Method for managing computing nodes, related apparatus and computer program product

Abstract

The application provides a method for managing a computing node, a related device and a computer program product. The application obtains a first node parameter set of a first computing node in an online state; obtains a state evaluation rule for the first computing node based on a node type of the first computing node, wherein the state evaluation rule records a first usage degree threshold corresponding to each first node parameter in the first node parameter set, and a contribution score of a parameter value of the first node parameter to a first node state evaluation score when the parameter value is greater than or equal to the first usage degree threshold; processes the first node parameter set based on the state evaluation rule to generate the first node state evaluation score; and adjusts the first computing node from the online state to an offline state in response to the first state evaluation score being greater than or equal to a first score threshold. Thus, by dynamically configuring a targeted state evaluation rule according to the type of the computing node, accurate evaluation of the running state of the computing node is achieved, thereby effectively preventing business interruption or performance degradation caused by overload, resource depletion or potential failure of the computing node, and improving the overall service availability and reliability of a system composed of the computing node.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, electronic device, computer-readable medium, and computer program product for managing computing nodes. Background Technology

[0002] With the rapid development of computer technology, the demand for computing power and computing resources in application scenarios such as big data processing, artificial intelligence training, Internet of Things data analysis, real-time stream computing, and financial transaction systems is growing stronger.

[0003] To address this trend, distributed system architectures built on multiple computing nodes (such as cloud computing and edge computing) have been more widely adopted in these application scenarios. These systems and architectures can effectively meet the demands of various application scenarios for high-performance computing and massive data processing by integrating distributed computing resources.

[0004] In a distributed system architecture, computing nodes can be used as basic processing units to achieve functional collaboration through specialized division of labor. This allows the system to provide elastic and scalable computing capabilities to the outside world in an integrated manner while maximizing resource utilization.

[0005] Therefore, how to manage computing nodes more effectively and improve the overall service availability and reliability of the system composed of computing nodes is a matter of concern and urgent need. Summary of the Invention

[0006] This application provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for managing computing nodes. By dynamically configuring targeted status assessment rules according to the type of computing node, it achieves accurate assessment of the operating status of computing nodes, thereby effectively preventing business interruption or performance degradation caused by computing node overload, resource exhaustion, or potential failure, and improving the overall service availability and reliability of the system composed of computing nodes.

[0007] One aspect of this application provides a method for managing computing nodes, comprising: obtaining a first node parameter set of a first computing node in an online state; obtaining a state evaluation rule for the first computing node based on the node type of the first computing node, wherein the state evaluation rule records a first utilization threshold corresponding to each first node parameter in the first node parameter set, and a contribution score to the first node state evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first utilization threshold; processing the first node parameter set based on the state evaluation rule to generate a first node state evaluation score; and adjusting the first computing node from an online state to an offline state in response to the first state evaluation score being greater than or equal to the first score threshold.

[0008] In another aspect, this application provides an apparatus for managing computing nodes, comprising: a first node parameter acquisition module configured to acquire a first node parameter set of a first computing node in an online state; a first evaluation rule acquisition module configured to acquire a state evaluation rule for the first computing node based on the node type of the first computing node, wherein the state evaluation rule records a first usage threshold corresponding to each first node parameter in the first node parameter set, and a contribution score to the first node state evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first usage threshold; a first state evaluation module configured to process the first node parameter set based on the state evaluation rule to generate a first node state evaluation score; and a first node state adjustment module configured to adjust the first computing node from an online state to an offline state in response to the first state evaluation score being greater than or equal to the first score threshold.

[0009] In another aspect of this application, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method for managing computing nodes as provided above.

[0010] Another aspect of this application provides a computer-readable storage medium having computer program instructions stored thereon, which can be executed by a processor to implement the method for managing computing nodes as provided above.

[0011] In another aspect of this application, there is a computer program product including a computer program having stored computer program instructions thereon, which, when executed by a processor, can implement the method for managing computing nodes as provided above.

