Smart Ethernet edge networking system

• US 9,621,375 B2
• Filed: 09/12/2006
• Issued: 04/11/2017
• Est. Priority Date: 09/12/2006
• Status: Active Grant

• Current Assignee: Ciena Corporation
• Original Assignee: Ciena Corporation
• Inventors: Giroux, Natalie, Young, Ken, Smith, Brian, Barrett, Chris, Frank, Pablo
• Primary Examiner(s): Chriss, Andrew
• Assistant Examiner(s): Cehic, Kenan
• Application Number:
  US11/519,503
• Publication Number:
  US 20080062876A1
• Time in Patent Office: 3,864 Days
• Field of Search: 370470-471, 370476, 370477, 370474, 370229-240
• CPC Class Codes: H04L 1/205 jitter monitoring
• CPC Class Codes: H04L 12/2856 Access arrangements, e.g. Internet access asynchronous transfer mode networks H04L12/5601; broadband local area networks H04L12/2801; optical access or distribution networks H04Q11/0067; access to open networks H04L12/5691; digital subscriber line end-user equipment and bit-level processing of data on a PSTN-based network H04M11/00; home network gateways H04L12/2834; wireless access networks H04W
• CPC Class Codes: H04L 41/26 using dedicated tools for LAN [Local Area Network] management
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 43/16 Threshold monitoring
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation

Abstract

A system is provided for controlling the flow of data-packet traffic through an Ethernet telecommunications network having a multiplicity of nodes interconnected by multiple network links. Incoming data-packet traffic from multiple customer connections are received at a first node for entry into the network via the first node. Flow control messages are generated to represent the states of the first node and, optionally, one or more network nodes upstream from the first node, and these states are used as factors in controlling the rate at which the incoming packets are admitted to the network. Alternatively, the flow control messages may be used to control the rate at which packets generated by a client application are transmitted to the first node.

Claims

1. A method of controlling the flow of data-packet traffic through an Ethernet telecommunications network having a multiplicity of nodes interconnected by multiple network links, comprising

receiving incoming Ethernet data-packet traffic from multiple customer connections at a first node of said multiplicity of nodes for entry into the network via said first node,

obtaining Ethernet flow control messages each representing a state of said first node or one or more nodes of said multiplicity of nodes upstream from said first node, and

using the state represented in each of said Ethernet flow control messages as factors in controlling the rate at which Excess Information Rate (EIR) traffic of said incoming Ethernet data-packet traffic is admitted to the network at said first node, wherein said controlling is based on a technique used to generate the Ethernet flow control messages with a step up in the rate being linear and a step down in the rate being exponential, wherein the step up and the step down are proportional to prescribed Ethernet traffic descriptors,

wherein said multiplicity of nodes in said network comprise queues for said Ethernet data-packet traffic being transmitted through respective nodes, and each of said multiplicity of nodes with queues generates said Ethernet flow control messages and transmits such messages to downstream nodes, wherein the Ethernet flow control messages comprise indications of which of a plurality thresholds are reached in said queues and the Ethernet flow control messages are used to shape the Ethernet data-packet traffic without stopping transmission of Ethernet data-packets, and

wherein said Ethernet flow control messages are selectively transmitted from said multiplicity of nodes directly in a backward path via hairpin connections at said multiplicity of nodes.

2. The method of claim 1 wherein at least one of said Ethernet flow control messages are received at said first node from nodes upstream of said first node.

3. The method of claim 1 further comprising:

receiving transit traffic at said first node, from one or more other nodes of said network, and

using said Ethernet flow control messages to control the rate at which said transit traffic is transmitted to said first node.

4. The method of claim 3 wherein said transit traffic received at said first node is assigned a higher transmission priority than the incoming traffic to be admitted to the network at said first node.

5. The method of claim 1 wherein the controlling the rate is performed by said first node.

6. The method of claim 3 wherein any reduction in the rate at which data packets are transmitted from said first node is greater for entering traffic than for said transit traffic.

7. The method of claim 1 wherein any node in a path manages the state information received for all upstream nodes, and sends state information representing only the worst congestion downstream for use in the controlling the rate.

8. The method of claim 1 wherein

said factors are based on the most congested state indicated by the flow control messages from any upstream node and said first node.

