WO2023019669A1 - Cdn quality inspection method and system, server, and storage medium - Google Patents

Abstract

A CDN quality inspection method and system, a server, and a storage medium. The method comprises: constructing multiple detection data packets, each detection data packet carrying a line identifier of one of multiple BGP lines from a CDN node to a target autonomous system (AS) (101); according to the line identifier carried in the detection data packet, sending the detection data packet from the CDN node to the target AS by means of the BGP line corresponding to the line identifier (102); and on the basis of the sent detection data packet, separately testing the multiple BGP lines to obtain a network quality parameter of each BGP line (103).

Description

CDN network quality detection method, system, server and storage medium

cross reference

This application is based on the Chinese patent application with the application number "202110956987.4" and the filing date is August 19, 2021, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby incorporated by reference. Apply.

technical field

The embodiments of the present application relate to the technical field of the Internet, and in particular to a CDN network quality detection method, system, server and storage medium.

Background technique

Content Delivery Network (CDN for short) is an intelligent virtual network built on the basis of the existing network, relying on the edge servers deployed in various places, through the load balancing, content distribution, scheduling and other functional modules of the central platform, so that users Obtain the desired content nearby, reduce network congestion, and improve user access response speed and hit rate.

The birth of the CDN network has greatly improved the service quality of the Internet. Therefore, traditional large-scale network service providers have begun to build their own CDN networks. The competition in the CDN field has become increasingly fierce, and customers have increasingly stringent requirements for service quality. A delay of just a few milliseconds may even determine the customer's choice of service provider. Therefore, a high-quality service network is becoming more and more important. There is no effective reference for service deployment, resulting in suboptimal service coverage. Based on the current CDN architecture, the next-generation CDN (NGCDN) is imminent. In addition to the business level and the network level, service providers hope to have more effective quality monitoring, network optimization and performance improvement. Therefore, how to improve the quality of customer service has become an urgent problem for service providers to solve.

Contents of the invention

The purpose of the embodiments of the present application is to provide a CDN network quality detection method, system, server and storage medium, which can effectively detect the CDN network quality, thereby improving the customer service quality of the CDN network.

The embodiment of the present application provides a method for detecting the quality of a CDN network. The CDN network includes: a CDN node, a plurality of autonomous systems AS provided by a plurality of network operators, the CDN node, and the plurality of autonomous systems AS Interconnected through Border Gateway Protocol BGP; the method includes: constructing a plurality of detection data packets, each of which carries the line identification of a BGP line in the multiple BGP lines from the CDN node to the target autonomous system AS ; According to the line identification carried in the detection data packet, the detection data packet is sent from the CDN node to the target autonomous system AS through the BGP line corresponding to the line identification; The multiple BGP lines are tested respectively to obtain network quality parameters of each BGP line.

The embodiment of the present application also provides a CDN network quality detection system, the CDN network includes: a CDN node, a plurality of autonomous systems AS provided by a plurality of network operators, the CDN node, the plurality of autonomous systems AS The ASs are interconnected through the Border Gateway Protocol BGP; the system further includes: a server located inside the CDN node, the server is used to schedule the CDN network to execute the CDN network quality detection method as described above.

The embodiment of the present application also provides a server, including: at least one processor; and a memory connected in communication with the at least one processor; wherein, the memory stores the information executable by the at least one processor Instructions, the instructions are executed by the at least one processor, so that the at least one processor can execute the CDN network quality detection method as described above.

Embodiments of the present application also provide a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the method for detecting the quality of a CDN network as described above is implemented.

In the implementation mode of this application, for a CDN network including CDN nodes and multiple autonomous systems AS provided by multiple network operators, the CDN nodes and multiple autonomous system ASs are interconnected through the Border Gateway Protocol BGP; by constructing multiple detection Each detection packet carries the line identifier of one of the multiple BGP lines from the CDN node to the target autonomous system AS; according to the line identifier carried in the detection packet, the detection packet is mapped to the The BGP lines are sent from the CDN node to the target autonomous system AS; multiple BGP lines are tested based on the sent detection packets, and the network quality parameters of each BGP line are obtained, so as to realize the communication between the CDN node and the target autonomous system AS. Evaluate the quality of each BGP line, so as to provide support for related operations based on the network quality of each BGP line. For example, by regularly adopting the CDN network quality detection method of this solution, the optimal BGP line serving each area can be obtained, thereby providing effective support and reference for background business deployment.

In addition, according to the network quality parameters of the respective BGP lines, the BGP lines used by the service flow between the CDN node and the target autonomous system AS are regulated, and/or the detected BGP lines are failure analysis. In this way, the BGP line used by the service traffic can be flexibly regulated, and/or, fault analysis can be performed on the BGP line.

