A data processing method and related apparatus

Abstract

The embodiment of the application discloses a data processing method, which is applied to a scheduling node, the scheduling node is deployed in a cloud system, the cloud system is used for processing a dial test task, and the method comprises the following steps: receiving first information, the first information is used for indicating a plurality of network nodes for transmitting a first message, a source address of the first message indicates a first application instance, a destination address of the first message indicates a second application instance, the first application instance is an application instance running on a first network node, the first network node is a head node in the plurality of network nodes, and the second application instance is an application instance running on a second network node, and the second network node is a tail node in the plurality of network nodes; receiving second information, the second information is used for indicating whether the first message reaches the second application instance; determining a dial test result according to the first information and the second information, and the dial test result comprises the first application instance, the plurality of network nodes and the second application instance.

Description

Technical Field

[0001] This application relates to the field of cloud computing, and more particularly to a data processing method and related apparatus. Background Technology

[0002] With the rapid development of cloud computing, the complexity of cloud network operation and maintenance has increased significantly. The black-box nature of network architecture results in a lack of end-to-end visibility into runtime status, leading to inefficient localization and handling of issues such as connectivity and network jitter.

[0003] By injecting simulated packets with colored tags into the testing task, network devices generate path fingerprints when they recognize the tags, thereby constructing the traffic path topology and realizing a white-box operation and maintenance interface. This enables network administrators and maintenance personnel to quickly define the scope of problems and perform precise repairs.

[0004] However, when users' businesses run in container network environments such as Kubernetes (K8S), access between container resources remains a black box, resulting in incomplete traffic paths in probing tasks. Summary of the Invention

[0005] This application provides a data processing method and related apparatus for connecting a basic network and a container network in a cloud environment to obtain the complete traffic path in a probing task.

[0006] In a first aspect, embodiments of this application provide a data processing method. This method is applied to a scheduling node, which is deployed in a cloud system. The cloud system is used to process probing tasks. The method includes:

[0007] Receive first information, the first information is used to indicate multiple network nodes transmitting the first message, the source address of the first message indicates the first application instance, the destination address of the first message indicates the second application instance, the first application instance is an application instance running on the first network node, the first network node is the head node among multiple network nodes, the second application instance is an application instance running on the second network node, and the second network node is the tail node among multiple network nodes.

[0008] Receive second information, which indicates whether the first message has reached the second application instance;

[0009] The test results are determined based on the first and second information. The test results include the first application instance, multiple network nodes, and the second application instance. The test results are the traffic path information of the test task.

[0010] In this application, probing is a network diagnostic method that simulates a user sending messages to test whether communication can be established between two target objects, thereby verifying whether the network between the two target objects is normal. In this application, the target object of the probing task is an application instance in a container network. An application instance can be understood as the smallest deployment unit in a container network, belonging to the workload resources of the container network, which depends on the underlying resources of the cloud system. Each application instance contains one or more containers sharing a network namespace, and each network node can host one or more application instances. For example, a Pod is an application instance in a Kubernetes (K8S) container network.

[0011] The first and second application instances are deployed on two different network nodes. In cross-node communication scenarios, network connectivity between application instances mainly relies on the Container Network Interface (CNI) plugin. The CNI plugin assigns IP addresses to application instances and manages inter-node routing. It uses encapsulation technologies such as Virtual Extensible Local Area Network (VXLAN) to encapsulate the raw data packets of application instances into the physical network interface card (NIC) packets of the nodes, thus completing cross-node traffic forwarding.

[0012] During the test, the scheduling node only simulates the first application instance sending a first packet to the second application instance to achieve link status detection. The first packet encapsulates the address information of the first and second application instances in its header. When the network interface card device connected to the second application instance receives the first packet, it reports to the scheduling node that the first packet will be discarded after arriving at the second application instance to prevent it from entering the second application instance's runtime environment.

[0013] Using the above method, network nodes and target application instances report message arrival information when they receive the first message, enabling the scheduling node to reconstruct and connect the paths of the container network and the basic network, thereby obtaining the complete message traffic path and improving the network connectivity diagnostic capability and link visualization capability of the cloud system.

[0014] In one possible implementation, the first message includes a first message header and a second message header, the second message header being the next level header of the first message header. The first message header includes a first coloring mark, and the second message header includes a second coloring mark. The first coloring mark is used to instruct multiple network nodes to report to the scheduling node whether the first message has arrived, and the second coloring mark is used to instruct a second application instance to report to the scheduling node whether the first message has arrived.

[0015] In this application, the first message adopts a layered encapsulation architecture, consisting of a first message header, a second message header, and a message data payload. Different message headers can correspond to different protocol types, with the first message header being the outer protocol header and the second message header being the inner protocol header. For example, the first message header can correspond to the VXLAN protocol, and the second message header can correspond to the Transmission Control Protocol (TCP). Coloring is implemented by defining the protocol encoding value through the DSCP bit in the message header. For example, when the DSCP value is between 60 and 63, it indicates that the message has been tagged.

[0016] It should be noted that reporting whether the first message has arrived can also be understood as reporting whether the content of the message's data payload has arrived. When the first message arrives at the second network node, the outer header of the first message is stripped away, leaving only the second header and the message data payload. At this point, the second application instance reports the arrival status of the message data payload through the inner coloring mark.

[0017] In one possible implementation, the test results also include faulty nodes, which are the network nodes where the first message did not reach the next hop.

[0018] If the network device in the traffic path or the network card device corresponding to the second application instance fails to report the arrival information of the first packet, it can be inferred that an anomaly occurred during the transmission of the first packet at the previous hop network node.

[0019] In one possible implementation, before receiving the first information, the method further includes:

[0020] Send a test request to the first network node. The test request is used to instruct the first network node to send the first message.

[0021] In one possible implementation, the first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes a second coloring mark.

[0022] In this application, the scheduling node can deploy a probing agent on the load node of the first application instance. When performing probing tasks, the agent injects a colored packet (i.e., a second packet) into the network interface card (NIC) device of the load node to simulate data transmission by the first application instance. When this packet passes through the tunnel device of the first network node, it is encapsulated into a VXLAN packet, i.e., the aforementioned first packet. The header of this VXLAN packet is the aforementioned first packet header, and it carries the aforementioned first colored tag.

