Port-based fairness protocol for a network element
US-9705812-B2 · Jul 11, 2017 · US
US2016241484A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2016241484-A1 |
| Application number | US-201415027131-A |
| Country | US |
| Kind code | A1 |
| Filing date | Oct 27, 2014 |
| Priority date | Oct 30, 2013 |
| Publication date | Aug 18, 2016 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method for queue management in a packet-switched network including at an intermediate node receiving first packets belonging to a first class associated with a first queue management mechanism and second packets belonging to a second class associated with a second queue management mechanism; marking or dropping of the first packets in accordance with the first queue management mechanism and marking or dropping of the second packets in accordance with the second queue management mechanism; and coupling the marking or dropping of the second packets to the marking or dropping of the first packets.
Opening claim text (preview).
1 . A method for queue management in a packet-switched network comprising one or more intermediate network nodes, the method comprising at an intermediate node: receiving first packets belonging to a first class associated with a first queue management mechanism and second packets belonging to a second class associated with a second queue management mechanism; marking or dropping of the first packets in accordance with the first queue management mechanism and marking or dropping of the second packets in accordance with the second queue management mechanism; and coupling the marking or dropping of the second packets to the marking or dropping of the first packets. 2 . The method of claim 1 , wherein the marking or dropping of the first packets is performed in accordance with a first marking or dropping probability and the marking or dropping of the second packets is performed in accordance with a second marking or dropping probability; and wherein the coupling comprises computing the second marking or dropping probability based on a measure which is representative for the first marking or dropping probability. 3 . The method of claim 2 , wherein the received first and second packets are stored in at least one queue buffer, and the first marking or dropping probability is determined based on a measure related to the number of first and second packets in the at least one queue. 4 . The method of claim 1 , wherein the receiving comprises classifying the first packets in a first queue and the second packets in a second queue; and the coupling comprises scheduling the transmission of marked or non-dropped first and second packets from the first queue and the second queue in accordance with a first and a second weight. 5 . The method of claim 4 , wherein a first used bandwidth is measured for the first packets and a second used bandwidth is measured for the second packets; wherein the first and second used bandwidth is used to calculate the first and the second weight, respectively. 6 . The method of claim 4 , wherein the marking or dropping of the first packets is performed in accordance with a first marking or dropping probability and the marking or dropping of the second packets is performed in accordance with a second marking or dropping probability; wherein the first and second marking or dropping probability is used to determine the first and second weight, respectively. 7 . The method of claim 1 , wherein the receiving comprises classifying the first packets in a first queue and the second packets in a second queue; and the method further comprises scheduling the transmission of marked or non-dropped second packets from the second queue with priority compared to the first packets of the first queue. 8 . The method of claim 1 , wherein the first and second class are associated to any of the following protocols: Transmission Control Protocol (TCP) Reno, Transmission Control Protocol (TCP) New Reno, CUBIC Transmission Control Protocol (TCP), High Speed TCP, Compound TCP, Scalable TCP, User Datagram Protocol (UDP) using TCP Friendly Rate Control (TFRC), Multiple TCP (MULTCP), Multiple TFRC (MULTFRC), Datagram Congestion Control Protocol (DCCP), Data Center TCP (DCTCP), D 2 TCP, D 3 TCP. 9 . The method of claim 1 , wherein said coupling is such that flows of the first packets and flows of the second packets are given a predetermined share, in particular a fair share, of an available bandwidth. 10 . A system for queue management in a packet-switched network, the system comprising a receiving module for receiving first packets belonging to a first class associated with a first queue management mechanism and second packets belonging to a second class associated with a second queue management mechanism; said system being configured for marking or dropping of the first packets in accordance with the first queue management mechanism and for marking or dropping of the second packets in accordance with the second queue management mechanism; and for coupling the marking or dropping of the second packets to the marking or dropping of the first packets. 11 . The system of claim 10 , wherein the system is adapted for marking or dropping of the first packets in accordance with a first marking or dropping probability; said system further comprising: a controller configured for marking or dropping of the second packets in accordance with a second marking or dropping probability; and a computing module configured for computing the second marking or dropping probability based on a measure which is representative for the first marking or dropping probability. 12 . The system of claim 11 , further comprising at least one queue buffer for storing the received first and second packets, and wherein the computing module is further configured for determining the first marking or dropping probability based on a measure related to the number of first and second packets in the at least one queue buffer. 13 . The system of claim 10 , wherein the receiving module comprises a classifier for classifying the first packets in a first queue and the second packets in a second queue; the system further comprising a scheduler configured for scheduling the transmission of marked or non-dropped first and second packets from the first queue and the second queue in accordance with a first and a second weight; optionally comprising a measuring device configured for measuring a first used bandwidth for the first packets and a second used bandwidth for the second packets; and a weight calculator configured for using the first and second used bandwidth to calculate the first and the second weight, the system being optionally configured for marking or dropping of the first packets in accordance with a first marking or dropping probability and marking or dropping of the second packets in accordance with a second marking or dropping probability; wherein the weight calculator is configured to calculate the first and second weight based on the first and second marking or dropping probability, respectively. 14 . The system of claim 10 , wherein the receiving module comprises a classifier configured for classifying the first packets in a first queue and the second packets in a second queue; and the system further comprises a priority scheduler configured for scheduling the transmission of marked or non-dropped second packets from the second queue with priority compared to the first packets of the first queue. 15 . Computer device or other hardware device programmed to perform the computing and controlling of the method of claim 1 .
Avoiding congestion; Recovering from congestion · CPC title
Individual queue per QOS, rate or priority · CPC title
by discarding or delaying data units, e.g. packets or frames · CPC title
Integration of transport layer protocols, e.g. TCP and UDP · CPC title
by tagging of packets, e.g. using discard eligibility [DE] bits · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.