Executing programs based on user-specified constraints

• US 8,010,651 B2
• Filed: 08/09/2010
• Issued: 08/30/2011
• Est. Priority Date: 03/31/2006
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Hoole, Quinton R., Vermeulen, Allan H., Theimer, Marvin M., Cabrera, Luis Felipe, DeSantis, Peter N., Paterson-Jones, Roland
• Primary Examiner(s): Jacobs; Lashonda T
• Application Number:
  US12/853,087
• Publication Number:
  US 20100312871A1
• Time in Patent Office: 386 Days
• Field of Search: 709/223, 709/224, 709/203, 709/217, 709/219, 709/229
• US Class Current: 709/223
• CPC Class Codes: G06F 2209/506 Constraint
• CPC Class Codes: G06F 9/5044 considering hardware capabilities

Abstract

Techniques are described for managing execution of programs on multiple computing systems, such as based at least in part of user-specified constraints. For example, constraints related to execution of a program may be based on a desired relative location of a host computing system to execute a copy of the program with respect to an indicated target (e.g., computing systems executing other copies of the program or copies of another indicated program), on particular geographic locations, and/or on factors not based on location (e.g., cost of use of a particular computing system, capabilities available from a particular computing system, etc.). Some or all of the multiple computing systems may be part of a program execution service for executing multiple programs on behalf of multiple users, and each may provide multiple virtual machines that are each capable of executing one or more programs for one or more users.

Claims

1. A computer-implemented method for executing programs for users in accordance with user-specified constraints, the method comprising:

receiving a request from a user to execute one or more copies of a program specified by the user, the request including an indication of one or more execution constraints for use in selecting one or more host computing systems to execute the one or more specified program copies for the user, the one or more execution constraints being based on at least one of locations of the one or more computing systems and of capabilities of the one or more computing systems related to executing the one or more program copies;

in response to the received request, automatically determining at least one candidate host computing system that is available to execute the one or more specified program copies for the user in accordance with the one or more execution constraints, the determined at least one candidate host computing systems being selected from multiple computing systems that are each configurable to execute any of a plurality of programs indicated by users of a program execution service, the automatic determining being performed by a configured computing device;

automatically selecting the one or more host computing systems from the determined at least one candidate host computing systems to execute the one or more specified program copies for the user, such that each of the selected one or more host computing systems is to execute at least one of the one or more specified program copies, the automatic selecting being performed by the configured computing device; and

automatically configuring each of the selected one or more host computing systems to execute the specified program, the automatic configuring being initiated by the configured computing device and including dynamically loading a copy of the specified program onto at least one of the selected one or more host computing systems, and initiating execution of the one or more specified program copies for the user on the selected configured one or more host computing systems.

2. The method of claim 1 wherein the multiple computing systems are part of one or more of multiple predefined groups and are inter-connected using one or more data exchange mediums, and wherein the automatic selecting of the one or more host computing systems is based at least in part on a degree of proximity between one of the selected host computing systems and at least one other computing system with respect to at least one of the one or more data exchange mediums.

3. The method of claim 2 wherein the degree of proximity is one of multiple connection-based proximity levels, the connection-based proximity levels including a level corresponding to a group of multiple computing systems connected by a switch-based data exchange medium, a level corresponding to a group of multiple switched groups of computing systems connected by a router-based data exchange medium, a level corresponding to a group of computing systems of a computing data center connected by a local area network of the data center, a level corresponding to multiple geographically proximate computing data centers connected by one or more dedicated high-speed data connections, and a level corresponding to multiple geographically distributed computing data centers connected by an internet.

4. The method of claim 3 wherein the multiple connection-based proximity levels are hierarchically organized, and wherein the one or more execution constraints indicate a range of one or more of the multiple connection-based proximity levels that is used as part of the automatic selecting of the one or more host computing systems.

5. The method of claim 1 wherein at least one of the one or more execution constraints is based on a relative location of each of the selected one or more host computing systems with respect to one or more indicated target computing resources, such that the determined at least one candidate host computing systems are each selected based at least in part on a relative location of the candidate host computing system with respect to at least one of the indicated target computing resources, wherein the indication from the user further includes an indication of the specified program and an indication to execute multiple copies of the specified program, and wherein the one or more indicated target computing resources are computing systems that each execute at least one copy of the specified program.

