Dynamically modifying program execution capacity

• US 8,352,609 B2
• Filed: 09/29/2009
• Issued: 01/08/2013
• 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, Geoffry Scott, Heitmann, John W., Lohia, Sumit, Chen, Liang, Musgrave, Zachary S.
• Primary Examiner(s): Lazaro, David
• Assistant Examiner(s): KIM, EDWARD J
• Application Number:
  US12/569,723
• Publication Number:
  US 20110078411A1
• Time in Patent Office: 1,197 Days
• Field of Search: 709201-207, 709212-215, 709217-222, 709223-226, 709/227, 709/229, 709/230, 709232-235, 709/249
• US Class Current: 709/226
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: G06F 9/5061 Partitioning or combining of resources
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/04 Billing or invoicing
• 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 67/34 involving the movement of software or configuration parameters network booting or remote initial program loading [RIPL] G06F9/4416
• CPC Class Codes: Y04S 10/50 Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

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, and with the aggregation of multiple determined modifications being able to be performed in various manners. Modifications may be requested or otherwise determined in various manners, including based on dynamic instructions specified by the user, and on satisfaction of triggers that are previously defined by the user. In some situations, the techniques are 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 computing system configured to dynamically modify program execution capacity for a user, comprising:

one or more processors; and

a system manager module that includes software instructions stored on memory and that is configured to, when executed by at least one of the one or more processors, manage program execution capacity for multiple users of a network-accessible service by, for each of the multiple users;

determining a desired program execution capacity for use in executing one or more software programs on behalf of the user, and determining a capacity modification trigger for use in later initiating automated modifications to the desired program execution capacity for the user, the capacity modification trigger including a execution capacity quantity change if the capacity modification trigger is satisfied;

associating a group of multiple available computing nodes with the user at a first time for use in providing the determined desired program execution capacity to the user; and

after the first time,

determining an actual program execution capacity that is available to the user from the computing nodes of the group at a later second time after the first time, the actual program execution capacity at the second time being distinct from the desired program execution capacity provided to the user at the first time;

determining a modified desired program execution capacity to be provided to the user at the second time based on multiple independent events that occur after the first time, the multiple independent events including the capacity modification trigger being determined to be satisfied and including a capacity modification instruction that is dynamically specified by the user with a user-specified capacity modification amount, the modified desired program execution capacity at the second time being based at least in part on the user-specified capacity modification amount and the execution capacity quantity change for the capacity modification trigger; and

modifying the computing nodes that are part of the group at the second time to harmonize the modified desired program execution capacity at the second time with the determined actual program execution capacity at the second time.

2. The computing system of claim 1 wherein the determined desired program execution capacity for one of the multiple users is indicated by the one user and is identified as an initial official program execution capacity that is recorded as being available to the one user at the first time, wherein the determining of the actual program execution capacity that is available to the one user at the second time is based at least in part on monitoring the computing nodes of the group for the one user during a period of time from the first time to the second time so as to identify one or more changes, the monitoring of the computing nodes including updating the recorded official program execution capacity that is available to the one user to reflect the one or more changes, wherein the recorded official program execution capacity that is available to the one user is not updated based on the determining of the modified desired program execution capacity at the second time, and wherein the modifying of the computing nodes that are part of the group at the second time is further performed so as to harmonize the recorded official program execution capacity at the second time with the modified desired program execution capacity at the second time, the harmonizing of the recorded official program execution capacity including identifying the modified desired program execution capacity at the second time as a further updated recorded official program execution capacity that is available to the one user.

3. The computing system of claim 2 wherein the determined capacity modification trigger for the one user is specified by the one user, wherein the network-accessible service is a program execution service that provides a plurality of computing nodes configurable to execute programs of remote users of the program execution service, and wherein the multiple computing nodes of the group for each of at least one of the multiple users are a subset of the plurality of computing nodes.

4. The computing system of claim 1 wherein the system manager module consists of a means for performing the managing of the program execution capacity for the multiple users of the network-accessible service.