[0012] The solution provided in this application involves obtaining a set of first node parameters for a first computing node that is currently online; obtaining a status evaluation rule for the first computing node based on its node type, wherein the status evaluation rule records a first utilization threshold corresponding to each first node parameter in the first node parameter set, and a contribution score to the first node status evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first utilization threshold; processing the first node parameter set based on the status evaluation rule to generate a first node status evaluation score; and adjusting the first computing node from an online state to an offline state in response to the first status evaluation score being greater than or equal to the first score threshold. Thus, by dynamically configuring targeted status evaluation rules according to the type of computing node, accurate evaluation of the computing node's operating status is achieved, effectively preventing business interruptions or performance degradation caused by computing node overload, resource exhaustion, or potential failures, thereby improving the overall service availability and reliability of the system composed of computing nodes. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0015] Figure 1 A flowchart illustrating a process for managing computing nodes is provided in one embodiment of this application;

[0016] Figure 2 A flowchart illustrating the process of bringing a computing node online, as provided in one embodiment of this application;

[0017] Figure 3 A flowchart illustrating the process of managing computing nodes in a specific application scenario, as provided in an embodiment of this application;

[0018] Figure 4 A schematic diagram of a device for managing computing nodes provided in an embodiment of this application;

[0019] Figure 5 This is a schematic diagram of the structure of an electronic device suitable for implementing the solutions in the embodiments of this application.

[0020] The same or similar reference numerals in the accompanying drawings represent the same or similar parts. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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, 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.

[0022] In a typical configuration of this application, the terminal and the service network devices each include one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0023] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0024] Computer-readable media include permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. Information can be computer program instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only optical disc (CD-ROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0025] As discussed above, how to manage computing nodes more effectively and improve the overall service availability and reliability of the system composed of computing nodes is a matter of concern and urgent need.

[0026] In some solutions, node parameters of compute nodes can be continuously acquired and reported to users who manage the compute nodes. This allows users to adjust the online and offline status of compute nodes based on the node parameters, thus achieving management of the compute nodes. However, this approach clearly suffers from low management efficiency and struggles to manage distributed systems with multiple compute nodes in a timely, efficient, and low-cost manner.

[0027] To address this, this application provides a method for managing computing nodes. The method obtains a set of first node parameters for a first computing node that is currently online. Based on the node type of the first computing node, it obtains a status evaluation rule for the first computing node. This rule records a first utilization threshold corresponding to each first node parameter in the parameter set, and a contribution score to the first node status evaluation score when the parameter value is greater than or equal to the first utilization threshold. The method processes the first node parameter set based on the status evaluation rule to generate a first node status evaluation score. In response to the first status evaluation score being greater than or equal to a first score threshold, the first computing node is adjusted from an online state to an offline state. Therefore, by dynamically configuring targeted status evaluation rules according to the type of computing node, accurate evaluation of the computing node's operating status is achieved, effectively preventing business interruptions or performance degradation caused by computing node overload, resource exhaustion, or potential failures, thereby improving the overall service availability and reliability of the system composed of computing nodes.

[0028] In practical scenarios, the execution entity of this method can be a user device, a device composed of a user device and a network device integrated through a network, or an application running on the aforementioned devices. User devices include, but are not limited to, various terminal devices such as computers, mobile phones, tablets, smartwatches, and wristbands. Network devices include, but are not limited to, network hosts, single network servers, multiple network server sets, or cloud computing-based computer sets. Here, the cloud consists of a large number of hosts or network servers based on cloud computing. Cloud computing is a type of distributed computing, consisting of a virtual computer composed of a group of loosely coupled computer sets.

[0029] When the executing entity is software, it can be installed in the electronic devices listed above. It can be implemented as multiple software programs or software modules, or as a single software program or software module, without specific limitations.

