Clustered RAID assimilation management

• US 9,619,351 B2
• Filed: 04/29/2016
• Issued: 04/11/2017
• Est. Priority Date: 01/07/2014
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Sundaram, Rajesh, Baddepudi, Bharat
• Primary Examiner(s): NGUYEN, HIEP T
• Application Number:
  US15/143,074
• Publication Number:
  US 20170075780A1
• Time in Patent Office: 347 Days
• CPC Class Codes: G06F 11/2069 Management of state, configuration or failover
• CPC Class Codes: G06F 11/2092 Techniques of failing over between control units
• CPC Class Codes: G06F 2201/805 Real-time
• CPC Class Codes: G06F 2201/82 Solving problems relating to consistency ensuring consistency in mirrored systems G06F11/2064
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0632 by initialisation or re-initialisation of storage systems
• CPC Class Codes: G06F 3/0634 by changing the state or mode of one or more devices
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

In one embodiment, a node of a cluster is coupled to a storage array of storage devices. The node executes a storage input/output (I/O) stack having a redundant array of independent disks (RAID) layer that organizes the storage devices within the storage array as a plurality of RAID groups. Configuration information is stored as a cluster database. The configuration information identifies the RAID groups associated with the storage devices. Each RAID group is associated with a plurality of segments and each segment has a different RAID configuration.

Claims

1. A system comprising:

a first node of a cluster coupled to a storage array of storage devices;

a first memory of the first node configured to store a storage input/output (I/O) stack executable by the first node, the storage I/O stack configured to organize a set of storage devices as an extent store within the storage array, the extent store having a plurality of RAID groups;

a first service storage device coupled to the first node and configured to store configuration information associating the RAID groups with one or more segments stored on the extent store, the set of storage devices of the extent store assimilated into the RAID groups by segment, each segment having a log-structured layout, the configuration information including an ownership of the extent store by the first node;

a second node of the cluster coupled to the storage array and coupled to a second service storage device, the configuration information replicated from the first service storage device to the second service storage device; and

a second memory of the second node configured to store a copy of the storage I/O stack executable by the second node, the copy of the storage I/O stack when executed, in response to a failure of the first node, configured to transfer ownership of the extent store from the first node to the second node and re-assimilate the set of storage devices of the extent store into the RAID groups by segment.

2. The system of claim 1 wherein replication of the configuration information is updated non-synchronously.

3. The system of claim 1 wherein a quorum of nodes of the cluster is used to update the configuration information.

4. The system of claim 1 wherein the configuration information is not stored in the RAID groups.

5. The system of claim 1 wherein the configuration information includes a status of each storage device in the set of storage devices, and wherein a change of the status of a respective storage device is updated via an atomic broadcast to the first and second nodes of the cluster.

6. The system of claim 1 wherein the configuration information includes RAID-related metadata of the RAID groups, and wherein the RAID-related metadata is separate from the extent store.

7. The system of claim 1 wherein the storage I/O stack when executed is further configured to:

in response to a failure of a storage device of the set of storage devices, re-assimilate a remaining portion of the set of storage devices into a new RAID group.

8. A method comprising:

organizing at a first node of a cluster coupled to a storage array of storage devices, a set of storage devices as an extent store having a plurality of RAID groups within the storage array, the extent store having one or more segments;

assimilating at the first node, the set of storage devices into the RAID groups by segment, each segment having a log-structured layout;

storing in a first service storage device coupled to the first node, configuration information associating the RAID groups with one or more segments of the extent store, the configuration information including an ownership of the extent store by the first node;

replicating the configuration information from the first service storage device to a second service storage device coupled to a second node of the cluster; and

in response to a failure of the first node, at a second node of the cluster, transferring ownership of the extent store from the first node to the second node and re-assimilating the set of storage devices of the extent store into the RAID groups by segment.

9. The method of claim 8 further comprising:

updating non-synchronously the replication of the configuration information.

10. The method of claim 8 wherein a quorum of nodes of the cluster is used to update the configuration information.

11. The method of claim 8 wherein the configuration information is not stored in the RAID groups.

12. The method of claim 8 further comprising:

updating a change of status of a storage device of the storage array via an atomic broadcast to the first and second nodes of the cluster, wherein the configuration information includes a status of each storage device in the set of storage devices.

13. The method of claim 8 wherein the configuration information includes RAID-related metadata of the RAID groups, and wherein the RAID-related metadata is separate from the extent store.

14. The method of claim 8 further comprising:

in response to a failure of a storage device of the set of storage devices, re-assimilating a remaining portion of the set of storage devices into a new RAID group.

15. A non-transitory computer readable medium including program instructions for execution on one or more processors, the program instructions configured to:

organize at a first node of a cluster coupled to a storage array of storage devices, a set of storage devices as an extent store having a plurality of RAID groups within the storage array, the extent store having one or more segments;

assimilate the set of storage devices into the RAID groups by segment, each segment having a log-structured layout;

store in a first service storage device coupled to the first node, configuration information associating the RAID groups with one or more segments of the extent store, the configuration information including an ownership of the extent store by the first node;

replicate the configuration information from the first service storage device to a second service storage device coupled to a second node of the cluster; and

in response to a failure of the first node, transfer ownership of the extent store from the first node to the second node and re-assimilate the set of storage devices of the extent store into the RAID groups by segment.

16. The non-transitory computer readable medium of claim 15 wherein program instructions are further configured to:

update non-synchronously the replication of the configuration information.

17. The non-transitory computer readable medium of claim 15 wherein a quorum of nodes of the cluster is used to update the configuration information.

18. The non-transitory computer readable medium of claim 15 wherein the configuration information is not stored in the RAID groups.

19. The non-transitory computer readable medium of claim 15 wherein the configuration information includes RAID-related metadata of the RAID groups, and wherein the RAID-related metadata is separate from the extent store.

20. The non-transitory computer readable medium of claim 15 wherein the program instructions are further configured to:

in response to a failure of a storage device of the set of storage devices, re-assimilate a remaining portion of the set of storage devices into a new RAID group.