Scheduling processing method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a scheduling processing method and device, computer equipment, a computer readable storage medium and a computer program product, and relates to the technical field of cloud computing. According to the invention, the problem of pressure measurement flow concentration can be avoided to a certain extent, so that the network request flow condition in reality can be better simulated. The method comprises the steps that a node recommendation value of each node in a cluster is obtained for each scheduling unit copy of a pressure measurement task, the node recommendation value is determined based on the deployment state of a node pool where the node is located for the pressure measurement task, and a target node of the scheduling unit copy is determined according to the node recommendation value of each node.

Description

Technical Field

[0001] The present application relates to the field of cloud computing technology, and in particular to a scheduling processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] Kubernetes (often referred to as K8s) is an open source container orchestration platform.

[0003] In a Kubernetes cluster, the component responsible for scheduling nodes for scheduling unit Pods can be called a scheduler (kube-scheduler). The scheduler has multiple stages when scheduling scheduling unit Pods, such as sorting, filtering, and so on. After completing all stages, the scheduler can schedule the scheduling unit Pod to run on the appropriate node.

[0004] Performance Testing Service (PTS) can be used to verify the stress resistance of the service by simulating network requests.

[0005] Among them, the cluster used by the performance testing service is a cloud-edge architecture cluster, which includes a central master node and edge worker nodes deployed in various locations.

[0006] In current technology, when the performance testing service starts a stress test task, the Kubernetes cluster will select the stress test node according to the preset scheduling algorithm. However, the result of this node scheduling often causes the stress test traffic to be concentrated in the same region, which is inconsistent with the actual traffic distribution and is difficult to be used to accurately simulate network request traffic. Summary of the invention

[0007] Based on this, it is necessary to provide a scheduling processing method, apparatus, computer equipment, computer-readable storage medium and computer program product to address the above technical issues.

[0008] In a first aspect, the present application provides a scheduling processing method, comprising:

[0009] For each scheduling unit copy of the stress testing task, obtain a node recommendation value of each node in the cluster; the node recommendation value is determined based on the deployment status of the stress testing task in the node pool where the node is located;

[0010] The target node of the scheduling unit copy is determined according to the node recommendation value of each of the nodes.

[0011] In one of the embodiments, obtaining the node recommended value of each node in the cluster includes: if the node recommended value of the node is not cached, obtaining the preliminary node recommended value of each node in the node pool where the node is located; the preliminary node recommended value is obtained by evaluating the node according to a preset recommended value evaluation model; according to the preliminary node recommended value of each node in the node pool and the deployment status of the node pool for the stress testing task, determining and caching the node recommended value of each node in the node pool; if the node recommended value of the node is cached, obtaining the cached node recommended value of the node.

[0012] In one of the embodiments, the node recommended value of each node in the node pool is determined and cached based on the node preliminary recommended value of each node in the node pool and the deployment status of the node pool for the stress testing task, including: if the deployment status of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task has been deployed, then the node recommended value of each node in the node pool is set to a preset value; if the deployment status of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task has not been deployed, then based on the node preliminary recommended value of each node in the node pool and the corresponding weight value, the node recommended value of each node in the node pool is obtained and cached; wherein the weight value is related to the size of the node preliminary recommended value of each node in the node pool.

[0013] In one of the embodiments, before obtaining and caching the node recommendation value of each node in the node pool based on the node preliminary recommendation value and the corresponding weight value of each node in the node pool, it also includes: based on the node preliminary recommended values ​​of each node in the node pool, determining the weight value corresponding to the largest node preliminary recommended value as a first weight value, and determining the weight values ​​corresponding to other node preliminary recommended values ​​as second weight values; wherein the first weight value is greater than the second weight value.

[0014] In one of the embodiments, after determining the target node of the scheduling unit copy according to the node recommendation value of each of the nodes, the method further includes: obtaining load information of each node in the cluster; the node includes the target node; if the load information of the target node meets the node replacement condition, selecting a replacement node for the target node based on the node pool where the target node is located; and scheduling the scheduling unit copy to the replacement node.

[0015] In one of the embodiments, the selecting a replacement node for the target node based on the node pool where the target node is located includes: if there is a first available node that meets the load condition in the node pool where the target node is located, obtaining the replacement node based on the first available node; if there is no first available node that meets the load condition in the node pool where the target node is located, determining a second available node that meets the load condition in other node pools, and obtaining the replacement node based on the second available node.

