Method and apparatus for stress management in a searchable data service

• US 8,392,400 B1
• Filed: 03/29/2006
• Issued: 03/05/2013
• Est. Priority Date: 12/29/2005
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Ransil, Patrick W., Martynov, Aleksey V., Larson, James S., Collette, James R., Chu, Robert Wai-Chi, Saha, Partha
• Primary Examiner(s): REYES, MARIELA D
• Application Number:
  US11/393,002
• Time in Patent Office: 2,533 Days
• Field of Search: 707/716, 707/719, 707/720
• US Class Current: 707/716
• CPC Class Codes: G06F 11/1446 Point-in-time backing up or restoration of persistent data
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 16/2228 Indexing structures
• CPC Class Codes: G06F 16/2255 Hash tables
• CPC Class Codes: G06F 16/2272 Management thereof
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/24552 Database cache management
• CPC Class Codes: G06F 16/24554 Unary operations; Data partitioning operations
• CPC Class Codes: G06F 16/24557 Efficient disk access during query execution
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: G06F 16/278 Data partitioning, e.g. horizontal or vertical partitioning
• CPC Class Codes: G06F 16/282 Hierarchical databases, e.g. IMS, LDAP data stores or Lotus Notes
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

Method and apparatus for stress management in a searchable data service. The searchable data service may provide a searchable index to a backend data store, and an interface to build and query the searchable index, that enables client applications to search for and retrieve locators for stored entities in the backend data store. Embodiments of the searchable data service may implement a distributed stress management mechanism that may provide functionality including, but not limited to, the automated monitoring of critical resources, analysis of resource usage, and decisions on and performance of actions to keep resource usage within comfort zones. In one embodiment, in response to usage of a particular resource being detected as out of the comfort zone on a node, an action may be performed to transfer at least part of the resource usage for the local resource to another node that provides a similar resource.

Claims

1. A searchable data service system, comprising:

a plurality of computer devices configured to implement a searchable data service, wherein the searchable data service is configured to process query requests from client applications to locate searchable data service objects in respective ones of a plurality of independent searchable indexes stored on the plurality of computer devices that satisfy the query requests, wherein each searchable data service object specifies two or more attributes of a particular entity in a particular one of a plurality of independent data stores on one or more storage devices each on a network and separate from the plurality of computer devices that implement the searchable data service, wherein each searchable index of the plurality of independent searchable indexes stores searchable data service objects for a particular one of the plurality of independent data stores, and wherein the attributes include a unique entity identifier for locating the particular entity in the particular data store;

wherein the searchable data service comprises two or more node groups, wherein each node group comprises two or more of a plurality of nodes implemented on the plurality of computer devices, each node including a plurality of local resources for supporting the searchable data service on the respective node, and wherein each node in each node group is configured to;

monitor one or more usage metrics for each of the plurality of local resources of the node; and

in response to detecting that a monitored usage metric for a particular local resource has crossed a boundary of a specified comfort zone for the monitored usage metric, communicate with at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another one of the nodes in the node group that includes a similar resource;

wherein said transferring at least part of the resource usage for the particular local resource on the node to another one of the nodes in the node group moves the monitored usage metric for the particular local resource into the specified comfort zone for the monitored usage metric on the node.

2. The system as recited in claim 1, wherein each attribute is expressed as a {name, value} pair.

3. The system as recited in claim 1, wherein, to communicate with at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another one of the nodes in the node group that includes a similar resource, the nodes in the node group are configured to communicate in accordance with a gossip protocol.

4. The system as recited in claim 1, wherein, to communicate with at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another one of the nodes in the node group that includes a similar resource, the nodes in the node group are configured to communicate in accordance with an anti-entropy protocol.

5. The system as recited in claim 1, wherein, to communicate with at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another one of the nodes in the node group that includes a similar resource, the nodes in the node group are configured to communicate in accordance with a gossip protocol and an anti-entropy protocol.