[0030] First refer to Figure 1 , Figure 1 A flowchart of a process 100 for managing computing nodes according to an embodiment of this application is shown. Process 100 may specifically include the following steps:

[0031] (Step) S101, Obtain the first node parameter set of the first computing node that is in the online state;

[0032] In the embodiments of this application, the execution entity (e.g., a "management server," "management node," "scheduling server," etc. used to manage and schedule computing nodes in a distributed system, or a "management server," "management node," "scheduling server," etc. independent of the distributed system, capable of managing computing nodes in the distributed system. In some scenarios, the execution entity may also be a "computing node" in the distributed system that can perform "management" functions, or it may be a "user device," etc., used for managing the distributed system) can obtain the node parameter set of computing nodes that are online.

[0033] For ease of description, a computing node that is currently online (i.e., in a "accessible" or "online running" state that can be directly accessed and used by, for example, a user's terminal, in which case the computing node can be assigned new processing and storage tasks) can be described as a "first computing node".

[0034] Correspondingly, the node parameters of the first computation node can be described as "first node parameters", and the set consisting of one, or at least two, or more, different dimensions of "first node parameters" can be called the "first node parameter set".

[0035] In practice, depending on the scenario and system, the computing node can be a server node used to perform tasks such as data processing, business computing, and content storage. For example, the computing node can be an "edge node," such as an IoT edge node, an industrial edge node, an e-commerce edge node, and so on.

[0036] Node parameters can be those parameters (parameter values) that are associated with the current running status of the compute node and the current service capabilities of the compute node. For example, node parameters can include the current disk storage (RAM disk) utilization, bandwidth utilization, central processing unit (CPU) utilization, etc.

[0037] In different embodiments, the specific details of the node parameters that need to be monitored and acquired for the computing node can be determined in advance based on the service objectives and node type of the computing node, so that monitoring and management can be carried out differently and in a targeted manner based on the different computing nodes.

[0038] Accordingly, the executing entity may obtain one or more of the specific node parameters mentioned above in this step to form a node parameter set (e.g., a first node parameter set) and use the node parameter set to complete the subsequent process of managing the computing nodes.

[0039] S102, Based on the node type of the first computing node, obtain the state evaluation rules for the first computing node;

[0040] In the embodiments of this application, after obtaining the first node parameter set of the first computing node based on the above S101, the execution entity can continue to obtain the state evaluation rules for the first computing node based on the node type of the first computing node.

[0041] The state evaluation rule records the first usage threshold corresponding to each node parameter in the node parameter set, and the contribution score of the first node state evaluation score of the first computing node when the parameter value of the node parameter is greater than or equal to the usage threshold.

[0042] It should be understood that, since the subsequent steps in this embodiment (e.g., S103) actually utilize this state evaluation rule to evaluate the first computing node, for ease of understanding, the content recorded in the state evaluation rule can be directly described as the first utilization threshold corresponding to each first node parameter in the first node parameter set, and the contribution score of the first node state evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first utilization threshold. That is, in the context of this embodiment, the state evaluation rule can specifically be applied to the "first node parameters".

[0043] For example, the status assessment rules can record the first usage threshold corresponding to the disk storage (RAM disk) utilization rate (specific parameter value), and the contribution score (or contribution rating) that a computing node can give to the status assessment score when the disk storage (RAM disk) utilization rate is greater than or equal to the first usage threshold. Furthermore, for ease of understanding, the term "node parameter" will be used directly in the following descriptions, without emphasizing the specific "parameter value of the node parameter".

[0044] For example, regarding disk storage (RAM disk) utilization, the corresponding first utilization threshold can be 40%, and the corresponding contribution score is "10 points". Accordingly, if the first node parameter, which is expressed as "disk storage (RAM disk) utilization", is 50%, the executing entity can respond to this and determine to contribute "10 points" to the "first node status evaluation score".

[0045] In the embodiments of this application, based on the functional differences of computing nodes (e.g., for storage, for data processing, for performing verification, etc.), computing nodes can be correspondingly classified into storage computing nodes, data processing computing nodes, verification computing nodes, etc. Accordingly, the state evaluation rules can be configured according to the node type. Therefore, by formulating differentiated state evaluation rules, precise and differentiated evaluation strategies can be implemented based on the specific operating environment and resource configuration of different types of computing nodes, thereby improving the accuracy and relevance of the evaluation of different computing nodes.

