WO2021057659A1 - 一种路径的流量分配方法、网络设备及网络系统 - Google Patents

一种路径的流量分配方法、网络设备及网络系统 Download PDF

Info

Publication number
WO2021057659A1
WO2021057659A1 PCT/CN2020/116515 CN2020116515W WO2021057659A1 WO 2021057659 A1 WO2021057659 A1 WO 2021057659A1 CN 2020116515 W CN2020116515 W CN 2020116515W WO 2021057659 A1 WO2021057659 A1 WO 2021057659A1
Authority
WO
WIPO (PCT)
Prior art keywords
path
link
traffic
flow
node
Prior art date
Application number
PCT/CN2020/116515
Other languages
English (en)
French (fr)
Inventor
刘大伟
刘文杰
程亮
李东锋
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP20868753.3A priority Critical patent/EP4030706A4/en
Publication of WO2021057659A1 publication Critical patent/WO2021057659A1/zh
Priority to US17/704,175 priority patent/US20220217089A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
    • H04L43/106—Active monitoring, e.g. heartbeat, ping or trace-route using time related information in packets, e.g. by adding timestamps
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/12—Avoiding congestion; Recovering from congestion
    • H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • H04L43/0882—Utilisation of link capacity
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • H04L45/124—Shortest path evaluation using a combination of metrics
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/70—Routing based on monitoring results
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/20—Traffic policing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
    • H04L47/2416—Real-time traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
    • H04L47/2466—Traffic characterised by specific attributes, e.g. priority or QoS using signalling traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
    • H04L47/2441—Traffic characterised by specific attributes, e.g. priority or QoS relying on flow classification, e.g. using integrated services [IntServ]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/28—Flow control; Congestion control in relation to timing considerations
    • H04L47/283—Flow control; Congestion control in relation to timing considerations in response to processing delays, e.g. caused by jitter or round trip time [RTT]