6. The system as recited in claim 1, wherein the two or more node groups each include a subset of the plurality of nodes, wherein each node in at least one of the node groups is configured to communicate with other nodes in the node group in accordance with a gossip protocol to propagate searchable data service information relevant to the node group.

7. The system as recited in claim 1, wherein monitored usage metrics for local resources on a node include one or more storage space usage metrics for a local storage resource.

8. The system as recited in claim 1, wherein monitored usage metrics for local resources on a node include one or more processor usage metrics for a local processor resource.

9. The system as recited in claim 1, wherein monitored usage metrics for local resources on a node include one or more read load metrics for a local storage resource.

10. The system as recited in claim 1, wherein monitored usage metrics for local resources on a node include one or more write load metrics for a local storage resource.

11. The system as recited in claim 1, wherein each of the plurality of nodes is configured to communicate monitored local resource usage metrics to one or more others of the plurality of nodes.

12. The system as recited in claim 1, wherein at least one of the node groups is configured to propagate monitored local resource usage metrics for each node in the node group to other nodes in the node group in accordance with a gossip protocol.

13. The system as recited in claim 1, wherein each node in at least one of the node groups is further configured to receive monitored local resource usage metrics from other nodes in the node group in accordance with a gossip protocol.

14. The system as recited in claim 1, wherein at least one of the node groups is a storage node group comprising a plurality of storage nodes each configured to:

persistently store at least one partition of at least one of the plurality of independent searchable indexes on a local storage resource;

monitor one or more storage space usage metrics for the local storage resource; and

in response to determining that a monitored storage space usage metric for the local storage resource crosses a boundary of a specified comfort zone for the storage space usage metric on the storage node, communicate with one or more others of the storage nodes in the storage node group to transfer at least part of the at least one partition of at least one of the plurality of independent searchable indexes to another storage node in the storage node group.

15. The system as recited in claim 1, wherein at least one of the node groups is a storage node group comprising a plurality of storage nodes each configured to:

persistently store a partition of one of the plurality of independent searchable indexes on a local storage resource;

monitor a storage space usage metric for the local storage resource; and

in response to determining that the monitored storage space usage metric for the local storage resource crosses a boundary of a specified comfort zone for the storage space usage metric on the storage node;

repartition the partition to generate two or more new partitions, wherein each of the two or more new partitions includes a different subset of the searchable data service objects stored in the respective searchable index;

communicate with one or more others of the storage nodes in the storage node group to locate another storage node in the storage node group that volunteers to receive one of the two or more new partitions; and

communicate with the other storage node to move one of the two or more new partitions to the other storage node.

16. The system as recited in claim 15, wherein each storage node is further configured to communicate with one or more others of the storage nodes in the storage node group to locate another storage node in the storage node group that volunteers to receive one of the two or more new partitions and to communicate with the other storage node to move one of the two or more new partitions to the other storage node in accordance with a gossip protocol and an anti-entropy protocol.

17. The system as recited in claim 1, wherein the plurality of nodes comprises:

a plurality of storage nodes each configured to persistently store at least one partition of at least one of the one of the plurality of independent searchable indexes;

one or more query nodes each configured to;

maintain a local query cache of responses to previous query requests;

access the local query cache on the query node to determine whether a query request can or cannot be satisfied from the local query cache; and

in response to determining that the query request cannot be satisfied from the local query cache, forward the query request to an appropriate one or more of the storage nodes;

one or more coordinator nodes each configured to;

receive service requests from the client application, wherein the service requests comprise storage requests and query requests;

forward each storage request to an appropriate one or more of the storage nodes; and

forward each query request to an appropriate one or more of the query nodes.

18. The system as recited in claim 17, wherein each of the one or more storage nodes is configured to:

receive a storage request from a coordinator node; and

modify a partition of one of the plurality of independent searchable indexes persistently stored by the storage node as specified in the storage request.

