Data center egress traffic scheduling system

Abstract

This application provides a data center egress traffic scheduling system. The system includes: an intelligent management and control device for acquiring egress traffic information and generating an egress traffic policy for each terminal device based on the egress traffic information; a terminal device that, based on the acquired egress traffic policy, performs a first encapsulation process on the egress packet data to be processed, generating a packet data packet; a node device in the data center's basic network for receiving the packet data packet, performing a second encapsulation process on the egress packet data to be processed based on the path in the routing extension header, generating a target packet data packet and forwarding it; and an egress gateway device that uses the routing extension header to decapsulate the target packet data packet, determines the target address information of the target packet data packet, and sends the egress packet data to be processed based on the target address information. The data center egress traffic scheduling system of this invention increases the granularity of data center egress traffic scheduling and improves the flexibility of traffic scheduling.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a scheduling system for data center outbound traffic. Background Art

[0002] SRv6 technology is typically used in transport networks and data center backbones. Designed based on the concept of source routing, SRv6 inserts a Segment Routing Header (SRH) into IPv6 packets, pushing an explicit IPv6 address stack onto the SRH. Intermediate nodes then continuously update the destination address and offset address stack to achieve hop-by-hop forwarding. With the continuous expansion of network scale and the emergence of new services such as 5G and smart cities, SRv6 technology has received strong attention and widespread application in the carrier sector due to its advantages such as protocol simplicity, scalability, programmability, and strong compatibility. However, its application and attention in the data center field are still relatively limited.

[0003] Existing data center outbound traffic scheduling methods are mainly based on the principles of basic network protocols such as Border Gateway Protocol (BGP) and Open Shortest Path First (OSPF). They control the routing rules of control devices to forward outbound traffic and regulate the path based on IP addresses. Alternatively, they can use isolated routing tables (VPN technology) to control the publication of routes and the routing of traffic, directing outbound traffic to designated data center outbound traffic.

[0004] However, existing methods for scheduling data center outbound traffic require extensive routing calculations and manual deployment of terminals with similar needs along the same path or in the same location during construction. This cannot meet the requirements for flexible data center expansion, flexible and precise traffic scheduling.

[0005] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0006] This application provides a data center egress traffic scheduling system to solve the technical problem that existing data center egress traffic scheduling methods cannot meet the requirements of flexible data center expansion and flexible traffic scheduling.

[0007] In a first aspect, this application provides a data center egress traffic scheduling system, the system comprising: an intelligent management and control device, configured to acquire traffic egress information and generate a traffic egress policy for each terminal device based on the traffic egress information, wherein the traffic egress information includes the egress information of each egress gateway among multiple egress gateways scheduled by the scheduling system; a terminal device, configured to perform a first encapsulation process on the egress packet data to be egressed based on the traffic egress policy acquired from the intelligent management and control device, generating a packet data packet, wherein the packet data packet includes: the egress packet data to be egressed and a routing extension header, the routing extension header indicating the path of the packet data; a node device in the data center infrastructure network, configured to receive the packet data packet and perform a second encapsulation process on the egress packet data to be egressed based on the path in the routing extension header, generating a target packet data packet and forwarding it, wherein the target packet data packet includes: the egress packet data to be egressed and a new routing extension header; and an egress gateway device, configured to decapsulate the target packet data packet using the routing extension header, determine the target address information of the target packet data packet, and send the egress packet data to be egressed based on the target address information.

[0008] Optionally, as in the aforementioned scheduling system, the aforementioned traffic egress information specifically includes the egress load and egress quality of each of the multiple egress gateways scheduled by the aforementioned scheduling system; the aforementioned intelligent management and control device is specifically used to obtain the traffic service requirements of each terminal device; based on the aforementioned traffic service requirements and the egress load and egress quality of each egress gateway, traffic path orchestration processing is performed to generate the aforementioned traffic egress strategy.