[0023] In one possible implementation, the first message is created at the network interface card (NIC) device of the first network node.

[0024] In this application, the scheduling node can also directly deploy a dial-up testing agent on the first network node, and inject colored packets (i.e., first packets) into the network card device of the first network node when executing dial-up testing tasks to simulate the first application instance sending data.

[0025] In one possible implementation, the network nodes include one or more of a virtualization server, a bare-metal server, and a switch. The virtualization server runs one or more virtual machines, each of which can act as a load balancer for an application instance.

[0026] Secondly, embodiments of this application provide a data processing method. The method is applied to a first network node, which is deployed in a cloud system. The cloud system is used to process probing tasks, and the cloud system also includes a scheduling node. The method includes:

[0027] A test request is received, which instructs a first network node to send a first message. The source address of the first message indicates a first application instance, and the destination address of the first message indicates a second application instance. The first message includes a first message header and a second message header. The second message header is the next level header of the first message header. The first message header includes a first coloring mark, and the second message header includes a second coloring mark. The first coloring mark is used to instruct multiple network nodes to report to the scheduling node whether the first message has arrived. The second coloring mark is used to instruct the second application instance to report to the scheduling node whether the first message has arrived. The multiple network nodes are network nodes used to transmit the first message, and the first network node is contained within the multiple network nodes.

[0028] Send the first message.

[0029] In this application, dial-up testing is a network diagnostic method that simulates a user sending messages to test whether communication can be established between two target objects, thereby verifying whether the network between the two target objects is normal. In this application, the target object of the dial-up testing task is an application instance in a container network. An application instance can be understood as the smallest deployment unit in a container network, belonging to the workload resources of the container network, which depends on the underlying resources of the cloud system. Each application instance contains one or more containers in a shared network namespace, and each network node can host one or more application instances. For example, a Pod is an application instance in a Kubernetes container network.

[0030] The first and second application instances are deployed on two different network nodes. In cross-node communication scenarios, network connectivity between application instances mainly relies on the CNI plugin. The CNI plugin assigns IP addresses to application instances and manages inter-node routing. It uses encapsulation technologies such as VXLAN to encapsulate the raw data packets of application instances into the physical network interface card (NIC) packets of the nodes, thus completing cross-node traffic forwarding.

[0031] During the test, the scheduling node only simulates the first application instance sending a first packet to the second application instance to achieve link status detection. The first packet encapsulates the address information of the first and second application instances in its header. When the network interface card device connected to the second application instance receives the first packet, it reports to the scheduling node that the first packet will be discarded after arriving at the second application instance to prevent it from entering the second application instance's runtime environment.

[0032] The first message employs a layered encapsulation architecture, consisting of a first message header, a second message header, and a message data payload. Different message headers correspond to different protocol types, with the first message header being the outer protocol header and the second message header being the inner protocol header. For example, the first message header could correspond to the VXLAN protocol, and the second message header could correspond to TCP. Coloring is implemented by defining the protocol encoding value using the DSCP bit in the message header. For example, a DSCP value of 60 to 63 indicates that the message has been tagged.

[0033] It should be noted that reporting whether the first message has arrived can also be understood as reporting whether the content of the message's data payload has arrived. When the first message arrives at the second network node, the outer header of the first message is stripped away, leaving only the second header and the message data payload. At this point, the second application instance reports the arrival status of the message data payload through the inner coloring mark.

[0034] Using the above method, network nodes and target application instances report message arrival information when they receive the first message, enabling the scheduling node to reconstruct and connect the paths of the container network and the basic network, thereby obtaining the complete message traffic path and improving the network connectivity diagnostic capability and link visualization capability of the cloud system.

[0035] In one possible implementation, the first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes a second coloring mark.

[0036] In this application, the scheduling node can deploy a probing agent on the load node of the first application instance. When performing probing tasks, the agent injects a colored packet (i.e., a second packet) into the network interface card (NIC) device of the load node to simulate data transmission by the first application instance. When this packet passes through the tunnel device of the first network node, it is encapsulated into a VXLAN packet, i.e., the aforementioned first packet. The header of this VXLAN packet is the aforementioned first packet header, and it carries the aforementioned first colored tag.

[0037] In one possible implementation, the first message is created at the network interface card (NIC) device of the first network node.

[0038] In this application, the scheduling node can also directly deploy a dial-up testing agent on the first network node, and inject colored packets (i.e., first packets) into the network card device of the first network node when executing dial-up testing tasks to simulate the first application instance sending data.

[0039] In one possible implementation, the network nodes include one or more of a virtualization server, a bare-metal server, and a switch. The virtualization server runs one or more virtual machines, each of which can act as a load balancer for an application instance.

[0040] Thirdly, embodiments of this application provide a data processing apparatus applied to a scheduling node, the scheduling node being deployed in a cloud system, the cloud system being used to process testing tasks, the apparatus comprising:

[0041] The receiving module is used to receive first information, which indicates multiple network nodes transmitting the first message. The source address of the first message indicates a first application instance, and the destination address of the first message indicates a second application instance. The first application instance is an application instance running on the first network node, and the first network node is the head node among multiple network nodes. The second application instance is an application instance running on the second network node, and the second network node is the tail node among multiple network nodes.

[0042] The receiving module is also used to receive second information, which is used to indicate whether the first message has arrived at the second application instance;

[0043] The processing module is used to determine the dialing test result based on the first information and the second information. The dialing test result includes the first application instance, multiple network nodes, and the second application instance.

[0044] In one possible implementation, the first message includes a first message header and a second message header, the second message header being the next level header of the first message header. The first message header includes a first coloring mark, and the second message header includes a second coloring mark. The first coloring mark is used to instruct multiple network nodes to report to the scheduling node whether the first message has arrived, and the second coloring mark is used to instruct a second application instance to report to the scheduling node whether the first message has arrived.

[0045] In one possible implementation, the test results also include faulty nodes, which are the network nodes where the first message did not reach the next hop.

[0046] In one possible implementation, the device further includes:

[0047] The sending module is used to send a test request to the first network node, which instructs the first network node to send a first message.

