requested committed request rate, and wherein each determined instances of the type of server is capable of having additional users sharing the determined instance of the type of server when request capacity for the determined instance of the type of server allows for the additional users.

5. The computer-implemented method of claim 4 , wherein the request is received from the customer or from a management component monitoring a usage by the customer.

6. The computer-implemented method of claim 4 , further comprising:
sending a message to the customer indicating whether the adjusted requested committed request rate is in effect.

7. The computer-implemented method of claim 4 , wherein
reducing the committed request rate includes reducing a number of instances of the type of server providing the committed request rate for the customer when a fewer number of instances of the type of server is available to provide the committed request rate.

8. The computer-implemented method of claim 4 , wherein
increasing or reducing the committed request rate includes moving at least one request handling commitment to a different instance of the type of server providing the committed request rate for the customer.

9. The computer-implemented method of claim 4 , wherein the customer is able to request an adjusted committed server rate that is substantially independent of a capacity of any single instance of the type of server.

10. The computer-implemented method of claim 4 , wherein the committed request rate for a type of server is a committed request rate of input/output operations per second (IOPS) for a data server.

11. The computer-implemented method of claim 4 , wherein each instance of the type of server is capable of supporting committed request rates for multiple customers, and wherein each instance of the type of server is capable of supporting requests for additional customers without committed request rates.

12. The computer-implemented method of claim 4 , wherein at least one instance of the type of server is configured to process requests for customers with uncommitted request rates using an uncommitted or unused portion of a capacity of the at least one instance of the type of server, and
wherein in an overload situation the requests for the customers with committed request rates are handled at a normal rate and the requests for the customers without committed request rates are slowed down to overcome the overload situation.

13. The computer-implemented method of claim 4 , wherein a customer with a committed request rate is able to exceed the committed request rate, and wherein any request over the committed request rate being handled at a rate for requests without rate commitments or at a blended rate between rates for requests with and without rate commitments.

14. The computer-implemented method of claim 4 , wherein determining an available committable request capacity of at least one instance of the type of server includes randomly contacting instances of the type of server for at least one of capacity or commitment information.

15. The computer-implemented method of claim 4 , further comprising:
charging the customer based at least in part on the adjusted committed request rate with respect to the type of server for the customer.

16. A computer-implemented method of adjusting usage of shared servers, comprising:
receiving a request for an adjusted committed rate of input/output operations per second (IOPS) guaranteed to a customer with respect to a type of server, wherein the IOPS are executed using servers of the type, wherein a portion of a capacity of the servers that is guaranteed to the customer and unused by the customer is available to at least one other customer, the customer having a current committed rate, the request capable of specifying an adjusted committed rate;
when the adjusted committed rate of IOPS is less than the current committed rate, reduce the committed rate for at least one instance of the type of server for the customer;
when the request for an adjusted committed rate of IOPS relates to increasing the committed rate, commit at least a portion of an available committable rate capacity of at least one instance of the type of server to obtain the adjusted committed rate; and
storing inform

Assignees

• Certain Tate Andrew
• Paterson-Jones Roland
• Hamilton James R
• Jain Sachin
• Garman Matthew S
• Sunderland David N
• Wei Danny
• Cattaneo Fiorenzo
• Amazon Tech Inc

Inventors

• Certain Tate Andrew
• Paterson-Jones Roland
• Hamilton James R
• Jain Sachin
• Garman Matthew S
• Sunderland David N
• Wei Danny
• Cattaneo Fiorenzo

Classifications

• G06Q30/0284 Primary

  Time or distance, e.g. usage of parking meters or taximeters · CPC title

• H04L47/83

  based on usage prediction · CPC title

• G06Q10/00 Primary

  Administration; Management · CPC title

• G06Q30/04

  Billing or invoicing · CPC title

• H04L67/10

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title