Definitions

  • This application relates to the field of communication technology, and more specifically, to a path flow distribution method, network equipment, and network system.
  • FIG. 1 is a schematic diagram of a network provided by an embodiment of the application. The following uses the example shown in FIG. 1 to illustrate the problems of the traditional path load balancing method.
  • the traditional path load balancing method uses polling or hashing to evenly distribute traffic on the three paths. It is assumed that the traditional path load balancing method allocates 1GB of sending traffic to the three paths. Since path 1 and path 2 will overlap at link C1-D, the sending traffic of link C1-D is 2GB. Since path 3 will pass through link C2-D and no other path will pass through link C2-D, the sending traffic of link C2-D is 1GB.
  • the link utilization rate of the link C1-D is 100%, indicating that the link C1-D is overloaded, so the link C1-D may be congested or packet loss; however, ,
  • the link utilization rate of the link C2-D is 50%, indicating that the link C2-D is in a light load state, so the link C2-D is not fully utilized.
  • the traditional path load balancing method may cause some links in the network to be overloaded, and some links in the network are in a light load state, so the link in the network cannot be guaranteed. Load balancing.
  • the embodiments of the present application provide a path traffic distribution method and network equipment, so as to make the load of the links in the network more balanced.
  • an embodiment of the present application provides a path traffic distribution method.
  • the method includes: an ingress node sends a measurement message to an egress node on each of at least two paths, and the at least two paths are the ingress node.
  • the measurement packet on each path is used to indicate the path information of each path.
  • the ingress node receives the response message sent by the egress node, and the response message is used to indicate the flow adjustment information of each path.
  • the ingress node determines the to-be-sent flow of each path according to the flow adjustment information of each path.
  • the ingress node can cooperate with the intermediate node and the egress node in the network, so that the ingress node can grasp the load of the link in the network, and the ingress node can distribute the sending traffic for each path, thereby ensuring that the network is The load of the link is more balanced.
  • the response message includes the flow adjustment amount of each path, and the flow adjustment amount of each path is used to indicate the flow that needs to be adjusted for each path.
  • the ingress node determines the to-be-sent traffic of each path according to the traffic adjustment information of each path.
  • the ingress node obtains the initial sending traffic of each path, and the ingress node determines the traffic adjustment amount of each path and the initial sending traffic of each path. The amount of traffic to be sent for each path.
  • the response message includes the distribution flow of each path, and the distribution flow of each path is used to indicate the transmission flow of each path link.
  • the ingress node determines the to-be-sent traffic of each path according to the traffic adjustment information of each path.
  • the ingress node obtains the initial sending traffic of each path, and the ingress node determines each path according to the initial sending traffic of each path and the assigned traffic of each path.
  • the ingress node determines the to-be-sent flow of each path according to the flow adjustment amount of each path and the initial sending flow of each path.
  • the response message includes the optimal utilization of each path and the fair bandwidth of each path.
  • the fair bandwidth of each path is used to indicate the bandwidth allocated to each path.
  • the optimal utilization is used to indicate the ratio between the sending traffic of each path and the fair bandwidth of each path.
  • the ingress node determines the to-be-sent traffic of each path according to the traffic adjustment information of each path, including: the ingress node determines the distribution flow of each path according to the optimal utilization rate of each path and the fair bandwidth of each path, and the ingress node obtains each path.
  • the ingress node determines the flow adjustment amount of each path according to the initial sending flow of each path and the distribution flow of each path, and the ingress node determines the flow adjustment amount of each path according to the flow adjustment amount of each path and the initial sending of each path
  • the flow determines the flow to be sent for each path.
  • the response message includes the fair bandwidth of each path
  • the ingress node determines the to-be-sent traffic of each path according to the traffic adjustment information of each path includes: the ingress node obtains the initial sending traffic of each path , The ingress node determines the optimal utilization of each path according to the initial sending traffic of each path and the fair bandwidth of each path, and the ingress node determines each path according to the optimal utilization of each path and the fair bandwidth of each path
  • the ingress node determines the flow adjustment amount of each path according to the initial sending flow of each path and the distribution flow of each path.
  • the ingress node determines the flow adjustment amount of each path according to the flow adjustment amount of each path and the initial sending flow of each path. The traffic to be sent for each path.
  • the response message includes the received traffic of each path and the information of the link of each path.
  • the link is the link with the highest link utilization rate on the path, and the link utilization rate is the link The ratio of the sending traffic of the road to the bandwidth of the link.
  • the ingress node determines the to-be-sent traffic of each path according to the traffic adjustment information of each path.
  • the ingress node determines the traffic to be sent for each path according to the received traffic of each path and the information of the link of each path.
  • To determine the fair bandwidth of each path the ingress node obtains the initial sending traffic of each path.
  • the ingress node determines the optimal utilization rate of each path according to the initial sending traffic of each path and the fair bandwidth of each path.
  • the optimal utilization of each path and the fair bandwidth of each path determine the distribution flow of each path.
  • the ingress node determines the flow adjustment amount of each path according to the initial sending flow of each path and the distribution flow of each path. Determine the to-be-sent flow of each path according to the flow adjustment amount of each path and the initial sending flow of each path.
  • the link information of each path includes the transmission traffic of the link of each path and the bandwidth of the link of each path, or the information of the link of each path includes each The link utilization of the link of the path.
  • determining the to-be-sent traffic of the first path includes: the ingress node calculates the sum of the flow adjustment amount of the first path and the initial sending traffic of the first path to obtain the to-be-sent traffic of the first path, and
  • the path is any one of each of the at least two paths.
  • determining the flow adjustment amount of the first path includes: the ingress node calculates the difference between the allocated flow rate of the first path and the initial sending flow rate of the first path to obtain the flow adjustment amount of the first path, and the first path It is any one of at least two paths in each path.
  • determining the allocated traffic of the first path includes: the ingress node calculates the product of the optimal utilization rate of each path and the fair bandwidth of the first path to obtain the allocated traffic of the first path, and the first path is Any one of at least two paths in each path.
  • determining the optimal utilization of each path includes: the ingress node calculates the sum of the initial transmission traffic of each path to obtain the total transmission traffic, and the ingress node calculates the sum of the fair bandwidth of each path to obtain the total For fair bandwidth, the ingress node calculates the quotient of the total sent traffic and the total fair bandwidth to obtain the optimal utilization of each path.
  • determining the fair bandwidth of the first path includes: the ingress node calculates the quotient of the received traffic of the first path and the transmitted traffic of the link of the first path to obtain the first ratio, and the first path is at least two For any path in each path of the two paths, the ingress node calculates the product of the first ratio and the bandwidth of the first path to obtain the fair bandwidth of the first path.
  • determining the fair bandwidth of the first path includes: the ingress node calculates the quotient of the received traffic of the first path and the link utilization rate of the link of the first path to obtain the fair bandwidth of the first path.
  • the measurement packet includes the sending traffic of the link and the bandwidth of the link.
  • the sending traffic of the link is the cumulative sending traffic of the link in the first time period, and the bandwidth of the link is in the first time period.
  • the bandwidth of the link in a period of time; or, the measurement packet includes the link utilization of the link, which is the ratio of the transmission traffic of the link to the bandwidth of the link; or, the measurement packet includes the link.
  • the sending traffic and the bandwidth of the link, the measurement packet also includes at least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the first time stamp is the sending time of the measurement packet
  • the initial sending traffic of the path is The cumulative sending traffic of the path in the second time period, or the initial sending traffic of the path is the cumulative sending traffic of the path corresponding to the first timestamp; or, the measurement packet includes the link utilization of the link, and the measurement packet also includes At least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the response message also includes the path identifier, the first time stamp, the second time stamp, the third time stamp, the receiving traffic of the path, the link utilization of the link, and the sending traffic of the link.
  • the second timestamp is the receiving time of the measurement message
  • the third timestamp is the sending time of the response message
  • the receiving traffic of the path is the cumulative receiving traffic of the path in the third time period
  • the received traffic of the path is the cumulative received traffic of the path corresponding to the second time stamp
  • the third time period is later than or equal to the second time period.
  • an embodiment of the present application provides a path traffic distribution method.
  • the method includes: an intermediate node receives a measurement packet on a first path of at least two paths, the at least two paths being an ingress node and an egress node
  • the measurement packet is used to indicate the information of the first link of the first path.
  • the intermediate node obtains the information of the second link.
  • the second link is connected to the outgoing port of the intermediate node on the first path.
  • Link when the intermediate node determines that the link utilization rate of the first link is greater than or equal to the link utilization rate of the second link according to the information of the first link and the information of the second link, the intermediate node sends to the egress node Measurement packets, link utilization is used to indicate the traffic occupancy of the link, and the intermediate node determines that the link utilization of the first link is less than the second link according to the information of the first link and the information of the second link When the link utilization rate is higher, the intermediate node fills the information of the second link into the measurement message, and the intermediate node sends the measurement message to the egress node.
  • the intermediate node in the network can cooperate with the ingress node and the egress node, so that the ingress node can grasp the load of the link in the network, and the ingress node can distribute the sending traffic for each path, thereby ensuring that the network is The load of the link is more balanced.
  • the information of the first link includes the sending traffic of the first link and the bandwidth of the first link
  • the information of the second link includes the sending traffic of the second link and the second link.
  • the information about the first link includes the link utilization rate of the first link
  • the information about the second link includes the link utilization rate of the second link.
  • the method further includes: the first intermediate node deletes the first measurement packet.
  • the first measurement packet further includes at least one of the path identifier of the first path, a time stamp, or the initial transmission traffic of the first path
  • the time stamp is the transmission time of the first measurement packet.
  • the second measurement message further includes at least one of the path identifier of the first path, a time stamp, or the initial transmission traffic of the first path.
  • the measurement packet includes the sending traffic of the link and the bandwidth of the link.
  • the sending traffic of the link is the cumulative sending traffic of the link in the first time period, and the bandwidth of the link is in the first time period.
  • the bandwidth of the link in a period of time; or, the measurement packet includes the link utilization of the link, which is the ratio of the transmission traffic of the link to the bandwidth of the link; or, the measurement packet includes the link.
  • the sending traffic and the bandwidth of the link, the measurement packet also includes at least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the first time stamp is the sending time of the measurement packet
  • the initial sending traffic of the path is The cumulative sending traffic of the path in the second time period, or the initial sending traffic of the path is the cumulative sending traffic of the path corresponding to the first timestamp; or, the measurement packet includes the link utilization of the link, and the measurement packet also includes At least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • an embodiment of the present application provides a path traffic distribution method.
  • the method includes: an egress node receives a measurement message sent by an ingress node on each of at least two paths, and the at least two paths are ingress. The path between the node and the egress node.
  • the measurement message on each path is used to indicate the path information of each path.
  • the egress node generates a response message according to the path information of each path and the received traffic of each path.
  • the text is used to indicate the flow adjustment information of each path, and the egress node sends a response message to the ingress node.
  • the egress node in the third aspect, can cooperate with the ingress node and the intermediate node, so that the ingress node can grasp the load of the link in the network, and the ingress node can distribute the sending traffic for each path, thereby ensuring the network The load of the link is more balanced.
  • the measurement packet includes the sending traffic of the link and the bandwidth of the link.
  • the sending traffic of the link is the cumulative sending traffic of the link in the first time period, and the bandwidth of the link is in the first time period.
  • the bandwidth of the link in a period of time; or, the measurement packet includes the link utilization of the link, which is the ratio of the transmission traffic of the link to the bandwidth of the link; or, the measurement packet includes the link.
  • the sending traffic and the bandwidth of the link, the measurement packet also includes at least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the first time stamp is the sending time of the measurement packet
  • the initial sending traffic of the path is The cumulative sending traffic of the path in the second time period, or the initial sending traffic of the path is the cumulative sending traffic of the path corresponding to the first timestamp; or, the measurement packet includes the link utilization of the link, and the measurement packet also includes At least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the response message includes the link information of each path and the received traffic of each path.
  • the egress node generates a response message according to the path information of each path and the received traffic of each path, including: the egress node determines the response message according to the link information of each path and the received traffic of each path. For the fair bandwidth of each path, the egress node generates a response message, which includes the fair bandwidth of each path.
  • the egress node generates a response message according to the path information of each path and the received traffic of each path, including: the egress node determines the response message according to the link information of each path and the received traffic of each path. For the fair bandwidth of each path, the egress node obtains the initial sending traffic of each path. The egress node determines the optimal utilization of each path according to the initial sending traffic of each path and the fair bandwidth of each path, and the egress node generates a response report. The response message includes the optimal utilization of each path and the fair bandwidth of each path.
  • the egress node generates a response message according to the path information of each path and the received traffic of each path, including: the egress node determines the response message according to the link information of each path and the received traffic of each path. For the fair bandwidth of each path, the exit node obtains the initial sending traffic of each path. The exit node determines the optimal utilization rate of each path according to the initial sending traffic of each path and the fair bandwidth of each path. The optimal utilization rate of the path and the fair bandwidth of each path determine the distribution flow of each path. The egress node generates a response message, and the response message includes the distribution flow of each path.
  • the egress node generates a response message according to the path information of each path and the received traffic of each path, including: the egress node determines the response message according to the link information of each path and the received traffic of each path.
  • the exit node obtains the initial sending traffic of each path.
  • the exit node determines the optimal utilization rate of each path according to the initial sending traffic of each path and the fair bandwidth of each path.
  • the optimal utilization of the path and the fair bandwidth of each path determine the distribution flow of each path.
  • the egress node determines the flow adjustment amount of each path according to the initial sending flow of each path and the distribution flow of each path, and the egress node generates Reply message, the reply message includes the traffic adjustment amount of each path.
  • the path information of each path includes the transmission traffic of the link of each path and the bandwidth of the link of each path, or the path information of each path includes the link of each path.
  • Link utilization
  • determining the fair bandwidth of the first path includes: the egress node calculates to determine the fair bandwidth of the first path according to the link information of the first path and the received traffic of the first path, and the first path is at least Any path in each of the two paths.
  • determining the optimal utilization rate of each path includes: the egress node calculates the sum of the initial transmission traffic of each path to obtain the total transmission traffic, and the egress node calculates the sum of the fair bandwidth of each path to obtain the total For fair bandwidth, the egress node calculates the quotient of the total sent traffic and the total fair bandwidth to obtain the optimal utilization of each path.
  • determining the assigned traffic of the first path includes: the egress node calculates the product of the optimal utilization rate of each path and the fair bandwidth of the first path to obtain the assigned traffic of the first path, and the first path is Any one of at least two paths in each path.
  • determining the flow adjustment amount of the first path includes: the egress node calculates the difference between the allocated flow rate of the first path and the initial sending flow rate of the first path to obtain the flow adjustment amount of the first path. It is any one of at least two paths in each path.
  • the response message also includes the path identifier, the first time stamp, the second time stamp, the third time stamp, the receiving traffic of the path, the link utilization of the link, and the sending traffic of the link.
  • the second timestamp is the receiving time of the measurement message
  • the third timestamp is the sending time of the response message
  • the receiving traffic of the path is the cumulative receiving traffic of the path in the third time period
  • the received traffic of the path is the cumulative received traffic of the path corresponding to the second time stamp
  • the third time period is later than or equal to the second time period.
  • the embodiments of the present application provide a network device, which has any possible implementation manner of the first aspect and the first aspect, and any possible implementation manner of the second aspect and the second aspect.
  • the function can be realized by hardware, or by hardware executing corresponding software.
  • the hardware or software includes one or more modules corresponding to the above-mentioned functions.
  • the network device may be a router.
  • an embodiment of the present application provides a network device.
  • the network device includes a processor and a memory, where the processor is configured to read software codes stored in the memory and execute the first aspect or any one of the first aspects.
  • the method in one possible implementation manner, or the computer or processor is caused to execute the method in any one of the foregoing second aspect or the second aspect, or the computer or the processor is caused to execute the third aspect or the third aspect.
  • the method in any possible implementation of the aspect.
  • the embodiments of the present application provide a computer-readable storage medium that stores instructions in the computer-readable storage medium, which when run on a computer, causes the computer to execute the first aspect or any of the first aspects.
  • a computer program product containing instructions which when running on a computer or processor, causes the computer or processor to execute the method in the first aspect or any one of the possible implementations of the first aspect. , Or, cause a computer or a processor to execute the method in the foregoing second aspect or any one of the possible implementations of the second aspect, or cause a computer or a processor to execute the foregoing third aspect or any of the foregoing possible implementations of the third aspect The method in the way.
  • the embodiments of the present application provide a network system.
  • the network system includes an ingress node, an intermediate node, and an egress node.
  • the ingress node is used to perform the above-mentioned first aspect or any one of the possible implementations of the first aspect.
  • the intermediate node is used to execute the method in any possible implementation manner of the second aspect or the second aspect
  • the exit node is used to execute the method in any possible implementation manner of the third aspect or the third aspect. method.
  • the ingress node, the intermediate node, and the egress node can cooperate with each other so that the ingress node can grasp the load status of the link in the network, and the ingress node can distribute the sending traffic for each path, thereby ensuring the link in the network.
  • the load is more balanced.
  • FIG. 1 is a schematic diagram of a network provided by an embodiment of this application.
  • Figure 2 is a schematic diagram of another network provided by an embodiment of the application.
  • FIG. 3 is a flowchart of a method for allocating path traffic according to an embodiment of the application
  • FIG. 4 is another schematic diagram of a network provided by an embodiment of this application.
  • FIG. 5 is a flowchart of yet another path traffic distribution method provided by an embodiment of the application.
  • FIG. 6 is a flowchart of yet another path traffic distribution method provided by an embodiment of the application.
  • FIG. 7 is a flowchart of yet another path traffic distribution method according to an embodiment of the application.
  • FIG. 8 is a schematic diagram of an ingress node provided by an embodiment of this application.
  • FIG. 9 is a schematic diagram of an intermediate node provided by an embodiment of this application.
  • FIG. 10 is a schematic diagram of an egress node provided by an embodiment of this application.
  • FIG. 11 is a schematic diagram of another ingress node provided by an embodiment of this application.
  • FIG. 12 is a schematic diagram of yet another intermediate node provided by an embodiment of this application.
  • FIG. 13 is a schematic diagram of another exit node provided by an embodiment of this application.
  • FIG. 14 is a schematic diagram of a network system provided by an embodiment of this application.
  • the path traffic distribution method provided in the embodiments of the present application can be applied to ingress nodes, intermediate nodes, and egress nodes in the network, and the ingress nodes, intermediate nodes, and egress nodes can be network devices with routing and forwarding functions such as routers.
  • the ingress node, the intermediate node, and the egress node can cooperate with each other so that the ingress node can grasp the load status of the link in the network, and the ingress node can distribute the sending traffic for each path, thereby ensuring the link in the network.
  • the load is more balanced.
  • FIG. 2 is a schematic diagram of another network provided by an embodiment of this application.
  • the network shown in Figure 2 includes an ingress node A, an intermediate node B1, an intermediate node B2, and an egress node C.
  • the two paths are path 1 and path 2. .
  • path 1 is node A->node B1->node C
  • path 2 is node A->node B2->node C.
  • Path 1 passes through link X1 and link X2, link X1 is the link between the outgoing port a1 of node A and node B1, and link X2 is the link between the outgoing port b1 of node B1 and node C.
  • Path 2 passes through link Y1 and link Y2, link Y1 is the link between the outgoing port a2 of node A and node B2, and link Y2 is the link between the outgoing port b2 of node B2 and node C.
  • the sending traffic U11 of the link X1 600MB
  • the sending traffic U12 of the link X2 800MB
  • the sending traffic U11 of the link X1 is the cumulative sending traffic of the outgoing port a1 of the ingress node A in the first time period
  • the sending traffic U12 of the link X2 is the outgoing port b1 of the ingress node B1 in the first time period
  • the sending traffic U21 of the link Y1 is the cumulative sending traffic of the outgoing port a2 of the ingress node A in the first time period
  • the sending traffic U22 of the link Y2 is the outgoing traffic of the ingress node B2 in the first time period.
  • the first time period is a preset time period.
  • the first time period can be set to 10 ⁇ s, 20 ⁇ s, or 30 ⁇ s in advance.
  • those skilled in the art can set the first time period according to the actual situation, and the first time period is not limited to the time length provided in the embodiment of the present application.
  • the initial sending traffic S1 of path 1 is the cumulative sending traffic of ingress node A on path 1 in the second time period
  • the initial sending traffic S2 of path 2 is the initial sending traffic S2 of ingress node A on path 2 in the second time period.
  • the received flow R1 of path 1 is the cumulative received flow of egress node C on path 1 in the third time period
  • the received flow R2 of path 2 is the cumulative received flow of egress node C on path 2 in the third time period.
  • the first time period, the second time period, and the third time period are all preset time periods.
  • the first time period can be set to 10 ⁇ s, 20 ⁇ s, 30 ⁇ s, or the like.
  • the second time period can be set to 10ms, 20ms, 30ms, and so on.
  • the third time period can be set to 10ms, 20ms, or 30ms.
  • the first time period is a period of time within the second time period
  • the third time period is later than the second time period. For example, suppose the first time period is 0-10 ⁇ s, the second time period is 0-3ms, and the third time period is 3ms-6ms.
  • first time period the second time period and the third time period according to the actual situation.
  • the first time period, the second time period and the third time period are not limited to the embodiments of the present application.
  • FIG. 3 is a flowchart of a path traffic distribution method according to an embodiment of the application.
  • the path traffic distribution method shown in FIG. 3 can be applied to the network shown in FIG. 2 .
  • the path traffic distribution method provided by the embodiment of the present application includes:
  • the egress port a1 of the ingress node A sends a measurement message G1 to the egress node C on the path 1, and the egress port a2 of the ingress node A sends a measurement message G2 to the egress node C on the path 2.
  • the measurement message G1 includes the sending traffic U11 (600MB) of the link X1, the bandwidth B11 (1000MB) of the link X1, and the initial sending traffic S1 (300MB) of the path 1.