[0048] In one possible implementation, the first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes a second coloring mark.

[0049] In one possible implementation, the first message is created at the network interface card (NIC) device of the first network node.

[0050] In one possible implementation, the multiple network nodes include one or more of a virtualization server, a bare metal server, and a switch.

[0051] Fourthly, embodiments of this application provide a data processing apparatus applied to a first network node, the first network node being deployed in a cloud system, the cloud system being used to process probing tasks, the cloud system further including a scheduling node, the apparatus comprising:

[0052] The receiving module is used to receive a test request. The test request is used to instruct a first network node to send a first message. The source address of the first message indicates a first application instance, and the destination address of the first message indicates a second application instance. The first message includes a first message header and a second message header. The second message header is the next level header of the first message header. The first message header includes a first coloring mark, and the second message header includes a second coloring mark. The first coloring mark is used to instruct multiple network nodes to report to the scheduling node whether the first message has arrived. The second coloring mark is used to instruct the second application instance to report to the scheduling node whether the first message has arrived. The multiple network nodes are network nodes used to transmit the first message, and the first network node is contained in the multiple network nodes.

[0053] The sending module is used to send the first message.

[0054] In one possible implementation, the first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes a second coloring mark.

[0055] In one possible implementation, the first message is created at the network interface card (NIC) device of the first network node.

[0056] In one possible implementation, the multiple network nodes include one or more of a virtualization server, a bare metal server, and a switch.

[0057] Fifthly, embodiments of this application provide a computing device, including: a processor, a memory, and a transceiver. The memory stores computer programs or computer instructions, and the processor is used to call and run the computer programs or computer instructions stored in the memory, causing the processor to perform processing operations as described in the first aspect and any implementation thereof. The transceiver is used to transmit and receive signals, such as implementing the receiving and sending operations as described in the first aspect and any implementation thereof.

[0058] Sixthly, embodiments of this application provide a computing device, including: a processor, a memory, and a transceiver. The memory stores computer programs or computer instructions, and the processor is used to call and run the computer programs or computer instructions stored in the memory, causing the processor to perform processing operations as described in the second aspect and any implementation thereof. The transceiver is used to transmit and receive signals, such as implementing the receiving and transmitting operations as described in the second aspect and any implementation thereof.

[0059] In a seventh aspect, embodiments of this application provide a computing device cluster, including at least one computing device, each computing device including a processor and a memory, the memory storing computer programs or computer instructions, the processor being used to call and run the computer programs or computer instructions stored in the memory, so that the computing device cluster performs the first aspect and any of its optional methods described above.

[0060] Eighthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the methods described in the first aspect and any of its alternatives.

[0061] In a ninth aspect, embodiments of this application provide a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the methods described in the second aspect and any of its alternatives.

[0062] In a tenth aspect, embodiments of this application provide a computer program product containing instructions. The computer program product may be a software or program product containing instructions capable of running on a computing device or stored on any usable medium. When the computer program product is run on at least one computing device, it causes the at least one computing device to perform the methods described in the first aspect and any of its alternatives.

[0063] Eleventhly, embodiments of this application provide a computer program product containing instructions. The computer program product may be a software or program product containing instructions capable of running on a computing device or stored on any usable medium. When the computer program product is run on at least one computing device, it causes the at least one computing device to perform the methods described in the second aspect and any of its alternatives.

[0064] The technical effects of the third, fifth, seventh, eighth, and tenth aspects of this application can be understood in conjunction with the technical effects of the first aspect and any implementation thereof; and the technical effects of the fourth, sixth, ninth, and eleventh aspects of this application can be understood in conjunction with the technical effects of the second aspect and any implementation thereof. Attached Figure Description

[0065] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0066] Figure 1 A schematic diagram of the architecture of the cloud platform provided in the embodiments of this application;

[0067] Figure 2 A schematic diagram of the cloud system framework provided in the embodiments of this application;

[0068] Figure 3 A schematic flowchart of a data processing method provided in an embodiment of this application;

[0069] Figure 4 This is a schematic diagram of the message structure provided in the embodiments of this application;

[0070] Figure 5 This is a schematic diagram of the network node structure provided in an embodiment of this application;

[0071] Figure 6 A schematic diagram of the structure of the data processing apparatus provided in the embodiments of this application;

[0072] Figure 7 A schematic diagram of the structure of the data processing apparatus provided in the embodiments of this application;

[0073] Figure 8 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application;

[0074] Figure 9 This is a schematic diagram of a computing device cluster provided in an embodiment of this application;

[0075] Figure 10 This is another schematic diagram of the computing device cluster provided in the embodiments of this application. Detailed Implementation

[0076] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0077] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0078] The method of this application can be applied to cloud systems, which are sometimes also called cloud computing systems, cloud service systems, or cloud storage systems, and are often simply referred to as "cloud".

[0079] Resources in the "cloud" appear to users to be infinitely expandable, readily available, usable on demand, expandable at any time, and payable only for usage.

[0080] As a provider of fundamental cloud capabilities, a cloud resource pool platform, also known as a cloud platform or simply a cloud platform, is established. This platform is generally referred to as Infrastructure as a Service (IaaS). Various types of virtual resources are deployed within the resource pool for external customers to choose from. The cloud resource pool primarily includes: devices (virtualized machines containing operating systems), storage devices, and network devices.

[0081] Based on logical function, a Platform as a Service (PaaS) layer can be deployed on top of the IaaS layer, followed by a Software as a Service (SaaS) layer. Alternatively, SaaS can be deployed directly on top of IaaS. PaaS is the platform for running software, such as databases and web containers. SaaS comprises various types of business software, such as web portals and bulk SMS senders. Generally, SaaS and PaaS are upper layers compared to IaaS.

[0082] The deployment of the above services in the cloud can also be understood as serverless. Serverless does not mean that it does not need to rely on servers or other resources, but rather that developers no longer need to think too much about server issues and can focus more on product code. At the same time, computing resources begin to appear as services rather than as the concept of servers.

