Cell-based link-level retry scheme

• US 9,306,769 B2
• Filed: 10/05/2010
• Issued: 04/05/2016
• Est. Priority Date: 10/05/2010
• Status: Active Grant

• Current Assignee: Mellanox Technologies TLV Ltd. (NVIDIA Corporation)
• Original Assignee: Mellanox Technologies TLV Ltd. (NVIDIA Corporation)
• Inventors: Kagan, Michael, Crupnicoff, Diego, Azarzar, Tamir, Ravid, Ran, Bloch, Gil
• Primary Examiner(s): VU, HOANG-CHUONG Q
• Application Number:
  US12/897,808
• Publication Number:
  US 20120082164A1
• Time in Patent Office: 2,009 Days
• Field of Search: 370/394, 370/395.1, 370/395.52, 370470-473, 370/476
• US Class Current: 1/1
• CPC Class Codes: H04L 12/5601 Transfer mode dependent, e.g. ATM
• CPC Class Codes: H04L 2012/5652 Cell construction, e.g. including header, packetisation, depacketisation, assembly, reassembly
• CPC Class Codes: H04L 47/34 ensuring sequence integrity, e.g. using sequence numbers

Abstract

A method for communication includes receiving a packet at a first node for transmission over a link to a second node. The data in the packet is divided into a sequence of cells of a predetermined data size. The cells have respective sequence numbers. The cells are transmitted in sequence over the link, while storing the transmitted cells in a buffer at the first node. The first node receives acknowledgments indicating the respective sequence numbers of the transmitted cells that were received at the second node. Upon receiving an indication at the first node that a transmitted cell having a given sequence number was not properly received at the second node, the stored cells are retransmitted from the buffer starting from the cell with the given sequence number.

Claims

1. A method for communication, comprising:

receiving a packet comprising data at a first node for transmission over a link to a second node;

dividing the data into a sequence of cells of a predetermined data size, the cells being identified by respective sequence numbers;

computing respective error detection codes for the payload data of each of the cells;

grouping the cells into link layer frames, such that each link layer frame includes multiple cells with their respective error detection codes for their payload data;

transmitting the link layer frames over the link, while storing the transmitted cells included in the transmitted link layer frames in a buffer at the first node;

receiving acknowledgments at the first node indicating the respective sequence numbers of the transmitted cells that were received at the second node; and

upon receiving an indication at the first node that a transmitted cell having a given sequence number was not properly received at the second node, retransmitting the stored cells from the buffer starting from the cell with the given sequence number.

2. The method according to claim 1, wherein the predetermined data size is no more than 128 bytes.

3. The method according to claim 2, wherein the predetermined data size is no more than 64 bytes.

4. The method according to claim 1, wherein receiving the indication comprises receiving a negative acknowledgment from the second node referring to the given sequence number.

5. The method according to claim 1, wherein receiving the indication comprises detecting that a time limit has expired for receiving an acknowledgment.

6. The method according to claim 1, and comprising, upon receiving an acknowledgment specifying an acknowledged sequence number, deleting from the buffer the transmitted cells whose respective sequence numbers are less than or equal to the acknowledged sequence number.

7. The method according to claim 1, wherein the cells transmitted from the first node to the second node are outgoing cells, and wherein the method comprises receiving at the first node incoming cells, having respective incoming sequence numbers, from the second node, and wherein transmitting the cells comprises adding to at least one of the outgoing cells at the first node an acknowledgment of the incoming cells, the acknowledgment comprising at least one of the incoming sequence numbers.

8. The method according to claim 1, wherein each frame comprises a header indicating a sequence number of at least one but not all of the cells in the frame, and wherein the transmitted cells do not contain the respective sequence numbers.

9. Communication apparatus, comprising:

a memory, which is disposed at a first node in a communication network and is configured to receive and buffer a packet comprising data for transmission over a link to a second node; and

a controller, which is coupled to the memory and is configured to divide the data into a sequence of cells of a predetermined data size, the cells being identified by respective sequence numbers, to compute respective error detection codes for the payload data of each of the cells, to group the cells into link layer frames, such that each link layer frame includes multiple cells with their respective error detection codes, and to transmit link layer frames over the link, while storing the transmitted cells included in the transmitted link layer frames in the memory, and

wherein the controller is configured to receive acknowledgments at the first node indicating the respective sequence numbers of the transmitted cells that were received at the second node, and upon receiving an indication at the first node that a transmitted cell having a given sequence number was not properly received at the second node, to retransmit the stored cells from the memory starting from the cell with the given sequence number.

10. The apparatus according to claim 9, wherein the predetermined data size is no more than 128 bytes.

11. The apparatus according to claim 10, wherein the predetermined data size is no more than 64 bytes.

12. The apparatus according to claim 9, wherein the indication that the transmitted cell was not properly received comprises a negative acknowledgment received from the second node referring to the given sequence number.

13. The apparatus according to claim 9, wherein the indication that the transmitted cell was not properly received comprises an expiration of a time limit for receiving an acknowledgment.

14. The apparatus according to claim 9, wherein the controller is configured, upon receiving an acknowledgment specifying an acknowledged sequence number, to delete from the memory the transmitted cells whose respective sequence numbers are less than or equal to the acknowledged sequence number.

15. The apparatus according to claim 9, wherein the cells transmitted from the first node to the second node are outgoing cells, and wherein incoming cells, having respective incoming sequence numbers, are received at the first node from the second node, and wherein the controller is configured to add to at least one of the outgoing cells at the first node an acknowledgment of the incoming cells, the acknowledgment comprising at least one of the incoming sequence numbers.

16. A switch, comprising:

a switching core;

a plurality of ports, coupled to the core, for receiving and transmitting data packets; and

circuitry associated respectively with each port among at least some of the ports of the switch, the circuitry comprising;

a memory, which is configured to receive from a port of the plurality of ports and buffer a packet comprising data for transmission via the switching core to another port of the plurality of ports; and

a controller, which is coupled to the memory and is configured to divide the data into a sequence of cells of a predetermined data size, the cells being identified by respective sequence numbers, to compute respective error detection codes for the payload data of each of the cells, to group the cells into link layer frames, such that each link layer frame includes multiple cells with their respective error detection codes, and to transmit the link layer frames via the switching core, while storing the transmitted cells included in the transmitted link layer frames in the memory, and

wherein the controller is configured to receive acknowledgments from the other port indicating the respective sequence numbers of the transmitted cells that were received at the other port, and upon receiving an indication that a transmitted cell having a given sequence number was not properly received at the other port, to retransmit the stored cells from the memory starting from the cell with the given sequence number.