[0016] In a second aspect, the present application further provides a scheduling processing device, including:

[0017] A recommended value acquisition module, used to obtain a node recommended value of each node in the cluster for each scheduling unit copy of the stress testing task; the node recommended value is determined based on the deployment status of the stress testing task in the node pool where the node is located;

[0018] The node determination module is used to determine the target node of the scheduling unit copy according to the node recommendation value of each node.

[0019] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0020] For each scheduling unit copy of the stress testing task, the node recommendation value of each node in the cluster is obtained; the node recommendation value is determined based on the deployment status of the stress testing task in the node pool where the node is located; and the target node of the scheduling unit copy is determined according to the node recommendation value of each node.

[0021] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0022] For each scheduling unit copy of the stress testing task, the node recommendation value of each node in the cluster is obtained; the node recommendation value is determined based on the deployment status of the stress testing task in the node pool where the node is located; and the target node of the scheduling unit copy is determined according to the node recommendation value of each node.

[0023] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0024] For each scheduling unit copy of the stress testing task, the node recommendation value of each node in the cluster is obtained; the node recommendation value is determined based on the deployment status of the stress testing task in the node pool where the node is located; and the target node of the scheduling unit copy is determined according to the node recommendation value of each node.

[0025] The above-mentioned scheduling processing method, device, computer equipment, computer-readable storage medium and computer program product obtain the node recommendation value of each node in the cluster for each scheduling unit copy of the stress testing task. The node recommendation value is determined based on the deployment status of the stress testing task by the node pool where the node is located, and the target node of the scheduling unit copy is determined according to the node recommendation value of each node. Therefore, the node pool where the node is located can be considered in the determination of the node recommendation value of the node. The nodes in the node pool are generally deployed in the same computer room. The node recommendation value is determined in combination with the deployment status of the stress testing task by the node pool where the node is located. It can avoid concentrating the target nodes of each scheduling unit copy of the stress testing task in the same node pool. Therefore, the scheduling unit copies of the stress testing task can be dispersed as much as possible to different regions, avoiding the problem of stress testing traffic concentration to a certain extent, so as to better simulate the network request traffic situation in reality. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 An application environment diagram of a scheduling processing method in an embodiment;

[0028] Figure 2 A schematic diagram of a flow chart of a scheduling processing method in one embodiment;

[0029] Figure 3 A schematic flow chart of a scheduling replacement process step in one embodiment;

[0030] Figure 4 is a structural block diagram of a scheduling processing device in one embodiment;

[0031] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0033] Some of the terms involved in this application:

[0034] PTS: Performance Testing Service, which verifies the service's stress resistance by simulating network requests.

[0035] Resource Pool: A unit consisting of multiple nodes in the same computer room.

[0036] The scheduling processing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be integrated on the server, or it can be placed on the cloud or other network servers. Among them, the terminal can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0037] In an exemplary embodiment, Figure 2 As shown, a scheduling processing method is provided, which can be applied to Figure 1 The method may include the following steps:

[0038] Step S201, for each scheduling unit copy of the stress testing task, obtain the node recommendation value of each node in the cluster.

[0039] The node recommendation value is determined based on the deployment status of the stress test task by the node pool where the node is located. The recommendation value can be a score determined for each node in the cluster based on the deployment status of the stress test task by the node pool where each node is located.

[0040] In this step, the user initiates a stress test task, the performance testing service calculates the number of scheduling unit Pod copies required, generates a deployment file and transmits it to the cluster (such as a Kubernetes cluster). The cluster can perform node scheduling for each scheduling unit copy, and can determine its node recommendation value based on the deployment status of the stress test task based on the node pool where the node is located. Among them, the deployment status of the stress test task can be a scheduling unit copy that has deployed the stress test task, or a scheduling unit copy that has not deployed the stress test task. As an implementation method, regional factors can be considered to increase the node recommendation value of the node where the scheduling unit copy of the stress test task is not deployed, and reduce the node recommendation value of the node where the scheduling unit copy of the stress test task is deployed, so as to avoid scheduling all the scheduling unit copies of the stress test task into the same node pool.

[0041] Step S202: Determine the target node of the scheduling unit copy according to the node recommendation value of each node.

[0042] In this step, for each scheduling unit replica, the node with the highest node recommendation value can be selected as the target node of the scheduling unit replica according to the node recommendation values ​​of each node in the cluster. Similarly, node scheduling can be performed on each scheduling unit replica of the stress testing task to complete the scheduling of all scheduling unit replicas of the stress testing task.

