CN117240784B - Burst flow processing method and device of data center flow scheduling system - Google Patents
Burst flow processing method and device of data center flow scheduling system Download PDFInfo
- Publication number
- CN117240784B CN117240784B CN202311365423.9A CN202311365423A CN117240784B CN 117240784 B CN117240784 B CN 117240784B CN 202311365423 A CN202311365423 A CN 202311365423A CN 117240784 B CN117240784 B CN 117240784B
- Authority
- CN
- China
- Prior art keywords
- flow
- traffic
- data
- ipv6
- data packet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title abstract description 14
- 238000005111 flow chemistry technique Methods 0.000 title abstract description 8
- 230000005540 biological transmission Effects 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000005641 tunneling Effects 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a burst flow processing method and a burst flow processing device of a data center flow scheduling system, which are used for acquiring flow data of each flow node in real time, and adding an I Pv6 header to all data packets transmitted in a first flow node when the flow variation amplitude of the first flow node is larger than or equal to a preset value to acquire the I Pv6 data packets; according to the flow property of the first flow node, determining network planes of all the I Pv6 data packets corresponding to the first flow node, and determining an I PV6over I PV4 tunnel appointed by each I Pv6 data packet according to the network planes; carrying out network slicing on each I Pv6 data packet to obtain a plurality of data packets to be transmitted, and forwarding each data packet to be transmitted respectively according to an I PV6over I PV4 tunnel appointed by each I Pv6 data packet; and receiving the transmission data packet of each IPV 6over IPV 4 tunnel outlet, merging all the transmission data packets according to the header in the transmission data packet to obtain a merged data packet, and converting the merged data packet into an IPV 4 data packet for normal transmission.
Description
Technical Field
The present invention relates to the field of traffic processing, and in particular, to a burst traffic processing method and apparatus for a data center traffic scheduling system.
Background
In order to improve the performance and stability of the flow scheduling system, a polling algorithm is often adopted to decide the distribution of the flow so that the flow is uniformly distributed on a plurality of servers or paths.
Networks using IPv6 traffic are gradually increasing, and a traffic scheduling system adopting IPv4 traffic in the prior art cannot be compatible with scheduling of IPv6 traffic.
In the prior art, when a polling algorithm is adopted to decide the distribution of the traffic, if the polling time is too short when the polling time is set, frequent convergence routing may be caused, so that frequent network oscillation is caused, and bad influence is brought to customer service. However, when the polling time is too long, partial port congestion is caused when the burst traffic is faced, so that traffic scheduling is affected.
Disclosure of Invention
The invention provides a method and a device for processing burst traffic of a data center traffic scheduling system, which are used for solving the problem that partial ports are congested when the current traffic scheduling system faces the burst traffic, so that traffic scheduling is affected.
In a first aspect, the present application provides a method for burst traffic processing in a data center traffic scheduling system, including:
Acquiring flow data of each flow node in real time, and adding an IPv6 header to all data packets transmitted in a first flow node when the flow variation amplitude of the first flow node is larger than or equal to a preset value to acquire an IPv6 data packet;
Determining network planes of all IPv6 data packets corresponding to the first flow node according to the flow property of the first flow node, and determining IPV6 over IPV4 tunnels appointed by all IPv6 data packets according to the network planes;
Carrying out network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and forwarding each data packet to be transmitted respectively according to an IPV6 over IPV4 tunnel appointed by each IPv6 data packet;
and receiving the transmission data packet of each IPV6 over IPV4 tunnel outlet, merging all the transmission data packets according to the header in the transmission data packet to obtain a merged data packet, and converting the merged data packet into an IPv4 data packet for normal transmission.