6. The method of claim 1 wherein the one or more specified program copies include multiple copies of the specified program, wherein the determined at least one candidate host computing system include multiple determined candidate host computing systems, wherein the selected one or more host computing systems include multiple selected host computing systems, wherein at least one of the one or more execution constraints is based on a relative location of each of the multiple selected host computing systems with respect to one or more indicated target computing resources, the relative location being based on a range of multiple degrees of proximity between the indicated target computing resources and the multiple selected host computing systems, wherein the multiple determined candidate host computing systems have differing degrees of proximity within the range to the indicated target computing resources, and wherein the automatic selecting of the multiple host computing systems from the multiple determined candidate host computing systems includes selecting host computing systems that have a preferred degree of proximity to the indicated target computing resources.

7. The method of claim 6 wherein the preferred degree of proximity is indicated by the user and is one of a degree of proximity within the range that is most proximate and of a degree of proximity within the range that is least proximate.

8. The method of claim 1 wherein the one or more specified program copies include multiple copies of the specified program, and wherein the one or more execution constraints specify a level of performance to be provided by the selected one or more host computing systems, the specified level of performance including at least one of a minimum degree of reliability in case of a failure that affects a subset of the multiple executing specified program copies and of a minimum degree of network connectivity performance between the multiple executing specified program copies, the minimum degree of reliability being based at least in part on the multiple executing specified program copies being executed on multiple computing systems having at least an indicated lack of proximity, and the minimum degree of network connectivity performance being based at least in part on the multiple executing specified program copies being executed on one or more computing systems having at least an indicated degree of proximity.

9. The method of claim 1 wherein the one or more execution constraints indicate one or more geographical locations of the selected one or more host computing systems with respect to one or more governmental boundaries.

10. The method of claim 1 wherein the one or more execution constraints indicate one or more capabilities of the selected one or more computing systems related to executing the one or more specified program copies.

11. The method of claim 1 further comprising, before the receiving of the indication from the user, defining a group of one or more execution constraints based on instructions received from the user, and wherein the indication from the user of the one or more execution constraints is based on an indication of the defined group.

12. The method of claim 1 wherein at least one of the selected one or more host computing systems each hosts multiple virtual machines that are each able to execute at least one program, and wherein the specified program is a virtual machine image to be executed by at least one virtual machine hosted by each of the at least one selected host computing systems.

13. The method of claim 1 wherein the configured computing device operates on behalf of the program execution service, wherein the specified program is one of multiple programs associated with the program execution service by customers of the program execution service, wherein the multiple computing systems are used by the program execution service to execute the multiple programs on behalf of the customers, and wherein the method further comprises receiving multiple requests from multiple users to execute instances of multiple programs, and automatically selecting one or more of the multiple computing systems for use with each of the requests.

14. The method of claim 1 wherein the automatic configuring of each of the selected one or more host computing systems to execute the specified program is performed at least in part by the configured computing device to enable the configured selected host computing system to execute the specified program, the configuring of at least one of the selected host computing systems including dynamically loading a copy of the specified program onto the at least one selected host computing system.

15. A non-transitory computer-readable medium whose stored contents configure a computing device to execute programs for users in accordance with user-specified constraints, by performing a method comprising:

receiving an indication from a user of one or more execution constraints for use in selecting one or more computing systems to execute one or more copies of a specified program on behalf of the user, the one or more computing systems to be selected from multiple computing systems that are configurable to execute any of a plurality of user programs, the one or more execution constraints being based on at least one of locations of the one or more computing systems, of capabilities of the one or more computing systems related to executing the one or more specified program copies, and of costs related to the one or more computing systems executing the one or more specified program copies;

automatically selecting the one or more computing systems from the multiple computing systems to execute the one or more specified program copies on behalf of the user, the automatic selecting being performed by the configured computing device and being based at least in part on the selected one or more computing systems satisfying the one or more execution constraints; and

providing one or more indications to initiate configuring of the selected one or more computing systems for the specified program and to initiate executing of the one or more program copies on the selected configured one or more computing systems.