[0009] Optionally, as in the scheduling system described above, the intelligent management and control device is specifically used to: obtain traffic latency and traffic demand size based on the traffic service requirements; obtain matching candidate egress gateway devices based on the traffic demand size and the egress load of each egress gateway; obtain target egress gateway devices based on the traffic latency and the egress quality of the candidate egress gateways; and perform traffic path orchestration processing based on the network topology of the target egress gateway devices to generate the traffic egress strategy.

[0010] Optionally, as in the aforementioned scheduling system, the aforementioned traffic egress policy includes the egress gateway address information and critical path node address information for traffic forwarding; the aforementioned terminal device is specifically used to perform packet header encapsulation processing on the aforementioned packet data to be egressed based on the aforementioned traffic egress policy obtained from the aforementioned intelligent management and control device, and generate the aforementioned routing extension header, wherein the aforementioned routing extension header encapsulates scheduling information, the aforementioned scheduling information includes the egress gateway device address information, the destination address information, and the critical path node address information; and generate the aforementioned packet data according to the aforementioned routing extension header and the aforementioned packet data to be egressed.

[0011] Optionally, as in the scheduling system described above, the node devices in the data center infrastructure network are specifically used to: receive the aforementioned message data packets; obtain the address information of the egress gateway device and the address information of the critical path node in the routing extension header of the aforementioned message data packets; perform a second encapsulation process on the aforementioned message data packets to be exported based on the egress gateway device address information, the aforementioned destination address information and the aforementioned critical path node address information, generate target message data packets and forward them until they are forwarded to the aforementioned egress gateway device.

[0012] Optionally, as in the scheduling system described above, the egress gateway device is specifically used to: receive the target packet data; decapsulate the target packet data based on the routing extension header to obtain the destination address information; convert the destination address information from an internal network address to an external network address based on preset address translation requirements; and send the packet data to be exported based on the external network address.

[0013] Optionally, as in the scheduling system described above, the aforementioned message data packet is an SRV6 message, and the aforementioned routing extension header is an SRH routing extension header.

[0014] Optionally, as in the scheduling system described above, the scheduling information is encapsulated after the header field of the SRH and before the variable-length TLV portion.

[0015] Optionally, as in the scheduling system described above, the intelligent control device is also used to: interact with each exit device to obtain exit information for each of the aforementioned exit devices.

[0016] Optionally, as in the scheduling system described above, the data center infrastructure network includes multiple node devices, which are used to connect terminal devices and multiple distributed egress gateway devices.

[0017] The data center egress traffic scheduling system provided in this application uses intelligent management and control equipment to acquire traffic egress information and generate a traffic egress policy for each terminal device based on the traffic egress information. The traffic egress information includes the egress information of each egress gateway among multiple egress gateways scheduled by the scheduling system. The terminal device performs a first encapsulation process on the egress packet data to be egressed based on the traffic egress policy acquired from the intelligent management and control equipment to generate a packet data package. The packet data package includes: the egress packet data and a routing extension header, the routing extension header indicating the path of the packet data. Nodes in the data center infrastructure network... The device is used to receive the aforementioned message data packets, and perform a second encapsulation process on the aforementioned message data to be exported based on the path in the aforementioned routing extension header, generating a target message data packet and forwarding it. The target message data packet includes: message data to be exported and a new routing extension header. The export gateway device is used to decapsulate the aforementioned target message data packet using the aforementioned routing extension header, determine the target address information of the aforementioned target message data packet, and send the message data to be exported based on the aforementioned target address information. The data center export traffic scheduling system of the present invention increases the fineness of data center export traffic scheduling and improves the flexibility of traffic scheduling. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] Figure 1 A schematic diagram of the structure of a data center egress traffic scheduling system provided in this application;

[0020] Figure 2 This is a schematic diagram of a routing extension header SRH encapsulation format provided in this application.

