Distributed data storage controller

• US 9,531,809 B1
• Filed: 08/11/2014
• Issued: 12/27/2016
• 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): Walsh, John B
• Application Number:
  US14/456,979
• Time in Patent Office: 869 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: G06F 16/188 Virtual file systems
• 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 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0617 in relation to availability
• CPC Class Codes: G06F 3/0662 Virtualisation aspects
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

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, comprising:

implementing a data mapping engine on a client device using a virtual machine instance running on the client device, the data mapping engine configured at least to receive data requests from the virtual machine instance running on the client device;

receiving, by the virtual machine instance, a portion of a data map;

determining, by the data mapping engine using at least the portion of the data map, a server request based at least in part on a data request of the received data requests, the server request identifying data within a data storage system, the server request determined at least in part by a placement engine implemented across one or more computer systems, the placement engine determining the server request based at least on data storage-related information received from at least one of the client device or the data storage system;

transmitting the server request to the data storage system;

after transmitting the server request, receiving a response from the data storage system;

updating, based at least in part on the response from the data storage system, the portion of the data map; and

transmitting information related to the updated portion of the data map to a map authority.

2. The computer-implemented method of claim 1, wherein the placement engine is configured at least to accept optimization requests from the client device;

and the method further comprises;

determining, by the placement engine, the server request in response to a optimization request; and

transmitting the information related to the updated portion of the data map to the client device.

3. The computer-implemented method of claim 2, wherein:

the optimization request is requested by the client device due to a level of at least one of accessibility or performance that is below a determined threshold; and

the information related to the updated portion of the data map transmitted to the client device is operable, by the client device, to access data at a second level of at least accessibility or performance that is at least equal to the determined threshold.

4. The computer-implemented method of claim 1, wherein the data mapping engine is implemented such that it is protected from hardware failure of one or more components of the client device.

5. The computer-implemented method of claim 1, wherein the data mapping engine communicates with the data storage system via a connection compliant with a connection standard that includes at least one of iSCSI, Global Network Block Device (GNBD), or Fibre Channel over Ethernet (FCoE).

6. The computer-implemented method of claim 1, wherein the data storage-related information includes an identification that the virtual machine instance has dissolved or diassociated.

7. The computer-implemented method of claim 1, further comprising transmitting the updated portion of the data map to the data mapping engine on the client device.

8. The computer-implemented method of claim 1, wherein the data storage-related information received from the data storage system indicates a data request level that is higher than a predetermined level.

9. The computer-implemented method of claim 1, further comprising, upon authentication by an entity associated with the client device, transmitting the updated portion of the data map to the entity.

10. One or more computer-readable storage devices for storing computer-executable instructions that, when executed by one or more computer systems, configure the one or more computer systems to perform operations, comprising:

implementing a data mapping engine on a client device, the data mapping engine configured to at least receive data requests;

receiving, by the client device, at least a portion of a map from a map authority that is implemented with the one or more computer systems, the portion of the map including information associating at least one or more block addresses accessible by the client device to one or more locations of a data storage system;

translating, using the map, the data requests of the client device into server requests to be transmitted to the data storage system, the server requests being operable to locate data responsive to the data requests within the data storage system;

transmitting the server requests to the data storage system;

collecting, by an instance running on the client device, characteristic information associated with translating the data requests of the client device into the server requests; and

optimizing a future translation of data requests based in part on the collected characteristic information.

11. The one or more computer-readable storage devices of claim 10, wherein the instructions further configure the one or more computer systems to perform operations comprising:

receiving server request information from the data storage system;

determining, based at least in part on the server request information, to adjust the map;

adjusting, based at least in part on the server request information, the map; and

providing at least information relating to the updated map to the map authority implemented by the one or more computer systems.

12. The one or more computer-readable storage devices of claim 11, wherein the instructions further configure the one or more computer systems to perform operations comprising:

determining, using a placement engine implemented across a subset of the one or more computer systems, a set of server requests from the server requests, the set of server requests being operable to locate the data at a level of at least one of performance or availability that is greater than a level of at least one of performance or availability of at least one alternate server request, and wherein;

the placement engine determines the set of server requests based at least on information received by the placement engine from at least one of the client device or the data storage system; and

the server requests include at least a particular server request from the set of server requests.

13. The one or more computer-readable storage devices of claim 12, wherein the placement engine and the map authority are implemented together on the one or more computer systems.

14. The one or more computer-readable storage devices of claim 12, wherein:

the placement engine is configured at least to receive optimization requests from at least an entity of the client device;

the placement engine determines an optimal set of server requests in response to the optimization requests; and

the information related to the updated map is transmitted to at least the entity of the client device.

15. The one or more computer-readable storage devices of claim 10, wherein the characteristic information includes at least one of latency, data storage availability, or performance characteristics.

16. A computer system, comprising:

memory that stores computer-executable instructions; and

at least one processor configured to access the memory and execute the computer-executable instructions to collectively at least;

implement a data mapping engine on a client, the data mapping engine configured to at least receive data requests;

store a data table at the client using an authoritative entity comprised of a subset of resources of the computer system;

receive a copy of the data table by the client of the computer system and from the authoritative entity;

process a data request operable to locate stored data within a data storage system by the client and using at least the copy of the data table received by the client;

transmit a data location command determined based in part on the data request by the client, the data location command from a plurality of data location commands to the data storage system;

receive, from the data storage system, a portion of the stored data related to the data location command;

determine, based in part on the portion of the stored data related to the data location command and determining that the copy of the data table contains at least one incorrect reference to data within the data storage system; and

adjust, by the client, the copy of the data table to correct the at least one incorrect reference.

17. The computer system of claim 16, wherein the data location command comprises a SCSI command.

18. The computer system of claim 16, wherein the data storage system comprises a plurality of data volumes that are attached to a plurality of clients of the computer system.

19. The computer system of claim 16, wherein the at least one processor is further configured to access the memory and execute the computer-executable instructions to collectively at least determine, using an engine implemented across one or more resources of the computer system, a set of data location commands among the plurality of data location commands, and wherein:

particular data location commands of the set of data location commands are operable to locate the stored data at a level of at least one of performance or availability that is greater than the level corresponding to at least one alternate set of data location commands;

the engine determines the set of data location commands based at least in part on information received by the engine from at least one of the client or the data storage system, and the plurality of data location commands includes at least the set of data location commands.

20. The computer system of claim 19, wherein:

the engine is configured at least to accept optimization requests from at least an entity of the client;

the engine determines a set of server requests in response to the optimization requests;

information related to the adjusted copy of the data table is submitted to at least the client; and

an updated portion of the data table is transmitted to at least the entity of the client device.