[0046] Typically, such "differences" can be reflected in the dimensions of the specific node parameters being referenced, the corresponding "first utilization" threshold, or the "contribution score." That is, for different state assessment rules, the differences can lie in the node parameters being assessed, the corresponding first utilization thresholds for different node parameters, or the "contribution score" provided after being greater than or equal to the corresponding first utilization threshold (of course, it can also be a combination of at least two of these). For example, state assessment rule A can assess disk storage (RAM) utilization and bandwidth usage, while rule B can assess disk storage (RAM) utilization, bandwidth usage, and CPU utilization. Furthermore, for state assessment rules A and C, which both assess disk storage (RAM) utilization and bandwidth usage, they can correspond to different values ​​for the "first utilization threshold" based on disk storage (RAM) utilization; for example, the "first utilization threshold" in state assessment rule A is "40%", while in state assessment rule C it is "60%".

[0047] In some embodiments, considering that computing nodes may experience peak and off-peak periods during actual use due to different scenarios, for example, computing nodes providing video may have greater usage demand during prime time in the evening, while computing nodes used for IoT computing may have greater usage demand during production periods, in order to evaluate and adapt to these scenarios more granularly (e.g., allowing greater bandwidth utilization, CPU utilization, etc. during these "peak" periods), the state evaluation rules can also set the first usage threshold and / or "contribution score" based on the dimensions of "time" and "time period".

[0048] That is, even for the same node parameters, different first utilization thresholds and / or contribution scores can be recorded in the state evaluation rules within different time intervals, so that the executing entity can evaluate the state of the computing node more granularly with reference to the time situation, so as to take into account both the utilization needs and security of the computing node.

[0049] In some embodiments, when the "time" dimension is introduced, the state evaluation rules can be further set to reference different node parameters in different time intervals to further balance the utilization needs and security of computing nodes.

[0050] Accordingly, in such a case, the state evaluation rule can actually record the first utilization threshold corresponding to each first node parameter in the first node parameter set in the current first time interval, and the contribution score of the first node parameter to the first node state evaluation score of the first computing node when the parameter value of the first node is greater than or equal to the first utilization threshold.

[0051] S103, Process the first node parameter set based on the state assessment rules to generate the first node state assessment score;

[0052] In the embodiments of this application, after obtaining the state evaluation rule corresponding to the first computing node based on S102, the execution entity can process the first node parameter set of the first computing node based on the state evaluation rule to generate a first node state evaluation score. The first node state evaluation score can be the result of direct summation or weighted summation of each "contribution score" (the weight of the summation can also be set accordingly in the state evaluation rule).

[0053] Then, the executing entity can compare the first node status assessment score with a first scoring threshold (which can be pre-set based on criteria such as believing that the "first computing node" has been overused, is in an "overloaded" state, or has a high probability of risk due to overuse).

[0054] If the first state evaluation score is greater than or equal to the first score threshold, the executing entity can respond by executing S104.

[0055] S104, adjust the first computing node from online to offline.

[0056] In the embodiments of this application, if the first state evaluation score is greater than or equal to the first score threshold, it means that the "comprehensive state" of the first computing node (i.e., under the comprehensive evaluation of different parameter dimensions) may be over-occupied, overloaded, or potentially pose a high risk. In response, the executing entity can choose to take the first computing node offline (e.g., no longer allowing terminals used by users to access or use the "computing node" with new access or usage requests, and no longer assigning new processing or storage tasks to it). This allows computing nodes that may currently be over-occupied to exit and go offline in a timely and effective manner, alleviating the current over-occupancy, overuse, and overload situation, preventing continuous over-occupancy and overuse that could lead to crashes or other issues, and improving the overall stability and security of the system composed of computing nodes.

