Content delivery network link transmission quality analysis method, device, equipment and medium

Abstract

The present disclosure relates to the technical field of content delivery networks, and discloses a content delivery network link transmission quality analysis method, apparatus and device, and a medium, the method comprising: obtaining a detection result of detecting a target link, and determining a first index for evaluating the transmission quality of the target link according to the detection result; acquiring protocol stack data corresponding to the target link in the actual data transmission process, and determining a second index for evaluating the transmission quality of the target link according to the protocol stack data; obtaining service data corresponding to the target link when the service request is carried out, and determining a third index used for evaluating the transmission quality of the target link according to the service data; and determining a comprehensive index for evaluating the transmission quality of the target link according to the first index, the second index and the third index. According to the invention, the final comprehensive index is comprehensively determined based on the multi-level indexes, and the link transmission quality of the service level can be fed back relatively truly and accurately based on the comprehensive index.

Description

Technical Field

[0001] The present disclosure relates to the technical field of content distribution networks, and in particular to a method, device, equipment and medium for analyzing transmission quality of a content distribution network link. Background Art

[0002] Content Delivery Network (CDN) refers to an Internet network service that uses the server closest to each end customer, based on file caching, network optimization and other technologies, to distribute various resources from the source site to end customers faster, more reliably and at a lower cost.

[0003] In recent years, with the continuous development of CDN, the business volume of dynamic acceleration scenarios such as API (Application Programming Interface) acceleration has gradually increased, and the demand for forwarding or back-to-source quality has become higher and higher. Due to the complexity of CDN resources themselves, on the one hand, there will be relatively unstable link scenarios such as cross-operator and cross-national. On the other hand, cheap resources and lines may be introduced for the purpose of reducing costs. In order to ensure the user experience of scenarios such as CDN dynamic acceleration, it is necessary to correct the back-to-source path more timely and accurately, eliminate abnormal links, and select links with better quality. At this time, it is very important to be able to evaluate the link transmission quality more accurately. Summary of the invention

[0004] In view of this, the present disclosure provides a content distribution network link transmission quality analysis method, apparatus, device and medium, so as to accurately evaluate the link transmission quality.

[0005] In a first aspect, the present disclosure provides a method for analyzing link transmission quality of a content distribution network, comprising:

[0006] Acquire a detection result of detecting a target link, and determine a first indicator for evaluating a transmission quality of the target link according to the detection result;

[0007] Acquire protocol stack data corresponding to the target link during actual data transmission, and determine a second indicator for evaluating the transmission quality of the target link according to the protocol stack data;

[0008] Acquire service data corresponding to the target link when making a service request, and determine a third indicator for evaluating the transmission quality of the target link according to the service data;

[0009] A comprehensive indicator for evaluating the transmission quality of the target link is determined according to the first indicator, the second indicator and the third indicator.

[0010] In a second aspect, the present disclosure provides a content distribution network link transmission quality analysis device, comprising:

[0011] A first acquisition module, used to acquire a detection result of detecting a target link, and determine a first indicator for evaluating a transmission quality of the target link according to the detection result;

[0012] A second acquisition module, used to acquire protocol stack data corresponding to the target link during the actual data transmission process, and determine a second indicator for evaluating the transmission quality of the target link according to the protocol stack data;

[0013] A third acquisition module, used to acquire service data corresponding to the target link when making a service request, and determine a third indicator for evaluating the transmission quality of the target link according to the service data;

[0014] A normalization module is used to determine a comprehensive indicator for evaluating the transmission quality of the target link based on the first indicator, the second indicator and the third indicator.

[0015] In a third aspect, the present disclosure provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the content distribution network link transmission quality analysis method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0016] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the content distribution network link transmission quality analysis method of the first aspect or any corresponding embodiment thereof.

[0017] The present invention determines the detection result of the target link in a detection manner, and obtains the protocol stack data at the transmission protocol level and the actual business data at the business level in the process of actual data transmission, and then based on the detection result, protocol stack data and business data, multi-level indicators can be determined, and then the final comprehensive indicator is determined based on the comprehensive indicators of the multi-levels. Based on the comprehensive indicator, the link transmission quality at the business level can be relatively truly and accurately fed back, which can serve as a reference for eliminating abnormal links and selecting links with better quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 is a schematic diagram of a client requesting a resource according to an embodiment of the present disclosure;

[0020] Figure 2 is a flow chart of a method for analyzing transmission quality of a content distribution network link according to an embodiment of the present disclosure;

[0021] Figure 3 is a flow chart of another content distribution network link transmission quality analysis method according to an embodiment of the present disclosure;

[0022] Figure 4 is a schematic diagram of detecting a link according to an embodiment of the present disclosure;

[0023] Figure 5 is a schematic diagram of collecting protocol stack data according to an embodiment of the present disclosure;

[0024] Figure 6 is a schematic diagram of an architecture in which a central node uniformly analyzes link transmission quality according to an embodiment of the present disclosure;

[0025] Figure 7 is a structural block diagram of a content distribution network link transmission quality analysis device according to an embodiment of the present disclosure;

[0026] Figure 8 It is a schematic diagram of the hardware structure of the computer device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0028] Figure 1 A schematic diagram showing a client requesting resources. Figure 1As shown, the client can access the access node of the CDN network. If the access node cache hits, the requested content is returned to the client; if the access node does not hit the cache, the request can be forwarded directly to the source station, or the request can be forwarded to the source station through internal forwarding via internal nodes (such as transit nodes, back-to-source nodes, etc.), and the source station then returns the content requested by the user.

[0029] like Figure 1 As shown, link detection can be performed between nodes to determine the link quality between nodes; and each node can also detect the source station to determine the link quality between the node and the source station.

[0030] Currently, link detection is mainly carried out through dial-up testing. However, dial-up testing is generally a periodic behavior of sending and receiving a small number of packets. It can be used as a benchmark data for transmission quality, but the transmission characteristics and performance are different from those of actual services (such as large file uploading, streaming and other scenarios). It may not be able to feedback the actual link transmission quality of the service, and the detection results cannot represent the link transmission quality of the service.

[0031] In addition, when the source station is used as a detection target, for security or cost reasons, the source station may not accept certain types of detection, or may be restricted in frequency. For example, security policies such as the ban on ping that are common in cloud servers make it difficult to accurately determine the link transmission quality of the source station.

[0032] The content distribution network link transmission quality analysis method provided in this embodiment combines data distributed at three levels: detection, transmission protocol stack, and business. It uses the indicators determined by the data at each level to comprehensively determine indicators that can reflect the link transmission quality at the business level. The determined results are more real and accurate.

[0033] According to an embodiment of the present disclosure, an embodiment of a method for analyzing link transmission quality in a content distribution network is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] In this embodiment, a method for analyzing link transmission quality of a content distribution network is provided, which can be applied to a link analysis system. The link analysis system can be deployed in a service node for analyzing link transmission quality, such as Figure 1 The access nodes, back-to-source nodes, etc. shown in the figure may also be deployed in a central node, and the central node uniformly analyzes the link transmission quality of each service node. Figure 2 is a flow chart of a method for analyzing transmission quality of a content distribution network link according to an embodiment of the present disclosure. Figure 2 As shown, the process includes the following steps.

[0035] Step S201: Acquire a detection result of a target link, and determine a first indicator for evaluating the transmission quality of the target link according to the detection result.

[0036] In this embodiment, when it is necessary to determine the transmission quality of a link between a first node and a second node in a content distribution network, the link may be used as a target link, that is, the target link is a link in the content distribution network; Figure 1 As shown, the target link may be a link between an access node and a back-to-source node, or the target link may be a link between an access node (or a back-to-source node) and a source station.

[0037] By detecting the target link, a detection result that can reflect the transmission quality of the target link can be obtained, and then an indicator that can evaluate the transmission quality of the target link, i.e., a first indicator, can be obtained based on the detection result. For example, if the detection result includes only one parameter, the parameter can be used as the first indicator.

[0038] The target link may be detected by dialing to obtain the detection result of the target link.

[0039] Step S202: Acquire protocol stack data corresponding to the target link during the actual data transmission process, and determine a second indicator for evaluating the transmission quality of the target link according to the protocol stack data.

[0040] In this embodiment, during the actual data transmission between the first node and the second node, that is, during the actual data transmission using the target link, data that can reflect the link transmission quality at the transmission protocol level can be obtained. Specifically, after the actual data transmission behavior is completed, the corresponding protocol stack data can be collected. The protocol stack data can feedback the actual transmission performance of the service level to a certain extent. Therefore, based on the protocol stack data, an indicator that can evaluate the transmission quality of the target link, that is, the second indicator, can also be calculated.

[0041] Step S203: acquiring service data corresponding to the target link when making a service request, and determining a third indicator for evaluating the transmission quality of the target link according to the service data.

[0042] In this embodiment, each time the client initiates a service request, the node can record the corresponding request log, from which data corresponding to the target link to be analyzed can be obtained, and then corresponding service data can be obtained through statistics and other methods, and the service data may include, for example, request time consumption, etc. Since the service data is determined based on real service requests, it can truly reflect the service performance of the target link, and thus can truly reflect the service-level transmission quality of the target link; therefore, based on the service data, an indicator that can evaluate the transmission quality of the target link, i.e., the third indicator, can also be determined.

[0043] Step S204: Determine a comprehensive indicator for evaluating the transmission quality of the target link according to the first indicator, the second indicator and the third indicator.

[0044] As mentioned above, the first indicator is an indicator determined based on the detection results, which can be used as the basic data of transmission quality. However, since the detection results are different from the actual business performance, the first indicator is difficult to accurately represent the business-level transmission quality. The second indicator is generated based on the protocol stack data in the actual transmission process, so the second indicator can reflect the real transmission quality of the target link, and to a certain extent, it can also reflect the transmission performance of the target link for real business. The third indicator is determined based on real business data, so the third indicator can further reflect the real business performance; but the third indicator is easily affected by the business volume. If the business volume is small, the calculated third indicator may have a certain deviation.

[0045] In this embodiment, the first indicator, the second indicator, and the third indicator are indicators at three different levels, and the three can respectively more accurately represent the link transmission quality at the service level. By combining the first indicator, the second indicator, and the third indicator, a unique indicator, namely the comprehensive indicator, is determined. The transmission quality of the target link is evaluated using the comprehensive indicator, which can relatively accurately feedback the link transmission quality information at the service level and can weaken the influence of parameters such as the service volume level.

[0046] Furthermore, after determining the comprehensive index of the target link, the service request related to the target link can be processed accordingly based on the comprehensive index of the target link. For example, the scheduling system can determine whether the target link is the link with the best quality based on the comprehensive index of the target link, so that the return path can be corrected in a timely and accurate manner; or, if the quality of the target link is poor, the target link can be eliminated.

[0047] The content distribution network link transmission quality analysis method provided in this embodiment determines the detection result of the target link in a detection manner, and obtains the protocol stack data at the transmission protocol level and the actual business data at the business level during the actual data transmission process. Based on the detection results, protocol stack data and business data, multi-level indicators can be determined, and then the final comprehensive indicator is determined based on the comprehensive indicators of the multi-level indicators. Based on the comprehensive indicator, the link transmission quality of the business level can be relatively truly and accurately fed back, which can serve as a reference for eliminating abnormal links and selecting links with better quality.

[0048] In this embodiment, a method for analyzing link transmission quality of a content distribution network is provided, which can be applied to a link analysis system. The link analysis system can be deployed in a service node for analyzing link transmission quality, such as Figure 1 The access nodes, back-to-source nodes, etc. shown in the figure may also be deployed in a central node, and the central node uniformly analyzes the link transmission quality of each service node. Figure 3 is a flow chart of a method for analyzing transmission quality of a content distribution network link according to an embodiment of the present disclosure. Figure 3 As shown, the process includes the following steps.

[0049] Step S301: Acquire a detection result of a target link, and determine a first indicator for evaluating the transmission quality of the target link according to the detection result.

[0050] For details, please see Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0051] In some optional implementations, the above step S301 of "obtaining a detection result of detecting the target link" may include steps A1 to A4.

[0052] Step A1, detecting the target link based on at least one transport layer protocol, and determining the transport layer detection result corresponding to each transport layer protocol.

[0053] In this embodiment, CDN nodes or customer source stations can be detected through transport layer dialing to determine the transmission quality of the corresponding link. Specifically, based on transport layer protocols such as TCP (Transmission Control Protocol) / UDP (User Datagram Protocol) / ICMP (Internet Control Message Protocol), detection can be performed using Ping to obtain corresponding detection results, that is, transport layer detection results. Among them, one transport layer protocol can be used for detection to determine one transport layer detection result, or multiple transport layer protocols can be used for detection separately to determine multiple transport layer detection results.

[0054] Step A2: when there are multiple transport layer detection results, the multiple transport layer detection results are mutually verified, and when the multiple transport layer detection results are consistent, it is determined that the multiple transport layer detection results are valid.

[0055] If the target link is detected based on only one transport layer protocol, the transport layer detection result obtained by default is valid.

[0056] If the target link is detected based on multiple transport layer protocols, in this embodiment, each transport layer detection result is mutually verified to determine whether each transport layer detection result is consistent. For example, the transport layer detection result includes a detection delay, which can be, for example, RTT (Round-Trip Time). If the detection delays of each transport layer detection result are relatively close to each other, it can be said that each transport layer detection result is consistent, that is, multiple transport layer detection results are valid. If one of the transport layer detection results is too large or too small, it can be determined that the transport layer detection result is invalid.

[0057] Step A3: detect the target link based on the application layer protocol and determine the corresponding application layer detection result.

[0058] In this embodiment, detection can also be performed at the application layer, that is, the target link is detected based on the application layer protocol, and the corresponding detection result, that is, the application layer detection result, can also be determined; the application layer protocol can specifically include HTTP (Hypertext Transfer Protocol) / HTTPS (Hypertext Transfer Protocol Secure) and the like.

[0059] Among them, detection through application layer protocol can obtain information that is closer to the actual transmission quality of the business than detection of transport layer protocol. However, since the application layer protocol detection overhead is relatively large and the source station can perceive the application layer protocol detection, the source station can choose whether to allow application layer protocol detection as needed.

[0060] Figure 4 A schematic diagram of link detection is shown in FIG. Figure 4 As shown, a basic dialing test system can be constructed, and the basic dialing test system distributes detection tasks to various dialing test devices; the dialing test devices are specifically service nodes, such as Figure 1 As shown in the access node, each dialing device may be provided with a basic dialing agent. After receiving the detection task, the basic dialing agent may detect the corresponding link based on the detection task, for example, mutual detection between nodes or detection of the source station may be performed.

[0061] Among them, when nodes detect each other, they can detect based on the transport layer protocol and the application layer protocol, such as Figure 4 As shown in the figure, detection can be performed based on TCP / UDP / HTTP Ping. When detecting the source station, it is necessary to detect based on the security policy of the source station. Figure 4 As shown, if source station A prohibits application layer protocol detection, when dialing device 1 detects source station A, it can perform detection based on the transport layer protocol (such as TCP Ping, specifically ACK / SYN Ping can be used); if source station B allows application layer protocol detection, when dialing device 2 detects source station B, it can perform comprehensive detection based on TCP+HTTP Ping.

[0062] Step A4, comprehensively determining the detection result of the target link according to the application layer detection result and the effective transport layer detection result.

[0063] The detection result of the target link can be determined comprehensively by combining the application layer detection result and the effective transport layer detection result. For example, each detection result (application layer detection result and effective transport layer detection result) is weighted and summed, and the weighted sum result is used as the detection result of the target link.

[0064] In this embodiment, the transport layer protocol detection is designed based on the protocol mechanism, without any business modification or perception, and through mutual verification, the link status can be jointly fed back; the application layer protocol can provide detection results that are closer to the actual business situation, and the comprehensive application layer detection results and effective transport layer detection results can make the determined detection results more truly and accurately represent the transmission quality of the target link.

[0065] In some optional implementations, the detection result includes multiple parameters, and the detection result specifically includes: detection delay, detection packet loss rate and detection delay jitter of the target link.

[0066] Furthermore, the above step S301 "determining a first indicator for evaluating the transmission quality of the target link according to the detection result" specifically includes step B1.

[0067] Step B1, calculating a first indicator for evaluating the transmission quality of the target link according to the detection delay, detection packet loss rate and detection delay jitter of the target link; the first indicator is positively correlated with the detection delay, detection packet loss rate and detection delay jitter of the target link.

[0068] In this embodiment, by detecting the target link, the detection delay, detection packet loss rate and detection delay jitter of the target link can be determined, and these parameters are all used as detection results. In addition, the detection delay, detection packet loss rate and detection delay jitter of the target link are integrated to calculate the first indicator, so that the first indicator can characterize the detection delay, detection packet loss rate and detection delay jitter of the target link, thereby representing the transmission quality of the target link from multiple angles.

[0069] Moreover, the first indicator is positively correlated with the detection delay, detection packet loss rate and detection delay jitter of the target link. That is, the larger the detection delay, detection packet loss rate and detection delay jitter of the target link, the larger the first indicator is, and the worse the transmission quality of the target link is. In other words, the smaller the first indicator is, the better the transmission quality of the target link is.

[0070] Optionally, the first indicator is obtained by multiplying the detection packet loss rate by the detection delay and the detection delay jitter.

[0071] In this embodiment, the detection packet loss rate, the detection delay, and the detection delay jitter represent the transmission quality of the target link from different dimensions and influence each other. The detection packet loss rate is multiplied by the detection delay and the detection delay jitter to obtain the first indicator. The influence between the detection packet loss rate and the detection delay and the detection delay jitter can be amplified by the product, so that the first indicator can better represent the comprehensive characteristics of the detection delay, the detection packet loss rate, and the detection delay jitter, thereby better representing the transmission quality of the target link.

[0072] In addition, optionally, in this embodiment, a first adjustment coefficient for adjusting the detection packet loss rate is configured for the detection packet loss rate; there is a positive correlation between the first adjustment coefficient and the real-time performance of the service, that is, the higher the real-time performance of the service, the larger the first adjustment coefficient, and the greater the impact of the detection packet loss rate on the first indicator.

[0073] For example, the first indicator can be calculated by the following formula (1):

[0074] score base =rtt*(1+k loss_rate *loss_rate)*k rtt_dev *rtt_dev (1)

[0075] Among them, score base is the first indicator, rtt is the detection delay, loss_rate is the detection packet loss rate, rtt_dev is the detection delay jitter, k loss_rate is the adjustment coefficient of the detected packet loss rate, i.e., the first adjustment coefficient, k rtt_dev is the adjustment coefficient for detecting delay jitter. loss_rate and adjustment factor k rtt_dev The specific value of is related to the real-time attribute of the actual business; for example, for real-time sensitive business, the first adjustment coefficient k can be appropriately increased. loss_rate For services with low real-time requirements such as downloading, the first adjustment coefficient k can be appropriately lowered. loss_rate Or adjustment factor k rtt_dev The value of .

[0076] Step S302: Acquire protocol stack data corresponding to the target link during the actual transmission process, and determine a second indicator for evaluating the transmission quality of the target link according to the protocol stack data.

[0077] For details, please see Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0078] In some optional implementations, the protocol stack data may also include multiple parameters, and the protocol stack data specifically includes: a smooth delay and a retransmission rate of a target link.

[0079] Furthermore, the above step S302 "determining a second indicator for evaluating the transmission quality of the target link according to the protocol stack data" specifically includes step B2.

[0080] Step B2: Calculate a second indicator for evaluating the transmission quality of the target link according to the smoothed delay and retransmission rate of the target link; the second indicator is positively correlated with the smoothed delay and retransmission rate of the target link.

[0081] In this embodiment, in the kernel protocol stack, the network data packet transmission process can be monitored through the Hook mechanism, so as to obtain the protocol stack data at the protocol level. The protocol stack data can specifically include smooth delay and retransmission rate, etc. The smooth delay is, for example, the smoothed round trip time (SRTT, Smoothed Round Trip Time).

[0082] Figure 5A schematic diagram of collecting protocol stack data is shown. Figure 5 As shown, a Hook statistics module is set in the kernel protocol stack. The Hook statistics module sets a hook function on the key path of the data packet flowing through the protocol stack, and uses the hook function to call the protocol stack interface of a specific protocol (such as TCP) or monitor the connection status, so as to obtain protocol stack data such as smoothing delay and retransmission rate. In addition, a data reporting agent (Agent) can also be set, and the data reporting agent can obtain the data protocol stack data generated by the Hook statistics module and report it; for example, when the method of this embodiment is executed by the central node, the data reporting agent of each node reports the protocol stack data obtained by each node to the central node, and the central node determines the link transmission quality of each node.

[0083] Furthermore, the second indicator is calculated by comprehensively considering the smooth delay and retransmission rate of the target link, so that the second indicator can characterize the smooth delay and retransmission rate of the target link, thereby representing the transmission quality of the target link from multiple angles.

[0084] Moreover, the second indicator is positively correlated with the smooth delay and retransmission rate of the target link, that is, the larger the smooth delay and retransmission rate of the target link, the larger the second indicator is, and the worse the transmission quality of the target link is; in other words, the smaller the second indicator is, the better the transmission quality of the target link is.

[0085] Optionally, the second indicator is obtained based on a multiplication operation of the retransmission rate and the smoothing delay.

[0086] In this embodiment, the retransmission rate and the smoothing delay represent the transmission quality of the target link from different dimensions and influence each other. By multiplying the retransmission rate and the smoothing delay to obtain the second indicator, the influence between the retransmission rate and the smoothing delay can be amplified by the product, so that the second indicator can better represent the comprehensive characteristics of the retransmission rate and the smoothing delay, thereby better representing the transmission quality of the target link.

[0087] In addition, optionally, a second adjustment coefficient for adjusting the retransmission rate is configured for the retransmission rate; the second adjustment coefficient is positively correlated with the real-time performance of the service, that is, the higher the real-time performance of the service, the larger the second adjustment coefficient, and the greater the impact of the retransmission rate on the second indicator.

[0088] For example, the second index can be calculated by the following formula (2):

[0089] score trans =srtt*(1+k retrans_rate *retrans_rate) (2)

[0090] Among them, score transis the second indicator, srtt is the delay after the protocol stack is smoothed, that is, the smoothed delay, retrans_rate is the retransmission rate, k retrans_rate is the adjustment coefficient of the retransmission rate, that is, the second adjustment coefficient. retrans_rate The specific value of is related to the real-time attribute of the actual business; for example, for real-time sensitive business, the second adjustment coefficient k can be appropriately increased. retrans_rate For services with low real-time requirements such as downloading, the second adjustment coefficient k can be appropriately lowered. retrans_rate The value of .

[0091] Step S303: acquiring service data corresponding to the target link when making a service request, and determining a third indicator for evaluating the transmission quality of the target link according to the service data.

[0092] For details, please see Figure 2 Step S203 of the illustrated embodiment will not be described in detail here.

[0093] In some optional implementations, the service data also includes multiple parameters, and the service data may specifically include: the request time consumption of the target link, the size of the request data volume, and the request failure rate.

[0094] Furthermore, the above step S303 "determining a third indicator for evaluating the transmission quality of the target link according to the service data" specifically includes step B3.

[0095] Step B3, calculate a third indicator for evaluating the transmission quality of the target link based on the request time, request data size and request failure rate of the target link; the third indicator is positively correlated with the request time and request failure rate of the target link, and is negatively correlated with the request data size of the target link.

[0096] In this embodiment, by collecting statistics on the data in the request log of the target link, actual business indicators such as request time, request data size, and request failure rate can be determined, and these business indicators are used as actual business data. The request time, request data size, and request failure rate of the target link are combined to calculate the third indicator, so that the third indicator can characterize the request time, request data size, and request failure rate of the target link, thereby representing the transmission quality of the target link from multiple angles.

[0097] Moreover, the third indicator is positively correlated with the request time and request failure rate of the target link, and negatively correlated with the request data volume of the target link. That is, the greater the request time and request failure rate of the target link, or the smaller the request data volume of the target link, the larger the third indicator is, and the worse the transmission quality of the target link is; in other words, the smaller the third indicator is, the better the transmission quality of the target link is.

[0098] Optionally, the third indicator is obtained by multiplying the request failure rate by the inverse of the request data size and the request duration.

[0099] In this embodiment, the request failure rate, the request time consumption, and the request data size represent the transmission quality of the target link from different dimensions, and they influence each other; and the request data size is negatively correlated with the third indicator, so the request failure rate is multiplied by the inverse of the request data size and the request time consumption, and then the third indicator is calculated, so that the influence between the request failure rate and the request time consumption and the request data size can be amplified through the product, so that the third indicator can better characterize the comprehensive characteristics of the request failure rate, request time consumption, and request data size, so as to better represent the transmission quality of the target link.

[0100] Among them, the request duration can be specifically the total request duration within a period of time, and the request data size can be specifically the total data size of requests within a period of time; determining the third indicator based on the inverse of the request data size is equivalent to dividing the request duration and the request data size. The result of the division between the two can represent the time required to transmit a certain unit size (for example, 1 byte, etc.) of data, thereby being able to uniformly represent the third indicators of different links.

[0101] In addition, optionally, a third adjustment coefficient for adjusting the request failure rate is configured for the request failure rate; there is a positive correlation between the third adjustment coefficient and the real-time performance of the business, that is, the higher the real-time performance of the business, the larger the third adjustment coefficient, and the greater the impact of the request failure rate on the third indicator.

[0102] For example, the third index can be calculated by the following formula (3):

[0103] score app =T req *(1+k failed_rate *failed_rate) / req_size (3)

[0104] Among them, score app is the third indicator, T req is the request duration, req_size is the request data size, failed_rate is the request failure rate, k failed_rate is the adjustment coefficient of the request failure rate, that is, the third adjustment coefficient. failed_rate The specific value of is related to the real-time attribute of the actual business; for example, for real-time sensitive business, the third adjustment coefficient k can be appropriately increased. failed_rate For services with low real-time requirements such as downloading, the third adjustment coefficient k can be appropriately lowered. failed_rateThe value of .

[0105] In this embodiment, the detection result, protocol stack data and service data all include multiple parameters, and the first index, the second index and the third index are determined based on the multiple parameters, so that the link transmission quality can be characterized in multiple dimensions. In addition, the corresponding index is calculated by multiplication operation between the parameters, which can amplify the influence between the parameters.

[0106] Step S304: Determine a comprehensive indicator for evaluating the transmission quality of the target link according to the first indicator, the second indicator and the third indicator.

[0107] Specifically, the above step S304 "determines a comprehensive indicator for evaluating the transmission quality of the target link according to the first indicator, the second indicator and the third indicator" includes the following steps S3041 to S3042.

[0108] Step S3041, setting corresponding weights for the first indicator, the second indicator and the third indicator respectively.

[0109] Since the first indicator, the second indicator and the third indicator are obtained based on different data and methods and there are certain differences between them, in this embodiment, corresponding weights are set for the first indicator, the second indicator and the third indicator respectively. For example, a first weight k1 is set for the first indicator, a second weight k2 is set for the second indicator, and a third weight k3 is set for the third indicator. Thus, the three indicators can be normalized based on the first weight k1, the second weight k2 and the third weight k3 to obtain a relatively accurate comprehensive indicator.

[0110] Optionally, the weight of each indicator is adjustable, and the above step S3041 "set corresponding weights for the first indicator, the second indicator and the third indicator respectively" includes the following steps C1.

[0111] Step C1, according to the current service level and / or service attribute of the target link, a first weight is set for the first indicator, a second weight is set for the second indicator, and a third weight is set for the third indicator.

[0112] Among them, the first weight k1 is negatively correlated with the business level; when the business attributes are affected by the protocol stack data, the second weight k2 is positively correlated with the degree of influence of the protocol stack data on the business attributes; when the business attributes are affected by the business data, the third weight k3 is positively correlated with the degree of influence of the business data on the business attributes.

[0113] In this embodiment, the first weight k1 is determined based on the business volume level, and there is a negative correlation between the first weight k1 and the business volume level, that is, the larger the business volume level, the smaller the first weight k1.

[0114] Specifically, when the business volume is small, there is not enough protocol stack data and business data. The second and third indicators determined at this time are prone to certain deviations. Therefore, the first weight k1 is set to a relatively large value. Correspondingly, the second weight k2 and the third weight k3 are relatively small. At this time, the comprehensive indicator is mainly determined by the first indicator determined based on the detection results, and the second and third indicators are auxiliary parameters.

[0115] When the business volume is large, sufficient protocol stack data and business data have been accumulated, and the second and third indicators can more accurately represent the link transmission quality. Therefore, the first weight k1 is set to a relatively small value. Correspondingly, the second weight k2 and the third weight k3 are relatively large. At this time, the comprehensive indicator is mainly determined by the second and third indicators, and the first indicator is an auxiliary parameter.

[0116] In addition, the second weight k2 and the third weight k3 may be adaptively adjusted based on the actually required service attributes.

[0117] Specifically, if the protocol stack data affects the service attributes, for example, the current service is sensitive to the retransmission rate, the greater the impact of the protocol stack data on the service attributes, the greater the second weight k2 is set. Similarly, if the service data affects the service attributes, for example, the current service is sensitive to the request failure rate, the greater the impact of the service data on the service attributes, the greater the third weight k3 is set.

[0118] For example, multiple weight combinations {k1, k2, k3} can be set, each weight combination includes three weight values. Based on the current actual situation, a suitable weight combination can be selected, and the values ​​in the selected weight combination can be assigned to the three weights to update the three weights, and then the comprehensive index can be calculated based on the updated weights.

[0119] Step S3042: normalize the first indicator, the second indicator, and the third indicator according to the weights to obtain a comprehensive indicator for evaluating the transmission quality of the target link.

[0120] In this embodiment, if the first weight k1 is set for the first indicator, the second weight k2 is set for the second indicator, and the third weight k3 is set for the third indicator, the three indicators can be normalized using the first weight k1, the second weight k2, and the third weight k3, and the normalized result can be used as the final comprehensive indicator.

[0121] For example, the comprehensive index can be calculated based on the following formula (4):

[0122]

[0123] Among them, score represents a comprehensive indicator, scorebase As the first indicator, score trans As the second indicator, score app Is the third indicator.

[0124] The content distribution network link transmission quality analysis method provided in this embodiment sets corresponding weights for the first indicator, the second indicator, and the third indicator respectively, and represents the parameter proportion when the indicators are normalized based on the weights, thereby realizing the normalization of multiple indicators. In addition, the weights of the three indicators are adaptively adjusted based on the actual business volume and business attributes, and the proportion of each indicator when normalized can be adaptively adjusted, so that the final comprehensive indicator has more reference value.

[0125] Figure 6 FIG. 1 shows a schematic diagram of an architecture in which a central node performs a unified analysis of the link transmission quality of each node. Figure 6 As shown, when it is necessary to determine the link transmission quality of each node, for example, if the business system generates a request to determine the transmission quality of multiple links based on the topology of the CDN network, and sends the request to the link analysis system of the central node, the link analysis system can send a detection task to the corresponding node.

[0126] like Figure 6 As shown, the link analysis system of the central node sends a detection task to the access node and the back-to-source node. After receiving the detection task, the access node can collect the corresponding detection results by dialing and report the detection results to the central node; and the access node performs actual service transmission based on the back-to-source request, and can determine the protocol stack data and service data of the corresponding link, and report the protocol stack data and service data to the central node. The central node determines three indicators based on the detection results, protocol stack data and service data reported by the access node, and finally determines the comprehensive indicator of the corresponding link.

[0127] In addition, the process of the back-to-source node reporting data based on the detection task is similar to the processing process of the access node, which will not be described here.

[0128] The content distribution network link transmission quality analysis method provided in this embodiment generates multi-level indicators through multi-level data, and generates the final comprehensive indicator by combining the multi-level indicators, which can reduce the disadvantages of a single data source and can more realistically feedback the link transmission quality information at the service level. In addition, normalizing the indicators at each level to represent the link transmission quality with a unified comprehensive indicator is also convenient for external systems to use and process, and is beneficial as a reference for eliminating abnormal links and selecting links with better quality.

[0129] In this embodiment, a content distribution network link transmission quality analysis device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0130] This embodiment provides a content distribution network link transmission quality analysis device, such as Figure 7 As shown, including:

[0131] A first acquisition module 701 is used to acquire a detection result of detecting a target link, and determine a first indicator for evaluating the transmission quality of the target link according to the detection result;

[0132] A second acquisition module 702 is used to acquire protocol stack data corresponding to the target link during the actual data transmission process, and determine a second indicator for evaluating the transmission quality of the target link according to the protocol stack data;

[0133] A third acquisition module 703, used to acquire service data corresponding to the target link when making a service request, and determine a third indicator for evaluating the transmission quality of the target link according to the service data;

[0134] The normalization module 704 is used to determine a comprehensive indicator for evaluating the transmission quality of the target link according to the first indicator, the second indicator and the third indicator.

[0135] In some optional implementations, the first acquisition module 701 acquires the detection result of detecting the target link, including:

[0136] Detecting the target link based on at least one transport layer protocol, and determining a transport layer detection result corresponding to each transport layer protocol;

[0137] When there are multiple transport layer detection results, mutually verify the multiple transport layer detection results, and when the multiple transport layer detection results are consistent, determine that the multiple transport layer detection results are valid;

[0138] Detecting the target link based on the application layer protocol and determining a corresponding application layer detection result;

[0139] A detection result for detecting the target link is comprehensively determined based on the application layer detection result and the effective transport layer detection result.

[0140] In some optional implementations, the detection result includes: detection delay, detection packet loss rate and detection delay jitter of the target link;

[0141] The first acquisition module 701 determines a first indicator for evaluating the transmission quality of the target link according to the detection result, including: calculating the first indicator for evaluating the transmission quality of the target link according to the detection delay, detection packet loss rate and detection delay jitter of the target link; the first indicator is positively correlated with the detection delay, detection packet loss rate and detection delay jitter of the target link;

[0142] The protocol stack data includes: smooth delay and retransmission rate of the target link;

[0143] The second acquisition module 702 determines a second indicator for evaluating the transmission quality of the target link according to the protocol stack data, including: calculating a second indicator for evaluating the transmission quality of the target link according to the smooth delay and retransmission rate of the target link; the second indicator is positively correlated with the smooth delay and retransmission rate of the target link;

[0144] The service data includes: the request time consumption, the request data volume and the request failure rate of the target link;

[0145] The third acquisition module 703 determines a third indicator for evaluating the transmission quality of the target link based on the business data, including: calculating the third indicator for evaluating the transmission quality of the target link based on the request time, request data volume and request failure rate of the target link; the third indicator is positively correlated with the request time and request failure rate of the target link, and is negatively correlated with the request data volume of the target link.

[0146] In some optional implementations, the first indicator is obtained by multiplying the detection packet loss rate by the detection delay and the detection delay jitter;

[0147] The second indicator is obtained by multiplying the retransmission rate by the smoothed delay;

[0148] The third indicator is obtained by multiplying the request failure rate by the inverse of the request data size and the request time.

[0149] In some optional implementations, the detected packet loss rate is configured with a first adjustment coefficient for adjusting the detected packet loss rate; the first adjustment coefficient is positively correlated with service real-time performance;

[0150] The retransmission rate is configured with a second adjustment coefficient for adjusting the retransmission rate; the second adjustment coefficient is positively correlated with the real-time performance of the service;

[0151] The request failure rate is configured with a third adjustment coefficient for adjusting the request failure rate; the third adjustment coefficient is positively correlated with the real-time performance of the service.

[0152] In some optional implementations, the normalization module 704 determines a comprehensive indicator for evaluating the transmission quality of the target link according to the first indicator, the second indicator, and the third indicator, including:

[0153] Setting corresponding weights for the first indicator, the second indicator and the third indicator respectively;

[0154] The first indicator, the second indicator and the third indicator are normalized according to the weight to obtain a comprehensive indicator for evaluating the transmission quality of the target link.

[0155] In some optional implementations, the normalization module 704 sets corresponding weights for the first indicator, the second indicator, and the third indicator, respectively, including:

[0156] According to the current service level and / or service attribute of the target link, setting a first weight for the first indicator, setting a second weight for the second indicator, and setting a third weight for the third indicator;

[0157] Wherein, there is a negative correlation between the first weight and the business level;

[0158] In the case where the service attribute is affected by the protocol stack data, there is a positive correlation between the second weight and the degree of influence of the protocol stack data on the service attribute;

[0159] In the case where the service attribute is affected by the service data, there is a positive correlation between the third weight and the degree of influence of the service data on the service attribute.

[0160] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0161] The content distribution network link transmission quality analysis device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, including a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0162] The present disclosure also provides a computer device having the above Figure 7 The content distribution network link transmission quality analysis device is shown.

[0163] See also Figure 8 , Figure 8 is a schematic diagram of a computer device provided by an optional embodiment of the present disclosure, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0164] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0165] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0166] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0167] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0168] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0169] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0170] A part of the present disclosure may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present disclosure through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0171] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for analyzing link transmission quality of a content distribution network, characterized in that: The method comprises: Acquire a detection result of detecting a target link, and determine a first indicator for evaluating a transmission quality of the target link according to the detection result; Acquire protocol stack data corresponding to the target link during actual data transmission, and determine a second indicator for evaluating the transmission quality of the target link according to the protocol stack data; Acquire service data corresponding to the target link when making a service request, and determine a third indicator for evaluating the transmission quality of the target link according to the service data; A comprehensive indicator for evaluating the transmission quality of the target link is determined according to the first indicator, the second indicator and the third indicator.

2. The method according to claim 1, characterized in that The obtaining of the detection result of the target link includes: Detecting the target link based on at least one transport layer protocol, and determining a transport layer detection result corresponding to each transport layer protocol; When there are multiple transport layer detection results, mutually verify the multiple transport layer detection results, and when the multiple transport layer detection results are consistent, determine that the multiple transport layer detection results are valid; Detecting the target link based on the application layer protocol and determining a corresponding application layer detection result; A detection result for detecting the target link is comprehensively determined based on the application layer detection result and the effective transport layer detection result.

3. The method according to claim 1, characterized in that The detection result includes: detection delay, detection packet loss rate and detection delay jitter of the target link; The determining, according to the detection result, a first indicator for evaluating the transmission quality of the target link comprises: calculating, according to the detection delay, detection packet loss rate, and detection delay jitter of the target link, the first indicator for evaluating the transmission quality of the target link; the first indicator is positively correlated with the detection delay, detection packet loss rate, and detection delay jitter of the target link; The protocol stack data includes: smooth delay and retransmission rate of the target link; The determining, according to the protocol stack data, a second indicator for evaluating the transmission quality of the target link comprises: calculating, according to the smoothing delay and the retransmission rate of the target link, a second indicator for evaluating the transmission quality of the target link; the second indicator is positively correlated with the smoothing delay and the retransmission rate of the target link; The service data includes: the request time consumption, the request data volume and the request failure rate of the target link; The third indicator for evaluating the transmission quality of the target link is determined based on the business data, including: calculating the third indicator for evaluating the transmission quality of the target link based on the request time, request data volume and request failure rate of the target link; the third indicator is positively correlated with the request time and request failure rate of the target link, and is negatively correlated with the request data volume of the target link.

4. The method according to claim 3, characterized in that: The first indicator is obtained by multiplying the detection packet loss rate by the detection delay and the detection delay jitter; The second indicator is obtained by multiplying the retransmission rate by the smoothed delay; The third indicator is obtained by multiplying the request failure rate by the inverse of the request data size and the request time.

5. The method according to claim 4, characterized in that The detected packet loss rate is configured with a first adjustment coefficient for adjusting the detected packet loss rate; the first adjustment coefficient is positively correlated with the real-time performance of the service; The retransmission rate is configured with a second adjustment coefficient for adjusting the retransmission rate; the second adjustment coefficient is positively correlated with the real-time performance of the service; The request failure rate is configured with a third adjustment coefficient for adjusting the request failure rate; the third adjustment coefficient is positively correlated with the real-time performance of the service.

6. The method according to any one of claims 1 to 5, characterized in that Determining a comprehensive indicator for evaluating the transmission quality of the target link according to the first indicator, the second indicator, and the third indicator includes: Setting corresponding weights for the first indicator, the second indicator and the third indicator respectively; The first indicator, the second indicator and the third indicator are normalized according to the weight to obtain a comprehensive indicator for evaluating the transmission quality of the target link.

7. The method according to claim 6, characterized in that The step of setting corresponding weights for the first indicator, the second indicator, and the third indicator respectively includes: According to the current service level and / or service attribute of the target link, setting a first weight for the first indicator, setting a second weight for the second indicator, and setting a third weight for the third indicator; Wherein, there is a negative correlation between the first weight and the business level; In the case where the service attribute is affected by the protocol stack data, there is a positive correlation between the second weight and the degree of influence of the protocol stack data on the service attribute; In the case where the service attribute is affected by the service data, there is a positive correlation between the third weight and the degree of influence of the service data on the service attribute.

8. A content distribution network link transmission quality analysis device, characterized in that: The device comprises: A first acquisition module, used to acquire a detection result of detecting a target link, and determine a first indicator for evaluating a transmission quality of the target link according to the detection result; A second acquisition module, used to acquire protocol stack data corresponding to the target link during the actual data transmission process, and determine a second indicator for evaluating the transmission quality of the target link according to the protocol stack data; A third acquisition module, used to acquire service data corresponding to the target link when making a service request, and determine a third indicator for evaluating the transmission quality of the target link according to the service data; A normalization module is used to determine a comprehensive indicator for evaluating the transmission quality of the target link based on the first indicator, the second indicator and the third indicator.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the content distribution network link transmission quality analysis method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the content distribution network link transmission quality analysis method according to any one of claims 1 to 7.

Images