Method for transmitting messages in a computer network, and computer network

Patent metadata

Field	Value
Publication number	US-9787494-B2
Application number	US-201415031861-A
Country	US
Kind code	B2
Filing date	Oct 15, 2014
Priority date	Oct 25, 2013
Publication date	Oct 10, 2017
Grant date	Oct 10, 2017

Abstract

The invention relates to a method for transmitting messages in a computer network, and to a computer network of this type. The computer network comprises computing nodes ( 101 - 105 ), said computing nodes ( 101 - 105 ) being interconnected via at least one star coupler ( 201 ) and/or at least one multi-hop network ( 1000 ), wherein each computing node ( 101 - 105 ) is connected via at least one communication line ( 110 ) to the at least one star coupler ( 201 ) and/or the at least one multi-hop network ( 1000 ), and wherein the computing nodes ( 101 - 105 ) exchange Ethernet messages with one another and with the at least one star coupler ( 201 ) and/or the at least one multi-hop network ( 1000 ). A set of two or more components are directly connected to one another in each case by two or more communication lines ( 110, 111 ), wherein each component in the set is either a computing node ( 101 - 105 ) or a star coupler ( 201 ), and sending components in the set of components send to at least two of the two or more communication lines ( 110, 111 ) at least a proportion of the Ethernet messages that are to be sent, and receiving components in the set of components then accept and/or forward at least a proportion of the Ethernet messages received via the two or more communication lines ( 110, 111 ) only if at least two identical messages are received via at least two different communication lines.

First claim

The invention claimed is:

1. A method for transmitting messages in a computer network, wherein the computer network comprises computing nodes ( 101 - 105 ), said computing nodes ( 101 - 105 ) being interconnected via at least one star coupler ( 201 ) and/or at least one multi-hop network ( 1000 ), wherein each computing node ( 101 - 105 ) is connected via at least one communication line ( 110 ) to the at least one star coupler ( 201 ) and/or the at least one multi-hop network ( 1000 ), and wherein the computing nodes ( 101 - 105 ) exchange Ethernet messages with one another and with the at least one star coupler ( 201 ) and/or the at least one multi-hop network ( 1000 ),
wherein in a set of components selected from two or more of those components comprised by the computer network those components within the set that are directly interconnected are directly interconnected in each case by two or more communication lines ( 110 , 111 ), the method comprising:
sending components in the set of components send to at least two of two or more communication lines ( 110 , 111 ) at least a proportion of the Ethernet messages that are to be sent, and
receiving components in the set of components then accept and/or forward at least a proportion of the Ethernet messages received via the two or more communication lines ( 110 , 111 ) only if at least two identical messages are received via at least two different communication lines.

2. The method of claim 1 , wherein the sending components in the set of components and/or the receiving components in the set of components consist in each case of two or more fault-containment units.

3. The method of claim 1 , wherein the sending and/or receiving components in the set of components, the fault-containment units are selected in such a way that, for each component, different MAC layers are located in different fault-containment units.

4. The method of claim 1 , wherein in the sending and/or receiving components of the at least one set of components, the fault-containment units are selected in such a way that, for each component, each MAC layer is allocated to precisely one of two fault-containment units.

5. The method of claim 1 , wherein in the sending components in the set of components, the fault-containment units are selected in such a way that, for each component, different PHY layers are located in different fault-containment units.

6. The method of claim 1 , wherein in the sending and/or receiving components in the set of components, the fault-containment units are selected in such a way that, for each component, each PHY layer is allocated to precisely one of two fault-containment units.

7. The method of claim 1 , wherein in the sending and/or receiving components in the set of components, the fault-containment units are selected in such a way that each MAC layer and/or PHY layer is allocated to precisely one of two fault-containment units.

8. The method of claim 1 , wherein a receiving component in the set of components forwards only one of the identical messages received by the receiving component at the least two different communication lines ( 110 , 111 ).