16. The non-transitory computer-readable medium of claim 15 wherein the selected one or more computing systems include two or more host computing systems, wherein the one or more execution constraints indicate relative locations of the two or more host computing systems with respect to one or more indicated target computing resources, wherein the indication from the user further indicates the specified program and a quantity of multiple copies of the specified program that are each to be executed on one of the two or more host computing systems, wherein the indicated target computing resources for use in determining the relative location of the two or more host computing systems executing the multiple specified program copies are other computing systems executing other copies of the specified program, and wherein the one or more execution constraints indicate at least one of a minimum and of a maximum degree of distance between computing systems that each execute a copy of the specified program, the minimum degree of distance being for use if indicated in providing a minimum degree of reliability in case of a failure that affects one of the executing multiple specified program copies, and the maximum degree of distance being for use if indicated in providing a minimum degree of network connectivity performance between at least the executing multiple specified program copies.

17. The non-transitory computer-readable medium of claim 15 wherein the providing of the one or more indications to initiate the configuring of the selected one or more computing systems for the specified program includes configuring each of the selected one or more computing systems to enable the configured selected computing system to execute the specified program, the configuring of at least one of the selected computing systems including dynamically loading a copy of the specified program onto the at least one selected computing system.

18. The non-transitory computer-readable medium of claim 15 wherein the computer-readable medium is a memory of the configured computing device, and wherein the contents are instructions that when executed program the configured computing device to perform the method.

19. The non-transitory computer-readable medium of claim 15 wherein the one or more computing systems include multiple computing systems that are part of one or more of multiple predefined groups and are inter-connected using one or more data exchange mediums, and wherein the automatic selecting is based at least in part on a degree of proximity between one of the selected computing systems and at least one other computing system with respect to at least one of the one or more data exchange mediums.

20. The non-transitory computer-readable medium of claim 15 wherein at least one of the one or more execution constraints is based on a relative location of each of the selected one or more computing systems with respect to one or more indicated target computing resources, the relative location being based on a range of multiple degrees of proximity between the indicated target computing resources and the selected one or more computing systems, and wherein the automatic selecting includes selecting one or more computing systems that have a preferred degree of proximity to the indicated target computing resources, the preferred degree of proximity being indicated by the user and being one of a most proximate degree of proximity within the range and of a least proximate degree of proximity within the range.

21. The non-transitory computer-readable medium of claim 15 wherein the one or more execution constraints indicate one or more geographical locations of the selected one or more computing systems with respect to one or more governmental boundaries.

22. The non-transitory computer-readable medium of claim 15 wherein the one or more execution constraints indicate one or more capabilities of the selected one or more computing systems related to executing the one or more specified program copies.

23. The non-transitory computer-readable medium of claim 15 wherein the configured computing device operates on behalf of a program execution service, wherein the specified program is one of multiple programs associated with the program execution service by customers of the program execution service, wherein the multiple computing systems are used by the program execution service to execute the multiple programs on behalf of the customers, and wherein the method further comprises receiving multiple requests from multiple users to execute instances of multiple programs, and automatically selecting one or more of the multiple computing systems for use with each of the requests.

24. The non-transitory computer-readable medium of claim 15 wherein at least one of the one or more execution constraints is based on a relative location of the selected one or more computing systems with respect to one or more indicated target computing resources, and wherein the one or more indicated target computing resources are each at least one of a computing system that executes one or more indicated programs and of a system that stores one or more indicated groups of data.

25. A system configured to execute programs for users in accordance with user-specified constraints, comprising:

one or more processors; and

a system manager component configured to, when executed by at least one of the one or more processors, and in response to a determination to execute one or more copies of a program specified by a user on one or more computing systems for the user in accordance with one or more user-specified execution constraints, the one or more execution constraints indicating relative locations of the one or more computing systems with respect to one or more indicated target computing resources;

automatically select the one or more computing systems to execute the one or more specified program copies, the one or more computing systems being selected from a group of multiple computing systems that are for use in executing programs for a program execution service and that are configurable to execute any of a plurality of user programs, the selected one or more computing systems satisfying the one or more execution constraints; and

initiate execution of the one or more specified program copies on the selected one or more computing systems.

