WO2016197727A1 - 一种数据传输方法及装置 - Google Patents

一种数据传输方法及装置 Download PDF

Info

Publication number
WO2016197727A1
WO2016197727A1 PCT/CN2016/080253 CN2016080253W WO2016197727A1 WO 2016197727 A1 WO2016197727 A1 WO 2016197727A1 CN 2016080253 W CN2016080253 W CN 2016080253W WO 2016197727 A1 WO2016197727 A1 WO 2016197727A1
Authority
WO
WIPO (PCT)
Prior art keywords
network feature
network
address
feature
congestion control
Prior art date
Application number
PCT/CN2016/080253
Other languages
English (en)
French (fr)
Inventor
姚杰
莫兰
陈文军
司玉美
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
Publication of WO2016197727A1 publication Critical patent/WO2016197727A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/12Avoiding congestion; Recovering from congestion
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/19Flow control; Congestion control at layers above the network layer
    • H04L47/193Flow control; Congestion control at layers above the network layer at the transport layer, e.g. TCP related

Definitions

  • the present invention relates to the field of communications, and in particular, to a data transmission method and apparatus.
  • the Transmission Control Protocol is a connection-oriented, reliable byte stream-based transport layer communication protocol.
  • Clients and servers can make data streams streamed in an orderly and reliable manner over the Internet (Internet) based on TCP.
  • Internet Internet
  • the Internet may be congested; if less TCP data packets are transmitted simultaneously in the Internet, the utilization of the transmission resources of the Internet is low. Therefore, in order to make the transmission performance of the TCP data packet higher, the transmission speed is faster, and the transmission is more stable, the size of the transmission window can be controlled according to the congestion control algorithm, and the impact of transmitting TCP data packets on the interconnection network is reduced.
  • a schematic diagram of a protocol stack structure includes an application layer, a TCP stack, and an Internet Protocol (IP) stack.
  • IP Internet Protocol
  • the server pre-configures multiple congestion control algorithms globally.
  • the TCP protocol stack receives the data packets transmitted by the application layer, it is encapsulated into TCP data packets, and a congestion control algorithm is obtained from multiple congestion control algorithms configured globally.
  • the TCP data packets of different applications on the server use the same congestion control algorithm.
  • the client connected to the server may come from different regions.
  • the network where the client is located in different regions the network condition when the client transmits TCP data packets is different.
  • the server can only use the unified congestion control algorithm to transmit all TCP data packets. It is not possible to perform different transmission processing on TCP data packets for different clients.
  • Embodiments of the present invention provide a data transmission method and apparatus, which can effectively perform different transmission processing on TCP data packets for networks in which different clients are located.
  • a data transmission method for a server, including:
  • the first network feature is a network feature of an area corresponding to the first IP address, where the network feature includes at least one of a packet loss rate, a delay, and a bandwidth;
  • the acquiring the first internet protocol IP address includes:
  • the first IP address is obtained from an IP address pre-stored by itself.
  • the acquiring the first network feature according to the first IP address includes:
  • the method further includes:
  • the IP network where the first IP address is located in the correspondence between the IP network segment and the network feature The network feature corresponding to the segment is updated to the second network feature.
  • the acquiring the first network feature according to the first IP address includes:
  • the first moment is a time when the first IP address is acquired or a first network feature is acquired according to the first IP address;
  • the method further includes:
  • the correspondence between the IP network segment, the network feature period, and the network feature is The network feature corresponding to the IP network segment where the first IP address is located is updated to the second network feature, where the first time is different from the second time, and the second time is in the network corresponding to the first network feature Within the feature period.
  • the updating of the network feature corresponding to the IP network segment where the first IP address is located to the second network feature includes:
  • the network feature corresponding to the first IP address is updated to the second network feature, and the number of times the network feature is not matched is the acquired first IP address.
  • the preset number of times that the network feature is different from the first network feature, and the preset threshold is a preset number of times that the acquired network feature of the first IP address is different from the first network feature.
  • a server including:
  • An obtaining unit configured to acquire a first Internet Protocol IP address, where the first IP address is used to identify an area where the client is located;
  • the acquiring unit is further configured to acquire, according to the first IP address, a first network feature, where the first network feature is a network feature of an area corresponding to the first IP address, where the network feature includes a packet loss rate, a time Extending at least one of the bandwidth;
  • the acquiring unit is further configured to acquire, according to the first network feature, a first congestion control algorithm corresponding to the first network feature, and a first congestion control algorithm, in a correspondence between a network feature and a congestion control algorithm. a parameter value, wherein different network features correspond to the same congestion control algorithm, and parameter values of the same congestion control algorithm are different, or different network features correspond to different congestion control algorithms;
  • a sending unit configured to send, according to the parameter values of the first congestion control algorithm and the first congestion control algorithm, a first transmission control protocol TCP data packet to a client of the first IP address corresponding area.
  • the acquiring unit is specifically configured to:
  • the first IP address is obtained from an IP address pre-stored by itself.
  • the obtaining unit is specifically configured to:
  • the server further includes:
  • an updating unit configured to: in the correspondence between the IP network segment and the network feature, the first IP, when the acquired second network feature of the first IP address is different from the first network feature The network feature corresponding to the IP network segment where the address is located is updated to the second network feature.
  • the acquiring unit is specifically configured to:
  • the first moment is a time when the first IP address is acquired or a first network feature is acquired according to the first IP address;
  • the server further includes:
  • an updating unit configured to: when the second network feature of the first IP address obtained by the second time is different from the first network feature, between the IP network segment, the network feature period, and the network feature Corresponding relationship, the network feature corresponding to the IP network segment where the first IP address is located is updated to the second network feature, the first time is different from the second time, and the second time is in the A network feature corresponds to a network feature period.
  • the updating unit is specifically configured to:
  • the network feature corresponding to the first IP address is updated to the second network feature, and the number of times the network feature is not matched is the acquired first IP address.
  • the preset number of times that the network feature is different from the first network feature, and the preset threshold is a preset number of times that the acquired network feature of the first IP address is different from the first network feature.
  • the data transmission method and device provided by the embodiments of the present invention.
  • the first IP address is obtained, where the first IP address is used to identify the area where the client is located; then, the first network feature is obtained according to the first IP address, where the first network feature is the first IP address.
  • the client in the address corresponding area sends the first TCP data packet.
  • the global congestion control algorithm is avoided in the prior art, and all TCP data packets can be transmitted only by using a unified congestion control algorithm.
  • the present invention obtains the congestion control applicable to the network feature according to the network characteristics of the area in which the client is located.
  • the algorithm, and the parameter value of the congestion control algorithm perform specific transmission processing on the first TCP data packet, so that the TCP data packet can be effectively processed for different networks according to the network where the different clients are located.
  • FIG. 2 is a schematic structural diagram of a network according to an embodiment of the present invention.
  • FIG. 3 is a flowchart of a data transmission method according to an embodiment of the present invention.
  • FIG. 4 is a flowchart of another data transmission method according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of a server according to an embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of another server according to an embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of another server according to an embodiment of the present invention.
  • the embodiment of the invention provides a schematic diagram of a network structure, as shown in FIG. 2, including:
  • TCP Client 10 TCP Client
  • Internet 11 TCP Server
  • Server 12 TCP Server
  • the client 10 and the server 12 are connected to the internet 11 respectively.
  • the client 10 is configured to request data of functions such as web browsing, video playing, chat communication, entertainment, and the like from the server 12 through the TCP, so that the user can browse the webpage, watch video, chat communication, entertainment, etc. through the client.
  • the client includes a variety of different applications, such as browsers, video players, chat software and online games, distributed in different areas such as residential areas, office areas or commercial areas.
  • the internetwork 11 is configured to provide communication between the client 10 and the server 12.
  • the internetwork includes an access network and a core network.
  • the server 12 is configured to provide data of webpage information, video files, communication, games, and the like to the client in response to requests from clients in different areas.
  • the server includes a web server, a video service Servers, communication servers, game servers, etc.
  • the client 10 is distributed in the range of the cell A, the range of the cell B, the range of the company C, and the range of the mall D.
  • Community A is an old community with a large number of elderly people, small bandwidth, large delay, and the network is more congested during the day, so it is better in the morning and evening.
  • Community B is a new community, with many young people, large bandwidth, small delay, better network during the day, and more congested in the morning and evening.
  • Company C is a new company with large bandwidth and small delay. The network is busy in the afternoon and evening, and it is very idle in the morning.
  • Mall D the bandwidth is large, the delay varies greatly, the bit error rate is high, the daytime is very congested, and it is very idle in the morning and evening.
  • An embodiment of the present invention provides a data transmission method, as shown in FIG. 3, including:
  • Step 101 Obtain a first Internet Protocol IP address, where the first IP address is used to identify an area where the client is located.
  • Step 102 Acquire a first network feature according to the first IP address, where the first network feature is a network feature of an area corresponding to the first IP address, where the network feature includes a packet loss rate, a delay, and a bandwidth. at least one.
  • Step 103 Acquire, according to the first network feature, a first congestion control algorithm corresponding to the first network feature, and a parameter value of the first congestion control algorithm, according to the correspondence between the network feature and the congestion control algorithm.