[0043] The scheduling processing method of this embodiment obtains the node recommendation value of each node in the cluster for each scheduling unit copy of the stress testing task. The node recommendation value is determined based on the deployment status of the stress testing task by the node pool where the node is located, and the target node of the scheduling unit copy is determined according to the node recommendation value of each node. Therefore, the node pool where the node is located can be considered in the determination of the node recommendation value of the node. The nodes in the node pool are generally deployed in the same computer room. The node recommendation value is determined in combination with the deployment status of the stress testing task by the node pool where the node is located. This can avoid concentrating the target nodes of each scheduling unit copy of the stress testing task in the same node pool. Therefore, the scheduling unit copies of the stress testing task can be dispersed as much as possible to different regions, avoiding the problem of stress testing traffic concentration to a certain extent, so as to better simulate the network request traffic situation in reality.

[0044] In an exemplary embodiment, obtaining the node recommendation value of each node in the cluster in step S201 may include:

[0045] If the node recommended value of the node is not cached, then the node preliminary recommended value of each node in the node pool where the node is located is obtained; the node preliminary recommended value is obtained by evaluating the node according to a preset recommended value evaluation model; based on the node preliminary recommended value of each node in the node pool and the deployment status of the node pool for the stress testing task, the node recommended value of each node in the node pool is determined and cached; if the node recommended value of the node is cached, the node recommended value of the cached node is obtained.

[0046] In this embodiment, for the stress testing task, the node recommended value of the calculated node can be cached. Thus, when it is necessary to obtain the node recommended value of each node in the cluster, it can be determined whether the node recommended value of the node is cached. If the node recommended value of the node is cached, the node recommended value of the cached node can be directly obtained without repeated calculation. If the node recommended value of the node is not cached, the node preliminary recommended value of all nodes in the node pool where the node is located can be obtained; the node preliminary recommended value can be obtained by evaluating the node using the default scheduling algorithm in the cluster (such as the minimum load algorithm, etc.) as the preset recommended value evaluation model. Thus, the node recommended values ​​of all nodes in the node pool can be determined based on the node preliminary recommended value of each node in the node pool and the deployment status of the node pool for the stress testing task, and the node recommended values ​​of all nodes in the node pool can be cached.

[0047] In an exemplary embodiment, further, the above-mentioned determining and caching the node recommended value of each node in the node pool according to the node preliminary recommended value of each node in the node pool and the deployment status of the node pool for the stress testing task may include:

[0048] If the deployment status of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task has been deployed, the node recommendation value of each node in the node pool is set to the preset value; if the deployment status of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task has not been deployed, the node recommendation value of each node in the node pool is obtained and cached based on the node preliminary recommended value of each node in the node pool and the corresponding weight value; wherein the weight value is related to the size of the node preliminary recommended value of each node in the node pool.

[0049] In this embodiment, if the deployment state of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task has been deployed, the node recommendation value of each node in the node pool can be set to a preset value such as 0 to reduce the node recommendation value of each node in the node pool, and the node recommendation value of each node in the node pool can be cached. If the deployment state of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task has not been deployed, a weight value corresponding to the size of the node preliminary recommended value calculated by the default scheduling algorithm in the cluster (such as the minimum load algorithm, etc.) can be assigned to it, and the node recommendation value of each node in the node pool can be obtained by multiplying the preliminary recommended value of each node with its weight value, and then the node recommendation value of each node in the node pool can be cached.

[0050] In an exemplary embodiment, before obtaining and caching the node recommendation value of each node in the node pool according to the node preliminary recommendation value and the corresponding weight value of each node in the node pool, the following may also be included:

[0051] According to the node preliminary recommended values ​​of each node in the node pool, the weight value corresponding to the largest node preliminary recommended value is determined as the first weight value, and the weight values ​​corresponding to the other node preliminary recommended values ​​are determined as the second weight values; wherein the first weight value is greater than the second weight value.

[0052] In this embodiment, the node preliminary recommended values ​​of each node in the node pool can be sorted from large to small, and the weight value corresponding to the largest node preliminary recommended value is determined as the first weight value w1, and the weight values ​​corresponding to the other node preliminary recommended values ​​are all determined as the second weight value w2. Among them, the first weight value w1 is greater than the second weight value w2, and the first weight value w1 and the second weight value w2 can be set between 0 and 1. This can facilitate the selection of a better node in the node pool of the scheduling unit replica where the stress testing task is not deployed as the target node.

[0053] In an exemplary embodiment, Figure 3 As shown, after determining the target node of the scheduling unit replica according to the node recommendation value of each node in step S202, the following steps may also be included:

[0054] Step S301, obtaining load information of each node in the cluster, wherein the node may include a target node.