  • the measurement message G2 includes the sending traffic U21 (1400MB) of the link Y1, the bandwidth B21 (2000MB) of the link Y1 and the initial sending traffic S2 (900MB) of the path 2.
  • the ingress node A of the embodiment of the present application can put the initial transmission flow S1 (300MB) of path 1 in the second time period (within 0-3ms) into the measurement message G1, and the initial transmission flow S1 (300MB) of path 1 ) Is the difference between the cumulative sending traffic of path 1 in 3ms and the cumulative sending traffic of 0ms.
  • the measurement message G1 may also include the path identifier of the path 1 and a timestamp t1, where the timestamp t1 is the sending time of the measurement message G1, and the second time period is 0-3 ms, then the timestamp t1 is 3 ms. If the measurement message G1 contains a time stamp t1, then the initial sending traffic S1 (300MB) of path 1 is the cumulative sending traffic of path 1 in 3 ms. Since the ingress node A sent the last measurement message G3 on path 1 at the 0th ms, the egress node C can extract the initial sent traffic S3 (0MB) and the measurement message of path 1 in the 0th ms of the measurement message G3.
  • the measurement message G2 may also include the path identifier of the path 2 and a timestamp t2, where the timestamp t2 is the sending time of the measurement message G2, and the second time period is 0-3 ms, then the timestamp t2 is 3 ms.
  • the purpose of ingress node A sending a measurement message to egress node C on each path is to put the information of the link with the highest link utilization rate on each path into the measurement message to facilitate the export Node C can grasp the information of the bottleneck link on each path, and re-allocate more link sending traffic to each path based on the information of the bottleneck link on each path.
  • the bottleneck link is the link with the highest link utilization rate on a path.
  • the intermediate node B1 receives the measurement message G1 sent by the outgoing port a1 of the ingress node A on the path 1, and calculates the link utilization rate H11 (60%) of the link X1 and the link utilization rate H12 (80%) of the link X2. %), determine that the link utilization rate H12 (80%) of the link X2 is greater than the link utilization rate H11 (60%) of the link X1, and combine the sending traffic U12 (800MB) of the link X2 with the bandwidth B12 of the link X2 (1000MB) is filled into the measurement message G1, and the egress port b1 of the intermediate node B1 sends the measurement message G1 to the egress node C on the path 1.
  • the link utilization rate of link X2 H12 link X2
  • the sending traffic U12 (800MB) ⁇ the bandwidth of the link X2 B12 (1000MB) 80%.
  • the link utilization rate of the link is the ratio of the sending traffic of the link to the bandwidth of the link, and the link utilization rate of the link is used to indicate the traffic occupancy of the link.
  • the higher the link utilization rate of the link the more traffic occupied by the link; the lower the link utilization rate of the link, the less traffic occupied by the link.
  • the link utilization rate H12 of link X2 is higher than the link utilization rate H11 of link X1, indicating that link X2 is the link with the highest link utilization rate in path 1.
  • X2 is the bottleneck link in path 1.
  • the intermediate node B2 receives the measurement message G2 sent by the outgoing port a2 of the ingress node A on the path 2, and calculates the link utilization rate H21 (70%) of the link Y1 and the link utilization rate H22 (75%) of the link Y2. %), it is determined that the link utilization rate H22 (75%) of the link Y2 is greater than the link utilization rate H21 (70%) of the link Y1, and the transmission traffic U22 (1500MB) of the link Y2 is combined with the bandwidth B22 of the link Y2 (2000MB) is filled into the measurement message G2, and the egress port b2 of the intermediate node B1 sends the measurement message G2 to the egress node C on the path 2.
  • the link utilization rate of link Y2 H22 link Y2
  • the sending traffic U22 (1500MB) ⁇ the bandwidth B22 (2000MB) of the link Y2 75%.
  • Link Y2 is the bottleneck link in path 2.
  • the egress node C respectively calculates the fair bandwidth D1 of path 1 and the fair bandwidth D2 of path 2 according to the link information in the measurement message G1 and the measurement message G2.
  • fair bandwidth D2 of path 2 (received traffic R2 of path 2 ⁇ transmission traffic U22 of link Y2 of path 2)
  • the sending traffic U12 of link X2 of path 1 is 800MB
  • the link bandwidth B12 of link X2 of path 1 is 1000MB
  • the receiving traffic R1 of path 1 is 300MB
  • the traffic of link X2 occupied by other paths is 500MB.
  • egress node C After egress node C knows that the received traffic of path 1 occupies 37.5% of the transmitted traffic of link X2, egress node C calculates the product of this ratio and the link bandwidth B12 of link X2 to obtain the fair bandwidth of path 1. D1, the fair bandwidth of path 1. D1 is used to indicate the maximum bandwidth allocated by link X2 for path 1, that is, the maximum bandwidth allocated by link X2 for path 1 is 375MB, and the sum of the maximum bandwidth allocated by link X2 for other paths is 625MB .
  • the fair bandwidth D2 of path 2 is used to indicate the maximum bandwidth allocated by link Y2 for path 2, that is, the maximum bandwidth allocated by link Y2 for path 2 is 1200MB, and the sum of the maximum bandwidth allocated by link X2 for other paths is 800MB.
  • the exit node C calculates the optimal utilization rate H of the path.
  • the optimal utilization rate H of the path is the ratio between the transmission traffic of all paths and the fair bandwidth of all paths, and the optimal utilization rate H of the path is used to indicate the ratio between the transmission traffic of the path and the fair bandwidth of the path.
  • the egress node C calculates the distribution flow K1 of path 1 and the distribution flow K2 of path 2 respectively.
  • the distribution flow K1 of path 1 is used to indicate the transmission flow of the path 1 link
  • the distribution flow K2 of path 2 is used to indicate the transmission flow of the path 2 link.
  • the exit node C calculates the flow adjustment amount L1 of path 1 and the flow adjustment amount L2 of path 2 respectively.
  • the flow adjustment amount L1 of path 1 is used to indicate the flow that needs to be adjusted in path 1
  • the flow adjustment amount L2 of path 2 is used to indicate the flow that needs to be adjusted in path 2.
  • the response message Y includes the flow adjustment amount L1 of path 1 and the flow adjustment amount L2 of path 2.
  • the response message may also include the path identifier of path 1, the path identifier of path 2, time stamp t1, time stamp t2, time stamp t3, time stamp t4, time stamp t5, path 1 receiving traffic R1, path 2 Receiving traffic R2, link utilization rate H12 (80%) of link X2, link utilization rate H22 (75%) of link Y2, transmission traffic U12 (800MB) of link X2, bandwidth B12 of link X2 ( 1000MB), at least one of the sending traffic U22 (1500MB) of the link Y2 or the bandwidth B22 (2000MB) of the link Y2, the time stamp t3 is the reception time of the measurement message G1, and the time stamp t4 is the reception of the measurement message G2 Time, the timestamp t5 is the sending time of the response message Y, the received traffic R1 of path 1 is the cumulative received traffic of path 1 in the third time period (3-6ms), and the received traffic R2 of path 2 is at the third time The cumulative received flow of path 2 in the segment (3-6ms).
  • the received traffic R1 of path 1 may also be the accumulated received traffic of path 1 corresponding to the time stamp t3. If the measurement message G1 contains a time stamp t3, then the received traffic R1 of path 1 is the cumulative sent traffic of path 1 at the time stamp t3.
  • the ingress node can calculate the path 1 in the third time period (3-6ms) according to the received traffic of the 3ms path 1 and the 6ms path 1 in the two adjacent response messages received. Cumulative received traffic.
  • the ingress node A receives the response message Y sent by the egress node C, and determines the to-be-sent traffic Z1 of path 1 and the to-be-sent traffic Z2 of path 2 according to the response message Y.
  • the to-be-sent flow Z2 of path 2 the flow adjustment amount of path 2 L2+path 2
  • the to-be-sent traffic Z1 of path 1 is the estimated cumulative sending traffic of ingress node A on path 1 in the fourth time period
  • the to-be-sent traffic Z2 of path 2 is expected to be the ingress node A’s on path in the fourth time period. Cumulative sending traffic on 2.
  • the fourth time period is later than the third time period.
  • the first time period is 0-10 ⁇ s
  • the second time period is 0-3ms
  • the third time period is 3ms-6ms
  • the fourth time period is 6ms-9ms.
  • the ingress node A, the intermediate node B1, the intermediate node B2, and the egress node C cooperate with each other so that the ingress node A can grasp the load of the bottleneck link in the network.
  • the ingress node A can then allocate the to-be-sent traffic to path 1 and path 2, so as to ensure that the load of the links in the network is more balanced.
  • the egress node C calculates the fair bandwidth D1 of path 1, the fair bandwidth D2 of path 2, the optimal utilization rate of path H, the allocation of path 1 The flow rate K1, the distribution flow rate K2 of the path 2, the flow rate adjustment amount L1 of the path 1, and the flow rate adjustment amount L2 of the path 2. Then, the egress node C puts the flow adjustment amount L1 of path 1 and the flow adjustment amount L2 of path 2 into the response message Y, and sends the response message Y to the ingress node A.
  • S104 to S109 provide an implementation manner in the embodiment of the present application, and the embodiment of the present application may also adopt other implementation manners.
  • the egress node C sends the received traffic R1 of path 1 and the link X2 of path 1
  • the traffic U12, the link bandwidth B12 of the link X2 of path 1, the receiving traffic R2 of the path 2, the sending traffic U22 of the link Y2 of the path 2, and the link bandwidth B22 of the link Y2 of the path 2 are put in the response message Y And send the response message Y to the ingress node A.
  • the ingress node A calculates the to-be-sent traffic Z1 of path 1 and the to-be-sent traffic Z2 of path 2 based on the information in the response message Y.
  • the egress node C uses the link information in the measurement message G1 and the measurement message G2.
  • the egress node C puts the fair bandwidth D1 of path 1 and the fair bandwidth D2 of path 2 into the response message Y, and sends the response message Y to the ingress node In A.
  • the ingress node A calculates the to-be-sent traffic Z1 of path 1 and the to-be-sent traffic Z2 of path 2 based on the information in the response message Y.
  • the egress node C uses the link information in the measurement message G1 and the measurement message G2 Calculate the fair bandwidth D1 of path 1 and the fair bandwidth D2 of path 2, the egress node C calculates the optimal utilization rate H of the path, and the egress node C calculates the fair bandwidth D1 of path 1 and the fair bandwidth D2 of path 2 and the optimal utilization of the path
  • the rate H is put into the response message Y, and the response message Y is sent to the ingress node A.
  • the ingress node A calculates the to-be-sent traffic Z1 of path 1 and the to-be-sent traffic Z2 of path 2 based on the information in the response message Y.
  • the egress node C uses the link information in the measurement message G1 and the measurement message G2.
  • the egress node C calculates the optimal utilization rate H of the path
  • the egress node C calculates the distribution flow K1 of path 1 and the distribution flow K2 of path 2
  • the egress node C calculates the path
  • the distribution flow K1 of 1 and the distribution flow K2 of path 2 are put into the response message Y, and the response message Y is sent to the ingress node A.
  • the ingress node A calculates the to-be-sent traffic Z1 of path 1 and the to-be-sent traffic Z2 of path 2 based on the information in the response message Y.
  • the measurement message includes the sending traffic of the link, the bandwidth of the link, and the initial sending traffic of the path.
  • the measurement message may also include the link utilization rate of the link and the initial sending traffic of the path.
  • the fair bandwidth of the path D the received traffic R of the path ⁇ the link utilization rate of the link.
  • the calculation result of this method is the same as the calculation of S104
  • FIG. 4 is another schematic diagram of a network provided by an embodiment of this application.
  • the network shown in FIG. 4 includes an ingress node A, an intermediate node B1, an intermediate node B2, an intermediate node B3, an intermediate node C1, an intermediate node C2, and an egress node D.
  • There are three paths between the ingress node A and the egress node D and the three paths are path 1, path 2, and path 3.
  • path 1 is node A->node B1->node C1->node D
  • path 2 is node A->node B2->node C1->node D
  • path 3 is node A->node B3-> Node C2->Node D.
  • the bottleneck link of path 1 is link C1-D
  • the bottleneck link of path 2 is link C1-D
  • the bottleneck link of path 3 is link C2-D
  • the sending traffic of link C1-D U1 2000MB
  • the sending traffic of link C2-D U2 1000MB
  • R1 of Path 1 Reception flow rate
  • the ingress node A sends a measurement message G1, a measurement message G2, and a measurement message G3 to the egress node D on path 1, path 2, and path 3, respectively.
  • the intermediate node B1, the intermediate node B2, the intermediate node B3, the intermediate node C1, and the intermediate node C2 please refer to S102 and S103 in the embodiment shown in FIG. 3, which will not be repeated here.
  • the egress node D calculates the fair bandwidth D1 of path 1, the fair bandwidth D2 of path 2, and The fair bandwidth D3 of path 3.
  • the fair bandwidth D1 of path 1 (received traffic R1 of path 1 ⁇ transmission traffic U1 of link C1-D of path 1)
  • the fair bandwidth of path 2 D2 (received traffic R2 of path 2 ⁇ transmission traffic U1 of link C1-D of path 2)
  • the egress node D calculates the optimal utilization rate H of the path.
  • the egress node C respectively calculates the distribution flow K1 of the path 1, the distribution flow K2 of the path 2, and the distribution flow K3 of the path 3.
  • the egress node C calculates the distribution flow K1 of path 1, the distribution flow K2 of path 2, and the distribution flow K3 of path 3, the egress node C calculates the flow adjustment amount L1 of path 1 respectively. , The flow adjustment amount L2 of path 2 and the flow adjustment amount L3 of path 3.
  • the egress node C after the egress node C calculates the flow adjustment amount L1 of path 1, the flow adjustment amount L2 of path 2, and the flow adjustment amount L3 of path 3, the egress node C sends a response to the ingress node A Message Y.
  • the response message Y includes the flow adjustment amount L1 of the path 1, the flow adjustment amount L2 of the path 2, and the flow adjustment amount L3 of the path 3.
  • the response message Y sent by the egress node C is received at the ingress node, and the to-be-sent traffic Z1 of path 1 and the to-be-sent traffic Z2 and path 3 of path 2 are determined according to the response message Y.
  • the sending traffic U1 of the link C1-D is the cumulative sending traffic of the link C1-D in the first time period
  • the sending traffic U2 of the link C2-D is the first time.
  • the cumulative sending traffic of link C2-D in the segment, the sending traffic S1 of path 1 is the cumulative sending traffic of egress node A on path 1 in the second time period, and the sending traffic S2 of path 2 is the second time period
  • the sending traffic S3 of path 3 is the cumulative sending traffic of exit node A on path 3 in the second time period
  • the receiving traffic R1 of path 1 is in the third time period
  • the cumulative received flow of egress node D on path 1, the received flow R2 of path 2 is the cumulative received flow of egress node D on path 2 in the third time period
  • the received flow R3 of path 3 is in the third time period
  • the to-be-sent traffic Z1 of path 1 is the cumulative sending traffic of the ingress node A on path 1 during the fourth time period, and the to-be-sent traffic Z2 of path 2 is expected to be in the fourth time period.
  • the cumulative sending traffic of ingress node A on path 2 in the segment, and the to-be-sent traffic Z3 of path 3 is the cumulative sending traffic of ingress node A on path 3 expected in the fourth time period.
  • the link utilization of the link C1-D and the link C2-D The rate is very balanced. It can be known from the embodiment shown in FIG. 4 that the solution provided by the embodiment of the present application can make the load of the links in the network more balanced.
  • FIG. 5 is a flowchart of another path traffic distribution method provided by an embodiment of the application.
  • the path traffic distribution method shown in FIG. 5 can be applied to an ingress node.
  • the method shown in FIG. 5 includes the following.
  • the ingress node sends a measurement message to the egress node on each of the at least two paths.
  • At least two paths are paths between the ingress node and the egress node, and the measurement message on each path is used to indicate the path information of each path.
  • the measurement message includes the sending traffic of the link and the bandwidth of the link.
  • the sending traffic of the link is the cumulative sending traffic of the link in the first time period
  • the bandwidth of the link is the link sending traffic in the first time period.
  • the bandwidth of the road also includes at least one of the initial sending flow of the path, the path identifier, or the first time stamp.
  • the first time stamp is the sending time of the measurement message
  • the initial sending flow of the path is the path in the second time period.
  • the initial sending traffic of the path is the cumulative sending traffic of the path corresponding to the first timestamp.
  • the measurement message includes the link utilization rate of the link, and the link utilization rate is the ratio of the transmission traffic of the link to the bandwidth of the link.
  • the measurement message also includes at least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the ingress node receives the response message sent by the egress node.
  • the response message is used to indicate the traffic adjustment information of each path.
  • the ingress node determines the to-be-sent flow of each path according to the flow adjustment information of each path.
  • the ingress node can cooperate with the intermediate node and the egress node in the network, so that the ingress node can grasp the load of the link in the network, and the ingress node can allocate and send traffic for each path. So as to ensure that the load of the links in the network is more balanced.
  • the response message includes the flow adjustment amount of each path, and the flow adjustment amount of each path is used to indicate the flow that needs to be adjusted for each path.
  • S203 shown in FIG. 5 may further include: the ingress node obtains the initial sending traffic of each path, and the ingress node determines the to-be-sent traffic of each path according to the traffic adjustment amount of each path and the initial sending traffic of each path.
  • the response message includes the distribution flow of each path, and the distribution flow of each path is used to indicate the transmission flow of each path link.
  • S203 shown in FIG. 5 may also include: the ingress node obtains the initial sending traffic of each path, and the ingress node determines the traffic adjustment amount of each path according to the initial sending traffic of each path and the assigned traffic of each path. The node determines the to-be-sent flow of each path according to the flow adjustment amount of each path and the initial sending flow of each path.
  • the response message includes the optimal utilization of each path and the fair bandwidth of each path.
  • the fair bandwidth of each path is used to indicate the bandwidth allocated to each path.
  • the optimal utilization of is used to indicate the ratio between the sending traffic of each path and the fair bandwidth of each path.
  • S203 shown in FIG. 5 may also include: the ingress node determines the allocated traffic of each path according to the optimal utilization rate of each path and the fair bandwidth of each path, the ingress node obtains the initial sending traffic of each path, and the ingress node obtains the initial sending traffic of each path.
  • the node determines the flow adjustment amount of each path according to the initial sending flow of each path and the distribution flow of each path, and the ingress node determines the to-be-sent of each path according to the flow adjustment amount of each path and the initial sending flow of each path. flow.
  • the response message includes the fair bandwidth of each path.
  • S203 shown in FIG. 5 may further include: the ingress node obtains the initial sending traffic of each path, and the ingress node determines the optimal utilization rate of each path according to the initial sending traffic of each path and the fair bandwidth of each path. The ingress node determines the distribution flow of each path according to the optimal utilization of each path and the fair bandwidth of each path. The ingress node determines the flow adjustment of each path according to the initial sending traffic of each path and the distribution flow of each path. The ingress node determines the to-be-sent flow of each path according to the flow adjustment amount of each path and the initial sending flow of each path.
  • the response message includes the received traffic of each path and the information of the link of each path.
  • the link is the link with the highest link utilization rate on the path, and the link utilization rate is The ratio of the link's sending traffic to the link's bandwidth.
  • S203 shown in FIG. 5 may also include: the ingress node determines the fair bandwidth of each path according to the received traffic of each path and the link information of each path, the ingress node obtains the initial sending traffic of each path, and the ingress node obtains the initial sending traffic of each path.
  • the node determines the optimal utilization of each path according to the initial sending traffic of each path and the fair bandwidth of each path, and the ingress node determines the distribution of each path according to the optimal utilization of each path and the fair bandwidth of each path Flow, the ingress node determines the flow adjustment amount of each path according to the initial sending flow of each path and the distribution flow of each path, and the ingress node determines each path according to the flow adjustment amount of each path and the initial sending flow of each path The traffic to be sent.
  • the response message further includes the path identifier, the first time stamp, the second time stamp, the third time stamp, the received traffic of the path, the link utilization rate of the link, and the transmission of the link.
  • At least one of the traffic or the bandwidth of the link is the second time stamp is the receiving time of the measurement message
  • the third time stamp is the sending time of the response message
  • the receiving traffic of the path is the cumulative reception of the path in the third time period Traffic
  • the received traffic of the path is the cumulative received traffic of the path corresponding to the second time stamp
  • the third time period is later than or equal to the second time period.
  • the ingress node determining the to-be-sent flow of the first path according to the flow adjustment amount of the first path and the initial sending flow of the first path may include: the ingress node calculates the flow adjustment amount of the first path and The sum of the initial sending traffic of the first path obtains the to-be-sent traffic of the first path.
  • the first path is any one of the at least two paths.
  • the ingress node determining the flow adjustment amount of the first path according to the initial sending flow of the first path and the allocated flow of the first path may include: the ingress node calculating the allocated flow of the first path and the first path The difference between the initial sending flows of the paths obtains the flow adjustment amount of the first path.
  • the ingress node determining the allocated traffic of the first path according to the optimal utilization rate of each path and the fair bandwidth of the first path may include: the ingress node calculating the optimal utilization rate of each path and The product of the fair bandwidth of the first path obtains the allocated traffic of the first path.
  • the ingress node determines the optimal utilization of each path according to the initial transmission traffic of each path and the fair bandwidth of each path, which may include: the ingress node calculates the initial transmission traffic of each path. Sum to get the total transmitted traffic, the ingress node calculates the sum of the fair bandwidth of each path to obtain the total fair bandwidth, and the ingress node calculates the quotient of the total transmitted traffic and the total fair bandwidth to obtain the optimal utilization of each path.
  • the ingress node determining the fair bandwidth of the first path according to the received traffic of the first path and the information of the link of the first path may include: the ingress node calculates the received traffic of the first path and the first path. The quotient of the sending traffic of the link of the path obtains the first ratio, and the ingress node calculates the product of the first ratio and the bandwidth of the first path to obtain the fair bandwidth of the first path.
  • the ingress node determining the fair bandwidth of the first path according to the received traffic of the first path and the link information of the first path may further include: the ingress node calculates the received traffic of the first path and the first path. The quotient of the link utilization rate of the link of one path obtains the fair bandwidth of the first path.
  • FIG. 6 is a flowchart of another path traffic distribution method provided by an embodiment of the present application.
  • the path traffic distribution method shown in FIG. 6 can be applied to an intermediate node.
  • the method shown in Figure 6 includes:
  • the intermediate node receives a measurement message on the first path of the at least two paths.
  • At least two paths are paths between the ingress node and the egress node, and the measurement message is used to indicate the information of the first link of the first path.
  • the measurement message includes the sending traffic of the link and the bandwidth of the link.
  • the sending traffic of the link is the cumulative sending traffic of the link in the first time period
  • the bandwidth of the link is the link sending traffic in the first time period.
  • the bandwidth of the road also includes at least one of the initial sending flow of the path, the path identifier, or the first time stamp.
  • the first time stamp is the sending time of the measurement message
  • the initial sending flow of the path is the path in the second time period.
  • the initial sending traffic of the path is the cumulative sending traffic of the path corresponding to the first timestamp.
  • the measurement message includes the link utilization rate of the link, and the link utilization rate is the ratio of the transmission traffic of the link to the bandwidth of the link.
  • the measurement message also includes at least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the intermediate node obtains information about the second link.
  • the second link is a link connected to the outgoing port of the intermediate node on the first path.
  • the intermediate node determines whether the link utilization rate of the first link is greater than or equal to the link utilization rate of the second link according to the information of the first link and the information of the second link. If yes, go to S304; otherwise, go to S305.
  • the intermediate node determines that the link utilization rate of the first link is greater than or equal to the link utilization rate of the second link according to the information of the first link and the information of the second link, the intermediate node sends a measurement to the egress node. Message, link utilization is used to indicate the traffic occupancy of the link.
  • the intermediate node determines that the link utilization rate of the first link is less than the link utilization rate of the second link according to the information of the first link and the information of the second link, the intermediate node converts the information of the second link Fill in the measurement message, and the intermediate node sends the measurement message to the egress node.
  • the intermediate node in the network can cooperate with the ingress node and the egress node so that the ingress node can grasp the load of the link in the network, and the ingress node can allocate and send traffic for each path. So as to ensure that the load of the links in the network is more balanced.
  • the information of the first link may include the transmission traffic of the first link and the bandwidth of the first link
  • the information of the second link includes the transmission traffic of the second link and the second link.
  • the bandwidth of the link may also include the link utilization rate of the first link, where the information about the second link includes the link utilization rate of the second link.
  • the path traffic distribution method provided in the embodiment of the present application may further include: the first intermediate node deletes the first measurement packet.
  • the first measurement packet may further include at least one of the path identifier of the first path, a time stamp, or the initial transmission traffic of the first path, and the time stamp is the transmission of the first measurement packet. time.
