US5167033A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Congestion control in computer networks
Assignee: Enterasys Networks Inc
•
Filing: 1990-06-27
•
Granted: 1992-11-24
•
Expires: 2010-06-27
Abstract
Abstract A known congestion avoidance system for computer networks detects congestion at a node output port if the average queue length (integral) over the last congestion cycle plus the current (incomplete) cycle exceeds a fixed constant (taken as 1). (A congestion cycle is a period for which the queue length is 1 or more plus the following period for which the queue length is 0.) The time of arrival or departure of a message is stored at 21, the interval from the previous event is calculated at 22 and 23, the length of the current cycle is incremented at 25 by adding in the interval just determined, and the queue length at 26 is incremented or decremented by 1. The running integral for the current cycle is updated by having added into it the product formed at 27 of the interval since the last event (stored at 23) and the current queue length. The integrals for the current and previous cycles (stored at 24 and 30) are added and the lengths of those two cycles (stored at 29 and 31) are added, and the first sum divided at 34 by the second to obtain a grand average queue length. If that exceeds a preset value, then a congestion bit is set in messages leaving that node output port. In the present system, the running queue length average (in 29') is maintained by adding (at 28') the queue length (in 26') into the average at regular intervals determined by timer ticks (from 60) (thus using integer addition instead of integer multiplication), and the grand average compared with the preset value by comparing (at 61) the total of the queue length averages with the total of the cycle periods (thus using integer addition and comparison instead of floating point operation).
Inventors
- 👤 Stewart F. Bryant
- 👤 Michael J. Seaman
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-30 00:51
CPC Classifications
H; H04; H04L; H04L47/00; H04L47/10; H04L47/26; H04L47/263; H04L47/12; H04L47/30
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
331 words
A system for monitoring message congestion at an output port of a node in a network, the system comprising: A. message transmission means associated with the output port for receiving messages for transmission through the output port, the message transmission means holding each message until the message can be transmitted through the output port; B. timing means for generating timing pulses; C. message counting means for counting messages held by the message transmission means and generating a message queue length count; D. cycle counting means for counting the timing pulses and generating a cycle time count where a cycle corresponds to the time period between two successive changes of the message count from zero; E. average queue length determining means for updating, in response to a timing pulse, an average queue length count, the average queue length determining means combining a count associated with the message queue length count and the average queue length count to produce an updated version of the average queue length count; F. average queue length count manipulating means for combining the average queue length count determined by the average queue length count determining means and a stored average queue length count associated with a previous cycle to produce a total average queue length count; G. average cycle time determining means for combining the cycle time count with a stored cycle time count associated with the previous cycle to produce a total cycle time count; H. comparison means for comparing the total average queue length count and the total cycle time count; I. signalling means for asserting a congestion signal if the comparison means determines that the total average queue length count is greater than the total cycle time count; J. storage means for storing, at the end of a cycle, the average queue length count and the cycle time count; and K. means for reducing the cycle count and the average queue length count to a predetermined value after the storage means has stored the counts.
Claim 2
Independent Claim
331 words
A system for monitoring message congestion at an output port of a node in a network, the system comprising: A. message transmission means associated with the output port for receiving messages for transmission through the output port, the message transmission means holding each message until the message can be transmitted through the output port; B. timing means for generating timing pulses; C. message counting means for counting messages held by the message transmission means and generating a message queue length count; D. cycle counting means for counting the timing pulses and generating a cycle time count where a cycle corresponds to the time period between two successive changes of the message count from zero; E. average queue length determining means for updating, in response to a timing pulse, an average queue length count, the average queue length determining means combining a count associated with the message queue length count and the average queue length count to produce an updated version of the average queue length count; F. average queue length count manipulating means for combining the average queue length count determined by the average queue length count determining means and a stored average queue length count associated with a previous cycle to produce a total average queue length count; G. average cycle time determining means for combining the cycle time count with a stored cycle time count associated with the previous cycle to produce a total cycle time count; H. comparison means for comparing the total average queue length count and the total cycle time count; I. signalling means for asserting a congestion signal if the comparison means determines that the total average queue length count is greater than the total cycle time count; J. storage means for storing, at the end of a cycle, the average queue length count and the cycle time count; and K. means for reducing the cycle count and the average queue length count to a predetermined value after the storage means has stored the counts.
Claim 3
Dependent Claim
32 words
The system of claim 1, wherein the average queue length determining means combines a multiple of the message count with the average queue length count to update the average queue length count.
Claim 4
Dependent Claim
59 words
The system of claim 1, wherein the system includes an arrival counter which counts the number of messages received by the message transmission means between timer pulses, the arrival means supplying to the message counter a fraction of the count at each timer pulse, and the message counter updating the message count by the fraction at each timer pulse.
Claim 5
Dependent Claim
48 words
The system of claim 1, wherein the message counting means increases the message queue length count for each message received by the message transmission means and decrements the message queue length count for each message transmitted by the message transmission means whenever a message is transmitted or received.
