Switch

• US 7,818,387 B1
• Filed: 02/09/2004
• Issued: 10/19/2010
• Est. Priority Date: 02/09/2004
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Oracle America, Inc. (Oracle Corporation)
• Inventors: Roles, Karen, King, James E.
• Primary Examiner(s): Nguyen; Thu
• Assistant Examiner(s): Hussain; Tauqir
• Application Number:
  US10/774,755
• Time in Patent Office: 2,444 Days
• Field of Search: 709/208, 714/10
• US Class Current: 709/208
• CPC Class Codes: G06F 11/0766 Error or fault reporting or storing
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• 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 41/0213 Standardised network management protocols, e.g. simple network management protocol [SNMP]
• CPC Class Codes: H04L 41/0613 based on the type or category of the network elements
• CPC Class Codes: H04L 69/40 for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection management of faults, events, alarms or notifications in data switching networks H04L41/06

Abstract

A combined switch and service processor module for a modular computer system is provided. The combined switch and service processor module comprises a switch portion; a service processor portion; and a data interface for communicating management information to other parts of the modular computer system. Wherein the service processor portion is operable to operate in master/slave relationship with a service processor portion of a further combined switch and service processor module of the modular computer system; and wherein the service processor portion is further operable automatically to synchronise management information with the service processor portion of the further combined switch and service processor via the data interface in accordance with the master/slave relationship.

Claims

1. An apparatus for a modular computer system, comprising:

a combined switch and service processor module configured to couple to an information processing module, wherein the combined switch and service processor module includes;

a switch portion;

a service processor portion;

a data interface configured to communicate with an external management entity via a network; and

a fault management unit configured to receive fault messages generated by the switch portion and by the service processor portion, including respective fault messages generated by the switch portion and the service processor portion that relate to a same fault of the information processing module, and wherein the fault management unit is further configured to perform processing on a received fault message to determine whether to forward the received message to the external management entity via the data interface, wherein the fault management unit is configured to not forward fault messages that relate to the same fault for which the fault management unit has already forwarded a fault message to the external management entity;

wherein the apparatus is further configured to detect that the information processing module is outputting erroneous data relating to the same fault, and, in response thereto, to disable further communication of erroneous data by the information processing module.

2. The apparatus of claim 1, wherein the fault management unit is implemented within the service processor portion.

3. The apparatus of claim 1, wherein the fault management unit is configured to store details of the fault messages irrespective of whether the fault messages are forwarded to the external management entity.

4. The apparatus of claim 3, wherein the stored details of the fault messages includes data describing an action taken by the originator of a given fault message in response to detection of the fault.

5. The apparatus of claim 3, wherein the stored details of the fault messages are analyzed to determine whether any reversement actions are required by the originator of a given fault message when a fault repair is attempted.

6. The apparatus of claim 1, wherein the switch portion and service processor portion are implemented by separate hardware within the combined switch and service processor module.

7. The apparatus of claim 1, wherein the switch portion and service processor portion are implemented by common hardware within the combined switch and service processor module.

8. The apparatus of claim 1, wherein the service processor portion is configured to operate in a master/slave relationship with a service processor portion of another combined switch and service processor module of the modular computer system;

and

wherein the service processor portion is further configured to automatically synchronize management information with the service processor portion of the other combined switch and service processor via the data interface in accordance with the master/slave relationship.

9. The apparatus of claim 1, wherein the switch and service processor portions are each configured to communicate with the external management entity to obtain a unique address within a computing environment into which the modular computer system is connected.

10. The apparatus of claim 1, wherein the service processor portion has a user interface configured to receive and forward communications between the external management entity and the switch portion.

11. The apparatus of claim 1, wherein the switch and service processor portions are each configured to create a unique identifier using data unique to the respective portions;

and

wherein the service processor portion is configured to supply the service processor portion'"'"'s unique identifier to the switch.

24. The apparatus module of claim 1, wherein the switch portion is configured to:

disable further communication of the erroneous data by the information processing module, by disabling a network port of the information processing module.