[0055] In this step, the load information of each node in the cluster including the target node may be obtained periodically.

[0056] Step S302: If the load information of the target node meets the node replacement condition, a replacement node for the target node is selected based on the node pool where the target node is located.

[0057] Among them, the load information of each node in the cluster can be obtained regularly so that when the load information of the target node used by the scheduling unit copy of a certain stress testing task meets the node replacement condition, the target node is replaced and the selection of the optimal target node is adjusted in time. In this step, the node replacement condition may include conditions such as the node load threshold, which can be used to evaluate whether the target node currently has a high load based on the load information. If it is satisfied, a replacement node for the target node can be selected based on the node pool where the target node is located, that is, another node can be selected in the node pool as the replacement node.

[0058] Step S303: Schedule the scheduling unit copy to the replacement node.

[0059] In this step, after the replacement node is determined, the scheduling unit replica can be scheduled to the replacement node.

[0060] In an exemplary embodiment, selecting a replacement node for the target node based on the node pool where the target node is located in step S302 may include:

[0061] If there is a first available node that meets the load conditions in the node pool where the target node is located, a replacement node is obtained based on the first available node; if there is no first available node that meets the load conditions in the node pool where the target node is located, a second available node that meets the load conditions is determined in other node pools, and a replacement node is obtained based on the second available node.

[0062] In this embodiment, a replacement node can be first searched in the node pool where the target node is located, and when it cannot be found, a replacement node can be searched in other node pools. Among them, all other nodes in the node pool where the target node is located can be traversed, all nodes whose load exceeds the load threshold can be filtered, and the node with the lowest load can be selected as the first available node that meets the load condition. If the first available node exists in the node pool where the target node is located, the first available node can be determined as the replacement node. If the first available node does not exist in the node pool where the target node is located, another node pool can be randomly selected from the cluster, and all nodes whose load exceeds the load threshold in the other node pool can be filtered and the node with the lowest load can be selected as the second available node that meets the load condition, and the second available node can be determined as the replacement node. In an embodiment, a high-load target node can be expelled and the scheduling unit copy of the stress measurement task can be scheduled from the target node to the newly selected replacement node by specifying the node. In some embodiments, if a replacement node is not found, node switching may not be performed.

[0063] In general, the scheduling processing method of the present application takes into account the regional distribution of stress testing traffic. When performing node scheduling, node recommendation values ​​can be formed based on regional distribution, which can avoid the concentration of stress testing traffic to a certain extent, thereby better simulating real network requests. At the same time, the node load can be monitored regularly to avoid the situation where a non-optimal node is selected due to consideration of regional distribution, resulting in a high node load.

[0064] In Kubernetes applications, you can develop a Kubernetes node scheduling plug-in to comprehensively consider the node load and node pool region when starting the PTS stress test task, and prioritize the deployment of stress test tasks on nodes in different node pools to distribute request traffic in different regions to avoid concentration in a certain area. At the same time, during the stress test process, you can adjust the scheduling node according to the node load to avoid selecting non-optimal nodes due to regional distribution, resulting in high node load.

[0065] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0066] Based on the same inventive concept, the embodiment of the present application also provides a scheduling processing device for implementing the scheduling processing method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more scheduling processing device embodiments provided below can refer to the above limitations on the scheduling processing method, and will not be repeated here.

[0067] In an exemplary embodiment, Figure 4 As shown, a scheduling processing device is provided, and the device 400 may include:

[0068] The recommended value acquisition module 401 is used to acquire the node recommended value of each node in the cluster for each scheduling unit copy of the stress testing task; the node recommended value is determined based on the deployment status of the stress testing task in the node pool where the node is located;

[0069] The node determination module 402 is used to determine the target node of the scheduling unit copy according to the node recommendation value of each node.

[0070] In an exemplary embodiment, the recommended value acquisition module 401 is used to obtain the preliminary node recommended value of each node in the node pool where the node is located if the node recommended value of the node is not cached; the preliminary node recommended value is obtained by evaluating the node according to a preset recommended value evaluation model; according to the preliminary node recommended value of each node in the node pool and the deployment status of the node pool for the stress testing task, the node recommended value of each node in the node pool is determined and cached; if the node recommended value of the node is cached, the cached node recommended value of the node is obtained.