In addition, according to the network quality parameters of the respective BGP lines, regulating the BGP lines used by the service flow between the CDN node and the target autonomous system AS includes: determining the CDN node to the The BGP line used by the service flow of the target autonomous system AS; after adding the line identifier corresponding to the determined BGP line to the data packet of the service flow, the data packet is sent from the CDN node. By adding the line identifier corresponding to the BGP line in the data packet of the service flow, the data packet is transmitted through the preferred BGP line, and the packet receiving experience of the customer in the target autonomous system is improved.

In addition, the line identifier is a differential service code point DSCP; the construction of the detection data packet includes: setting the coding value of the differential service code point DSCP of each detection data packet to one of a plurality of preset coding values Either one, the plurality of preset coded values correspond one-to-one to the first autonomous system AS interconnected with the CDN node among the plurality of BGP lines; according to the line identifier carried in the detection data packet, Sending the detection data packet from the CDN node to the target autonomous system AS through the BGP line corresponding to the line identifier includes: according to the code value of the differentiated service code point DSCP carried in the detection data packet, the The detection data packet is forwarded to the autonomous system AS corresponding to the code value, and the detection data packet is sent from the CDN The node sends to the target autonomous system AS. Use DSCP as the line identifier to specify the first AS after the detection data packet leaves the CDN node, so that based on the BGP route selection rules, the BGP line including the first AS can be selected to send the detection data packet.

In addition, the source address of the detection packet sent from the CDN node to the target autonomous system AS is a plurality of addresses in the IP address segment corresponding to the CDN node, and corresponds to the plurality of BGP lines one by one; correspondingly The sending the detection data packet from the CDN node to the target autonomous system AS includes: according to the source address of the detection data packet, passing a plurality of the detection data packets respectively through the source of each detection data packet The BGP line corresponding to the address is sent to the target autonomous system. By differently setting the source addresses of the detection data packets used to detect different BGP lines, it is convenient to distinguish the network quality parameters obtained by testing different BGP lines.

In addition, the CDN node is a CDN node in a unicast communication scenario; according to the network quality parameters of each BGP line, the BGP used for the service flow between the CDN node and the target autonomous system AS Regulating the line includes: according to the network quality parameters of each BGP line, setting one or more IP address segments corresponding to the target autonomous system AS to access through one of the BGP lines respectively; Different service flows between the CDN node and the target autonomous system AS are correspondingly sent to one IP address segment in the plurality of IP address segments. By specifying different IP address segments of the target self-made system AS to use different BGP lines for access, access control based on the current state of network quality in unicast communication can be implemented.

In addition, the CDN node is a CDN node in anycast communication scenario; according to the network quality parameters of each BGP line, the BGP used for the service flow between the CDN node and the target autonomous system AS Line regulation includes: according to the network quality parameters of the BGP lines corresponding to each of the CDN nodes in anycast communication scenarios, determining the network quality of each of the CDN nodes covering the target autonomous system AS; according to each of the CDN nodes The node covers the network quality of the target autonomous system AS, and adjusts the range of the target autonomous system AS covered by anycast of each CDN node. On the basis of unicast, by confirming that each CDN node covers the network quality of the corresponding target self-made system AS, the network quality of each CDN node covering AS can be obtained; and then by adjusting the coverage of each node AS range, so as to achieve the optimal coverage of each CDN node on the AS.

Description of drawings

One or more embodiments are exemplified by the pictures in the corresponding drawings, and these exemplifications do not constitute a limitation to the embodiments. Elements with the same reference numerals in the drawings represent similar elements. Unless otherwise stated, the drawings in the drawings are not limited to scale.

FIG. 1 is a structural diagram of a CDN network topology according to a first embodiment of the present application;

FIG. 2 is a structural diagram of a CDN network topology according to the first embodiment of the present application;

FIG. 3 is a specific flow chart of a CDN network quality detection method according to the first embodiment of the present application;

FIG. 4 is a specific flow chart of a CDN network quality detection method according to the second embodiment of the present application;

FIG. 5 is a specific flowchart of a CDN network quality detection method according to a third embodiment of the present application;

FIG. 6 is a structural diagram of a CDN network topology according to a third embodiment of the present application;

FIG. 7 is a specific flowchart of a CDN network quality detection method according to a fourth embodiment of the present application;

FIG. 8 is a specific flowchart of a CDN network quality detection method according to a fifth embodiment of the present application;

FIG. 9 is a specific flow chart of a CDN network quality detection method according to the sixth embodiment of the present application;

FIG. 10 is a structural diagram of a CDN network topology according to a sixth embodiment of the present application;

Fig. 11 is a schematic structural diagram of a server according to an eighth embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, various implementations of the present application will be described in detail below in conjunction with the accompanying drawings. However, those of ordinary skill in the art can understand that, in each implementation manner of the present application, many technical details are provided for readers to better understand the present application. However, even without these technical details and various changes and modifications based on the following implementation modes, the technical solution claimed in this application can also be realized.