  • the second measurement message may also include at least one of the path identifier of the first path, a time stamp, or the initial transmission traffic of the first path.
  • FIG. 7 is a flowchart of another path flow distribution method provided by an embodiment of the application.
  • the path flow distribution method shown in FIG. 7 can be applied to an egress node.
  • the method shown in Figure 7 includes:
  • the egress node receives a measurement message sent by the ingress node on each of the at least two paths.
  • At least two paths are paths between the ingress node and the egress node, and the measurement message on each path is used to indicate the path information of each path.
  • the measurement message includes the sending traffic of the link and the bandwidth of the link.
  • the sending traffic of the link is the cumulative sending traffic of the link in the first time period
  • the bandwidth of the link is the link sending traffic in the first time period.
  • the bandwidth of the road also includes at least one of the initial sending flow of the path, the path identifier, or the first time stamp.
  • the first time stamp is the sending time of the measurement message
  • the initial sending flow of the path is the path in the second time period.
  • the initial sending traffic of the path is the cumulative sending traffic of the path corresponding to the first timestamp.
  • the measurement message includes the link utilization rate of the link, and the link utilization rate is the ratio of the transmission traffic of the link to the bandwidth of the link.
  • the measurement message also includes at least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the egress node generates a response message according to the path information of each path and the received traffic of each path.
  • the response message is used to indicate the traffic adjustment information of each path.
  • S403 The egress node sends a response message to the ingress node.
  • the response message includes at least one piece of quality information.
  • the response message may include the fair bandwidth of each path, and the fair bandwidth of each path is the quality information of each path.
  • the response message may include the optimal utilization rate of each path and the fair bandwidth of each path, and the optimal utilization rate of each path and the fair bandwidth of each path are the quality information of each path.
  • the response message may include the distribution flow of each path, and the distribution flow of each path is the quality information of each path.
  • the response message may include the flow adjustment amount of each path, and the flow adjustment amount of each path is the quality information of each path.
  • S401 and S403 refer to the description of S104 to S108 in the embodiment shown in FIG. 3.
  • the egress node in the network can cooperate with the ingress node and the intermediate node so that the ingress node can grasp the load status of the links in the network, and the ingress node can allocate and send traffic for each path. So as to ensure that the load of the links in the network is more balanced.
  • S402 in FIG. 7 may include: the egress node determines the fair bandwidth of each path according to the link information of each path and the received traffic of each path, and the egress node generates a response message , The response message includes the fair bandwidth of each path.
  • S402 in FIG. 7 may include: the egress node determines the fair bandwidth of each path according to the link information of each path and the received traffic of each path, and the egress node obtains each path.
  • the egress node determines the optimal utilization of each path according to the initial transmit flow of each path and the fair bandwidth of each path.
  • the egress node generates a response message, and the response message includes the optimal utilization of each path Rate and fair bandwidth of each path.
  • S402 in FIG. 7 may include: the egress node determines the fair bandwidth of each path according to the link information of each path and the received traffic of each path, and the egress node obtains each path.
  • the egress node determines the optimal utilization of each path according to the initial transmission traffic of each path and the fair bandwidth of each path, and the ingress node determines the optimal utilization of each path and the fair bandwidth of each path Determine the distribution flow of each path, the egress node generates a response message, and the response message includes the distribution flow of each path.
  • S402 in FIG. 7 may include: the egress node determines the fair bandwidth of each path according to the link information of each path and the received traffic of each path, and the egress node obtains each path.
  • the egress node determines the optimal utilization of each path according to the initial transmission traffic of each path and the fair bandwidth of each path, and the ingress node determines the optimal utilization of each path and the fair bandwidth of each path Determine the distribution flow of each path.
  • the ingress node determines the flow adjustment amount of each path according to the initial sending flow of each path and the distribution flow of each path.
  • the egress node generates a response message, which includes the flow of each path. Adjust the amount.
  • the response message also includes the path identifier, the first time stamp, the second time stamp, the third time stamp, the received traffic of the path, the link utilization rate of the link, and the transmission of the link. At least one of the traffic or the bandwidth of the link, the second time stamp is the receiving time of the measurement message, the third time stamp is the sending time of the response message, and the receiving traffic of the path is the cumulative reception of the path in the third time period Traffic, or the received traffic of the path is the cumulative received traffic of the path corresponding to the second time stamp, and the third time period is later than or equal to the second time period.
  • the egress node determining the fair bandwidth of the first path according to the link information of the first path and the received traffic of the first path may include: the egress node calculating the information of the link according to the first path And the received traffic of the first path to determine the fair bandwidth of the first path.
  • the first path is any one of the at least two paths.
  • the egress node determining the optimal utilization rate of each path according to the initial transmission traffic of each path and the fair bandwidth of each path may include: the egress node calculates the initial transmission traffic of each path. The egress node calculates the sum of the fair bandwidth of each path to obtain the total fair bandwidth, and the egress node calculates the quotient of the total transmitted traffic and the total fair bandwidth to obtain the optimal utilization rate of each path.
  • the egress node determining the allocated traffic of each path according to the optimal utilization rate of each path and the fair bandwidth of the first path may include: the egress node calculating the optimal utilization rate of each path and The product of the fair bandwidth of the first path obtains the allocated traffic of the first path.
  • the first path is any one of the at least two paths.
  • the egress node determining the flow adjustment amount of the first path according to the initial sending flow of the first path and the distribution flow of the first path may include: the egress node calculating the distribution flow of the first path and the first path The difference between the initial sending flows of the paths obtains the flow adjustment amount of the first path.
  • the first path is any one of the at least two paths.
  • FIG. 8 is a schematic diagram of an ingress node provided by an embodiment of the application.
  • the entry node shown in Figure 8 includes the following modules:
  • the sending module 11 is configured to send a measurement message to the egress node on each of the at least two paths.
  • At least two paths are paths between the ingress node and the egress node, and the measurement message on each path is used to indicate the path information of each path.
  • the receiving module 12 receives the response message sent by the egress node.
  • the response message is used to indicate the traffic adjustment information of each path.
  • the determining module 13 is configured to determine the to-be-sent traffic of each path according to the traffic adjustment information of each path.
  • the sending module 11, the receiving module 12, and the determining module 13 please refer to the detailed description of S101 and S109 in the method embodiment shown in FIG. 3 above.
  • the response message includes the flow adjustment amount of each path, and the flow adjustment amount of each path is used to indicate the flow that needs to be adjusted for each path.
  • the determining module 13 is specifically configured to obtain the initial sending traffic of each path, and determine the to-be-sent traffic of each path according to the traffic adjustment amount of each path and the initial sending traffic of each path.
  • the response message includes the distribution flow of each path, and the distribution flow of each path is used to indicate the transmission flow of each path link.
  • the determining module 13 is specifically used to obtain the initial sending flow of each path; determining the flow adjustment amount of each path according to the initial sending flow of each path and the allocated flow of each path; according to the flow adjustment amount of each path And the initial sending traffic of each path determine the to-be-sent traffic of each path.
  • the response message includes the optimal utilization of each path and the fair bandwidth of each path.
  • the fair bandwidth of each path is used to indicate the bandwidth allocated to each path.
  • the optimal utilization is used to indicate the ratio between the sending traffic of each path and the fair bandwidth of each path.
  • the determining module 13 is specifically configured to determine the distribution flow of each path according to the optimal utilization rate of each path and the fair bandwidth of each path; obtain the initial sending traffic of each path; and according to the initial sending traffic of each path Determine the flow adjustment amount of each path with the allocated flow of each path; determine the to-be-sent flow of each path according to the flow adjustment amount of each path and the initial sending flow of each path.
  • the response message includes the fair bandwidth of each path.
  • the determining module 13 is specifically used to obtain the initial sending traffic of each path; determining the optimal utilization rate of each path according to the initial sending traffic of each path and the fair bandwidth of each path; The utilization rate and the fair bandwidth of each path determine the distribution flow of each path; determine the flow adjustment amount of each path according to the initial sending flow of each path and the distribution flow of each path; according to the flow adjustment amount of each path and The initial sending traffic of each path determines the to-be-sent traffic of each path.
  • the response message includes the received traffic of each path and the information of the link of each path.
  • the link is the link with the highest link utilization rate on the path, and the link utilization rate is the link The ratio of the sending traffic of the road to the bandwidth of the link.
  • the determining module 13 is specifically configured to determine the fair bandwidth of each path according to the received traffic of each path and the information of the link of each path; obtain the initial sending traffic of each path; and according to the initial sending traffic of each path And the fair bandwidth of each path to determine the optimal utilization of each path; determine the distribution flow of each path according to the optimal utilization of each path and the fair bandwidth of each path; The distribution flow of each path determines the flow adjustment amount of each path; the flow adjustment amount of each path and the initial sending flow of each path determine the to-be-sent flow of each path.
  • the determining module 13 is specifically configured to calculate the sum of the flow adjustment amount of the first path and the initial sending flow of the first path to obtain the to-be-sent flow of the first path, and the first path is at least two Any path in each path of the path.
  • the determining module 13 is specifically configured to calculate the difference between the allocated flow of the first path and the initial sending flow of the first path to obtain the flow adjustment amount of the first path, and the first path is at least two paths. Any path in each path.
  • the determining module 13 is specifically configured to calculate the product of the optimal utilization rate of each path and the fair bandwidth of the first path to obtain the allocated traffic of the first path, and the first path is at least two paths. Any path in each path.
  • the determining module 13 is specifically used to calculate the sum of the initial transmission traffic of each path to obtain the total transmission traffic, calculate the sum of the fair bandwidth of each path to obtain the total fair bandwidth, and calculate the total transmission traffic and The quotient of the total fair bandwidth obtains the optimal utilization of each path.
  • the determining module 13 is specifically configured to calculate the quotient of the received traffic of the first path and the send traffic of the link of the first path to obtain the first ratio, and the first path is each of the at least two paths. For any one of the two paths, calculate the product of the first ratio and the bandwidth of the first path to obtain the fair bandwidth of the first path.
  • the determining module 13 is specifically configured to calculate the quotient of the received traffic of the first path and the link utilization rate of the link of the first path to obtain the fair bandwidth of the first path.
  • the measurement packet includes the sending traffic of the link and the bandwidth of the link, where the sending traffic of the link is the cumulative sending traffic of the link in the first time period, and the bandwidth of the link is The bandwidth of the link in the first time period.
  • the measurement message also includes at least one of the initial sending flow of the path, the path identifier, or the first time stamp.
  • the first time stamp is the sending time of the measurement message, and the initial sending flow of the path is the path in the second time period.
  • the initial sending traffic of the path is the cumulative sending traffic of the path corresponding to the first timestamp.
  • the measurement message includes the link utilization rate of the link, and the link utilization rate is the ratio of the transmission traffic of the link to the bandwidth of the link. Moreover, the measurement message also includes at least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the response message also includes the path identifier, the first time stamp, the second time stamp, the third time stamp, the receiving traffic of the path, the link utilization of the link, and the sending traffic of the link.
  • the second timestamp is the receiving time of the measurement message
  • the third timestamp is the sending time of the response message
  • the receiving traffic of the path is the cumulative receiving traffic of the path in the third time period
  • the received traffic of the path is the cumulative received traffic of the path corresponding to the second time stamp
  • the third time period is later than or equal to the second time period.
  • FIG. 9 is a schematic diagram of an intermediate node provided by an embodiment of the application.
  • the intermediate node shown in Figure 9 includes the following modules:
  • the receiving module 21 is configured to receive a measurement message on a first path of at least two paths, the at least two paths are paths between an ingress node and an egress node, and the measurement message is used to indicate the first link of the first path Road information.
  • the obtaining module 22 is configured to obtain information about the second link, and the second link is a link connected to the outgoing port of the intermediate node on the first path.
  • the determining module 23 is configured to call the sending module 24 when it is determined that the link utilization rate of the first link is greater than or equal to the link utilization rate of the second link according to the information of the first link and the information of the second link.
  • the egress node sends measurement packets, and the link utilization is used to indicate the traffic occupancy of the link.
  • the information of the second link is filled in the measurement message , Call the sending module 24 to send a measurement message to the egress node.
  • the sending module 24 is used to send measurement messages to the egress node.
  • the receiving module 21, the acquiring module 22, the determining module 23, and the sending module 24 please refer to the detailed description of S102 and S103 in the method embodiment shown in FIG. 3 above.
  • the information of the first link includes the sending traffic of the first link and the bandwidth of the first link
  • the information of the second link includes the sending traffic of the second link and the second link. Bandwidth.
  • the information about the first link includes the link utilization rate of the first link
  • the information about the second link includes the link utilization rate of the second link.
  • the determining module 23 is also used to delete the first measurement message.
  • the measurement packet includes the sending traffic of the link and the bandwidth of the link, where the sending traffic of the link is the cumulative sending traffic of the link in the first time period, and the bandwidth of the link is The bandwidth of the link in the first time period.
  • the measurement message also includes at least one of the initial sending flow of the path, the path identifier, or the first time stamp.
  • the first time stamp is the sending time of the measurement message, and the initial sending flow of the path is the path in the second time period.
  • the initial sending traffic of the path is the cumulative sending traffic of the path corresponding to the first timestamp.
  • the measurement message includes the link utilization rate of the link, and the link utilization rate is the ratio of the transmission traffic of the link to the bandwidth of the link. Moreover, the measurement message also includes at least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • FIG. 10 is a schematic diagram of an egress node provided by an embodiment of the application.
  • the exit node shown in Figure 10 includes the following modules:
  • the receiving module 31 is configured to receive the measurement message sent by the ingress node on each of the at least two paths.
  • at least two paths are paths between the ingress node and the egress node, and the measurement message on each path is used to indicate the path information of each path.
  • the generating module 32 is configured to generate a response message according to the path information of each path and the received traffic of each path. Among them, the response message is used to indicate the traffic adjustment information of each path.
  • the sending module 33 is used to send a response message to the ingress node.
  • the receiving module 31, the generating module 32, and the sending module 33 please refer to the detailed description of S104 to S108 in the method embodiment shown in FIG. 3 above.
  • the generating module 32 is specifically configured to determine the fair bandwidth of each path according to the link information of each path and the received traffic of each path; generate a response message, the response message including each path The fair bandwidth of each path.
  • the generating module 32 is specifically configured to determine the fair bandwidth of each path according to the link information of each path and the received traffic of each path; obtain the initial sending traffic of each path; The initial sending traffic of each path and the fair bandwidth of each path determine the optimal utilization of each path; a response message is generated, which includes the optimal utilization of each path and the fair bandwidth of each path.
  • the generating module 32 is specifically configured to determine the fair bandwidth of each path according to the link information of each path and the received traffic of each path; obtain the initial sending traffic of each path; The initial sending traffic of each path and the fair bandwidth of each path determine the optimal utilization rate of each path; determine the distribution flow of each path according to the optimal utilization rate of each path and the fair bandwidth of each path; generate a response Message, the response message includes the distribution flow of each path.
  • the generating module 32 is specifically configured to determine the fair bandwidth of each path according to the link information of each path and the received traffic of each path; obtain the initial sending traffic of each path; The initial sending traffic of each path and the fair bandwidth of each path determine the optimal utilization rate of each path; the optimal utilization rate of each path and the fair bandwidth of each path determine the distribution flow of each path; The initial sending traffic of each path and the distribution traffic of each path determine the traffic adjustment amount of each path; a response message is generated, and the response message includes the traffic adjustment amount of each path.
  • the generating module 32 is specifically configured to calculate the fair bandwidth of the first path according to the link information of the first path and the received traffic of the first path, and the first path is the ratio of at least two paths. Any path in each path.
  • the generating module 32 is specifically used to calculate the sum of the initial transmission traffic of each path to obtain the total transmission traffic, calculate the sum of the fair bandwidth of each path to obtain the total fair bandwidth, and calculate the total transmission traffic and The quotient of the total fair bandwidth obtains the optimal utilization of each path.
  • the generating module 32 is specifically configured to calculate the product of the optimal utilization rate of each path and the fair bandwidth of the first path to obtain the allocated traffic of the first path, and the first path is at least two paths. Any path in each path.
  • the generating module 32 is specifically configured to calculate the difference between the allocated flow of the first path and the initial sending flow of the first path to obtain the flow adjustment amount of the first path, and the first path is at least two paths. Any path in each path.
  • the measurement packet includes the sending traffic of the link and the bandwidth of the link, where the sending traffic of the link is the cumulative sending traffic of the link in the first time period, and the bandwidth of the link is The bandwidth of the link in the first time period.
  • the measurement message also includes at least one of the initial sending flow of the path, a path identifier, or a first time stamp.
  • the first time stamp is the sending time of the measurement message
  • the initial sending flow of the path is the path in the second time period.
  • the initial sending traffic of the path is the cumulative sending traffic of the path corresponding to the first timestamp.
  • the measurement message includes the link utilization rate of the link, and the link utilization rate is the ratio of the transmission traffic of the link to the bandwidth of the link. Moreover, the measurement message also includes at least one of the initial sending traffic of the path, the path identifier, or the first time stamp.
  • the response message also includes the path identifier, the first time stamp, the second time stamp, the third time stamp, the receiving traffic of the path, the link utilization of the link, and the sending traffic of the link.
  • the second timestamp is the receiving time of the measurement message
  • the third timestamp is the sending time of the response message
  • the receiving traffic of the path is the cumulative receiving traffic of the path in the third time period
  • the received traffic of the path is the cumulative received traffic of the path corresponding to the second time stamp
  • the third time period is later than or equal to the second time period.
  • FIG. 11 is a schematic diagram of another ingress node provided by an embodiment of this application.
  • the entry node shown in FIG. 11 includes a processor 41, a memory 42, a bus 43, and an input/output interface 44.
  • the input/output interface 44 of the terminal device can send a measurement message to the egress node on each of the at least two paths, and receive a response message sent by the egress node.
  • the bus 43 can transmit the response message received by the input/output interface 44 to the memory 42.
  • the processor 41 may obtain the response message in the memory 42, and determine the to-be-sent traffic of each path according to the flow adjustment information of each path in the response message.
  • the ingress node shown in FIG. 11 is equivalent to the ingress node mentioned in FIG. 2 to FIG. 10. For the ingress node in FIG. 11, refer to the detailed description of the ingress node in the embodiment corresponding to FIG. 2 to FIG. 10.
  • FIG. 12 is a schematic diagram of another intermediate node provided by an embodiment of the application.
  • the intermediate node shown in FIG. 12 includes a processor 51, a memory 52, a bus 53 and an input/output interface 54.
  • the input/output interface 54 of the intermediate node can receive the measurement message on the first path of the at least two paths, and obtain the information of the second link.
  • the bus 53 can transmit the measurement message received by the input/output interface 54 and the information of the second link to the memory 52.
  • the processor 51 may obtain the information of the first link and the information of the second link in the measurement message in the memory 52, and determine the information of the first link according to the information of the first link and the information of the second link.
  • the input/output interface 54 is invoked to send a measurement message to the egress node.
  • the intermediate node shown in FIG. 12 is equivalent to the intermediate node mentioned in FIG. 2 to FIG. 10.
  • the intermediate node in FIG. 12 refer to the detailed description of the intermediate node in the embodiment corresponding to FIG. 2 to FIG. 10.
  • FIG. 13 is a schematic diagram of another egress node provided by an embodiment of the application.
  • the exit node shown in FIG. 13 includes a processor 61, a memory 62, a bus 63, and an input/output interface 64.
  • the input/output interface 64 of the egress node can receive the measurement message sent by the ingress node on each of the at least two paths, and send a response message to the ingress node.
  • the bus 63 can transmit the measurement message received by the input/output interface 64 to the memory 62.
  • the processor 61 may obtain the path information of each path and the received traffic of each path in the memory 62, and generate a response message according to the path information of each path and the received traffic of each path.
  • the exit node shown in FIG. 13 is equivalent to the exit node mentioned in FIG. 2 to FIG. 10. For the exit node in FIG. 13, refer to the detailed description of the exit node in the embodiment corresponding to FIG. 2 to FIG. 10.
  • FIG. 14 is a schematic diagram of a network system provided by an embodiment of this application.
  • the network system shown in FIG. 14 includes an ingress node 100, an intermediate node 200, and an egress node 300.
  • the specific structure of the ingress node 100 shown in FIG. 14 may refer to the ingress node shown in FIG. 8 and the ingress node shown in FIG. 11, and the specific structure of the intermediate node 200 shown in FIG. 14 may refer to the middle node shown in FIG. Nodes and the intermediate nodes shown in FIG. 12, and the specific structure of the exit node 300 shown in FIG. 14 can refer to the exit node shown in FIG. 10 and the exit node shown in FIG.
  • the relevant software or modules in the software may be stored in a computer-readable medium or transmitted as one or more instructions or codes on the computer-readable medium.
  • the computer-readable medium includes a computer storage medium and a communication medium, where the communication medium includes any medium that facilitates the transfer of a computer program from one place to another.
  • the storage medium may be any available medium that can be accessed by a computer. Take this as an example but not limited to: computer readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or can be used to carry or store instructions or data in the form of structure The desired program code and any other medium that can be accessed by the computer. In addition.
  • any connection can suitably become a computer-readable medium.
  • the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave
  • coaxial cable , Fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, wireless and microwave are included in the fixing of the media.
  • Disk and disc include compact discs (CD), laser discs, optical discs, digital versatile discs (DVD), floppy discs and Blu-ray discs.
  • Discs usually copy data magnetically, while discs The laser is used to optically copy the data.
  • the above combination should also be included in the protection scope of the computer-readable medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Environmental & Geological Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Cardiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本申请实施例公开了一种路径的流量分配方法、网络设备及网络系统，该路径的流量分配方法可以应用于网络中的入口节点、中间节点和出口节点中，入口节点、中间节点和出口节点可以为路由器等具有路由转发功能的网络设备。本申请实施例通过入口节点、中间节点和出口节点之间的相互配合，可以使入口节点掌握网络中链路的负载情况，入口节点便可以为每个路径分配发送流量，从而保证网络中链路的负载更加均衡。