5. A computer-implemented method comprising:

determining, by one or more configured computing systems of a network-accessible service, a desired program execution capacity for use in executing one or more software programs on behalf of a user, and a capacity modification trigger for use in later initiating automated modifications to the desired program execution capacity, the capacity modification trigger including a execution capacity quantity change if the capacity modification trigger is satisfied;

associating, by the one or more configured computing systems, a group of multiple available computing nodes with the user at a first time for use in providing the determined desired program execution capacity; and

after the first time,

determining, by the one or more configured computing systems, an actual program execution capacity that is available from the computing nodes of the group at a later second time after the first time, the actual program execution capacity at the second time being distinct from the desired program execution capacity provided at the first time;

determining, by the one or more configured computing systems, a modified desired program execution capacity to be provided at the second time based on multiple independent events that occur after the first time, the multiple independent events including the capacity modification trigger being determined to be satisfied and including a capacity modification instruction that is dynamically specified by the user with a user-specified capacity modification amount, the modified desired program execution capacity at the second time being based at least in part on the user-specified capacity modification amount and the execution capacity quantity change for the capacity modification trigger; and

modifying, by the one or more configured computing systems, the computing nodes that are part of the group at the second time to harmonize the modified desired program execution capacity at the second time with the determined actual program execution capacity at the second time.

6. The computer-implemented method of claim 5 wherein the determined desired program execution capacity is indicated by the user, and wherein the determining of the actual program execution capacity that is available to the user at the second time is based at least in part on monitoring the computing nodes of the group between the first time and the second time to identify one or more changes.

7. The computer-implemented method of claim 6 wherein the determined desired program execution capacity is identified as an initial official program execution capacity that is recorded as available to the one user at the first time, wherein the monitoring of the computing nodes including updating the recorded official program execution capacity that is available to the one user to reflect the one or more changes, and wherein the modifying of the computing nodes that are part of the group at the second time is further performed to harmonize the recorded official program execution capacity at the second time with the modified desired program execution capacity at the second time, the harmonizing of the recorded official program execution capacity including identifying the modified desired program execution capacity at the second time as a further updated recorded official program execution capacity that is available to the user.

8. The computer-implemented method of claim 5 wherein the determined capacity modification trigger is specified by the user, wherein the network-accessible service is a program execution service that provides a plurality of computing nodes configurable to execute programs of remote users of the program execution service, and wherein the multiple computing nodes of the group are a subset of the plurality of computing nodes.

9. The computer-implemented method of claim 5 wherein program execution capacity of the group is measured based on a quantity of computing nodes that are part of the group, such that the determined desired program execution capacity is an initial desired quantity of computing nodes, the determined actual program execution capacity at the second time is an actual quantity of computing nodes that are available as part of the group at the second time, and the determined modified desired program execution capacity is a modified desired quantity of computing nodes for the group.

10. The computer-implemented method of claim 9 wherein the modifying of the computing nodes that are part of the group includes changing the actual quantity of the computing nodes that are part of the group to be the modified desired quantity.

11. The computer-implemented method of claim 9 wherein the execution capacity quantity change of the capacity modification trigger is a first indicated change in quantity of computing nodes of the group, and wherein the user-specified capacity modification amount is a second indicated change in quantity of computing nodes of the group.

12. The computer-implemented method of claim 11 wherein the determining of the modified desired program execution capacity for the group includes determining a third change in quantity of computing nodes of the group by aggregating the first and second indicated changes in quantity of computing nodes of the group, and modifying the initial desired quantity of computing nodes by the determined third change in quantity of computing nodes of the group.

13. The computer-implemented method of claim 12 wherein the aggregating of the first and second indicated changes in quantity of computing nodes of the group includes accumulating the first and second indicated changes in quantity.

14. The computer-implemented method of claim 12 wherein the aggregating of the first and second indicated changes in quantity of computing nodes of the group includes offsetting the first and second indicated changes in quantity.

15. The computer-implemented method of claim 12 wherein the aggregating of the first and second indicated changes in quantity of computing nodes of the group includes selecting a single one of the first and second indicated changes in quantity.

16. The computer-implemented method of claim 5 further comprising monitoring the computing nodes of the group to determine one or more values for at least one type of performance characteristic related to the executing of the one or more software programs, and determining that the capacity modification trigger is satisfied based at least in part on the determined values for the at least one type of performance characteristic.

17. The computer-implemented method of claim 16 wherein the at least one type of performance characteristic includes an actual quantity of computing nodes that is available as part of the group.

