High-availability of a storage system in a hierarchical virtual server environment

• US 8,386,838 B1
• Filed: 12/01/2009
• Issued: 02/26/2013
• Est. Priority Date: 12/01/2009
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Byan, Stephen M.
• Primary Examiner(s): MASKULINSKI, MICHAEL C
• Application Number:
  US12/628,913
• Time in Patent Office: 1,183 Days
• Field of Search: None
• US Class Current: 714/6.2
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1438 Restarting or rejuvenating
• CPC Class Codes: G06F 11/1484 involving virtual machines
• CPC Class Codes: G06F 11/2041 with more than one idle spare processing component
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence

Abstract

Described herein is a high-availability storage system having hierarchical levels of storage functions. The storage system may comprise one or more hierarchical levels, each hierarchical level comprising physical servers and be assigned to perform a particular set of storage functions. Each physical server may implement one or more VMs configured to perform only the set of storage functions assigned to the hierarchical level on which the VM executes. VMs of a first hierarchical level may be configured to organize the VMs of a second hierarchical level into a redundant array of storage access servers for providing data reliability and high-availability of the storage system. VMs of a first hierarchical level are configured to produce and route sub-requests to the VMs of a second hierarchical level. Failure of a sub-request is detected and remedied by a VM of the first hierarchical level.

Claims

1. A method for providing high-availability of client data comprising:

configuring a plurality of storage access servers as a redundant array of storage access servers (RASAS), each storage access server comprising;

a set of one or more storage devices for storing client data;

one or more storage access virtual machines (VMs), each storage access VM executing a separate storage operating system providing an overall set of storage functions, each storage access VM configured for performing only an assigned sub-set of storage functions of the overall set of storage functions and is not configured for performing all storage functions of the overall set of storage functions provided by the storage operating system, the assigned sub-set of storage functions of each storage access VM comprising storage access functions for receiving storage access sub-requests from a storage transaction server and executing the storage access sub-requests on the set of storage devices; and

configuring at least one storage transaction server for;

receiving an access request from a client system;

producing at least two storage access sub-requests from the received access request, the at least two storage access sub-requests being based on the RASAS configuration of the plurality of storage access servers;

communicating each storage access sub-request to a storage access server for execution.

2. The method of claim 1, wherein:

the at least one storage transaction server is further configured for monitoring the success or failure of the at least two storage access sub-requests.

3. The method of claim 1, wherein:

the at least one storage transaction server is further configured for invoking a storage reconstruction operation involving at least one of the at least two storage access servers.

4. The method of claim 3, wherein:

invoking a storage reconstruction operation allocates a replacement storage access VM on a physical server.

5. The method of claim 4, further comprising:

replay of logged write requests to the replacement storage access VM on a physical server.

6. The method of claim 1, wherein:

the plurality of storage access servers is configured as a RASAS using a mirroring configuration;

the received access request comprises a write request comprising client data to be stored; and

the at least two storage access sub-requests comprises a first storage access sub-request communicated to a first storage access server and a second storage access sub-request communicated to a second storage access server, each storage access sub-request specifying storage of all the received client data, the first storage access server storing all the received client data to its set of storage devices and the second storage access server storing all the received client data to its set of storage devices.

7. The method of claim 1, wherein:

the plurality of storage access servers is configured as a RASAS using a striping configuration;

the received access request comprises a write request comprising client data to be stored; and

the at least two storage access sub-requests comprises a first storage access sub-request communicated to a first storage access server and a second storage access sub-request communicated to a second storage access server, the first storage access sub-request specifying storage of a first sub-set of the client data and the second storage access sub-request specifying storage of a second sub-set of the client data, the first storage access server storing the first sub-set of the client data to its set of storage devices and the second storage access server storing the second sub-set of the client data to its set of storage devices.

8. A non-transitory computer readable medium having instructions stored thereon when executed by a processor, provide high-availability of client data, the computer readable medium comprising instructions for:

configuring a plurality of storage access servers as a redundant array of storage access servers (RASAS), each storage access server comprising;

a set of one or more storage devices for storing client data;

one or more storage access virtual machines (VMs), each storage access VM executing a separate storage operating system providing an overall set of storage functions, each storage access VM configured for performing only an assigned sub-set of storage functions of the overall set of storage functions and is not configured for performing all storage functions of the overall set of storage functions provided by the storage operating system, the assigned sub-set of storage functions of each storage access VM comprising storage access functions for receiving storage access sub-requests from a storage transaction server and executing the storage access sub-requests on the set of storage devices; and

configuring at least one storage transaction server for;

receiving an access request from a client system;

producing at least two storage access sub-requests from the received access request, the at least one storage access sub-requests being based on the RASAS configuration of the plurality of storage access servers;

communicating each storage access sub-request to a storage access server for execution.