The first embodiment of the present application relates to a method for detecting the quality of a CDN network. As shown in FIG. 1, the CDN network includes: a CDN node (CDN Node), a plurality of autonomous systems (Autonomous System, AS for short), such as AS 1299, AS 2914, AS 6453 and AS Client shown in Figure 1; CND nodes and multiple ASs are interconnected through Border Gateway Protocol (BGP). The CDN Node has multiple BGP lines, which broadcast the 1.1.1.0/24 network segment to the outside world, and learn the AS client network segment 2.2.2.0/24 through the three BGP lines shown in Figure 1. For the convenience of illustration, only the first AS directly connected to the CDN Node egress among the three BGP lines is shown in Fig. AS client) are schematically covered in the Internet network. It should be noted that, according to the actual network distribution, each BGP line leading to the AS client may only contain the AS provided by one network operator, or contain ASs provided by multiple network operators at the same time. In Figure 1, only It exemplarily shows three ASs provided by network operators that are directly connected to the egress of the CND node.

By default, the CDN Node will automatically select a BGP line as the optimal line to reach the AS Client according to the BGP routing rules, as shown in Figure 2. For example, when the BGP line where AS1299 is located, all access 2.2.2.0/24( The traffic of AS client) will pass through the BGP line where AS1299 is located first, and the BGP lines where AS2914 and AS6453 are located are used as a backup solution. The route rule is selected as the optimal route and used as the route to reach the AS Client. In this process, the network quality of other BGP lines is not known, which makes it impossible to perform reasonable related operations based on the network quality of each BGP line, such as traffic control and fault analysis on each BGP line.

The CDN network quality detection method provided by the embodiment of the present application specifies to send a detection packet to the destination AS (such as the AS Client in Figure 1) through a specific BGP line, so as to realize the detection of each BGP line leading to the destination AS. Network quality parameters are detected to find the optimal BGP line usage strategy, optimize and guide line regulation.

As shown in Figure 3, the CDN network quality detection method provided by the embodiment of the present application can schedule the CDN node to execute through the test server connected to the CDN node, including the following steps:

Step 101: Construct multiple detection data packets, and each detection data packet carries the line identifier of one of the multiple BGP lines from the CDN node to the target autonomous system AS.

Specifically, when the test server constructs the detection data packet, in addition to adding the basic data content used to detect the network quality parameters of the BGP line to the data packet, the detection data packet also carries the line identifier used to indicate the BGP line, indicated The BGP line of is any one of multiple BGP lines leading from the CDN node to the target autonomous system AS. The line identifier can exist in data formats supported by multiple data packets, and can also borrow specified identifier bits in existing data packets.

Step 102: According to the line identification carried in the detection data packet, the detection data packet is sent from the CDN node to the target autonomous system AS through the BGP line corresponding to the line identification.

By default, the CDN Node will pre-learn the multiple BGP lines leading to the target autonomous system locally, such as the above-mentioned access to the AS Client, but when allocating traffic for accessing the AS Client, it will select a BGP route according to the BGP routing rules lines to transmit access traffic. In this embodiment, the test server can be used to intervene in the action of CDN Node sending data packets, so that the router of CDN Node does not use BGP routing rules when sending detection data packets, but transmits detection data packets through pre-designated BGP lines , so as to realize the process of sending the detection data packet from the CDN node to the target autonomous system through different BGP lines.

Among them, this embodiment does not limit the action mode of intervening in CDN Node sending data packets, for example, it is possible to control the sending of detection packets through different CDN Node addresses or ports, and specify the corresponding relationship between these addresses or ports and BGP lines, so that Make the router select the corresponding BGP line to send by detecting the sending address or port of the data packet; for another example, a line identification for identifying the BGP line can be added in the detection data packet, and the router can identify the line identification in the detection data packet. Therefore, the BGP line corresponding to the line identifier is selected to send the detection data packet.

Wherein, the detection data packet can be the detection data packet used in at least one detection method in ICMP Ping, TCP Ping, UDP Ping, and http detection.

Step 103: Test multiple BGP lines respectively based on the sent detection data packets, and obtain network quality parameters of each BGP line.

Specifically, after the CDN node sends the detection data packet, it will receive the response data packet of the detection data packet from the target autonomous system AS, and the test server will learn the network quality parameters used to evaluate the quality of the BGP line based on the response data.

For example, when ICMP Ping, TCP Ping, and UDP Ping are used for detection, 180 detection packets can be sent per minute for detection, and the detection results within five minutes are output; when http detection is used, the pull can be determined by pulling the corresponding url The response time required by the corresponding file, etc.

