Highly utilized communication channel with order and retransmissions

• US 9,722,763 B2
• Filed: 01/19/2010
• Issued: 08/01/2017
• Est. Priority Date: 02/07/2007
• Status: Active Grant

• Current Assignee: Valens Semiconductor Ltd.
• Original Assignee: Valens Semiconductor Ltd.
• Inventors: Lida, Eyran, Banet, Nadav
• Primary Examiner(s): Tabone, Jr., John J
• Application Number:
  US12/689,359
• Publication Number:
  US 20100122135A1
• Time in Patent Office: 2,751 Days
• Field of Search: 714748, 714749, 714751, 714752, 714786, 714821, 714712, 370217, 370218, 370222, 370241, 370242, 370244, 370250, 375224, 375225
• CPC Class Codes: H04L 1/007 Unequal error protection for format H04L1/0078; for codes per se H03M13/35
• CPC Class Codes: H04L 1/1819 with retransmission of additional or different redundancy
• CPC Class Codes: H04L 1/1841 Resequencing
• CPC Class Codes: H04L 1/1887 Scheduling and prioritising arrangements
• CPC Class Codes: H04L 25/4919 using balanced multilevel codes H04L25/4927 takes precedence
• CPC Class Codes: H04L 27/0008 arrangements for allowing a transmitter or receiver to use more than one type of modulation negotiating modulation type for two-way transmission paths H04L5/1453
• CPC Class Codes: H04L 5/143 for modulated signals H04L5/1469 takes precedence

Abstract

A communication link comprising: a first transceiver configured to transmit a first set of packets at a predetermined rate with a first error resistance level, store the transmitted data in a buffer, receive a retransmission request, and retransmit the relevant data using one or more packets encoded with a second error resistance level that is higher than the first error resistance level. And a second transceiver configured to receive the first set of packets, detect an erroneous packet, request retransmission of the erroneous packet, and forward the data received in the packets according to its original order approximately after a fixed delay.

Claims

1. A network comprising at least two wired communication links, comprising:

a first transceiver configured to;

transmit packets comprising payloads with a first error resistance level to a second transceiver over a first wired communication link, store the payloads in a first buffer, receive a first retransmission request for a first payload that is included in the payloads, and retransmit the first payload using a first retransmission packet encoded with a second error resistance level that is higher than the first error resistance level, resulting in no additional retransmissions being required to transmit the first payload successfully;

the second transceiver is configured to;

receive the packets from the first transceiver, transmit non-retransmitted packets after a fixed delay with the first error resistance level to a third transceiver over a second wired communication link, store the payloads in a second buffer, receive a second retransmission request for a second payload that is included in the payloads, and retransmit the second payload using a second retransmission packet encoded with the second error resistance level that is higher than the first error resistance level, resulting in no additional retransmissions being required to transmit the second payload successfully.

2. The network of claim 1, wherein most of the packets comprise packet headers featuring a higher error resistance level than error resistance level of the payloads.

3. The network of claim 1, wherein average throughput and maximum burst of the first and second retransmissions are controlled, and the packets are transmitted at a predetermined rate.

4. The network of claim 3, wherein maximal throughput of the transmissions of the packets and the first retransmission approaches maximum capacity of the first wired communication link.

5. The network of claim 3, wherein the first and second retransmission packets are transmitted with a priority higher than priority of the packets, whereby the higher priority reduces latency of the first and second wired communication links.

6. The network of claim 3, wherein the second wired communication link is coupled to an end device that does not support retransmission.

7. The network of claim 1, wherein the fixed delay is in order of round trip delay between the first transceiver and the second transceiver.

8. A network comprising at least two wired communication links, comprising:

a first transceiver comprising;

a first packet buffer configured to store packets received over a first wired communication link, and a packet processing element coupled to the first packet buffer and configured to send a first retransmission request for a first retransmitted packet upon detection of a first erroneous packet, wherein the first retransmitted packet features a higher error resistance than the received packets, resulting in no additional retransmissions being required to transmit the first retransmitted packet successfully;

the first packet buffer is further configured to store at least one additional packet before storing the first retransmitted packet; and

the first packet processing element is further configured to maintain original order of the received packets by replacing the first erroneous packet with the first retransmitted packet; and

a second transceiver comprising;

a second packet buffer configured to store packets received from the first transceiver over a second wired communication link after a fixed delay, and a second packet processing element coupled to the second packet buffer and configured to send a second retransmission request for a second retransmitted packet upon detection of a second erroneous packet, wherein the second retransmitted packet features a higher error resistance than received non-retransmitted packets, resulting in no additional retransmissions being required to transmit the second retransmitted packet successfully;

the second packet buffer is further configured to store at least one additional packet before storing the second retransmitted packet; and

the second packet processing element is further configured to maintain original order of the received packets by replacing the second erroneous packet with the second retransmitted packet.