9. The method of claim 1 further comprising setting threshold levels at which the rate of transmission of said Ethernet data-packet traffic to a prescribed node is to be increased or decreased, and generating flow control messages when said threshold levels are reached.

10. The method of claim 1 further comprising aggregating traffic from multiple customer connections and using the state of such aggregation as a factor in controlling the rate at which said incoming Ethernet data-packet traffic are admitted to the network.

11. The method of claim 1 wherein the rate at which said incoming Ethernet data-packet traffic are admitted to the network is controlled by traffic shaping which buffers incoming packets and admits the buffered packets into the network at a rate that changes according to parameters that include a contracted rate of transmission and the congestion state of the network.

12. The method of claim 1 wherein the rate at which said incoming Ethernet data-packet traffic are admitted to the network is controlled by a policing mechanism that takes into account a contracted rate of transmission and the congestion state of the network.

13. The method of claim 1 further comprising throttling said incoming Ethernet data-packet traffic as a function of the congestion of the network at said first node and upstream of said first node.

14. The method of claim 1 wherein the rate at which said incoming Ethernet data-packet traffic are admitted to the network satisfies a minimum requirement for an application generating said incoming packets.

15. The method of claim 1 further comprising monitoring the Ethernet data-packet traffic received at said first node from each customer connection, and separately controlling the rate at which the Ethernet data-packet traffic from each customer connection are admitted to the network.

16. The method of claim 15 wherein said monitoring and controlling are effected by a traffic shaper.

17. The method of claim 15 further comprising intermediate queues in which an intermediate queue aggregates data packets received from multiple customer connections, and using the state of such aggregation as a factor in controlling the rate at which said data packets are admitted to the network.

18. The method of claim 17 further comprising setting threshold levels, representing the number of data packets in said intermediate queues, at which the rate of transmission of said data packets in said intermediate queues to a prescribed node is to be increased or decreased, and generating flow control messages when said threshold levels are reached.

19. The method of claim 1 wherein upstream nodes are the nodes where the traffic in the queues that cause the flow control messages to be generated, enters the network.

20. The method of claim 1 wherein contracted bandwidth corresponds to a prescribed quality of service, and the contracted bandwidth is increased or decreased by changing a contracted quality of service.

21. The method of claim 20 wherein said contracted bandwidth is adjusted based on time-of-day, time-of-year behavior.

22. The method of claim 20 wherein said contracted bandwidth is adjusted based on user signaling.

23. The method of claim 1, where the controlling the rate comprises reducing a rate at which Excess Information Rate (EIR) traffic is admitted based upon said flow control messages.

32. The method of claim 1, wherein the hairpin connections are used for control messaging to minimize delay before flow control information reaches a traffic admission mechanism.

33. The method of claim 1, wherein the Ethernet flow control messages comprise indications of different levels of congestion, providing information about the state of a given queuing point.

34. The method of claim 33, wherein the Ethernet flow control messages are generated when packets are being discarded for a given connection.

35. The method of claim 1, wherein a new connection starts at a minimum rate of a Committed Information Rate (CIR) and increases until reaching an EIR of the new connection or until receiving the Ethernet flow control messages, and in response to the Ethernet flow control messages, the new connection operates responsive to the Ethernet flow control messages.

36. The method of claim 1, wherein a new connection starts at a maximum rate of an EIR of the new connection until receiving the Ethernet flow control messages, and in response to the Ethernet flow control messages, the new connection operates responsive to the Ethernet flow control messages.

37. The method of claim 1, wherein a new connection starts at a minimum rate of a Committed Information Rate (CIR) and, responsive to receiving the Ethernet flow control messages from the one or more node, operates responsive to the Ethernet flow control messages.

38. The method of claim 1, wherein the rate at which said incoming Ethernet data-packet traffic are admitted to the network is controlled by traffic shaping, using the Ethernet flow control messages, and using different congestion control actions based on a deep packet inspection device placed upstream from the traffic shaper, which identifies different types of traffic in the Ethernet data-packet traffic.