Thus, when the burst traffic is faced, the IPv4 data packet is converted into the IPv6 data packet for transmission, so that the transmission of the IPv6 network is supported. And determining the requirements of clients in each flow node according to the flow properties of the flow nodes, and selecting a proper network plane according to different requirements. Furthermore, by performing network slicing on the IPv6 data packet and merging the data packets to be transmitted at the tunnel outlet, the data transmission efficiency can be improved, the problem of port congestion caused by flow change can be solved, and the reliability of flow scheduling can be improved. Meanwhile, the data center network flow is classified, so that the service quality of the data center network can be remarkably improved. The network connection quality of the key service can be ensured. The traffic of the key service is preferentially processed, so that delay and packet loss can be reduced, the network performance is improved, and the stable operation of the key service is ensured. For online services provided by a data center, such as cloud computing, video streaming media and the like, hierarchical priority can ensure that users can obtain better service experience. For example, in a video streaming media application, by preferentially processing the transmission of a video stream, the churning and loading time can be reduced, and the user viewing experience can be improved. While network resources are allocated reasonably. By dynamically adjusting the network bandwidth allocation, the resource waste and congestion phenomenon can be avoided, the resource utilization rate is improved, and the operation cost is reduced.
Further, when the flow variation amplitude of the first flow node is greater than or equal to a preset value, adding an IPv6 header to all data packets transmitted in the first flow node to obtain an IPv6 data packet, specifically:
Determining a preset value according to the flow bearing capacity of each flow node and the polling time in the flow scheduling system;
When the flow variation amplitude of the first flow node is larger than or equal to a preset value, all data packets transmitted in the first flow node are transmitted to a SRv server, and an IPv6 data packet is obtained after an IPv6 header is added to the data packet through the SRv server.
Therefore, the preset value is determined according to the flow bearing capacity of the flow node and the polling time of the flow scheduling system, and can be dynamically adjusted according to actual conditions, so that the flow change of different nodes can be better adapted. And by transmitting the data packet in the flow node to SRv server and adding IPv6 header on the server, the function of SRv server can be utilized to process and forward the IPv6 data packet, thereby realizing more flexible and efficient data transmission.
Further, the determining, according to the traffic properties of the first traffic node, network planes of all IPv6 data packets corresponding to the first traffic node specifically includes:
judging whether the flow property of the first flow node is low-delay flow or not;
If the traffic property of the first traffic node is low-delay traffic, determining the IPv6 data packet as a service traffic plane according to the message header parts in all the IPv6 data packets;
and if the traffic property of the first traffic node is not low-delay traffic, determining the IPv6 data packet as a storage service traffic plane according to the message header parts in all the IPv6 data packets.
Therefore, the traffic with short delay requirement and the traffic with lower delay requirement because of connection stability are distinguished, and the traffic with higher delay requirement is preferentially forwarded.
Further, the network slicing is performed on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and each data packet to be transmitted is forwarded according to an IPv6over IPv4 tunnel specified by each IPv6 data packet, which specifically includes:
performing network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and adding an identification data segment into each data packet to be transmitted;
and setting SRv paths, and sending each data packet to be transmitted to an IPV6 over IPV4 tunnel appointed by the corresponding IPv6 data packet through SRv paths according to the identification data segment in each data packet to be transmitted.
Further, after the converting the merged data packet into the IPv4 data packet for normal transmission, the method includes:
and acquiring flow data of each flow node in real time, stopping adding an IPv6 header to a data packet transmitted in a first flow node when the flow variation amplitude of the first flow node is smaller than a preset value, and normally transmitting the data packet by an IPv4 protocol.
Therefore, the IPV6 over IPV4 tunnel is not occupied for a long time, the reserved tunnel is only used under the condition of burst traffic, the running maintenance cost of the tunnel is reduced, and the problem of port congestion caused by traffic change is solved.
In a second aspect, the present application provides a burst traffic processing apparatus of a data center traffic scheduling system, including: the system comprises a header adding module, a tunnel designating module, a data forwarding module and a data transmission module;
The header adding module is used for obtaining flow data of each flow node in real time, and adding IPv6 headers to all data packets transmitted in a first flow node when the flow variation amplitude of the first flow node is larger than or equal to a preset value to obtain IPv6 data packets;
The tunnel assignment module is used for determining network planes of all IPv6 data packets corresponding to the first flow node according to the flow property of the first flow node, and determining IPV6 over IPV4 tunnels assigned by all IPv6 data packets according to the network planes;
The data forwarding module is used for carrying out network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and forwarding each data packet to be transmitted respectively according to an IPV6 over IPV4 tunnel appointed by each IPv6 data packet;
The data transmission module is used for receiving the transmission data packet of each IPV6 over IPV4 tunnel outlet, combining all the transmission data packets according to the header in the transmission data packet to obtain a combined data packet, and converting the combined data packet into an IPv4 data packet for normal transmission.