Description

一种路径的流量分配方法、网络设备及网络系统 技术领域
本申请涉及通信技术领域，更具体的说，涉及路径的流量分配方法、网络设备及网络系统。
背景技术
在网络中，传统的路径负载均衡方法主要关注于入口节点和出口节点之间的多个路径的发送流量是否均衡，从而保证网络中路径的负载均衡。虽然采用传统的路径负载均衡方法可以保证入口节点与出口节点之间的路径的负载均衡，但这种方法可能会导致网络中的某些链路处于超载状态，某些链路处于轻载状态，从而无法保证网络中链路的负载均衡。请参见图1所示，图1为本申请实施例提供的一种网络示意图，下面通过图1所示的示例来说明传统的路径负载均衡方法存在的问题。
在图1所示的示例中，假设入口节点A与出口节点D之间包括三条最优路径，这三条最优路径分别为路径1、路径2和路径3，其中，路径1为入口节点A->中间节点B1->中间节点C1->出口节点D，路径2为入口节点A->中间节点B2->中间节点C1->出口节点D，路径3为入口节点A->中间节点B3->中间节点C2->出口节点D。图1中每两个相邻的节点之间均通过链路连接，其中，假设图1中链路C1-D和链路C2-D的带宽均为2GB。
在图1所示的示例中，传统的路径负载均衡方法会采用轮询或哈希的方式在三条路径上平均分配流量，假设传统的路径负载均衡方法为三条路径分配的发送流量均为1GB。由于路径1与路径2会在链路C1-D处重叠，所以链路C1-D的发送流量为2GB。由于路径3会经过链路C2-D，且没有其他路径经过链路C2-D，所以链路C2-D的发送流量为1GB。此时，链路C1-D的链路利用率＝链路C1-D的发送流量÷链路C1-D的带宽＝2GB÷2GB＝100％，链路C2-D的链路利用率＝链路C2-D的发送流量÷链路C2-D的带宽＝1GB÷2GB＝50％。
在图1所示的示例中，链路C1-D的链路利用率为100％，说明链路C1-D为超载状态，所以链路C1-D可能会出现拥堵或丢包的情况；然而，链路C2-D的链路利用率为50％，说明链路C2-D为轻载状态，所以链路C2-D没有得到充分的利用。
因此，通过上述内容可以得知，传统的路径负载均衡方法可能会使得网络中的某些链路处于超载状态，使得网络中的某些链路处于轻载状态，所以无法保证网络中链路的负载均衡。
发明内容
本申请实施例提供一种路径的流量分配方法及网络设备，以使网络中链路的负载更加均衡。
第一方面，本申请实施例提供了一种路径的流量分配方法，该方法包括：入口节点在至少两个路径中的每个路径上向出口节点发送测量报文，至少两个路径为入口节 点与出口节点之间的路径，每个路径上的测量报文用于指示每个路径的路径信息。入口节点接收出口节点发送的应答报文，应答报文用于指示每个路径的流量调整信息。入口节点根据每个路径的流量调整信息确定每个路径的待发送流量。
在第一方面中，在网络中入口节点可以与中间节点和出口节点相互配合，以使入口节点掌握网络中链路的负载情况，入口节点便可以为每个路径分配发送流量，从而保证网络中链路的负载更加均衡。
在一种可能的实现方式中，应答报文包括每个路径的流量调整量，每个路径的流量调整量用于指示每个路径需要调整的流量。入口节点根据每个路径的流量调整信息确定每个路径的待发送流量包括：入口节点获取每个路径的初始发送流量，入口节点根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在一种可能的实现方式中，应答报文包括每个路径的分配流量，每个路径的分配流量用于指示每个路径链路的发送流量。入口节点根据每个路径的流量调整信息确定每个路径的待发送流量包括：入口节点获取每个路径的初始发送流量，入口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，入口节点根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在一种可能的实现方式中，应答报文包括每个路径的最优利用率和每个路径的公平带宽，每个路径的公平带宽用于指示分配给每个路径的带宽，每个路径的最优利用率用于指示每个路径的发送流量与每个路径的公平带宽之间的比例。入口节点根据每个路径的流量调整信息确定每个路径的待发送流量包括：入口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，入口节点获取每个路径的初始发送流量，入口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，入口节点根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在一种可能的实现方式中，应答报文包括每个路径的公平带宽，入口节点根据每个路径的流量调整信息确定每个路径的待发送流量包括：入口节点获取每个路径的初始发送流量，入口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，入口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，入口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，入口节点根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在一种可能的实现方式中，应答报文包括每个路径的接收流量和每个路径的链路的信息，链路为路径上的链路利用率最大的链路，链路利用率为链路的发送流量与链路的带宽的比值，入口节点根据每个路径的流量调整信息确定每个路径的待发送流量包括：入口节点根据每个路径的接收流量和每个路径的链路的信息确定每个路径的公平带宽，入口节点获取每个路径的初始发送流量，入口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，入口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，入口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，入口节点根据每个 路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在一种可能的实现方式中，每个路径的链路的信息包括每个路径的链路的发送流量和每个路径的链路的带宽，或者，每个路径的链路的信息包括每个路径的链路的链路利用率。
在一种可能的实现方式中，确定第一路径的待发送流量包括：入口节点计算第一路径的流量调整量与第一路径的初始发送流量之和得到第一路径的待发送流量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，确定第一路径的流量调整量包括：入口节点计算第一路径的分配流量与第一路径的初始发送流量之差得到第一路径的流量调整量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，确定第一路径的分配流量包括：入口节点计算每个路径的最优利用率与第一路径的公平带宽之积得到第一路径的分配流量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，确定每个路径的最优利用率包括：入口节点计算每个路径的初始发送流量之和得到总发送流量，入口节点计算每个路径的公平带宽之和得到总公平带宽，入口节点计算总发送流量与总公平带宽之商得到每个路径的最优利用率。
在一种可能的实现方式中，确定第一路径的公平带宽包括：入口节点计算第一路径的接收流量与第一路径的链路的发送流量之商得到第一比值，第一路径为至少两个路径的每个路径中的任意一个路径，入口节点计算第一比值与第一路径的带宽之积得到第一路径的公平带宽。
在一种可能的实现方式中，确定第一路径的公平带宽包括：入口节点计算第一路径的接收流量与第一路径的链路的链路利用率之商得到第一路径的公平带宽。
在一种可能的实现方式中，测量报文包括链路的发送流量和链路的带宽，链路的发送流量为在第一时间段内链路的累计发送流量，链路的带宽为在第一时间段内链路的带宽；或者，测量报文包括链路的链路利用率，链路利用率为链路的发送流量与链路的带宽的比值；或者，测量报文包括链路的发送流量和链路的带宽，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，第一时间戳为测量报文的发送时间，路径的初始发送流量为在第二时间段内路径的累计发送流量，或者，路径的初始发送流量为第一时间戳对应的路径的累计发送流量；或者，测量报文包括链路的链路利用率，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个。
在一种可能的实现方式中，应答报文还包括路径标识、第一时间戳、第二时间戳、第三时间戳、路径的接收流量、链路的链路利用率、链路的发送流量或链路的带宽中的至少一个，第二时间戳为测量报文的接收时间，第三时间戳为应答报文的发送时间，路径的接收流量为在第三时间段内路径的累计接收流量，或者，路径的接收流量为第二时间戳对应的路径的累计接收流量，第三时间段晚于或等于第二时间段。
第二方面，本申请实施例提供了一种路径的流量分配方法，该方法包括：中间节点在至少两个路径中的第一路径上接收测量报文，至少两个路径为入口节点与出口节 点之间的路径，测量报文用于指示第一路径的第一链路的信息，中间节点获取第二链路的信息，第二链路为在第一路径上与中间节点的出端口连接的链路，在中间节点根据第一链路的信息和第二链路的信息确定第一链路的链路利用率大于或等于第二链路的链路利用率时，中间节点向出口节点发送测量报文，链路利用率用于指示链路的流量占用情况，在中间节点根据第一链路的信息和第二链路的信息确定第一链路的链路利用率小于第二链路的链路利用率时，中间节点将第二链路的信息填入测量报文中，中间节点向出口节点发送测量报文。
在第二方面中，在网络中中间节点可以与入口节点和出口节点相互配合，以使入口节点掌握网络中链路的负载情况，入口节点便可以为每个路径分配发送流量，从而保证网络中链路的负载更加均衡。
在一种可能的实现方式中，第一链路的信息包括第一链路的发送流量和第一链路的带宽，第二链路的信息包括第二链路的发送流量和第二链路的带宽，或者，第一链路的信息包括第一链路的链路利用率，第二链路的信息包括第二链路的链路利用率。
在一种可能的实现方式中，第一中间节点向出口节点发送第二测量报文之后，方法还包括：第一中间节点删除第一测量报文。
在一种可能的实现方式中，第一测量报文还包括第一路径的路径标识、时间戳或第一路径的初始发送流量中的至少一个，时间戳为第一测量报文的发送时间，第二测量报文还包括第一路径的路径标识、时间戳或第一路径的初始发送流量中的至少一个。
在一种可能的实现方式中，测量报文包括链路的发送流量和链路的带宽，链路的发送流量为在第一时间段内链路的累计发送流量，链路的带宽为在第一时间段内链路的带宽；或者，测量报文包括链路的链路利用率，链路利用率为链路的发送流量与链路的带宽的比值；或者，测量报文包括链路的发送流量和链路的带宽，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，第一时间戳为测量报文的发送时间，路径的初始发送流量为在第二时间段内路径的累计发送流量，或者，路径的初始发送流量为第一时间戳对应的路径的累计发送流量；或者，测量报文包括链路的链路利用率，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个。
第三方面，本申请实施例提供了一种路径的流量分配方法，该方法包括：出口节点在至少两个路径中的每个路径上接收入口节点发送的测量报文，至少两个路径为入口节点与出口节点之间的路径，每个路径上的测量报文用于指示每个路径的路径信息，出口节点根据每个路径的路径信息和每个路径的接收流量生成应答报文，应答报文用于指示每个路径的流量调整信息，出口节点向入口节点发送应答报文。
在第三方面中，在网络中出口节点可以与入口节点和中间节点相互配合，以使入口节点掌握网络中链路的负载情况，入口节点便可以为每个路径分配发送流量，从而保证网络中链路的负载更加均衡。
在一种可能的实现方式中，测量报文包括链路的发送流量和链路的带宽，链路的发送流量为在第一时间段内链路的累计发送流量，链路的带宽为在第一时间段内链路的带宽；或者，测量报文包括链路的链路利用率，链路利用率为链路的发送流量与链路的带宽的比值；或者，测量报文包括链路的发送流量和链路的带宽，测量报文还包 括路径的初始发送流量、路径标识或第一时间戳中的至少一个，第一时间戳为测量报文的发送时间，路径的初始发送流量为在第二时间段内路径的累计发送流量，或者，路径的初始发送流量为第一时间戳对应的路径的累计发送流量；或者，测量报文包括链路的链路利用率，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个。
在一种可能的实现方式中，应答报文包括每个路径的链路的信息和每个路径的接收流量。
在一种可能的实现方式中，出口节点根据每个路径的路径信息和每个路径的接收流量生成应答报文包括：出口节点根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽，出口节点生成应答报文，应答报文包括每个路径的公平带宽。
在一种可能的实现方式中，出口节点根据每个路径的路径信息和每个路径的接收流量生成应答报文包括：出口节点根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽，出口节点获取每个路径的初始发送流量，出口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，出口节点生成应答报文，应答报文包括每个路径的最优利用率和每个路径的公平带宽。
在一种可能的实现方式中，出口节点根据每个路径的路径信息和每个路径的接收流量生成应答报文包括：出口节点根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽，出口节点获取每个路径的初始发送流量，出口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，出口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，出口节点生成应答报文，应答报文包括每个路径的分配流量。
在一种可能的实现方式中，出口节点根据每个路径的路径信息和每个路径的接收流量生成应答报文包括：出口节点根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽，出口节点获取每个路径的初始发送流量，出口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，出口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，出口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，出口节点生成应答报文，应答报文包括每个路径的流量调整量。
在一种可能的实现方式中，每个路径的路径信息包括每个路径的链路的发送流量和每个路径的链路的带宽，或者，每个路径的路径信息包括每个路径的链路的链路利用率。
在一种可能的实现方式中，确定第一路径的公平带宽包括：出口节点计算根据第一路径的链路的信息和第一路径的接收流量确定第一路径的公平带宽，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，确定每个路径的最优利用率包括：出口节点计算每个路径的初始发送流量之和得到总发送流量，出口节点计算每个路径的公平带宽之和得到总公平带宽，出口节点计算总发送流量与总公平带宽之商得到每个路径的最优利用率。
在一种可能的实现方式中，确定第一路径的分配流量包括：出口节点计算每个路径的最优利用率与第一路径的公平带宽之积得到第一路径的分配流量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，确定第一路径的流量调整量包括：出口节点计算第一路径的分配流量与第一路径的初始发送流量之差得到第一路径的流量调整量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，应答报文还包括路径标识、第一时间戳、第二时间戳、第三时间戳、路径的接收流量、链路的链路利用率、链路的发送流量或链路的带宽中的至少一个，第二时间戳为测量报文的接收时间，第三时间戳为应答报文的发送时间，路径的接收流量为在第三时间段内路径的累计接收流量，或者，路径的接收流量为第二时间戳对应的路径的累计接收流量，第三时间段晚于或等于第二时间段。
第四方面，本申请实施例提供了一种网络设备，该网络设备具有实现上述第一方面、第一方面的任一种可能实现方式、第二方面、第二方面的任一种可能实现方式、第三方面或第三方面的任一种可能实现方式的方法中网络设备行为的功能。所述功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多于一个与上述功能相对应的模块。可选的，该网络设备可以是路由器。
第五方面，本申请实施例提供了一种网络设备，网络设备包括处理器和存储器，其中，处理器用于读取存储在存储器中的软件代码并执行上述第一方面或第一方面的任一种可能实现方式中的方法，或者，使得计算机或处理器执行上述第二方面或第二方面的任一种可能实现方式中的方法，或者，使得计算机或处理器执行上述第三方面或第三方面的任一种可能实现方式中的方法。
第六方面，本申请实施例提供了一种计算机可读存储介质，该计算机可读存储介质中存储有指令，当其在计算机上运行时，使得计算机执行上述第一方面或第一方面的任一种可能实现方式中的方法，或者，使得计算机或处理器执行上述第二方面或第二方面的任一种可能实现方式中的方法，或者，使得计算机或处理器执行上述第三方面或第三方面的任一种可能实现方式中的方法。
第七方面，提供了一种包含指令的计算机程序产品，当其在计算机或处理器上运行时，使得计算机或处理器执行上述第一方面或第一方面的任一种可能实现方式中的方法，或者，使得计算机或处理器执行上述第二方面或第二方面的任一种可能实现方式中的方法，或者，使得计算机或处理器执行上述第三方面或第三方面的任一种可能实现方式中的方法。
第八方面，本申请实施例提供了一种网络系统，网络系统包括入口节点、中间节点和出口节点，入口节点用于执行如上述第一方面或第一方面的任一种可能实现方式中的方法，中间节点用于执行如上述第二方面或第二方面的任一种可能实现方式中的方法，出口节点用于执行如上述第三方面或第三方面的任一种可能实现方式中的方法。
本申请实施例通过入口节点、中间节点和出口节点之间的相互配合，可以使入口节点掌握网络中链路的负载情况，入口节点便可以为每个路径分配发送流量，从而保证网络中链路的负载更加均衡。
附图说明
图1为本申请实施例提供的一种网络示意图；
图2为本申请实施例提供的另一种网络示意图；
图3为本申请实施例提供的一种路径的流量分配方法的流程图；
图4为本申请实施例提供的又一种网络示意图；
图5为本申请实施例提供的又一种路径的流量分配方法的流程图；
图6为本申请实施例提供的又一种路径的流量分配方法的流程图；
图7为本申请实施例提供的又一种路径的流量分配方法的流程图；
图8为本申请实施例提供的一种入口节点的示意图；
图9为本申请实施例提供的一种中间节点的示意图；
图10为本申请实施例提供的一种出口节点的示意图；
图11为本申请实施例提供的又一种入口节点的示意图；
图12为本申请实施例提供的又一种中间节点的示意图；
图13为本申请实施例提供的又一种出口节点的示意图；
图14为本申请实施例提供的一种网络系统的示意图。
具体实施方式
本申请实施例提供的路径的流量分配方法可以应用于网络中的入口节点、中间节点和出口节点中，入口节点、中间节点和出口节点可以为路由器等具有路由转发功能的网络设备。本申请实施例通过入口节点、中间节点和出口节点之间的相互配合，可以使入口节点掌握网络中链路的负载情况，入口节点便可以为每个路径分配发送流量，从而保证网络中链路的负载更加均衡。下面通过一个具体的应用场景来介绍本申请的实现方式。
请参见图2所示，图2为本申请实施例提供的另一种网络示意图。图2所示的网络中包括入口节点A、中间节点B1、中间节点B2和出口节点C，在入口节点A和出口节点C之间具有两条路径，这两条路径分别是路径1和路径2。示例的，路径1为节点A->节点B1->节点C，路径2为节点A->节点B2->节点C。路径1经过链路X1和链路X2，链路X1为节点A的出端口a1与节点B1之间的链路，链路X2为节点B1的出端口b1与节点C之间的链路。路径2经过链路Y1和链路Y2，链路Y1为节点A的出端口a2与节点B2之间的链路，链路Y2为节点B2的出端口b2与节点C之间的链路。
在图2所示的实施例中，假设链路X1的带宽B11＝链路X2的带宽B12＝1000MB，链路X1的发送流量U11＝600MB，链路X2的发送流量U12＝800MB，入口节点A统计路径1的初始发送流量S1＝300MB，出口节点C统计路径1的接收流量R1＝300MB。
在图2所示的实施例中，假设链路Y1的带宽B21＝链路Y2的带宽B22＝2000MB，链路Y1的发送流量U21＝1400MB，链路Y2的发送流量U22＝1500MB，入口节点A统计路径2的初始发送流量S2＝900MB，出口节点C统计路径2的接收流量R2＝900MB。
示例的，链路X1的发送流量U11是在第一时间段内入口节点A的出端口a1的累计发送流量，链路X2的发送流量U12是在第一时间段内入口节点B1的出端口b1的累计发送流量，链路Y1的发送流量U21是在第一时间段内入口节点A的出端口a2的累计发送流量，链路Y2的发送流量U22是在第一时间段内入口节点B2的出端口b2的累 计发送流量。其中，第一时间段为预先设定好的时间段。例如，预先可以将第一时间段设定为10μs、20μs或30μs等。当然，本领域技术人员可以依据实际情况来设定第一时间段，第一时间段并不局限于本申请实施例提供的时间长度。
示例的，路径1的初始发送流量S1是在第二时间段内入口节点A在路径1上的累计发送流量，路径2的初始发送流量S2是在第二时间段内入口节点A在路径2上的累计发送流量。路径1的接收流量R1是在第三时间段内出口节点C在路径1上的累计接收流量，路径2的接收流量R2是在第三时间段内出口节点C在路径2上的累计接收流量。
其中，第一时间段、第二时间段和第三时间段均为预先设定好的时间段。例如，可以将第一时间段设定为10μs、20μs或30μs等。又如，可以将第二时间段设定为10ms、20ms或30ms等。再如，可以将第三时间段设定为10ms、20ms或30ms等。
其中，第一时间段为第二时间段内的一段时间，而且，第三时间段晚于第二时间段。例如，假设第一时间段为0-10μs，第二时间段为0-3ms，第三时间段为3ms-6ms。
当然，本领域技术人员可以依据实际情况来设定第一时间段、第二时间段和第三时间段，第一时间段、第二时间段和第三时间段并不局限于本申请实施例提供的时间长度。
请参见图2和图3所示，图3为本申请实施例提供的一种路径的流量分配方法的流程图，图3所示的路径的流量分配方法可以应用于图2所示的网络中，本申请实施例提供的路径的流量分配方法包括：
S101、入口节点A的出端口a1在路径1上向出口节点C发送测量报文G1，入口节点A的出端口a2在路径2上向出口节点C发送测量报文G2。
示例的，测量报文G1包括链路X1的发送流量U11(600MB)、链路X1的带宽B11(1000MB)和路径1的初始发送流量S1(300MB)。测量报文G2包括链路Y1的发送流量U21(1400MB)、链路Y1的带宽B21(2000MB)和路径2的初始发送流量S2(900MB)。
其中，本申请实施例的入口节点A可以将第二时间段内(0-3ms内)路径1的初始发送流量S1(300MB)放入测量报文G1中，路径1的初始发送流量S1(300MB)为路径1在3ms的累计发送流量与在0ms的累计发送流量之差。
当然，测量报文G1还可以包括路径1的路径标识和时间戳t1，时间戳t1为测量报文G1的发送时间，第二时间段为0-3ms，那么时间戳t1为3ms。如果测量报文G1中包含时间戳t1，那么路径1的初始发送流量S1(300MB)为路径1在3ms的累计发送流量。由于入口节点A在第0ms时且在路径1上发送了上一个测量报文G3，出口节点C便可以提取测量报文G3中第0ms时路径1的初始发送流量S3(0MB)和测量报文G1中第3ms时路径1的初始发送流量S1(300MB)，然后，出口节点C计算路径1在3ms的累计发送流量S1(300MB)与在0ms的累计发送流量S3(0MB)之差，得到第二时间段内(0-3ms内)路径1的初始发送流量(300MB)。
同理，测量报文G2也可以包括路径2的路径标识和时间戳t2，时间戳t2为测量报文G2的发送时间，第二时间段为0-3ms，那么时间戳t2为3ms。
在S101中，入口节点A在每个路径上向出口节点C发送测量报文的目的在于：将每个路径上的链路利用率最大的链路的信息放入测量报文中，以便于出口节点C可以 掌握每个路径上瓶颈链路的信息，并基于每个路径上瓶颈链路的信息重新为每个路径分配更加链路的发送流量。其中，瓶颈链路为一个路径上链路利用率最大的链路。