24. A method, comprising

receiving incoming Ethernet traffic at a node in an Ethernet network, wherein the incoming traffic enters the Ethernet network at the node,

generating Ethernet flow control messages at each of a plurality of nodes in the Ethernet network, wherein the Ethernet flow control messages comprise status of the nodes and queues disposed within the nodes and comprise indications of which of a plurality thresholds are reached in said queues and the Ethernet flow control messages are used to shape the Ethernet traffic without stopping transmission of Ethernet data-packets,

exchanging the Ethernet flow control messages over the Ethernet network, wherein the Ethernet flow control messages are selectively sent directly in a backward path of the Ethernet network to downstream nodes via hairpin connections at each of the nodes and the Ethernet flow control messages are sent at a highest priority, and

based on the Ethernet control messages, adjusting a rate at which a portion of the incoming traffic is admitted to the Ethernet network at the node, wherein the portion comprises Excess Information Rate (EIR) traffic, and wherein said adjusting is based on said Ethernet flow control messages with a step up in the rate being linear and a step down in the rate being exponential, wherein the step up and the step down are proportional to prescribed Ethernet traffic descriptors.

29. The method of claim 24, wherein the hairpin connections are used for control messaging to minimize delay before flow control information reaches a traffic admission mechanism.

30. The method of claim 24, wherein the Ethernet flow control messages comprise indications of different levels of congestion, providing information about the state of a given queuing point.

31. The method of claim 24, wherein the Ethernet flow control messages are generated when packets are being discarded for a given connection.

39. The method of claim 24, wherein a new connection starts at a minimum rate of a Committed Information Rate (CIR) and increases until reaching an EIR of the new connection or until receiving the Ethernet flow control messages, and in response to the Ethernet flow control messages, the new connection operates responsive to the Ethernet flow control messages.

40. The method of claim 24, wherein a new connection starts at a maximum rate of an EIR of the new connection until receiving the Ethernet flow control messages, and in response to the Ethernet flow control messages, the new connection operates responsive to the Ethernet flow control messages.

41. The method of claim 24, wherein a new connection starts at a minimum rate of a Committed Information Rate (CIR) and, responsive to receiving the Ethernet flow control messages from the one or more node, operates responsive to the Ethernet flow control messages.

25. An Ethernet network, comprising

a first switch,

a second switch,

an upstream path of Ethernet packets connecting the first switch to the second switch,

a downstream path of Ethernet packets connecting the second switch to the first switch,

a first hairpin connection at the first switch selectively coupling the downstream path to the upstream path, and

a second hairpin connection at the second switch selectively coupling the upstream path to the downstream path,

wherein each of the first switch and the second switch are configured to

generate Ethernet flow control messages comprising node status and status of queues disposed therein and comprising indications of which of a plurality thresholds are reached in said queues and the Ethernet flow control messages are used to shape the Ethernet data-packet traffic without stopping transmission of Ethernet data-packets,

selectively send the Ethernet flow control messages at a highest priority directly in a backward direction via either the first hairpin connection or the second hairpin connection, and

based on the Ethernet flow control messages, adjust a rate in which a portion of the incoming traffic is admitted to the Ethernet network, wherein the portion comprises Excess Information Rate (EIR) traffic, and wherein said adjusting is based on said Ethernet flow control messages with a step up in the rate being linear and a step down in the rate being exponential, wherein the step up and the step down are proportional to prescribed Ethernet traffic descriptors.

26. The Ethernet network of claim 25, wherein the first hairpin connection and the second hairpin connection are used for control messaging to minimize delay before flow control information reaches a traffic admission mechanism.

27. The Ethernet network of claim 25, wherein the Ethernet flow control messages comprise indications of different levels of congestion, providing information about the state of a given queuing point.

28. The Ethernet network of claim 27, wherein the Ethernet flow control messages are generated when packets are being discarded for a given connection.

42. The network of claim 25, wherein a new connection starts at a minimum rate of a Committed Information Rate (CIR) and increases until reaching an EIR of the new connection or until receiving the Ethernet flow control messages, and in response to the Ethernet flow control messages, the new connection operates responsive to the Ethernet flow control messages.

43. The network of claim 25, wherein a new connection starts at a maximum rate of an EIR of the new connection until receiving the Ethernet flow control messages, and in response to the Ethernet flow control messages, the new connection operates responsive to the Ethernet flow control messages.

44. The network of claim 25, wherein a new connection starts at a minimum rate of a Committed Information Rate (CIR) and, responsive to receiving the Ethernet flow control messages from the one or more node, operates responsive to the Ethernet flow control messages.