26. The system of claim 25 wherein the initiating of the execution of the one or more specified program copies on the selected one or more computing systems includes configuring each of the selected one or more computing systems to enable the configured selected computing system to execute the specified program, the configuring of at least one of the selected one or more computing systems including dynamically loading a copy of the specified program onto the at least one selected computing system.

27. The system of claim 26 further comprising the multiple computing systems, the multiple computing systems having multiple groups that each have two or more computing systems sharing a common physical data connection not shared by computing machines external to the group, at least one of the multiple groups being in a first geographic location distinct from a second geographic location of at least one other of the multiple groups, wherein the relative locations of the one or more computing systems are based at least in part on the groups of computing systems, wherein the initiating of the execution of the one or more specified program copies on the selected one or more computing systems includes performing the execution of the one or more specified program copies on the selected one or more computing systems, wherein at least some of the multiple computing systems are each configured to host multiple virtual machines that are each able to execute at least one program for a user, such that each of the at least some computing systems is able to simultaneously execute multiple distinct programs for multiple users, wherein the selected one or more computing systems include one or more of the at least some computing systems, and wherein the common physical data connections shared by the multiple computing machines of the multiple groups are each provided by at least one of a network switch, a network router that supports multiple network switches, and a local area network of a data center.

28. The system of claim 25 wherein the multiple computing systems are part of one or more of multiple predefined groups, wherein each of the multiple predefined groups has a distinct data exchange medium via which computing systems of the predefined group are inter-connected, and wherein the automatic selecting of the one or more host computing systems is based at least in part on a degree of proximity between one of the selected computing systems and at least one other computing system with respect to at least one of the data exchange mediums for the multiple predefined groups.

29. The system of claim 28 wherein the degree of proximity is one of multiple connection-based proximity levels, the connection-based proximity levels including a level corresponding to a group of multiple computing systems connected by a switch-based data exchange medium, a level corresponding to a group of multiple switched groups of computing systems connected by a router-based data exchange medium, a level corresponding to a group of computing systems of a computing data center connected by a local area network of the data center, a level corresponding to multiple geographically proximate computing data centers connected by one or more dedicated high-speed data connections, and a level corresponding to multiple geographically distributed computing data centers connected by an internet.

30. The system of claim 29 wherein the multiple connection-based proximity levels are hierarchically organized, and wherein the one or more execution constraints indicate a range of one or more of the multiple connection-based proximity levels that is used as part of the automatic selecting of the one or more computing systems.

31. The system of claim 25 wherein the one or more indicated target computing resources are computing systems that execute one or more indicated programs.

32. The system of claim 25 wherein the one or more indicated target computing resources are computing systems that store one or more indicated groups of data.

33. The system of claim 25 wherein the determination to execute the one or more specified program copies is based on one or more indications from the user of the specified program and to execute multiple copies of the specified program, and wherein the one or more indicated target computing resources are computing systems that each execute at least one copy of the specified program.

34. The system of claim 25 wherein the system includes a first computing device of which at least one of the one or processors is a part, and wherein the system manager component includes software instructions for execution by the first computing device using the at least one processor.

35. The system of claim 25 wherein the system manager component consists of a means for, in response to a determination to execute one or more copies of a program specified by a user on one or more computing systems for the user in accordance with one or more user-specified execution constraints, the one or more execution constraints indicating relative locations of the one or more computing systems with respect to one or more indicated target computing resources:

automatically selecting the one or more computing systems to execute the one or more specified program copies, the one or more computing systems being selected from a group of multiple computing systems that are for use in executing programs for a program execution service and that are configurable to execute any of a plurality of user programs, the selected one or more computing systems satisfying the one or more execution constraints; and

initiating execution of the one or more specified program copies on the selected one or more computing systems.

