Serviceability and test infrastructure for distributed systems

• US 7,475,296 B2
• Filed: 05/20/2004
• Issued: 01/06/2009
• Est. Priority Date: 05/20/2004
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Rao, Sudhir G., Satyanarayana, Pradeep
• Primary Examiner(s): Chace; Christian P.
• Assistant Examiner(s): Hoffler; Raheem
• Application Number:
  US10/849,658
• Publication Number:
  US 20050273675A1
• Time in Patent Office: 1,692 Days
• Field of Search: 714/100, 714/39, 714/49, 707/49
• US Class Current: 714/100
• CPC Class Codes: G06F 11/0709 in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
• CPC Class Codes: G06F 11/0778 Dumping, i.e. gathering error/state information after a fault for later diagnosis
• CPC Class Codes: G06F 11/0784 Routing of error reports, e.g. with a specific transmission path or data flow
• CPC Class Codes: G06F 9/542 Event management; Broadcasting; Multicasting; Notifications
• CPC Class Codes: H04L 43/0817 by checking functioning

Abstract

A method and system for capturing a state of a distributed computer system is provided. The state is captured in response to an error or event message received by one of the clients and/or server nodes of the system. In response to receipt of the error or event message, the recipient initiates transmission of a special protocol message of affected members of the system. Upon receipt of the message, all recipients will conduct a freeze of their respective operating system image. Depending upon the characteristics of the error or event, the message may be transmitted to a selection of members of the system, or the entire system.

Claims

1. A method for servicing a computer system comprising:

delivering a dedicated message to all nodes in said system affected by an event, wherein said nodes are members of a computer cluster with one or more nodes to coordinate access to a storage area network, and a cluster leader in said cluster to own one or more tasks for which members of said cluster require communication with said cluster leader to support a service; and

capturing a state of at least two of said nodes responsive to receipt of said message, wherein the step of capturing a state of at least two of said nodes supports creation of a logical image of each of said nodes at a point in time, and prevents transition of said nodes to another state.

2. The method of claim 1, wherein said message is selected from a group consisting of:

an out of band communication and an in-band communication.

3. The method of claim 1, further comprising broadcasting said capture of said state to all nodes in said cluster if said event is resident on at least one node in said cluster including capturing a state of all client and server nodes at a point-in-time in receipt of said message.

4. The method of claim 3, further comprising said cluster of nodes sending an external message to all clients in communication with at least one of said cluster nodes.

5. The method of claim 1, wherein said event is selected from a group consisting of:

an error embedded in a computer readable medium, an operator generated command, and occurrence of a predefined action, and combinations thereof.

6. The method of claim 1, further comprising analyzing a frozen state of captured nodes.

7. A computer system comprising:

a processor;

an application program executed by the processor, wherein the application program comprising;

a coordinator to deliver a dedicated message to all nodes in said system affected by occurrence of an event, wherein said nodes are members of a computer cluster with one or more nodes to coordinate access to a storage area network and a cluster leader in said cluster for at least one function in said system; and

a capture of a state on at least two of said nodes upon receipt of said message, wherein said capture of a state creates a logical image of said at least two nodes at a point in time and prevents transmission of a message from said at least two nodes.

8. The system of claim 7, wherein said message is selected from a group consisting of:

an out-of band communication and an in-band communication.

9. The system of claim 7, further comprising an announcement of said event to all nodes in said cluster, wherein receipt of said announcement initiates a freeze command to capture a state of all nodes in said cluster at a point-in-time.

10. The system of claim 9, further comprising an external message adapted to be communicated to all clients in communication with at least one of said cluster nodes.

11. The system of claim 7, wherein said event is selected from a group consisting of:

an error embedded in a computer readable medium, an operator generated command, and occurrence of a predefined action, and combinations thereof.

12. The system of claim 7, further comprising a frozen state of a captured node adapted to be analyzed.

13. An article comprising:

a computer-readable storage medium;

means in the medium for delivering a dedicated message to all nodes affected by an event, wherein said nodes are members of a computer cluster with one or more nodes to coordinate access to a storage area network and a cluster leader in said cluster for at least one function in said system; and

means in the medium for initiating a capture of a state of at least two of said nodes upon receipt of said message, wherein said capture of a state is a logical image of said node, and wherein said capture of a state prevents transmission of a message from said node.

14. The article of claim 13, wherein said message is selected from a group consisting of:

an out-of band communication and an in-band communication.

15. The article of claim 13, further comprising means in the medium for announcing said capture of said state to all cluster member nodes in said cluster if said event is resident on at least one node in said cluster.

16. The article of claim 15, further comprising means in the medium for communicating said message to all clients in communication with at least one of said cluster nodes.

17. The article of claim 13, wherein said event is selected from a group consisting of:

an error embedded in a computer readable medium, an operator generated command, and occurrence of a predefined action, and combinations thereof.

18. The article of claim 13, further comprising means in the medium for analyzing a frozen state of said captured node.

19. A method for servicing a computer system comprising:

delivering an out-of-band disk based message to all nodes in said system, and in communication with a storage area network, affected by an event, wherein said nodes are members of a computer cluster with one or more nodes to coordinate access to a storage area network;

using said message to freeze a state of at least two of said nodes upon receipt of said message; and

preventing transmission of a message from said node having a frozen state.