Further, the header adding module includes: a preset value determining unit and a data adding unit;
the preset value determining unit is used for determining a preset value according to the flow bearing capacity of each flow node and the polling time in the flow scheduling system;
The data adding unit is configured to transmit all data packets transmitted in a first traffic node to a SRv server when a traffic variation amplitude of the first traffic node is greater than or equal to a preset value, and obtain an IPv6 data packet after adding an IPv6 header to the data packet by the SRv server.
Further, the tunnel specifying module includes: a first judging unit and a network plane determining unit;
the first judging unit is used for judging whether the flow property of the first flow node is low-delay flow or not;
The network plane determining unit is configured to determine, when the first judging unit determines that the traffic property of the first traffic node is low-delay traffic, the IPv6 data packets as a traffic plane according to the message headers in all the IPv6 data packets;
the network plane determining unit is further configured to determine, when the first judging unit determines that the traffic property of the first traffic node is not low latency traffic, the IPv6 data packet as a storage traffic plane according to the header of the packet in all the IPv6 data packets.
Further, the data forwarding module includes: a data slicing unit and a tunnel transmission unit;
the data slicing unit is used for carrying out network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and adding an identification data segment into each data packet to be transmitted;
the tunneling unit is configured to set SRv paths, and send each data packet to be transmitted to an IPv6 over IPv4 tunnel specified by the corresponding IPv6 data packet through SRv paths according to the identification data segment in each data packet to be transmitted.
Further, the burst flow processing device of the data center flow scheduling system further comprises a real-time monitoring module;
the real-time monitoring module is used for acquiring flow data of each flow node in real time, stopping adding an IPv6 header to a data packet transmitted in a first flow node when the flow variation amplitude of the first flow node is smaller than a preset value, and normally transmitting the data packet by an IPv4 protocol.
Thus, when the burst traffic is faced, the IPv4 data packet is converted into the IPv6 data packet for transmission, so that the transmission of the IPv6 network is supported. And determining the requirements of clients in each flow node according to the flow properties of the flow nodes, and selecting a proper network plane according to different requirements. Furthermore, by performing network slicing on the IPv6 data packet and merging the data packets to be transmitted at the tunnel outlet, the data transmission efficiency can be improved, the problem of port congestion caused by flow change can be solved, and the reliability of flow scheduling can be improved. Meanwhile, the data center network flow is classified, so that the service quality of the data center network can be remarkably improved. The network connection quality of the key service can be ensured. The traffic of the key service is preferentially processed, so that delay and packet loss can be reduced, the network performance is improved, and the stable operation of the key service is ensured. For online services provided by a data center, such as cloud computing, video streaming media and the like, hierarchical priority can ensure that users can obtain better service experience. For example, in a video streaming media application, by preferentially processing the transmission of a video stream, the churning and loading time can be reduced, and the user viewing experience can be improved. While network resources are allocated reasonably. By dynamically adjusting the network bandwidth allocation, the resource waste and congestion phenomenon can be avoided, and the resource utilization rate is improved.
Drawings
Fig. 1: the invention provides a flow diagram of one embodiment of a burst flow processing method of a data center flow scheduling system;
Fig. 2: the invention provides a module structure diagram of an embodiment of a burst flow processing device of a data center flow scheduling system.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
SRv6 (Segment Routing over IPv, segment routing based on IPv6 forwarding plane), SR (Segment Routing) +ipv6, is a new generation IP bearer protocol.
