Attributing causality to program execution capacity modifications

• US 10,360,083 B2
• Filed: 05/09/2016
• Issued: 07/23/2019
• Est. Priority Date: 09/29/2009
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Maclinovsky, Alex, Meike, Blake, Buragohain, Chiranjeeb, Kommareddy, Christopher Reddy, Pare, Geoffrey Scott, Heitmann, John W., Lohia, Sumit, Chen, Liang
• Primary Examiner(s): Anya, Charles E
• Application Number:
  US15/150,251
• Publication Number:
  US 20160253224A1
• Time in Patent Office: 1,170 Days
• CPC Class Codes: G06F 2209/508 Monitor
• CPC Class Codes: G06F 9/50 Allocation of resources, e.g. of the central processing unit [CPU]
• CPC Class Codes: G06F 9/542 Event management; Broadcasting; Multicasting; Notifications
• CPC Class Codes: G06F 9/543 User-generated data transfer, e.g. clipboards, dynamic data exchange [DDE], object linking and embedding [OLE]
• CPC Class Codes: G06Q 20/085 involving remote charge determination or related payment systems
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0283 Price estimation or determination

Abstract

Techniques are described for managing program execution capacity, such as for a group of computing nodes that are provided for executing one or more programs for a user. In some situations, dynamic program execution capacity modifications for a computing node group that is in use may be performed periodically or otherwise in a recurrent manner, such as to aggregate multiple modifications that are requested or otherwise determined to be made during a period of time. In addition, various operations may be performed to attribute causality information or other responsibility for particular program execution capacity modifications that are performed, including by attributing a single event as causing one capacity modification, and a combination of multiple events as possible causes for another capacity modification. The techniques may in some situations be used in conjunction with a fee-based program execution service that executes multiple programs on behalf of multiple users of the service.

Claims

1. A non-transitory computer-readable medium including stored contents that, when executed, cause a computing system to:

receive a request for information regarding execution capacity changes that have occurred to a group of multiple computing nodes; and

in response to the request;

retrieve, by a Program Execution Service System Manager module (PESSM) of the computing system, information that was previously stored by a Program Execution Service Capacity Maintenance Manager module (PESCMM) as part of monitoring the group of multiple computing nodes;

identify, by the PESSM module of the computing system and based on the retrieved information, and for the group of multiple computing nodes that execute one or more software programs between a first time and a later second time and that have a change in an amount of program execution capacity being provided by the group of multiple computing nodes between the first time and the later second time, a plurality of events that occur between the first time and the later second time, wherein the plurality of events include satisfaction of a first capacity modification trigger that is based on a first performance characteristic and further include an independent satisfaction of a second capacity modification trigger that is based on a second performance characteristic, and wherein each of the first and second capacity modification triggers has an associated specified modification of program execution capacity;

determine, by the PESSM module of the computing system, a capacity modification trigger from the first and second capacity modification triggers that is satisfied to cause the change in the amount of program execution capacity;

determine, by the PESSM module of the computing system, one or more events of the plurality of events that are associated with the determined capacity modification trigger and the change in the amount of program execution capacity; and

provide, by the PESSM module of the computing system, information about the determined one or more events for the change in the amount of program execution capacity.

2. The non-transitory computer-readable medium of claim 1 wherein the stored contents include software instructions that, when executed, further cause the computing system to receive and store information about multiple capacity modification triggers that include the first and second capacity modification triggers, and to perform the change in the amount of program execution capacity of the group of multiple computing nodes by selecting the specified modification of program execution capacity associated with one of the first and second capacity modification triggers.

3. The non-transitory computer-readable medium of claim 2 wherein the stored contents further cause the computing system to select the first capacity modification trigger to use and to determine to not use the second capacity modification trigger for the change in the amount of program execution capacity of the group of multiple computing nodes.

4. The non-transitory computer-readable medium of claim 2 wherein the computing system is part of a program execution service that provides the group of multiple computing nodes for a user of the program execution service, wherein the stored contents further cause the computing system to receive information from the user to specify the first and second capacity modification triggers, and wherein the storing of the information about the capacity modification triggers is based at least in part on the received information from the user.