  • the different network features correspond to the same congestion control algorithm, and the parameter values of the same congestion control algorithm are different, or different network features correspond to different congestion control algorithms.
  • Step 104 Send a first transmission control protocol TCP data packet to the client of the first IP address corresponding area according to the parameter values of the first congestion control algorithm and the first congestion control algorithm.
  • the first IP address is obtained, where the first IP address is used to identify the area where the client is located; then, the first network feature is obtained according to the first IP address, where the first network feature is a network feature of the area corresponding to the first IP address, where the network feature includes at least one of a packet loss rate, a delay, and a bandwidth; and further, according to the first network feature, the corresponding relationship between the network feature and the congestion control algorithm a first congestion control algorithm corresponding to the first network feature, and a parameter value of the first congestion control algorithm, and finally, according to parameter values of the first congestion control algorithm and the first congestion control algorithm,
  • the client in the area corresponding to the first IP address sends the first TCP data packet.
  • the present invention obtains the congestion control algorithm applicable to the network feature according to the network feature, and the parameter value of the congestion control algorithm according to the network feature of the area where the client is located, and specifies the first TCP data packet.
  • the transmission processing can effectively perform different transmission processing on TCP data messages for the network where different clients are located.
  • An embodiment of the present invention provides a data transmission method, as shown in FIG. 4, including:
  • Step 201 The server acquires a first IP address.
  • the second TCP data packet sent by the client to the server the server receiving the second TCP data packet sent by the client, and acquiring the first IP address from the second TCP data packet, the second TCP
  • the data message includes the first IP address.
  • a TCP connection is established through the three-way handshake technique of TCP.
  • the server initializes the algorithm values of the globally configured congestion control algorithm and the congestion control algorithm.
  • the server obtains information such as the IP address and port number of the client.
  • the second TCP data packet is a message when establishing a TCP connection or a request message for requesting data from a server.
  • the first TCP data packet may further include a port number of the client.
  • the IP address may correspond to an area, and the clients in the area can be distinguished by the port number.
  • the server obtains the first IP address from an IP address pre-stored by the server.
  • Step 202 The server acquires the first network feature according to the first IP address.
  • the first network feature is a network feature of an area corresponding to the first IP address, where the network feature includes at least one of a packet loss rate, a delay, and a bandwidth.
  • the network feature corresponding to the first IP address is determined as the first network feature, and the first IP address is in the first, from a correspondence between an IP network segment and a network feature.
  • the IP network segment corresponding to the network feature can be configured in the form of a configuration file in the server or in the database of the server.
  • the server pre-configures the area information table and the area model table.
  • the area information table includes a correspondence between an IP network segment, a port range, an area identification code, and an area name of at least one area. As shown in Table 1, the area information table.
  • IP network segment Port range Area identification code Area name 10.71.162.0/24 1000 ⁇ 5000 1 Community A 10.70.102.0/24 5000 ⁇ 30000 2 Community B 16.8.205.0/24 4000 ⁇ 55862 3 Company C 182.50.0.0/16 1000 ⁇ 38435 4 Mall D > .... .... ....
  • the regional model table includes network features of at least one region.
  • the network characteristics include packet loss rate, delay, and bandwidth.
  • the network features also include bit error rate and jitter characteristics.
  • the jitter feature is that the network in which the client is located has a significant change in network characteristics such as packet loss rate, delay, and bandwidth in a short period of time. For example, the bandwidth of the network in which the client is located within 1 minute has the largest bandwidth and the smallest bandwidth. As shown in Table 2, the regional model table.
  • the area model table may further include a network feature period, and one area identifier code may correspond to a plurality of different network feature periods, and each network feature period corresponds to a different network feature.
  • the server may obtain the first time, where the first time is the time when the first IP address is obtained or the first network feature is obtained according to the first IP address; from the IP network segment, the network Determining, in the correspondence between the feature period and the network feature, that the first moment is in any network feature period corresponding to the first IP address, and the first IP address corresponds to multiple network feature periods; from the IP network Determining, in the correspondence between the segment, the network feature period, and the network feature, the network feature of the any network feature period in which the first moment corresponding to the first IP address is located is the first network And the first time in the network feature period corresponding to the first network feature, the first IP address is in an IP network segment corresponding to the first network feature.
  • the server first queries the area information table according to the first IP address of the client, and obtains the area identifier code corresponding to the first IP address of the client.
  • the server may query the area information table according to the first IP address and the port number of the client, and obtain the area identifier code corresponding to the first IP address of the client.
  • the area information table of the table 1 is obtained, and the first IP address of the client and the area identifier code corresponding to the port number are 4, and the area identifier code is The corresponding area of 4 is mall D.
  • the server queries the area model table according to the area identifier code to obtain the first network feature.
  • the first network feature is a network feature of an area corresponding to the area identification code.
  • the network feature period corresponding to the first moment is obtained according to the area identifier code and the first time query area model table, where the first network moment corresponding to the network feature period is acquired.
  • the server queries the area model table of the table 2 according to the area identifier code 4, and obtains the network feature of the mall D corresponding to the area identifier code 4.
  • the network feature of the mall D corresponding to the area identifier code 4 is 9:00 am.
  • Step 203 The server obtains, according to the first network feature, a first congestion control algorithm corresponding to the first network feature, and a parameter value of the first congestion control algorithm, according to the corresponding feature of the network feature and the congestion control algorithm.
  • Different network features correspond to the same congestion control algorithm, and the parameter values of the same congestion control algorithm are different, or different network features correspond to different congestion control algorithms.
  • the correspondence between the network feature and the congestion control algorithm may be configured in the form of a configuration file in the server or in a database of the server.
  • the congestion control algorithm relationship table includes a correspondence between a network feature of at least one area and a congestion control algorithm, and a correspondence between the congestion control algorithm and parameters of the congestion control algorithm. As shown in Table 3, the congestion control algorithm relationship table.
  • the westwood+ algorithm when the network characteristics of the area are large bandwidth, large delay, high packet loss, and high bit error rate, the westwood+ algorithm can be used.
  • the FastTCP algorithm When the network characteristics of the area are small bandwidth, stable delay, and low packet loss, the FastTCP algorithm can be used.
  • the cubic algorithm When the network characteristics of the area are large bandwidth, small delay, and low packet loss, the cubic algorithm can be used.
  • the hybla algorithm can be used. Table 3 is only a schematic illustration, and other congestion control algorithms may also be included in the actual application.
  • the administrator can configure the area information table, the area model table, and the congestion control algorithm relationship table to the server through a configuration file or an application programming interface (API).
  • the administrator can also dynamically modify the congestion control algorithm relationship table according to the network characteristics of the area to implement dynamic configuration of the congestion control algorithm relation table.
  • the congestion control algorithm in the congestion control algorithm relation table is a congestion control algorithm that the server has globally configured and can use.
  • the corresponding relationship in the relationship table of the congestion control algorithm may be a correspondence between the implementation suggestions provided by the provider of the congestion control algorithm in the relationship table of the congestion control algorithm, or a different congestion control algorithm according to the specific network feature and the The algorithm parameters corresponding to the congestion control algorithm are tested multiple times, and the congestion control algorithm with the best test effect is selected, and the correspondence between the network characteristics and the congestion control algorithm is established.
  • the server queries the congestion control algorithm relationship table according to the first network feature, and obtains a first congestion control algorithm corresponding to the first network feature, and a parameter value of the first congestion control algorithm.
  • Step 204 The server sends a first transmission control protocol TCP data packet to the client of the first IP address corresponding area according to the parameter values of the first congestion control algorithm and the first congestion control algorithm.
  • the server initializes the congestion control algorithm according to the congestion control algorithm corresponding to the first network feature and the parameter value of the congestion control algorithm, and transmits a first TCP data packet to the client. It should be noted that, if the client requests data from the server, the first TCP data packet includes data requested by the client. Alternatively, the client does not request data from the server, and the first TCP data message includes data that the server simultaneously sends to multiple clients.
  • the client sends a request to the server to access the TCP data packet of Sina Weibo, and the server transmits the TCP response to the Sina Weibo to the client according to the westwood+ algorithm corresponding to the network feature of the area.
  • the data message, the TCP data message that responds to the Sina Weibo includes the user data that the user needs Sina Weibo.
  • Step 205 The server receives an acknowledgement message sent by the client.
  • the server After the server transmits the first TCP data packet to the client according to the congestion control algorithm corresponding to the first network feature, the client needs to send an acknowledgement message (ACK) to the server.
  • ACK acknowledgement message
  • the server monitors network data of the current transmission process in real time, for example, packet loss rate, delay, and bandwidth.
  • the period between the sending of the TCP data packet from the server to the client and the receipt of the ACK message sent by the server to the client is set to the delay.
  • the packet loss rate during transmission is counted by the difference between the number of TCP data packets sent by the server to the client and the number of acknowledgment messages sent by the server.
  • the server can calculate the bandwidth of the current transmission process according to the number of bytes of the transmitted TCP data packet and the delay information. Step 206 or step 207 is performed.
  • Step 206 When the second network feature of the first IP address obtained by the server is different from the first network feature, the first IP address in the correspondence between the IP network segment and the network feature The network feature corresponding to the IP network segment is updated to the second network feature.
  • Step 207 When the second network feature of the first IP address acquired by the server at the second time is different from the first network feature, the pair between the IP network segment, the network feature period, and the network feature In the relationship, the network feature corresponding to the IP network segment where the first IP address is located is updated to the second network feature.
  • the first moment is different from the second moment, and the second moment is within a network feature period corresponding to the first network feature.
  • the network feature corresponding to the first IP address is updated to the second network feature, and the number of times the network feature is not matched is the obtained first
  • the network feature of the IP address is different from the first network feature
  • the preset threshold is a preset number of times that the acquired network feature of the first IP address is different from the first network feature.
  • the server may use the global configuration.
  • the congestion control algorithm and the parameter values of the congestion control algorithm may be used.
  • the first IP address is obtained, where the first IP address is used to identify the area where the client is located; then, the first network feature is obtained according to the first IP address, where the first network feature is a network feature of the area corresponding to the first IP address, where the network feature includes at least one of a packet loss rate, a delay, and a bandwidth; and further, according to the first network feature, the corresponding relationship between the network feature and the congestion control algorithm a first congestion control algorithm corresponding to the first network feature, and a parameter value of the first congestion control algorithm, and finally, according to parameter values of the first congestion control algorithm and the first congestion control algorithm,
  • the client in the area corresponding to the first IP address sends the first TCP data packet.
  • the global congestion control algorithm is avoided in the prior art, and all TCP data packets can be transmitted only by using a unified congestion control algorithm.
  • the present invention obtains the congestion control applicable to the network feature according to the network characteristics of the area in which the client is located.
  • the algorithm, and the parameter value of the congestion control algorithm perform specific transmission processing on the first TCP data packet, so that the TCP data packet can be effectively processed for different networks according to the network where the different clients are located.
  • the embodiment of the present invention provides a server 30, as shown in FIG. 5, including:
  • the obtaining unit 301 is configured to obtain a first internet protocol IP address, where the first IP address is used to identify an area where the client is located;
  • the obtaining unit 301 is further configured to acquire, according to the first IP address, a first network feature, where the first network feature is a network feature of an area corresponding to the first IP address, and the network feature includes At least one of a packet rate, a delay, and a bandwidth;
  • the obtaining unit 301 is further configured to acquire, according to the correspondence between the network feature and the congestion control algorithm, the first congestion control algorithm corresponding to the first network feature, and the first congestion control algorithm according to the first network feature.
  • the parameter value wherein different network features correspond to the same congestion control algorithm, and the parameter values of the same congestion control algorithm are different, or different network features correspond to different congestion control algorithms;
  • the sending unit 302 is configured to send, according to the parameter values of the first congestion control algorithm and the first congestion control algorithm, a first transmission control protocol TCP data packet to a client in the first IP address corresponding area.
  • the first IP address is obtained, where the first IP address is used to identify the area where the client is located; then, the first network feature is obtained according to the first IP address, where the first network feature is a network feature of the area corresponding to the first IP address, where the network feature includes at least one of a packet loss rate, a delay, and a bandwidth; and further, according to the first network feature, the corresponding relationship between the network feature and the congestion control algorithm a first congestion control algorithm corresponding to the first network feature, and a parameter value of the first congestion control algorithm, and finally, according to parameter values of the first congestion control algorithm and the first congestion control algorithm,
  • the client in the area corresponding to the first IP address sends the first TCP data packet.
  • the global congestion control algorithm is avoided in the prior art, and all TCP data packets can be transmitted only by using a unified congestion control algorithm.
  • the present invention obtains the congestion control applicable to the network feature according to the network characteristics of the area in which the client is located.
  • the algorithm, and the parameter value of the congestion control algorithm perform specific transmission processing on the first TCP data packet, so that the TCP data packet can be effectively processed for different networks according to the network where the different clients are located.
  • the obtaining unit 301 is specifically configured to:
  • the first IP address is obtained from an IP address pre-stored by itself.
  • the obtaining unit 301 is specifically configured to:
  • the server 30 further includes:
  • the updating unit 303 is configured to: when the acquired second network feature of the first IP address is different from the first network feature, the first relationship between the IP network segment and the network feature, the first The network feature corresponding to the IP network segment where the IP address is located is updated to the second network feature.
  • the obtaining unit 301 is specifically configured to:
  • the first moment is a time when the first IP address is acquired or a first network feature is acquired according to the first IP address;
  • the updating unit 303 is configured to: when the second network feature of the first IP address acquired at the second time is different from the first network feature, between the IP network segment, the network feature period, and the network feature Corresponding relationship, the network feature corresponding to the IP network segment where the first IP address is located is updated to the second network feature, the first time is different from the second time, and the second time is in the A network feature corresponds to a network feature period.
  • the update unit 303 is specifically configured to:
  • the network feature corresponding to the first IP address is updated to the second network feature, and the number of times the network feature is not matched is the acquired first IP address.
  • the preset number of times that the network feature is different from the first network feature, and the preset threshold is a preset number of times that the acquired network feature of the first IP address is different from the first network feature.
  • the embodiment of the present invention provides a server 40, as shown in FIG. 7, comprising:
  • a memory 401 configured to store program code
  • the processor 402 is configured to invoke the program code stored in the memory 401 to execute the following method:
  • the first network feature is a network feature of an area corresponding to the first IP address, where the network feature includes at least one of a packet loss rate, a delay, and a bandwidth;
  • the transmitter 403 is configured to send, according to the parameter values of the first congestion control algorithm and the first congestion control algorithm, a first transmission control protocol TCP data packet to a client of the first IP address corresponding area.
  • a bus 404 is configured to connect with the memory 401, the processor 402, and the transmitter 403 to complete communication with each other.
  • the first IP address is obtained, where the first IP address is used to identify the area where the client is located; then, the first network feature is obtained according to the first IP address, where the first network feature is a network feature of the area corresponding to the first IP address, where the network feature includes at least one of a packet loss rate, a delay, and a bandwidth; and further, according to the first network feature, the corresponding relationship between the network feature and the congestion control algorithm a first congestion control algorithm corresponding to the first network feature, and a parameter value of the first congestion control algorithm, and finally, according to parameter values of the first congestion control algorithm and the first congestion control algorithm,
  • the client in the area corresponding to the first IP address sends the first TCP data packet.
  • the global congestion control algorithm is avoided in the prior art, and all TCP data packets can be transmitted only by using a unified congestion control algorithm.
  • the present invention obtains the congestion control applicable to the network feature according to the network characteristics of the area in which the client is located.
  • the algorithm, and the parameter value of the congestion control algorithm perform specific transmission processing on the first TCP data packet, so that the TCP data packet can be effectively processed for different networks according to the network where the different clients are located.
  • the processor 402 is specifically configured to:
  • the first IP address is obtained from an IP address pre-stored by itself.
  • the processor 402 is specifically configured to:
  • the processor 402 is further configured to: when the acquired second network feature of the first IP address is different from the first network feature, in a correspondence between the IP network segment and a network feature, The network feature corresponding to the IP network segment where the first IP address is located is updated to the second network feature.
  • the processor 402 is specifically configured to:
  • the first moment is a time when the first IP address is acquired or a first network feature is acquired according to the first IP address;
  • the processor 402 is further configured to: when the second network feature of the first IP address obtained by receiving the third TCP data packet at the second moment is different from the first network feature, the IP network segment And the corresponding relationship between the network feature period and the network feature, the network feature corresponding to the IP network segment where the first IP address is located is updated to the second network feature, and the first time is different from the second time The second moment is within a network feature period corresponding to the first network feature.
  • the processor 402 is specifically configured to:
  • the network feature corresponding to the first IP address is updated to the second network feature, and the number of times the network feature is not matched is the acquired first IP address.
  • the preset number of times that the network feature is different from the first network feature, and the preset threshold is a preset number of times that the acquired network feature of the first IP address is different from the first network feature.
  • the congestion control algorithm according to the present invention includes a westwood+ algorithm, a FastTCP algorithm, a cubic algorithm, and a hybla algorithm.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules or units is only a logical function division.
  • there may be another division manner for example, multiple units or components may be used. Combinations can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本发明实施例公开了一种数据传输方法及装置,涉及通信领域,能够有效地针对不同客户端所处的网络在不同时刻进行不同的传输处理。获取第一IP地址,第一IP地址用于标识客户端所处的区域;根据第一IP地址获取第一网络特征,第一网络特征为第一IP地址对应的区域的网络特征;从网络特征与拥塞控制算法的对应关系中,根据第一网络特征获取第一网络特征对应的第一拥塞控制算法,以及第一拥塞控制算法的参数值;根据第一拥塞控制算法和第一拥塞控制算法的参数值,向第一IP地址对应区域的客户端发送第一TCP数据报文。本发明用于传输数据报文。

Description

一种数据传输方法及装置
本申请要求于2015年6月11日提交中国专利局、申请号为201510319516.7,发明名称为“一种数据传输方法及装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本发明涉及通信领域,尤其涉及一种数据传输方法及装置。
背景技术
传输控制协议(Transmission Control Protocol,TCP)是一种面向连接的、可靠的基于字节流的传输层通信协议。客户端和服务器可以根据TCP使数据流在互联网络(Internet)中有序而可靠的传输。但是,如果在互联网络中同时传输较多的TCP数据报文,互联网络可能产生拥塞;如果在互联网络中同时传输较少的TCP数据报文,导致互联网络的传输资源的利用率较低。因此,为了使TCP数据报文的传输性能更高、传输速度更快和传输更稳定,可以根据拥塞控制算法,对传输窗口的大小进行控制,减少传输TCP数据报文对互联网络的影响。
现有技术中,如图1所示,协议栈结构示意图,包括应用层、TCP栈和网际协议(Internet Protocol,IP)栈。服务器预先全局配置多个拥塞控制算法,当TCP协议栈接收到应用层传输的数据报文后,封装成TCP数据报文,从全局配置的多个拥塞控制算法中获取一个拥塞控制算法,使得所述服务器上不同应用的TCP数据报文使用同一个拥塞控制算法。
但是,服务器所连接的客户端可能来自不同区域,不同区域的客户端所处的网络,客户端传输TCP数据报文时的网络情况是不同的。通过全局配置拥塞控制算法,服务器只能使用统一的拥塞控制算法传输所有TCP数据报文,无法针对不同客户端所处的网络对TCP数据报文进行不同的传输处理。
发明内容
本发明的实施例提供一种数据传输方法及装置,能够有效地针对不同客户端所处的网络对TCP数据报文进行不同的传输处理。
为达到上述目的,本发明的实施例采用如下技术方案:
第一方面,提供一种数据传输方法,应用于服务器,包括:
获取第一网际协议IP地址,所述第一IP地址用于标识客户端所处的区域;
根据所述第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;
从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,其中,不同的网络特征对应同一拥塞控制算法,且所述同一拥塞控制算法的参数值不同,或者,不同的网络特征对应不同的拥塞控制算法;
根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一传输控制协议TCP数据报文。
结合第一方面,在第一种可实现方式中,所述获取第一网际协议IP地址包括:
从所述客户端发送的第二TCP数据报文中获取所述第一IP地址,所述第二TCP数据报文包括所述第一IP地址;
或,从自身预先存储的IP地址中获取所述第一IP地址。
结合第一方面或第一种可实现方式,在第二种可实现方式中,所述根据所述第一IP地址获取第一网络特征包括:
从IP网段和网络特征之间的对应关系中,将与所述第一IP地址对应的网络特征确定为所述第一网络特征,所述第一IP地址在所述第一网络特征对应的IP网段内。
结合第二种可实现方式,在第三种可实现方式中,所述方法还包括:
当获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征。
结合第一方面或第一种可实现方式,在第四种可实现方式中,所述根据所述第一IP地址获取第一网络特征包括:
获取第一时刻,所述第一时刻为获取到所述第一IP地址的时刻或根据所述第一IP地址获取第一网络特征的时刻;
从IP网段、网络特征时段和网络特征之间的对应关系中,确定所述第一时刻在所述第一IP地址对应的任一网络特征时段内,所述第一IP地址对应多个网络特征时段;
从IP网段、网络特征时段和网络特征之间的对应关系中,将与所述第一IP地址对应的所述第一时刻所在的所述任一网络特征时段的网络特征确定为所述第一网络特征,所述第一时刻在所述第一网络特征对应的网络特征时段内,所述第一IP地址在所述第一网络特征对应的IP网段内。
结合第四种可实现方式,在第五种可实现方式中,所述方法还包括:
当在第二时刻获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段、网络特征时段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征,所述第一时刻与所述第二时刻不同,所述第二时刻在所述第一网络特征对应的网络特征时段内。
结合第三种或第五种可实现方式,在第六种可实现方式中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征包括:
当网络特征不匹配的次数大于预设阈值时,所述第一IP地址对应的网络特征更新为所述第二网络特征,所述网络特征不匹配的次数为获取的所述第一IP地址的网络特征与所述第一网络特征不同的次数,所述预设阈值为获取的所述第一IP地址的网络特征与所述第一网络特征不同的预设次数。
第二方面,提供一种服务器,包括:
获取单元,用于获取第一网际协议IP地址,所述第一IP地址用于标识客户端所处的区域;
所述获取单元还用于根据所述第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;
所述获取单元还用于从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,其中,不同的网络特征对应同一拥塞控制算法,且所述同一拥塞控制算法的参数值不同,或者,不同的网络特征对应不同的拥塞控制算法;
发送单元,用于根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一传输控制协议TCP数据报文。
结合第二方面,在第一种可实现方式中,所述获取单元具体用于:
从所述客户端发送的第二TCP数据报文中获取所述第一IP地址,所述第二TCP数据报文包括所述第一IP地址;
或,从自身预先存储的IP地址中获取所述第一IP地址。
结合第二方面或第一种可实现方式,在第二种可实现方式中,所述获取单元具体用于:
从IP网段和网络特征之间的对应关系中,将与所述第一IP地址对应的网络特征确定为所述第一网络特征,所述第一IP地址在所述第一网络特征对应的IP网段内。
结合第二种可实现方式,在第三种可实现方式中,所述服务器还包括:
更新单元,用于当获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征。
结合第二方面或第一种可实现方式,在第四种可实现方式中,所述获取单元具体用于:
获取第一时刻,所述第一时刻为获取到所述第一IP地址的时刻或根据所述第一IP地址获取第一网络特征的时刻;
从IP网段、网络特征时段和网络特征之间的对应关系中,确定所述第一时刻在所述第一IP地址对应的任一网络特征时段内,所述第一IP地址对应多个网络特征时段;
从IP网段、网络特征时段和网络特征之间的对应关系中,将与所述第一IP地址对应的所述第一时刻所在的所述任一网络特征时段的网络特征确定为所述第一网络特征,所述第一时刻在所述第一网络特征对应的网络特征时段内,所述第一IP地址在所述第一网络特征对应的IP网段内。
结合第四种可实现方式,在第五种可实现方式中,所述服务器还包括:
更新单元,用于当在第二时刻通过获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段、网络特征时段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征,所述第一时刻与所述第二时刻不同,所述第二时刻在所述第一网络特征对应的网络特征时段内。
结合第三种或第五种可实现方式,在第六种可实现方式中,所述更新单元具体用于:
当网络特征不匹配的次数大于预设阈值时,所述第一IP地址对应的网络特征更新为所述第二网络特征,所述网络特征不匹配的次数为获取的所述第一IP地址的网络特征与所述第一网络特征不同的次数,所述预设阈值为获取的所述第一IP地址的网络特征与所述第一网络特征不同的预设次数。
本发明实施例提供的数据传输方法及装置。首先,获取第一IP地址,所述第一IP地址用于标识客户端所处的区域;然后,根据该第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;再从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,最后,根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一TCP数据报文。避免现有技术中全局配置拥塞控制算法,只能使用统一的拥塞控制算法传输所有TCP数据报文,本发明通过客户端所处的区域的网络特征,根据网络特征获取该网络特征适用的拥塞控制算法,以及该拥塞控制算法的参数值,对该第一TCP数据报文进行特定的传输处理,从而能够有效地针对不同客户端所处的网络对TCP数据报文进行不同的传输处理。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为现有技术提供一种协议栈结构示意图;
图2为本发明实施例提供一种网络结构示意图;
图3为本发明实施例提供一种数据传输方法流程图;
图4为本发明实施例提供另一种数据传输方法流程图;
图5为本发明实施例提供一种服务器结构示意图;
图6为本发明实施例提供另一种服务器结构示意图;
图7为本发明实施例提供又一种服务器结构示意图。
具体实施方式
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
实施例1
本发明实施例提供一种网络结构示意图,如图2所示,包括:
客户端10(TCP Client)、互联网络11和服务器12(TCP Server)。客户端10和服务器12分别与互联网络11连接。
所述客户端10,用于通过TCP向所述服务器12请求网页浏览、视频播放、聊天交流和娱乐休闲等功能的数据,以便于用户通过客户端浏览网页、收看视频、聊天交流和娱乐休闲等。该客户端包括浏览器、视频播放器、聊天软件和网络游戏等多种不同应用,分布在住宅区域、办公区域或商业区域等不同区域。
所述互联网络11,用于为所述客户端10和所述服务器12之间提供通信。该互联网络包括接入网络和核心网络等。
所述服务器12,用于响应不同区域的客户端的请求,向客户端提供网页信息、视频文件、交流、游戏等功能的数据。该服务器包括网页服务器、视频服 务器、交流服务器和游戏服务器等。
其中,例如客户端10分布在小区A的范围内、小区B的范围内、公司C的范围内和商场D的范围内。小区A为老社区,老年人居多,带宽小,时延大,网络白天较拥塞,早晚比较好。小区B为新社区,年轻人居多,带宽大,时延小,网络白天比较好,早晚较拥塞。公司C为新公司,带宽大,时延小,网络下午和晚上较繁忙,上午非常空闲。商场D,带宽较大,时延变化大,误码率高,白天非常拥塞,早晚非常空闲。
实施例2
本发明实施例提供一种数据传输方法,如图3所示,包括:
步骤101、获取第一网际协议IP地址,所述第一IP地址用于标识客户端所处的区域。
步骤102、根据所述第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个。
步骤103、从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值。
其中,不同的网络特征对应同一拥塞控制算法,且所述同一拥塞控制算法的参数值不同,或者,不同的网络特征对应不同的拥塞控制算法。
步骤104、根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一传输控制协议TCP数据报文。
这样一来,首先,获取第一IP地址,所述第一IP地址用于标识客户端所处的区域;然后,根据该第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;再从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,最后,根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一TCP数据报文。避免现有技术中全局配置拥塞控制算法,只能使用统一的拥塞控制算法传输所有 TCP数据报文,本发明通过客户端所处的区域的网络特征,根据网络特征获取该网络特征适用的拥塞控制算法,以及该拥塞控制算法的参数值,对该第一TCP数据报文进行特定的传输处理,从而能够有效地针对不同客户端所处的网络对TCP数据报文进行不同的传输处理。
实施例3
本发明实施例提供一种数据传输方法,如图4所示,包括:
步骤201、服务器获取第一IP地址。
可选的,客户端向服务器发送的第二TCP数据报文,服务器接收客户端发送的第二TCP数据报文,从该第二TCP数据报文中获取第一IP地址,所述第二TCP数据报文包括所述第一IP地址。
客户端和服务器之间传输TCP数据报文之前,需要通过TCP的三次握手(three-way handshake)技术建立TCP连接。在连接建立过程中,服务器初始化全局配置的拥塞控制算法和拥塞控制算法的算法值。连接建立完成后,服务器得到客户端的IP地址和端口号等信息。所述第二TCP数据报文为建立TCP连接时的报文或向服务器请求数据的请求报文。所述第一TCP数据报文还可以包括客户端的端口号。IP地址可能对应着一个区域,区域内的客户端可以用端口号区别。
可选的,服务器从自身预先存储的IP地址中获取所述第一IP地址。
步骤202、服务器根据第一IP地址获取第一网络特征。
所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个。
可选的,从IP网段和网络特征之间的对应关系中,将与所述第一IP地址对应的网络特征确定为所述第一网络特征,所述第一IP地址在所述第一网络特征对应的IP网段内。IP网段和网络特征之间的对应关系可以以配置文件的形式配置在服务器中,或者配置在服务器的数据库中。
示例的,假设服务器预先配置区域信息表和区域模型表。
所述区域信息表包括至少一个区域的IP网段、端口范围、区域标识码和区域名称之间的对应关系。如表1所示,区域信息表。
表1区域信息表
IP网段 端口范围 区域标识码 区域名称
10.71.162.0/24 1000~5000 1 小区A
10.70.102.0/24 5000~30000 2 小区B
16.8.205.0/24 4000~55862 3 公司C
182.50.0.0/16 1000~38435 4 商场D
…… …… …… ……
所述区域模型表包括至少一个区域的网络特征。所述网络特征包括丢包率、时延和带宽。所述网络特征还包括误码率和抖动特征。所述抖动特征为客户端所处的网络在较短的时段内丢包率、时延和带宽等网络特征出现明显的变化。例如,在1分钟内客户端所处的网络的带宽出现最大带宽和最小带宽的情况。如表2所示,区域模型表。
表2区域模型表
Figure PCTCN2016080253-appb-000001
需要说明的是,区域模型表还可以包括网络特征时段,一个区域标识码可以对应多个不同的网络特征时段,每个网络特征时段对应不同的网络特征。
可选的,服务器可以先获取第一时刻,所述第一时刻为获取到所述第一IP地址的时刻或根据所述第一IP地址获取第一网络特征的时刻;从IP网段、网络特征时段和网络特征之间的对应关系中,确定所述第一时刻在所述第一IP地址对应的任一网络特征时段内,所述第一IP地址对应多个网络特征时段;从IP网段、网络特征时段和网络特征之间的对应关系中,将与所述第一IP地址对应的所述第一时刻所在的所述任一网络特征时段的网络特征确定为所述第一网络 特征,所述第一时刻在所述第一网络特征对应的网络特征时段内,所述第一IP地址在所述第一网络特征对应的IP网段内。
具体的,服务器先根据客户端的第一IP地址查询区域信息表,得到所述客户端的第一IP地址对应的区域标识码。可选的,服务器可以根据所述客户端的第一IP地址和端口号查询区域信息表,得到所述客户端的第一IP地址对应的区域标识码。
假设客户端的第一IP地址为182.50.0.10,端口号为1010,查询表1区域信息表,得到所述客户端的第一IP地址和所述端口号对应的区域标识码为4,该区域标识码4对应的区域为商场D。
服务器根据所述区域标识码查询区域模型表,得到第一网络特征。所述第一网络特征为所述区域标识码对应的区域的网络特征。可选的,根据所述区域标识码和第一时刻查询区域模型表,得到所述第一时刻对应的网络特征时段,所述网络特征时段对应的第一网络特征,所述第一时刻为获取到所述第一IP地址的时刻或根据所述区域标识码查询区域模型表的时刻。
例如,服务器根据所述区域标识码4查询表2区域模型表,得到所述区域标识码4对应的商场D的网络特征,所述区域标识码4对应的商场D的网络特征为上午9点到下午5点的网络特征,此时为上午10点,则所述区域标识码4对应的商场D的网络特征为丢包率>=2%、时延>=100ms和带宽>=100M。
步骤203、服务器从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值。
不同的网络特征对应同一拥塞控制算法,且所述同一拥塞控制算法的参数值不同,或者,不同的网络特征对应不同的拥塞控制算法。
网络特征与拥塞控制算法的对应关系可以以配置文件的形式配置在服务器中,或者配置在服务器的数据库中。
示例的,假设服务器预先配置拥塞控制算法关系表。所述拥塞控制算法关系表包括至少一个区域的网络特征与拥塞控制算法的对应关系,以及所述拥塞控制算法与所述拥塞控制算法的参数的对应关系。如表3所示,拥塞控制算法关系表。
表3拥塞控制算法关系表
Figure PCTCN2016080253-appb-000002
从表3中可以看出,当区域的网络特征为带宽大、时延大、丢包高和误码率高等,可以采用westwood+算法。当区域的网络特征为带宽小、时延稳定和丢包低等,可以采用FastTCP算法。当区域的网络特征为带宽大、时延小和丢包低,可以采用cubic算法。当区域的网络特征为时延变化大,丢包随机,可以采用hybla算法。表3只是示意性说明,实际应用中还可以包括其他的拥塞控制算法。
需要说明的是,管理员可以通过配置文件或应用程序编程接口(Application Programming Interface,API)将区域信息表、区域模型表和拥塞控制算法关系表配置到服务器。管理员也可以根据区域的网络特征动态的修改拥塞控制算法关系表,实现拥塞控制算法关系表的动态配置。拥塞控制算法关系表中的拥塞控制算法为服务器已经全局配置并可以使用的拥塞控制算法。拥塞控制算法关系表中的对应关系可以是提供拥塞控制算法关系表中的拥塞控制算法的提供方提供的实施建议建立的对应关系,也可以是根据具体的网络特征采用不同的拥塞控制算法以及该拥塞控制算法对应的算法参数进行多次测试,选择测试效果最佳的拥塞控制算法,建立的网络特征与拥塞控制算法的对应关系。
服务器根据所述第一网络特征查询拥塞控制算法关系表,得到所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值。
服务器根据所述区域标识码4对应的商场D的网络特征查询拥塞控制算法关系表,得到所述区域的网络特征对应的拥塞控制算法为westwood+以及westwood+算法对应的参数γ=60。
步骤204、服务器根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一传输控制协议TCP数据报文。
服务器根据所述第一网络特征对应的所述拥塞控制算法和所述拥塞控制算法的参数值,初始化所述拥塞控制算法,向所述客户端传输第一TCP数据报文。需要说明的是,如果客户端向服务器请求数据,所述第一TCP数据报文包括客户端请求的数据。或者,客户端没有向服务器请求数据,第一TCP数据报文包括服务器向多个客户端同时发送的数据。
假设用户需要访问新浪微博,客户端向服务器发送的请求访问新浪微博的TCP数据报文,服务器根据所述区域的网络特征对应的westwood+算法向所述客户端传输响应访问新浪微博的TCP数据报文,该响应访问新浪微博的TCP数据报文包括用户需要新浪微博的用户数据。
步骤205、服务器接收客户端发送的确认消息。
在服务器根据所述第一网络特征对应的拥塞控制算法向所述客户端传输第一TCP数据报文后,客户端需要向服务器发送确认消息(ACK)。
进一步的,服务器实时监测当前传输过程的网络数据,例如,丢包率、时延和带宽等。从服务器向客户端发送TCP数据报文,到服务器收到客户端发送的确认消息ACK之间的时段设置为时延。通过服务器向客户端发送TCP数据报文的数量,和服务器收到客户端发送的确认消息的数量之差,统计出传输过程中的丢包率。服务器可以根据传输的TCP数据报文的字节数量以及时延信息,计算出当前传输过程的带宽情况。执行步骤206或步骤207。
步骤206、当服务器获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征。
步骤207、当服务器在第二时刻获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段、网络特征时段和网络特征之间的对 应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征。