19. The system as recited in claim 17, wherein each of the one or more storage nodes is configured to:

receive a query request from a query node;

search a partition of one of the plurality of independent searchable indexes persistently stored by the storage node to locate a set of one or more searchable data service objects in the respective searchable index that satisfy the query request; and

return at least the entity identifiers from the set of one or more searchable data service objects that satisfy the query request to the client application.

20. The system as recited in claim 17, wherein the two or more node groups each include a subset of the plurality of nodes, wherein each node in at least one of the node groups is configured to communicate with other nodes in the node group in accordance with a gossip protocol and an anti-entropy protocol to propagate searchable data service information within the node group, and wherein the two or more node groups include:

one or more storage node groups each comprising two or more storage nodes;

one or more query node groups each comprising two or more query nodes; and

one or more coordinator node groups each comprising two or more coordinator nodes.

21. The system as recited in claim 20, wherein each query node and each coordinator node comprises an instance of a storage node locator component of the searchable data service, wherein the storage node locator component is configured to locate appropriate storage nodes to receive service requests, and wherein the two or more node groups include one or more storage node locator groups each including a subset of the query nodes and the coordinator nodes.

22. The system as recited in claim 17, wherein the plurality of nodes is distributed among two or more data centers, wherein each data center includes two or more of the storage nodes, one or more of the query nodes, and one or more of the coordinator nodes.

23. The system as recited in claim 1, further comprising a web services platform configured to provide a web service interface to the searchable data service, wherein the web services platform is configured to:

receive service requests from the client applications in accordance with the web service interface to the searchable data service, wherein the service requests comprise query requests and storage requests;

forward the received service requests to one or more of the plurality of nodes; and

return searchable data service responses to the service requests to the client applications in accordance with the web service interface to the searchable data service.

24. A method, comprising:

processing query requests received from a plurality of client applications on a plurality of nodes configured to participate in a searchable data service to locate searchable data service objects in respective ones of a plurality of independent searchable indexes on the plurality of nodes that satisfy the query requests, wherein each searchable data service object specifies two or more attributes of a particular entity in a particular one of a plurality of independent data stores on one or more storage devices each on a network and separate from a plurality of computer devices that implement the plurality of nodes, wherein each searchable index of the plurality of independent searchable indexes stores searchable data service objects for a particular one of the plurality of independent data stores, and wherein the attributes include a unique entity identifier for locating the particular entity in the data store;

wherein the plurality of nodes are organized into two or more node groups each including a subset of the plurality of nodes, each node including two or more local resources for supporting the searchable data service on the respective node;

monitoring on each node in each node group one or more usage metrics for each of the two or more local resources of the node;

detecting on one of the nodes in one of the node groups that a monitored usage metric for a particular local resource has crossed a boundary of a specified comfort zone for the monitored usage metric;

communicating between the node and at least one other node in the respective node group to transfer at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource;

wherein said transferring at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource moves the monitored usage metric for the particular local resource on the node into the specified comfort zone for the monitored usage metric on the node.

25. The method as recited in claim 24, wherein each attribute is expressed as a {name, value} pair.

26. The method as recited in claim 24, wherein each node in at least one of the node groups is configured to communicate with other nodes in the node group in accordance with a gossip protocol to propagate searchable data service information relevant to the node group.

27. The method as recited in claim 24, wherein said communicating between the node and at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource comprises communicating between the node and at least one other node in the node group in accordance with a gossip protocol.

28. The method as recited in claim 24, wherein said communicating between the node and at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource comprises communicating between the node and at least one other node in the node group in accordance with an anti-entropy protocol.

29. The method as recited in claim 24, wherein said communicating between the node and at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource comprises communicating between the node and at least one other node in the node group in accordance with a gossip protocol and an anti-entropy protocol.

30. The method as recited in claim 24, wherein monitored usage metrics for local resources on a node include one or more storage space usage metrics for a local storage resource.