9. The non-transitory computer readable medium of claim 8, wherein:

the at least one storage transaction server is further configured for monitoring the success or failure of the at least one storage access sub-requests.

10. The non-transitory computer readable medium of claim 8, wherein:

the at least one storage transaction server is further configured for invoking a storage reconstruction operation involving at least one of the at least two storage access servers.

11. The non-transitory computer readable medium of claim 10, wherein:

invoking a storage reconstruction operation allocates a replacement storage access VM on a physical server.

12. The non-transitory computer readable medium of claim 11, further comprising instructions for:

replay of logged write requests to the replacement storage access VM on a physical server.

13. The non-transitory computer readable medium of claim 8, wherein:

the plurality of storage access servers is configured as a RASAS using a mirroring configuration;

the received access request comprises a write request comprising client data to be stored; and

the at least two storage access sub-requests comprises a first storage access sub-request communicated to a first storage access server and a second storage access sub-request communicated to a second storage access server, each storage access sub-request specifying storage of all the received client data, the first storage access server storing all the received client data to its set of storage devices and the second storage access server storing all the received client data to its set of storage devices.

14. The non-transitory computer readable medium of claim 8, wherein:

the plurality of storage access servers is configured as a RASAS using a striping configuration;

the received access request comprises a write request comprising client data to be stored; and

the at least two storage access sub-requests comprises a first storage access sub-request communicated to a first storage access server and a second storage access sub-request communicated to a second storage access server, the first storage access sub-request specifying storage of a first sub-set of the client data and the second storage access sub-request specifying storage of a second sub-set of the client data, the first storage access server storing the first sub-set of the client data to its set of storage devices and the second storage access server storing the second sub-set of the client data to its set of storage devices.

15. A system comprising:

a plurality of storage access servers configured as a redundant array of storage access servers (RASAS), each storage access server comprising;

a set of one or more storage devices for storing client data;

a memory for storing application instructions;

a processor for executing the application instructions;

one or more storage access virtual machines (VMs), each storage access VM executing a separate storage operating system providing an overall set of storage functions, each storage access VM configured for performing only an assigned sub-set of storage functions of the overall set of storage functions and is not configured for performing all storage functions of the overall set of storage functions provided by the storage operating system, the assigned sub-set of storage functions of each storage access VM comprising storage access functions for receiving storage access sub-requests from a storage transaction server and executing the storage access sub-requests on the set of storage devices; and

at least one storage transaction server configured for;

receiving an access request from a client system;

producing at least two storage access sub-requests from the received access request, the at least two storage access sub-requests being based on the RASAS configuration of the plurality of storage access servers;

communicating each storage access sub-request to a storage access server for execution.

16. The system of claim 15, wherein:

the at least one storage transaction server is further configured for monitoring the success or failure of the at least two storage access sub-requests.

17. The system of claim 15, wherein:

the at least one storage transaction server is further configured for invoking a storage reconstruction operation involving at least one of the at least two storage access servers.

18. The system of claim 17, wherein:

invoking a storage reconstruction operation allocates a replacement storage access VM on a physical server.

19. The system of claim 18, wherein:

logged write requests are replayed to the replacement storage access VM on a physical server.

20. The system of claim 15, wherein:

the plurality of storage access servers is configured as a RASAS using a mirroring configuration;

the received access request comprises a write request comprising client data to be stored; and

the at least two storage access sub-requests comprises a first storage access sub-request communicated to a first storage access server and a second storage access sub-request communicated to a second storage access server, each storage access sub-request specifying storage of all the received client data, the first storage access server storing all the received client data to its set of storage devices and the second storage access server storing all the received client data to its set of storage devices.

21. The system of claim 15, wherein:

the plurality of storage access servers is configured as a RASAS using a striping configuration;

the received access request comprises a write request comprising client data to be stored; and

the at least two storage access sub-requests comprises a first storage access sub-request communicated to a first storage access server and a second storage access sub-request communicated to a second storage access server, the first storage access sub-request specifying storage of a first sub-set of the client data and the second storage access sub-request specifying storage of a second sub-set of the client data, the first storage access server storing the first sub-set of the client data to its set of storage devices and the second storage access server storing the second sub-set of the client data to its set of storage devices.