所述第一时刻与所述第二时刻不同,所述第二时刻在所述第一网络特征对应的网络特征时段内。
进一步的,当网络特征不匹配的次数大于预设阈值时,所述第一IP地址对应的网络特征更新为所述第二网络特征,所述网络特征不匹配的次数为获取的所述第一IP地址的网络特征与所述第一网络特征不同的次数,所述预设阈值为获取的所述第一IP地址的网络特征与所述第一网络特征不同的预设次数。
特别的,如果服务器没有获取到向第一IP地址对应区域的客户端发送第一TCP数据报文所需要的第一拥塞控制算法和所述第一拥塞控制算法的参数值,服务器可以使用全局配置的拥塞控制算法和该拥塞控制算法的参数值。
这样一来,首先,获取第一IP地址,所述第一IP地址用于标识客户端所处的区域;然后,根据该第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;再从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,最后,根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一TCP数据报文。避免现有技术中全局配置拥塞控制算法,只能使用统一的拥塞控制算法传输所有TCP数据报文,本发明通过客户端所处的区域的网络特征,根据网络特征获取该网络特征适用的拥塞控制算法,以及该拥塞控制算法的参数值,对该第一TCP数据报文进行特定的传输处理,从而能够有效地针对不同客户端所处的网络对TCP数据报文进行不同的传输处理。
实施例4
本发明实施例提供一种服务器30,如图5所示,包括:
获取单元301,用于获取第一网际协议IP地址,所述第一IP地址用于标识客户端所处的区域;
所述获取单元301还用于根据所述第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢 包率、时延和带宽中至少一个;
所述获取单元301还用于从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,其中,不同的网络特征对应同一拥塞控制算法,且所述同一拥塞控制算法的参数值不同,或者,不同的网络特征对应不同的拥塞控制算法;
发送单元302,用于根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一传输控制协议TCP数据报文。
这样一来,首先,获取第一IP地址,所述第一IP地址用于标识客户端所处的区域;然后,根据该第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;再从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,最后,根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一TCP数据报文。避免现有技术中全局配置拥塞控制算法,只能使用统一的拥塞控制算法传输所有TCP数据报文,本发明通过客户端所处的区域的网络特征,根据网络特征获取该网络特征适用的拥塞控制算法,以及该拥塞控制算法的参数值,对该第一TCP数据报文进行特定的传输处理,从而能够有效地针对不同客户端所处的网络对TCP数据报文进行不同的传输处理。
所述获取单元301具体用于:
从所述客户端发送的第二TCP数据报文中获取所述第一IP地址,所述第二TCP数据报文包括所述第一IP地址;
或,从自身预先存储的IP地址中获取所述第一IP地址。
可选的,所述获取单元301具体用于:
从IP网段和网络特征之间的对应关系中,将与所述第一IP地址对应的网络特征确定为所述第一网络特征,所述第一IP地址在所述第一网络特征对应的IP网段内。
如图6所示,所述服务器30还包括:
更新单元303,用于当获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征。
可选的,所述获取单元301具体用于:
获取第一时刻,所述第一时刻为获取到所述第一IP地址的时刻或根据所述第一IP地址获取第一网络特征的时刻;
从IP网段、网络特征时段和网络特征之间的对应关系中,确定所述第一时刻在所述第一IP地址对应的任一网络特征时段内,所述第一IP地址对应多个网络特征时段;
从IP网段、网络特征时段和网络特征之间的对应关系中,将与所述第一IP地址对应的所述第一时刻所在的所述任一网络特征时段的网络特征确定为所述第一网络特征,所述第一时刻在所述第一网络特征对应的网络特征时段内,所述第一IP地址在所述第一网络特征对应的IP网段内。
更新单元303,用于当在第二时刻获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段、网络特征时段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征,所述第一时刻与所述第二时刻不同,所述第二时刻在所述第一网络特征对应的网络特征时段内。
所述更新单元303具体用于:
当网络特征不匹配的次数大于预设阈值时,所述第一IP地址对应的网络特征更新为所述第二网络特征,所述网络特征不匹配的次数为获取的所述第一IP地址的网络特征与所述第一网络特征不同的次数,所述预设阈值为获取的所述第一IP地址的网络特征与所述第一网络特征不同的预设次数。
实施例5
本发明实施例提供一种服务器40,如图7所示,包括:
存储器401,用于存储程序代码;
处理器402用于调用所述存储器401存储的程序代码执行如下方法:
获取第一网际协议IP地址,所述第一IP地址用于标识客户端所处的区域;
根据所述第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;
从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,其中,不同的网络特征对应同一拥塞控制算法,且所述同一拥塞控制算法的参数值不同,或者,不同的网络特征对应不同的拥塞控制算法;
发射器403,用于根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一传输控制协议TCP数据报文。
总线404,用于与所述存储器401、所述处理器402和所述发射器403连接完成相互间的通信。
这样一来,首先,获取第一IP地址,所述第一IP地址用于标识客户端所处的区域;然后,根据该第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;再从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,最后,根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一TCP数据报文。避免现有技术中全局配置拥塞控制算法,只能使用统一的拥塞控制算法传输所有TCP数据报文,本发明通过客户端所处的区域的网络特征,根据网络特征获取该网络特征适用的拥塞控制算法,以及该拥塞控制算法的参数值,对该第一TCP数据报文进行特定的传输处理,从而能够有效地针对不同客户端所处的网络对TCP数据报文进行不同的传输处理。
所述处理器402具体用于:
从所述客户端发送的第二TCP数据报文中获取所述第一IP地址,所述第二TCP数据报文包括所述第一IP地址;
或,从自身预先存储的IP地址中获取所述第一IP地址。
可选的,所述处理器402具体用于:
从IP网段和网络特征之间的对应关系中,将与所述第一IP地址对应的网络特征确定为所述第一网络特征,所述第一IP地址在所述第一网络特征对应的IP网段内。
所述处理器402还用于当获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征。
可选的,所述处理器402具体用于:
获取第一时刻,所述第一时刻为获取到所述第一IP地址的时刻或根据所述第一IP地址获取第一网络特征的时刻;
从IP网段、网络特征时段和网络特征之间的对应关系中,确定所述第一时刻在所述第一IP地址对应的任一网络特征时段内,所述第一IP地址对应多个网络特征时段;
从IP网段、网络特征时段和网络特征之间的对应关系中,将与所述第一IP地址对应的所述第一时刻所在的所述任一网络特征时段的网络特征确定为所述第一网络特征,所述第一时刻在所述第一网络特征对应的网络特征时段内,所述第一IP地址在所述第一网络特征对应的IP网段内。
所述处理器402还用于当在第二时刻通过接收第三TCP数据报文获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段、网络特征时段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征,所述第一时刻与所述第二时刻不同,所述第二时刻在所述第一网络特征对应的网络特征时段内。
所述处理器402具体用于:
当网络特征不匹配的次数大于预设阈值时,所述第一IP地址对应的网络特征更新为所述第二网络特征,所述网络特征不匹配的次数为获取的所述第一IP地址的网络特征与所述第一网络特征不同的次数,所述预设阈值为获取的所述第一IP地址的网络特征与所述第一网络特征不同的预设次数。
需要说明的是,本发明所述的拥塞控制算法包括westwood+算法、FastTCP算法、cubic算法和hybla算法。
通过以上的实施方式的描述,所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,仅以上述各功能模块的划分进行举例说明,实际应用中,可以根据需要而将上述功能分配由不同的功能模块完成,即将装置的内部结构划分成不同的功能模块,以完成以上描述的全部或者部分功能。上述描述的系统,装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述模块或单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本发明各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)或处理器(processor)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,仅为本发明的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本发明的保护范围之内。因此,本发明的保护范围应以所述权利要求的保护范围为准。