Wherein, the network quality parameters of the BGP line obtained through the test may include: at least one of average delay, average packet loss rate, TCP average delay, UDP average delay, and bandwidth.

In the implementation mode of this application, for a CDN network including CDN nodes and multiple autonomous systems AS provided by multiple network operators, the CDN nodes and multiple autonomous system ASs are interconnected through the Border Gateway Protocol BGP; by constructing multiple detection data Each detection packet carries the line identifier of one of the multiple BGP lines from the CDN node to the target autonomous system AS; according to the line identifier carried in the detection packet, the detection packet is passed through the corresponding The BGP line is sent from the CDN node to the target autonomous system AS; multiple BGP lines are tested based on the sent detection packets, and the network quality parameters of each BGP line are obtained, so as to realize the detection of each link between the CDN node and the target autonomous system AS. Evaluate the quality of each BGP line to provide support for related operations based on the network quality of each BGP line. For example, by regularly adopting the CDN network quality detection method of this solution, the optimal BGP line serving each area can be obtained, thereby providing effective support and reference for background business deployment.

The second implementation manner of the present application relates to a CDN network quality detection method. The second embodiment is an improvement made on the basis of the first embodiment. The improvement is: after obtaining the network quality parameters of each BGP line, according to the network quality parameters of each BGP line, the CDN node to the target autonomous system AS Regulate the BGP lines used by the business traffic between them, and/or perform fault analysis on the detected BGP lines.

As shown in Fig. 4, the above method further includes the following steps.

Step 104: According to the network quality parameters of each BGP line, adjust the BGP line used by the service flow between the CDN node and the target autonomous system AS, and/or perform fault analysis on the detected BGP line.

Specifically, according to the network quality parameters of each BGP line, the network quality level of each BGP line can be determined from multiple BGP lines leading from the CDN node to the target autonomous system, and then related operations based on the network quality level can be performed, including such as Regulation of business traffic on BGP lines, and analysis of whether faults occur on each BGP line.

Specifically, through the above network quality test on multiple BGP lines, it is possible to accurately calculate the network quality parameters such as the time delay for each line to reach the destination AS, packet loss, and bandwidth, so as to calculate the network quality parameters of the CDN nodes covering the corresponding area. The quality level of the line, and complete related operations based on the quality level. For example, when the existing bandwidth of a certain BGP line exceeds the specified threshold, the automatic dispatching system can use this data to perform optimization processing, and dispatch the coverage traffic in some areas to the suboptimal line, so as to achieve coverage optimization and service quality stability.

In an example, according to the network quality parameters of each BGP line, the BGP line used by the service flow between the CDN node and the target autonomous system AS is regulated, which may specifically include:

Determining the BGP line used by the business flow from the CDN node to the target autonomous system AS; adding the line identifier corresponding to the determined BGP line to the data packet of the business flow, and sending the data packet from the CDN node.

For example, by comparing the network quality parameters of multiple BGP lines from the CDN node to the target autonomous system AS, the BGP lines used for subsequent transmission of different service flows are determined. During subsequent service flow transmission, the test server may add the line identifier corresponding to the determined BGP line to the data packet corresponding to the service flow, and the CDN node sends the data packet. The border router can forward the data packet to the corresponding BGP line according to the configuration policy, so as to transmit the data packet to the target autonomous system AS through the BGP line. For the specific sending process, reference may be made to the aforementioned processing process of sending the detection data packet, which will not be repeated here.

The embodiment of the present application utilizes the detected network quality parameters of each BGP line to realize the regulation and control of the service flow on each BGP line, as well as the line fault analysis, and realizes the optimization and maintenance of the CDN node network. In particular, by adding the line identifier corresponding to the BGP line in the data packet of the service flow, the data packet is transmitted through the preferred BGP line, and the packet receiving experience of the customer in the target autonomous system is improved.

The third embodiment of the present application relates to a CDN network quality detection method. The third embodiment is an improvement made on the basis of the first embodiment. The improvement is that: the above-mentioned line is marked as a differential service code point DSCP; correspondingly, the process of constructing multiple detection data packets includes: setting each detection data The coding value of the differentiated service code point DSCP of the packet is any one of multiple preset coding values, and the multiple preset coding values correspond one-to-one to the first autonomous system AS interconnected with the CDN node among the multiple BGP lines. Correspondingly, according to the line identification carried in the detection data packet, sending the detection data packet from the CDN node to the target autonomous system AS through the BGP line corresponding to the line identification includes: according to the differential service code point carried in the detection data packet DSCP code value, the detection data packet is forwarded to the autonomous system AS corresponding to the code value, and the detection data packet is sent from the CDN node through the BGP circuit with the autonomous system AS as the first autonomous system AS Send to the target autonomous system AS.