S102、中间节点B1在路径1上接收入口节点A的出端口a1发送的测量报文G1，计算链路X1的链路利用率H11(60％)和链路X2的链路利用率H12(80％)，确定链路X2的链路利用率H12(80％)大于链路X1的链路利用率H11(60％)，将链路X2的发送流量U12(800MB)和链路X2的带宽B12(1000MB)填入至测量报文G1中，中间节点B1的出端口b1在路径1上向出口节点C发送测量报文G1。
示例的，链路X1的链路利用率H11＝链路X1的发送流量U11(600MB)÷链路X1的带宽B11(1000MB)＝60％，链路X2的链路利用率H12＝链路X2的发送流量U12(800MB)÷链路X2的带宽B12(1000MB)＝80％。
其中，链路的链路利用率为链路的发送流量与链路的带宽的比值，链路的链路利用率用于指示链路的流量占用情况。链路的链路利用率越高，说明该链路的流量占用越多；链路的链路利用率越低，说明该链路的流量占用越少。路径1上只有链路X1和链路X2，链路X2的链路利用率H12高于链路X1的链路利用率H11，说明链路X2为路径1中链路利用率最高的链路，链路X2为路径1中的瓶颈链路。
S103、中间节点B2在路径2上接收入口节点A的出端口a2发送的测量报文G2，计算链路Y1的链路利用率H21(70％)和链路Y2的链路利用率H22(75％)，确定链路Y2的链路利用率H22(75％)大于链路Y1的链路利用率H21(70％)，将链路Y2的发送流量U22(1500MB)和链路Y2的带宽B22(2000MB)填入至测量报文G2中，中间节点B1的出端口b2在路径2上向出口节点C发送测量报文G2。
示例的，链路Y1的链路利用率H21＝链路Y1的发送流量U21(1400MB)÷链路Y1的带宽B21(2000MB)＝70％，链路Y2的链路利用率H22＝链路Y2的发送流量U22(1500MB)÷链路Y2的带宽B22(2000MB)＝75％。
示例的，路径2上只有链路Y1和链路Y2，链路Y2的链路利用率H22高于链路Y1的链路利用率H21，说明链路Y2为路径2中链路利用率最高的链路，链路Y2为路径2中的瓶颈链路。
在S102和S103中，由于入口节点A在路径1和路径2上同时向出口节点C发送测量报文G1和测量报文G2，如果链路X1的延时和链路Y1的延时相同，那么S102和S103是同时发生的，S102和S103不存在先后顺序。
S104、出口节点C根据测量报文G1和测量报文G2中的链路的信息，分别计算路径1的公平带宽D1和路径2的公平带宽D2。
示例的，路径1的公平带宽D1＝(路径1的接收流量R1÷路径1的链路X2的发送流量U12)×路径1的链路X2的链路带宽B12＝(300MB÷800MB)×1000MB＝375MB，路径2的公平带宽D2＝(路径2的接收流量R2÷路径2的链路Y2的发送流量U22)×路径2的链路Y2的链路带宽B22＝(900MB÷1500MB)×2000MB＝1200MB。
示例的，路径1的链路X2的发送流量U12为800MB，路径1的链路X2的链路带宽B12为1000MB，路径1的接收流量R1为300MB，说明路径1占用链路X2的流量为300MB，其他路径占用链路X2的流量为500MB。为了将链路X2的带宽链路的分配给路径1，需要计算路径1的接收流量R1与路径1的链路X2的发送流量U12的比值，该 比值用于指示路径1的接收流量占据了链路X2的发送流量的百分比，该比值＝300MB÷800MB＝37.5％。在出口节点C得知路径1的接收流量占据了链路X2的发送流量的百分比为37.5％以后，出口节点C计算该比值与链路X2的链路带宽B12之积可以得到路径1的公平带宽D1，路径1的公平带宽D1用于指示链路X2为路径1分配的最大带宽，即链路X2为路径1分配的最大带宽为375MB，链路X2为其他路径分配的最大带宽的总和为625MB。
同理，路径2的公平带宽D2用于指示链路Y2为路径2分配的最大带宽，即链路Y2为路径2分配的最大带宽为1200MB，链路X2为其他路径分配的最大带宽的总和为800MB。
S105、出口节点C计算路径的最优利用率H。
示例的，路径的最优利用率H＝所有路径的发送流量÷所有路径的公平带宽＝(路径1的初始发送流量S1+路径2的初始发送流量S2)÷(路径1的公平带宽D1+路径2的公平带宽D2)＝(300MB+900MB)÷(375MB+1200MB)＝76％。
其中，路径的最优利用率H为所有路径的发送流量与所有路径的公平带宽之间的比值，路径的最优利用率H用于指示路径的发送流量与路径的公平带宽之间的比例。
S106、出口节点C分别计算路径1的分配流量K1和路径2的分配流量K2。
示例的，路径1的分配流量K1＝路径的最优利用率H×路径1的公平带宽D1＝76％×375MB＝285MB。路径2的分配流量K2＝路径的最优利用率H×路径2的公平带宽D2＝76％×1200MB＝912MB。
其中，路径1的分配流量K1用于指示路径1链路的发送流量，路径2的分配流量K2用于指示路径2链路的发送流量。
S107、出口节点C分别计算路径1的流量调整量L1和路径2的流量调整量L2。
示例的，路径1的流量调整量L1＝路径1的分配流量K1－路径1的初始发送流量S1＝285MB-300MB＝-15MB。路径2的流量调整量L2＝路径2的分配流量K2－路径2的初始发送流量S2＝912MB-900MB＝12MB。
示例的，路径1的流量调整量L1用于指示路径1需要调整的流量，路径2的流量调整量L2用于指示路径2需要调整的流量。
S108、出口节点C向入口节点A发送应答报文Y。
示例的，应答报文Y包括路径1的流量调整量L1和路径2的流量调整量L2。
另外，应答报文还可以包括路径1的路径标识、路径2的路径标识、时间戳t1、时间戳t2、时间戳t3、时间戳t4、时间戳t5、路径1的接收流量R1、路径2的接收流量R2、链路X2的链路利用率H12(80％)、链路Y2的链路利用率H22(75％)、链路X2的发送流量U12(800MB)、链路X2的带宽B12(1000MB)、链路Y2的发送流量U22(1500MB)或链路Y2的带宽B22(2000MB)中的至少一个，时间戳t3为测量报文G1的接收时间，时间戳t4为测量报文G2的接收时间，时间戳t5为应答报文Y的发送时间，路径1的接收流量R1为在第三时间段内(3-6ms)路径1的累计接收流量，路径2的接收流量R2为在第三时间段内(3-6ms)路径2的累计接收流量。
当然，路径1的接收流量R1也可以为时间戳t3对应的路径1的累计接收流量。如果测量报文G1中包含时间戳t3，那么路径1的接收流量R1为路径1在时间戳t3 时的累计发送流量。入口节点可以根据接收到的相邻的两个应答报文内的第3ms的路径1的接收流量和第6ms的路径1的接收流量，计算在第三时间段内(3-6ms)路径1的累计接收流量。
S109、入口节点A接收出口节点C发送的应答报文Y，并根据应答报文Y确定路径1的待发送流量Z1和路径2的待发送流量Z2。
示例的，路径1的待发送流量Z1＝路径1的流量调整量L1+路径1的初始发送流量S1＝-15MB+300MB＝285MB，路径2的待发送流量Z2＝路径2的流量调整量L2+路径2的初始发送流量S2＝12MB+900MB＝912MB。
在S109中，由于路径1的流量调整量L1＝-15MB，说明路径1实际发送的流量有点多，可以减少15MB的流量。由于路径2的流量调整量L2＝12MB，说明路径2实际发送的流量有点少，可以增加12MB的流量。
示例的，路径1的待发送流量Z1是预计在第四时间段段内入口节点A在路径1上的累计发送流量，路径2的待发送流量Z2是预计在第四时间段段内入口节点A在路径2上的累计发送流量。
其中，第四时间段晚于第三时间段。例如，假设第一时间段为0-10μs，第二时间段为0-3ms，第三时间段为3ms-6ms，第四时间段为6ms-9ms。
在图2和图3所示的实施例中，通过入口节点A、中间节点B1、中间节点B2和出口节点C之间的相互配合，可以使入口节点A掌握网络中瓶颈链路的负载情况，入口节点A便可以为路径1和路径2分配待发送流量，从而保证网络中链路的负载更加均衡。
在图2和图3所示的实施例中，在S104至S109中，出口节点C计算出路径1的公平带宽D1、路径2的公平带宽D2、路径的最优利用率H、路径1的分配流量K1、路径2的分配流量K2、路径1的流量调整量L1和路径2的流量调整量L2。然后，出口节点C将路径1的流量调整量L1和路径2的流量调整量L2放入应答报文Y中，并将应答报文Y发送至入口节点A中。
S104至S109提供的是本申请实施例中的一种实现方式，本申请实施例还可以采用其他的实现方式，下面简单的介绍几种具体的方式。
第一种方式，在出口节点C接收到中间节点B1和中间节点B2发送的测量报文G1和测量报文G2以后，出口节点C将路径1的接收流量R1、路径1的链路X2的发送流量U12、路径1的链路X2的链路带宽B12、路径2的接收流量R2、路径2的链路Y2的发送流量U22和路径2的链路Y2的链路带宽B22放入应答报文Y中，并将应答报文Y发送至入口节点A中。在入口节点A接收到应答报文Y以后，入口节点A基于应答报文Y中的信息计算路径1的待发送流量Z1和路径2的待发送流量Z2。
第二种方式，在出口节点C接收到中间节点B1和中间节点B2发送的测量报文G1和测量报文G2以后，出口节点C根据测量报文G1和测量报文G2中的链路的信息计算路径1的公平带宽D1和路径2的公平带宽D2，出口节点C将路径1的公平带宽D1和路径2的公平带宽D2放入应答报文Y中，并将应答报文Y发送至入口节点A中。在入口节点A接收到应答报文Y以后，入口节点A基于应答报文Y中的信息计算路径1的待发送流量Z1和路径2的待发送流量Z2。
第三种方式，在出口节点C接收到中间节点B1和中间节点B2发送的测量报文G1和测量报文G2以后，出口节点C根据测量报文G1和测量报文G2中的链路的信息计算路径1的公平带宽D1和路径2的公平带宽D2，出口节点C计算路径的最优利用率H，出口节点C将路径1的公平带宽D1、路径2的公平带宽D2和路径的最优利用率H放入应答报文Y中，并将应答报文Y发送至入口节点A中。在入口节点A接收到应答报文Y以后，入口节点A基于应答报文Y中的信息计算路径1的待发送流量Z1和路径2的待发送流量Z2。
第四种方式，在出口节点C接收到中间节点B1和中间节点B2发送的测量报文G1和测量报文G2以后，出口节点C根据测量报文G1和测量报文G2中的链路的信息计算路径1的公平带宽D1和路径2的公平带宽D2，出口节点C计算路径的最优利用率H，出口节点C计算路径1的分配流量K1和路径2的分配流量K2，出口节点C将路径1的分配流量K1和路径2的分配流量K2放入应答报文Y中，并将应答报文Y发送至入口节点A中。在入口节点A接收到应答报文Y以后，入口节点A基于应答报文Y中的信息计算路径1的待发送流量Z1和路径2的待发送流量Z2。
在图2和图3所示的实施例中，测量报文包括链路的发送流量、链路的带宽和路径的初始发送流量。当然，测量报文也可以包括链路的链路利用率和路径的初始发送流量。如果测量报文包括链路的链路利用率和路径的初始发送流量，那么路径的公平带宽D＝路径的接收流量R÷链路的链路利用率，这种方式的计算结果与S104的计算结果相同，其他参数的计算方式不变。例如，路径1的公平带宽D1＝路径1的接收流量R1÷链路X2的链路利用率H12＝300MB÷80％＝375MB。
请参见图4所示，图4为本申请实施例提供的又一种网络示意图。图4所示的网络中包括入口节点A、中间节点B1、中间节点B2、中间节点B3、中间节点C1、中间节点C2和出口节点D。在入口节点A和出口节点D之间具有三条路径，这三条路径分别是路径1、路径2和路径3。示例的，路径1为节点A->节点B1->节点C1->节点D，路径2为节点A->节点B2->节点C1->节点D，路径3为节点A->节点B3->节点C2->节点D。
在图4所示的实施例中，假设路径1的瓶颈链路为链路C1-D，路径2的瓶颈链路为链路C1-D，路径3的瓶颈链路为链路C2-D,链路C1-D的带宽B1＝链路C2-D的带宽B2＝2000MB，链路C1-D的发送流量U1＝2000MB，链路C2-D的发送流量U2＝1000MB，路径1的发送流量S1＝路径2的发送流量S2＝路径3的发送流量S3＝路径1的接收流量R1＝路径2的接收流量R2＝路径3的接收流量R3＝1000MB。
在图4所示的实施例中，入口节点A在路径1、路径2和路径3上分别向出口节点D发送测量报文G1、测量报文G2和测量报文G3。关于中间节点B1、中间节点B2、中间节点B3、中间节点C1和中间节点C2的执行过程请参见图3所示的实施例中的S102和S103，在此不做赘述。
在图4所示的实施例中，在出口节点D接收到测量报文G1、测量报文G2和测量报文G3以后，出口节点D计算路径1的公平带宽D1、路径2的公平带宽D2和路径3的公平带宽D3。
示例的，路径1的公平带宽D1＝(路径1的接收流量R1÷路径1的链路C1-D的发 送流量U1)×路径1的链路C1-D的链路带宽B1＝(1000MB÷2000MB)×2000MB＝1000MB。
示例的，路径2的公平带宽D2＝(路径2的接收流量R2÷路径2的链路C1-D的发送流量U1)×路径2的链路C1-D的链路带宽B1＝(1000MB÷2000MB)×2000MB＝1000MB。
示例的，路径3的公平带宽D3＝(路径3的接收流量R3÷路径3的链路C2-D的发送流量U2)×路径3的链路C2-D的链路带宽B2＝(1000MB÷1000MB)×2000MB＝2000MB。
在图4所示的实施例中，在出口节点D计算路径1的公平带宽D1、路径2的公平带宽D2和路径3的公平带宽D3以后，出口节点D计算路径的最优利用率H。
示例的，路径的最优利用率H＝所有路径的发送流量÷所有路径的公平带宽＝(路径1的初始发送流量S1+路径2的初始发送流量S2+路径3的初始发送流量S3)÷(路径1的公平带宽D1+路径2的公平带宽D2+路径3的公平带宽D3)＝(1000MB+1000MB+1000MB)÷(1000MB+1000MB+2000MB)＝75％。
在图4所示的实施例中，在出口节点D计算路径的最优利用率H以后，出口节点C分别计算路径1的分配流量K1、路径2的分配流量K2和路径3的分配流量K3。
示例的，路径1的分配流量K1＝路径的最优利用率H×路径1的公平带宽D1＝75％×1000MB＝750MB。
示例的，路径2的分配流量K2＝路径的最优利用率H×路径2的公平带宽D2＝75％×1000MB＝750MB。
示例的，路径3的分配流量K3＝路径的最优利用率H×路径3的公平带宽D3＝75％×2000MB＝1500MB。
在图4所示的实施例中，在出口节点C分别计算路径1的分配流量K1、路径2的分配流量K2和路径3的分配流量K3以后，出口节点C分别计算路径1的流量调整量L1、路径2的流量调整量L2和路径3的流量调整量L3。
示例的，路径1的流量调整量L1＝路径1的分配流量K1－路径1的初始发送流量S1＝750MB-1000MB＝-250MB。
示例的，路径2的流量调整量L2＝路径2的分配流量K2－路径2的初始发送流量S2＝750MB-1000MB＝-250MB。
示例的，路径3的流量调整量L3＝路径3的分配流量K3－路径3的初始发送流量S3＝1500MB-1000MB＝500MB。
在图4所示的实施例中，在出口节点C分别计算路径1的流量调整量L1、路径2的流量调整量L2和路径3的流量调整量L3以后，出口节点C向入口节点A发送应答报文Y。
示例的，应答报文Y包括路径1的流量调整量L1、路径2的流量调整量L2和路径3的流量调整量L3。
在图4所示的实施例中，在入口节点接收到出口节点C发送的应答报文Y，并根据应答报文Y确定路径1的待发送流量Z1、路径2的待发送流量Z2和路径3的待发送流量Z3。
示例的，路径1的待发送流量Z1＝路径1的流量调整量L1+路径1的初始发送流量S1＝-250MB+1000MB＝750MB。
示例的，路径2的待发送流量Z2＝路径2的流量调整量L2+路径2的初始发送流量 S2＝-250MB+1000MB＝750MB。
示例的，路径3的待发送流量Z3＝路径3的流量调整量L3+路径3的初始发送流量S3＝500MB+1000MB＝1500MB。
在图4所示的实施例中，链路C1-D的发送流量U1为在第一时间段内链路C1-D的累计发送流量，链路C2-D的发送流量U2为在第一时间段内链路C2-D的累计发送流量，路径1的发送流量S1为在第二时间段内出口节点A在路径1上的累计发送流量，路径2的发送流量S2为在第二时间段内出口节点A在路径2上的累计发送流量，路径3的发送流量S3为在第二时间段内出口节点A在路径3上的累计发送流量，路径1的接收流量R1为在第三时间段内出口节点D在路径1上的累计接收流量，路径2的接收流量R2为在第三时间段内出口节点D在路径2上的累计接收流量，路径3的接收流量R3为在第三时间段内出口节点D在路径3上的累计接收流量。
在图4所示的实施例中，路径1的待发送流量Z1为预计在第四时间段内入口节点A在路径1上的累计发送流量，路径2的待发送流量Z2为预计在第四时间段内入口节点A在路径2上的累计发送流量，路径3的待发送流量Z3为预计在第四时间段内入口节点A在路径3上的累计发送流量。
在图4所示的实施例中，假设第一时间段为0-10μs，第二时间段为0-3ms，第三时间段为3ms-6ms，第四时间段为6ms-9ms。在第一时间段内，链路C1-D的链路利用率H1＝链路C1-D的发送流量U1÷链路C1-D的带宽B1＝2000MB÷2000MB＝100％，链路C2-D的链路利用率H2＝链路C2-D的发送流量U2÷链路C2-D的带宽B2＝1000MB÷2000MB＝50％，其中，链路C1-D处于超载状态，链路C2-D处于轻载状态。在第四时间段内，链路C1-D的链路利用率H1＝链路C1-D的发送流量U1÷链路C1-D的带宽B1＝1500MB÷2000MB＝75％，链路C2-D的链路利用率H2＝链路C2-D的发送流量U2÷链路C2-D的带宽B2＝1500MB÷2000MB＝75％，其中，链路C1-D和链路C2-D的链路利用率非常均衡，通过图4所示的实施例可以得知，本申请实施例提供的方案可以使网络中链路的负载更加均衡。
请参见图5所示，图5为本申请实施例提供的又一种路径的流量分配方法的流程图，图5所示的路径的流量分配方法可以应用于入口节点中。图5所示的方法包括以下。
S201、入口节点在至少两个路径中的每个路径上向出口节点发送测量报文。
其中，至少两个路径为入口节点与出口节点之间的路径，每个路径上的测量报文用于指示每个路径的路径信息。
例如，测量报文包括链路的发送流量和链路的带宽，其中，链路的发送流量为在第一时间段内链路的累计发送流量，链路的带宽为在第一时间段内链路的带宽。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，第一时间戳为测量报文的发送时间，路径的初始发送流量为在第二时间段内路径的累计发送流量，或者，路径的初始发送流量为第一时间戳对应的路径的累计发送流量。
又如，测量报文包括链路的链路利用率，链路利用率为链路的发送流量与链路的带宽的比值。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个。
关于S201的具体实现，可以参见图3所示的实施例中关于S101的说明。
S202、入口节点接收出口节点发送的应答报文。
其中，应答报文用于指示每个路径的流量调整信息。
S203、入口节点根据每个路径的流量调整信息确定每个路径的待发送流量。
关于S202和S203的具体实现，可以参见图3所示的实施例中关于S109的说明。
在图5所示的实施例中，在网络中入口节点可以与中间节点和出口节点相互配合，以使入口节点掌握网络中链路的负载情况，入口节点便可以为每个路径分配发送流量，从而保证网络中链路的负载更加均衡。
在图5所示的实施例中，应答报文包括每个路径的流量调整量，每个路径的流量调整量用于指示每个路径需要调整的流量。其中，图5所示的S203还可以包括：入口节点获取每个路径的初始发送流量，入口节点根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在图5所示的实施例中，应答报文包括每个路径的分配流量，每个路径的分配流量用于指示每个路径链路的发送流量。其中，图5所示的S203还可以包括：入口节点获取每个路径的初始发送流量，入口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，入口节点根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在图5所示的实施例中，应答报文包括每个路径的最优利用率和每个路径的公平带宽，每个路径的公平带宽用于指示分配给每个路径的带宽，每个路径的最优利用率用于指示每个路径的发送流量与每个路径的公平带宽之间的比例。其中，图5所示的S203还可以包括：入口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，入口节点获取每个路径的初始发送流量，入口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，入口节点根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在图5所示的实施例中，应答报文包括每个路径的公平带宽。其中，图5所示的S203还可以包括：入口节点获取每个路径的初始发送流量，入口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，入口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，入口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，入口节点根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在图5所示的实施例中，应答报文包括每个路径的接收流量和每个路径的链路的信息，链路为路径上的链路利用率最大的链路，链路利用率为链路的发送流量与链路的带宽的比值。其中，图5所示的S203还可以包括：入口节点根据每个路径的接收流量和每个路径的链路的信息确定每个路径的公平带宽，入口节点获取每个路径的初始发送流量，入口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，入口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，入口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，入口节点根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在图5所示的实施例中，应答报文还包括路径标识、第一时间戳、第二时间戳、 第三时间戳、路径的接收流量、链路的链路利用率、链路的发送流量或链路的带宽中的至少一个，第二时间戳为测量报文的接收时间，第三时间戳为应答报文的发送时间，路径的接收流量为在第三时间段内路径的累计接收流量，或者，路径的接收流量为第二时间戳对应的路径的累计接收流量，第三时间段晚于或等于第二时间段。
在图5所示的实施例中，入口节点根据第一路径的流量调整量和第一路径的初始发送流量确定第一路径的待发送流量可以包括：入口节点计算第一路径的流量调整量与第一路径的初始发送流量之和得到第一路径的待发送流量。其中，第一路径为至少两个路径的每个路径中的任意一个路径。
在图5所示的实施例中，入口节点根据第一路径的初始发送流量和第一路径的分配流量确定第一路径的流量调整量可以包括：入口节点计算第一路径的分配流量与第一路径的初始发送流量之差得到第一路径的流量调整量。
在图5所示的实施例中，入口节点根据每个路径的最优利用率和第一路径的公平带宽确定第一路径的分配流量可以包括：入口节点计算每个路径的最优利用率与第一路径的公平带宽之积得到第一路径的分配流量。
在图5所示的实施例中，入口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率可以包括：入口节点计算每个路径的初始发送流量之和得到总发送流量，入口节点计算每个路径的公平带宽之和得到总公平带宽，入口节点计算总发送流量与总公平带宽之商得到每个路径的最优利用率。
在图5所示的实施例中，入口节点根据第一路径的接收流量和第一路径的链路的信息确定第一路径的公平带宽可以包括：入口节点计算第一路径的接收流量与第一路径的链路的发送流量之商得到第一比值，入口节点计算第一比值与第一路径的带宽之积得到第一路径的公平带宽。
在图5所示的实施例中，入口节点根据第一路径的接收流量和第一路径的链路的信息确定第一路径的公平带宽还可以包括：入口节点计算第一路径的接收流量与第一路径的链路的链路利用率之商得到第一路径的公平带宽。
请参见图6所示，图6为本申请实施例提供的又一种路径的流量分配方法的流程图，图6所示的路径的流量分配方法可以应用于中间节点中。图6所示的方法包括：
S301、中间节点在至少两个路径中的第一路径上接收测量报文。
