Multiplex communications – Data flow congestion prevention or control – Flow control of data transmission through a network
Reexamination Certificate
1998-05-14
2001-03-13
Hsu, Alpus H. (Department: 2738)
Multiplex communications
Data flow congestion prevention or control
Flow control of data transmission through a network
C370S390000, C370S417000
Reexamination Certificate
active
06201792
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates generally to data communications equipment and more particularly relates to an apparatus for and a method of implementing a multicast queue responsive to backpressure.
BACKGROUND OF THE INVENTION
More and more reliance is being placed on data communication networks to carry increasing amounts of data. In a data communications network, data is transmitted from end to end in groups of bits which are called packets, frames, cells, messages, etc. depending on the type of data communication network. For example, Ethernet networks transport frames, X.25 and TCP/IP networks transport packets and ATM networks transport cells. Regardless of what the data unit is called, each data unit is defined as part of the complete message that the higher level software application desires to send from a source to a destination. Alternatively, the application may wish to send the data unit to multiple destinations.
Asynchronous Transfer Mode
ATM originated as a telecommunication concept defined by the Comite Consulatif International Telegraphique et Telephonique (CCITT), now known as the ITU, and the American National Standards Institute (ANSI) for carrying user traffic on any User to Network interface (UNI) and to facilitate multimedia networking between high speed devices at multi-megabit data rates. ATM is a method for transferring network traffic, including voice, video and data, at high speed. Using this connection oriented switched networking technology centered around a switch, a great number of virtual connections can be supported by multiple applications through the same physical connection. The switching technology enables bandwidth to be dedicated for each application, overcoming the problems that exist in a shared media networking technology, like Ethernet, Token Ring and Fiber Distributed Data Interface (FDDI). ATM allows different types of physical layer technology to share the same higher layer—the ATM layer.
More information on ATM networks can be found in the book “ATM: The New Paradigm for Internet, Intranet and Residential Broadband Services and Applications,” Timothy Kwok, Prentice Hall, 1998.
ATM uses very short, fixed length packets called cells. The first five bytes, called the header, of each cell contain the information necessary to deliver the cell to its destination. The cell header also provides the network with the ability to implement congestion control and traffic management mechanisms. Fixed length cells offer smaller and more predictable switching delays as cell switching is less complex than variable length packet switching and can be accomplished in hardware for many cells in parallel. The cell format also allows for multi-protocol transmissions. Since ATM is protocol transparent, the various protocols can be transported at the same time. With ATM, phone, fax, video, data and other information can be transported simultaneously.
ATM is a connection oriented transport service. To access the ATM network, a station requests a virtual circuit between itself and other end stations, using the signaling protocol in the ATM switch. ATM provides the User Network Interface (UNI) which is typically used to interconnect an ATM user with an ATM switch that is managed as part of the same network.
Unicast and Multicast Connections
The transmission of data to a single destination is termed a unicast connection while the transmission of data to multiple destinations is termed a multicast connection. For example, in connection with ATM switches, for each call connection within the switch, each cell has associated with it a routing tag that identifies the destination for the cell. For multicast connections, the routing tag includes identification of several destinations for the cell.
The majority of data communication networks today attempt to not lose even a single bit of information. In order to achieve such high levels of performance and low error rates, the network equipment is constructed with relatively large sized queues. The large queues are needed in order to handle the accumulation of cells (or packets, frames, etc.) without overflowing the queues. An overflow of a queue will result in cells being lost, i.e., dropped. Cells may be dropped at the source queue if the destination is full and thus cannot receive additional cells. In this case, the source queue fills up and at some point will overflow, with the consequent cell loss.
The destination queue uses a backpressure signal to indicate to the source queue that the destination queue is full and cannot receive additional cells. This problem is exasperated in multicast connections since each cell in the source multicast is replicated to several destination queues. In prior art data communications devices, the backpressure signal from any output port on the distribution list of the multicast connection will cause cell traffic to cease to the output port that is full and all the other output ports in the multicast group regardless of whether they are congested or not.
SUMMARY OF THE INVENTION
The present invention is a multicast queue for controlling cell traffic to individual output queues in a multicast group in accordance with the backpressure information generated by each output queue. One or more destinations that are sending the backpressure signal are identified and, in response thereto, the corresponding one or more destinations are removed from the
The multicast source queue associated with a multicast connection holds cells that are designated to be sent to several destinations. When a cell is transmitted, it is duplicated at the far end, i.e., at the designated destination queues. A backpressure signal is generated from a port whose associated output queue is full and cannot further receive cell traffic. If the output queue that is full is one of the destinations of the multicast cell that is at the head of the multicast queue, then, in prior art devices, the cell will not be transmitted to all the destinations in the multicast group. Only when no backpressure data is received for all destination output queues, are cells permitted to be transmitted. This may cause relatively long delays on all non backpressured (non congested) destination output queues and requires the use of extremely large buffers for the multicast queue to overcome the problem.
For each unicast call connection within the switch, each cell has associated with it a routing tag that identifies the destination for the cell. For multicast connections, the routing tag includes identification of several destinations for the cell. The present invention functions to identify the one or more destinations that are sending the backpressure signal. In response to the backpressure signal, the corresponding one or more destinations are removed from the ‘distribution list’ in the connection tag field. In this fashion, a cell that originated at a multicast source queue can be transmitted to the remaining destination queues that are not in a congested state. Cell traffic will cease only to those destination queues that generated the backpressure signal indicating that they are full.
In this fashion, the multicast queue is not loaded and all the non backpressured (non congested) destination output queues receive the multicast cell traffic with minimal delay. Suitable applications for the present invention include video transmission over the UDP transport layer, voice over ATM and any other time sensitive application including those that utilize UDP over IP.
There is provided in accordance with the present invention a multicast queue in a data communication device, the data communication device consisting of a plurality of output queues, each output queue associated with an output port, wherein each output port generates a backpressure signal when its associated output queue becomes full, the multicast queue comprising a multicast tag register having a plurality of bits, wherein each bit is associated with one of the output ports, each bit in the multicast register indicating membership in a multicast group, each
3Com Corporation
Hsu Alpus H.
Qureshi Afsar M.
Weitz David J.
Wilson Sonsini Goodrich & Rosati
LandOfFree
Backpressure responsive multicast queue does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Backpressure responsive multicast queue, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Backpressure responsive multicast queue will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2435734