As shown in FIG. 5 , the above step 101 includes the following sub-steps.

Sub-step 1011: set the code value of the differential service code point DSCP of each probe data packet to any one of multiple preset code values, the multiple preset code values and the first BGP line interconnected with the CDN node There is a one-to-one correspondence between autonomous systems AS.

For example, as shown in Figure 6, when the test server (Test Server) constructs the detection data packet, in all the detection data packets that need to be transmitted through the BGP line where AS 1299 is located, the service in the IP header of each data packet The category TOS identification byte will be automatically marked with the DSCP 8 identification; in all detection packets that need to be transmitted through the BGP line where AS 2914 is located, the service category TOS identification byte in the IP header of each data packet will be It is automatically marked with DSCP 9; in all detection packets that need to be transmitted through the BGP line where AS 6453 is located, the service category TOS identification byte in the IP header of each data packet will be automatically marked with DSCP 10 .

Correspondingly, step 102 includes the following sub-steps.

Sub-step 1021: According to the code value of the differentiated service code point DSCP carried in the probe data packet, forward the probe data packet to the autonomous system AS corresponding to the code value, and use the autonomous system AS as the first A BGP line of an autonomous system AS sends a detection packet from the CDN node to the target autonomous system AS.

For example, as shown in Figure 6, when the test server constructs the detection data packet, because in all the detection data packets that need to be transmitted through the BGP line where AS 1299 is located, the service category TOS identification byte in the IP header of each data packet DSCP 8 is automatically marked in the network, so that after the relevant traffic reaches the border router, it will match the policy and automatically forward the traffic from the line where AS 1299 is located; because all detection data that needs to be transmitted through the BGP line where AS 2914 is located In the packet, the TOS identification byte of the IP header of each data packet is automatically marked with the DSCP 9 identification, so that after the relevant traffic reaches the border router, it will match the policy and automatically route the traffic from the line where the corresponding AS 2914 is located. Forwarding; because in all detection packets that need to be transmitted through the BGP line where AS 6453 is located, the service category TOS identification byte of each data packet IP header is automatically marked with DSCP 10, so that the relevant traffic reaches the border router After that, the policy will be matched and the traffic will be automatically forwarded from the line where the corresponding AS 6453 is located. After receiving the detection data packet, the first AS of each BGP line sends the detection data packet to the target autonomous system according to the pre-learned routing path on the BGP line.

In the embodiment of the present application, by setting the line identifier in the detection data packet, the detection data is sent to the target autonomous system through the specified BGP line by intervention control, so as to realize the test of the corresponding BGP line. Further, the DSCP is used as the line identifier to designate the first AS after the detection data packet leaves the CDN node, so that the BGP line including the first AS can be selected based on the BGP route selection rules to send the detection data packet.

The fourth implementation manner of the present application relates to a CDN network quality detection method. The fourth embodiment is an improvement made on the basis of any of the above embodiments. The improvement is that the source address of the probe data packet sent from the CDN node to the target autonomous system AS is a plurality of addresses in the IP address segment corresponding to the CDN node , and corresponds to multiple BGP lines one by one; correspondingly, sending the detection data packet from the CDN node to the target autonomous system AS includes: according to the source address of the detection data packet, passing multiple detection data packets through the The BGP line corresponding to the source address is sent to the target autonomous system. By differently setting the source addresses of the detection data packets used to detect different BGP lines, it is convenient to distinguish the network quality parameters obtained by testing different BGP lines.

As shown in Figure 7, the above step 102 may specifically include:

Step 1022: According to the source address of the detection data packet, send multiple detection data packets to the target autonomous system respectively through the BGP line corresponding to the source address of each detection data packet; wherein, the detection data sent from the CDN node to the target autonomous system AS The source address of the packet is multiple addresses in the IP address segment corresponding to the CDN node, and corresponds to multiple BGP lines one by one.

For example, for the CDN network shown in Figure 6, the test server can respectively configure three test addresses as the source addresses of the probe data packets to test the network quality of the three BGP lines reaching the destination AS (AS Client in the figure). For example, the source address of the probe data packet via AS 1299 can be configured as 1.1.1.1, so that the relevant traffic originating from 1.1.1.1 reaches the AS Client through the BGP line where AS 1299 is located; the source address of the probe data packet via AS 2914 The address can be configured as 1.1.1.2, so that the relevant traffic originating from 1.1.1.2 can reach the AS Client through the BGP line where AS 2914 is located; The traffic related to 1.1.1.3 reaches AS Client through the BGP line where AS 6453 is located.

In this way, when the test server receives the corresponding response data packet, it can distinguish which BGP line the response data packet is for. Of course, the specific content included in the response data packet can also be used to distinguish which BGP line the response data packet is for. The specific content may be the content agreed upon with the probe data packet.