27. The apparatus of claim 1, wherein the fault management unit is configured to:

receive a first fault message generated by the switch portion that relates to a particular fault;

forward the first fault message to the external management entity;

receive a second fault message generated by the service portion, wherein the second fault message relates to the particular fault, and wherein the second fault message is received by the fault management unit after receiving the first fault message; and

not forward the second fault message to the external management entity in response to determining that the second fault message is related to the particular fault and that the first fault message has already been forwarded to the external management entity.

12. A computer system comprising:

an information processing module;

a combined switch and service processor module, including;

a switch portion;

a service processor portion;

a data interface configured to communicate with an external management entity via a network; and

a fault management unit configured to receive fault messages generated by the switch portion and by the service processor portion, including respective fault messages generated by the switch portion and the service processor portion that relate to a same fault of the information processing module, and wherein the fault management unit is further configured to perform processing on a received fault message to determine whether to forward the received message to the external management entity via the data interface, wherein the fault management unit is configured to not forward fault messages that relate to the same fault for which the fault management unit has already forwarded a fault message to the external management entity;

wherein the computer system is further configured to detect that the information processing module is outputting erroneous data relating to the same fault, and, in response thereto, to disable further communication of erroneous data by the information processing module.

14. The computer system of claim 12, wherein the fault management unit is implemented within the service processor portion.

15. The computer system of claim 12, wherein the fault management unit is further configured to store details of the fault messages irrespective of whether the fault messages are forwarded to the external management entity.

16. The computer system of claim 15, wherein the stored details of the fault messages include data describing an action taken by the originator of a given fault message in response to detection of the fault.

17. The computer system of claim 15, wherein the fault management unit is further configured to analyze the stored details of the fault messages to determine whether any reversement actions are required by the originator of a given fault message when a fault repair is attempted.

18. The computer system of claim 12, wherein the service processor portion is configured to operate in a master/slave relationship with a service processor portion of another combined switch and service processor module of the computer system;

and

wherein the service processor portion is further configured to automatically synchronize management information with the service processor portion of the other combined switch and service processor via the data interface in accordance with the master/slave relationship.

25. The computer system of claim 12, wherein the switch portion is configured to:

disable further communication of the erroneous data by the information processing module, by disabling a network port of the information processing module.

13. A method of operating a combined switch and service processor module for a modular computer system, the combined switch and service processor module having:

a switch portion;

a service processor portion;

a data interface configured to communicate with an external management entity via a network; and

a fault management unit;

the method comprising;

the fault management unit receiving fault messages generated by the switch portion and by the service processor portion including a first fault message generated by the switch portion and a second fault message generated by the service processor portion, wherein the first and second fault messages relate to a same fault of an information processing module of the modular computer system;

the fault management unit performing processing on a received fault message to determine whether to forward the received message to the external management entity via the data interface;

the fault management unit not forwarding fault messages that relate to the same fault for which the fault management unit has already forwarded a fault message to the external management entity;

the modular computer system detecting that the information processing module is outputting erroneous data relating to the same fault, and, in response thereto, disabling further communication of erroneous data by the information processing module.

19. The method of claim 13, wherein the fault management unit is implemented within the service processor portion.

20. The method of claim 13, further comprising the fault management unit storing details of the fault messages irrespective of whether the fault messages are forwarded to the external management entity.

21. The method of claim 20, wherein the stored details of the fault messages includes data describing an action taken by the originator of a given fault message in response to detection of the fault.

22. The method of claim 20, further comprising the fault management unit analyzing the stored details of the fault messages to determine whether any reversement actions are required by the originator of a given fault message when a fault repair is attempted.

23. The method of claim 13, further comprising operating the service processor portion in a master/slave relationship with a service processor portion of another combined switch and service processor module of the modular computer system;

and

the service processor portion automatically synchronizing management information with the service processor portion of the other combined switch and service processor via the data interface in accordance with the master/slave relationship.

26. The method of claim 13, further comprising:

the switch portion disabling further communication of the erroneous data by the information processing module, by disabling a network port of the information processing module.