31. The method as recited in claim 24, wherein monitored usage metrics for local resources on a node include one or more processor usage metrics for a local processor resource.

32. The method as recited in claim 24, wherein monitored usage metrics for local resources on a node include one or more read load metrics for a local storage resource.

33. The method as recited in claim 24, wherein monitored usage metrics for local resources on a node include one or more write load metrics for a local storage resource.

34. The method as recited in claim 24, further comprising communicating monitored local resource usage metrics from each node in a node group to one or more others of the plurality of nodes.

35. The method as recited in claim 24, further comprising communicating monitored local resource usage metrics from each node in a node group to one or more others of the plurality of nodes in accordance with a gossip protocol.

36. The method as recited in claim 24, further comprising receiving on each node in a node group monitored local resource usage metrics from one or more others of the plurality of nodes in accordance with a gossip protocol.

37. The method as recited in claim 24, wherein the plurality of nodes comprises a plurality of storage nodes, the method further comprising, on each of the plurality of storage nodes:

persistently storing at least one partition of at least one of the plurality of independent searchable indexes on a local storage resource;

monitoring one or more storage space usage metrics for the local storage resource; and

communicating with one of the other storage nodes to transfer at least part of the at least one partition of at least one of the plurality of independent searchable indexes to the other storage node in response to determining that a monitored storage space usage metric for the local storage resource crosses a boundary of a specified comfort zone for the storage space usage metric on the storage node.

38. The method as recited in claim 24, wherein the plurality of nodes comprises a plurality of storage nodes, and wherein the method further comprises, on each of the plurality of storage nodes:

persistently storing a partition of one of the plurality of independent searchable indexes on a local storage resource;

monitoring a storage space usage metric for the local storage resource; and

in response to determining that the monitored storage space usage metric for the local storage resource crosses a boundary of a specified comfort zone for the storage space usage metric on the storage node;

repartitioning the partition to generate two or more new partitions, wherein each of the two or more new partitions includes a different subset of the searchable data service objects stored in the respective searchable index;

communicating with one or more others of the storage nodes to locate another storage node that volunteers to receive one of the two or more new partitions; and

communicating with the other storage node to move one of the two or more new partitions to the other storage node.

39. The method as recited in claim 38, wherein said communicating with one or more others of the storage nodes to locate another storage node that volunteers to receive one of the two or more new partitions and said communicating with the other storage node to move one of the two or more new partitions to the other storage node are performed in accordance with a gossip protocol and an anti-entropy protocol.

40. The method as recited in claim 24, wherein the plurality of nodes comprises a plurality of storage nodes, one or more coordinator nodes, and one or more query nodes, and wherein the method further comprises:

persistently storing at least one partition of at least one of the plurality of independent searchable indexes on each of the plurality of storage nodes;

on each of the one or more coordinator nodes;

receiving service requests from the client application, wherein the service requests comprise storage requests and query requests;

forwarding each storage request to an appropriate one or more of the storage nodes; and

forwarding each query request to an appropriate one or more of the query nodes;

on each of the one or more query nodes;

maintaining a local query cache of responses to previous query requests;

accessing the local query cache on the query node to determine whether a query request can or cannot be satisfied from the local query cache;

forwarding the query request to an appropriate one or more of the storage nodes in response to determining that the query request cannot be satisfied from the local query cache.

41. The method as recited in claim 40, further comprising, on each of the one or more storage nodes:

receiving a storage request from a coordinator node; and

modifying a partition of one of the plurality of independent searchable indexes persistently stored by the storage node as specified in the storage request.

42. The method as recited in claim 40, further comprising, on each of the one or more storage nodes:

receiving a query request from a query node;

searching a partition of one of the plurality of independent searchable indexes persistently stored by the storage node to locate a set of one or more searchable data service objects in the respective searchable index that satisfy the query request; and

returning at least the entity identifiers from the set of one or more searchable data service objects that satisfy the query request to the client application.