5. The non-transitory computer-readable medium of claim 4 wherein the receiving of the information from the user includes receiving, via a graphical user interface provided by the program execution service, information from the user for one or more parameter values to use with each of the first and second capacity modification triggers and instructions from the user to provide the group of multiple computing nodes for use by the user, and wherein the stored contents further cause the computing system to, in response to the instructions, select the multiple computing nodes for the group of multiple computing nodes from a plurality of computing nodes provided by the program execution service, and provide the selected multiple computing nodes for use by the user.

6. The non-transitory computer-readable medium of claim 4 wherein the receiving of the information from the user includes receiving, via one or more programmatic interfaces provided by the program execution service, instructions from a computing device of the user to provide the group of multiple computing nodes for use by the user and to implement the first capacity modification trigger for use with the group of multiple computing nodes, and wherein the stored contents further cause the computing system to, in response to the instructions, provision the multiple computing nodes for use in the group of multiple computing nodes, and provide the provisioned multiple computing nodes for use by the user.

7. The non-transitory computer-readable medium of claim 2 wherein the change in the amount of program execution capacity is based at least in part on a combination of the amounts of program execution capacity modification associated with the first capacity modification trigger and with a third capacity modification trigger that is satisfied.

8. The non-transitory computer-readable medium of claim 2 wherein the computing system is part of a program execution service that provides the group of multiple computing nodes for a user of the program execution service, wherein the stored contents further cause the computing system to receive, from the user and after the first time while the group of multiple computing nodes is executing the one or more software programs, instructions to modify the program execution capacity being provided by the group of multiple computing nodes, and wherein an additional one of the determined multiple events corresponds to implementation by the program execution service of the instructions.

9. The non-transitory computer-readable medium of claim 1 wherein the change in the amount of program execution capacity being provided by the group of multiple computing nodes includes a change in quantity of computing nodes in the group of multiple computing nodes, and wherein the providing of the information includes identifying multiple events together as a cause of the change in the amount of program execution capacity.

10. The non-transitory computer-readable medium of claim 9 wherein the identifying of the multiple events as the cause of the change in the amount of program execution capacity includes identifying a combination of the multiple events as the cause.

11. The non-transitory computer-readable medium of claim 9 wherein the determining of the one or more events includes identifying the satisfaction of the first capacity modification trigger as one of the multiple events and not identifying the satisfaction of the second capacity modification trigger as one of the multiple events.

12. The non-transitory computer-readable medium of claim 9 wherein the determining of the one or more events includes selecting a subset of only some of the plurality of events as the determined one or more events, the subset including the satisfaction of the first capacity modification trigger and not including the satisfaction of the second capacity modification trigger.

13. A computer-implemented method, comprising:

providing, by one or more configured computing systems that provide a program execution service, a group of multiple computing nodes that provides program execution capacity at a first time for executing one or more software programs for a user of the program execution service;

receiving, by the one or more configured computing systems, a request for information regarding execution capacity changes that have occurred to the group of multiple computing nodes; and

in response to the request;

retrieving, by a Program Execution Service System Manager (PESSM) of the one or more configured computing systems, information that was previously stored by a Program Execution Service Capacity Maintenance Manager (PESCMM) as part of monitoring the group of multiple computing nodes;

identifying, by the PESSM of the one or more configured computing systems and based on the retrieved information, a plurality of events that occur between the first time and a later second time while the group of multiple computing nodes is executing the one or more software programs and that each is capable of resulting in a modification of the program execution capacity being provided by the group of multiple computing nodes, wherein the plurality of events include satisfaction of a first capacity modification trigger that is based on a first performance characteristic and an independent satisfaction of a second capacity modification trigger that is based on a second performance characteristic, and wherein each of the first and second capacity modification triggers has an associated specified modification of program execution capacity;

determining, by the PESSM of the one or more configured computing systems, a capacity modification trigger from the first and second capacity modification triggers that is satisfied to cause change in an amount of program execution capacity being provided by the group of multiple computing nodes between the first time and the later second time;

determining, by the PESSM of the one or more configured computing systems, multiple events of the plurality of events that are associated with the determined capacity modification trigger; and

providing, by the PESSM of the one or more configured computing systems, information identifying a combination of the determined multiple events as a cause of the change in the amount of program execution capacity being provided by the group of multiple computing nodes.