[0021] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0022] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0023] In existing technologies, data center egress scheduling methods are mainly based on the configuration and optimization of network protocols on the basis of native IP addresses. Current data center egress scheduling methods include the following: Method 1: The data center egress device uses Border Gateway Protocol (BGP) to send default routes to the data center network, and egress traffic selects the nearest egress point in the network according to the BGP routing principle; Method 2: The data center egress device uses the BGP protocol to send default routes and AS_PATH lists to the data center network, adjusting the routing priority of a certain egress gateway in the data center network through the AS_PATH list, and scheduling some traffic with slightly longer routes to a specific egress point; Method 3: A portion of traffic is imported into a VPN, and a default VPNv4 route is sent to the VPN through a designated gateway device, scheduling the egress traffic of network devices and servers deployed in the VPN to the designated gateway device.

[0024] However, in Method 1, the data center egress device uses the BGP protocol to send default routes into the data center network. Egress traffic can only leave the data center at the nearest egress, which cannot meet the requirements for flexible traffic adjustment, rapid fault convergence, and egress traffic migration. In Method 2, the routing priority of a certain egress in the data center network is adjusted through the AS_PATH list, scheduling some traffic with slightly longer routes to a specific egress. This is still based on the routing principle of the BGP protocol, controlling traffic routing to a specific egress by manually calculating the network protocol length from the terminal to the egress. In the scenario of distributed data centers, there may be scenarios where traffic from multiple data centers needs to go to different egress, or even traffic from adjacent servers in the same data center needs to go to different egress. Using a simple AS_PATH list cannot meet these high-precision egress scheduling requirements. In Method 3, traffic control is performed through VPN technology. VPN traffic must iterate through a tunnel before it can be forwarded. Tunnel technology is complex to configure and has high technical requirements for intermediate equipment, which will introduce additional network equipment acquisition, modification, and maintenance costs. In addition, in ultra-large data centers, the egress device needs to maintain numerous VPN routing tables and corresponding routing protocol relationships, and performance will become a bottleneck in the application process.

[0025] The specific application scenario of this application is the outbound traffic scheduling of data centers. SRv6 technology has received strong attention and widespread application in the carrier field due to its advantages such as simple protocol, scalability, programmability, and strong compatibility, but its application and attention in the data center field are still relatively limited.

[0026] The data center outbound traffic scheduling system provided in this application aims to solve the above-mentioned technical problems of the prior art.

[0027] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0028] Figure 1 This is a schematic diagram of the structure of a data center egress traffic scheduling system provided in this application. Figure 1 As shown, the data center egress traffic scheduling system may include: intelligent management and control device 10, terminal device 20, node device 30 in the data center basic network, and egress gateway device 40.

[0029] In this embodiment, the intelligent management and control device 10 is used to acquire traffic egress information and generate a traffic egress policy for each terminal device based on the traffic egress information; the terminal device 20 is used to perform a first encapsulation process on the data to be egressed based on the traffic egress policy acquired from the intelligent management and control device to generate a data packet, wherein the data packet includes: the data to be egressed and a routing extension header; the node device 30 in the data center infrastructure network is used to receive the data packet and perform a second encapsulation process on the data to be egressed based on the path in the routing extension header to generate a target data packet and forward it, wherein the target data packet includes: the data to be egressed and a new routing extension header; the egress gateway device 40 is used to decapsulate the target data packet using the routing extension header, determine the target address information of the target data packet, and send the data to be egress based on the target address information.

[0030] It should be noted that the above traffic egress information includes the egress information of each of the multiple egress gateways scheduled by the above scheduling system, and also includes the egress load and egress quality of each of the multiple egress gateways scheduled by the above scheduling system; the above routing extension header is used to indicate the path of the above message data.

[0031] It should also be noted that the above message data packet is an SRV6 message, and the above routing extension header is an SRH routing extension header. SRv6 achieves hop-by-hop forwarding by inserting a routing extension header SRH into the IPv6 message and pushing an explicit IPv6 address stack onto the SRH. Intermediate nodes continuously update the destination address and offset address stack.

