System and method for monitoring cluster partner boot status over a cluster interconnect

• US 7,171,452 B1
• Filed: 10/31/2002
• Issued: 01/30/2007
• Est. Priority Date: 10/31/2002
• Status: Expired due to Fees

• Current Assignee: NetApp, Inc.
• Original Assignee: Network Appliance Incorporated (NetApp, Inc.)
• Inventors: Gole, Abhijeet
• Primary Examiner(s): Barot; Bharat
• Application Number:
  US10/284,795
• Time in Patent Office: 1,552 Days
• Field of Search: 709/203, 709/212, 709/217, 709/224, 709/227, 709/228, 709/230, 709/250, 709/222
• US Class Current: 709/212
• CPC Class Codes: G06F 11/2092 Techniques of failing over between control units
• CPC Class Codes: G06F 11/3055 Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available error or fault processing without redundancy G06F11/0703; error detection or correction by redundancy in data representation G06F11/08; error detection or correction by redundancy in operation G06F11/14; error detection or correction by redundancy in hardware G06F11/16
• CPC Class Codes: G06F 11/3065 Monitoring arrangements determined by the means or processing involved in reporting the monitored data error or fault reporting or logging G06F11/0766
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/0817 by checking functioning
• CPC Class Codes: H04L 43/10 Active monitoring, e.g. heartbeat, ping or trace-route

Abstract

A system and method for monitoring cluster partner boot status over a RDMA-capable transport protocol is provided. Upon initialization, a storage system in a cluster generates a virtual interface connection using a predetermined and pre-assigned fibre channel identification and virtual interface number. The surviving storage system may then open a connection to this predetermined and predefined virtual interface connection and issue RDMA commands thereto. This surviving storage system may utilize the RDMA capabilities of the virtual interface protocol to obtain a set of boot statistics to determine whether the booting file or storage system is progressing normally.

Claims

1. A method for monitoring a cluster partner boot status over a remote direct memory access-capable transport protocol, the method comprising the steps of:

creating, on a booting cluster partner, a protocol interface, the protocol interface utilizing a predetermined and pre-assigned identification;

opening, by a surviving cluster partner, a connection to the created protocol interface; and

performing, by the surviving cluster partner via the connection, a remote direct memory access to obtain a set of boot variables of the booting cluster partner.

2. The method of claim 1 further comprising the steps of:

determining, from the set of boot variables, whether the booting cluster partner is progressing normally;

performing, in response to the booting cluster partner not progressing normally, a failover routine; and

completing, in response to the booting cluster partner progressing normally, an initialization routine on the booting cluster partner.

3. The method of claim 1 wherein the transport protocol further comprises a virtual interface protocol.

4. The method of claim 1 wherein the predetermined and pre-assigned identification further comprises a virtual interface number and fibre channel identification.

5. A method for monitoring cluster partner boot status over a cluster interconnect, the method comprising the steps of:

generating, upon boot initialization, one or more protocol connections, the protocol connections utilizing a predetermined and pre-assigned identification;

issuing, by a non-booting cluster partner, a remote direct memory access operation to the booting cluster partner; and

whereby the remote direct memory access operation retrieves a set of boot variables from the booting cluster partner.

6. The method of claim 5 further comprising the steps of:

determining, from the set of boot variables, whether the booting cluster partner is progressing normally.

7. A storage system cluster comprising:

a booting storage system, the booting storage system configured to create, using predetermined and preassigned identification, one or more connection interfaces;

a surviving storage system, the surviving storage system configured to perform remote direct memory access operations using the connection interfaces to obtain a set of boot variables; and

whereby the surviving storage system is further configured to determine from the set of boot variables whether to perform a failover operation.

8. The storage system cluster of claim 7 wherein the remote direct memory access operations are performed using a virtual interface connection.

9. A storage system, comprising:

a first cluster partner configured to;

i) begin an initialization process in response a failure of the first cluster partner, and ii) store a boot status of the initialization process as one or more boot variables;

a second cluster partner configured to monitor the boot status of the first cluster partner; and

a cluster interconnect to connect the first and second cluster partners, wherein the second cluster partner is further configured to request the boot variables from the first cluster partner over the cluster interconnect prior to completion of the initialization process.

10. The storage system of claim 9, wherein the second cluster partner is further configured to determine that the initialization process on the first cluster partner is not progressing normally based on the boot variables, and in response, to perform a failover routine.

11. The storage system of claim 9, wherein the second cluster partner is further configured to determine that the initialization process on the first cluster partner is progressing normally based on the boot variables, and in response, to allow the initialization process to complete.

12. The storage system of claim 9, further comprising:

a memory of the first cluster partner configured to store the boot variables in a particular location, wherein the second cluster partner is further adapted to request the boot variables by sending a read request to the memory of the first cluster partner for the particular location.

13. The storage system of claim 9, wherein the second cluster partner is further configured to determine the boot variables of the first cluster partner by a remote direct memory access by the second cluster partner to the first cluster partner.

14. The storage system of claim 9, wherein the cluster interconnect comprises a Virtual Interface.

15. The storage system of claim 9, wherein the cluster interconnect is configured to utilize a Fibre Channel protocol.

16. The storage system of claim 9, wherein the first and second cluster partners are storage systems.

17. The storage system of claim 9, wherein at least one of the boot variables indicates a boot stage of the initialization process.

18. The storage system of claim 9, wherein at least one of the boot variables indicates a boot progress of the initialization process.

19. The storage system of claim 9, wherein the boot progress is indicated by a value adapted to be incremented in response to progression of the initialization process.