43. The method as recited in claim 40, wherein the two or more node groups include:

one or more storage node groups each comprising a subset of the storage nodes;

one or more query node groups each comprising a subset of the query nodes; and

one or more coordinator node groups each comprising a subset of the coordinator nodes.

44. The method as recited in claim 40, wherein each query node and each coordinator node comprises an instance of a storage node locator component of the searchable data service, wherein the storage node locator component is configured to locate appropriate storage nodes to receive service requests, and wherein the two or more node groups include one or more storage node locator groups each including a subset of the query nodes and the coordinator nodes.

45. The method as recited in claim 40, wherein the plurality of nodes is distributed among two or more data centers, wherein each data center includes two or more of the storage nodes, one or more of the query nodes, and one or more of the coordinator nodes.

46. The method as recited in claim 24, further comprising:

receiving service requests from the client applications on a web services platform configured to provide a web service interface to the searchable data service and in accordance with the web service interface to the searchable data service, wherein the service requests comprise query requests and storage requests;

forwarding the received service requests from the web services platform to one or more of the plurality of nodes; and

returning searchable data service responses to the service requests from the web services platform to the client applications in accordance with the web service interface to the searchable data service.

47. A computer-accessible memory medium storing program instructions, wherein the program instructions are executable to implement a searchable data service on a plurality of nodes, wherein the searchable data service is configured to:

process query requests from a plurality of client applications on the plurality of nodes to locate searchable data service objects in respective ones of a plurality of independent searchable indexes on the plurality of nodes that satisfy the query requests, wherein each searchable data service object specifies two or more attributes of a particular entity in a particular one of a plurality of independent data stores on one or more storage devices each on a network and separate from a plurality of computer devices that implement the plurality of nodes, wherein each searchable index of the plurality of independent searchable indexes stores searchable data service objects for a particular one of the plurality of independent data stores, and wherein the attributes include a unique entity identifier for locating the particular entity in the data store;

wherein the plurality of nodes are organized into two or more node groups each including a subset of the plurality of nodes, each node including two or more local resources for supporting the searchable data service on the respective node;

on each node in each node group;

monitor one or more usage metrics for each of the two or more local resources of the node;

detect that a monitored usage metric for a particular local resource crosses a boundary of a specified comfort zone for the monitored usage metric;

communicate with at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource;

wherein said transferring at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource moves the monitored usage metric for the particular local resource into the specified comfort zone for the monitored usage metric on the node.

48. The computer-accessible memory medium as recited in claim 47, wherein each attribute is expressed as a {name, value} pair.

49. The computer-accessible memory medium as recited in claim 47, wherein each node in at least one of the node groups is configured to communicate with other nodes in the node group in accordance with a gossip protocol to propagate searchable data service information relevant to the node group.

50. The computer-accessible memory medium as recited in claim 47, wherein, to communicate with at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource, the nodes in the node group are configured to communicate in accordance with a gossip protocol.

51. The computer-accessible memory medium as recited in claim 47, wherein, to communicate with at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource, the nodes in the node group are configured to communicate in accordance with an anti-entropy protocol.

52. The computer-accessible memory medium as recited in claim 47, wherein, to communicate with at least one other node in the node group to transfer at least part of the resource usage for the particular local resource on the node to another node in the node group that includes a similar resource, the nodes in the node group are configured to communicate in accordance with a gossip protocol and an anti-entropy protocol.

53. The computer-accessible memory medium as recited in claim 47, wherein monitored usage metrics for local resources on a node include one or more storage space usage metrics for a local storage resource.

54. The computer-accessible memory medium as recited in claim 47, wherein monitored usage metrics for local resources on a node include one or more processor usage metrics for a local processor resource.

55. The computer-accessible memory medium as recited in claim 47, wherein monitored usage metrics for local resources on a node include one or more read load metrics for a local storage resource.

