Congestion control in a network device having a buffer circuit

• US 6,898,182 B1
• Filed: 07/21/2000
• Issued: 05/24/2005
• Est. Priority Date: 07/21/2000
• Status: Expired due to Fees

• Current Assignee: Arris International, Inc. (CommScope Holding Company, Inc.)
• Original Assignee: Arris International, Inc. (CommScope Holding Company, Inc.)
• Inventors: Cloonan, Thomas J.
• Primary Examiner(s): Rao, Seema S.
• Assistant Examiner(s): Harper, Kevin C.
• Application Number:
  US09/620,821
• Time in Patent Office: 1,768 Days
• Field of Search: 370229-236, 370412-413, 370/415, 370/417, 370/428, 370/389, 370/395, 710/52, 710/54, 710/57, 570/429
• US Class Current: 370/232
• CPC Class Codes: H04L 47/10 Flow control; Congestion control
• CPC Class Codes: H04L 47/2441 relying on flow classification, e.g. using integrated services [IntServ]
• CPC Class Codes: H04L 47/30 in combination with information about buffer occupancy at either end or at transit nodes
• CPC Class Codes: H04L 47/32 by discarding or delaying data units, e.g. packets or frames

Abstract

Each packet of the present invention is assigned a priority level. The current data packet flow rate is detected. This data packet flow rate is quantized into at least one data rate level. The current buffer circuit depth is determined as is the priority associated with the current data packet. The probability that the current packet is either dropped or used is determined by using the current data packet service flow rate, the data packet priority, and the current buffer circuit depth.

Claims

1. A method for providing data packet congestion control for a data network having a buffer circuit, each data packet comprising a priority, the method comprising the steps of:

determining a particular service flow associated with a data packet;

detecting a data packet flow rate through the data network for the particular service flow associated with the data packet;

quantizing the data packet flow rate into at least one level;

detecting a buffer circuit depth;

determining the priority associated with the current data packet;

processing the packet in response to the current data packet flow rate, the data packet priority, and the current buffer circuit depth; and

determining a probability of dropping the data packet using the data packet flow rate, the data packet priority, and the buffer circuit depth to access, from a matrix of plots indicating the probability of dropping the data packet, each of the plots within the matrix of plots indicating the packet drop probability as a function of the buffer circuit depth.

2. A method for providing data packet congestion control for a data network having a buffer circuit, each data packet comprising a priority, the method comprising the steps of:

determining a particular service flow associated with a data packet;

detecting a data packet flow rate through the data network for the particular service flow associated with the data packet;

quantizing the data packet flow rate into at least one level;

detecting a buffer circuit depth;

determining the priority associated with the current data packet;

processing the packet in response to the current data packet flow rate, the data packet priority, and the current buffer circuit depth; and

determining a probability of dropping the data packet using the data packet flow rate, the data packet priority, and the buffer circuit depth to access, from a matrix of plots indicating the probability of dropping the data packet, each of the plots within the matrix of plots indicating the packet drop probability as a function of the buffer circuit depth with plots that have the same shape and parameters as the plots used for random early Discard congestion control techniques.

3. A method for providing data packet congestion control for a data network having a buffer circuit, each data packet having a priority associated therewith, the method comprising the steps of:

determining a particular service flow associated with a data packet;

detecting a current data packet flow rate through the data network for the particular service flow associated with the data packet;

quantizing the current data packet flow rate into one of four different flow rate categories by comparing the service flow'"'"'s data packet flow rate with a minimum data rate threshold, a mid-level data rate threshold and a maximum data rate threshold, a first of the four different flow rate categories corresponding to a flow rate that is less than the minimum data rate threshold, a second category corresponding to a flow rate that is greater than the minimum threshold but less than the mid-level threshold, a third category corresponding to a flow rate that is greater than the mid-level threshold but less than the maximum threshold and a forth category corresponding to a flow rate that is greater than the maximum threshold;

determining the priority associated with the data packet; and

processing the data packet in response to the current data packet flow rate category, the data packet priority, and a current buffer circuit depth.