14. The computer-implemented method of claim 13 wherein the determined multiple events include a capacity modification request specified by the user after the first time for an indicated modification to the program execution capacity being provided by the group of multiple computing nodes, and wherein the determined multiple events include implementation of the capacity modification request.

15. The computer-implemented method of claim 13 further comprising receiving configuration information from the user before the first time that specifies multiple capacity modification triggers for use in later initiating automated modifications to the program execution capacity provided by the group of multiple computing nodes if one or more specified criteria are satisfied, wherein the multiple capacity modification triggers include a first capacity modification trigger with a first threshold for a first performance characteristic and a second capacity modification trigger with a second threshold for a second performance characteristic, wherein the determining of the multiple events includes selecting the satisfaction of the first capacity modification trigger as one of the multiple events and not selecting the satisfaction of the second capacity modification trigger as one of the multiple events.

16. The computer-implemented method of claim 13 wherein the program execution capacity of the group of multiple computing nodes is measured based on a quantity of computing nodes that are part of the group of multiple computing nodes, and wherein the change in the amount of program execution capacity being provided by the group of multiple computing nodes includes one or more computing nodes of the group of multiple computing nodes becoming unavailable or one or more additional computing nodes being added to the group of multiple computing nodes.

17. The computer-implemented method of claim 13 wherein the program execution service provides multiple physical computing systems that each hosts one or more virtual machines for use by users of the program execution service, and wherein the providing of the group of multiple computing nodes includes selecting, by the one or more configured computing systems, one or more virtual machines hosted on one or more of the multiple physical computing systems to include in the group of multiple computing nodes, and provisioning the selected one or more virtual machines for use by the user.

18. A system comprising:

one or more hardware processors of one or more computing systems; and

one or more memories with stored instructions that, when executed by at least one of the one or more hardware processors, cause the at least one hardware processor to;

execute one or more software programs for a user on a group of multiple computing nodes;

receive a request for information regarding execution capacity changes that have occurred to the group of multiple computing nodes; and

in response to the request;

retrieving, by a Program Execution Service System Manager (PESSM) of the one or more configured computing systems, information that was previously stored by a Program Execution Service Capacity Maintenance Manager (PESCMM) as part of monitoring the group of multiple computing nodes;

identify, by the PESSM and based on the retrieved information, a plurality of events that occur between a first time and a later second time while the group of multiple computing nodes is executing the one or more software programs and that are associated with a change in an amount of program execution capacity being provided by the group of multiple computing nodes between the first time and the later second time, wherein the plurality of events include satisfaction of a first capacity modification trigger with a first threshold for a first performance characteristic and further include a separate and independent satisfaction of a second capacity modification trigger with a second threshold for a second performance characteristic, and wherein each of the first and second capacity modification triggers has an associated specified modification of program execution capacity if used to cause changes to program execution capacity being provided;

determine, by the PESSM, to use the first capacity modification trigger to contribute to the change in the amount of program execution capacity for the group of multiple computing nodes and to not use the second capacity modification trigger to contribute to the change in the amount of program execution capacity for the group of multiple computing nodes; and

provide, by the PESSM, information about one or more events of the plurality of events that are a cause of the change in the amount of program execution capacity, wherein the one or more events include the satisfaction of the first capacity modification trigger and do not include the satisfaction of the second capacity modification trigger.

19. The system of claim 18 wherein the one or more events include multiple events, and wherein the stored instructions are at least part of a program execution service and further cause the at least one processor to determine, before the providing of the information, the multiple events based on the multiple events being associated together as a combination with the change in the amount of program execution capacity.

20. The system of claim 18 wherein the stored instructions further cause the at least one processor to:

receive, before the executing of the one or more software programs, information from the user that requests the multiple computing nodes be provided for the group of multiple computing nodes and that specifies one or more capacity modification triggers for use in later initiating automated modifications to the program execution capacity provided by the group of multiple computing nodes, the one or more capacity modification triggers including at least one of the first and second capacity modification triggers;

provide the multiple computing nodes for the user; and

implement, based on the determining, and to the program execution capacity provided by the group of multiple computing nodes, the specified modification of program execution capacity associated with the first capacity modification trigger.