[0032] As an optional embodiment, the intelligent management and control device 10 is responsible for collecting the load status and egress quality of each gateway egress gateway device 40, and allocating terminal traffic egress policies based on the collected data, and issuing the egress policies to the terminal devices 20 and the data center egress gateway devices 40; the terminal device 20, as the initiator of egress traffic, needs to send traffic to the external network of the data center to meet business needs, and can encapsulate the egress traffic with SRv6 headers according to the policies issued by the intelligent management and control device 10; the node devices 30 in the data center basic network, as the foundation of the data center, connect each terminal and multiple distributed data centers and egress gateway devices; the egress gateway device 40 is responsible for decapsulating the egress traffic with SRH, converting internal and external network addresses, and finally sending the egress packet data based on the converted address.

[0033] In one optional embodiment, the aforementioned data center infrastructure network includes multiple node devices, which are used to connect terminal devices and multiple distributed egress gateway devices.

[0034] Through the embodiments of this application, the packet path is programmed and managed using the Software Defined Network (SDN) method and SRv6 technology. No network equipment needs to be modified or adapted, and the gateway device does not need to maintain any protocol relationships. It only needs to perform simple decapsulation processing on the packets to achieve the technical effect of fine-grained and flexible scheduling of data center outbound traffic by using SRv6 to carry key forwarding nodes, outbound gateway devices and final destination addresses.

[0035] In one optional embodiment, the aforementioned intelligent management and control device is specifically used to acquire the traffic service requirements of each terminal device; based on the aforementioned traffic service requirements and the egress load and egress quality of each egress gateway, it performs traffic path orchestration processing to generate the aforementioned traffic egress strategy.

[0036] As an optional embodiment, the intelligent management and control device performs traffic path orchestration processing based on the traffic service requirements of each terminal device and the outbound load and quality information of each outbound gateway device, and generates the traffic outbound strategy based on the orchestration processing results.

[0037] In one optional embodiment, the intelligent management and control device is specifically used to: obtain traffic latency and traffic demand size according to the traffic service requirements; obtain matching candidate egress gateway devices according to the traffic demand size and the egress load of each egress gateway; obtain target egress gateway devices according to the traffic latency and the egress quality of the candidate egress gateways; and perform traffic path orchestration processing according to the network topology of the target egress gateway devices to generate the traffic egress strategy.

[0038] As an optional embodiment, in a data center egress traffic scheduling system, the aforementioned intelligent management and control device can be used to acquire traffic service demands in real time, determine the traffic latency and traffic demand size within these demands, and acquire the egress load of each egress gateway in real time. Based on the traffic demand size within the traffic service demands, suitable candidate egress gateway devices can be matched. For example, after acquiring the traffic service demands, the intelligent management and control device first determines the traffic demand size within the demands and simultaneously acquires the egress load of each egress gateway. If the egress load meets preset requirements, candidate egress gateway devices are determined based on the traffic demand size.

[0039] Optionally, it is also necessary to determine the target egress gateway device based on the traffic latency in the business requirements and the egress quality of the candidate egress gateway devices. For example, traffic services with lower traffic latency can be preferentially assigned to egress gateway devices with lower egress quality but meeting the egress quality requirements, while traffic services with higher traffic latency can be preferentially assigned to egress gateway devices with higher egress quality.

[0040] Optionally, after determining the target egress gateway device, traffic path orchestration is performed based on the network topology of the target egress gateway device to obtain the orchestration result. The traffic egress policy is then generated based on this orchestration result. The traffic egress information obtained through the intelligent management and control device, along with the generated traffic egress policy for each terminal device, enables fine-grained scheduling of data center egress traffic. This eliminates the need to maintain numerous VPN routing tables and corresponding routing protocol relationships, and also avoids manually calculating the network protocol length from the terminal to the egress to control traffic routing to a specific egress.

[0041] It should be noted that the above process of matching egress gateway devices and allocating traffic services is for illustrative purposes only. In actual applications, it can be adjusted or changed according to the actual situation.

[0042] In one optional embodiment, the traffic egress policy includes egress gateway address information and critical path node address information for traffic forwarding; the terminal device is specifically used to perform packet header encapsulation processing on the packet data to be egressed based on the traffic egress policy obtained from the intelligent management and control device, generate the routing extension header, and generate the packet data according to the routing extension header and the packet data to be egressed.