[0071] In an exemplary embodiment, the recommended value acquisition module 401 is used to set the node recommended value of each node in the node pool to a preset value if the deployment status of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task has been deployed; if the deployment status of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task has not been deployed, then obtain and cache the node recommended value of each node in the node pool based on the node preliminary recommended value and the corresponding weight value of each node in the node pool; wherein the weight value is related to the size of the node preliminary recommended value of each node in the node pool.

[0072] In an exemplary embodiment, the recommendation value acquisition module 401 is also used to determine the weight value corresponding to the largest node preliminary recommended value as the first weight value, and determine the weight values ​​corresponding to the other node preliminary recommended values ​​as the second weight value based on the node preliminary recommended values ​​of each node in the node pool; wherein the first weight value is greater than the second weight value.

[0073] In an exemplary embodiment, the node determination module 402 is also used to obtain the load information of each node in the cluster; the node includes the target node; if the load information of the target node meets the node replacement condition, a replacement node of the target node is selected based on the node pool where the target node is located; and the scheduling unit copy is scheduled to the replacement node.

[0074] In an exemplary embodiment, the node determination module 402 is also used to obtain the replacement node based on a first available node that meets the load condition if there is a first available node that meets the load condition in the node pool where the target node is located; if there is no first available node that meets the load condition in the node pool where the target node is located, determine a second available node that meets the load condition in other node pools, and obtain the replacement node based on the second available node.

[0075] Each module in the above-mentioned scheduling processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0076] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device can be used to store data such as node recommendation values. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a scheduling processing method is implemented.

[0077] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0078] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0079] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0080] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0081] It should be noted that 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, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0082] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0083] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0084] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A scheduling processing method, characterized in that: The method comprises: For each scheduling unit copy of the stress testing task, obtain a node recommendation value of each node in the cluster; the node recommendation value is determined based on the deployment status of the stress testing task in the node pool where the node is located; The target node of the scheduling unit copy is determined according to the node recommendation value of each of the nodes.

2. The method according to claim 1, characterized in that The obtaining of the node recommendation value of each node in the cluster includes: If the node recommendation value of the node is not cached, obtaining the node preliminary recommendation value of each node in the node pool where the node is located; the node preliminary recommendation value is obtained by evaluating the node according to a preset recommendation value evaluation model; Determine and cache the node recommended value of each node in the node pool according to the node preliminary recommended value of each node in the node pool and the deployment status of the node pool for the stress testing task; If the node recommendation value of the node is cached, the cached node recommendation value of the node is obtained.

3. The method according to claim 2, characterized in that The determining and caching the node recommended value of each node in the node pool according to the node preliminary recommended value of each node in the node pool and the deployment status of the node pool for the stress testing task includes: If the deployment status of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task has been deployed, setting the node recommended value of each node in the node pool to a preset value; If the deployment status of the node pool for the stress testing task is that the scheduling unit copy of the stress testing task is not deployed, then the node recommendation value of each node in the node pool is obtained and cached based on the node preliminary recommendation value and the corresponding weight value of each node in the node pool; wherein the weight value is related to the size of the node preliminary recommendation value of each node in the node pool.

4. The method according to claim 3, characterized in that Before obtaining and caching the node recommendation value of each node in the node pool according to the node preliminary recommendation value and the corresponding weight value of each node in the node pool, the method further includes: According to the node preliminary recommended values ​​of each node in the node pool, the weight value corresponding to the largest node preliminary recommended value is determined as the first weight value, and the weight values ​​corresponding to the other node preliminary recommended values ​​are determined as the second weight value; wherein the first weight value is greater than the second weight value.

5. The method according to any one of claims 1 to 4, characterized in that After determining the target node of the scheduling unit copy according to the node recommendation value of each node, the method further includes: Obtaining load information of each node in the cluster; the nodes include the target node; If the load information of the target node meets the node replacement condition, selecting a replacement node for the target node based on the node pool where the target node is located; The scheduling unit replica is scheduled to the replacement node.

6. The method according to claim 5, characterized in that The selecting a replacement node for the target node based on the node pool where the target node is located includes: If there is a first available node that meets the load condition in the node pool where the target node is located, obtaining the replacement node according to the first available node; If there is no first available node that meets the load condition in the node pool where the target node is located, a second available node that meets the load condition is determined in other node pools, and the replacement node is obtained based on the second available node.

7. A scheduling processing device, characterized in that: The device comprises: A recommended value acquisition module, used to obtain a node recommended value of each node in the cluster for each scheduling unit copy of the stress testing task; the node recommended value is determined based on the deployment status of the stress testing task in the node pool where the node is located; The node determination module is used to determine the target node of the scheduling unit copy according to the node recommendation value of each node.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images