CA2299022A1 - Method and apparatus for bandwidth management of aggregate data flows - Google Patents

Method and apparatus for bandwidth management of aggregate data flows Download PDF

Info

Publication number
CA2299022A1
CA2299022A1 CA002299022A CA2299022A CA2299022A1 CA 2299022 A1 CA2299022 A1 CA 2299022A1 CA 002299022 A CA002299022 A CA 002299022A CA 2299022 A CA2299022 A CA 2299022A CA 2299022 A1 CA2299022 A1 CA 2299022A1
Authority
CA
Canada
Prior art keywords
destination point
packets
packet
transmission device
output
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
CA002299022A
Other languages
French (fr)
Inventor
Alan Stanley John Chapman
Hsiang-Tsung Kung
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nortel Networks Ltd
Original Assignee
Nortel Networks Ltd
Nortel Networks Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nortel Networks Ltd, Nortel Networks Corp filed Critical Nortel Networks Ltd
Publication of CA2299022A1 publication Critical patent/CA2299022A1/en
Abandoned legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/27Evaluation or update of window size, e.g. using information derived from acknowledged [ACK] packets
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/26Flow control; Congestion control using explicit feedback to the source, e.g. choke packets
    • H04L47/263Rate modification at the source after receiving feedback
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/16Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
    • H04L69/161Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
    • H04L69/162Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields involving adaptations of sockets based mechanisms
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/16Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
    • H04L69/163In-band adaptation of TCP data exchange; In-band control procedures
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00Arrangements for detecting or preventing errors in the information received
    • H04L1/12Arrangements for detecting or preventing errors in the information received by using return channel
    • H04L1/16Arrangements for detecting or preventing errors in the information received by using return channel in which the return channel carries supervisory signals, e.g. repetition request signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/16Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00Reducing energy consumption in communication networks
    • Y02D30/50Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate

Abstract

The present invention relates to a transmission device implementing a flow control mechanism for aggregate trunks. The transmission device can be implemented as a router that includes an input for receiving aggregate traffic streams, an output for releasing the aggregate traffic streams to a destination point and a control unit capable to regulate the rate of release of packets from the output. Specifically, the flow control operation effected by the control unit is dependent on receipt of acknowledgement messages issued at the destination point, each acknowledgement message confirming the receipt of one or more particular packets at the destination point. The control unit will continuously increase the packet sending rate until a packet is lost in the network between the transmission device and the destination point. On detection of packet loss, based on the lack of one or more corresponding acknowledgement messages from the destination point, the control unit will reduce the packet sending rate.

Description

TITLE: METHOD AND APPARATUS FOR BANDWIDTH MANAGEMENT OF AGGREGATE DATA
FLOws FIELD OF THE INVENTION
The present invention relates to the field of digital data transmission. More specifically, it pertains to a method and apparatus for performing traffic management functions, such as bandwidth management of aggregate traffic streams between two points of a data transport network.
BACKGROUND OF THE INVENTION
A typical data transport network operates in a connectionless mode whereby there is no negotiation between the transmitter/receiver and the network with regard to the type or quantity of traffic that is to be sent. The transmitter simply sends the traffic on the network, and relies on the network components to deliver that traffic to the receiver accurately.
These network components consist typically of routing nodes (also known as routers or switches) joined by physical links. The main function of the routing nodes is to direct incoming packets to the appropriate outgoing links.
Many communication network applications have adopted the Internet Protocol (IP), a library of routines called on by various network communications applications for transporting packets of data from node to node. The Transmission Control Protocol (TCP) is used for most IP network transactions and provides for both reliable transmission and rate adaptation in order to adjust to available network bandwidth. TCP allows adaptive use of available bandwidth and accommodation of different rates at different points in the internetwork or network.
G~~ithin the IP networks, there is a growing interest in managing data traffic in the form of aggregate flows. a flow, also referred to as a connection, is a stream of traffic under control of one sender within the network. Specifically, aggregating individual traffic flows into one larger flow simplifies the management of the network; routes can be pinned down for the aggregates more simply than if all flows were visible. Treatments such as bandwidth allocation or forwarding priority can be assigned to the aggregate rather than having to manage it on a per-flow basis. In the future, it may be desirable to provide flow control for these aggregates, similar to TCP, so that they can compete for available bandwidth in a controlled manner.
In Internet terminology, aggregating data traffic by encapsulating them into a single IP packet stream is often called tunneling, where the encapsulated traffic flow through the IP
network is referred to as an aggregate trunk or tunnel. When the number of aggregate trunks becomes very large, it may be desirable to add another level of aggregation by putting several such trunks into a new, larger trunk between chosen points in the network. One way to do this is to encapsulate the packets again with another TCP/IP header. Unfortunately, adding more headers to data packets is inefficient in bandwidth use and may be problematical if the longer packets violate Maximum Transport Unit (MTU) limits. Multi-protocol Label Switching (MPLS), another form of aggregation currently under development, minimizes the overhead by using a very small label instead of a full TCP/IP header. Unfortunately, the small header envisaged for MPLS does not provide room for the information usually carried in a TCP/IP flow controlled connection.
The background information herein clearly shows that there exists a need in the industry to provide an improved mechanism for ensuring flow control of an aggregate stream between two points in a network.
SUMMARY OF THE INVENTION
The present ;~nvention is directed to a transmission device for controlling the flow of an aggregate traffic stream between two points in a network, specifically a forwarding point and a destination point. 'rhe transmission device at the forwarding point includes an input for receiving aggregate traffic streams, an output for forwarding aggregate traffic streams to the destination point and a control unit for regulating the rate of release of data packets being forwarded by the transmission device to the destination point in dependence of acknowledgement messages received from the destination point. The acknowledgement messages are sent from the destination point to the forwarding point to confirm receipt or loss of one or more packets at the destination point.
The transmission device can detect and react to congestion within the network and allows for rate regulation of the aggregate flow without adding marking data to every existing packet.
According to one embodiment of the present invention, the forwarding point is analogous to a virtual sender, implemented by a router. Similarly, the destination point is analogous to a virtual receiver, also implemented by a router. The two routers are connected across a network of components by an aggregate trunk.
The forwarding router includes a control unit responsible for implementing the flow control of the aggregate trunk. The control unit observes incoming packets to find for each packet a packet identifier. More specifically, the sender will look at the packet structure to find a bit sequence that is sufficiently unique to distinguish the packet from other packets in the stream. This packet identifier is recorded in a,data structure. The control unit processes this data structure in conjunction with successive acknowledgement messages received from the virtual receiver, also containing the packet identifier (read or observed by the virtual receiver and included in the acknowledgement message), to determine if packets are being dropped. In the affirmative, the packet forwarding rate is decreased, otherwise it is increased.
According to yet another embodiment of the present invention, control packets are inserted into the aggregate trunk traffic stream at the forwarding point. The destination point is only responsible for acknowledging the control packets, and not the data packets of the aggregate traffic stream. Thus, flow control of the aggregate trunk can be implemented by looking only at the control packets. The control packets can be distinguished from the other packets based on some arbitrary identifier that is present in the control packets but absent in the other (non-control) packets. A
possible variant is to insert packet sequence information in the control packets, such that the destination point can send a control message to the forwarding point only when a control packet is missing.
In yet another embodiment, some of the aggregate traffic stream packets are marked at the forwarding point, and the destination point only acknowledges these marked packets. A
possible variant is to use the marking data to convey packet sequence information, such that the destination point can send a control message to the forwarding point only when a marked packet is missing.
The present invention also encompasses a method for controlling the flow of an aggregate traffic stream between a forwarding point and a destination point.
Other aspects and features of the present invention will become apparent to those ordinarily skilled in the art upon review of the following description of specific embodiments of the invention in conjunction with the accompanying figures.