其中，至少两个路径为入口节点与出口节点之间的路径，测量报文用于指示第一路径的第一链路的信息。
例如，测量报文包括链路的发送流量和链路的带宽，其中，链路的发送流量为在第一时间段内链路的累计发送流量，链路的带宽为在第一时间段内链路的带宽。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，第一时间戳为测量报文的发送时间，路径的初始发送流量为在第二时间段内路径的累计发送流量，或者，路径的初始发送流量为第一时间戳对应的路径的累计发送流量。
又如，测量报文包括链路的链路利用率，链路利用率为链路的发送流量与链路的带宽的比值。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个。
S302、中间节点获取第二链路的信息。
其中，第二链路为在第一路径上与中间节点的出端口连接的链路。
S303、中间节点根据第一链路的信息和第二链路的信息确定第一链路的链路利用率是否大于或等于第二链路的链路利用率。如果是，执行S304；否则，执行S305。
S304、在中间节点根据第一链路的信息和第二链路的信息确定第一链路的链路利用率大于或等于第二链路的链路利用率时，中间节点向出口节点发送测量报文，链路利用率用于指示链路的流量占用情况。
S305、在中间节点根据第一链路的信息和第二链路的信息确定第一链路的链路利用率小于第二链路的链路利用率时，中间节点将第二链路的信息填入测量报文中，中间节点向出口节点发送测量报文。
关于S301和S305的具体实现，可以参见图3所示的实施例中关于S102和S103的说明。
在图6所示的实施例中，在网络中中间节点可以与入口节点和出口节点相互配合，以使入口节点掌握网络中链路的负载情况，入口节点便可以为每个路径分配发送流量，从而保证网络中链路的负载更加均衡。
在图6所示的实施例中，第一链路的信息可以包括第一链路的发送流量和第一链路的带宽，第二链路的信息包括第二链路的发送流量和第二链路的带宽。当然，第一链路的信息也可以包括第一链路的链路利用率，其中，第二链路的信息包括第二链路的链路利用率。
在图6所示的实施例中，在S305以后，本申请实施例提供的路径的流量分配方法还可以包括：第一中间节点删除第一测量报文。
在图6所示的实施例中，第一测量报文还可以包括第一路径的路径标识、时间戳或第一路径的初始发送流量中的至少一个，时间戳为第一测量报文的发送时间。第二测量报文还可以包括第一路径的路径标识、时间戳或第一路径的初始发送流量中的至少一个。
请参见图7所示，图7为本申请实施例提供的又一种路径的流量分配方法的流程图，图7所示的路径的流量分配方法可以应用于出口节点中。图7所示的方法包括：
S401、出口节点在至少两个路径中的每个路径上接收入口节点发送的测量报文。
其中，至少两个路径为入口节点与出口节点之间的路径，每个路径上的测量报文用于指示每个路径的路径信息。
例如，测量报文包括链路的发送流量和链路的带宽，其中，链路的发送流量为在第一时间段内链路的累计发送流量，链路的带宽为在第一时间段内链路的带宽。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，第一时间戳为测量报文的发送时间，路径的初始发送流量为在第二时间段内路径的累计发送流量，或者，路径的初始发送流量为第一时间戳对应的路径的累计发送流量。
又如，测量报文包括链路的链路利用率，链路利用率为链路的发送流量与链路的带宽的比值。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个。
S402、出口节点根据每个路径的路径信息和每个路径的接收流量生成应答报文。
其中，应答报文用于指示每个路径的流量调整信息。
S403、出口节点向入口节点发送应答报文。
其中，应答报文包括至少一个质量信息。例如，应答报文可以包括每个路径的公平带宽，那么每个路径的公平带宽为每个路径的质量信息。又如，应答报文可以包括每个路径的最优利用率和每个路径的公平带宽，那么每个路径的最优利用率和每个路径的公平带宽为每个路径的质量信息。又如，应答报文可以包括每个路径的分配流量，那么每个路径的分配流量为每个路径的质量信息。又如，应答报文可以包括每个路径的流量调整量，那么每个路径的流量调整量为每个路径的质量信息。
关于S401和S403的具体实现，可以参见图3所示的实施例中关于S104至S108的说明。
在图7所示的实施例中，在网络中出口节点可以与入口节点和中间节点相互配合，以使入口节点掌握网络中链路的负载情况，入口节点便可以为每个路径分配发送流量，从而保证网络中链路的负载更加均衡。
在图7所示的实施例中，图7中的S402可以包括：出口节点根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽，出口节点生成应答报文，应答报文包括每个路径的公平带宽。
在图7所示的实施例中，图7中的S402可以包括：出口节点根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽，出口节点获取每个路径的初始发送流量，出口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，出口节点生成应答报文，应答报文包括每个路径的最优利用率和每个路径的公平带宽。
在图7所示的实施例中，图7中的S402可以包括：出口节点根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽，出口节点获取每个路径的初始发送流量，出口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，入口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，出口节点生成应答报文，应答报文包括每个路径的分配流量。
在图7所示的实施例中，图7中的S402可以包括：出口节点根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽，出口节点获取每个路径的初始发送流量，出口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率，入口节点根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量，入口节点根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量，出口节点生成应答报文，应答报文包括每个路径的流量调整量。
在图7所示的实施例中，应答报文还包括路径标识、第一时间戳、第二时间戳、第三时间戳、路径的接收流量、链路的链路利用率、链路的发送流量或链路的带宽中的至少一个，第二时间戳为测量报文的接收时间，第三时间戳为应答报文的发送时间，路径的接收流量为在第三时间段内路径的累计接收流量，或者，路径的接收流量为第二时间戳对应的路径的累计接收流量，第三时间段晚于或等于第二时间段。
在图7所示的实施例中，出口节点根据第一路径的链路的信息和第一路径的接收流量确定第一路径的公平带宽可以包括：出口节点计算根据第一路径的链路的信息和 第一路径的接收流量确定第一路径的公平带宽。其中，第一路径为至少两个路径的每个路径中的任意一个路径。
在图7所示的实施例中，出口节点根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率可以包括：出口节点计算每个路径的初始发送流量之和得到总发送流量，出口节点计算每个路径的公平带宽之和得到总公平带宽，出口节点计算总发送流量与总公平带宽之商得到每个路径的最优利用率。
在图7所示的实施例中，出口节点根据每个路径的最优利用率和第一路径的公平带宽确定每个路径的分配流量可以包括：出口节点计算每个路径的最优利用率与第一路径的公平带宽之积得到第一路径的分配流量。其中，第一路径为至少两个路径的每个路径中的任意一个路径。
在图7所示的实施例中，出口节点根据第一路径的初始发送流量和第一路径的分配流量确定第一路径的流量调整量可以包括：出口节点计算第一路径的分配流量与第一路径的初始发送流量之差得到第一路径的流量调整量。其中，第一路径为至少两个路径的每个路径中的任意一个路径。
请参见图8所示，图8为本申请实施例提供的一种入口节点的示意图。图8所示的入口节点包括以下模块：
发送模块11，用于在至少两个路径中的每个路径上向出口节点发送测量报文。
其中，至少两个路径为入口节点与出口节点之间的路径，每个路径上的测量报文用于指示每个路径的路径信息。
接收模块12，接收出口节点发送的应答报文。
其中，应答报文用于指示每个路径的流量调整信息。
确定模块13，用于根据每个路径的流量调整信息确定每个路径的待发送流量。
关于发送模块11、接收模块12和确定模块13的具体详细的实现方式，请参考上述图3所示的方法实施例中S101和S109的详细描述。
在一种可能的实现方式中，应答报文包括每个路径的流量调整量，每个路径的流量调整量用于指示每个路径需要调整的流量。其中，确定模块13，具体用于获取每个路径的初始发送流量，根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在一种可能的实现方式中，应答报文包括每个路径的分配流量，每个路径的分配流量用于指示每个路径链路的发送流量。其中，确定模块13，具体用于获取每个路径的初始发送流量；根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量；根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在一种可能的实现方式中，应答报文包括每个路径的最优利用率和每个路径的公平带宽，每个路径的公平带宽用于指示分配给每个路径的带宽，每个路径的最优利用率用于指示每个路径的发送流量与每个路径的公平带宽之间的比例。其中，确定模块13，具体用于根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量；获取每个路径的初始发送流量；根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量；根据每个路径的流量调整量和每个路径的初始发 送流量确定每个路径的待发送流量。
在一种可能的实现方式中，应答报文包括每个路径的公平带宽。其中，确定模块13，具体用于获取每个路径的初始发送流量；根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率；根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量；根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量；根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在一种可能的实现方式中，应答报文包括每个路径的接收流量和每个路径的链路的信息，链路为路径上的链路利用率最大的链路，链路利用率为链路的发送流量与链路的带宽的比值。其中，确定模块13，具体用于根据每个路径的接收流量和每个路径的链路的信息确定每个路径的公平带宽；获取每个路径的初始发送流量；根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率；根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量；根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量；根据每个路径的流量调整量和每个路径的初始发送流量确定每个路径的待发送流量。
在一种可能的实现方式中，确定模块13，具体用于计算第一路径的流量调整量与第一路径的初始发送流量之和得到第一路径的待发送流量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，确定模块13，具体用于计算第一路径的分配流量与第一路径的初始发送流量之差得到第一路径的流量调整量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，确定模块13，具体用于计算每个路径的最优利用率与第一路径的公平带宽之积得到第一路径的分配流量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，确定模块13，具体用于计算每个路径的初始发送流量之和得到总发送流量，计算每个路径的公平带宽之和得到总公平带宽，计算总发送流量与总公平带宽之商得到每个路径的最优利用率。
在一种可能的实现方式中，确定模块13，具体用于计算第一路径的接收流量与第一路径的链路的发送流量之商得到第一比值，第一路径为至少两个路径的每个路径中的任意一个路径，计算第一比值与第一路径的带宽之积得到第一路径的公平带宽。
在一种可能的实现方式中，确定模块13，具体用于计算第一路径的接收流量与第一路径的链路的链路利用率之商得到第一路径的公平带宽。
在一种可能的实现方式中，测量报文包括链路的发送流量和链路的带宽，其中，链路的发送流量为在第一时间段内链路的累计发送流量，链路的带宽为在第一时间段内链路的带宽。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，第一时间戳为测量报文的发送时间，路径的初始发送流量为在第二时间段内路径的累计发送流量，或者，路径的初始发送流量为第一时间戳对应的路径的累计发送流量。
在一种可能的实现方式中，测量报文包括链路的链路利用率，链路利用率为链路 的发送流量与链路的带宽的比值。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个。
在一种可能的实现方式中，应答报文还包括路径标识、第一时间戳、第二时间戳、第三时间戳、路径的接收流量、链路的链路利用率、链路的发送流量或链路的带宽中的至少一个，第二时间戳为测量报文的接收时间，第三时间戳为应答报文的发送时间，路径的接收流量为在第三时间段内路径的累计接收流量，或者，路径的接收流量为第二时间戳对应的路径的累计接收流量，第三时间段晚于或等于第二时间段。
请参见图9所示，图9为本申请实施例提供的一种中间节点的示意图。图9所示的中间节点包括以下模块：
接收模块21，用于在至少两个路径中的第一路径上接收测量报文，至少两个路径为入口节点与出口节点之间的路径，测量报文用于指示第一路径的第一链路的信息。
获取模块22，用于获取第二链路的信息，第二链路为在第一路径上与中间节点的出端口连接的链路。
确定模块23，用于在根据第一链路的信息和第二链路的信息确定第一链路的链路利用率大于或等于第二链路的链路利用率时，调用发送模块24向出口节点发送测量报文，链路利用率用于指示链路的流量占用情况。在根据第一链路的信息和第二链路的信息确定第一链路的链路利用率小于第二链路的链路利用率时，将第二链路的信息填入测量报文中，调用发送模块24向出口节点发送测量报文。
发送模块24，用于向出口节点发送测量报文。
关于接收模块21、获取模块22、确定模块23和发送模块24的具体详细的实现方式，请参考上述图3所示的方法实施例中S102和S103的详细描述。
在一种可能的实现方式中，第一链路的信息包括第一链路的发送流量和第一链路的带宽，第二链路的信息包括第二链路的发送流量和第二链路的带宽。或者，第一链路的信息包括第一链路的链路利用率，第二链路的信息包括第二链路的链路利用率。
在一种可能的实现方式中，确定模块23，还用于删除第一测量报文。
在一种可能的实现方式中，测量报文包括链路的发送流量和链路的带宽，其中，链路的发送流量为在第一时间段内链路的累计发送流量，链路的带宽为在第一时间段内链路的带宽。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，第一时间戳为测量报文的发送时间，路径的初始发送流量为在第二时间段内路径的累计发送流量，或者，路径的初始发送流量为第一时间戳对应的路径的累计发送流量。
在一种可能的实现方式中，测量报文包括链路的链路利用率，链路利用率为链路的发送流量与链路的带宽的比值。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个。
请参见图10所示，图10为本申请实施例提供的一种出口节点的示意图。图10所示的出口节点包括以下模块：
接收模块31，用于在至少两个路径中的每个路径上接收入口节点发送的测量报文。其中，至少两个路径为入口节点与出口节点之间的路径，每个路径上的测量报文用于指示每个路径的路径信息。
生成模块32，用于根据每个路径的路径信息和每个路径的接收流量生成应答报文。其中，应答报文用于指示每个路径的流量调整信息。
发送模块33，用于向入口节点发送应答报文。
关于接收模块31、生成模块32和发送模块33的具体详细的实现方式，请参考上述图3所示的方法实施例中S104至S108的详细描述。
在一种可能的实现方式中，生成模块32，具体用于根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽；生成应答报文，应答报文包括每个路径的公平带宽。
在一种可能的实现方式中，生成模块32，具体用于根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽；获取每个路径的初始发送流量；根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率；生成应答报文，应答报文包括每个路径的最优利用率和每个路径的公平带宽。
在一种可能的实现方式中，生成模块32，具体用于根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽；获取每个路径的初始发送流量；根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率；根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量；生成应答报文，应答报文包括每个路径的分配流量。
在一种可能的实现方式中，生成模块32，具体用于根据每个路径的链路的信息和每个路径的接收流量确定每个路径的公平带宽；获取每个路径的初始发送流量；根据每个路径的初始发送流量和每个路径的公平带宽确定每个路径的最优利用率；根据每个路径的最优利用率和每个路径的公平带宽确定每个路径的分配流量；根据每个路径的初始发送流量和每个路径的分配流量确定每个路径的流量调整量；生成应答报文，应答报文包括每个路径的流量调整量。
在一种可能的实现方式中，生成模块32，具体用于计算根据第一路径的链路的信息和第一路径的接收流量确定第一路径的公平带宽，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，生成模块32，具体用于计算每个路径的初始发送流量之和得到总发送流量，计算每个路径的公平带宽之和得到总公平带宽，计算总发送流量与总公平带宽之商得到每个路径的最优利用率。
在一种可能的实现方式中，生成模块32，具体用于计算每个路径的最优利用率与第一路径的公平带宽之积得到第一路径的分配流量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，生成模块32，具体用于计算第一路径的分配流量与第一路径的初始发送流量之差得到第一路径的流量调整量，第一路径为至少两个路径的每个路径中的任意一个路径。
在一种可能的实现方式中，测量报文包括链路的发送流量和链路的带宽，其中，链路的发送流量为在第一时间段内链路的累计发送流量，链路的带宽为在第一时间段内链路的带宽。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，第一时间戳为测量报文的发送时间，路径的初始发送流量为在第二时 间段内路径的累计发送流量，或者，路径的初始发送流量为第一时间戳对应的路径的累计发送流量。
在一种可能的实现方式中，测量报文包括链路的链路利用率，链路利用率为链路的发送流量与链路的带宽的比值。而且，测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个。
在一种可能的实现方式中，应答报文还包括路径标识、第一时间戳、第二时间戳、第三时间戳、路径的接收流量、链路的链路利用率、链路的发送流量或链路的带宽中的至少一个，第二时间戳为测量报文的接收时间，第三时间戳为应答报文的发送时间，路径的接收流量为在第三时间段内路径的累计接收流量，或者，路径的接收流量为第二时间戳对应的路径的累计接收流量，第三时间段晚于或等于第二时间段。
请参见图11所示，图11为本申请实施例提供的又一种入口节点的示意图。图11所示的入口节点包括处理器41、存储器42、总线43和输入/输出接口44。
其中，终端设备的输入/输出接口44可以在至少两个路径中的每个路径上向出口节点发送测量报文，以及接收出口节点发送的应答报文。总线43可以将输入/输出接口44接收的应答报文传输至存储器42中。处理器41可以在存储器42中获取应答报文，并且根据应答报文中的每个路径的流量调整信息确定每个路径的待发送流量。图11所示的入口节点等同于图2至图10中提到的入口节点，关于图11中的入口节点可以参见图2至图10对应的实施例中对于入口节点的详细说明。
请参见图12所示，图12为本申请实施例提供的又一种中间节点的示意图。图12所示的中间节点包括处理器51、存储器52、总线53和输入/输出接口54。
其中，中间节点的输入/输出接口54可以在至少两个路径中的第一路径上接收测量报文，以及获取第二链路的信息。总线53可以将输入/输出接口54接收的测量报文和第二链路的信息传输至存储器52中。处理器51可以在存储器52中获取测量报文中的第一链路的信息和第二链路的信息，并且在根据第一链路的信息和第二链路的信息确定第一链路的链路利用率大于或等于第二链路的链路利用率时，调用输入/输出接口54向出口节点发送测量报文。在根据第一链路的信息和第二链路的信息确定第一链路的链路利用率小于第二链路的链路利用率时，将第二链路的信息填入测量报文中，调用输入/输出接口54向出口节点发送测量报文。图12所示的中间节点等同于图2至图10中提到的中间节点，关于图12中的中间节点可以参见图2至图10对应的实施例中对于中间节点的详细说明。
请参见图13所示，图13为本申请实施例提供的又一种出口节点的示意图。图13所示的出口节点包括处理器61、存储器62、总线63和输入/输出接口64。
其中，出口节点的输入/输出接口64可以在至少两个路径中的每个路径上接收入口节点发送的测量报文，以及向入口节点发送应答报文。总线63可以将输入/输出接口64接收的测量报文传输至存储器62中。处理器61可以在存储器62中获取每个路径的路径信息和每个路径的接收流量，并且根据每个路径的路径信息和每个路径的接收流量生成应答报文。图13所示的出口节点等同于图2至图10中提到的出口节点，关于图13中的出口节点可以参见图2至图10对应的实施例中对于出口节点的详细说明。
请参见图14所示，图14为本申请实施例提供的一种网络系统的示意图。图14所示的网络系统包括入口节点100、中间节点200和出口节点300。
其中，图14所示的入口节点100的具体结构可以参考图8所示的入口节点和图11所示的入口节点，图14所示的中间节点200的具体结构可以参考图9所示的中间节点和图12所示的中间节点，图14所示的出口节点300的具体结构可以参考图10所示的出口节点和图13所示的出口节点。
需要说明的是，当上述实施例中涉及软件实现的功能时，相关软件或软件中的模块可存储在计算机可读介质中或作为计算机可读介质上的一个或多个指令或代码进行传输。计算机可读介质包括计算机存储介质和通信介质，其中通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。存储介质可以是计算机能够存取的任何可用介质。以此为例但不限于：计算机可读介质可以包括RAM、ROM、EEPROM、CD-ROM或其他光盘存储、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质。此外。任何连接可以适当的成为计算机可读介质。例如，如果软件是使用同轴电缆、光纤光缆、双绞线、数字用户线(DSL)或者诸如红外线、无线电和微波之类的无线技术从网站、服务器或者其他远程源传输的，那么同轴电缆、光纤光缆、双绞线、DSL或者诸如红外线、无线和微波之类的无线技术包括在所属介质的定影中。如本申请所使用的，盘(Disk)和碟(disc)包括压缩光碟(CD)、激光碟、光碟、数字通用光碟(DVD)、软盘和蓝光光碟，其中盘通常磁性的复制数据，而碟则用激光来光学的复制数据。上面的组合也应当包括在计算机可读介质的保护范围之内。
此外，以上实施例仅用以说明本申请的技术方案而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，然而本领域的普通技术人员应当理解：其依然可对前述各实施例所记载的技术方案进行修改，或对其中部分技术特征进行等同替换。