[0083] The data processing method provided in this application runs on a cloud system, and the architecture of this scenario can be found in [reference needed]. Figure 1 To understand, such as Figure 1 As shown in the embodiments of this application, the scenario includes a cloud and multiple terminal devices, and the cloud can communicate with the multiple terminal devices through a network. The cloud can be software or services of a cloud system, or software or services deployed on nodes in a network, such as edge nodes. The cloud can run on a standalone physical machine or on virtualized resources. Applications can run on the terminal devices, and users interact with the cloud using these applications. These applications can be applications provided based on container networks. Container networks rely on the underlying resources of the cloud system. A container network is a virtual network environment built using container technology, used to encapsulate and run applications and their dependencies to enable communication between containerized applications.

[0084] Terminal devices can send data processing requests to the cloud. The cloud can then generate data processing tasks based on these requests, process the data related to the tasks, and return the processing results to the terminal devices. The terminal devices can also display these results.

[0085] Figure 1 The nodes in the cloud include scheduling nodes and network nodes (or worker nodes). After receiving a data processing request from a terminal device, the cloud can have the scheduling node execute the corresponding data processing procedure. The scheduling node can also distribute the data processing request to one or more network nodes in the cloud system, and one or more network nodes can execute the corresponding data processing procedure.

[0086] The functionality of a scheduling node can be implemented through software or hardware.

[0087] As an example of a software functional unit, a scheduling node can include code running on a compute instance. A compute instance can include at least one of a physical host (computer device), a virtual machine, or a container. Furthermore, the aforementioned compute instance can be one or more. For example, a scheduling node can include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code can be distributed within the same region or in different regions. Further, the multiple hosts / virtual machines / containers used to run the code can be distributed within the same availability zone (AZ) or in different AZs, each AZ comprising one or more geographically proximate data centers. Typically, a region can include multiple AZs.

[0088] Similarly, multiple hosts / virtual machines / containers used to run this code can be distributed within the same Virtual Private Cloud (VPC) or across multiple VPCs. Typically, a VPC is set up within a single region. Communication between two VPCs within the same region, as well as between VPCs in different regions, requires a communication gateway to be set up within each VPC to enable interconnection between VPCs.

[0089] As an example of a hardware functional unit, a scheduling node can include at least one computer device, such as a server. Alternatively, a scheduling node can also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The aforementioned PLD can be implemented using a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), generic array logic (GAL), or any combination thereof.

[0090] The scheduling node comprises multiple computer devices that can be distributed in the same region or in different regions. Similarly, the scheduling node can be located within the same Availability Zone (AZ) or in different AZs. Likewise, the scheduling node can be located within the same Virtual Private Cloud (VPC) or multiple VPCs. These multiple computer devices can be any combination of server, ASIC, PLD, CPLD, FPGA, and GAL computer devices.

[0091] Network nodes can be physical machines, virtual machines (VMs), or containers, etc. A network node can include one or more central processing units (CPUs) and graphics processing units (GPUs). A network node can also be a CPU or a GPU, a bare metal server (BMS), or a switching device, such as a network virtualization edge (NVE) device at the top of the rack (TOR).

[0092] Terminal equipment, also known as user equipment (UE), mobile station (MS), or mobile terminal (MT), is a device that includes wireless communication capabilities (providing voice / data connectivity to users). Examples include handheld devices with wireless connectivity. Currently, some examples of terminal equipment include: mobile phones, tablets, laptops, PDAs, wireless routers, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, self-driving cars, vehicle-to-everything (V2X) networks, remote medical surgery, smart grids, transportation safety, smart cities, and smart homes. For example, wireless terminals in V2X networks can be in-vehicle equipment, vehicle-mounted equipment, in-vehicle modules, or vehicles themselves. In industrial control, wireless terminals can be robots, etc. For example, in autonomous driving, the wireless terminal can be a drone. This terminal device can run Android, iOS, Windows, or other operating systems.

[0093] for Figure 1 The data that needs to be processed in this application mainly utilizes the cloud system to process the probing tasks during network operation and maintenance. The probing task aims to simulate users sending messages to test the communication capabilities between two target objects. These two objects can be container network application instances on the same network node or on different nodes (i.e., across nodes).

[0094] The data processing method provided in this application is mainly used to solve the problem of incomplete test results in cross-node testing scenarios.

[0095] Currently, when performing probing tasks, a common practice is to inject simulated packets with differentiated services code point (DSCP) coloring at the beginning of the probing path; then filter and mirror the coloring packets at the network nodes of the path to the server-side analyzer; thus reconstructing the traffic path. Finally, the coloring packets are truncated at the end nodes of the path to prevent them from entering the actual business virtual machine.

[0096] Because the colored packet has been truncated at the network node, when the user's business is running in a container network environment, the traffic path in the probing results cannot point to the specific application instance, resulting in incomplete probing results.

[0097] Please see Figure 2 , Figure 2 This is a schematic diagram of a cloud system framework for handling cross-node dialing provided in an embodiment of this application. Figure 2 As shown, the cloud system includes a scheduling node and multiple network nodes. The scheduling node is responsible for scheduling multiple network nodes to perform probing tasks.

[0098] Based on logical functions, these multiple network nodes can be divided into the underlying network layer, the IaaS layer, and the container network layer.

[0099] The underlying network layer consists of a series of physical network devices, including routers, switches, fiber optic cables, etc. Figure 2 As shown, the underlying network layer may include at least one switch and at least one physical machine connected to each switch, and any two switches are connected through the network.

[0100] In this context, the switch can be a TOR NVE. TOR NVE uses encapsulated remote switch port analyzer (ERSPAN) technology, also known as packet mirroring, to copy packets from the source port (mirror port) and transmit them over the network to a remote destination port (observation port). During this process, the packet is encapsulated to allow it to traverse intermediate Layer 2 or Layer 3 networks to reach the remote monitoring device. At the destination port, the packet is decapsulated and sent to the network analysis device connected to that port for analysis, and the analysis results are reported to the scheduling node.

[0101] Specifically, after identifying the colored message provided in this application, TOR NVE mirrors it to the network analysis device and reports it to the scheduling node.

[0102] The IaaS layer includes one or more physical machines, which can be servers (HOSTs) used for virtualization or bare metal servers (BMSs). Figure 2 (Not shown in the drawing).