18. The computer-implemented method of claim 16 wherein the at least one performance characteristic type corresponds to a computing load on the computing nodes of the group.

19. The computer-implemented method of claim 16 wherein the multiple independent events further include a second capacity modification trigger being satisfied based on one or more patterns identified from historical data, and wherein the method further comprises automatically determining that the second specified capacity modification trigger is satisfied based at least in part on the determined values for the at least one type of performance characteristic corresponding to at least one of the one or more patterns.

20. The computer-implemented method of claim 5 wherein the multiple independent events further include a second capacity modification trigger being satisfied based on a current time matching one or more specified times.

21. A non-transitory computer-readable medium having stored contents that configure a computing system to perform a method, the method comprising:

determining, by the configured computing system, a desired program execution capacity for use in executing one or more software programs on behalf of a user, and a capacity modification trigger for use in later initiating automated modifications to the desired program execution capacity, the capacity modification trigger including a execution capacity quantity change if the capacity modification trigger is satisfied;

associating, by the configured computing system, a group of multiple available computing nodes with the user at a first time for use in providing the determined desired program execution capacity; and

after the first time,

determining, by the configured computing system, an actual program execution capacity that is available from the computing nodes of the group at a later second time after the first time, the actual program execution capacity at the second time being distinct from the desired program execution capacity provided at the first time;

determining, by the configured computing system, a modified desired program execution capacity to be provided at the second time based on multiple independent events that occur after the first time, the multiple independent events including the capacity modification trigger being determined to be satisfied and including a capacity modification instruction that is dynamically specified by the user with a user-specified capacity modification amount, the modified desired program execution capacity at the second time being based at least in part on the user-specified capacity modification amount and the execution capacity quantity change for the capacity modification trigger; and

modifying, by the configured computing system, the computing nodes that are part of the group at the second time to harmonize the modified desired program execution capacity at the second time with the determined actual program execution capacity at the second time.

22. The non-transitory computer-readable medium of claim 21 wherein the determined capacity modification trigger is specified by the user, wherein the configured computing system is part of a program execution service that provides a plurality of computing nodes configurable to execute programs of remote users of the program execution service, and wherein the multiple computing nodes of the group are a subset of the plurality of computing nodes.

23. The non-transitory computer-readable medium of claim 21 wherein program execution capacity of the group is measured based on a quantity of computing nodes that are part of the group, such that the determined desired program execution capacity is an initial desired quantity of computing nodes, the determined actual program execution capacity at the second time is an actual quantity of computing nodes that are available as part of the group at the second time, and the determined modified desired program execution capacity is a modified desired quantity of computing nodes for the group.

24. The non-transitory computer-readable medium of claim 21 wherein the determining of the modified desired program execution capacity includes accumulating the user-specified capacity modification amount and the execution capacity quantity change for the capacity modification trigger.

25. The non-transitory computer-readable medium of claim 21 wherein the determining of the modified desired program execution capacity includes offsetting the user-specified capacity modification amount and the execution capacity quantity change for the capacity modification trigger.

26. The non-transitory computer-readable medium of claim 21 wherein the determining of the modified desired program execution capacity includes selecting one of the user-specified capacity modification amount and the execution capacity quantity change for the capacity modification trigger.

27. The non-transitory computer-readable medium of claim 21 wherein the method further comprises monitoring the computing nodes of the group to determine one or more values for at least one type of performance characteristic related to the executing of the one or more software programs, and determining that the capacity modification trigger is satisfied based at least in part on the determined values for the at least one type of performance characteristic.

28. The non-transitory computer-readable medium of claim 27 wherein the at least one type of performance characteristic includes an actual quantity of computing nodes that is available as part of the group.

29. The non-transitory computer-readable medium of claim 27 wherein the at least one performance characteristic type corresponds to a computing load on the computing nodes of the group.

30. The non-transitory computer-readable medium of claim 27 wherein the multiple independent events further include a second capacity modification trigger being satisfied based on one or more patterns identified from historical data, and wherein the method further comprises automatically determining that the second specified capacity modification trigger is satisfied based at least in part on the determined values for the at least one type of performance characteristic corresponding to at least one of the one or more patterns.

31. The non-transitory computer-readable medium of claim 27 wherein the multiple independent events further include a second capacity modification trigger being satisfied based on a current time matching one or more specified times.