Environment-sensitive distributed data management

• US 8,935,203 B1
• Filed: 03/29/2012
• Issued: 01/13/2015
• Est. Priority Date: 03/29/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Brooker, Marc J., Parthasarathy, Madhuvanesh, Certain, Tate Andrew, Lee, Kerry Q.
• Primary Examiner(s): Obisesan, Augustine K
• Assistant Examiner(s): Mitiku, Berhanu
• Application Number:
  US13/434,551
• Time in Patent Office: 1,020 Days
• Field of Search: 707/610, 707/655, 707/736, 707/764, 711/162, 711/100, 711/E12.001, 711/E12.103
• US Class Current: 707/610
• CPC Class Codes: G06F 13/28 using burst mode transfer, e.g. direct memory access DMA, cycle steal G06F13/32 takes precedence
• CPC Class Codes: G06F 16/119 Details of migration of file systems migration mechanisms in storage systems G06F3/0647
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06
• CPC Class Codes: G06F 16/176 Support for shared access to files; File sharing support
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: G06F 16/1824 implemented using Network-attached Storage [NAS] architecture distributed or networked storage systems G06F3/067; protocols for distributed storage of data in a network H04L67/1097
• CPC Class Codes: G06F 16/1837 Management specially adapted to peer-to-peer storage networks topology management mechanisms of peer-to-peer networks H04L67/1042
• CPC Class Codes: G06F 16/185 Hierarchical storage management [HSM] systems, e.g. file migration or policies thereof details of archiving G06F16/11
• CPC Class Codes: G06F 16/196 Specific adaptations of the file system to access devices and non-file objects via standard file system access operations, e.g. pseudo file systems dedicated interfaces to storage systems G06F3/0601
• CPC Class Codes: G06F 16/211 Schema design and management
• CPC Class Codes: G06F 16/214 Database migration support
• 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 21/6218 to a system of files or objects, e.g. local or distributed file system or database
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0655 Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
• CPC Class Codes: G06F 3/0683 Plurality of storage devices

Abstract

A storage controller is implemented for controlling a storage system. The storage controller may be implemented using a distributed computer system and may include components for servicing client data requests based on the characteristics of the distributed computer system, the client, or the data requests. The storage controller is scalable independently of the storage system it controls. All components of the storage controller, as well as the client, may be virtual or hardware-based instances of a distributed computer system.

Claims

1. A computer-implemented method for accessing data storage devices, comprising:

receiving, by a computer system, from a client of a plurality of clients, information relating to requests by the client for data located on a first set of networked storage nodes among a plurality of networked storage nodes in a storage system, the information relating to requests by the client including data usage patterns associated with use of the data by the client;

receiving, from the storage system, information relating to at least an operational characteristic of the plurality of networked storage nodes;

determining, by the computer system, using at least the received data request-related information and the received operational characteristic-related information, that at least a subset of the data on the first set of networked storage nodes should at least be stored on a second set of networked storage nodes that differs from the first set, the received data request-related information indicating that the data to be located will be frequently accessed;

querying a map authority that non-transitively stores at least one data map, the at least one data map enabling the client to determine a location of the data on the plurality of networked storage nodes, for an authorization to store the subset of the data on the second set of networked storage nodes;

storing the subset of the data on the second set of networked storage nodes by moving from at least one device within the first set of storage nodes to at least one device within the second set of storage nodes, the second set of storage nodes having a higher level of input/output operations per time period than the first set of storage nodes; and

notifying the map authority to update the stored data map such that the updated stored data map enables the client to determine a location of the stored subset of the data on the plurality of networked storage nodes.

2. The computer-implemented method of claim 1, wherein the received client data request-related information includes information that the client is unable to access a subset of the data.

3. The computer-implemented method of claim 1, wherein the second set of storage nodes differs from the first set of storage nodes by a differing level of input/output operations per time period.

4. The computer-implemented method of claim 1, wherein the data request-related information includes information related to a history of past data access by the client.

5. The computer-implemented method of claim 1, wherein the authorization is an acknowledgement by the map authority.

24. The computer-implemented method of claim 1, wherein the client is implemented as a virtual machine instance.

6. A computer-implemented method for accessing data storage devices, comprising:

receiving, by a computer system, information relating to access of data stored, on a storage system, by an associated client entity of a plurality of client entities, the information relating to access of the data stored on the storage system including data usage patterns associated with use of the data by the associated client entity;

determining, by the computer system, using at least the received information relating to data access, that at least a subset of the data should be stored on a different location within the storage system, the received information relating to data access indicating that the data to be located will be frequently accessed;

communicating with a map authority that retains at least one data map, the at least one data map enabling the client to locate the data, to change the data map to reflect that the subset of the data is stored on the different location within the storage system; and

causing the subset of the data to be stored on the different location within the storage system by moving from at least one device within the storage system to at least one device within the different location of the storage system, the at least one device within the different location of the storage system having a higher level of input/output operations per time period than the at least one device within the storage system.