[0103] When the physical machine is the host, one or more virtual machines (VMs) can be deployed on the host, such as... Figure 2HOST 1 through HOST 4 and VM 1 through VM 6, each VM can act as a load balancer node in the container network. They are connected to a virtual bridge (such as a CNI-bridge) on the host machine via veth devices. Utilizing the network forwarding capabilities of the CNI (Container Network Interface), packets sent by the containers can be forwarded along the normal path.

[0104] When the physical machine is a BMS, the BMS directly acts as a load balancer node in the container network. When sending packets, the BMS transmits the data packets to the bare metal gateway (BMS Gateway, or BMSGW for short) through the physical connection, and then the BMSGW forwards the data packets to the switch.

[0105] The container network layer comprises one or more application instances, which can be considered the smallest deployment unit in the container network, carrying the workload of the container network and relying on the underlying resources of the cloud system. Each application instance typically contains one or more containers sharing a network namespace, and each network node can host one or more application instances. Figure 2 As shown, application instance A and application instance B are hosted on VM 1, and application instance C and application instance D are hosted on VM 6.

[0106] by Figure 2 For example, the container network shown is a Kubernetes (K8S) container network, and its application instance is a pod in K8S. The load balancing node of a pod can be a VM or a BMS.

[0107] In this application, the scheduling node is located on the load node of the application instance (e.g., Figure 2 A probing agent is deployed on the host and virtual machine (VM) in the system. When performing probing tasks, the agent sends simulated packets with colored tags to the target application instance (target pod) by simulating the source application instance (source pod) to analyze whether the traffic path is abnormal.

[0108] Please see Figure 3 , Figure 3 This is a flowchart illustrating a data processing method provided in an embodiment of this application. Based on Figure 2 The system framework shown illustrates that this data processing method is applied to a scheduling node deployed in a cloud system. This cloud system handles probing tasks and includes multiple network nodes. The method includes:

[0109] 301. Receive first information, the first information is used to indicate multiple network nodes transmitting the first message, the source address of the first message indicates a first application instance, the destination address of the first message indicates a second application instance, the first application instance is an application instance running on the first network node, the first network node is the head node among multiple network nodes, the second application instance is an application instance running on the second network node, and the second network node is the tail node among multiple network nodes.

[0110] Combination Figure 2 The system framework shown indicates that the first information indicates multiple network nodes as the traffic path of the first packet at the IaaS layer, while the first application instance and the second application instance reside at the container network layer. Upon receiving the first packet, these multiple network nodes report the packet's arrival information to the scheduling node. For example, they might send a mirror image of the packet to the analyzer. The scheduling node obtains the mirror image packets from each network node between the head node and the tail node, and its path analyzer determines the topology of the traffic path based on the reported timing.

[0111] A test request can be initiated by a cloud user to the cloud system based on factors such as version updates or configuration changes, or it can be an operation and maintenance task created by the cloud system based on factors such as periodic maintenance checks or network path optimization. Test requests primarily analyze whether the traffic path between a source object and a target object is abnormal by simulating the sending of simulated packets. In this embodiment, the first application instance and the second application instance are the source object and the target object of the test request, respectively.

[0112] Understandably, the first message is a simulated message used to perform the probing task. Although the source and destination addresses of the first message point to the source object (first application instance) and target object (second application instance) in the probing task, respectively, this is only used to simulate the path of a real message, not actual communication. During actual transmission, after receiving the first message, the virtual gateway connected to the second application instance will report the message arrival information to the scheduling node to complete the data collection for the probing task. After this, the virtual gateway will discard the first message and will not forward it to the second application instance to avoid interfering with the normal business of the second application instance.

[0113] by Figure 2 Taking the scenario shown as an example, the source object can be... Figure 2 In this example, application instance A is the target application instance D, the first network node is VM 1, and the second network node is VM 6. The probing task is used to detect the traffic path from application instance A to application instance D.

[0114] In one possible implementation, before the scheduling node receives the first information, the method further includes: sending a dial-up request to a first network node carrying the first application instance, the dial-up request being used to instruct the first network node to send the first message.

[0115] For example, a dial-up test request includes information such as the source IP address, source port, destination port, and transport layer protocol.

[0116] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of the first message. The first message adopts a layered encapsulation architecture, consisting of a first message header, a second message header, and a message data payload. The second message header is the next level header after the first message header. Different message headers can correspond to different protocol types, with the first message header being the outer protocol header and the second message header being the inner protocol header. For example, the first message header could correspond to the Virtual Extensible Local Area Network (VXLAN) protocol, and the second message header could correspond to the Transmission Control Protocol (TCP). The first message header contains a first coloring flag. When a network node receives the message and recognizes the first coloring flag, it will report the arrival of the first message to the scheduling node. The second message header contains a second coloring flag, used to instruct the second application instance to report whether the first message has arrived to the scheduling node.

[0117] It should be noted that reporting whether the first message has arrived can also be understood as reporting whether the content of the message's data payload has arrived. When the first message arrives at the second network node, the outer header of the first message is stripped away, leaving only the second header and the message data payload. At this point, the second application instance reports the arrival status of the message data payload through the inner coloring mark.

[0118] For example, coloring can be implemented by defining the protocol-encoded value of the DSCP bit in the message header. For instance, a DSCP value of 60 to 63 indicates that the message has been tagged.

[0119] Specifically, after receiving the test request, the agent deployed in the first network node will simulate the first application instance to send colored packets.

[0120] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of the first network node.

[0121] Taking Kubernetes (K8S) container networks as an example, K8S load balancing nodes fall into two categories:

[0122] First, the K8S load balancing nodes are IaaS layer virtual machine nodes (VM nodes).

[0123] Load node is Figure 5 The virtual machine (VM) is running on the virtualization server HOST connected to the TOR NVE on the right. The HOST communicates with the TOR NVE by simulating the function of a physical network card through the virtual network interface eth0.

[0124] In one possible implementation, the agent component installed on the VM node of the K8S load will construct a packet with a DSCP coloring mark when it receives a probe task, and inject the packet into the virtual network interface veth device on the host machine connected to the source pod. The network forwarding capability of its CNI virtual bridge (CNI-bridge) will then forward the packet out through the path of a regular packet.