In the embodiment of the present application, the source addresses of the detection data packets used to detect different BGP lines are set differently, so as to facilitate the distinction of the network quality parameters obtained by testing different BGP lines.

The fifth implementation manner of the present application relates to a CDN network quality detection method. The fifth embodiment is an improvement made on the basis of the above embodiments. The improvement is that: the CDN node is a CDN node in a unicast communication scenario; correspondingly, according to the network quality parameters of each BGP line, the CDN node Regulate the BGP lines used by the service traffic to the target autonomous system AS, including: according to the network quality parameters of each BGP line, set one or more IP address segments corresponding to the target autonomous system AS through a BGP line respectively Access: According to the preset control strategy, different business traffic between the CDN node and the target autonomous system AS is correspondingly sent to one of the multiple IP address segments, so as to realize the traffic regulation in the unicast communication scenario.

As shown in FIG. 8, the above step 104 may include the following sub-steps.

Sub-step 1041: According to the network quality parameters of each BGP line, set one or more IP address segments corresponding to the target autonomous system AS to access through a BGP line respectively.

As shown in Figure 6, the CDN Node has multiple BGP lines, which broadcast the 1.1.1.0/24 network segment to the outside world, and learn the AS client network segment 2.2.2.0/24 through the three BGP lines shown in Figure 6.

Build a test server inside the CDN Node, and set the test address as follows.

Table 1 Test address

test address	Flow ID	Corresponding line	AS	DSCP
1.1.1.1	————	Telia	1299	8
1.1.1.2	__________	NTT	2914	9
1.1.1.3	--------	TATA	6453	10

The test server is configured with 3 test addresses as the source addresses of the probe data packets, which are used to test the network quality of the 3 BGP lines reaching the destination AS (AS Client in the figure). For example, the source address of the detection data packet via AS 1299 can be configured as 1.1.1.1, and all the traffic originating from 1.1.1.1 will be automatically marked with DSCP 8 after testing so that the related traffic originating from 1.1.1.1 , reach the AS Client via the BGP line where AS 1299 is located; the source address of the probe data packet via AS 2914 can be configured as 1.1.1.2, and all traffic originating from 1.1.1.2 will be automatically marked with DSCP 9 after testing In this way, the relevant traffic originating from 1.1.1.2 can reach the AS Client via the BGP line where AS 2914 is located; the source address of the detection data packet via AS 6453 can be configured as 1.1.1.3, and all traffic originating from 1.1.1.3 can be routed through The test server will be marked with DSCP 10 automatically so that the relevant traffic originating from 1.1.1.3 will reach AS Client through the BGP line where AS 6453 is located.

Based on the response data packets corresponding to the detection data packets, the test server can obtain the network quality parameters of different BGP lines as follows.

Table 2 Network quality parameters

Through the above BGP line test, it is possible to accurately calculate the network quality parameters such as the delay of each line to the destination AS, packet loss and bandwidth, and thus calculate the optimal line for the CDN node to cover the corresponding area. For example, when the existing bandwidth of a certain BGP line exceeds the specified threshold, the automatic dispatching system can use this data to perform optimization processing, and dispatch the coverage traffic in some areas to the suboptimal line, so as to achieve coverage optimization and service quality stability. In order to facilitate the adjustment of the traffic on each line, you can set the routes announced by the AS client to have three IP address segments: 2.2.2.0/24, 3.3.3.0/24, and 4.4.4.0/24, and set each address segment Access through a BGP line to realize the association between each network segment and the BGP line.

Sub-step 1042: According to the preset control strategy, correspondingly send different service flows between the CDN node and the target autonomous system AS to one IP address segment among the plurality of IP address segments.

Wherein, the control policy is a policy adopted when judging which BGP line to use when sending the service flow to the target autonomous system AS.

For example, when it is determined that certain service traffic is sent from the CDN node to the target autonomous system AS through BGP line 1 according to the preset control policy, the target network segment address of the service traffic can be set to the network address corresponding to BGP line 1. segment, such as 2.2.2.0/24, so that the service traffic is sent to the target autonomous system AS through BGP line 1, so as to realize the regulation and control of the service traffic.

In the embodiment of the present application, by specifying different IP address segments of the target self-made system AS to use different BGP lines for access, access control based on the current state of network quality in unicast communication can be implemented.

The sixth implementation manner of the present application relates to a CDN network quality detection method. The sixth embodiment is an improvement made on the basis of the above embodiments. The improvement is that: the CDN node is a CDN node in an anycast communication scenario; According to the network quality parameters of the BGP lines corresponding to each CDN node in the anycast communication scenario, determine the network quality of each CDN node covering the target autonomous system AS; according to each CDN node Cover the network quality of the target autonomous system AS, and adjust the scope of the target autonomous system AS covered by anycast of each CDN node. On the basis of unicast, by confirming that each CDN node covers the network quality of the corresponding target self-made system AS, the network quality of each CDN node covering AS can be obtained; and then by adjusting the coverage of each node AS range, so as to achieve the optimal coverage of each CDN node on the AS.