36. The system of claim 25 wherein the relative locations of the one or more computing systems with respect to one or more indicated target computing resources are based on a range of multiple degrees of proximity between the indicated target computing resources and the selected one or more computing systems, and wherein the automatic selecting includes selecting one or more computing systems that have a preferred degree of proximity to the indicated target computing resources, the preferred degree of proximity being indicated by the user and being one of a most proximate degree of proximity within the range and of a least proximate degree of proximity within the range.

37. The system of claim 25 wherein the one or more user-specified execution constraints further reflect one or more geographical locations of the selected one or more computing systems with respect to one or more governmental boundaries.

38. The system of claim 25 wherein the one or more user-specified execution constraints further reflect one or more capabilities of the selected one or more computing systems related to executing the one or more specified program copies.

39. The system of claim 25 wherein the specified program is one of multiple programs associated with the program execution service by customers of the program execution service, and wherein the system manager component is further configured to receive multiple requests from multiple users to execute instances of multiple programs, and to automatically select one or more of the multiple computing systems for use with each of the requests.

40. A computer-implemented method for executing programs for users in accordance with user-specified constraints, the method comprising:

receiving an indication from a user of one or more execution constraints for use in selecting one or more host computing systems to execute one or more copies of a specified program for the user, the one or more execution constraints being based on specified relative locations of the one or more host computing systems with respect to one or more indicated target computing resources;

automatically determining at least one candidate host computing system that is available to execute the one or more specified program copies for the user in accordance with the one or more execution constraints based at least in part on each of the determined at least one candidate host computing systems having a location that satisfies the specified relative location with respect to the one or more indicated target computing resources, the determined at least one candidate host computing systems being selected from multiple computing systems that are each configurable to execute one of a plurality of programs indicated by users of a program execution service, the automatic determining being performed by a configured computing device of the program execution service;

automatically selecting the one or more host computing systems from the determined at least one candidate host computing systems to execute the one or more specified program copies for the user, each of the selected one or more host computing systems being for use in executing at least one of the one or more specified program copies, the automatic selecting being performed by the configured computing device; and

automatically configuring each of the selected one or more host computing systems to execute the specified program, the automatic configuring being initiated by the configured computing device, and initiating execution of the one or more specified program copies for the user on the selected configured one or more host computing systems.

41. The method of claim 40 wherein the specified relative locations of the one or more host computing systems with respect to the one or more indicated target computing resources are based on one or more indicated degrees of proximity between the one or more indicated target computing resources and the one or more host computing systems, and wherein the location of each of the determined at least one candidate host computing systems is within at least one of the indicated degrees of proximity with respect to at least one of the one or more indicated target computing resources.

42. The method of claim 41 wherein the multiple computing systems are part of one or more of multiple predefined groups and are inter-connected using one or more data exchange mediums, and wherein the one or more indicated degrees of proximity are based at least in part on at least one of the one or more data exchange mediums.

43. The method of claim 42 wherein the one or more indicated degrees of proximity each correspond to at least one of multiple connection-based proximity levels, the connection-based proximity levels including a level corresponding to multiple programs executing on a single computing system that share a data exchange medium within the single computing system, a level corresponding to a group of multiple computing systems connected by a switch-based data exchange medium, a level corresponding to a group of multiple switched groups of computing systems connected by a router-based data exchange medium, a level corresponding to a group of computing systems of a computing data center connected by a local area network of the data center, a level corresponding to multiple geographically proximate computing data centers connected by one or more dedicated high-speed data connections, and a level corresponding to multiple geographically distributed computing data centers connected by an internet.

44. The method of claim 43 wherein the connection-based proximity levels are hierarchically organized, and wherein the one or more execution constraints indicate a range of one or more of the proximity levels.

45. The method of claim 40 wherein the one or more indicated target computing resources include one or more computing systems that execute one or more indicated programs.

46. The method of claim 40 wherein the one or more indicated target computing resources include one or more computing systems that store one or more indicated groups of data.

47. The method of claim 40 wherein the indication from the user further includes an indication of the specified program and an indication to execute multiple copies of the specified program, and wherein the one or more indicated target computing resources are computing systems that each execute at least one copy of the specified program.