SRv6 is mainly embodied in three layers of programmable space, and adds SRH information in the expansion header part of the IPv6 message, namely the message expansion header of the SRH. Of the most important of these is SEGMENT LIST in the SRH, where each SEGMENT LIST is a 128-bit IPv6 address, SEGMENT LIST also being used to direct the forwarding of messages. The first layer of programmable space is embodied in the order SEGMENT LIST and the SEGMENT LIST order can be customized to achieve the path programmability. And each 128-bit SEGMENT LIST contains three parts, locator, function, and Args, respectively. The Locator mainly carries routing position information; the Function is used for binding message forwarding operation instructions, the instructions comprise end, end X, end DX, end DT and the like, and each instruction expresses different operations; args is an optional parameter, which defaults to null, by modification of this information, i.e. the second layer programmable space. The last programmable space is embodied on Optional TLV, and application information can be carried in the TLV, so that VPN, service chain and TE related functions are realized.
Example 1
Referring to fig. 1, a burst traffic processing method of a data center traffic scheduling system according to an embodiment of the present invention includes steps S1 to S4, where each step is specifically as follows:
Step S1: acquiring flow data of each flow node in real time, and adding an IPv6 header to all data packets transmitted in a first flow node when the flow variation amplitude of the first flow node is larger than or equal to a preset value to acquire an IPv6 data packet;
In a specific embodiment, to monitor the client traffic in real time, when the traffic node of the client generates the bursty traffic, the bursty traffic is drained to the SRV6 server, and an IPV6 header is added;
Wherein the burst flow is a flow change amplitude which is larger than or equal to a preset value.
Further, when the flow variation amplitude of the first flow node is greater than or equal to a preset value, adding an IPv6 header to all data packets transmitted in the first flow node to obtain an IPv6 data packet, specifically:
Determining a preset value according to the flow bearing capacity of each flow node and the polling time in the flow scheduling system;
In one embodiment, the preset value is set according to the exit burst traffic tolerance capability and the polling time of the traffic scheduling system, and when the traffic system polling time is 30s, it is determined that the traffic exceeds 20G for 1 minute at the total exit.
When the flow variation amplitude of the first flow node is larger than or equal to a preset value, all data packets transmitted in the first flow node are transmitted to a SRv server, and an IPv6 data packet is obtained after an IPv6 header is added to the data packet through the SRv server.
In a specific embodiment, the IPV6 header includes an SRH extension message of the new SRv, which facilitates the programming control of the SRH field by the subsequent reference.
Therefore, the preset value is determined according to the flow bearing capacity of the flow node and the polling time of the flow scheduling system, and can be dynamically adjusted according to actual conditions, so that the flow change of different nodes can be better adapted. And by transmitting the data packet in the flow node to SRv server and adding IPv6 header on the server, the function of SRv server can be utilized to process and forward the IPv6 data packet, thereby realizing more flexible and efficient data transmission.
Step S2: determining network planes of all IPv6 data packets corresponding to the first flow node according to the flow property of the first flow node, and determining IPV6over IPV4 tunnels appointed by all IPv6 data packets according to the network planes;
Further, the determining, according to the traffic properties of the first traffic node, network planes of all IPv6 data packets corresponding to the first traffic node specifically includes:
judging whether the flow property of the first flow node is low-delay flow or not;
If the traffic property of the first traffic node is low-delay traffic, determining the IPv6 data packet as a service traffic plane according to the message header parts in all the IPv6 data packets;
and if the traffic property of the first traffic node is not low-delay traffic, determining the IPv6 data packet as a storage service traffic plane according to the message header parts in all the IPv6 data packets.
Therefore, the traffic with short delay requirement and the traffic with lower delay requirement because of connection stability are distinguished, and the traffic with higher delay requirement is preferentially forwarded.
In a specific embodiment, the traffic properties of the first traffic node are identified by an SRH field in the IPv6 packet header.