[0043] As an optional embodiment, the terminal device receives traffic scheduling configuration from the intelligent management and control device, encapsulates the SRH packet header according to the configuration as outbound traffic, and generates the aforementioned routing extension header. The routing extension header encapsulates scheduling information, including outbound gateway device address information, destination address information, and critical path node address information.

[0044] Optional, such as Figure 2 The diagram illustrates the SRH (Segment Routing Header) encapsulation format. SRv6 achieves hop-by-hop forwarding by inserting a SRH into the IPv6 packet, pushing an explicit IPv6 address stack onto the SRH, and having intermediate nodes continuously update the destination address and offset address stacks. To enable data center outbound traffic to be adjusted as needed, the terminal device sending traffic (which can be a server) encapsulates an SRv6 header into the original packet according to actual traffic requirements, and encapsulates the outbound information and the key node information that must be passed to reach the corresponding outbound into the SRH.

[0045] Optional, as before Figure 2 As shown, the next header can also be represented as "next header," the last entry as "last entry," the header extension length as "hdr etx len," the Flags attribute as the Flags attribute in a programming language (VB), the routing type as "routing type," the remaining segments as "segments left," the tag as "tag," and the variable-length TLV part as "optional TLV objects." Through the format and field definitions of SRv6 scheduling messages, SRv6 message data carries key forwarding nodes, egress gateway devices, and the final destination address, thereby achieving fine-grained scheduling of data center egress traffic. Utilizing the programmable space in the IPv6 message header, and employing SDN methods and SRv6-related technologies, message paths can be programmed and managed without any modifications or adaptations to network devices. Gateway devices do not need to maintain any protocol relationships; they only need to perform simple decapsulation and repackaging of messages, reducing manual workload and improving efficiency.

[0046] It should be noted that the above scheduling information is encapsulated after the header field of the SRH and before the variable-length TLV part.

[0047] In one optional embodiment, the node device in the aforementioned data center infrastructure network is specifically configured to: receive the aforementioned packet data; obtain the aforementioned egress gateway device address information and the aforementioned critical path node address information from the aforementioned routing extension header in the aforementioned packet data; perform a second encapsulation process on the aforementioned packet data to be exported based on the aforementioned egress gateway device address information, the aforementioned destination address information and the aforementioned critical path node address information, generate a target packet data and forward it until it is forwarded to the aforementioned egress gateway device.

[0048] As an optional embodiment, the encapsulated data packet (the aforementioned packet data) enters the node device in the data center infrastructure network. The node device re-encapsulates the packet data to be exported according to the egress gateway device address information, the destination address information, and the critical path node address information indicated by the SRH, and forwards it to the egress gateway device based on the egress gateway device address information and the critical path node address information.

[0049] In one optional embodiment, the aforementioned egress gateway device is specifically configured to: receive the aforementioned target packet data; decapsulate the aforementioned target packet data based on the aforementioned routing extension header to obtain the aforementioned destination address information; convert the aforementioned destination address information from an internal network address to an external network address based on a preset address translation requirement; and send the packet data to be egressed based on the aforementioned external network address.

[0050] As an optional embodiment, after receiving a data packet containing a re-encapsulated SRH header, the egress gateway device decapsulates the SRH header, converts the actual destination IP carried in the SRH header into the destination IP of the final egress packet, performs source address translation according to the preset requirements of the intelligent control device, determines the translated address as the source IP of the final egress packet, and performs transmission processing based on the aforementioned source IP of the egress packet.

[0051] In an optional embodiment, the aforementioned intelligent control device is further configured to: interact with each exit device to obtain exit information for each of the aforementioned exit devices.

[0052] In this embodiment of the application, the format and field definition of the scheduling message based on SRv6 enable the SRv6 message to carry key forwarding nodes, egress gateway devices and final destination addresses, and achieve fine-grained scheduling of data center egress traffic based on the traffic egress information obtained by the intelligent management and control device and the traffic egress policy generated for each terminal device.