Figure 1 is a block diagram of a flow controlled aggregate stream in an IP network, in accordance with an embodiment of the present invention;
Figure 2 is a block diagram of a muter (T~rirtual sender) shown in Figure 1;
Figure 3 illustrates a TCP congestion window function used in an embodiment of the present invention;
Figure 4 is a flowchart illustrating the operation of a program element in the router depicted in Figures 1 and 2 which implements the flow control of the aggregate stream.

A conventional IP network implements bandwidth sharing among host machines using the Transport Control Protocol (TCP). although data flow in the network can be bi-directional, it is usual to refer to the originator of a particular piece of data as the sender 15 and the other end as the receiver. In TCP, the sender (sender host machine) constantly tests the network to see if more bandwidth is available and uses the loss of a packet determined by sequence numbers of TCP packets as an indication to decrease its rate. Any lost packets are sent again so that there is a reliable flow of 20 traffic. The loss of too many packets can cause the TCP connection to enter the timed out state.
Each packet contains a sequence number, which increases according to the number of bytes transmitted. The receiver acknowledges packets using this numbering scheme and always 25 acknowledges the latest packet received in correct sequence. It may acknowledge each packet individually or wait in order to reduce overhead. It should definitely send an acknowledgement at least every second packet. Such acknowledgements can be piggybacked on data packets going in the reverse direction (from receiver to 30 sender), or can be sent as stand-alone packets with no data. If a packet is received which is not in correct sequence, the receiver will immediately send an acknowledgement but the sequence number it acknowledges will be that of the last packet which was received in correct sequence. ~t should be noted that the sequence number in a packet corresponds to the last byte in the packet and the acknowledgement contains the next expected in-sequence byte number and thus acknowledges all bytes up to that number. in general terminology, a packet is acknowledged when the receiver reports that the next expected byte number is later than any bytes contained in that packet.
The general characteristic of TCP is that it is self-clocking.
That is to say, the sender will wait for an acknowledgement from the receiver for the packets already sent before sending more packets. If the sender waited for each individual packet to be acknowledged than the maximum rate that the connection could achieve would be one packet per round trip time of the connection.
To increase the sending rate while keeping the self-clocking nature of the protocol, the sender is allowed to send some number of packets while waiting for an earlier packet to be acknowledged.
This number of packets is called the window. The receiver itself may constrain the size of the window in order to limit its buffer requirement.
The current size of the window is called the congestion window and can vary between one packet and the maximum that the receiver is prepared to accept. As the sender receives acknowledgements, the window slides forward and also increases in size. An increase in size allows the connection to run faster. If a packet is not acknowledged it will eventually be considered lost and this loss is assumed to be a result of congestion at some merge point. The sender, in addition to re-transmitting the packet, will reduce the window size. The slow and gradual increase in window size then begins again.
One embodiment of the present invention uses a mechanism to manage the data f low rate over a virtual connection between two points within a network that has some common points to the TCP
process. This mechanism is referred to as TCP-like since the virtual sender receives an indication that forwarded packets have successfully passed through the virtual receiver, and the virtual sender uses the presence or absence of these acknowledgements to reduce and increase its rate. The term virtual refers to the fact that the connection corresponds to a control loop running between two points in the network (not necessarily host machines or encapsulation/decapsulation points). Further, the traffic flowing over the virtual connection between virtual sender and virtual receiver is not being generated at the virtual sender.
Figure 1 illustrates an embodiment of a flow controlled aggregate connection (trunk), hereafter referred to as the virtual connection 106. The virtual connection 106 can be initiated between any two points in the network. Specific to this example, one of these points is referred to as the virtual sender, implemented as a router 100, while the other is referred to as the virtual receiver, implemented as router 102. Router 100 is the forwarding point and determines the packet sending rate (i.e. rate at which packets are forwarded onward). Router 102 is the destination point and monitors and acknowledges all packets received from the virtual sender 100. The functionality of these routers will be described in further detail below. The connection between virtual sender 100 and virtual receiver 102 may comprise a plurality of network 104 components, such as other routers.
As shown in Figure 2, router 100 (virtual sender) generally includes a control unit 222 and an internal bus 204. The control unit 200 itself includes a memory 200 and a processor 202, and is responsible for implementing the flow control of the aggregate trunk 106, as will be described_in further detail below. The internal bus 204 interconnects the router 100 components, enabling data and control signals to be exchanged between them. Links 224 and 226 provide for the input and output of data to and from the components of the control unit 222, in cooperation with the internal bus 204. Input ports 206, 208 and 210 connect the router 100 to physical links 216, 218 and 220, respectively, for receiving network traffic over the different link flows, where these flows have all been assigned (as per customer choice) to the virtual trunk initiated between virtual sender i00 and virtual receiver 102. Virtual port 212 is an output port that connects the router 100 to the virtual connection 106 for forwarding aggregate traffic streams to the virtual receiver 102.
The memory 200 of the control unit 222 includes a First-In-First-Out (FIFO) buffer 214 that can hold data packets received at the various input ports. The purpose of the buffer is to provide a temporary storage mechanism for holding all traffic allocated to the virtual connection 106 (i.e. traffic from all three input ports 206, 208 and 210) until a decision is made by the control unit 222 to forward the packets onward over the virtual connection 106. The physical configuration of the buffer 214 does not need to be described in detail because such components are readily available in the marketplace and the selection of the appropriate buffer mechanism suitable for use in the present invention is well within the reach of a person skilled in the art. The memory 200 also supports a standard TCP congestion window and a storage data structure, the latter including a packet identity table and a packet scoreboard table, for use by the virtual sender 100 control unit 222, all three of which will be described in further detail below.
