Method, apparatus and program storage device for providing failover for high availability in an N-way shared-nothing cluster system

• US 20050283658A1
• Filed: 05/21/2004
• Published: 12/22/2005
• Est. Priority Date: 05/21/2004
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: D'Costa, Austin F., Rao, Sudhir G., Clark, Thomas K., Seeger, James J.
• Application Number:
  US10/850,749
• Publication Number:
  US 20050283658A1
• Time in Patent Office: Days
• US Class Current: 714/11
• CPC Class Codes: G06F 11/1482 by means of middleware or OS functionality
• CPC Class Codes: G06F 11/2025 using centralised failover control functionality
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/203 using migration
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence
• CPC Class Codes: G06F 11/2048 where the redundant components share neither address space nor persistent storage

Abstract

A method, apparatus and program storage device for providing failover for continuous or near-continuous availability in an N-way logical shared-nothing cluster system is disclosed. Cluster application data space partitions are assigned to each node in the cluster and each node'"'"'s or server software'"'"'s internal architecture is partitioned in accordance with the application data partitions assigned to the node. Cluster-integrity protection is performed. A failover and recovery protocol is performed based upon the assigned partitions and the partitioned and bound internal architecture. Containment of the impact of failure is provided such that most of the application data space partitions are not impacted. Affected partition sets are failed over fast and in constant time and so actual load on the surviving nodes does not affect failover duration. When shared storage is not provided, synchronous log replication may be used to facilitate failover and log-based recovery.

Claims

1. A program storage device, comprising:

program instructions executable by a processing device to perform operations for providing continuous or near-continuous availability in an N-way shared-nothing cluster system, the operations comprising;

assigning cluster application data space partitions to each node in a cluster; and

partitioning and binding internal architecture to the cluster application data space partitions assigned to the node.

2. The program storage device of claim 1 further comprising:

performing cluster-integrity protection; and

performing a failover and recovery protocol based upon the assigned partitions and the partitioned and bound internal architecture.

3. The program storage device of claim 2, wherein the N-way shared-nothing cluster system includes shared storage for providing a logical shared-nothing cluster system, wherein the failover and recovery protocol comprises accessing by at least one node in the cluster system logs and data space partitions of the failed node in the cluster system.

4. The program storage device of claim 2, wherein the N-way shared-nothing cluster system includes a plurality of nodes, each of the plurality of nodes owning a storage device for providing a physical shared-nothing cluster system, wherein the failover and recovery protocol comprises providing a surviving node synchronous log record access to logs of a failed node and replicating the log of the failed node in storage owned by the surviving node.

5. The program storage device of claim 1, wherein the partitioning and binding internal architecture to the cluster application data space partitions assigned to the node comprises partitioning internal system architecture and structures of a node in accordance with partitioned application data space of the node.

6. The program storage device of claim 5, wherein the partitioning internal system architecture and structures includes partitioning of transaction queues, buffer cache and associated synchronization primitives of a node in accordance with partitioned application data space of the node.

7. The program storage device of claim 2, wherein the performing cluster-integrity protection further comprises:

maintaining nodes in a cluster membership during cluster recovery unless the node fails or is dropped from the cluster by administrative action;

monitoring cluster members participating in the recovery protocol by a leader determined from the nodes in the cluster; and

monitoring the leader by the cluster members participating in the recovery protocol.

8. The program storage device of claim 2, wherein the recovery protocol further comprises:

initiating cluster membership validation and teardown of affected file sets;

updating cluster membership based upon initiation of cluster membership validation and concurrently fencing rogue servers;

committing the cluster membership update; and

failing over affected partitions to at least one surviving node.

9. A computing device for use in a N-way shared-nothing cluster system, comprising:

memory for storing data therein; and

a processor, coupled to the memory, the processor configured to perform an operation by assigning cluster application data space partitions, and partitioning and binding internal architecture to the cluster application data space partitions.

10. The computing device of claim 9, wherein the processor is further configured to perform cluster-integrity protection and to perform a failover and recovery protocol based upon the assigned partitions and the partitioned and bound internal architecture.

11. The computing device of claim 10, wherein the processor performs a failover and recovery protocol by accessing logs of a failed node and replicating the log of the failed node.

12. The computing device of claim 9, wherein the processor partitions and binds internal architecture to cluster application data space partitions by partitioning internal system architecture and structures in accordance with partitioned application data space.

13. The computing device of claim 10, wherein the processor performs cluster-integrity protection by maintaining nodes in a cluster membership during cluster recovery unless the node fails or is dropped from the cluster by administrative action, monitoring cluster members participating in the recovery protocol by a leader determined from the nodes in the cluster and monitoring the leader by the cluster members participating in the recovery protocol.

14. The computing device of claim 10, wherein the processor performs the failover and recovery protocol by initiating cluster membership validation and teardown of affected file sets, updating cluster membership based upon initiation of cluster membership validation and concurrently fencing rogue servers, committing the cluster membership update and carrying out failing over of affected partitions to at least one surviving node.

15. A method providing continuous or near-continuous availability in an N-way shared-nothing cluster system, comprising:

assigning cluster application data space partitions to each node in a cluster; and

partitioning and binding internal architecture to the cluster application data space partitions assigned to the node.

16. The method of claim 15 further comprising:

performing cluster-integrity protection; and

performing a failover and recovery protocol based upon the assigned partitions and the partitioned and bound internal architecture.

17. The method of claim 16, wherein the N-way shared-nothing cluster system includes shared storage for providing a logical shared-nothing cluster system, wherein the failover and recovery protocol comprises accessing by at least one node in the cluster system logs and data space partitions of the failed node in the cluster system.

18. The method of claim 16, wherein the N-way shared-nothing cluster system includes a plurality of nodes, each of the plurality of nodes owning a storage device for providing a physical shared-nothing cluster system, wherein the failover and recovery protocol comprises providing a surviving node synchronous log record access to logs of a failed node and replicating the log of the failed node in storage owned by the surviving node.

19. The method of claim 15, wherein the partitioning and binding internal architecture to the cluster application data space partitions assigned to the node comprises partitioning internal system architecture and structures of a node in accordance with partitioned application data space of the node.

20. The method of claim 19, wherein the partitioning internal system architecture and structures includes partitioning of transaction queues, buffer cache and associated synchronization primitives of a node in accordance with partitioned application data space of the node.

21. The method of claim 16, wherein the performing cluster-integrity protection further comprises:

maintaining nodes in a cluster membership during cluster recovery unless the node fails or is dropped from the cluster by administrative action;

monitoring cluster members participating in the recovery protocol by a leader determined from the nodes in the cluster; and

monitoring the leader by the cluster members participating in the recovery protocol.

22. The method of claim 16, wherein the recovery protocol further comprises:

initiating cluster membership validation and teardown of affected file sets;

updating cluster membership based upon initiation of cluster membership validation and concurrently fencing rogue servers;

committing the cluster membership update; and

failing over affected partitions to at least one surviving node.