56. The computer-accessible memory medium as recited in claim 47, wherein monitored usage metrics for local resources on a node include one or more write load metrics for a local storage resource.

57. The computer-accessible memory medium as recited in claim 47, wherein the searchable data service is further configured to, on each node in a node group, communicate monitored local resource usage metrics to one or more others of the plurality of nodes in accordance with a gossip protocol.

58. The computer-accessible memory medium as recited in claim 47, wherein the searchable data service is further configured to, on each node in a node group, receive monitored local resource usage metrics from one or more others of the plurality of nodes in accordance with a gossip protocol.

59. The computer-accessible memory medium as recited in claim 47, wherein the program instructions are configured to implement one or more of the plurality of nodes as searchable data service storage nodes each configured to:

persistently store at least one partition of at least one of the plurality of independent searchable indexes on a local storage resource;

monitor one or more storage space usage metrics for the local storage resource; and

in response to determining that a monitored storage space usage metric for the local storage resource crosses a boundary of a specified comfort zone for the storage space usage metric on the storage node, communicate with one of the other storage nodes to transfer at least part of the at least one partition of at least one of the plurality of independent searchable indexes to the other storage node.

60. The computer-accessible memory medium as recited in claim 47, wherein the program instructions are configured to implement one or more of the plurality of nodes as searchable data service storage nodes each configured to:

persistently store a partition of one of the plurality of independent searchable indexes on a local storage resource;

monitor a storage space usage metric for the local storage resource; and

in response to determining that the monitored storage space usage metric for the local storage resource crosses a boundary of a specified comfort zone for the storage space usage metric on the storage node;

repartition the partition to generate two or more new partitions, wherein each of the two or more new partitions includes a different subset of the searchable data service objects stored in the respective searchable index;

communicate with one or more others of the storage nodes to locate another storage node that volunteers to receive one of the two or more new partitions; and

communicate with the other storage node to move one of the two or more new partitions to the other storage node.

61. The computer-accessible memory medium as recited in claim 60, wherein each storage node is further configured to communicate with one or more others of the storage nodes to locate another storage node that volunteers to receive one of the two or more new partitions and to communicate with the other storage node to move one of the two or more new partitions to the other storage node in accordance with a gossip protocol and an anti-entropy protocol.

62. The computer-accessible memory medium as recited in claim 47, wherein the program instructions are configured to implement the searchable data service on the plurality of nodes as:

a plurality of storage nodes each configured to persistently store at least one partition of at least one of the plurality of independent searchable indexes;

one or more query nodes each configured to;

maintain a local query cache of responses to previous query requests;

access the local query cache on the query node to determine whether a query request can or cannot be satisfied from the local query cache; and

in response to determining that the query request cannot be satisfied from the local query cache, forward the query request to an appropriate one or more of the storage nodes;

one or more coordinator nodes each configured to;

receive service requests from the client application, wherein the service requests comprise storage requests and query requests;

forward each storage request to an appropriate one or more of the storage nodes; and

forward each query request to an appropriate one or more of the query nodes.

63. The computer-accessible memory medium as recited in claim 62, wherein each of the one or more storage nodes is further configured to:

receive a storage request from a coordinator node; and

modify a partition of one of the plurality of searchable indexes persistently stored by the storage node as specified in the storage request.

64. The computer-accessible memory medium as recited in claim 62, wherein each of the one or more storage nodes is further configured to:

receive a query request from a query node;

search a partition of one of the plurality of independent searchable indexes persistently stored by the storage node to locate a set of one or more searchable data service objects in the respective searchable index that satisfy the query request; and

return at least the entity identifiers from the set of one or more searchable data service objects that satisfy the query request to the client application.

65. The computer-accessible memory medium as recited in claim 62, wherein the two or more node groups include:

one or more storage node groups each comprising a subset of the storage nodes;

one or more query node groups each comprising a subset of the query nodes; and

one or more coordinator node groups each comprising a subset of the coordinator nodes.