As shown in FIG. 9, the above step 104 may include the following sub-steps.

Sub-step 1043: According to the network quality parameters of the BGP lines corresponding to each CDN node in the anycast communication scenario, determine the network quality of each CDN node covering the target autonomous system AS.

As shown in Figure 10, CDN Node 1, CDN Node 2, and CDN Node 3 respectively announce the Anycast network segment 100.100.100.0/24, and specify the detection of each address through the policy restriction of setting the line identifier as the differential service code point DSCP The egress direction of the packet.

Build a test server inside each CDN Node, and set the test address as follows.

Table 3 Test address

In CDN Node1, the test server marks the source address 100.100.100.1 with DSCP 16; after all the traffic with the source address 100.100.100.1 arrives at the egress router, it will match the policy routing and forward it from the Telia line. Similarly, traffic with source address 100.100.100.2 will be forwarded from NTT line; traffic with source address 100.100.100.3 will be forwarded from TATA line;

In CDN Node2, the test server marks the source address 100.100.100.1 with DSCP 16; after all the traffic with the source address 100.100.100.1 arrives at the egress router, it will match the policy routing and forward it from the Telia line. Similarly, traffic with a source address of 100.100.100.2 will be forwarded through the Level3 line; traffic with a source address of 100.100.100.3 will be forwarded through the TATA line;

In CDN Node3, add DSCP 16 to the address with source address 100.100.100.1; after all the traffic with source address 100.100.100.1 arrives at the egress router, it will match the policy routing and forward it from the Telia line. Similarly, traffic with a source address of 100.100.100.2 will be forwarded out of the NTT line; traffic with a source address of 100.100.100.3 will be forwarded out of a Level3 line.

Based on the response data packets corresponding to the detection data packets, the test server can obtain the network quality parameters of different BGP lines as shown in Table 4.

Through the test, the anycast coverage of each node and each line for each area/AS can be collected, so as to provide decision-making for the background and formulate an optimal coverage plan.

Sub-step 1044: According to the network quality of the target autonomous system AS covered by each CDN node, adjust the range of the target autonomous system AS covered by each CDN node anycast.

For example, when the traffic on a BGP line on a certain CDN node exceeds the threshold, the subsequent traffic on this line will be automatically switched to the suboptimal CDN node, so as to achieve the optimization of network coverage and the stability of service quality.

The implementation mode of this application confirms that each CDN node covers the network quality of the corresponding target self-made system AS, thereby obtaining the pros and cons of the network quality of each CDN node covering the AS; and then by adjusting the coverage of each CDN node AS, In this way, the optimal coverage of each CDN node on the AS is realized.

Table 4 Network quality parameters

The seventh embodiment of the present application relates to a CDN network quality detection system. The CDN network includes: a CDN node, a plurality of autonomous systems AS provided by a plurality of network operators, and a connection between the CDN node and the plurality of autonomous systems AS The system is interconnected through the Border Gateway Protocol BGP; the system also includes: a server located inside the CDN node, and the server is used to schedule the CDN network to execute the CDN network quality detection method described in any method embodiment above.

Wherein, the server located inside the CDN section may be the test server in the above embodiment.

The eighth embodiment of the present application relates to a server, as shown in FIG. 11 , including at least one processor 202; and a memory 201 communicatively connected to at least one processor 202; Instructions executed by 202, the instructions are executed by at least one processor 202, so that at least one processor 202 can execute any one of the foregoing method embodiments.

Wherein, the memory 201 and the processor 202 are connected by a bus, and the bus may include any number of interconnected buses and bridges, and the bus connects one or more processors 202 and various circuits of the memory 201 together. The bus may also connect together various other circuits such as peripherals, voltage regulators, and power management circuits, all of which are well known in the art and therefore will not be further described herein. The bus interface provides an interface between the bus and the transceivers. A transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing means for communicating with various other devices over a transmission medium. The data processed by the processor 202 is transmitted on the wireless medium through the antenna, and further, the antenna also receives the data and transmits the data to the processor 202 .

Processor 202 is responsible for managing the bus and general processing, and may also provide various functions including timing, peripheral interfacing, voltage regulation, power management, and other control functions. And the memory 201 may be used to store data used by the processor 202 when performing operations.

The ninth embodiment of the present application relates to a computer-readable storage medium storing a computer program. When the computer program is executed by the processor, any one of the above method embodiments is realized.

