Multi-class heterogeneous clients in a clustered filesystem

• US 9,606,874 B2
• Filed: 09/09/2014
• Issued: 03/28/2017
• Est. Priority Date: 06/05/2001
• Status: Expired due to Term

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Silicon Graphics International Corporation (Hewlett-Packard Enterprise Company)
• Inventors: Moore, Daniel, Gildfind, Andrew
• Primary Examiner(s): Choi, Yuk Ting
• Application Number:
  US14/481,666
• Publication Number:
  US 20150012778A1
• Time in Patent Office: 931 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1448 Management of the data involved in backup or backup restore
• CPC Class Codes: G06F 11/1464 for networked environments
• CPC Class Codes: G06F 11/2069 Management of state, configuration or failover
• CPC Class Codes: G06F 16/128 Details of file system snapshots on the file-level, e.g. snapshot creation, administration, deletion use of snapshots for error detection or correction G06F11/14, G06F11/16
• CPC Class Codes: G06F 16/1827 Management specifically adapted to NAS management of storage area networks [SAN] G06F3/067
• 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 3/0617 in relation to availability
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: H04L 41/0813 characterised by the conditions triggering a change of settings
• 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 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

A cluster of computer system nodes connected by a storage area network include two classes of nodes. The first class of nodes can act as clients or servers, while the other nodes can only be clients. The client-only nodes require much less functionality and can be more easily supported by different operating systems. To minimize the amount of data transmitted during normal operation, the server responsible for maintaining a cluster configuration database repeatedly multicasts the IP address, its incarnation number and the most recent database generation number. Each node stores this information and when a change is detected, each node can request an update of the data needed by that node. A client-only node uses the IP address of the server to connect to the server, to download the information from the cluster database required by the client-only node and to upload local disk connectivity information.

Claims

1. A method for maintaining mirror consistency of data volumes in a cluster of computer system nodes, the method comprising:

maintaining mirror specific state information by one or more volume manager servers mirroring a data volume, wherein the mirrored data volume is accessible by any node in the cluster, wherein one or more servers are chosen to be a volume manager server when initializing a cluster of servers, and wherein at least one of the one or more volume manager servers stores a first mirror of the data volume;

determining that there was data lost on a data storage device storing at least a portion of the first mirrored data volume;

initiating the revival of data in an address range in the first mirrored data volume, wherein I/O requests from client nodes made to the address range being revived are refused by the at least one of the one or more volume manager servers mirroring the data volume during the revival of the address range in the first mirrored data volume; and

writing mirrored data from a second mirror of the data volume corresponding to the address range being revived in the first mirror of the data volume, wherein the mirrored data written to the first mirrored data volume was read from the second mirror of the data volume prior to writing.

2. The method of claim 1, wherein at least one other of the one or more volume manager servers receives configuration information from all client nodes and distributes changes to each of the client nodes.

3. The method of claim 1, wherein the refusing of at least one of the I/O requests comprising retiring at least one I/O request from a client node of the client nodes after a predetermined time interval without informing an application running on the client node when the mirrored data is currently being read from the second mirror.

4. The method of claim 3, further comprising:

receiving a message from the client node that the application wants to perform an I/O request to a portion of the of the address range being revived; and

transmitting a reply to the client node.

5. The method of claim 4, wherein the reply indicates that the I/O request overlaps an area being revived, and wherein the client node enters a loop where the access is retired periodically until it is successful without the application being aware that the client node entered the loop.

6. The method of claim 1, wherein at least the first mirrored data volume or the second mirrored data volume are striped across a plurality of data storage devices.

7. The method of claim 1, wherein the least one of the one or more volume manager servers receives configuration information from all client nodes and distributes changes to each client node of the client nodes.