[0125] Specifically, the agent in the VM injects packets (creates colored packets) into the network interface card (NIC) device of the first application instance. The injected packet includes a second header carrying the second colored tag and a packet data payload. When the packet arrives at the host's VTAP device, the agent in the host further encapsulates the packet with a first header, carrying the first colored tag in the first header. When the packet passes through the tunnel (tunnel) device of the first network node, it is encapsulated into a VXLAN packet, i.e., the aforementioned first packet.

[0126] The VM communicates with the host's virtual network interface card (vtap) via eth0, and multiple VMs can be deployed on the same host. Figure 5 (Not shown in the diagram), multiple VMs can communicate with each other through a virtual bridge (internal bridge, Br-int).

[0127] Second, the K8S load nodes are bare metal nodes (BMS nodes) at the IaaS layer.

[0128] In this scenario, the load balancer in Kubernetes is the bare metal server (BMS), not a virtual machine on a compute node. The difference lies in the physical connection between the BMS's network interface card (NIC) and the bare metal gateway (BMSGW), which is not a virtual network (vtap) or veth pair device. However, the principle of packet coloring is the same as in the virtual machine scenario: the agent injects colored packets into the veth device connected to the pod on the BMS, forwards the packets to the BMSGW via CNI, and then the tun device on the BMSGW encapsulates them into VXLAN packets for further forwarding.

[0129] Specifically, the network interface card (NIC) device of the first application instance is injected with packets through the agent in the BMS. The injected packet includes a second packet header carrying the second coloring mark and a packet data payload. When the packet arrives at the VTAP device of the BMSGW, the agent in the BMSGW will further encapsulate the packet with a first packet header, carrying the first coloring mark in the first packet header. When the packet passes through the tunnel (tunnel) device of the first network node, it will be encapsulated into a VXLAN packet, i.e., the aforementioned first packet.

[0130] BMS communicates with the virtual network interface card (vtap) of BMSGW via eth0, and BMSGW connects the container to the external network through network bridging (gw-bridge) technology.

[0131] In one possible implementation, container networking uses tunneling for communication. In tunneling mode, packets originating from a pod require initial tunnel encapsulation. If, at this point, the colored packet is still injected into the network interface card (NIC) connected to the source pod, the resulting packet received by the Kubernetes load balancer will be encapsulated into a VXLAN packet by a tunnel device after passing through the CNI-Bridge device. At this point, the colored packet injected by the agent has already been encapsulated within this inner VXLAN packet. When this packet reaches the compute node itself or the bare metal gateway's tunnel NIC, it will be encapsulated into a VXLAN packet again and forwarded. At this point, the inner VXLAN packet is still a VXLAN packet; that is, the packet sent by the network node has a three-layer header, and the colored marker is located in the first and third layer headers.

[0132] To address this issue, when the container network is detected to be in tunnel mode, the sent colored packets will automatically switch to the following packet injection mode:

[0133] ①The agent simulates a colored message, which will construct a VXLAN message with both the inner and outer layers colored.

[0134] ② The injection location is switched to the tun device on the Kubernetes worker node, instead of the veth device, which is directly connected to the pod. The Kubernetes worker node is the network node that hosts the load balancer for Kubernetes, i.e., through... Figure 5 The agent in the HOST performs packet injection on the tun device, or the agent in the BMSGW performs packet injection on the tun device (corresponding to...). Figure 5 (The dashed line in the middle).

[0135] 302. Receive second information, which indicates whether the first message has arrived at the second application instance.

[0136] Combination Figure 2 The system framework shown indicates that the second piece of information indicates the traffic path of the first message in the container network layer. For example, "Application Instance A -- Application Instance D".

[0137] Specifically, when the first packet arrives at the second network node, the outer first packet header is stripped off, and the inner original packet (i.e., the second packet header and packet data payload) is extracted and submitted to the virtual network interface card (Veth) device corresponding to the second application instance. Upon receiving the original packet with the stained label, the Veth device of the second application instance reports the packet's arrival information to the scheduling node. Furthermore, it discards the original packet to prevent it from entering the second application instance's service environment.

[0138] 303. Determine the dialing test results based on the first information and the second information. The dialing test results include the first application instance, multiple network nodes, and the second application instance.

[0139] Based on the first and second information, the scheduling node determines the test result of the probe task, namely the traffic path of the first packet in the IaaS layer and the container network layer. By reconstructing and concatenating the container network path with the basic network path, complete path information is obtained.

[0140] In one possible implementation, the test results may also include information about the faulty node. The faulty node refers to the network node where the first packet failed to reach the next hop. When the network device in the traffic path or the CNI-Bridge device corresponding to the second application instance fails to report the arrival information of the first packet, it can be inferred that an anomaly occurred during the transmission of the first packet at the previous hop network node.

[0141] For example, links before a faulty node can be represented by a bright color or a solid line, while links after a faulty node can be represented by a gray or dashed line.

[0142] Using the above method, the scheduling node instructs the network node carrying the source object (first application instance) in the probing task to send a message with inner and outer coloring tags. Upon receiving the message, the network node and the target application instance report the message arrival information, enabling the scheduling node to reconstruct and connect the paths between the container network and the underlying network, thereby obtaining the complete message traffic path and improving the cloud system's network connectivity diagnostic capabilities and link visualization capabilities. Furthermore, by instructing agents deployed on network devices or load nodes to generate simulated coloring messages, various scenarios in container networks can be addressed, such as tunnel mode or routing mode.

[0143] The methods provided in the embodiments of this application have been described in detail above. Next, the device for performing the above methods provided in the embodiments of this application will be described.

[0144] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a data processing device 600 provided in an embodiment of this application. Figure 6 As shown, this device is applied to a scheduling node, which is deployed in a cloud system. The cloud system is used to process probing tasks. The device includes:

[0145] The receiving module 601 is used to receive first information, which is used to indicate multiple network nodes transmitting the first message. The source address of the first message indicates a first application instance, and the destination address of the first message indicates a second application instance. The first application instance is an application instance running on the first network node, and the first network node is the head node among multiple network nodes. The second application instance is an application instance running on the second network node, and the second network node is the tail node among multiple network nodes.