Step S3: carrying out network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and forwarding each data packet to be transmitted respectively according to an IPV6 over IPV4 tunnel appointed by each IPv6 data packet;
Further, the network slicing is performed on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and each data packet to be transmitted is forwarded according to an IPv6over IPv4 tunnel specified by each IPv6 data packet, which specifically includes:
performing network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and adding an identification data segment into each data packet to be transmitted;
and setting SRv paths, and sending each data packet to be transmitted to an IPV6 over IPV4 tunnel appointed by the corresponding IPv6 data packet through SRv paths according to the identification data segment in each data packet to be transmitted.
Step S4: and receiving the transmission data packet of each IPV6 over IPV4 tunnel outlet, merging all the transmission data packets according to the header in the transmission data packet to obtain a merged data packet, and converting the merged data packet into an IPv4 data packet for normal transmission.
Further, after the converting the merged data packet into the IPv4 data packet for normal transmission, the method includes:
and acquiring flow data of each flow node in real time, stopping adding an IPv6 header to a data packet transmitted in a first flow node when the flow variation amplitude of the first flow node is smaller than a preset value, and normally transmitting the data packet by an IPv4 protocol.
Therefore, the IPV6 over IPV4 tunnel is not occupied for a long time, the reserved tunnel is only used under the condition of burst traffic, the running maintenance cost of the tunnel is reduced, and the problem of port congestion caused by traffic change is solved.
In one embodiment, the client traffic node is monitored, and when the traffic data in the client traffic node has stopped bursty traffic, the server flooding is ended SRv, returning to general traffic scheduling.
Here, the general traffic scheduling is not limited to the original traffic scheduling method.
Thus, when the burst traffic is faced, the IPv4 data packet is converted into the IPv6 data packet for transmission, so that the transmission of the IPv6 network is supported. And determining the requirements of clients in each flow node according to the flow properties of the flow nodes, and selecting a proper network plane according to different requirements. Furthermore, by performing network slicing on the IPv6 data packet and merging the data packets to be transmitted at the tunnel outlet, the data transmission efficiency can be improved, the problem of port congestion caused by flow change can be solved, and the reliability of flow scheduling can be improved.
Example two
Referring to fig. 2, a block diagram of an embodiment of a burst traffic processing apparatus of a data center traffic scheduling system according to the present invention is shown.
A burst traffic processing apparatus of a data center traffic scheduling system, comprising: a header adding module 210, a tunnel specifying module 220, a data forwarding module 230, and a data transmission module 240;
The header adding module 210 is configured to obtain flow data of each flow node in real time, and add an IPv6 header to all data packets transmitted in a first flow node when a flow variation amplitude of the first flow node is greater than or equal to a preset value, so as to obtain an IPv6 data packet;
the tunnel assignment module 220 is configured to determine, according to traffic properties of the first traffic node, network planes of all IPv6 data packets corresponding to the first traffic node, and determine, according to the network planes, IPv6 over IPv4 tunnels assigned by each IPv6 data packet;
The data forwarding module 230 is configured to perform network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and forward each data packet to be transmitted according to an IPv6 over IPv4 tunnel specified by each IPv6 data packet;
The data transmission module 240 is configured to receive the transmission data packet of each IPV6 over IPV4 tunnel exit, combine all the transmission data packets according to the header in the transmission data packet, obtain a combined data packet, and convert the combined data packet into an IPV4 data packet for normal transmission.
Further, the header adding module 210 includes: a preset value determining unit 211 and a data adding unit 212;
The preset value determining unit 211 is configured to determine a preset value according to the traffic bearing capacity of each traffic node and the polling time in the traffic scheduling system;
The data adding unit 212 is configured to, when there is a first traffic node with a traffic variation amplitude greater than or equal to a preset value, transmit all data packets transmitted in the first traffic node to a SRv server, and obtain an IPv6 data packet by adding an IPv6 header to the data packet by the SRv server.