That is, those skilled in the art can understand that all or part of the steps in the method of the above-mentioned embodiments can be completed by instructing related hardware through a program, the program is stored in a storage medium, and includes several instructions to make a device ( It may be a single-chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. .

Those of ordinary skill in the art can understand that the above-mentioned implementation modes are specific examples for realizing the present application, and in practical applications, various changes can be made to it in form and details without departing from the spirit and spirit of the present application. scope.

Claims (10)

1. A method for detecting the quality of a CDN network, the CDN network comprising: a CDN node, a plurality of autonomous systems AS provided by a plurality of network operators, and the border gateway protocol BGP between the CDN node and the plurality of autonomous systems AS interconnected; said method comprising:

   Constructing multiple detection data packets, each of which carries the line identifier of a BGP line in the multiple BGP lines from the CDN node to the target autonomous system AS;

   According to the line identification carried in the detection data packet, sending the detection data packet from the CDN node to the target autonomous system AS through the BGP line corresponding to the line identification;

   Based on the sent detection data packets, the multiple BGP lines are tested respectively to obtain network quality parameters of each BGP line.
2. The method according to claim 1, said method further comprising:

   According to the network quality parameters of the BGP lines, regulate the BGP lines used by the traffic flow between the CDN node and the target autonomous system AS, and/or perform fault analysis on the detected BGP lines .
3. The method according to claim 2, wherein, according to the network quality parameters of the BGP lines, regulating the BGP lines used by the traffic flow between the CDN node and the target autonomous system AS includes: :

   determining the BGP line used by the traffic flow from the CDN node to the target autonomous system AS;

   After adding the line identifier corresponding to the determined BGP line to the data packet of the service flow, the data packet is sent from the CDN node.
4. The method according to claim 1, wherein the line identification is a differential service code point DSCP; the construction of a plurality of detection packets includes:

   Set the coding value of the differential service code point DSCP of each detection data packet to any one of a plurality of preset coding values, the multiple preset coding values are related to the multiple BGP lines, and the CDN The first autonomous system AS of node interconnection corresponds one by one;

   According to the line identification carried in the detection data packet, sending the detection data packet from the CDN node to the target autonomous system AS through the BGP line corresponding to the line identification includes:

   According to the code value of the differential service code point DSCP carried in the probe data packet, forward the probe data packet to the autonomous system AS corresponding to the code value, and use the autonomous system AS in the multiple BGP lines As the BGP line of the first autonomous system AS, the detection data packet is sent from the CDN node to the target autonomous system AS.
5. The method according to any one of claims 1 to 4, wherein the source address of the probe data packet sent from the CDN node to the target autonomous system AS is a multiple of the corresponding IP address segment of the CDN node addresses, and one-to-one correspondence with the multiple BGP lines;

   Sending the detection data packet from the CDN node to the target autonomous system AS includes:

   According to the source address of the detection data packet, the multiple detection data packets are respectively sent to the target autonomous system AS through the BGP line corresponding to the source address of each detection data packet.
6. The method according to claim 2, wherein the CDN node is a CDN node in a unicast communication scenario;

   According to the network quality parameters of the BGP lines, regulating the BGP lines used by the traffic flow between the CDN node and the target autonomous system AS includes:

   According to the network quality parameters of each BGP line, one or more IP address segments corresponding to the target autonomous system AS are set to be accessed through one of the BGP lines respectively;

   Correspondingly sending different service flows between the CDN node and the target autonomous system AS to one IP address segment in the plurality of IP address segments according to a preset control policy.
7. The method according to claim 2, wherein the CDN node is a CDN node in an anycast communication scenario;

   According to the network quality parameters of the BGP lines, regulating the BGP lines used by the traffic flow between the CDN node and the target autonomous system AS includes:

   According to the network quality parameters of the BGP lines corresponding to each of the CDN nodes in anycast communication scenarios, determine the network quality of each of the CDN nodes covering the target autonomous system AS;

   According to the network quality of each CDN node covering the target autonomous system AS, the range of the target autonomous system AS covered by each CDN node anycast is adjusted.
8. A CDN network quality detection system, wherein the CDN network includes: a CDN node, a plurality of autonomous systems AS provided by a plurality of network operators, and the border gateway protocol between the CDN node and the plurality of autonomous systems AS BGP interconnection; the system further includes: a server located inside the CDN node, the server is used to schedule the CDN network to execute the CDN network quality detection method according to any one of claims 1 to 7.
9. A server comprising:

   at least one processor; and,

   a memory communicatively coupled to the at least one processor; wherein,

   The memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1 to 7 The CDN network quality detection method described in item.
10. A computer-readable storage medium, storing a computer program, and implementing the CDN network quality detection method according to any one of claims 1 to 7 when the computer program is executed by a processor.

Images