The memory 200 further contains a program element that regulates the flow control operation of the router 100. That program element is comprised of individual instructions that are executed by the processor 202, for implementing the flow control of the aggregate connection 106 between virtual sender 100 and virtual receiver 102. This program element will be described in further detail below.
In this embodiment the virtual sender 100 adds no information to the data packets that it receives and forwards on to the virtual receiver 102. The sender 100 and the receiver 102 achieve packet identification by inspecting a part or all of the packet's existing contents. This part is called "packet identifier". This means that to perform packet identification, say at the sender 100, the sender 100 will look at the packet structure to find a bit sequence that is sufficiently unique such as to allow to distinguish this packet from other packets in the flow. Once a packet is received by the virtual receiver 102 , the receiver 102 reads some or all of the contents of the packet ;yn order to determine its unique identity (packet identifier) in the same manner as the sender 100. The sender 100 and the receiver 102 are set to look at the same part of the packet when they perform packet identification, so that they extract the same bit sequence. The particular packet part or section looked at by the virtual sender 100 and the receiver 102 can be arbitrarily set. It should also be noted that the entire packet may serve as the packet identifier, as the packet identifier is not necessarily limited to a portion of the packet.
The receiver 102 then sends an Acknowledgement Message containing this packet identifier to the sender 100 in order to confirm receipt of the particular packet. Assume for this example that the packets being forwarded from the virtual sender 100 to the virtual receiver 102 originated at a TCP/IP encapsulation. point.
Each packet will contain a unique sequence number for the encapsulated TCP connection and an identifier for the trunk (for instance the source and destination IP addresses), forming for each packet the requisite packet identifier. Thus, in this case, the sender 100 and the receiver 102 are programmed to look at the sequence number field to generate a packet identifier.
In another example, the packets may be coming from a TCP
sender in a host, where typically there is already a well understood way of using IP addresses, TCP port numbers and a sequence number to get a unique packet identifier. In yet another example, the packets may be unencapsulated Unacknowledged Datagram Protocol (UDP) packets, MPLS packets or encrypted packets, for which a hash coded form of the packet contents can be used to form the unique packet identifier. In such a case, it is necessary to take a large enough number of bytes from the packet in order to ensure that the hash code generated has a high probability of being unique. Further, the bytes selected from the packet must not include fields that might change between virtual sender 100 and . virtual receiver 102, such as a Time-To-Live (TTL) indication.
Note that over an MPLS path the packet is not changed, so there is more freedom in choosing the bytes to use.
Most preferably, the virtual receiver 102 acknowledges every packet received from the virtual sender 100. Note that the virtual receiver 102 can compose Acknowledgement Messages containing one or more packet receipt acknowledgements and insert them into the flow of traffic traveling towards the virtual sender 100.
The router 102 (virtual receiver) is structurally very similar to the virtual sender 100, and as such will not be described from a structural point of view. Although for this example the virtual receiver 102 as shown in Figure 1 is the destination point for only one trunk, notably virtual connection 106, in a typical telecommunications network such a router may act as the terminating point for a plurality of such trunks, where each trunk forms a particular virtual connection between the virtual receiver 102 and a different virtual sender. Since the virtual receiver 102 has no knowledge of which packets come from which sender, it acknowledges receipt of a packet to the virtual sender for each of the trunks it is terminating. An Acknowledgemer2t Message is broadcast by the virtual receiver 102 to all of the virtual senders to which it is connected. Note that in the case of an MPLS packet stream, the labels give a direct indication of which sender to respond to, avoiding the requirement for an acknowledgement broadcast. For the sake of the present example, assume hereinafter that the virtual receiver 102 is connected to only one sender, notably virtual sender 100.
Since there is no sequence number information added to the packets passing through virtual sender 100 with respect to the virtual connection 106, later Acknowledgement Messages sent by the virtual receiver 102 can not imply receipt of earlier packets, as is currently implemented by the standard TCP acknowledgement protocol. The loss of such an Acknowledgement Message may have an undesirable effect by suggesting the loss of many packets. In the context of the present invention, it is preferred that the virtual receiver 102 repeats an Acknowledgement Message until virtual sender 100 acknowledges receipt of it. Under this implementation, the virtual sender 100 acknowledges every Acknowledgement Message received from the virtual receiver 102 with a Return Acknowledgement Message.
When the virtual sender 100 transmits a packet over the virtual connection 106, it first determines the packet's unique identifier and its length, with which it calculates an equivalent byte sequence number. It then stores this sequence number by mapping it to the particular packet identifier in the aforementioned packet identity table of memory 200. When the virtual sender 100 receives Acknowledgement Messages from the virtual receiver 102, it reconstructs sequence number information by extracting the packet identifier from the Acknowledgement Message and reading the corresponding sequence number from the packet identity table.
Byte sequence numbers manage the congestion window stored in memory 200 of the virtual sender 100, as per standard TCP protocol.
A typical example of such a congestion window is that shown in Figure 3, where the left-hand side of the congestion window 300 is aligned with the earliest packet that has been sent but not acknowledged. Since the congestion window 300 is a feature of TCP
