Reliable leader election in storage area network

• US 20050132154A1
• Filed: 10/03/2003
• Published: 06/16/2005
• Est. Priority Date: 10/03/2003
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Rao, Sudhir G., Rees, Robert M., Burns, Randal C., Long, Darrell D. E.
• Application Number:
  US10/678,858
• Publication Number:
  US 20050132154A1
• Time in Patent Office: Days
• US Class Current: 711/162
• CPC Class Codes: G06F 11/1425 by reconfiguration of node membership
• 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 67/61 taking into account QoS or priority requirements

Abstract

A method and system for election of a cluster leader in a storage area network is provided Each node in a grouping of storage area network nodes communicates with each of the nodes on a periodic basis to determine if any of the nodes have failed (42). In the event of a cluster fault, each node may request a position of cluster leader. A pruning protocol (60) is invoked to ensure efficient convergence of a single cluster leader candidate to favor a majority grouping leader candidate to become the new cluster leader. In the event the leader candidate from the majority grouping has failed to become the new cluster leader, a minority grouping leader candidate can become the cluster leader. Following the pruning protocol, a voting protocol (100) is invoked followed by lock of the quorum disk (138) by the elected cluster leader candidate.

Claims

1. A method of leader election in a multi-node storage area network, comprising:

(a) each node communicating to all nodes within a cluster of storage area network nodes of loss of connectivity between a node in said cluster and a cluster leader,

(b) pruning a quantity of cluster leader candidates in response to loss of connectivity; and

(c) validating approval of node leadership election within said cluster of nodes to function as a new cluster leader.

2. The method of claim 1, wherein the step of pruning cluster leader candidates includes a recipient node of said communication requesting a node with a higher identifier node value to refrain from requesting a position of new cluster leader candidate.

3. The method of claim 1, further comprising determining if said new leader candidate is from a majority grouping of said nodes within said cluster of nodes.

4. The method of claim 1, wherein the step of poling cluster leader candidates includes mitigating time to convergence of election of said new cluster leader.

5. The method of claim 1, wherein the step of validating approval of node leadership election within said cluster of nodes to function as a new cluster leader includes biasing cluster reformation from a group consisting of:

a majority grouping of nodes within said cluster of nodes, and connectivity with a select group of clients in communication with said cluster, and combinations thereof.

6. The method of claim 5, further comprising requiring additional time for election of said node leader candidate from a minority grouping of nodes within said cluster of nodes.

7. The method of claim 1, further comprising the step of electing said new cluster leader candidate from a minority grouping of nodes within said cluster of nodes upon failure of a cluster leader candidate from a majority grouping of nodes, wherein said failure is selected from a group consisting of lock of said quorum disk, and said cluster leader candidate, and combinations thereof.

8. The method of claim 1, further comprising election a node within a connected grouping of nodes to function as a new leader candidate, wherein said node is selected from a group consisting of a majority connected grouping of nodes and a minority connected grouping of nodes.

9. A storage area network system comprising:

a group of storage area network nodes with one node adapted to function as a cluster leader,

a communication manager to enable each node to inform all nodes within a cluster of nodes of loss of connectivity between a node in said cluster and said cluster leader,

a pruning protocol adapted to mitigate a quantity of cluster leader candidates in response to the loss of connectivity; and

a validation protocol adapted to approve a new cluster leader in response to said pruning protocol.

10. The system of claim 9, wherein said pruning protocol includes an informed node adapted to petition all nodes within said group of nodes with a higher node identifier to refrain from a request for position of cluster leader.

11. The system of claim 9, wherein said validation protocol includes a determination of origination of said cluster leader candidate from a majority grouping of said nodes.

12. The system of claim 9, wherein said validation protocol is adapted to bias cluster reformation from a group consisting of:

a majority grouping of nodes within said cluster of nodes, and connectivity with a select group of clients in communication with said cluster, and combinations thereof.

13. The system of claim 9, further comprising an election manager adapted to enable election of said new cluster leader candidate from a group consisting of:

a majority connected grouping of nodes, and a minority connected grouping of nodes.

14. The system of claim 13, wherein said election manager is responsive to failure of a cluster leader candidate from a majority grouping of nodes to acquire a quorum disk lock.

15. An article comprising:

a computer-readable signal-rig medium;

means in the medium for informing all nodes within a cluster of storage area network nodes of loss of communication between a node in said cluster and a cluster leader,

means in the medium for mitigating a quantity of cluster leader candidates responsive to said loss of communication; and

means in the medium for validating election of a new cluster leader responsive to mitigation of said quantity of candidates.

16. The article of claim 15, wherein the medium is selected from a group consisting of;

a recordable data storage medium, and a modulated carrier signal.

17. The article of claim 15, wherein said means for informing all nodes of loss of communication with a cluster leader includes a communication manager.

18. The article of claim 15, wherein said means for mitigating a quantity of cluster leader candidates includes a pruning protocol adapted to petition all informed nodes with a higher node identifier to refrain from a request for a new cluster leader position.

19. The article of claim 15, wherein said means for validating election of a new cluster leader includes a validation protocol adapted to bias cluster reformation from a group consisting of:

a majority grouping of nodes within said cluster of nodes, and connectivity with a select group of clients in communication with said cluster, and combinations thereof.

20. The article of claim 15, wherein said new cluster leader is selected from a group consisting of:

a majority connected grouping of nodes, and a minority connected grouping of nodes.