Further, the tunnel assignment module 220 includes: a first judging unit 221 and a network plane determining unit 222;
the first determining unit 221 is configured to determine whether the traffic property of the first traffic node is low-latency traffic;
The network plane determining unit 222 is configured to determine, when the first judging unit 221 determines that the traffic property of the first traffic node is low-latency traffic, the IPv6 data packet as a traffic plane according to the header of the packet in all the IPv6 data packets;
The network plane determining unit 222 is further configured to determine, when the first determining unit 221 determines that the traffic property of the first traffic node is not low latency traffic, the IPv6 data packet as a storage traffic plane according to the header of the packet in all IPv6 data packets.
Further, the data forwarding module 230 includes: a data slicing unit 231 and a tunneling unit 232;
the data slicing unit 231 is configured to perform network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and add an identification data segment to each data packet to be transmitted;
The tunneling unit 232 is configured to set SRv paths, and send each data packet to be transmitted to an IPv6 over IPv4 tunnel specified by the corresponding IPv6 data packet through SRv paths according to the identification data segment in each data packet to be transmitted.
Further, the burst flow processing device of the data center flow scheduling system further comprises a real-time monitoring module 250;
The real-time monitoring module 250 is configured to obtain, in real time, flow data of each flow node, and stop adding an IPv6 header to a data packet transmitted in a first flow node when a flow variation amplitude of the first flow node is smaller than a preset value, and perform normal transmission on the data packet according to an IPv4 protocol.
Thus, when the burst traffic is faced, the IPv4 data packet is converted into the IPv6 data packet for transmission, so that the transmission of the IPv6 network is supported. And determining the requirements of clients in each flow node according to the flow properties of the flow nodes, and selecting a proper network plane according to different requirements. Furthermore, by performing network slicing on the IPv6 data packet and merging the data packets to be transmitted at the tunnel outlet, the data transmission efficiency can be improved, the problem of port congestion caused by flow change can be solved, and the reliability of flow scheduling can be improved. Meanwhile, the data center network flow is classified, so that the service quality of the data center network can be remarkably improved. The network connection quality of the key service can be ensured. The traffic of the key service is preferentially processed, so that delay and packet loss can be reduced, the network performance is improved, and the stable operation of the key service is ensured. For online services provided by a data center, such as cloud computing, video streaming media and the like, hierarchical priority can ensure that users can obtain better service experience. For example, in a video streaming media application, by preferentially processing the transmission of a video stream, the churning and loading time can be reduced, and the user viewing experience can be improved. While network resources are allocated reasonably. By dynamically adjusting the network bandwidth allocation, the resource waste and congestion phenomenon can be avoided, and the resource utilization rate is improved.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention, and are not to be construed as limiting the scope of the invention. It should be noted that any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art without departing from the spirit and principles of the present invention are intended to be included in the scope of the present invention.
Claims (6)
1. A burst traffic processing method for a data center traffic scheduling system, comprising:
Acquiring flow data of each flow node in real time, and adding an IPv6 header to all data packets transmitted in a first flow node when the flow variation amplitude of the first flow node is larger than or equal to a preset value to acquire an IPv6 data packet;
Determining network planes of all IPv6 data packets corresponding to the first flow node according to the flow property of the first flow node, and determining IPV6over IPV4 tunnels appointed by all IPv6 data packets according to the network planes;
performing network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and adding an identification data segment into each data packet to be transmitted;
Setting SRv paths, and sending each data packet to be transmitted to an IPV6 over IPV4 tunnel appointed by the corresponding IPv6 data packet through SRv paths according to the identification data segment in each data packet to be transmitted;
Receiving transmission data packets of each IPV6 over IPV4 tunnel outlet, merging all the transmission data packets according to the header in the transmission data packets to obtain merged data packets, and converting the merged data packets into IPv4 data packets for normal transmission;
The determining, according to the traffic properties of the first traffic node, network planes of all IPv6 data packets corresponding to the first traffic node specifically includes:
judging whether the flow property of the first flow node is low-delay flow or not;
If the traffic property of the first traffic node is low-delay traffic, determining the IPv6 data packet as a service traffic plane according to the message header parts in all the IPv6 data packets;
and if the traffic property of the first traffic node is not low-delay traffic, determining the IPv6 data packet as a storage service traffic plane according to the message header parts in all the IPv6 data packets.