[0146] The receiving module 601 is also used to receive second information, which is used to indicate whether the first message has arrived at the second application instance;

[0147] The processing module 602 is used to determine the dialing test result based on the first information and the second information. The dialing test result includes the first application instance, multiple network nodes, and the second application instance.

[0148] In one possible implementation, the first message includes a first message header and a second message header, the second message header being the next level header of the first message header. The first message header includes a first coloring mark, and the second message header includes a second coloring mark. The first coloring mark is used to instruct multiple network nodes to report to the scheduling node whether the first message has arrived, and the second coloring mark is used to instruct a second application instance to report to the scheduling node whether the first message has arrived.

[0149] In one possible implementation, the test results also include faulty nodes, which are the network nodes where the first message did not reach the next hop.

[0150] In one possible implementation, the device further includes:

[0151] The sending module is used to send a test request to the first network node, which instructs the first network node to send a first message.

[0152] In one possible implementation, the first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes a second coloring mark.

[0153] In one possible implementation, the first message is created at the network interface card (NIC) device of the first network node.

[0154] In one possible implementation, the multiple network nodes include one or more of a virtualization server, a bare metal server, and a switch.

[0155] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of a data processing apparatus 700 provided in an embodiment of this application. Figure 7 As shown, the device is applied to a first network node, which is deployed in a cloud system. The cloud system is used to process probing tasks and also includes a scheduling node. The device includes:

[0156] The receiving module 701 is used to receive a dial-up request. The dial-up request is used to instruct a first network node to send a first message. The source address of the first message indicates a first application instance, and the destination address of the first message indicates a second application instance. The first message includes a first message header and a second message header. The second message header is the next level header of the first message header. The first message header includes a first coloring mark, and the second message header includes a second coloring mark. The first coloring mark is used to instruct multiple network nodes to report to the scheduling node whether the first message has arrived. The second coloring mark is used to instruct a second application instance to report to the scheduling node whether the first message has arrived. The multiple network nodes are network nodes used to transmit the first message, and the first network node is contained in the multiple network nodes.

[0157] The sending module 702 is used to send the first message.

[0158] In one possible implementation, the first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes a second coloring mark.

[0159] In one possible implementation, the first message is created at the network interface card (NIC) device of the first network node.

[0160] In one possible implementation, the multiple network nodes include one or more of a virtualization server, a bare metal server, and a switch.

[0161] This application also provides a computing device 100. For example... Figure 8 As shown, the computing device 100 includes a bus 102, a processor 104, a memory 106, and a communication interface 108. The processor 104, the memory 106, and the communication interface 108 communicate with each other via the bus 102. The computing device 100 can be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computing device 100.

[0162] Bus 102 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 8 The bus 102 may be represented by a single line, but this does not mean that there is only one bus or one type of bus. The bus 102 may include a path for transmitting information between various components of the computing device 100 (e.g., memory 106, processor 104, communication interface 108).

[0163] The processor 104 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0164] Memory 106 may include volatile memory, such as random access memory (RAM). Processor 104 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0165] The memory 106 stores executable program code, and the processor 104 executes the executable program code to implement the functions of the aforementioned receiving module and processing module, thereby realizing the data processing method. That is, the memory 106 stores instructions for executing the data processing method.

[0166] Alternatively, the memory 106 stores executable code, which the processor 104 executes to implement the functions of the aforementioned data processing device, thereby implementing the data processing method. That is, the memory 106 stores instructions for executing the data processing method.

[0167] The communication interface 108 uses transceiver modules such as, but not limited to, network interface cards and transceivers to enable communication between the computing device 100 and other devices or communication networks.

[0168] It should be understood that the computing device 100 provided according to this application may correspond to the data processing device 600 in this application, and may correspond to the execution of the embodiments according to the present invention. Figure 3 The scheduling node in the method shown, and the above and other operations and / or functions of each module of the computing device 100 are respectively implemented for the purpose of... Figure 3 For the sake of brevity, the corresponding processes of each method in the code will not be elaborated here.

[0169] This application also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0170] like Figure 9 As shown, the computing device cluster includes at least one computing device 100. The memory 106 of one or more computing devices 100 in the computing device cluster may store the same instructions for executing data processing methods.

[0171] In some possible implementations, the memory 106 of one or more computing devices 100 in the computing device cluster may also store partial instructions for executing data processing methods. In other words, a combination of one or more computing devices 100 can jointly execute instructions for executing data processing methods.

[0172] It should be noted that the memories 106 in different computing devices 100 within the computing device cluster can store different instructions, each used to execute a portion of the functions of the data processing device. That is, the instructions stored in the memories 106 of different computing devices 100 can implement the functions of one or more devices in the receiving module and processing module.

[0173] In some possible implementations, one or more computing devices in a computing device cluster can be connected via a network. This network can be a wide area network (WAN) or a local area network (LAN), etc. Figure 10 One possible implementation is shown. For example... Figure 10 As shown, two computing devices 100A and 100B are connected via a network. Specifically, they are connected to the network through communication interfaces in each computing device. In this possible implementation, the memory 106 in computing device 100A stores instructions for performing the functions of the receiving module. Simultaneously, the memory 106 in computing device 100B stores instructions for performing the functions of the processing module.

[0174] It should be understood that Figure 10The functions of the computing device 100A shown can also be performed by multiple computing devices 100. Similarly, the functions of the computing device 100B can also be performed by multiple computing devices 100.

[0175] This application also provides a computer program product containing instructions. The computer program product may be a software or program product containing instructions, capable of running on a computing device or stored on any usable medium. When the computer program product is run on at least one computing device, it causes the at least one computing device to perform a data processing method.

[0176] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium capable of being stored by a computing device, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to perform a data processing method.

[0177] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data processing method, characterized in that, The method is applied to a scheduling node, which is deployed in a cloud system, and the cloud system is used to process probing tasks. The method includes: Receive first information, the first information is used to indicate multiple network nodes transmitting the first message, the source address of the first message indicates a first application instance, the destination address of the first message indicates a second application instance, the first application instance is an application instance running on the first network node, the first network node is the head node among the multiple network nodes, the second application instance is an application instance running on the second network node, and the second network node is the tail node among the multiple network nodes. Receive second information, which indicates whether the first message has reached the second application instance; The dialing test result is determined based on the first information and the second information, and the dialing test result includes the first application instance, the plurality of network nodes and the second application instance.