8. A non-transitory computer readable storage medium having embodied thereon a program executable to perform a method for maintaining mirror consistency of data volumes in a cluster of computer system nodes, the method comprising:

maintaining mirror specific state information by one or more volume manager servers mirroring a data volume, wherein the mirrored data volume is accessible by any node in the cluster, wherein one or more servers are chosen to be a volume manager server when initializing a cluster of servers, and wherein at least one of the one or more volume manager servers stores a first mirror of the data volume;

determining that there was data lost on a data storage device storing at least a portion of the first mirrored data volume;

initiating the revival of data in an address range in the first mirrored data volume, wherein I/O requests from client nodes made to the address range being revived are refused by the at least one of the one or more volume manager servers mirroring the data volume during the revival of the address range in the first mirrored data volume; and

writing mirrored data from a second mirror of the data volume corresponding to the address range being revived in the first mirror of the data volume, wherein the mirrored data written to the first mirrored data volume was read from the second mirror of the data volume prior to writing.

9. The non-transitory computer readable storage medium of claim 8, wherein at least one other of the one or more volume manager servers receives configuration information from all client nodes and distributes changes to each of the client nodes.

10. The non-transitory computer readable storage medium of claim 8, wherein the refusing of at least one of the I/O requests comprising retiring at least one I/O request from a client node of the client nodes after a predetermined time interval without informing an application running on the client node when the mirrored data is currently being read from the second mirror.

11. The non-transitory computer readable storage medium of claim 10, the program being further executable to:

receive a message from the client node that the application wants to perform an I/O request to a portion of the of the address range being revived; and

transmit a reply to the client node.

12. The non-transitory computer readable storage medium of claim 11, wherein the reply indicates that the I/O request overlaps an area being revived, and wherein the client node enters a loop where the access is retired periodically until it is successful without the application being aware that the client node entered the loop.

13. The non-transitory computer readable storage medium of claim 8, wherein at least the first mirrored data volume or the second mirrored data volume are striped across a plurality of data storage devices.

14. The non-transitory computer readable storage medium of claim 8, wherein the least one of the one or more volume manager servers receives configuration information from all client nodes and distributes changes to each client node of the client nodes.

15. A system for maintaining mirror consistency of data volumes in a cluster of computer system nodes, the system comprising:

a processor and a memory in each of one or more volume manager servers mirroring a data volume, wherein the processor in each of the one or more volume manager servers executes instructions out of its memory to;

maintain mirror specific state information, wherein the mirrored data volume is accessible by any node in the cluster, wherein one or more servers are chosen to be a volume manager server when initializing a cluster of servers, and wherein at least one of the one or more volume manager servers stores a first mirror of the data volume;

determine that there was data lost on a data storage device storing at least a portion of the first mirrored data volume;

initiate the revival of data in an address range in the first mirrored data volume, wherein I/O requests from client nodes made to the address range being revived are refused by the at least one of the one or more volume manager servers mirroring the data volume during the revival of the address range in the first mirrored data volume; and

write mirrored data from a second mirror of the data volume corresponding to the address range being revived in the first mirror of the data volume, wherein the mirrored data written to the first mirrored data volume was read from the second mirror of the data volume prior to writing.

16. The system of claim 15, wherein at least one other of the one or more volume manager servers receives configuration information from all client nodes and distributes changes to each of the client nodes.

17. The system of claim 15, wherein the refusing of at least one of the I/O requests comprising retiring at least one I/O request from a client node of the client nodes after a predetermined time interval without informing an application running on the client node when the mirrored data is currently being read from the second mirror.

18. The system of claim 17, wherein the processor in each of the one or more volume manager servers executes instructions out of its memory to:

receive a message from the client node that the application wants to perform an I/O request to a portion of the of the address range being revived; and

transmit a reply to the client node.

19. The system of claim 18, wherein the reply indicates that the I/O request overlaps an area being revived, and wherein the client node enters a loop where the access is retired periodically until it is successful without the application being aware that the client node entered the loop.

20. The system of claim 15, wherein at least the first mirrored data volume or the second mirrored data volume are striped across a plurality of data storage devices.