9. The network of claim 8, wherein the first transceiver is configured to operate at a throughput close to its maximum possible throughput.

10. The network of claim 8, wherein some of the received packets are to be protected by retransmission requests and some of the received packets are not to be protected by retransmission requests.

11. The network of claim 10, wherein the received packets comprise a field used to mark whether the received packet is to be protected by retransmission, and in most of the received packets the field features a higher error resistance than the error resistance of payloads of the packets.

12. The network of claim 8, wherein the first transceiver receives packets belonging to a first stream and a second stream;

at least some packets of the first stream are to be protected by retransmissions, and packets of the second stream are not to be protected by retransmissions.

13. The network of claim 8, wherein the network ensures low latency variance.

14. The network of claim 13, wherein the network is configured to operate with end devices that do not support retransmission.

15. A network of at least two links, comprising:

first, second, and third transceivers configured to transmit a set of packets, with a first error resistance level, over the at least two links;

the first transceiver is configured to transmit a first retransmitted packet with a second error resistance level, which is higher than the first error resistance level, resulting in no additional retransmissions being required to transmit the first retransmitted packet successfully;

the second transceiver is configured to request the first retransmitted packet and is configured to maintain original order of the set of packets over the at least two links by forwarding a first set of non-retransmitted packets to the third transceiver after a fixed delay; and

the third transceiver is configured to request a second retransmitted packet from the second transceiver and is configured to maintain original order of the set of packets over the at least two links by forwarding a second set of non-retransmitted packets to their destination after storing them for the fixed delay.

16. The network of claim 15, wherein most of the initial transmitted packets comprise packet headers featuring a higher error resistance than error resistance of payloads of the initial transmitted packets.

17. The network of claim 15, wherein average throughput and maximum burst of the retransmitted packets are controlled.

18. The network of claim 17, wherein the network carries one or more main streams, and a maximum amount of the retransmitted packets is determined so as not to interfere with proper transmission of the main streams.

19. The network of claim 17, wherein the retransmitted packets are transmitted with a priority higher than priority of most of the initial transmitted packets, whereby a higher priority mechanism reduces latency of the network.

20. The network of claim 15, wherein the network carries a first stream and a second stream;

at least some packets of the first stream are to be protected by retransmissions, and packets of the second stream are not to be protected by retransmissions.

21. The network of claim 15, wherein the network is configured to operate at a throughput close to maximum possible throughput of the network.

22. A method for operating a communication link with a fixed latency, comprising:

transmitting a stream of data at a predetermined rate;

the stream of data comprises payloads featuring a first error resistance level;

receiving the stream, and storing the payloads in a buffer;

requesting a retransmission upon detection of an erroneous part of the payload;

retransmitting the erroneous part of the payload with a second error resistance level that is higher than the first error resistance level, resulting in no additional retransmissions being required to transmit the erroneous part of the payload;

inserting the retransmitted erroneous part of the payload into a proper location in the buffer so as to maintain original order of the payloads of the stream; and

wherein the method is operated over each hop of a network that maintains the original order of the payload and features a fixed latency over each hop.

23. The method of claim 22, wherein the stream is transmitted using packets, and most of the packets comprise packet headers featuring a higher error resistance than error resistance of the payloads.

24. The method of claim 23, further comprising modulating most of the headers using a lower modulation than modulation used to modulate the payloads.

25. The method of claim 23, wherein the detected error includes a missing packet error, and further comprising identifying the missing packet using a packet identification code that is assigned according to a predefined series of codes.

26. The method of claim 23, further comprising transmitting another stream for which no retransmissions are requested.

27. The method of claim 23, further comprising marking which of the packets is to be protected by the retransmission and which is not.

28. The method of claim 23, wherein the stream of data comprises time-sensitive data, and ensuring fixed latency with low latency variance.

29. The method of claim 23, further comprising receiving the stream of data at the predetermined rate with the first error resistance level from an end device that does not support retransmission.