Claims (20)

  1. 一种路径的流量分配方法，其特征在于，所述方法包括：
    入口节点在至少两个路径中的每个路径上向出口节点发送测量报文，所述至少两个路径为所述入口节点与所述出口节点之间的路径，所述每个路径上的测量报文用于指示所述每个路径的路径信息；
    所述入口节点接收所述出口节点发送的应答报文，所述应答报文用于指示所述每个路径的流量调整信息；
    所述入口节点根据所述每个路径的流量调整信息确定所述每个路径的待发送流量。
  2. 根据权利要求1所述的方法，其特征在于，所述应答报文包括所述每个路径的流量调整量，所述每个路径的流量调整量用于指示所述每个路径需要调整的流量；
    所述入口节点根据所述每个路径的流量调整信息确定所述每个路径的待发送流量包括：
    所述入口节点获取所述每个路径的初始发送流量；
    所述入口节点根据所述每个路径的流量调整量和所述每个路径的初始发送流量确定所述每个路径的待发送流量。
  3. 根据权利要求1所述的方法，其特征在于，所述应答报文包括所述每个路径的分配流量，所述每个路径的分配流量用于指示所述每个路径链路的发送流量；
    所述入口节点根据所述每个路径的流量调整信息确定所述每个路径的待发送流量包括：
    所述入口节点获取所述每个路径的初始发送流量；
    所述入口节点根据所述每个路径的初始发送流量和所述每个路径的分配流量确定所述每个路径的流量调整量；
    所述入口节点根据所述每个路径的流量调整量和所述每个路径的初始发送流量确定所述每个路径的待发送流量。
  4. 根据权利要求1-3任意一项所述的方法，其特征在于：
    所述测量报文包括链路的发送流量和链路的带宽，所述链路的发送流量为在第一时间段内所述链路的累计发送流量，所述链路的带宽为在所述第一时间段内所述链路的带宽；或者，
    所述测量报文包括链路的链路利用率，所述链路利用率为所述链路的发送流量与所述链路的带宽的比值；或者，
    所述测量报文包括所述链路的发送流量和所述链路的带宽，所述测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，所述第一时间戳为所述测量报文的发送时间，所述路径的初始发送流量为在第二时间段内所述路径的累计发送流量，或者，所述路径的初始发送流量为所述第一时间戳对应的所述路径的累计发送流量；或者，
    所述测量报文包括所述链路的链路利用率，所述测量报文还包括所述路径的初始发送流量、所述路径标识或所述第一时间戳中的至少一个。
  5. 根据权利要求4所述的方法，其特征在于：
    所述应答报文还包括路径标识、所述第一时间戳、第二时间戳、第三时间戳、路径的接收流量、所述链路的链路利用率、所述链路的发送流量或所述链路的带宽中的至少一个，所述第二时间戳为所述测量报文的接收时间，所述第三时间戳为所述应答报文的发送时间，所述路径的接收流量为在第三时间段内所述路径的累计接收流量，或者，所述路径的接收流量为所述第二时间戳对应的所述路径的累计接收流量，所述第三时间段晚于或等于所述第二时间段。
  6. 一种路径的流量分配方法，其特征在于，所述方法包括：
    出口节点在至少两个路径中的每个路径上接收入口节点发送的测量报文，所述至少两个路径为所述入口节点与所述出口节点之间的路径，所述每个路径上的测量报文用于指示所述每个路径的路径信息；
    所述出口节点根据所述每个路径的路径信息和所述每个路径的接收流量生成应答报文，所述应答报文用于指示所述每个路径的流量调整信息；
    所述出口节点向所述入口节点发送应答报文。
  7. 根据权利要求6所述的方法，其特征在于：
    所述测量报文包括链路的发送流量和链路的带宽，所述链路的发送流量为在第一时间段内所述链路的累计发送流量，所述链路的带宽为在所述第一时间段内所述链路的带宽；或者，
    所述测量报文包括链路的链路利用率，所述链路利用率为所述链路的发送流量与所述链路的带宽的比值；或者，
    所述测量报文包括所述链路的发送流量和所述链路的带宽，所述测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，所述第一时间戳为所述测量报文的发送时间，所述路径的初始发送流量为在第二时间段内所述路径的累计发送流量，或者，所述路径的初始发送流量为所述第一时间戳对应的所述路径的累计发送流量；或者，
    所述测量报文包括所述链路的链路利用率，所述测量报文还包括所述路径的初始发送流量、所述路径标识或所述第一时间戳中的至少一个。
  8. 根据权利要求6或7所述的方法，其特征在于，所述出口节点根据所述每个路径的路径信息和所述每个路径的接收流量生成应答报文包括：
    所述出口节点根据所述每个路径的链路的信息和所述每个路径的接收流量确定所述每个路径的公平带宽；
    所述出口节点获取所述每个路径的初始发送流量；
    所述出口节点根据所述每个路径的初始发送流量和所述每个路径的公平带宽确定 所述每个路径的最优利用率；
    所述出口节点根据所述每个路径的最优利用率和所述每个路径的公平带宽确定所述每个路径的分配流量；
    所述出口节点生成应答报文，所述应答报文包括所述每个路径的分配流量。
  9. 根据权利要求6或7所述的方法，其特征在于，所述出口节点根据所述每个路径的路径信息和所述每个路径的接收流量生成应答报文包括：
    所述出口节点根据所述每个路径的链路的信息和所述每个路径的接收流量确定所述每个路径的公平带宽；
    所述出口节点获取所述每个路径的初始发送流量；
    所述出口节点根据所述每个路径的初始发送流量和所述每个路径的公平带宽确定所述每个路径的最优利用率；
    所述出口节点根据所述每个路径的最优利用率和所述每个路径的公平带宽确定所述每个路径的分配流量；
    所述出口节点根据所述每个路径的初始发送流量和所述每个路径的分配流量确定所述每个路径的流量调整量；
    所述出口节点生成应答报文，所述应答报文包括所述每个路径的流量调整量。
  10. 根据权利要求8或9所述的方法，其特征在于：
    所述应答报文还包括路径标识、所述第一时间戳、第二时间戳、第三时间戳、路径的接收流量、所述链路的链路利用率、所述链路的发送流量或所述链路的带宽中的至少一个，所述第二时间戳为所述测量报文的接收时间，所述第三时间戳为所述应答报文的发送时间，所述路径的接收流量为在第三时间段内所述路径的累计接收流量，或者，所述路径的接收流量为所述第二时间戳对应的所述路径的累计接收流量，所述第三时间段晚于或等于所述第二时间段。
  11. 一种入口节点，其特征在于，所述入口节点包括：
    发送模块，用于在至少两个路径中的每个路径上向出口节点发送测量报文，所述至少两个路径为所述入口节点与所述出口节点之间的路径，所述每个路径上的测量报文用于指示所述每个路径的路径信息；
    接收模块，用于接收所述出口节点发送的应答报文，所述应答报文用于指示所述每个路径的流量调整信息；
    确定模块，用于根据所述每个路径的流量调整信息确定所述每个路径的待发送流量。
  12. 根据权利要求11所述的入口节点，其特征在于，所述应答报文包括所述每个路径的流量调整量，所述每个路径的流量调整量用于指示所述每个路径需要调整的流量；
    所述确定模块，具体用于获取所述每个路径的初始发送流量，根据所述每个路径 的流量调整量和所述每个路径的初始发送流量确定所述每个路径的待发送流量。
  13. 根据权利要求11所述的入口节点，其特征在于，所述应答报文包括所述每个路径的分配流量，所述每个路径的分配流量用于指示所述每个路径链路的发送流量；
    所述确定模块，具体用于获取所述每个路径的初始发送流量；根据所述每个路径的初始发送流量和所述每个路径的分配流量确定所述每个路径的流量调整量；根据所述每个路径的流量调整量和所述每个路径的初始发送流量确定所述每个路径的待发送流量。
  14. 根据权利要求11-13任意一项所述的入口节点，其特征在于：
    所述测量报文包括链路的发送流量和链路的带宽，所述链路的发送流量为在第一时间段内所述链路的累计发送流量，所述链路的带宽为在所述第一时间段内所述链路的带宽；或者，
    所述测量报文包括链路的链路利用率，所述链路利用率为所述链路的发送流量与所述链路的带宽的比值；或者，
    所述测量报文包括所述链路的发送流量和所述链路的带宽，所述测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，所述第一时间戳为所述测量报文的发送时间，所述路径的初始发送流量为在第二时间段内所述路径的累计发送流量，或者，所述路径的初始发送流量为所述第一时间戳对应的所述路径的累计发送流量；或者，
    所述测量报文包括所述链路的链路利用率，所述测量报文还包括所述路径的初始发送流量、所述路径标识或所述第一时间戳中的至少一个。
  15. 根据权利要求14所述的入口节点，其特征在于：
    所述应答报文还包括路径标识、所述第一时间戳、第二时间戳、第三时间戳、路径的接收流量、所述链路的链路利用率、所述链路的发送流量或所述链路的带宽中的至少一个，所述第二时间戳为所述测量报文的接收时间，所述第三时间戳为所述应答报文的发送时间，所述路径的接收流量为在第三时间段内所述路径的累计接收流量，或者，所述路径的接收流量为所述第二时间戳对应的所述路径的累计接收流量，所述第三时间段晚于或等于所述第二时间段。
  16. 一种出口节点，其特征在于，所述出口节点包括：
    接收模块，用于在至少两个路径中的每个路径上接收入口节点发送的测量报文，所述至少两个路径为所述入口节点与所述出口节点之间的路径，所述每个路径上的测量报文用于指示所述每个路径的路径信息；
    生成模块，用于根据所述每个路径的路径信息和所述每个路径的接收流量生成应答报文，所述应答报文用于指示所述每个路径的流量调整信息；
    发送模块，用于向所述入口节点发送应答报文。
  17. 根据权利要求16所述的出口节点，其特征在于：
    所述测量报文包括链路的发送流量和链路的带宽，所述链路的发送流量为在第一时间段内所述链路的累计发送流量，所述链路的带宽为在所述第一时间段内所述链路的带宽；或者，
    所述测量报文包括链路的链路利用率，所述链路利用率为所述链路的发送流量与所述链路的带宽的比值；或者，
    所述测量报文包括所述链路的发送流量和所述链路的带宽，所述测量报文还包括路径的初始发送流量、路径标识或第一时间戳中的至少一个，所述第一时间戳为所述测量报文的发送时间，所述路径的初始发送流量为在第二时间段内所述路径的累计发送流量，或者，所述路径的初始发送流量为所述第一时间戳对应的所述路径的累计发送流量；或者，
    所述测量报文包括所述链路的链路利用率，所述测量报文还包括所述路径的初始发送流量、所述路径标识或所述第一时间戳中的至少一个。
  18. 根据权利要求16或17所述的出口节点，其特征在于：
    所述生成模块，具体用于根据所述每个路径的链路的信息和所述每个路径的接收流量确定所述每个路径的公平带宽；获取所述每个路径的初始发送流量；根据所述每个路径的初始发送流量和所述每个路径的公平带宽确定所述每个路径的最优利用率；根据所述每个路径的最优利用率和所述每个路径的公平带宽确定所述每个路径的分配流量；生成应答报文，所述应答报文包括所述每个路径的分配流量。
  19. 根据权利要求16或17所述的出口节点，其特征在于：
    所述生成模块，具体用于根据所述每个路径的链路的信息和所述每个路径的接收流量确定所述每个路径的公平带宽；获取所述每个路径的初始发送流量；根据所述每个路径的初始发送流量和所述每个路径的公平带宽确定所述每个路径的最优利用率；根据所述每个路径的最优利用率和所述每个路径的公平带宽确定所述每个路径的分配流量；根据所述每个路径的初始发送流量和所述每个路径的分配流量确定所述每个路径的流量调整量；生成应答报文，所述应答报文包括所述每个路径的流量调整量。
  20. 根据权利要求18或19所述的出口节点，其特征在于：
    所述应答报文还包括路径标识、所述第一时间戳、第二时间戳、第三时间戳、路径的接收流量、所述链路的链路利用率、所述链路的发送流量或所述链路的带宽中的至少一个，所述第二时间戳为所述测量报文的接收时间，所述第三时间戳为所述应答报文的发送时间，所述路径的接收流量为在第三时间段内所述路径的累计接收流量，或者，所述路径的接收流量为所述第二时间戳对应的所述路径的累计接收流量，所述第三时间段晚于或等于所述第二时间段。
PCT/CN2020/116515 2019-09-27 2020-09-21 一种路径的流量分配方法、网络设备及网络系统 WO2021057659A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20868753.3A EP4030706A4 (en) 2019-09-27 2020-09-21 TRAFFIC ALLOCATION METHOD FOR A PATH, NETWORK DEVICE AND NETWORK SYSTEM
US17/704,175 US20220217089A1 (en) 2019-09-27 2022-03-25 Path traffic allocation method, network device, and network system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910922263.0 2019-09-27
CN201910922263.0A CN112583729B (zh) 2019-09-27 2019-09-27 一种路径的流量分配方法、网络设备及网络系统

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/704,175 Continuation US20220217089A1 (en) 2019-09-27 2022-03-25 Path traffic allocation method, network device, and network system

Publications (1)

Publication Number Publication Date
WO2021057659A1 true WO2021057659A1 (zh) 2021-04-01

Family

ID=75109657

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/116515 WO2021057659A1 (zh) 2019-09-27 2020-09-21 一种路径的流量分配方法、网络设备及网络系统

Country Status (4)

Country Link
US (1) US20220217089A1 (zh)
EP (1) EP4030706A4 (zh)
CN (1) CN112583729B (zh)
WO (1) WO2021057659A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11546239B2 (en) * 2021-03-31 2023-01-03 Versa Networks, Inc. Data packet traffic conditioning with packet striping through lossy data paths
US11683126B2 (en) 2021-03-31 2023-06-20 Versa Networks, Inc. Data packet traffic conditioning through multiple lossy data paths with forward error correction
US11916674B2 (en) 2021-03-31 2024-02-27 Versa Networks, Inc. Data packet traffic conditioning through a lossy data path with forward error correction
CN113949666B (zh) * 2021-11-15 2024-03-19 中国银行股份有限公司 流量控制方法、装置、设备及系统
US20230362090A1 (en) * 2022-05-06 2023-11-09 Nokia Technologies Oy Packet validity time enhancement for quality of service flows

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101616061A (zh) * 2008-06-26 2009-12-30 华为技术有限公司 路径确定方法、路径确定装置及网络系统
CN101938484A (zh) * 2010-09-09 2011-01-05 奇智软件（北京）有限公司 一种分布式流量控制方法及系统
CN104092628A (zh) * 2014-07-23 2014-10-08 杭州华三通信技术有限公司 一种流量分配方法和网络设备
CN104967571A (zh) * 2015-06-08 2015-10-07 杭州华三通信技术有限公司 一种带宽调整方法及装置
CN107204933A (zh) * 2016-03-16 2017-09-26 华为技术有限公司 分布式流量调节方法及装置
CN108107730A (zh) * 2017-12-17 2018-06-01 北京世纪隆博科技有限责任公司 一种裂解炉多变量智能协调控制方法
US20180331955A1 (en) * 2016-01-26 2018-11-15 Huawei Technologies Co., Ltd. Service Traffic Allocation Method and Apparatus

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7957266B2 (en) * 2004-05-28 2011-06-07 Alcatel-Lucent Usa Inc. Efficient and robust routing independent of traffic pattern variability
US10075258B2 (en) * 2012-08-22 2018-09-11 Telefonaktiebolaget Lm Ericsson (Publ) Distributing path delay data in a connection-oriented communications network
WO2015021615A1 (zh) * 2013-08-14 2015-02-19 华为技术有限公司 路由流量调整方法、装置及控制器
CN106817299B (zh) * 2015-11-27 2019-11-29 新华三技术有限公司 软件定义网络的表项生成方法和装置以及报文转发方法
CN110199505B (zh) * 2016-12-21 2022-11-18 英国电讯有限公司 确定通信链路的带宽
CN109600322A (zh) * 2019-01-11 2019-04-09 国家电网有限公司 一种适用于电力骨干通信网的流量负载均衡控制方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101616061A (zh) * 2008-06-26 2009-12-30 华为技术有限公司 路径确定方法、路径确定装置及网络系统
CN101938484A (zh) * 2010-09-09 2011-01-05 奇智软件（北京）有限公司 一种分布式流量控制方法及系统
CN104092628A (zh) * 2014-07-23 2014-10-08 杭州华三通信技术有限公司 一种流量分配方法和网络设备
CN104967571A (zh) * 2015-06-08 2015-10-07 杭州华三通信技术有限公司 一种带宽调整方法及装置
US20180331955A1 (en) * 2016-01-26 2018-11-15 Huawei Technologies Co., Ltd. Service Traffic Allocation Method and Apparatus
CN107204933A (zh) * 2016-03-16 2017-09-26 华为技术有限公司 分布式流量调节方法及装置
CN108107730A (zh) * 2017-12-17 2018-06-01 北京世纪隆博科技有限责任公司 一种裂解炉多变量智能协调控制方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4030706A4 *

Also Published As

Publication number Publication date
CN112583729A (zh) 2021-03-30
CN112583729B (zh) 2023-11-28
EP4030706A1 (en) 2022-07-20
EP4030706A4 (en) 2022-11-02
US20220217089A1 (en) 2022-07-07

Similar Documents

Publication Publication Date Title
WO2021057659A1 (zh) 一种路径的流量分配方法、网络设备及网络系统
CN101939955B (zh) 分组网络中同步数据的链路饱和控制方法和系统
US7327681B2 (en) Admission control method in internet differentiated service network
KR100560748B1 (ko) 알피알 공평 메카니즘을 이용한 대역폭 할당 방법
CN100518144C (zh) 一种用于在分布的网元中均等地调整带宽的方法和系统
KR100484305B1 (ko) 이중 링에서의 부하 분산과 공평성 제공을 고려한 자원할당 방법
EP3605975A1 (en) Client service transmission method and device
WO2009110429A1 (ja) 動的帯域割当方法及び動的帯域割当装置
CN102318312A (zh) 控制带宽共享
Tschorsch et al. Tor is unfair—And what to do about it
US20050259689A1 (en) Providing soft bandwidth guarantees using elastic TCP-based tunnels
CN112152933B (zh) 一种发送流量的方法和装置
CN112825512A (zh) 负载均衡方法及装置
US7280560B2 (en) Differentiated services with multiple tagging levels
US20230336486A1 (en) Service flow scheduling method and apparatus, and system
Sadon et al. Dynamic hierarchical bandwidth allocation using Russian Doll Model in EPON
JP5349242B2 (ja) パケット交換装置及びパケット交換方法
JP2004289780A (ja) 光加入者線端局装置、光加入者線終端装置およびそれらによって用いられる帯域割当方法
Wu et al. Minimum cost maximum flow algorithm for upstream bandwidth allocation in OFDMA passive optical networks
PT2103055E (pt) Processo de optimização da partilha de uma pluralidade de recursos de rede entre uma pluralidade de fluxos de aplicação
JP5697212B2 (ja) 下り通信伝送帯域割り当て方法
JP5613261B2 (ja) 通信ネットワーク内で通信パイプを割り当てる方法および割当てユニット
JP6281347B2 (ja) パケット交換装置、及びパケット交換方法
JP5938939B2 (ja) パケット交換装置、パケット交換方法及び帯域制御プログラム
JP7193787B2 (ja) 通信システム、ブリッジ装置、通信方法、及びプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20868753

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2020868753

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2020868753

Country of ref document: EP

Effective date: 20220428