Method for operating a distributed computer system

• US 20040062265A1
• Filed: 09/19/2003
• Published: 04/01/2004
• Est. Priority Date: 03/30/2001
• Status: Active Grant

• Current Assignee: TTTech Computertechnik AG
• Original Assignee: TTTech Computertechnik AG
• Inventors: Poledna, Stefan
• Granted Patent: US 7,023,870 B2
• Time in Patent Office: Days
• US Class Current: 370/442
• CPC Class Codes: G06F 11/1425 by reconfiguration of node membership
• CPC Class Codes: G06F 11/1482 by means of middleware or OS functionality
• CPC Class Codes: G06F 11/18 using passive fault-masking of the redundant circuits error detection by comparing the output of redundant processing systems with continued operation after detection of the error G06F11/165
• CPC Class Codes: G06F 11/181 Eliminating the failing redundant component
• CPC Class Codes: G06F 11/182 based on mutual exchange of the output between redundant processing components

Abstract

A method for operation of a distributed computer system (SYS) comprising network nodes (NKN, NK1-NK6), each of which has at least one node controller (STR, ST1-ST6) and one communication controller (KK1-KK6), the communication controllers (KKK, KK1-KK6) being connected to each other via at least one communication channel (BUS), and provision being made between the communication controller (KK1-KK6) and the node controller (STR, ST1-ST6) of a network node (NKN, NK1-NK6) for a fault tolerance layer (FTS, FT1-FT6) that is set up to receive messages exchanged between the network nodes (NKN, NK1-NK6), the fault tolerance layer (FTS, FT1-FT6) deciding, based on information received pertaining to the status of at least one network node(NKN, NK1-NK6), about the functioning of the at least one network node (NK1-NK6) via a coordination procedure, and the coordination result being made available as an output signal (ASS, AS1-AS6), the at least one network node (NKN, NK1-NK6) being triggered as a function of the output signal (ASS, AS1-AS6).

Claims

1. A method for operation of a distributed computer system (SYS) comprising network nodes (NKN, NK1-NK6), each of which has at least one node controller (STR, ST1-ST6) and one communication controller (KK1-KK6), the communication controllers (KKK, KK1-KK6) being connected to each other via at least one communication channel (BUS), and provision being made between the communication controller (KK1-KK6) and the node controller (STR, ST1-ST6) of a network node (NKN, NK1-NK6) for a fault tolerance layer (FTS, FT1-FT6) that is set up to receive messages exchanged between the network nodes (NKN, NK1-NK6), wherein the fault tolerance layer (FTS, FT1-FT6) decides, based on information received pertaining to the status of at least one network node (NKN, NK1-NK6), about the functioning of the at least one network node (NK1-NK6) via a coordination procedure, and the coordination result is made available as an output signal (ASS, AS1-AS6), the at least one network node (NKN, NK1-NK6) being triggered as a function of the output signal (ASS, AS1-AS6).

2. The method as described in claim 1, wherein the coordination result is made available at one or more hardware outputs of the communication controller (KKK, KK1-KK6)

3. The method as described in claim 1 or 2, wherein the result of the coordination is made available as a digital output signal on at least one pin of the communication controller (KKK, KK1-KK6).

4. The method as described in claims 1 to 3, wherein membership information of the communication controller (KKK, KK1-KK6) in question is included in the coordination procedure.

5. The method as described in any of claims 1 to 3, wherein the fault tolerance layer (FTS, FT1-FT6) uses its own data structure, which is independent of the data structures of the communication controller (KKK, KK1-KK6) and the node controller (STR, ST1-ST2), for the selection of a coordination algorithm and the evaluation messages (NA1-NA6) enlisted for the coordination.

6. The method as described in any of claims 1 to 4, wherein the coordination result is made available within network nodes in a memory storage area.

7. The method as described in any of claims 1 to 5, wherein at least one node controller (STR, ST1-ST6) is restarted as a function of the output signal (ASS, AS1-AS6).

8. The method as described in any of claims 1 to 6, wherein an emergency shutoff of a node controller (ST1-ST6) is executed as a function of the output signal (ASS, AS1-AS6).

9. The method as described in any of claims 1 to 7, wherein at least one network node (NKN, NK1-NK6) has an actuator (AKT, AK1-AK4) connected to the node controller (STR, ST1-ST6), and the actuator (AKT, AK1-AK4) is brought into a preferred or secure state by the output signal (ASS, AS1-AS6).

10. The method as described in any of claims 1 to 8, wherein the communication between the network nodes (NKN, NK1-NK6) occurs on a time-triggered basis according to the TTP/C protocol.