protocol that is well known in the art and has been well documented, it will not be described in further detail. The control unit 222 of the virtual sender 100 keeps a history of identities of packets passed forward but not yet acknowledged and processes this history in conjunction with arriving Acknowledgement Messages to adjust the pointers to the congestion window 300 and thus regulate the rate at which packets are forwarded over the virtual connection 106. In a particular example, this history is stored in a packet scoreboard in memory 200 of the virtual sender 100. The packet scoreboard is an array of binary variables, indexed by the packet byte sequence numbers. When a packet is sent over the virtual connection '106, the variable indexed by the packet identifier's corresponding sequence number is set to 1. When a packet is acknowledged, the variable indexed by the packet identifier's corresponding sequence number is cleared to 0 and, if it is the earliest packet, the left side of the congestion window 300 is moved to align with the earliest packet sent but not yet acknowledged. Thus, the packet scoreboard is a rolling list of packets that corresponds to the current congestion window 300, allowing the virtual sender 100 to detect the equivalent of multiple duplicate acknowledgements and decide whether a packet has been lost. Normal TCP mechanisms are used by the virtual sender 100 to implement window increase and decrease for controlling the sending rate of packets being transmitted over the virtual connection 106. Specifically, the virtual sender 100 will progressively increase the congestion window 300 size, and thus the sending rate, until one or more packets are lost in the network between itself and the virtual receiver 102. The virtual sender 100 detects packet loss in dependence upon the Acknowledgment Messages, or lack thereof, received from the virtual receiver 102.
On detecting packet loss (i.e. a packet forwarded over the virtual connection 106 to the virtual receiver 102 is never acknowledged), the virtual sender 100 reduces its congestion window 300 in order to decrease the sending rate. A lower sending rate on the aggregate trunk will be reflected as packet discard at the FIFO
buffer 214, which in turn will eventually be seen by the real sender.
Note that once a packet loss has been acted on by the virtual sender 100, the packet is marked as delivered. The virtual receiver 102 does not wait for resends of packets that have been lost, but rather simply passes on all packets as fast as possible to avoid adding to network latency. If required, the real sender, that is the originator of the packet (i.e. TCP sender in a host, TCP/IP encapsulation point, etc), will achieve packet reliability.
Consequently, the virtual sender 100 does not retransmit lost packets or store them once they are sent over the virtual connection 106.
Figure 4 provides a complete flowchart illustrating an example of the operation of the program element stored in the memory 200, and executed by the processor 202, that regulates the operation of the virtual sender 100, in particular the flow control of the aggregate trunk 106. At step 400, a packet from a traffic flow assigned to the aggregate trunk 106 arrives at input port 206 of the virtual sender 100, and is stored in FIFO buffer 214. At step 402, a unique packet identifier is determined and a corresponding byte sequence number calculated for the packet. The two values are stored and mapped to each other in the packet identity table in memory 200 of the virtual sender 100. The packet is next sent over the aggregate trunk 106 to the virtual receiver 102, at step 404.
Immediately following transmission, at step 406, the packet scoreboard in memory 200 of the virtual sender 100 is accessed and the variable indexed by the packet's sequence number is set to 1, indicating that the packet has been sent but has not yet been acknowledged. The program next waits for a packet Acknowledgement Message from the virtual receiver 102 at step 408. ;When such a message is received, the packet identifier is read from the message and the corresponding byte sequence number obtained from the packet identity table, at step 410. Assume for this example, that the message received acknowledges receipt of the particular packet sent out earlier at step 404. At step 412, the virtual sender 100 sends a Return Acknowledgement Message back to the virtual receiver 102 confirming receipt of the particular packet Acknowledgement Message, where this Return Acknowledgement Message includes the particular packet identifier. Next, the appropriate variable in the packet scoreboard is cleared,' indicating that the packet has been sent and acknowledged, at step 414. At step 416, the program checks to determine whether the acknowledged packet corresponds to the earliest packet in the congestion window 300. If so, the window is shifted at step 418 to align with the earliest packet that has been sent but not acknowledged.
In an alternative embodiment of the present invention, simple marking of the packets is implemented by a marking unit at the virtual sender, allowing for certain packets to be selectively marked for acknowledgement by the virtual receiver. Thus flow control is implemented by looking only at the marked packets, which is somewhat analogous to sampling the network between virtual sender and receiver in order to provide the virtual sender with a view of the existing congestion conditions. Such an implementation reduces the processing power required as well as the amount of acknowledgement traffic because fewer packets need to be processed.
Objectively, more bandwidth is consumed since marking data must be inserted in some of the packets. The marking data is a unique combination of bits placed by the marking unit at a known location in the packet. Such a location can be in an existing field of the packet or a new field can be created and appended to the packet.
The receiver 102 is set to look for this unique combination of bits at the predetermined location and examines each packet for this feature. Only packets containing this feature are being acknowledged.
In a possible variant, the marking data in addition to being an identifier may also include a sequence number. Thus the marking data may be structured as a two-element data block, the first element indicating that this is a marked packet and the second element indicating the sequence number of the packet that is different from one packet to the other. The sequence number is useful because it allows the virtual receiver to determine which packets have been dropped only by observing the sequence continuity in the received marked packets. Thus the virtual receiver may issue a control message to indicate the loss of one or more marked packets, rather than issuing acknowledgement messages to confirm the receipt of each marked packet. This is preferred since confirming loss of marked packets will require fewer messages from the virtual receiver to the virtual sender than confirming receipt of all marked packets.
In yet another alternative embodiment, the virtual sender includes a packet generator unit for generating control packets.

