Switch-based reliable multicast service

Patent metadata

Field	Value
Publication number	US-10419329-B2
Application number	US-201715473643-A
Country	US
Kind code	B2
Filing date	Mar 30, 2017
Priority date	Mar 30, 2017
Publication date	Sep 17, 2019
Grant date	Sep 17, 2019

Abstract

Communication apparatus includes a plurality of interfaces for receiving and transmitting data packets from and to a network and a memory, which receives and stores context data with respect to multicast groups. Packet processing circuitry establishes reliable connections over the network with the receiving nodes in the multicast groups, and upon receiving from a packet source on the network an incoming unicast packet containing multicast data and containing multicast metadata that identifies a multicast group, sends an acknowledgment of the incoming unicast packet to the packet source, reads the context data from the memory with respect to the identified multicast group, and transmits multiple outgoing unicast packets containing the multicast data via respective egress interfaces to the receiving nodes in the multicast group over the reliable connections.

First claim

The invention claimed is:

1. A communication apparatus, comprising:
a plurality of interfaces, which are configured to serve as ingress interfaces and egress interfaces for receiving and transmitting data packets from and to a network;
a memory, which is configured to receive and store context data with respect to multicast groups, each multicast group comprising a set of receiving nodes on the network; and
packet processing circuitry, which is configured to establish reliable connections over the network with the receiving nodes in the multicast groups, to receive from a packet source on the network, via an ingress interface, an incoming unicast packet containing multicast data and containing multicast metadata that identifies a multicast group, to send an acknowledgment of the incoming unicast packet to the packet source, to read the context data from the memory with respect to the identified multicast group, and to transmit, based on the context data, multiple outgoing unicast packets containing the multicast data via respective egress interfaces to the receiving nodes in the multicast group over the reliable connections,
wherein the packet processing circuitry is configured to generate and transmit the multiple outgoing unicast packets concurrently via the respective egress interfaces.

2. The apparatus according to claim 1 , wherein the packet processing circuitry is configured to receive, from the receiving nodes over the reliable connections, acknowledgments of receipt of the outgoing unicast packets, and to track the received acknowledgments in order to verify completion of distribution of the multicast data to the identified multicast group.

3. The apparatus according to claim 2 , wherein the packet processing circuitry is configured to retransmit an outgoing unicast packet to a receiving node in the identified multicast group when a positive acknowledgment is not received from the receiving node within a predefined time limit.

4. The apparatus according to claim 1 , wherein the packet processing circuitry is configured to insert the multicast metadata in the outgoing unicast packets.

5. The apparatus according to claim 1 , wherein the packet source is a host computer connected to the network.

6. The apparatus according to claim 1 , wherein the packet source is a switch in the network.

7. A communication apparatus, comprising:
a plurality of interfaces, which are configured to serve as ingress interfaces and egress interfaces for receiving and transmitting data packets from and to a network;
a memory, which is configured to receive and store context data with respect to multicast groups, each multicast group comprising a set of receiving nodes on the network; and
packet processing circuitry, which is configured to establish reliable connections over the network with the receiving nodes in the multicast groups, to receive from a packet source on the network, via an ingress interface, an incoming unicast packet containing multicast data and containing multicast metadata that identifies a multicast group, to send an acknowledgment of the incoming unicast packet to the packet source, to read the context data from the memory with respect to the identified multicast group, and to transmit, based on the context data, multiple outgoing unicast packets containing the multicast data via respective egress interfaces to the receiving nodes in the multicast group over the reliable connections,
wherein the packet processing circuitry is configured to insert the multicast metadata in the outgoing unicast packets, and
wherein at least one of the receiving nodes in at least one of the multicast groups is a switch in the network, which receives one of the outgoing unicast packets transmitted by the apparatus and generates, in response to the multicast metadata in the one of the unicast packets, one or more further outgoing unicast packets containing the multicast data for transmission to one or more further receiving nodes.

8. The apparatus according to claim 7 , wherein the packet processing circuitry is configured to receive, from the switch, an acknowledgment of receipt of the one of the outgoing unicast packets, and to track the received acknowledgment in order to verify completion of distribution of the multicast data to the identified multicast group.

9. A communication apparatus, comprising:
a plurality of interfaces, which are configured to serve as ingress interfaces and egress interfaces for receiving and transmitting data packets from and to a network;
a memory, which is configured to receive and store context data with respect to multicast groups, each multicast group comprising a set of receiving nodes on the network; and
packet processing circuitry, which is configured to establish reliable connections over the network with the receiving nodes in the multicast groups, to receive from a packet source on the network, via an ingress interface, an incoming unicast packet containing multicast data and containing multicast metadata that identifies a multicast group, to send an acknowledgment of the incoming unicast packet to the packet source, to read the context data from the memory with respect to the identified multicast group, and to transmit, based on the context data, multiple outgoing unicast packets containing the multicast data via respective egress interfaces to the receiving nodes in the multicast group over the reliable connections,
wherein the packet processing circuitry is configured to receive from the packet source a multi-packet multicast message comprising an input sequence of incoming unicast packets including at least a first packet and a last packet, to identify the multicast group using the multicast metadata in the first packet in the input sequence, and to transmit multiple output sequences of the outgoing unicast packets via the respective egress interfaces to the receiving nodes, such that the first packet in the output sequences is transmitted before the last packet in the input sequence has been received through the ingress interface.

10. A method for communication, comprising:
storing, in a switch having a plurality of interfaces serving as ingress interfaces and egress interfaces for receiving and transmitting data packets from and to a network, context data with respect to multicast groups, each multicast group comprising a set of receiving nodes on the network;
establishing reliable connections over the network with the receiving nodes in the multicast groups;
receiving from a packet source on the network, via an ingress interface, an incoming unicast packet containing multicast data and containing multicast metadata that identifies a multicast group;
sending an acknowledgment of the received incoming unicast packet to the packet source; and
transmitting, based on the stored context data with respect to the identified multicast group, multiple outgoing unicast packets containing the multicast data via respective egress interfaces of the switch to the receiving nodes in the multicast group over the reliable connections,
wherein transmitting the multiple outgoing unicast packets comprises generating and transmitting the multiple outgoing unicast packets concurrently via the respective egress interfaces.

11. The method according to claim 10 , and comprising receiving, from the receiving nodes over the reliable connections, acknowledgments of receipt of the outgoing unicast packets, and tracking the received acknowledgments in order to verify completion of distribution of the multicast data to the identified multicast group.

12. The method according to claim 11 , and comprising retransmitting an outgoing unicast packet to a receiving node in th

Assignees

• Mellanox Tech Tlv Ltd

Inventors

• Levi Lion
• Elias George
• Wertheim Oded
• Marelli Amiad
• Menes Miriam
• Rabenstein Itamar
• Avital Noam
• Romlet Evyatar
• Merdler Ofir

Classifications

• H04L1/16

  in which the return channel carries supervisory signals, e.g. repetition request signals · CPC title

• H04L45/16 Primary

  Multipoint routing · CPC title

• H04L1/1835

  Buffer management · CPC title

• H04L1/188

  Time-out mechanisms · CPC title

• H04L2001/0093

  Point-to-multipoint · CPC title