7. The computer-implemented method of claim 6, wherein the data access-related information is received from the associated client entity.

8. The computer-implemented method of claim 6, wherein the data access-related information includes information that at least a portion of the stored data is inaccessible by the associated client entity.

9. The computer-implemented method of claim 6, wherein the data access-related information includes information that the associated client entity'"'"'s demand for at least a portion of the stored data is greater than a predetermined level.

10. The computer-implemented method of claim 6, wherein the data is located on a data volume that is accessible by at least the associated client entity and that comprises a plurality of storage nodes in the storage system.

11. The computer-implemented method of claim 6, wherein the data access-related information includes information about one or more operational characteristics of the storage system.

12. A computer system for accessing data storage devices, comprising:

one or more processors; and

memory, including instructions executable by the one or more processors to cause the computer system to at least;

process information that relates to access, by a client entity of a plurality of client entities, to data on a storage system to determine characteristics of the client entity'"'"'s interaction with the data, the characteristics including data usage patterns associated with use of the data by the client entity;

determine, by at least analyzing the determined data interaction characteristics and at least one operational characteristic of the storage system, whether the data should be associated with a different location within the storage system, the information that relates to access indicating that the data to be located will be frequently accessed;

when determined that the data should associated with a different location, then request authorization from an authorizing entity to reassociate the data; and

when receiving the authorization in response to the request, then at least;

reassociating the data with the different location by moving from at least one device within the storage system to at least one device within the different location of the storage system, the at least one device within the different location of the storage system having a higher level of input/output operations per time period than the at least one device within the storage system; and

submitting information related to the different location to the authorizing entity such that the authorizing entity enables the client entity to locate the reassociated data.

13. The computer system of claim 12, wherein the client entity'"'"'s data interaction includes at least one of data write requests or data read requests.

14. The computer system of claim 12, wherein the determination of the data interaction characteristics includes an analysis of a data access history of at least the client entity.

15. The computer system of claim 12, wherein:

the access-related information is received from the client entity; and

the access-related information includes an indication that the client entity is unable to access a subset of the data.

16. The computer system of claim 12, wherein the executable instructions further cause the computer system to determine, by at least analyzing performance characteristics of at least a portion of the storage system, the at least one operational characteristic of the storage system.

17. The computer system of claim 16, wherein the at least one operational characteristic includes at least availability, to the client entity, of a plurality of data locations on the storage system.

18. One or more non-transitory computer-readable storage media having collectively stored thereon executable instructions that, when executed by one or more processors of a computing resource provider'"'"'s computer system, cause the computer system to at least:

determine whether data stored upon a storage system should be reassociated from a first location on the storage system to a second location on the storage system by at least;

analyzing data access information, received from a client instance of the computer system, about access to the data by the client instance, the data access information including data usage patterns associated with the use of the data by the client instance, the data access information indicating that the data to be located will be frequently accessed; and

analyzing storage system information, received from the storage system, about operational parameters of the storage system;

and when determined that the data should be reassociated, then cause the computer system to at least;

request an authorization from a map authority that stores mappings, the mappings enabling at least the client instance to locate the data within the storage system;

when the requested authorization is received, then at least;

reassociate the data from the first location to the second location by moving from at least one device within the first location on the storage system to at least one device within the second location on the storage system, the at least one device within the second location on the storage system having a higher level of input/output operations per time period than the at least one device within the first location on the storage system; and

submit information about the second location to the map authority.

19. The non-transitory computer-readable storage media of claim 18, wherein the data access information includes at least one of a latency of the client instance'"'"'s access to the data, availability of the data to the client instance, or a level of data throughput.

20. The non-transitory computer-readable storage media of claim 18, wherein the instructions further cause the computer system to determine whether the data should be reassociated based at least in part on a business-related requirement.

21. The non-transitory computer-readable storage media of claim 18, wherein the instructions are executed by at least the client instance.

22. The non-transitory computer-readable storage media of claim 18, wherein the reassociated data is moved from the first location to the second location.

23. The non-transitory computer-readable storage media of claim 18, wherein the data is reassociated by updating a copy of at least one of the mappings on the client instance.