Claim 6
Independent Claim
198 words
A method for monitoring message congestion at an output port of a node in a network, the method comprising the steps of: A. maintaining a count of messages held by the node for transmission through the output port during a cycle, where a cycle corresponds to a period between two successive changes of the message count from zero; B. counting timing pulses in a cycle to produce a cycle time count; C. at each timing pulse i. adding to an average queue length sum the count of the messages held by the node; ii. adding the cycle time count to a stored cycle time count associated with a preceding cycle to produce a total cycle time count; iii. adding the average queue length sum to a stored average queue length sum associated with the preceding cycle to produce a total queue length sum; D. asserting a congestion signal if the total queue length sum is greater than the total cycle time count; E. at the end of a cycle, storing the average queue length sum and the total cycle count; F. reducing the cycle time count and the average queue length to zero; and G. repeating steps A-F.
Claim 7
Independent Claim
198 words
A method for monitoring message congestion at an output port of a node in a network, the method comprising the steps of: A. maintaining a count of messages held by the node for transmission through the output port during a cycle, where a cycle corresponds to a period between two successive changes of the message count from zero; B. counting timing pulses in a cycle to produce a cycle time count; C. at each timing pulse i. adding to an average queue length sum the count of the messages held by the node; ii. adding the cycle time count to a stored cycle time count associated with a preceding cycle to produce a total cycle time count; iii. adding the average queue length sum to a stored average queue length sum associated with the preceding cycle to produce a total queue length sum; D. asserting a congestion signal if the total queue length sum is greater than the total cycle time count; E. at the end of a cycle, storing the average queue length sum and the total cycle count; F. reducing the cycle time count and the average queue length to zero; and G. repeating steps A-F.
Claim 8
Independent Claim
166 words
A method for monitoring message congestion at an output port of a node in a network, the method comprising the steps of: A. maintaining a message count of messages held by the node for transmission through the output port during a cycle, where a cycle corresponds to a period between two successive changes of the message count from zero; B. at each timing pulse i. adding to an average queue length sum the message count and producing a new average queue length sum, ii. decrementing a congestion count by one and incrementing the congestion count by a number associated with the average queue length sum, iii. adding the congestion count to a stored congestion count to produce a congestion total, and iv. asserting a congestion signal if the congestion total is greater than a predetermined minimum value; C. at the end of a cycle, storing the congestion count; D. reducing the congestion count and the average queue length sum to zero; and E. repeating steps A-D.
Claim 9
Independent Claim
166 words
A method for monitoring message congestion at an output port of a node in a network, the method comprising the steps of: A. maintaining a message count of messages held by the node for transmission through the output port during a cycle, where a cycle corresponds to a period between two successive changes of the message count from zero; B. at each timing pulse i. adding to an average queue length sum the message count and producing a new average queue length sum, ii. decrementing a congestion count by one and incrementing the congestion count by a number associated with the average queue length sum, iii. adding the congestion count to a stored congestion count to produce a congestion total, and iv. asserting a congestion signal if the congestion total is greater than a predetermined minimum value; C. at the end of a cycle, storing the congestion count; D. reducing the congestion count and the average queue length sum to zero; and E. repeating steps A-D.
Claim 10
Independent Claim
200 words
A system for monitoring message congestion at an output port of a node in a network, the system comprising: A. message transmission means associated with the output port for receiving messages for transmission through the output port, the message transmission means holding each message until the message can be transmitted through the output port; B. timing means for generating timing pulses; C. cycle count means which, in response to a timing pulse generated by the timing means, increments a cycle message queue length count by an amount associated with the number of messages that the message transmission is holding, to produce a cycle count where a cycle corresponds to a period between two successive changes of the message count from zero; D. an adder for adding the cycle count to a cycle count associated with a preceding cycle; E. signalling means for asserting a congestion signal, the signalling means asserting the congestion signal if the adder produces a sum which is greater than a predetermined minimum; F. storage means for storing the cycle count at the end of the cycle; and G. means for reducing the cycle count to a predetermined value after the storage means has stored the count.
Claim 11
Independent Claim
200 words
A system for monitoring message congestion at an output port of a node in a network, the system comprising: A. message transmission means associated with the output port for receiving messages for transmission through the output port, the message transmission means holding each message until the message can be transmitted through the output port; B. timing means for generating timing pulses; C. cycle count means which, in response to a timing pulse generated by the timing means, increments a cycle message queue length count by an amount associated with the number of messages that the message transmission is holding, to produce a cycle count where a cycle corresponds to a period between two successive changes of the message count from zero; D. an adder for adding the cycle count to a cycle count associated with a preceding cycle; E. signalling means for asserting a congestion signal, the signalling means asserting the congestion signal if the adder produces a sum which is greater than a predetermined minimum; F. storage means for storing the cycle count at the end of the cycle; and G. means for reducing the cycle count to a predetermined value after the storage means has stored the count.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1995-11-24 | 1996-05-25 | 1996-11-24 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1999-11-24 | 2000-05-25 | 2000-11-24 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2003-11-24 | 2004-05-25 | 2004-11-24 | $7700.00 | Window Closed / Lapsed |