[0053] Through the embodiments of this application, the packet path is programmed and managed using software-defined networking methods and SRv6 technology. No network devices need to be modified or adapted, and the gateway device does not need to maintain any protocol relationships. It only needs to perform simple decapsulation processing on the packets to achieve the technical effect of using SRv6 to carry key forwarding nodes, egress gateway devices and final destination addresses, thereby achieving fine-grained and flexible scheduling of data center egress traffic.

[0054] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

[0055] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0056] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0057] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0058] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0059] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0060] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0061] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as these combinations of technical features do not contradict each other, they should be considered within the scope of this specification.

[0062] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0063] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A scheduling system for data center egress traffic, characterized in that, The system includes: Intelligent management and control equipment is used to acquire traffic exit information and generate a traffic exit strategy for each terminal device based on the traffic exit information, wherein the traffic exit information includes the exit information of each exit gateway among the multiple exit gateways scheduled by the scheduling system. A terminal device is configured to perform a first encapsulation process on the outgoing packet data based on the traffic outgoing policy obtained from the intelligent management and control device, and generate a packet data packet, wherein the packet data packet includes: the outgoing packet data and a routing extension header, the routing extension header being used to indicate the path of the packet data; A node device in the data center infrastructure network is used to receive the packet data and perform a second encapsulation process on the packet data to be exported based on the path in the routing extension header, generate a target packet data and forward it, wherein the target packet data includes: the packet data to be exported and a new routing extension header; An egress gateway device is used to decapsulate the target packet data using the routing extension header, determine the target address information of the target packet data, and send the packet data to be egressed based on the target address information.

2. The scheduling system according to claim 1, characterized in that, The traffic exit information specifically includes the exit load and exit quality of each of the multiple exit gateways scheduled by the scheduling system; The intelligent management and control device is specifically used to acquire the traffic service requirements of each terminal device. Based on the traffic service requirements and the egress load and egress quality of each egress gateway, traffic path orchestration is performed to generate the traffic egress policy.

3. The scheduling system according to claim 2, characterized in that, The intelligent control device is specifically used for: Based on the traffic service requirements, obtain the traffic latency and traffic demand size; Based on the traffic demand and the outbound load of each outbound gateway, obtain matching candidate outbound gateway devices; Based on the traffic latency and the egress quality of the candidate egress gateways, the target egress gateway device is obtained; Based on the network topology of the target egress gateway device, traffic path orchestration is performed to generate the traffic egress policy.

4. The scheduling system according to claim 1, characterized in that, The traffic egress strategy includes the egress gateway address information and critical path node address information for traffic forwarding; The terminal device is specifically used to encapsulate the header of the message data to be exported based on the traffic export policy obtained from the intelligent management and control device, and generate the routing extension header. The routing extension header encapsulates scheduling information, which includes export gateway device address information, destination address information and critical path node address information. The packet data is generated based on the routing extension header and the packet data to be exported.

5. The scheduling system according to claim 4, characterized in that, The node devices in the data center infrastructure network are specifically used for: Receive the message data packet; Obtain the egress gateway device address information and the critical path node address information from the routing extension header in the message data packet; Based on the egress gateway device address information, the destination address information, and the critical path node address information, the packet to be exported is subjected to a second encapsulation process to generate a target packet and forward it until it is forwarded to the egress gateway device.

6. The scheduling system according to claim 5, characterized in that, The egress gateway device is specifically used for: Receive the target message data packet; The destination address information is obtained by decapsulating the target packet based on the routing extension header. Based on preset address translation requirements, the destination address information is converted from an internal network address to an external network address; The data to be sent is processed based on the external network address.

7. The scheduling system according to claim 4, characterized in that, The message data packet is an SRV6 message, and the routing extension header is an SRH routing extension header.

8. The scheduling system according to claim 7, characterized in that, The scheduling information is encapsulated after the header field of the SRH and before the variable-length TLV portion.

9. The scheduling system according to claim 1, characterized in that, The intelligent control device is also used to: interact with each exit device to obtain exit information for each exit device.

10. The scheduling system according to any one of claims 1 to 9, characterized in that, The data center infrastructure network includes multiple node devices, which are used to connect terminal devices and multiple distributed egress gateway devices.

Images