Claims (14)

  1. 一种数据传输方法,其特征在于,应用于服务器,包括:
    获取第一网际协议IP地址,所述第一IP地址用于标识客户端所处的区域;
    根据所述第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;
    从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,其中,不同的网络特征对应同一拥塞控制算法,且所述同一拥塞控制算法的参数值不同,或者,不同的网络特征对应不同的拥塞控制算法;
    根据所述第一拥塞控制算法和所述第一拥塞控制算法的参数值,向所述第一IP地址对应区域的客户端发送第一传输控制协议TCP数据报文。
  2. 根据权利要求1所述的方法,其特征在于,所述获取第一网际协议IP地址包括:
    从所述客户端发送的第二TCP数据报文中获取所述第一IP地址,所述第二TCP数据报文包括所述第一IP地址;
    或,从自身预先存储的IP地址中获取所述第一IP地址。
  3. 根据权利要求1或2所述的方法,其特征在于,所述根据所述第一IP地址获取第一网络特征包括:
    从IP网段和网络特征之间的对应关系中,将与所述第一IP地址对应的网络特征确定为所述第一网络特征,所述第一IP地址在所述第一网络特征对应的IP网段内。
  4. 根据权利要求3所述的方法,其特征在于,所述方法还包括:
    当获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征。
  5. 根据权利要求1或2所述的方法,其特征在于,所述根据所述第一IP地址获取第一网络特征包括:
    获取第一时刻,所述第一时刻为获取到所述第一IP地址的时刻或根据所述第一IP地址获取第一网络特征的时刻;
    从IP网段、网络特征时段和网络特征之间的对应关系中,确定所述第一时刻在所述第一IP地址对应的任一网络特征时段内,所述第一IP地址对应多个网络特征时段;
    从IP网段、网络特征时段和网络特征之间的对应关系中,将与所述第一IP地址对应的所述第一时刻所在的所述任一网络特征时段的网络特征确定为所述第一网络特征,所述第一时刻在所述第一网络特征对应的网络特征时段内,所述第一IP地址在所述第一网络特征对应的IP网段内。
  6. 根据权利要求5所述的方法,其特征在于,所述方法还包括:
    当在第二时刻获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段、网络特征时段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征,所述第一时刻与所述第二时刻不同,所述第二时刻在所述第一网络特征对应的网络特征时段内。
  7. 根据权利要求4或6所述的方法,其特征在于,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征包括:
    当网络特征不匹配的次数大于预设阈值时,所述第一IP地址对应的网络特征更新为所述第二网络特征,所述网络特征不匹配的次数为获取的所述第一IP地址的网络特征与所述第一网络特征不同的次数,所述预设阈值为获取的所述第一IP地址的网络特征与所述第一网络特征不同的预设次数。
  8. 一种服务器,其特征在于,包括:
    获取单元,用于获取第一网际协议IP地址,所述第一IP地址用于标识客户端所处的区域;
    所述获取单元还用于根据所述第一IP地址获取第一网络特征,所述第一网络特征为所述第一IP地址对应的区域的网络特征,所述网络特征包括丢包率、时延和带宽中至少一个;
    所述获取单元还用于从网络特征与拥塞控制算法的对应关系中,根据所述第一网络特征获取所述第一网络特征对应的第一拥塞控制算法,以及所述第一拥塞控制算法的参数值,其中,不同的网络特征对应同一拥塞控制算法,且所述同一拥塞控制算法的参数值不同,或者,不同的网络特征对应不同的拥塞控制算法;
    发送单元,用于根据所述第一拥塞控制算法和所述第一拥塞控制算法的参 数值,向所述第一IP地址对应区域的客户端发送第一传输控制协议TCP数据报文。
  9. 根据权利要求8所述的服务器,其特征在于,所述获取单元具体用于:
    从所述客户端发送的第二TCP数据报文中获取所述第一IP地址,所述第二TCP数据报文包括所述第一IP地址;
    或,从自身预先存储的IP地址中获取所述第一IP地址。
  10. 根据权利要求8或9所述的服务器,其特征在于,所述获取单元具体用于:
    从IP网段和网络特征之间的对应关系中,将与所述第一IP地址对应的网络特征确定为所述第一网络特征,所述第一IP地址在所述第一网络特征对应的IP网段内。
  11. 根据权利要求10所述的服务器,其特征在于,所述服务器还包括:
    更新单元,用于当获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征。
  12. 根据权利要求8或9所述的服务器,其特征在于,所述获取单元具体用于:
    获取第一时刻,所述第一时刻为获取到所述第一IP地址的时刻或根据所述第一IP地址获取第一网络特征的时刻;
    从IP网段、网络特征时段和网络特征之间的对应关系中,确定所述第一时刻在所述第一IP地址对应的任一网络特征时段内,所述第一IP地址对应多个网络特征时段;
    从IP网段、网络特征时段和网络特征之间的对应关系中,将与所述第一IP地址对应的所述第一时刻所在的所述任一网络特征时段的网络特征确定为所述第一网络特征,所述第一时刻在所述第一网络特征对应的网络特征时段内,所述第一IP地址在所述第一网络特征对应的IP网段内。
  13. 根据权利要求12所述的服务器,其特征在于,所述服务器还包括:
    更新单元,用于当在第二时刻获取的所述第一IP地址的第二网络特征与所述第一网络特征不同时,将所述IP网段、网络特征时段和网络特征之间的对应关系中,所述第一IP地址所在的IP网段对应的网络特征更新为所述第二网络特征,所述第一时刻与所述第二时刻不同,所述第二时刻在所述第一网络特征 对应的网络特征时段内。
  14. 根据权利要求11或13所述的服务器,其特征在于,所述更新单元具体用于:
    当网络特征不匹配的次数大于预设阈值时,所述第一IP地址对应的网络特征更新为所述第二网络特征,所述网络特征不匹配的次数为获取的所述第一IP地址的网络特征与所述第一网络特征不同的次数,所述预设阈值为获取的所述第一IP地址的网络特征与所述第一网络特征不同的预设次数。
PCT/CN2016/080253 2015-06-11 2016-04-26 一种数据传输方法及装置 WO2016197727A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510319516.7 2015-06-11
CN201510319516.7A CN106302230B (zh) 2015-06-11 2015-06-11 一种数据传输方法及装置