9. The method of claim 1 , wherein at least a proportion of the Ethernet messages is sent by the computing nodes in a time-controlled manner.

10. The method of claim 1 , wherein at least a proportion of the Ethernet messages is forwarded by the star couplers in a time-controlled manner.

11. The method of claim 1 , wherein the SAE AS602 standard or a standard based thereon or a standard following on therefrom is used in order to communicate in a time-controlled manner.

12. The method of claim 1 , wherein the IEEE 802.1AS standard or a standard based thereon or a standard following on therefrom is used in order to communicate in a time-controlled manner.

13. The method of claim 1 , wherein the IEEE 1588 standard or a standard based thereon or a standard following on therefrom is used in order to communicate in a time-controlled manner.

14. The method of claim 1 , wherein the components in the set of components use the two or more communication lines, at moments at which no identical Ethernet messages are transmitted via two or more communication lines, for the transmission of different Ethernet messages.

15. The of claim 14 , wherein a link aggregation method according to standard IEEE 802.1AX or a method based thereon or a standard following on therefrom is used to send different messages via the two or more communication lines.

16. The method of claim 1 , wherein the set of components contains exclusively star couplers ( 201 ), i.e. two or more star couplers ( 201 ).

17. The method of claim 1 , wherein the error-containment units are selected in such a way that each component in itself forms an error-containment unit.

18. The method of claim 1 , wherein the error-containment units are selected in such a way that each star coupler ( 201 ) forms an error-containment unit.

19. The method of claim 1 , wherein the error-containment units are selected in such a way that at least one computing node ( 101 - 105 ) together with in each case at least one star coupler ( 201 ) forms an error-containment unit.

20. The method of claim 19 , wherein the error-containment units are selected in such a way that in each case precisely one computing node ( 101 - 105 ) together with precisely one star coupler ( 201 ) forms an error-containment unit.

21. The method of claim 1 , wherein each component in the set of components is a sending component, a receiving component, or both a sending and a receiving component.

22. A computer network for transmitting messages in a computer network, wherein the computer network comprises computing nodes, said computing nodes ( 101 - 105 ) being interconnected via at least one star coupler ( 201 ) and/or at least one multi-hop network ( 1000 ), wherein each computing node ( 101 - 105 ) is connected via at least one communication line ( 110 ) to the at least one star coupler ( 201 ) and/or the at least one multi-hop network ( 1000 ), and wherein the computing nodes ( 101 - 105 ) exchange Ethernet messages with one another and with the at least one star coupler ( 201 ) and/or the at least one multi-hop network ( 1000 ), wherein:
in a set of components selected from those components comprised by the computer network, i.e. computing nodes and/or star couplers and/or multi-hop networks, wherein the set comprises two or more components of this type, those components within the set that are directly interconnected are directly interconnected in each case by two or more communication lines ( 110 , 111 ), and
sending components in the set of components are configured to send to at least two of two or more communication lines ( 110 , 111 ) at least a proportion of the Ethernet messages that are to be sent, and
receiving components in the set of components are configured to accept and/or forward at least a proportion of the Ethernet messages received via the two or more communication lines ( 110 , 111 ) only if at least two identical messages are received via at least two different communication lines.

23. The computer network of claim 22 , wherein the sending components in the set of components and/or the receiving components in the set of components consist in each case of two or more fault-containment units.

24. The computer network of claim 22 , wherein in the sending and/or receiving components in the set of components, the fault-containment un

Assignees

• Fts Computertechnik Gmbh

Inventors

• Steiner Wilfried
• Bauer Günther

Classifications

• H04L49/254

  Centralised controller, i.e. arbitration or scheduling · CPC title

• H04L61/2038

  Electricity · mapped topic

• H04L12/40189

  by using a plurality of bus systems · CPC title

• H04L61/2007

  Electricity · mapped topic

• H04L12/40182 Primary

  by using a plurality of communication lines · CPC title