2. The method according to claim 1, characterized in that, The first message includes a first message header and a second message header, the second message header being the next level header of the first message header. The first message header includes a first coloring mark, and the second message header includes a second coloring mark. The first coloring mark is used to instruct the plurality of network nodes to report to the scheduling node whether the first message has arrived, and the second coloring mark is used to instruct the second application instance to report to the scheduling node whether the first message has arrived.

3. The method according to claim 1 or 2, characterized in that, The test results also include faulty nodes, which are the network nodes where the first message did not reach the next hop.

4. The method according to any one of claims 1-3, characterized in that, Before receiving the first information, the method further includes: A test request is sent to the first network node, the test request being used to instruct the first network node to send the first message.

5. The method according to claim 4, characterized in that, The first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes the second coloring mark.

6. The method according to claim 4, characterized in that, The first message is created at the network interface card (NIC) device of the first network node.

7. The method according to claims 1-6, characterized in that, The plurality of network nodes includes one or more of virtualization servers, bare metal servers, and switches.

8. A data processing method, characterized in that, The method is applied to a first network node, which is deployed in a cloud system. The cloud system is used to process probing tasks and further includes a scheduling node. The method includes: A test request is received, the test request being used to instruct the first network node to send a first message, the source address of the first message indicating a first application instance, the destination address of the first message indicating a second application instance, the first message including a first message header and a second message header, the second message header being a next-level message header of the first message header, the first message header including a first coloring mark, the second message header including a second coloring mark, the first coloring mark being used to instruct multiple network nodes to report to the scheduling node whether the first message has arrived, the second coloring mark being used to instruct the second application instance to report to the scheduling node whether the first message has arrived, the multiple network nodes being network nodes used to transmit the first message, and the first network node being included in the multiple network nodes; Send the first message.

9. The method according to claim 8, characterized in that, The first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes the second coloring mark.

10. The method according to claim 8, characterized in that, The first message is created at the network interface card (NIC) device of the first network node.

11. The method according to claims 8-10, characterized in that, The plurality of network nodes includes one or more of virtualization servers, bare metal servers, and switches.

12. A data processing apparatus, characterized in that, The device is applied to a scheduling node, the scheduling node is deployed in a cloud system, and the cloud system is used to process probing tasks. The device includes: A receiving module is configured to receive first information, the first information being used to indicate multiple network nodes transmitting a first message, the source address of the first message indicating a first application instance, the destination address of the first message indicating a second application instance, the first application instance being an application instance running on a first network node, the first network node being the head node among the multiple network nodes, the second application instance being an application instance running on a second network node, and the second network node being the tail node among the multiple network nodes. The receiving module is further configured to receive second information, the second information being used to indicate whether the first message has reached the second application instance; The processing module is used to determine the dialing test result based on the first information and the second information, wherein the dialing test result includes the first application instance, the plurality of network nodes and the second application instance.

13. The apparatus according to claim 12, characterized in that, The first message includes a first message header and a second message header, the second message header being the next level header of the first message header. The first message header includes a first coloring mark, and the second message header includes a second coloring mark. The first coloring mark is used to instruct the plurality of network nodes to report to the scheduling node whether the first message has arrived, and the second coloring mark is used to instruct the second application instance to report to the scheduling node whether the first message has arrived.

14. The apparatus according to claim 12 or 13, characterized in that, The test results also include faulty nodes, which are the network nodes where the first message did not reach the next hop.

15. The apparatus according to any one of claims 12-14, characterized in that, The device further includes: The sending module is used to send a test request to the first network node, the test request being used to instruct the first network node to send the first message.

16. The apparatus according to claim 15, characterized in that, The first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes the second coloring mark.

17. The apparatus according to claim 15, characterized in that, The first message is created at the network interface card (NIC) device of the first network node.

18. The apparatus according to claims 12-17, characterized in that, The plurality of network nodes includes one or more of virtualization servers, bare metal servers, and switches.

19. A data processing apparatus, characterized in that, The device is applied to a first network node, which is deployed in a cloud system. The cloud system is used to process probing tasks, and the cloud system also includes a scheduling node. The device comprises: A receiving module is configured to receive a test request, the test request being used to instruct the first network node to send a first message, the source address of the first message indicating a first application instance, the destination address of the first message indicating a second application instance, the first message including a first message header and a second message header, the second message header being a next-level message header of the first message header, the first message header including a first coloring mark, the second message header including a second coloring mark, the first coloring mark being used to instruct multiple network nodes to report to the scheduling node whether the first message has arrived, the second coloring mark being used to instruct the second application instance to report to the scheduling node whether the first message has arrived, the multiple network nodes being network nodes used to transmit the first message, and the first network node being included in the multiple network nodes; The sending module is used to send the first message.

20. The apparatus according to claim 19, characterized in that, The first message is obtained by encapsulating the second message through the network interface card (NIC) device of the first network node. The second message is created at the NIC device of the first application instance, and the header of the second message includes the second coloring mark.

21. The apparatus according to claim 19, characterized in that, The first message is created at the network interface card (NIC) device of the first network node.

22. The apparatus according to claims 19-21, characterized in that, The plurality of network nodes includes one or more of virtualization servers, bare metal servers, and switches.

23. A data processing apparatus, characterized in that, Includes modules or units for performing the method as described in any one of claims 1 to 11.

24. A computing device cluster, characterized in that, It includes at least one computing device, each computing device including a processor and memory; The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device to cause the cluster of computing devices to perform the method as claimed in claims 1-7, or to perform the method as claimed in claims 8-11.

25. A computer program product containing instructions, characterized in that, When the instruction is executed by the computing device cluster, the computing device cluster performs the method as described in any one of claims 1-7, or performs the method as described in claims 8-11.

26. A computer-readable storage medium, characterized in that, Includes computer program instructions, which, when executed by a cluster of computing devices, perform the method as described in any one of claims 1-7, or the method as described in claims 8-11.

Images