2. The burst traffic processing method of the data center traffic scheduling system according to claim 1, wherein when the traffic variation amplitude of the first traffic node is greater than or equal to a preset value, adding an IPv6 header to all data packets transmitted in the first traffic node to obtain an IPv6 data packet, specifically:
Determining a preset value according to the flow bearing capacity of each flow node and the polling time in the flow scheduling system;
When the flow variation amplitude of the first flow node is larger than or equal to a preset value, all data packets transmitted in the first flow node are transmitted to a SRv server, and an IPv6 data packet is obtained after an IPv6 header is added to the data packet through the SRv server.
3. The burst traffic processing method of the data center traffic scheduling system according to claim 1, wherein after the converting the merged data packet into an IPv4 data packet for normal transmission, comprising:
and acquiring flow data of each flow node in real time, stopping adding an IPv6 header to a data packet transmitted in a first flow node when the flow variation amplitude of the first flow node is smaller than a preset value, and normally transmitting the data packet by an IPv4 protocol.
4. A burst traffic handling device for a data center traffic scheduling system, comprising: the system comprises a header adding module, a tunnel designating module, a data forwarding module and a data transmission module;
The header adding module is used for obtaining flow data of each flow node in real time, and adding IPv6 headers to all data packets transmitted in a first flow node when the flow variation amplitude of the first flow node is larger than or equal to a preset value to obtain IPv6 data packets;
The tunnel assignment module is used for determining network planes of all IPv6 data packets corresponding to the first flow node according to the flow property of the first flow node, and determining IPV6 over IPV4 tunnels assigned by all IPv6 data packets according to the network planes;
The data forwarding module is used for carrying out network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and forwarding each data packet to be transmitted respectively according to an IPV6 over IPV4 tunnel appointed by each IPv6 data packet;
the data transmission module is used for receiving the transmission data packet of each IPV6 over IPV4 tunnel outlet, combining all the transmission data packets according to the header in the transmission data packet to obtain a combined data packet, and converting the combined data packet into an IPv4 data packet for normal transmission;
Wherein, the data forwarding module includes: a data slicing unit and a tunnel transmission unit;
the data slicing unit is used for carrying out network slicing on each IPv6 data packet to obtain a plurality of data packets to be transmitted, and adding an identification data segment into each data packet to be transmitted;
The tunnel transmission unit is used for setting SRv paths, and sending each data packet to be transmitted to an IPV6over IPV4 tunnel appointed by the corresponding IPv6 data packet through SRv paths according to the identification data segment in each data packet to be transmitted;
the tunnel specifying module includes: a first judging unit and a network plane determining unit;
the first judging unit is used for judging whether the flow property of the first flow node is low-delay flow or not;
The network plane determining unit is configured to determine, when the first judging unit determines that the traffic property of the first traffic node is low-delay traffic, the IPv6 data packets as a traffic plane according to the message headers in all the IPv6 data packets;
the network plane determining unit is further configured to determine, when the first judging unit determines that the traffic property of the first traffic node is not low latency traffic, the IPv6 data packet as a storage traffic plane according to the header of the packet in all the IPv6 data packets.
5. The burst traffic processing apparatus of a data center traffic scheduling system according to claim 4, wherein the header adding module comprises: a preset value determining unit and a data adding unit;
the preset value determining unit is used for determining a preset value according to the flow bearing capacity of each flow node and the polling time in the flow scheduling system;
The data adding unit is configured to transmit all data packets transmitted in a first traffic node to a SRv server when a traffic variation amplitude of the first traffic node is greater than or equal to a preset value, and obtain an IPv6 data packet after adding an IPv6 header to the data packet by the SRv server.