These control packets are inserted into the aggregate trunk traffic stream and flow control implemented by lookir_g only at the control packets, thus eliminating the requirement for robust identification of packets. Although a control packet could be sent for each user packet, it would be more efficient for control packets to be sent only as often as required to maintain a responsive control loop.
The control packets are sampling the network between virtual sender and virtual receiver in order ~o give the sender a view of the existing congestion conditions. In such an implementation of a virtual TCP connection, the virtual sender maintains accounting on the whole traffic flow in order to perform window management.
Although additional bandwidth is required to transport the control packets, this embodiment uses less bandwidth than prior art approaches where encapsulation requires that every data packet contain control information.
In a possible variant, the control packets may include sequence number information, removing the need for identification of user packets. Further, the virtual receiver may send a control message to notify the virtual sender of one or more missing packets, as opposed to sending acknowledgement messages upon receipt of every control packet. Such an alternative reduces the processing power required at a router (no packet identification required) and reduces acknowledgement traffic at the cost of some bandwidth.
The above description of a preferred embodiment under the present invention should not be read in a limitative manner as refinements and variations are possible without departing from the spirit of the invention. The scope of the invention is defined in the appended claims and their equivalents.

Claims (38)

WE CLAIM:
1. A transmission device for forwarding aggregate traffic streams towards a destination point, an aggregate traffic stream being comprised of a plurality of packets including respective identifiers allowing to distinguish one packet from another, said transmission device comprising:
- an input for receiving the aggregate traffic streams;
- an output for forwarding the aggregate traffic streams to the destination point;
- a control unit having an input for receiving an acknowledgement message issued from the destination point to notify said transmission device that a certain packet released from said output has been received at the destination point, said control unit being operative to regulate a rate at which packets are released from said output at least in part in dependence upon said acknowledgement message.
2. A transmission device as defined in claim 1, wherein said control unit forwards the aggregate traffic stream to the destination point without adding data elements to the packets of the aggregate traffic streams.
3. A transmission device as defined in claim 2, wherein said acknowledgement message conveys information relative to a packet identifier.
4. A transmission device as defined in claim 3, wherein said control unit includes a data structure, said control unit being operative for recording the identifiers of packets released at said output for forwarding to the destination point in said data structure, said control unit being operative to process said data structure in conjunction with successive acknowledgement messages received from the destination point to regulate the rate at which packets are released from said output.
5. A transmission device as defined in claim 4, wherein said control unit is operative to process said data structure in conjunction with successive acknowledgement messages received from the destination point in order to determine whether packets forwarded to the destination point have not been received at the destination point.
6. A transmission device as defined in claim 5, wherein if at least one packet has not been received at the destination point, said control unit is operative to reduce a rate of release of the packets from said output.
7. A transmission device as defined in claim 6, wherein said control unit is operative to progressively increase a rate of release of the packets from said output until a packet is not received at the destination point.
8. A method for controlling the flow of an aggregate traffic stream between a transmission device and a destination point, the aggregate traffic stream being comprised of a plurality of packets having respective identifiers allowing to distinguish one packet from another, said transmission device comprising:
- an input for receiving the aggregate traffic streams;
- an output for forwarding the aggregate traffic streams to the destination point;
- said method comprising regulating a rate at which packets are released from said output at least in part in dependence upon an acknowledgement message issued at the destination point to notify said transmission device that at least one packet released from said output has been received at the destination point.
9. A method as defined in claim 8, wherein the regulation of the rate at which packets are released from said output is performed without adding any data to packets released from said output.
10. A method as defined in claim 9, wherein said acknowledgement message conveys information relative to a packet identifier.
11. A method as defined in claim 10, comprising recording the identifiers of packets released at said output for forwarding to the destination point in a data structure, and processing said data structure in conjunction with successive acknowledgement messages received from the destination point to regulate the rate at which packets are released from said output.
12. A method as defined in claim 11, comprising processing said data structure in conjunction with successive acknowledgement messages received from the destination point in order to determine whether packets forwarded to the destination point have not been received at the destination point.
13. A method as defined in claim 12, wherein if at least one packet has not been received at the destination point, said method comprises reducing a rate of release of the packets from said output.
14. A method as defined in claim 13, wherein said method comprises the step of progressively increasing a rate of release of the packets from said output until a packet is not received at the destination point.
15. A transmission device for forwarding aggregate traffic streams towards a destination point, an aggregate traffic stream being comprised of a plurality of data packets, said transmission device comprising:
- an input for receiving the aggregate traffic streams;
- a packet generator unit for generating and inserting in the aggregate traffic stream control packets;
- an output for releasing the aggregate traffic streams and the control packets inserted in the aggregate traffic stream to the destination point, - a control unit having an input for receiving a control message issued from the destination point allowing the transmission device to determine if a control packet released from said output has been received at the destination point, said control unit being operative to regulate a rate at which data packets are released from said output at least in part in dependence upon said control message.
16. A transmission device as defined in claim 15, wherein each control packet includes sequence information indicative of a sequence of insertion of the control packet relative to other control packets inserted by the packet generator in the aggregate traffic stream.
17. A transmission device as defined in claim i6, wherein said packet generator inserts control packets into the aggregate traffic streams at predetermined intervals.
18. A transmission device as defined in claim 17, wherein said control message is an acknowledgement message that conveys to the transmission device the sequence information of at least one control packet received at the destination point.
19. A transmission device as defined in claim 18, wherein said control unit is operative to process successive acknowledgement messages received from the destination point in order to determine whether control packets forwarded to the destination point have not been received at the destination point.
20. A transmission device as defined in claim 19, wherein if at least one control packet has not been received at the destination point, said control unit is operative to reduce a rate of release of the data packets from said output.
21. A transmission device as defined in claim 20, wherein said control unit is operative to progressively increase a rate of release of the data packets from said output until a control packet is not received at the destination point.
22. A method for controlling the flow of an aggregate traffic stream between a transmission device and a destination point, the aggregate traffic stream being comprised of a plurality of data packets, said transmission device comprising:
- an input for receiving the aggregate traffic stream;
- an output for forwarding the aggregate traffic stream to the destination point;
- said method comprising:
a) inserting control packets into the aggregate traffic stream;
b) regulating a rate at which data packets are released from said output at least in part in dependence upon a control message issued at the destination point allowing the transmission device to determine if a certain control packet released from said output has been received at the destination point.
23. A method as defined in claim 22, wherein each control packet includes sequence information indicative of a sequence of insertion of the control packet relative to other control packets inserted in the aggregate traffic stream.
24. A method as defined in claim 23, wherein said control message is an acknowledgement message representative of the sequence information of at least one control packet received at the destination point.
25. A method as defined in claim 24, wherein said method comprises the step of processing successive acknowledgement messages received from the destination point in order to determine whether control packets have not been received at the destination point.
26. A method as defined in claim 25, wherein if at least one control packet has not been received at the destination point, said method comprises the step of reducing a rate of release of data packets from said output.
27. A method as defined in claim 26, wherein said method comprises the step of progressively increasing a rate of release of the data packets from said output until a control packet is not received at the destination point.
28. A transmission device for forwarding an aggregate traffic stream towards a destination point, an aggregate traffic stream being comprised of a plurality of packets including respective identifiers allowing to distinguish one packet from another, said transmission device comprising:
- an input for receiving the aggregate traffic stream;
- an output for forwarding the aggregate traffic stream to the destination point;
- a marking unit for selectively marking certain packets of the aggregate traffic streams received at said input with marking data prior to their release from said output, said marking data allowing to distinguish the marked packet from another packet in the traffic stream;
- a control unit having an input for receiving a control message issued from the destination point allowing said transmission device to determine if a certain marked packet released from said output has been received at the destination point, said control unit being operative to regulate a rate at which packets are released from said output at least in part in dependence upon said control message.
29. A transmission device as defined in claim 28, wherein said control message is an acknowledgement message indicating that a certain marked packet has been received by the destination point.
30. A transmission device as defined in claim 29, wherein said acknowledgement message contains the marked data of a packet.
31. A transmission device as defined in claim 30, wherein said control unit includes a data structure, said control unit being operative for recording the identifiers of marked packets released at said output for forwarding to the destination point in said data structure, said control unit being operative to process said data structure in conjunction with successive acknowledgement messages received from the destination point to regulate the rate at which packets are released from said output.
32. A transmission device as defined in claim 31, wherein said control unit is operative to process said data structure in conjunction with successive acknowledgement messages received from the destination point in order to determine whether marked packets forwarded to the destination point have not been received at the destination point.
33. A transmission device as defined in claim 32, wherein if at least one marked packet has not been received at the destination point, said control unit is operative to reduce a rate of release of the packets from said output.
34. A transmission device as defined in claim 33, wherein said control unit is operative to progressively increase a rate of release of the packets from said output until a marked packet is not received at the destination point.
35. A method for controlling the flow of an aggregate traffic stream between a transmission device and a destination point, the aggregate traffic stream being comprised of a plurality of packets including respective identifiers allowing to distinguish one packet from another, said transmission device comprising:

- an input for receiving the aggregate traffic streams;
- an output for forwarding the aggregate traffic streams to the destination point;
- said method comprising:
a) selectively marking certain packets of the aggregate traffic streams received at said input with marking data prior to their release from said output, the marking data allowing to distinguish one marked packet from another marked packet;

b) regulating a rate at which packets are released from said output at least in part in dependence upon a control message issued at the destination point and allowing said transmission device to determine if a certain marked packet released from said output has been received at the destination point.
36. A transmission device for forwarding aggregate traffic streams towards a destination point, an aggregate traffic stream being comprised of a plurality of packets including respective identifiers allowing to distinguish one packet from another, said transmission device comprising:

- input means for receiving the aggregate traffic streams in the transmission device;

- output means for releasing the aggregate traffic streams from the transmission device toward the destination point;
- control means having an input for receiving an acknowledgement message issued from the destination point to notify said transmission device that a certain packet released from said output means has been received at the destination point, said control unit being operative to regulate a rate at which packets are released from said output means at least in part in dependence upon said acknowledgement message.
37. A transmission device for forwarding aggregate traffic streams towards a destination point, an aggregate traffic stream being comprised of a plurality of data packets, said transmission device comprising:

- input means for receiving the aggregate traffic streams in the transmission device;

- packet generator means for generating and inserting in the aggregate traffic stream control packets;

- output means for releasing the aggregate traffic streams and the control packets inserted in the aggregate traffic stream to the destination point;

- control means having an input for receiving a control message issued from the destination point allowing the transmission device to determine if a control packet released from said output means has been received at the destination point, said control unit being operative to regulate a rate at which data packets are released from said output at least in part in dependence upon said control message.
38. A transmission device for forwarding an aggregate traffic stream towards a destination point, an aggregate traffic stream being comprised of a plurality of packets having respective identifiers allowing to distinguish one packet from another, said transmission device comprising:
- input means for receiving the aggregate traffic stream into the transmission device;
- output means for releasing the aggregate traffic stream from the transmission device toward the destination point;

- marking means for marking selectively certain packets of the aggregate traffic streams received at said input means with marking data prior to their release from said output means, said marking data allowing to distinguish one marked packet from another packet in the traffic streams;

- control means having an input for receiving a message issued from the destination point allowing said transmission device to determine if a certain marked packet released from said output means has been received at the destination point, said control means being operative to regulate a rate at which packets are released from said output means at least in part in dependence upon said control message.
CA002299022A 1999-04-30 2000-02-18 Method and apparatus for bandwidth management of aggregate data flows Abandoned CA2299022A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US30237599A 1999-04-30 1999-04-30
US09/302,375 1999-04-30

Publications (1)

Publication Number Publication Date
CA2299022A1 true CA2299022A1 (en) 2000-10-30

Family

ID=23167489

Family Applications (1)

Application Number Title Priority Date Filing Date
CA002299022A Abandoned CA2299022A1 (en) 1999-04-30 2000-02-18 Method and apparatus for bandwidth management of aggregate data flows

Country Status (4)

Country Link
US (1) US7742420B2 (en)
EP (1) EP1049299A1 (en)
JP (1) JP2000324176A (en)
CA (1) CA2299022A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113193944A (en) * 2019-10-01 2021-07-30 柏思科技有限公司 Method and system for transmitting and receiving transmission control protocol segments on internet protocol packets

Families Citing this family (62)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6920133B1 (en) * 2000-06-07 2005-07-19 At&T Corp. Techniques for introducing in-band network management packets in multi-protocol label switching networks
US20040037317A1 (en) * 2000-09-20 2004-02-26 Yeshayahu Zalitzky Multimedia communications over power lines
TW527804B (en) * 2001-05-25 2003-04-11 Accton Technology Corp Method and apparatus for bandwidth management of TCP traffic employing post-acknowledgement control
US7441017B2 (en) * 2001-06-29 2008-10-21 Thomas Lee Watson System and method for router virtual networking
FR2831742B1 (en) * 2001-10-25 2004-02-27 Cit Alcatel METHOD FOR TRANSMITTING PACKETS VIA A TELECOMMUNICATIONS NETWORK USING THE IP PROTOCOL
US7433947B1 (en) * 2002-01-04 2008-10-07 Network General Technology System and method for determining real-time application verb response times
EP1500236B1 (en) * 2002-04-29 2008-05-07 Nokia Siemens Networks Gmbh & Co. Kg Method for monitoring the transmission quality of connections in mpls networks
US7436848B1 (en) 2002-07-17 2008-10-14 Sprint Spectrum L.P. Method for mobile node registration management
KR100678223B1 (en) * 2003-03-13 2007-02-01 삼성전자주식회사 Method and apparatus for packet transmitting in a communication system
US8793394B2 (en) * 2003-12-03 2014-07-29 Nec Corporation Session relaying apparatus, session relay method, and session relay program
US9647952B2 (en) 2004-08-06 2017-05-09 LiveQoS Inc. Network quality as a service
US7953114B2 (en) 2004-08-06 2011-05-31 Ipeak Networks Incorporated System and method for achieving accelerated throughput
US8009696B2 (en) 2004-08-06 2011-08-30 Ipeak Networks Incorporated System and method for achieving accelerated throughput
US9189307B2 (en) 2004-08-06 2015-11-17 LiveQoS Inc. Method of improving the performance of an access network for coupling user devices to an application server
JP4643330B2 (en) 2005-03-28 2011-03-02 ソニー株式会社 COMMUNICATION PROCESSING DEVICE, DATA COMMUNICATION SYSTEM, COMMUNICATION PROCESSING METHOD, AND COMPUTER PROGRAM
ATE544266T1 (en) * 2005-06-10 2012-02-15 Partec Cluster Competence Ct Gmbh DATA COMMUNICATION METHOD AND SYSTEM WITH VIRTUAL PORTS
US7644343B2 (en) * 2006-01-17 2010-01-05 Rajugopal Gubbi Error resilience methods for multi-protocol encapsulation forward error correction implementations
US8139768B2 (en) * 2006-01-19 2012-03-20 Microsoft Corporation Encrypting content in a tuner device and analyzing content protection policy
US8774229B2 (en) * 2007-01-12 2014-07-08 Wi-Lan, Inc. Multidiversity handoff in a wireless broadcast system
US7912057B2 (en) 2007-01-12 2011-03-22 Wi-Lan Inc. Convergence sublayer for use in a wireless broadcasting system
US8064444B2 (en) * 2007-01-12 2011-11-22 Wi-Lan Inc. Wireless broadcasting system
US7944919B2 (en) * 2007-01-12 2011-05-17 Wi-Lan, Inc. Connection identifier for wireless broadcast system
US8548520B2 (en) 2007-01-26 2013-10-01 Wi-Lan Inc. Multiple network access system and method
US7903604B2 (en) * 2007-04-18 2011-03-08 Wi-Lan Inc. Method and apparatus for a scheduler for a macro-diversity portion of a transmission
US8711833B2 (en) * 2007-04-18 2014-04-29 Wi-Lan, Inc. Base station synchronization for a single frequency network
KR101018685B1 (en) * 2008-03-04 2011-03-04 삼성전자주식회사 Apparatus and method for controling automatic repeat request reset in wireless broadbandinternet system
US8036223B2 (en) * 2009-02-26 2011-10-11 Research In Motion Limited Method, apparatus and system for improving packet throughput based on classification of packet loss in data transmissions
US20100226384A1 (en) * 2009-03-09 2010-09-09 Prabhakar Balaji S Method for reliable transport in data networks
US8159939B1 (en) * 2009-05-08 2012-04-17 Adobe Systems Incorporated Dynamic network congestion control
US10951743B2 (en) 2011-02-04 2021-03-16 Adaptiv Networks Inc. Methods for achieving target loss ratio
US9590913B2 (en) 2011-02-07 2017-03-07 LiveQoS Inc. System and method for reducing bandwidth usage of a network
US8717900B2 (en) 2011-02-07 2014-05-06 LivQoS Inc. Mechanisms to improve the transmission control protocol performance in wireless networks
US9591069B2 (en) 2011-10-31 2017-03-07 Adobe Systems Incorporated Peer-to-peer assist for live media streaming
WO2015142241A1 (en) * 2014-03-20 2015-09-24 Telefonaktiebolaget L M Ericsson (Publ) Tunnel congestion volume policing
US10178431B2 (en) 2014-07-28 2019-01-08 Adobe Inc. Hybrid stream delivery
US9830289B2 (en) * 2014-09-16 2017-11-28 Apple Inc. Methods and apparatus for aggregating packet transfer over a virtual bus interface
US9798377B2 (en) 2014-10-08 2017-10-24 Apple Inc. Methods and apparatus for recovering errors with an inter-processor communication link between independently operable processors
DK3032771T3 (en) * 2014-12-12 2017-12-18 Sensolus Nv Battery powered device, cloud application and associated methods for transmitting / receiving data messages over a low-through network
US10042794B2 (en) 2015-06-12 2018-08-07 Apple Inc. Methods and apparatus for synchronizing uplink and downlink transactions on an inter-device communication link
US10085214B2 (en) 2016-01-27 2018-09-25 Apple Inc. Apparatus and methods for wake-limiting with an inter-device communication link
US10558580B2 (en) 2016-02-29 2020-02-11 Apple Inc. Methods and apparatus for loading firmware on demand
US10191859B2 (en) 2016-03-31 2019-01-29 Apple Inc. Memory access protection apparatus and methods for memory mapped access between independently operable processors
US10775871B2 (en) 2016-11-10 2020-09-15 Apple Inc. Methods and apparatus for providing individualized power control for peripheral sub-systems
US10591976B2 (en) 2016-11-10 2020-03-17 Apple Inc. Methods and apparatus for providing peripheral sub-system stability
US10346226B2 (en) 2017-08-07 2019-07-09 Time Warner Cable Enterprises Llc Methods and apparatus for transmitting time sensitive data over a tunneled bus interface
US10331612B1 (en) 2018-01-09 2019-06-25 Apple Inc. Methods and apparatus for reduced-latency data transmission with an inter-processor communication link between independently operable processors
US10630597B2 (en) * 2018-02-23 2020-04-21 Hewlett Packard Enterprise Development Lp Aggregate interface including millimeter-wave interface and wireless local area network interface
US11792307B2 (en) 2018-03-28 2023-10-17 Apple Inc. Methods and apparatus for single entity buffer pool management
US11381514B2 (en) 2018-05-07 2022-07-05 Apple Inc. Methods and apparatus for early delivery of data link layer packets
US10430352B1 (en) 2018-05-18 2019-10-01 Apple Inc. Methods and apparatus for reduced overhead data transfer with a shared ring buffer
US10585699B2 (en) 2018-07-30 2020-03-10 Apple Inc. Methods and apparatus for verifying completion of groups of data transactions between processors
US10846224B2 (en) 2018-08-24 2020-11-24 Apple Inc. Methods and apparatus for control of a jointly shared memory-mapped region
US10719376B2 (en) 2018-08-24 2020-07-21 Apple Inc. Methods and apparatus for multiplexing data flows via a single data structure
US10838450B2 (en) 2018-09-28 2020-11-17 Apple Inc. Methods and apparatus for synchronization of time between independently operable processors
US10789110B2 (en) 2018-09-28 2020-09-29 Apple Inc. Methods and apparatus for correcting out-of-order data transactions between processors
US11558348B2 (en) 2019-09-26 2023-01-17 Apple Inc. Methods and apparatus for emerging use case support in user space networking
US11829303B2 (en) 2019-09-26 2023-11-28 Apple Inc. Methods and apparatus for device driver operation in non-kernel space
US11606302B2 (en) 2020-06-12 2023-03-14 Apple Inc. Methods and apparatus for flow-based batching and processing
US11775359B2 (en) 2020-09-11 2023-10-03 Apple Inc. Methods and apparatuses for cross-layer processing
US11799986B2 (en) 2020-09-22 2023-10-24 Apple Inc. Methods and apparatus for thread level execution in non-kernel space
US11876719B2 (en) 2021-07-26 2024-01-16 Apple Inc. Systems and methods for managing transmission control protocol (TCP) acknowledgements
US11882051B2 (en) 2021-07-26 2024-01-23 Apple Inc. Systems and methods for managing transmission control protocol (TCP) acknowledgements

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0596159A1 (en) * 1992-11-05 1994-05-11 Alcatel N.V. Policing device and policing method using same
EP0712220A1 (en) * 1994-11-08 1996-05-15 International Business Machines Corporation Hop-by-hop flow control in an ATM network
US6252851B1 (en) * 1997-03-27 2001-06-26 Massachusetts Institute Of Technology Method for regulating TCP flow over heterogeneous networks
US6473425B1 (en) * 1997-10-02 2002-10-29 Sun Microsystems, Inc. Mechanism for dispatching packets via a telecommunications network
US6466985B1 (en) * 1998-04-10 2002-10-15 At&T Corp. Method and apparatus for providing quality of service using the internet protocol

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113193944A (en) * 2019-10-01 2021-07-30 柏思科技有限公司 Method and system for transmitting and receiving transmission control protocol segments on internet protocol packets
CN113193944B (en) * 2019-10-01 2024-02-23 柏思科技有限公司 Improved method and system for transmitting and receiving transmission control protocol segments on internet protocol packets

Also Published As

Publication number Publication date
EP1049299A1 (en) 2000-11-02
US7742420B2 (en) 2010-06-22
JP2000324176A (en) 2000-11-24
US20060039285A1 (en) 2006-02-23

Similar Documents

Publication Publication Date Title
US7742420B2 (en) Method and apparatus for bandwidth management of aggregate data flows
US6922390B1 (en) Method and apparatus for forecasting and controlling congestion in a data transport network
US7032111B1 (en) Method for optimizing of data transmission
US6535482B1 (en) Congestion notification from router
US6625118B1 (en) Receiver based congestion control
CN110661723B (en) Data transmission method, computing device, network device and data transmission system
US6882624B1 (en) Congestion and overload control in a packet switched network
US6160793A (en) ECN-based approach for congestion management in hybrid IP-ATM networks
US7719982B2 (en) Switching device utilizing flow-control management
US6215769B1 (en) Enhanced acknowledgment pacing device and method for TCP connections
US6757248B1 (en) Performance enhancement of transmission control protocol (TCP) for wireless network applications
US7315515B2 (en) TCP acceleration system
US7443845B2 (en) Apparatus and method for a lightweight, reliable, packet-based transport protocol
US7577136B1 (en) Ethernet switch fabric interface
CA2354360A1 (en) Policy enforcing switch
EP1139602A1 (en) Method and device for multicasting
US20080101237A1 (en) Communication device
US6590895B1 (en) Adaptive retransmission for error control in computer networks
Wu et al. ACK delay control for improving TCP throughput over satellite links
CN1238875A (en) Routing of packets in telecommunications system
EP1091527A2 (en) Method and apparatus for controlling bandwidth sharing in a data transport network
Rouhana et al. TCP rate implicit control (TRIC)
Jiuping et al. Early explicit congestion notification algorithm (E/sup 2/CN)
Lazaris et al. High speed transport protocols: an attempt to find the best solution

Legal Events

Date Code Title Description
EEER Examination request
FZDE Discontinued