Publications (1)

Publication Number Publication Date
WO2016197727A1 true WO2016197727A1 (zh) 2016-12-15

Family

ID=57502780

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/080253 WO2016197727A1 (zh) 2015-06-11 2016-04-26 一种数据传输方法及装置

Country Status (2)

Country Link
CN (1) CN106302230B (zh)
WO (1) WO2016197727A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110784414A (zh) * 2019-10-30 2020-02-11 北京达佳互联信息技术有限公司 数据交互方法、装置和电子设备

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115643210A (zh) * 2019-11-30 2023-01-24 华为技术有限公司 控制数据包发送方法及系统
CN111404823A (zh) * 2020-03-05 2020-07-10 广东睿江云计算股份有限公司 一种tcp动态选择拥塞算法的方法及其系统
CN114726790B (zh) * 2021-01-06 2024-04-16 北京中科海网科技有限公司 一种基于传输内容大小的拥塞控制选择方法及系统
CN116192754A (zh) * 2021-11-26 2023-05-30 苏州盛科通信股份有限公司 报文的控制方法和装置、存储介质及电子装置
CN114389959B (zh) * 2021-12-30 2023-10-27 深圳清华大学研究院 网络拥塞控制方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007124154A1 (en) * 2006-04-21 2007-11-01 Microsoft Corporation Enabling network devices to run multiple congestion control algorithms
CN101115002A (zh) * 2007-03-19 2008-01-30 重庆邮电大学 利用TCP Veno提高无线自组织网络性能的方法
CN101521557A (zh) * 2008-02-29 2009-09-02 华为技术有限公司 差错控制和拥塞控制的方法和系统
CN102204182A (zh) * 2010-12-29 2011-09-28 华为技术有限公司 一种数据传输的拥塞控制方法及装置
CN103973591A (zh) * 2014-06-04 2014-08-06 浪潮电子信息产业股份有限公司 一种智能网络流量拥塞解决方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101137199A (zh) * 2006-08-28 2008-03-05 大唐移动通信设备有限公司 拥塞控制方法、系统及移动通信网络
CN101938400B (zh) * 2009-06-30 2012-05-23 华为技术有限公司 网络拥塞控制的方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007124154A1 (en) * 2006-04-21 2007-11-01 Microsoft Corporation Enabling network devices to run multiple congestion control algorithms
CN101115002A (zh) * 2007-03-19 2008-01-30 重庆邮电大学 利用TCP Veno提高无线自组织网络性能的方法
CN101521557A (zh) * 2008-02-29 2009-09-02 华为技术有限公司 差错控制和拥塞控制的方法和系统
CN102204182A (zh) * 2010-12-29 2011-09-28 华为技术有限公司 一种数据传输的拥塞控制方法及装置
CN103973591A (zh) * 2014-06-04 2014-08-06 浪潮电子信息产业股份有限公司 一种智能网络流量拥塞解决方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110784414A (zh) * 2019-10-30 2020-02-11 北京达佳互联信息技术有限公司 数据交互方法、装置和电子设备
CN110784414B (zh) * 2019-10-30 2023-06-23 北京达佳互联信息技术有限公司 数据交互方法、装置、电子设备和存储介质

Also Published As

Publication number Publication date
CN106302230B (zh) 2019-11-26
CN106302230A (zh) 2017-01-04

Similar Documents

Publication Publication Date Title
WO2016197727A1 (zh) 一种数据传输方法及装置
US10715282B2 (en) Method and related device for improving TCP transmission efficiency using delayed ACK
US10587544B2 (en) Message processing method, processing server, terminal, and storage medium
US20160234303A1 (en) Peer-to-Peer Upload Scheduling
US10027781B2 (en) TCP link configuration method, apparatus, and device
US9392081B2 (en) Method and device for sending requests
US9083583B1 (en) Latency reduction via adaptive speculative preconnection
KR102208935B1 (ko) 데이터 교환을 위한 컨텍스트를 설정하는 http 프로토콜을 통한 메시징 api
US11640368B2 (en) Acceleration system for facilitating processing of API calls
WO2019201072A1 (zh) Cdn业务调度处理方法及cdn服务器
CN103401946A (zh) Http上传加速方法和系统
CN105262836A (zh) 服务器推送信息的方法及客户端接收推送信息的方法
US20180041439A1 (en) System and method of providing compression technique for jitter sensitive application through multiple network links
WO2020098435A1 (zh) 一种数据报文发送和接收方法、存储介质及处理器
WO2016202224A1 (zh) 一种传输层参数调整方法和装置
WO2012075853A1 (zh) 一种点对点通信方法、装置及系统
CN107872538B (zh) 解耦tcp长连接的业务处理方法、反向代理和业务服务器
US9124598B2 (en) Method and apparatus of establishing a connection between devices using cached connection information
CN107135091A (zh) 一种应用质量指标映射方法、服务器和客户端
WO2013159492A1 (zh) 信息上报与下载的方法及系统
US8966070B1 (en) System and method of reducing network latency
WO2016177135A1 (zh) 资源管理方法、装置及控制终端
CN111245874A (zh) 信息推送方法、装置、服务器及存储介质
TWI691184B (zh) 資料傳輸及接收方法
EP4231607A1 (en) Data transmission method and communication apparatus

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: 16806625

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16806625

Country of ref document: EP

Kind code of ref document: A1