6. The burst traffic processing device of the data center traffic scheduling system according to claim 4, further comprising a real-time monitoring module;
the real-time monitoring module is used for acquiring flow data of each flow node in real time, stopping adding an IPv6 header to a data packet transmitted in a first flow node when the flow variation amplitude of the first flow node is smaller than a preset value, and normally transmitting the data packet by an IPv4 protocol.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311365423.9A CN117240784B (en) | 2023-10-20 | 2023-10-20 | Burst flow processing method and device of data center flow scheduling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311365423.9A CN117240784B (en) | 2023-10-20 | 2023-10-20 | Burst flow processing method and device of data center flow scheduling system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117240784A CN117240784A (en) | 2023-12-15 |
| CN117240784B true CN117240784B (en) | 2024-06-21 |
Family
ID=89086086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311365423.9A Active CN117240784B (en) | 2023-10-20 | 2023-10-20 | Burst flow processing method and device of data center flow scheduling system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117240784B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1842051A (en) * | 2005-03-30 | 2006-10-04 | 国际商业机器公司 | Flow equalization apparatus and process and network forwarding apparatus and method using same |
| CN115277548A (en) * | 2021-04-30 | 2022-11-01 | 中国移动通信有限公司研究院 | Transmission method, device and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107770169A (en) * | 2017-10-18 | 2018-03-06 | 盛科网络（苏州）有限公司 | In bag forwarding chip between IPv4 and IPv6 tunnels rapid translating protocol header method |
| US11425022B1 (en) * | 2019-09-30 | 2022-08-23 | Juniper Networks, Inc. | Service-based tunnel selection scheme for mapping services to tunnels |
| CN115037688A (en) * | 2022-04-22 | 2022-09-09 | 新华三技术有限公司 | Flow congestion control method and device |
-
2023
- 2023-10-20 CN CN202311365423.9A patent/CN117240784B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1842051A (en) * | 2005-03-30 | 2006-10-04 | 国际商业机器公司 | Flow equalization apparatus and process and network forwarding apparatus and method using same |
| CN115277548A (en) * | 2021-04-30 | 2022-11-01 | 中国移动通信有限公司研究院 | Transmission method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117240784A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6556544B1 (en) | Method and system for provisioning network resources for dynamic multicast groups | |
| US10181977B2 (en) | Cross-stratum optimization protocol | |
| JP7434552B2 (en) | Transmission quality detection method, device and system, and storage medium | |
| US9270598B1 (en) | Congestion control using congestion prefix information in a named data networking environment | |
| CN103476062B (en) | Data flow scheduling method, equipment and system | |
| EP2405608B1 (en) | Performing path-orientated systems management | |
| US7792031B2 (en) | Optimal fragmentation of multicast packets | |
| CN111555982B (en) | Method and system for intelligently routing message based on IPv6 extension header | |
| CN113132225B (en) | Path selection method, path selection device, computer equipment and computer readable medium | |
| CN113301000B (en) | Data transmission method, device, medium and equipment | |
| US9130857B2 (en) | Protocol independent multicast with quality of service support | |
| CN113301096A (en) | Method, system and node equipment for data transmission between nodes in content distribution network | |
| US9030926B2 (en) | Protocol independent multicast last hop router discovery | |
| US20080137654A1 (en) | Method of managing signaling message in path-based signaled paths to mpls-enabled core network | |
| CN111884872B (en) | Performance test method and device for service path | |
| CN117240784B (en) | Burst flow processing method and device of data center flow scheduling system | |
| US11489768B2 (en) | Method for creating inter-domain bidirectional tunnel, communication method and device, and storage medium | |
| US9036462B2 (en) | Internet group management protocol version three for quality of service support | |
| US20230291679A1 (en) | Dynamic use of a packet recovery mechanism to avoid congestion along a network path | |
| CN109040199A (en) | A kind of method, system and storage medium for distributing resource data | |
| JP2002077257A (en) | Stream distribution network service method and its system | |
| CN115486041B (en) | Data message format for communication across different networks | |
| CN111600798B (en) | Method and equipment for sending and obtaining assertion message | |
| JP5045683B2 (en) | Communication system for performing traffic control in units of flow, management apparatus and program used in the communication system | |
| EP3131344A1 (en) | Method and system for discovery of access aggregation points for bonding approaches in a telecommunication network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |