Detection based on network service

Abstract

A detection method based on a network service, a device, a program product, and a storage medium, relating to the technical field of Internet and used for detecting a network service system. The network service system comprises an access point device cluster and a plurality of intermediate network devices connected to the access point device cluster; at least one Anycast address is configured for the access point device cluster; different Anycast addresses correspond to different types of network services; different types of network services indicate that a destination end is accessed by means of different network paths; and each network path involves one or more intermediate network devices. The method comprises: sending to an Anycast address a plurality of Anycast detection packets accessing a destination end; upon successfully receiving the Anycast detection packets, access point devices in an access point device cluster sending the Anycast detection packets to the destination end on the basis of a target Anycast address in the Anycast detection packets by means of a target network path corresponding to the target Anycast address; and on the basis of the number of successfully responded Anycast detection packets among the plurality of Anycast detection packets, determining whether a network service system is normal.

Description

Detection based on network services Technical Field

[0001] This disclosure relates to the field of Internet technology, and more particularly to network service-based detection. Background Technology

[0002] In traditional network services, the user constructs packets from the originator to the destination. After the packet is sent from the originator, its network path is determined by the operator and is unpredictable. As network scale continues to increase and business demands grow, this traditional best-effort forwarding can no longer meet business requirements. Traditional link-level probing solutions such as the Ping command are difficult to apply to some new service-oriented network architectures. Summary of the Invention

[0003] To overcome the problems existing in related technologies, embodiments of this disclosure provide a detection method, device, program product, and storage medium based on network services.

[0004] According to a first aspect of the present disclosure, a network service-based detection method is provided. The network service system includes an access point device cluster and multiple intermediate network devices connected to the access point device cluster. The access point device cluster is configured with at least one anycast address, and different anycast addresses correspond to different types of network services. The different types of network services refer to accessing a destination through different network paths, and the network paths include one or more of the intermediate network devices. The method includes: sending multiple anycast probe messages to the at least one anycast address to access the destination; the access point devices in the access point device cluster are configured to, upon successfully receiving the anycast probe message, send the anycast probe message to the destination through a target network path corresponding to the target anycast address based on the target anycast address in the anycast probe message; and determine whether the network service system is functioning normally based on the number of successful responses in the multiple anycast probe messages.

[0005] According to a second aspect of the present disclosure, a network service-based detection method is provided for detecting a network service system. The network service system includes a detection terminal, an access point device cluster, and multiple intermediate network devices connected to the access point device cluster. The access point device cluster is configured with at least one anycast address, and different anycast addresses correspond to different types of network services. The different types of network services refer to accessing a destination through different network paths, and the network paths include one or more of the intermediate network devices. The detection terminal is used to send multiple anycast detection packets to the at least one anycast address to access the destination. The method is applied to the access point devices in the access point device cluster, and the method includes: in response to receiving anycast detection packets sent by the detection terminal, obtaining a target anycast address in the anycast detection packet; and sending the anycast detection packet to the destination through a target network path corresponding to the target anycast address. The number of successful responses in the multiple anycast detection packets is used to determine whether the network service system is functioning normally.

[0006] According to a third aspect of the present disclosure, a network service system is provided, the system comprising an access point device cluster and a plurality of intermediate network devices connected to the access point device cluster; the access point device cluster is configured with at least one Anycast address, different Anycast addresses corresponding to different types of network services; the different types of network services refer to accessing a destination through different network paths, the network paths including one or more of the intermediate network devices; the system further comprises a probe terminal, the probe terminal being used to perform the steps of the method described in the first aspect; and / or, the access point devices in the access point device cluster are used for the steps of the method described in the second aspect.

[0007] According to a fourth aspect of the present disclosure, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method embodiments described in the first or second aspect above.

[0008] According to a fifth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method embodiments described in the first or second aspect above.

[0009] According to a sixth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method embodiments described in the first or second aspect.

[0010] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: In the new service-oriented network architecture of this disclosure, the network service system includes an access point device cluster and multiple intermediate network devices connected to the access point device cluster; the access point device cluster is configured with at least one Anycast address, and different Anycast addresses correspond to different types of network services; the different types of network services refer to accessing the destination through different network paths, and the network path includes one or more of the intermediate network devices. Therefore, the network service system can be encapsulated into different types of network services, allowing services to actively choose to consume different services, thereby meeting the differentiated needs of services. Under the above-mentioned new service-oriented network architecture, the detection method proposed in this embodiment simulates a real network service process, sending multiple Anycast detection packets to the Anycast address to access the destination. If the access point device can successfully receive the Anycast detection packet, it will send the Anycast detection packet to the destination through the target network path corresponding to the target Anycast address based on the target Anycast address in the Anycast detection packet; therefore, the normality of the network service system can be determined based on the number of successful responses in the Anycast detection packet.

[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0012] Figure 1A is a schematic diagram of a network service system according to an exemplary embodiment of the present disclosure.

[0013] Figure 1B is a flowchart illustrating a network service-based detection method according to an exemplary embodiment of this disclosure.

[0014] Figure 2A is a flowchart illustrating a network service-based detection method according to an exemplary embodiment of this disclosure.

[0015] Figure 2B is a schematic diagram illustrating a detection method according to an exemplary embodiment of this disclosure.

[0016] Figure 2C is a schematic diagram illustrating another detection method according to an exemplary embodiment of the present disclosure.

[0017] Figure 2D is a schematic diagram illustrating another detection method according to an exemplary embodiment of the present disclosure.

[0018] Figure 2E is a schematic diagram illustrating another detection method according to an exemplary embodiment of this disclosure.

[0019] Figure 3 is a hardware structure diagram of a computer device containing a network service-based detection device according to an exemplary embodiment of the present disclosure.

[0020] Figure 4 is a structural diagram of a network service-based detection device according to an exemplary embodiment of this disclosure.

[0021] Figure 5 is a structural diagram of another network service-based detection device according to an exemplary embodiment of this disclosure. Detailed Implementation

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

[0023] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0024] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0025] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points shall be provided for users to choose to authorize or refuse.

[0026] In traditional network services, the user constructs packets from the originator to the destination. After the packet is sent from the originator, its network path is determined by the operator and is unpredictable. As network scale continues to increase and business demands grow, this traditional best-effort forwarding can no longer meet business requirements. Currently, there are new service-oriented network architectures. Under these new architectures, the network can be encapsulated into different levels of services, allowing users to actively choose different network services to meet their diverse needs.

[0027] Figure 1A is a schematic diagram of a network service system according to an exemplary embodiment of the present disclosure. The network service system can provide services to user terminals (user terminal 101, user terminal 102, etc. in Figure 1A). The network service system includes an access point device cluster 110 and an intermediate network device cluster 120 connected to the access point device cluster 110. That is, the intermediate network device cluster 120 may include multiple intermediate network devices, and the access point device cluster 110 may be connected to multiple intermediate network devices.

[0028] The access point device cluster may include one or more access point devices; the access point device cluster can provide user service access. Each access point device can be any computer device, including but not limited to routers, switches, firewalls, load balancers, or gateways.

[0029] Intermediate network devices are responsible for data forwarding and routing between the access point device cluster and the target device, including but not limited to network devices such as routers, switches, firewalls, load balancers, or gateways.

[0030] The network service system of this embodiment can provide different types of network services. Different types of network services refer to accessing the destination through different network paths, where each network path includes one or more intermediate network devices. As an example, a network path can be the transmission path from the access point device cluster after the packet from the initiating end successfully reaches the destination 130. Different transmission paths will cover different intermediate network devices. Based on this novel service-oriented network, this embodiment proposes a method for detecting this service-oriented network.

[0031] Figure 1B is a flowchart illustrating a network service method of a network service system according to an exemplary embodiment of this disclosure. The method is applied to access point devices in the access point device cluster. The method may include: in step 102, in response to receiving a network packet sent by an initiating end to access a destination end, obtaining the target Anycast address in the network packet. In step 104, sending the network packet to the destination end through a target network path corresponding to the target Anycast address.

[0032] Anycast is a network communication technology that allows devices on a network to communicate using a single IP address, which can be mapped to multiple locations within the network. Anycast is a network addressing and routing technology that allows multiple network nodes (such as servers or routers) in different locations to communicate using the same IP address. These nodes are distributed across different locations, but when a data packet is sent to that IP address, the router forwards it to the nearest (usually the one with the lowest latency) node, thus accelerating network speeds.

[0033] In this embodiment, the network packet can be a client-side packet that, based on the original packet, is constructed by encapsulating a tunnel to send to a specific Anycast address in the access point cluster. For example, if the original packet is sent from IP_A to IP_B, a tunnel can be encapsulated on the original packet to generate a new network packet that wraps the original packet. This new network packet is then sent from IP_A to the designated Anycast address in the access point cluster. When an access point device in the cluster receives this network packet, it can perform a decapsulation operation to obtain the original packet and forward it accordingly.

[0034] In the network service system of this embodiment, the access point devices in the access point device cluster can be located in the same location; the network packet originating from the access point device can be received by any access point device in the access point device cluster.

[0035] As an example, assume that the access point device cluster provides two types of network services, namely service X and service Y. For these two services, the Anycast address corresponding to service A is address x, and the Anycast address corresponding to service B is address y. From the access point device cluster to the destination, two different network paths are constructed: network path 1 for service A, which passes through three intermediate network devices A, B, and C; and network path 2 for service B, which passes through two intermediate network devices A and B.

[0036] As an example, path 1 involves more intermediate network devices, resulting in higher latency, higher bandwidth, and lower cost; while path 2 involves fewer intermediate network devices, resulting in lower latency, lower bandwidth, and higher cost.

[0037] In practical applications, different types of network services can refer to differences in one or more dimensions such as latency, bandwidth, or cost.

[0038] As an example, taking a cloud service scenario, a cloud service provider offers object storage services to users. The data storage center (destination) is located in one location, while the service center (access point device) is located in another. From the service center to the data storage center, considering the cost or bandwidth issues of different lines, the two paths mentioned above can be constructed. In this way, different network services can be provided to different users. Some users are cost-sensitive and can choose service A, while others have high latency requirements and can choose service B. Still others have high bandwidth requirements and can choose service A.

[0039] It is understood that this is only for illustration purposes. In actual applications, the number of network services and network paths can be much greater, and this embodiment does not limit this.

[0040] As can be seen from the above embodiments, the network service system can be encapsulated into different types of network services, allowing services to actively choose to consume different services, thereby meeting the differentiated needs of services. In the traditional best-effort forwarding mode, it is unknown which path the packet will take to reach the destination after it is sent from the initiator, while the new network service system provides predictable network services, that is, network packets can be transmitted along a specified network path.

[0041] Under the aforementioned new service-oriented network architecture, traditional network measurement methods focus on link-level probing, which has certain limitations. For example, in traditional Ping probing, the initiating end sends a probe packet to the IP address to be probed. This probing method does not conform to the actual use of the network service system described in this embodiment, because in the network service system, the user's network packets first arrive at a device in the access point device cluster based on Anycast, and then that device selects a network path to forward them to the destination.

[0042] Therefore, the detection method of link-level network probing is inconsistent with the packet sending process when users use network services of the network service system, thus failing to accurately detect whether the network service system is functioning normally. It also fails to deeply integrate with the characteristics of the service network architecture, failing to fully leverage the advantages brought by the new architecture. Link-level network probing focuses primarily on the stability of the network link; in some scenarios, it cannot perceive the status of upper-layer network services, resulting in network service failures going undetected even when all network links appear normal.

[0043] Based on this, the present disclosure also provides a method for detecting a network service system. As shown in FIG2A, it is a flowchart of a method for detecting a network service system according to an exemplary embodiment of the present disclosure, which includes the following steps.

[0044] In step 202, send an Anycast probe message to the at least one Anycast address to access the destination.

[0045] The access point devices in the access point device cluster are used to send the Anycast probe message to the destination based on the target Anycast address in the Anycast probe message and through the target network path corresponding to the target Anycast address, when the Anycast probe message is successfully received.

[0046] In step 204, based on the number of successful responses in the multiple Anycast probe messages, it is determined whether the network service system is functioning normally.

[0047] As an example, the detection method of this embodiment is applied to a detection terminal, which can be a program deployed on a computer device. The computer device on which the detection terminal is deployed in this embodiment can be arbitrary; for example, the computer device can be configured independently to deploy the detection terminal, and this computer device can be a device independent of the network service system. Alternatively, the detection terminal can also be deployed on a user device; this embodiment does not limit this. In some examples, steps 202 and 204 can both be executed by the detection terminal; in other examples, steps 202 and 204 are optional on different devices; this embodiment does not limit this.

[0048] The detection method in this embodiment can simulate the process of a real network service. The detection end initiates Anycast probe packets to one or more Anycast addresses configured in the access point device cluster to access the destination. If the access point device cluster has multiple Anycast addresses, probe packets can be initiated for each Anycast address separately. Each Anycast probe packet can carry an Anycast address, i.e., the target Anycast address. Therefore, if any access point device in the access point device cluster successfully receives an Anycast probe packet, it can send the Anycast probe packet to the destination based on the target Anycast address in the Anycast probe packet, through the target network path corresponding to the target Anycast address.

[0049] In some examples, each network service publishes an Anycast address for users to access the network service. When an access point device cluster is configured with multiple Anycast addresses, if only the access point device cluster is being probed, the probe can send multiple Anycast probe packets to at least one Anycast address to access the destination. Based on the number of successful responses among the multiple Anycast probe packets, it can be determined whether the network service system is functioning normally; for example, it can be determined whether there are faulty devices in the access point device cluster.

[0050] As an example, a strict standard can be used, such as considering the network service system abnormal if any Anycast probe message fails to receive a response. A more lenient standard can also be used, such as determining that the network service system is abnormal if the number of unsuccessful responses is greater than or equal to a preset threshold. This preset threshold can be flexibly configured according to actual needs; this embodiment does not limit this. Alternatively, the standard can be determined based on the proportion of unsuccessful responses to the total number of probe messages sent by the probe. For example, if this proportion is greater than or equal to a preset proportion threshold, the network service system is determined to be abnormal. This preset threshold can be flexibly configured according to actual needs; this embodiment does not limit this.

[0051] In some examples, sending Anycast probe packets to the at least one Anycast address to access the destination may include: sending multiple Anycast probe packets to the at least one Anycast address based on the number of devices in the access point device cluster and the network links between the initiating end and the access point device cluster; wherein the number of Anycast probe packets to the at least one Anycast address is greater than or equal to the number of devices and greater than or equal to the number of network links, so that each access point device in the access point device cluster can be allocated at least one Anycast probe packet; determining whether the network service system is normal based on the number of successful responses in the multiple Anycast probe packets includes: determining whether there are faulty devices in the access point device cluster based on the number of successful responses in the multiple Anycast probe packets.

[0052] As an example, to identify whether there are faulty devices in an access point device cluster, this embodiment can send a large number of Anycast probe messages, which can be sent continuously, so that each access point device in the cluster can be allocated at least one Anycast probe message. For example, if all access point devices in the cluster are located in the same location, and the number of Anycast probe messages for Anycast addresses is greater than or equal to the number of devices, and the number of messages is positively correlated with the number of devices in the cluster, then when multiple Anycast probe messages are sent continuously, these multiple Anycast probe messages will be evenly distributed among the access point devices.

[0053] As an example, if all access point devices in a cluster are located in the same area, the cluster will distribute packets based on load balancing principles, such as ECMP (Equal-Cost Multi-Path Routing) strategies. By using the same metric, traffic is distributed reasonably across multiple devices. Therefore, theoretically, multiple consecutive Anycast probe packets will be evenly distributed to each access point device. Taking IPv6 (Internet Protocol version 6) packets as an example, the Flow Label in IPv6 is a 20-bit field in the IPv6 packet header used to identify a specific traffic flow. This field was designed to support load balancing and quality of service control in the network. Based on this, the Flow Labels in multiple consecutive Anycast probe packets can be different. The cluster will calculate the corresponding hash value for the Flow Label of each Anycast probe packet, and the packet will be assigned to the access point device corresponding to the hash value. Therefore, considering that calculating the hash value ensures that each access point device receives at least one packet, the number of Anycast probe packets can be designed based on the number of devices.

[0054] As an example, the number of packets can also be determined by considering the network links between the probe and the access point device cluster. The probe and the access point device cluster can be located in the same location, such as in the same data center, in which case the probe can directly connect to the access point device cluster via the internal network. In real-world applications, real users are often not located in the same location as the access point device cluster, but the network link between the user (as the initiating end) and the access point device cluster can be known in advance. To simulate real service, the probe and the access point device cluster can also be located in different locations, in which case there can be one or more predetermined network links between them. In this embodiment, the network link refers to the path that the packet sent by the probe needs to traverse to reach the access point device cluster, and the path can include one or more network devices. The number of Anycast probe packets in this embodiment can be greater than or equal to the number of network links to cover each network link and the network devices on each network link. Based on this, the solution in this embodiment can cover multiple links and minimize the impact of link failures.

[0055] Therefore, based on this, the normality of the network service system can be determined by the number of successful responses among multiple Anycast probe messages. In practical applications, there are several ways to determine whether an Anycast probe message has received a successful response. For example, the probe end can determine whether it has received a response message corresponding to the Anycast probe message. Alternatively, it can determine whether the destination end has successfully received the Anycast probe message.

[0056] In some examples, determining whether there are faulty devices in the access point device cluster based on the number of successful responses among the plurality of Anycast probe messages may include: if the number of successful responses is lower than the number of Anycast probe messages, then it is determined that there are packet-lost Anycast probe messages, and the presence of faulty devices in the access point device cluster is determined according to the proportion of the number of packet-lost Anycast probe messages to the total number of Anycast probe messages sent; the method further includes: if it is determined that there are faulty devices, then the number of faulty devices is determined according to the proportion.

[0057] As an example, if Anycast probe messages successfully reach the access point device cluster, then one access point device in the cluster will be able to respond successfully. If the number of successful responses is less than the number of Anycast probe messages, it indicates that some Anycast probe messages have been lost. This embodiment can calculate the proportion of lost Anycast probe messages to the total number of Anycast probe messages sent, and thus determine whether there are faulty devices in the access point device cluster based on the proportion. In practical applications, specific standards can be set; for example, any message not exceeding 0% is considered a faulty device, or a proportion greater than or equal to a preset threshold is considered a faulty device. Furthermore, if faulty devices are determined to exist, this embodiment can determine the number of faulty devices based on the proportion; for example, multiplying the proportion by the number of devices in the access point device cluster gives the number of faulty devices.

[0058] As an example, suppose the access point device cluster has 4 devices and sends out 100 Anycast probe messages. Theoretically, each device should receive 25. After probing, it is found that 75 devices responded successfully, and 25 packets were lost, resulting in a packet loss rate of 25%. Therefore, the number of faulty devices can be determined to be 25% * 4 = 1. Thus, it can be confirmed that there is one faulty device in the access point device cluster.

[0059] Therefore, this embodiment can detect whether there are faulty devices in the access point device cluster through the above method.

[0060] To quickly identify problems in an access point device cluster, other embodiments can be combined to locate faulty devices. In some examples, each access point device in the cluster is configured with a corresponding unicast address; the method further includes: sending a unicast probe message to the unicast address to request the access point device to send the unicast probe message to the destination; and determining that the target access point device is a faulty device based on packet loss in the unicast probe message sent to the target access point device.

[0061] In this embodiment, a combined unicast approach is used to locate faulty devices. Each access point device can be configured with a unicast address. Unicast is a network communication method that allows one device to send a message to another, and the message can only be received by the receiving device. Unicast is a one-to-one communication method. The unicast address configured for each access point device in this embodiment can be used only for detection and does not provide external services.

[0062] Optionally, each Unicast address may send one or more Unicast probe messages to the destination; similarly, the number of network links between the probe and the access point device cluster may be determined, for example, it may be greater than or equal to the number of network links.

[0063] For example, if there are 4 access point devices in the cluster and 3 network links between the probe and the cluster, then the Unicast probe messages sent by the probe to each Unicast address need to cover these 3 links as much as possible. For example, it can send more than 3 Unicast probe messages to the Unicast address continuously.

[0064] Therefore, the presence of faulty devices can be determined based on the response status of Unicast probe messages. Unicast probe messages are normally sent to the access point device corresponding to the probe message. If an Anycast probe message is not responded to, the access point device corresponding to that probe message can be considered malfunctioning. Each Unicast address can send multiple probe messages, so the number of successful responses to probe messages sent to each Unicast address can be obtained. For example, based on the number of successful responses to Unicast probe messages sent to each access point device, it can be determined whether each access point device is a faulty device. For instance, if the number of successful responses to Unicast probe messages for each access point device is equal to the total number of probe messages sent to that access point device, the device can be considered normal; if they are not equal, and the number of successful responses is less than the total number of probe messages sent to that access point device, the device can be considered faulty. As an example, if the packet loss rate of the Unicast address corresponding to one device is 100%, and the packet loss rate of the Unicast address corresponding to other devices is 0%, then this device is faulty.

[0065] Figure 2B is a schematic diagram illustrating a detection method according to an exemplary embodiment of this disclosure. In Figure 2B, ServiceNetwork refers to a network service system, and Device1, Device2, Device3, and Device4 refer to an access point device cluster.

[0066] The probe can continuously send multiple Anycast probe messages to the destination based on the Anycast address.

[0067] The probe can continuously send multiple Unicast probe messages to the destination for each Unicast address.

[0068] Faulty nodes can be analyzed based on packet loss data of Anycast and Unicast probe messages. As shown in the figure, four devices correspond to four different Unicast addresses. Assuming the Anycast address packet loss rate is 25%, if the Unicast address corresponding to one device has a 100% packet loss rate while the Unicast address corresponding to the other devices has a 0% packet loss rate, then this device is faulty.

[0069] In other examples, a multi-service, multi-path probing approach can also be used. For instance, sending multiple Anycast probe messages to the Anycast address to access the destination can include: sending an Anycast probe message to each Anycast address to access the destination; determining whether the network service system is functioning normally can include: determining whether there is a faulty network path based on the destination's reception of each Anycast probe message.

[0070] As mentioned in the foregoing embodiments, the network service system can provide different types of network services, and different types of network services access the destination through different network paths; based on this, in order to identify whether each network path is normal, Anycast probe messages can also be sent to each service.

[0071] In some cases, since the network path is selected by the access point device based on the Anycast address in the message after successfully receiving the Anycast probe message, the detection of whether the network path is normal can be performed after confirming that the access point device cluster is normal.

[0072] Alternatively, it is also optional to simultaneously probe the access point device cluster and the network path. As an example, multiple Anycast probe packets can be sent to each Anycast address, and the number of Anycast probe packets sent to each Anycast address can be determined based on the aforementioned embodiments.

[0073] As an example, since Anycast probe messages to the destination are sent to each Anycast address, these messages cover every network path. If a network path fails, the Anycast probe messages transmitted along that path will not be received by the destination. Therefore, by analyzing the destination's reception of each Anycast probe message, it can be determined whether a faulty network path exists. For instance, if all Anycast probe messages sent to each Anycast address are successfully received by the destination, then all network paths are normal. If an Anycast probe message sent to a particular Anycast address fails to be received by that destination, then the network path corresponding to that Anycast address can be considered faulty.

[0074] In some examples, determining whether a faulty network path exists based on the destination's reception of each Anycast probe message may include: if a packet-loss faulty Anycast probe message is determined to exist, determining the network path corresponding to the faulty Anycast probe message as the faulty network path.

[0075] Figure 2C is a schematic diagram of another detection method according to an exemplary embodiment of the present disclosure; Device A in the figure is an access point device in an access point device cluster; taking two types of network services and two network paths as an example: service X is reached by the access point device through network path 1 (passing through devices B and C); service Y is reached by the access point device through network path 2 (passing through device B).

[0076] In this embodiment, the probe end constructs probe packets for services X and Y, that is, it sends an Anycast probe packet to the destination end to the Anycast address x corresponding to service X; and sends an Anycast probe packet to the destination end to the Anycast address y corresponding to service Y.

[0077] Whether a network path is functioning correctly can be determined based on whether services X and Y experience packet loss, and faulty nodes can be analyzed based on packet loss patterns. For example, if network path 1 corresponding to service X has a problem, Anycast probe packets sent to Anycast address x will fail to reach their destination, thus confirming that network path 1 corresponding to service X has a problem.

[0078] Whether an Anycast probe message sent to Anycast address x reaches its destination can be determined in several ways. For example, it can be based on the Anycast probe message received at the destination. For instance, the Anycast probe message may carry identification information that represents the corresponding network path. By parsing the identification information of the Anycast probe message, it can be determined which path successfully reaches the destination. For example, if network path 1 corresponding to service X has a problem, while network path 2 corresponding to service Y is normal, the destination can receive probe messages sent to Anycast address y corresponding to service Y. Then, it can parse the identification information representing network path 2 from the probe message, thus determining that network path 2 is normal. Conversely, if network path 1 is abnormal, the corresponding probe message cannot be received, thus determining that network path 1 has a problem.

[0079] As another example, suppose there are n different types of network services, and m Anycast probe messages are sent to the Anycast address of each network service, then a total of n*m Anycast probe messages will be sent.

[0080] Assuming the access point device cluster is functioning normally and all network paths are working properly, the destination can receive n*m ​​Anycast probe packets. If a network path is faulty, then the m Anycast probe packets corresponding to that network path may not be fully received, or only a small number may be received. Therefore, the presence of a fault in a network path can be determined based on the ratio of the number of Anycast probe packets received by the destination from each network path to the number of Anycast probe packets sent from that path.

[0081] In practical applications, there may be situations where the network path is functional but the latency is high, which can also be considered a network path anomaly. Therefore, in other examples, latency can be used to determine whether each network path is normal; Anycast probe messages can carry the sending time; at the destination, the receiving time of the received Anycast probe message can be obtained. The latency is calculated by the difference between the receiving time and the sending time of each Anycast probe message. If the latency is greater than or equal to a set duration threshold, the transmission of that Anycast probe message can be considered abnormal, thus inferring whether the network path is abnormal.

[0082] Based on this, in this embodiment, for each network path, the presence of a network path fault can be determined by combining the number of Anycast probe messages received by the destination end and the ratio of the number sent, as well as the latency of the Anycast probe messages received by the destination end.

[0083] The above embodiments can be used to check whether the network path is abnormal. The network path contains one or more intermediate network devices. The abnormality of the network path may be caused by the failure of some intermediate network devices in the network path. Based on this, the faulty intermediate network devices can also be located by detection.

[0084] In some examples, the method may further include: determining relevant normal network paths based on the faulty network path; the set of intermediate network devices included in the relevant normal network path intersects with the set of multiple intermediate network devices included in the faulty network path; determining that a faulty device exists among the intermediate network devices in the faulty network path other than the intersection.

[0085] In this embodiment, when there are multiple network paths, for a faulty network path, this embodiment designs a method to use the associated normal network paths to determine the faulty device in the faulty network path.

[0086] As an example, assume that: network path Z1 contains the following intermediate network devices in sequence: device d1, device d2, device d3, and device d4; network path Z2 contains the following intermediate network devices in sequence: device d1, device d2, and device d5; the set of intermediate network devices in network path Z1 intersects with the set of intermediate network devices in network path Z2: device d1 and device d2; since network path Z2 is normal, the intermediate network devices within the intersection are normal devices; among the intermediate network devices in network path Z1 other than the intersection (devices d3 and d4), there are faulty devices. Thus, through the above embodiment, the range of faulty devices in the network path can be located, thereby achieving fault location.

[0087] Furthermore, if in a faulty network path, the difference set with the relevant normal network path contains only one faulty device, then the intermediate network device in that difference set is the faulty device. The difference set refers to the set of elements in sets Set1 and Set2 that belong to Set1 but not Set2.

[0088] For example, suppose that the intermediate network devices included in network path Z3 are, in order: device d1, device d2, device d3 and device d5; the difference between network path Z1 and network path Z3 is device d4, and it can be determined that device d4 is a faulty device.

[0089] In the embodiment shown in Figure 2C, if the network path corresponding to service X is faulty, while the network path corresponding to service Y is normal; since service X is sent from the access point device through two devices B and C, while service Y is sent from the access point device through B, it can be concluded that device B is normal and device C is a faulty device.

[0090] Thus, this embodiment can accurately locate the faulty device in the network path by means of the above method.

[0091] In some cases, based on the characteristics of network service systems, service consistency monitoring can also be performed. In a network service system, under normal business conditions, network packets can carry service type information, indicating the type of network service. Specifically, normal network packets can carry service type information in the packet header. During normal business, when a user selects a service, the client can encapsulate an Anycast tunnel on the original packet (sent from the originator to the destination). This tunnel contains the service type information; that is, a new packet header is encapsulated on the original packet to obtain a new network packet containing the Anycast address, so that the new network packet is sent to the Anycast address. After the new network packet arrives at the access point device, the access point device can decapsulate the tunnel, that is, strip the packet header from the new network packet to obtain the original packet, and then encapsulate the original packet again to form a tunnel for forwarding from the access point device to the destination. During this forwarding, the service type information is still encapsulated in the tunnel, and this tunnel inherits the service type information of the previous tunnel. Thus, the service remains consistent throughout the entire forwarding process. If the access point device inherits incorrectly when encapsulating the tunnel, the service type information will change. In the packet header, the service type information can be set in the Anycast address field, where several bits represent the service type information. Normally, only the access point device modifies the packet header.

[0092] In this embodiment, for service consistency monitoring, the probe message carries service type information not only in the header but also in the payload. The probe message can be forwarded between the access point device and various intermediate network devices. Specifically, each device forwards the message based on the service type information in the packet, while also carrying the service type information to the next-hop device. During this process, the device does not modify the payload during forwarding, but the header may contain inheritance errors. The service type information carried in the payload is used as the standard. If the service type information in the header differs from that in the payload, it indicates an error in the mapping of a certain device, which will cause the service to deviate from the expected service performance.

[0093] Sending an Anycast probe message to the Anycast address to access the destination may include: constructing an Anycast probe message whose header and payload both carry service type information, and then sending the Anycast probe message to the Anycast address to access the destination; so that the collection terminal collects the Anycast probe messages received by the access point device and / or the intermediate network device, and by parsing the header and payload of the collected Anycast probe message, if the service type information carried in the header is different from the service type information carried in the payload, it is determined that the device receiving the Anycast probe message is faulty.

[0094] As an example, Figure 2D is a schematic diagram illustrating another detection method according to an exemplary embodiment of this disclosure. In this embodiment, each device in the network service system can implement the SFlow protocol, which is a protocol for analyzing network traffic based on sampling and can intercept packet headers for analysis.

[0095] In this embodiment, the probe end constructs Anycast probe packets whose header and payload both carry service type information, such as "class = X" as shown in the figure. Each device can enable sflow collection and report flow logs to the collection end. In this embodiment, the collection end can be the probe end or another end different from the collection end. The collection end analyzes the sflow logs of each device in real time, parses and compares the service class field in the packet header and payload, and finds devices with incorrect mappings.

[0096] For example, sflow contains flow and counter. The flow in the device truncates the original probe packets before sending them, allowing analysis of changes in the packets sent by the probe at each hop. Therefore, the packets sent by the probe can be obtained at each hop during forwarding; the payload is not modified during forwarding, but fields in the header may be modified. By comparing the service type information in the payload with the service type information in the header, it is possible to detect any mapping errors.

[0097] As can be seen from the above embodiments, this embodiment simulates a real business probing based on network services initiated from the end side, deeply integrates the architectural characteristics of service-oriented networks, and realizes the discovery and accurate location of network service anomalies.

[0098] By using joint Anycast and Unicast detection, simulating real-world business operations to simultaneously probe both Anycast and Unicast, and combining Anycast's anomaly detection capabilities with Unicast's precise location capabilities, abnormal network services can be quickly identified and accurately located.

[0099] By using multi-service and multi-path detection, the architectural features of service-oriented networks are fully utilized to associate different paths with different network services, enabling rapid discovery and accurate location of abnormal nodes.

[0100] By monitoring service consistency and integrating sFlow technology, we can deeply analyze network traffic content, send customized probe packets, and effectively identify service inconsistencies by capturing packet payloads, thus ensuring the continuity and stability of network services.

[0101] In this system, network service systems can be encapsulated into different types of network services, allowing businesses to proactively choose and consume different services to meet their differentiated needs. Under this novel service-oriented network architecture, this embodiment provides a service-based detection method initiated from the endpoint. By deeply integrating the architectural characteristics of service-oriented networks, it achieves rapid discovery and accurate location of network service anomalies, effectively ensuring the continuous and stable operation of network services.

[0102] Figure 2E is a flowchart illustrating a network service-based probing method according to an exemplary embodiment of this disclosure. This method can be used to probe a network service system, which includes a probe terminal, an access point device cluster, and multiple intermediate network devices connected to the access point device cluster. The access point device cluster is configured with at least one Anycast address, and different Anycast addresses correspond to different types of network services. These different types of network services refer to accessing a destination through different network paths, where each network path includes one or more of the intermediate network devices. The probe terminal is used to send multiple Anycast probe messages to the at least one Anycast address to access the destination. The method is applied to the access point devices in the access point device cluster and may include the following steps.

[0103] In step 212, in response to receiving an Anycast probe message sent by the probe end, the target Anycast address in the Anycast probe message is obtained.

[0104] In step 214, the Anycast probe message is sent to the destination via the target network path corresponding to the target Anycast address. The number of successful responses among the multiple Anycast probe messages is used to determine whether the network service system is functioning correctly.

[0105] The specific implementation of the method in this embodiment can be referred to the description of the foregoing embodiments, and will not be repeated here.

[0106] Corresponding to the aforementioned embodiments of the network service-based detection method, this disclosure also provides embodiments of the network service-based detection device and the computer equipment used thereon.

[0107] The embodiments of the network service-based detection device disclosed herein can be applied to computer devices, such as servers or terminal devices. The device embodiments can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by its processor reading the corresponding computer program instructions from non-volatile memory into memory for execution. From a hardware perspective, as shown in Figure 3, it is a hardware structure diagram of the computer device where the detection device / network service device of the network service system of this disclosure resides. In addition to the processor 310, network interface 320, memory 330, and non-volatile memory 340 shown in Figure 3, the computer device where the network service-based detection device resides in the embodiments may also include other hardware depending on the actual functions of the computer device, which will not be elaborated further.

[0108] As shown in Figure 4, which is a structural diagram of a network service-based detection device according to an exemplary embodiment of the present disclosure, the network service system includes an access point device cluster and a plurality of intermediate network devices connected to the access point device cluster; the access point device cluster is configured with at least one Anycast address, and different Anycast addresses correspond to different types of network services; the different types of network services refer to accessing the destination through different network paths, and the network path includes one or more of the intermediate network devices.

[0109] The apparatus includes: a sending module 41, configured to: send multiple Anycast probe messages to the at least one Anycast address to access the destination; an access point device in the access point device cluster, configured to, upon successfully receiving the Anycast probe message, send the Anycast probe message to the destination via a target network path corresponding to the target Anycast address, based on the target Anycast address in the Anycast probe message; and a determining module 42, configured to: determine whether the network service system is functioning normally based on the number of successful responses in the multiple Anycast probe messages.

[0110] In some examples, the sending module 41 is further configured to: send multiple Anycast probe messages to the at least one Anycast address based on the number of devices in the access point device cluster and the network links between the local end and the access point device cluster; wherein the number of Anycast probe messages for the at least one Anycast address is greater than or equal to the number of devices and greater than or equal to the number of network links, so that each access point device in the access point device cluster can be allocated at least one Anycast probe message; the determining module 42 is further configured to: determine whether there is a faulty device in the access point device cluster based on the number of successful responses in the multiple Anycast probe messages.

[0111] In some examples, the determining module 42 is further configured to: if the number of successful responses is lower than the number of Anycast probe messages, determine that there are lost Anycast probe messages; determine whether there are faulty devices in the access point device cluster based on the ratio of the number of lost Anycast probe messages to the total number of sent Anycast probe messages; if faulty devices are determined to exist, determine the number of faulty devices based on the ratio.

[0112] In some examples, each access point device in the access point device cluster is configured with a corresponding Unicast address; the determining module 42 is further configured to: send a Unicast probe message to each of the Unicast addresses to request the access point device to send the Unicast probe message to the destination; and determine whether each access point device is a faulty device based on the number of successful responses to the Unicast probe messages sent to each access point device.

[0113] In some examples, the determining module 42 is further configured to: send an Anycast probe message to each Anycast address to access the destination; and determine whether there is a faulty network path based on the destination's reception of each Anycast probe message.

[0114] In some examples, the determining module 42 is further configured to: if it is determined that there is a packet loss fault Anycast probe message, determine that the network path corresponding to the fault Anycast probe message is a faulty network path.

[0115] In some examples, the determining module 42 is further configured to: determine relevant normal network paths based on the faulty network path; the set of intermediate network devices included in the relevant normal network path intersects with the set of multiple intermediate network devices included in the faulty network path; and determine that there is a faulty device among the intermediate network devices in the faulty network path other than the intersection.

[0116] In some examples, the sending module 41 is further configured to: construct an Anycast probe message in which both the header and payload carry service type information, and then send the Anycast probe message to the Anycast address to access the destination; collect Anycast probe messages received by the access point device and / or the intermediate network device; parse the header and payload in the collected Anycast probe message, and if the service type information carried in the header is different from the service type information carried in the payload, determine that the device receiving the Anycast probe message is faulty.

[0117] As shown in Figure 5, which is a structural diagram of a network service-based detection device according to an exemplary embodiment of the present disclosure, the device is used to detect a network service system. The network service system includes a detection terminal, an access point device cluster, and multiple intermediate network devices connected to the access point device cluster. The access point device cluster is configured with at least one Anycast address, and different Anycast addresses correspond to different types of network services. The different types of network services refer to accessing a destination through different network paths, and the network path includes one or more of the intermediate network devices. The detection terminal is used to send multiple Anycast detection packets to the at least one Anycast address to access the destination.

[0118] The device is applied to access point devices in the access point device cluster. The device includes: an acquisition module 51, configured to: in response to receiving an Anycast probe message sent by the probe end, acquire the target Anycast address in the Anycast probe message; and a sending module 52, configured to: send the Anycast probe message to the destination end through a target network path corresponding to the target Anycast address; wherein the number of successful responses in the plurality of Anycast probe messages is used to determine whether the network service system is normal.

[0119] The implementation process of the functions and roles of each module in the above-mentioned network service-based detection device is detailed in the implementation process of the corresponding steps in the above-mentioned network service-based detection method, and will not be repeated here.

[0120] Accordingly, this disclosure also provides a network service system, the system including an access point device cluster and multiple intermediate network devices connected to the access point device cluster; the access point device cluster is configured with at least one Anycast address, and different Anycast addresses correspond to different types of network services; the different types of network services refer to accessing a destination through different network paths, and the network paths include one or more of the intermediate network devices; the system also includes a probe, the probe being used to execute the steps of the aforementioned method embodiments; and / or, the access point devices in the access point device cluster are used to execute the steps of the aforementioned method embodiments.

[0121] Accordingly, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the aforementioned network service-based detection method embodiments.

[0122] Accordingly, this disclosure also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the network service-based detection method embodiment.

[0123] Accordingly, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the network service-based detection method embodiment.

[0124] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0125] The above embodiments can be applied to one or more computer devices. The computer device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. The hardware of the computer device includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0126] The computer device can be any electronic product that can interact with the user, such as a personal computer, tablet computer, smartphone, personal digital assistant (PDA), game console, interactive network television (IPTV), smart wearable device, etc.

[0127] The computer equipment may also include network equipment and / or user equipment. The network equipment includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0128] The network in which the computer device is located includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, and virtual private network (VPN).

[0129] The foregoing has described specific embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0130] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this application.

[0131] While this disclosure contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the multiple embodiments of this disclosure may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0132] The terms "specific example" or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with the embodiments or examples, which are included in at least one embodiment or example of this disclosure. In this disclosure, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0133] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention applied herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not claimed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0134] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0135] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A network service based probing method for probing a network service system, the network service system comprising an access point device cluster and a plurality of intermediate network devices connected with the access point device cluster; the access point device cluster is configured with at least one Anycast address, different Anycast addresses correspond to different types of network services; the different types of network services refer to accessing a destination through different network paths, the network paths containing one or more intermediate network devices; the method comprising: sending a plurality of Anycast probe packets for accessing the destination to the at least one Anycast address; an access point device in the access point device cluster is configured to, in the case of successfully receiving the Anycast probe packet, send the Anycast probe packet to the destination through a target network path corresponding to a target Anycast address based on the target Anycast address in the Anycast probe packet; determining whether the network service system is normal based on the number of successful responses in the plurality of Anycast probe packets. 2.The method of claim 1, wherein the sending of the Anycast probe packets for accessing the destination to the at least one Anycast address comprises: sending a plurality of Anycast probe packets to the at least one Anycast address based on the number of devices in the access point device cluster and the number of network links between the local end and the access point device cluster; wherein the number of Anycast probe packets for the at least one Anycast address is greater than or equal to the number of devices and greater than or equal to the number of network links, so that each access point device in the access point device cluster can be allocated at least one Anycast probe packet; the determining of whether the network service system is normal based on the number of successful responses in the plurality of Anycast probe packets comprises: determining whether there is a faulty device in the access point device cluster based on the number of successful responses in the plurality of Anycast probe packets. 3.The method of claim 2, wherein the determining of whether there is a faulty device in the access point device cluster based on the number of successful responses in the plurality of Anycast probe packets comprises: if the number of successful responses is less than the number of Anycast probe packets, determining that there are lost Anycast probe packets, and determining whether there is a faulty device in the access point device cluster according to the proportion of the number of lost Anycast probe packets in the total number of sent Anycast probe packets; the method further comprises: if it is determined that there is a faulty device, determining the number of faulty devices according to the proportion. 4.The method of any one of claims 1 to 3, wherein each access point device in the access point device cluster is configured with a corresponding Unicast address; the method further comprises: sending a Unicast probe packet to each of the Unicast addresses to request the access point device to send the Unicast probe packet to the destination end; determining whether each of the access point devices is a faulty device based on the number of successful responses of the Unicast probe packet sent to each of the access point devices.

5. The method of claim 2, wherein the sending of the multiple Anycast probe packets to the Anycast addresses to access the destination end comprises: sending an Anycast probe packet to each of the Anycast addresses to access the destination end, respectively; the determining of whether the network service system is normal comprises: determining whether there is a faulty network path based on the reception of the Anycast probe packets by the destination end.

6. The method of claim 5, wherein the determining of whether there is a faulty network path based on the reception of the Anycast probe packets by the destination end comprises: if a faulty Anycast probe packet with packet loss is determined, determining that a network path corresponding to the faulty Anycast probe packet is a faulty network path.

7. The method of claim 6, further comprising: determining a relevant normal network path based on the faulty network path; the relevant normal network path contains a set of intermediate network devices that has an intersection with a set of multiple intermediate network devices contained in the faulty network path; determining that there is a faulty device in an intermediate network device other than the intersection in the faulty network path.

8. The method of claim 1, wherein the sending of the Anycast probe packets to the Anycast addresses to access the destination end comprises: after constructing an Anycast probe packet carrying service type information in both a packet header and a payload, sending the Anycast probe packet to the Anycast addresses to access the destination end; so that the collection end collects the Anycast probe packets received by the access point device and / or the intermediate network device, analyzes the packet header and the payload in the collected Anycast probe packet, and determines that a device receiving the Anycast probe packet is faulty if the service type information carried in the packet header is different from the service type information carried in the payload.

9. A network service-based probe method for probing a network service system, the network service system comprising a probe end, a cluster of access point devices, and multiple intermediate network devices connected to the cluster of access point devices; the cluster of access point devices is configured with at least one Anycast address, and different Anycast addresses correspond to different types of network services; the different types of network services refer to accessing a destination end through different network paths, and the network paths contain one or more intermediate network devices; the probe end is configured to send multiple Anycast probe packets to the at least one Anycast address to access the destination end. The method is applied to an access point device in the access point device cluster, and the method comprises: In response to receiving an Anycast probe packet sent by the probe end, obtaining a target Anycast address in the Anycast probe packet; Sending the Anycast probe packet to the destination end through a target network path corresponding to the target Anycast address; wherein the number of successfully responded Anycast probe packets is used to determine whether the network service system is normal. 10.A network service system, comprising an access point device cluster and a plurality of intermediate network devices connected to the access point device cluster; the access point device cluster is configured with at least one Anycast address, and different Anycast addresses correspond to different types of network services; the different types of network services refer to accessing a destination end through different network paths, and the network paths contain one or more intermediate network devices; The system further comprises a probe end for executing the steps of the method of any one of claims 1 to 8; and / or an access point device in the access point device cluster for executing the steps of the method of claim 9.

11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 9. 12.A computer program product, comprising a computer program, wherein the computer program is executed by a processor to implement the steps of the method of any one of claims 1 to 9. 13.A computer readable storage medium, having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the method of any one of claims 1 to 9.

Images