66. The computer-accessible memory medium as recited in claim 62, wherein each query node and each coordinator node comprises an instance of a storage node locator component of the searchable data service, wherein the storage node locator component is configured to locate appropriate storage nodes to receive service requests, and wherein the two or more node groups include one or more storage node locator groups each including a subset of the query nodes and the coordinator nodes.

67. The computer-accessible memory medium as recited in claim 62, wherein the plurality of nodes is distributed among two or more data centers, wherein each data center includes two or more of the storage nodes, one or more of the query nodes, and one or more of the coordinator nodes.

68. The computer-accessible memory medium as recited in claim 47, wherein the program instructions are further configured to implement a web service interface to the searchable data service, wherein the web service interface is configured to:

receive service requests from the client applications in accordance with the web service interface, wherein the service requests comprise query requests and storage requests;

forward the received service requests to one or more of the plurality of nodes; and

return searchable data service responses to the service requests to the client applications in accordance with the web service interface.

69. A searchable data service node, comprising:

one or more processors;

a network interface configured to communicatively couple to a network; and

a memory comprising program instructions, wherein the program instructions are executable by the one or more processors to;

process query requests received from a plurality of client applications via the network to locate searchable data service objects in respective ones of a plurality of independent searchable indexes for a plurality of independent data stores used by the client applications that satisfy the query requests, wherein the plurality of independent searchable indexes are distributed on a plurality of searchable data service nodes on the network, each searchable data service node including two or more local resources for supporting a searchable data service on the respective searchable data service node, wherein the data stores are on one or more storage devices each on the network and separate from computer devices on the network that implement the searchable data service nodes, wherein each searchable index of the plurality of independent searchable indexes stores searchable data service objects for a particular one of the plurality of independent data stores, wherein each searchable data service object specifies two or more attributes of a particular entity in a particular data store, and wherein the attributes include a unique entity identifier for locating the particular entity in the particular data store;

monitor one or more usage metrics for each of the two or more local resources of the searchable data service node;

in response to detecting that a monitored usage metric for a particular local resource of the searchable data service node has crossed a boundary of a specified comfort zone for the monitored usage metric, communicate via the network with another searchable data service node to transfer at least part of the resource usage for the particular local resource on the searchable data service node to the other searchable data service node that includes a similar resource;

wherein said transferring at least part of the resource usage for the particular local resource on the searchable data service node to the other searchable data service node moves the monitored usage metric for the particular local resource into the specified comfort zone for the monitored usage metric on the searchable data service node.

70. The searchable data service node as recited in claim 69, wherein each attribute is expressed as a {name, value} pair.

71. The searchable data service node as recited in claim 69, wherein, to communicate via the network with another searchable data service node to transfer at least part of the resource usage for the particular local resource on the searchable data service node to the other searchable data service node that includes a similar resource, the program instructions are further executable by the one or more processors to communicate via the network with the other searchable data service node in accordance with a gossip protocol.

72. The searchable data service node as recited in claim 69, wherein, to communicate via the network with another searchable data service node to transfer at least part of the resource usage for the particular local resource on the searchable data service node to the other searchable data service node that includes a similar resource, the program instructions are further executable by the one or more processors to communicate via the network with the other searchable data service node in accordance with an anti-entropy protocol.

73. The searchable data service node as recited in claim 69, wherein monitored usage metrics for local resources on the searchable data service node include one or more storage space usage metrics for a local storage resource.

74. The searchable data service node as recited in claim 69, wherein monitored usage metrics for local resources on the searchable data service node include one or more processor usage metrics for a local processor resource.

75. The searchable data service node as recited in claim 69, wherein monitored usage metrics for local resources on the searchable data service node include one or more read load metrics for a local storage resource.

76. The searchable data service node as recited in claim 69, wherein monitored usage metrics for local resources on the searchable data service node include one or more write load metrics for a local storage resource.