CONFIGURATION OF PEERED CLUSTER STORAGE ENVIRONMENT ORGANIZED AS DISASTER RECOVERY GROUP

• US 20160057009A1
• Filed: 10/28/2014
• Published: 02/25/2016
• Est. Priority Date: 08/21/2014
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Keremane, Hrishikesh, Ramasubramaniam, Vaiapuri, Mittal, Rishabh, Patel, Chaitanya, Deshpande, Sameer, Kadayam, Harihara, Unnikrishnan, Santhosh
• Granted Patent: US 9,928,148 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/2069 Management of state, configuration or failover
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 11/2097 maintaining the standby controller/processing unit updated initialisation or re-synchronisation thereof G06F11/1658 and subgroups
• CPC Class Codes: H04L 41/0663 Performing the actions predefined by failover planning, e.g. switching to standby network elements
• CPC Class Codes: H04L 41/0873 Checking configuration conflicts between network elements
• CPC Class Codes: H04L 41/0893 Assignment of logical groups to network elements
• CPC Class Codes: H04L 45/02 Topology update or discovery
• CPC Class Codes: H04L 45/28 using route fault recovery
• CPC Class Codes: H04L 49/357 Fibre channel switches
• 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]

Abstract

A technique efficiently configures a peered cluster storage environment. The configuration technique illustratively includes three phases: a discovery phase, a node setup phase and a cluster setup phase. The discovery phase may be employed to initiate discovery of nodes of a disaster recovery (DR) group through transmission of multicast advertisement packets by the nodes over interconnects, including a Fibre Channel (FC) fabric, to each other node of the group. In the node setup phase, each node of a cluster assigns its relationships to the nodes discovered and present in the FC fabric; illustratively, the assigned relationships include high availability (HA) partner, DR primary partner and DR auxiliary partner. In the cluster setup phase, the discovered nodes of the FC fabric are organized as the peered cluster storage environment (DR group) configured to service data in a highly reliable and available manner.

Claims

1. A method comprising:

generating an advertisement at each node interconnected by a communication fabric of a disaster recovery (DR) group including two or more high availability (HA) groups;

transmitting the advertisement as a multicast transmission over the communication fabric, wherein the advertisement includes a payload containing properties of the node transmitting the advertisement;

processing the properties of the advertisement at each node of the DR group receiving the advertisement to assign roles to each node, wherein the assignment of roles is determined by sorting and ordering of each node to enable pairing of partner nodes based on ordinal numbering of a system identifier of each node;

constructing a node list indicating the assigned role of each node of the DR group; and

verifying a DR group configuration by comparing the node list to a cluster configuration table replicated at each node.

2. A system comprising:

one or more processors of a first node interconnected by a communication fabric to a plurality of second nodes to create a disaster recovery (DR) group including two or more high availability (HA) groups; and

a memory coupled to the one or more processors and configured to store a storage operating system implemented as one or more processes executable by the one or more processors to configure the DR group in accordance with a configuration technique, the one or more processes when executed operable to;

receive advertisements over the communication fabric from the second nodes of the DR group;

process the advertisements to assign roles to the second nodes, wherein the assigned roles include HA partner, DR primary partner and DR auxiliary partner roles; and

organize the first and second nodes as the DR group to service data in a reliable and available manner.

3. The system of claim 2 wherein the advertisements are multicast configuration packets.

4. The system of claim 2 wherein the configuration technique includes a discovery phase to initiate discovery of the first and second nodes of the DR group through multicast transmission of the advertisements by the first and second nodes over the communication fabric.

5. The system of claim 4 wherein the communication fabric is a Fibre Channel (FC) fabric and wherein the multicast transmission of the advertisements over the FC fabric uses an Extended Link Service (ELS) of a FC protocol.

6. The system of claim 5 wherein a process of the first node is embodied as a FC transport module configured to cooperate with the ELS to identify ports of an adapter of the first node that are present in the FC fabric.

7. The system of claim 6 wherein FC transport module simulates the multicast transmission by transmitting the advertisements one-by-one over the ports of the adapter.

8. The system of claim 2 wherein a payload of each advertisement contains role identification information embodied as properties of each second node transmitting the advertisement.

9. The system of claim 8 wherein the properties comprise:

a cluster identifier (ID) that identifies a cluster associated with the transmitting node; and

a node system ID that identifies hardware of the transmitting node.

10. The system of claim 9 wherein the node system ID comprises a non-volatile random access memory (NVRAM) ID.

11. The system of claim 9 wherein the configuration technique includes a node setup phase to assign the roles to the second nodes discovered in the communication fabric.

12. The system of claim 11 wherein a process of the first node is embodied as a configuration control module that assigns partner roles to the discovered nodes according to an algorithm that specifies sorting and ordering of the discovered nodes on each HA group to enable pairing of partner nodes based on ordinal numbering of the node system ID.

13. The system of claim 12 wherein the configuration control module constructs a node list indicating the roles and relationships among all nodes of the DR group.

14. The system of claim 13 wherein the configuration technique includes a cluster setup phase wherein the first node commits the node list to local storage to persistently store a DR group configuration and verifies the DR group configuration.

15. The system of claim 14 wherein the node list is persistently stored in response to a command invoked automatically by the configuration control module.

16. The system of claim 15 wherein verification of the DR group configuration is enabled by a globally reachable service configured as a cluster configuration table that is replicated on each node of the DR group.

17. The system of claim 16 wherein the DR group configuration of the node list is compared with global DR group configuration of the cluster configuration table to verify the DR group configuration.

18. The system of claim 17 wherein mirroring is activated in the DR group in response to verification of the DR group configuration.

19. The system of claim 18 wherein the mirroring comprises one of non-volatile random access memory (NVRAM) mirroring and write cache mirroring.

20. A non-transitory computer readable medium including program instructions for execution on one or more processors, the program instructions when executed operable to:

generate an advertisement at each node interconnected by a communication fabric of a disaster recovery (DR) group including two or more high availability (HA) groups;

transmit the advertisement as a multicast transmission over the communication fabric, wherein the advertisement includes a payload containing properties of the node transmitting the advertisement;

process the properties of the advertisement at each node of the DR group receiving the advertisement to assign roles to each node, wherein the assignment of roles is determined by sorting and ordering of each node to enable pairing of partner nodes based on ordinal numbering of a system identifier of each node;

construct a node list indicating the assigned role of each node of the DR group; and

verify a DR group configuration by comparing the node list to a cluster configuration table replicated at each node.