[0057] In some embodiments, if the state evaluation rule involves "time," such as the one discussed above, where the state evaluation rule records the first utilization threshold corresponding to each first node parameter in the first node parameter set within the current first time interval (e.g., the first time interval is set based on peak and off-peak times), and the contribution score of the first node parameter to the first node state evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first utilization threshold, then in such a case, the executing entity may, as an alternative or alternative, select, in this step, in response to the first state evaluation score being greater than or equal to the first score threshold, to adjust the first computing node from an online state to an offline state within the first time interval. That is, the executing entity only adjusts the first computing node to be in an "offline state" within the first time interval. This ensures that the online and offline adjustment actions and strategies are matched with the state evaluation rules, so as to avoid the situation of reducing the evaluation quality and incorrectly taking computing nodes offline due to the use of potentially inappropriate state evaluation rules (for example, unintentionally using state evaluation rules that are not for the current time) to make undesirable evaluations of situations outside the "first time interval", thereby improving the management quality of computing nodes.

[0058] In some embodiments, where the state assessment rules are allowed to be subdivided based on the "time" dimension, a second scoring threshold greater than the first scoring threshold can be configured to allow for differentiated management of compute nodes. For example, if the "overload" of a compute node cannot be successfully mitigated within the first time interval, it can prevent the node from being brought back online without mitigating the overload after the first time interval ends.

[0059] Accordingly, in such a case, a second time interval can be configured corresponding to the second scoring threshold. The length of the second time interval is greater than that of the first time interval, so that the length of the second time interval can be used to "delay" the re-launch of the computing node. For example, the first time interval can correspond to the "peak time or period" within a day, while the second time interval can correspond to "a day".

[0060] In such an embodiment, the first scoring threshold may correspond to the standard that can usually be mitigated within the first time interval, while the second scoring threshold may correspond to the standard that can usually be mitigated within the second time interval, so that the computing node can have more time to mitigate when it is extremely occupied and used.

[0061] In some embodiments, when the state evaluation rules target a "first time interval," based on the difference in the first scoring threshold, the executing entity can also choose to take the first computing node offline within a third time interval shorter than or less than the first time interval. (For example, if the first scoring threshold is set low, the computing node's "mitigation" efficiency may be high. In such cases, the computing node may not need as long as the first time interval to complete the mitigation. In this case, the third time interval can be set based on the mitigation rate and the average mitigation duration. For example, the third time interval can start from the time the computing node is taken offline, and the "average" is the length of the time interval.) This allows the first computing node to be put back into use as soon as possible, improving the overall performance of the system composed of computing nodes.

[0062] Subsequently, the method for managing computing nodes provided in this application obtains a set of first node parameters for a first computing node that is online; based on the node type of the first computing node, it obtains a status evaluation rule for the first computing node, wherein the status evaluation rule records the first utilization threshold corresponding to each first node parameter in the first node parameter set, and the contribution score of the first node parameter to the first node status evaluation score when the parameter value is greater than or equal to the first utilization threshold; it processes the first node parameter set based on the status evaluation rule to generate a first node status evaluation score; and in response to the first status evaluation score being greater than or equal to the first score threshold, it adjusts the first computing node from an online state to an offline state. Thus, by dynamically configuring targeted status evaluation rules according to the type of computing node, accurate evaluation of the computing node's operating status is achieved, thereby effectively preventing business interruptions or performance degradation caused by computing node overload, resource exhaustion, or potential failures, and improving the overall service availability and reliability of the system composed of computing nodes.

[0063] In some embodiments, the state evaluation rule described above may also record the second usage threshold corresponding to each first node parameter in the first node parameter set, and the value of the second usage threshold is greater than the first usage threshold.

[0064] Correspondingly, in such a case, the executing entity may also choose to determine whether there is a target first node parameter based on the state evaluation rules, where the parameter value of the target first node parameter is greater than or equal to the corresponding second usage threshold.

[0065] If present, the executing entity can respond by adjusting the first computing node from an online state to an offline state. This allows for a more granular evaluation of specific node parameters in addition to the overall status assessment of the (first) node parameters. This enables timely management and offline management of computing nodes should an anomaly occur when a specific node parameter exhibits a significant abnormality.

[0066] In some embodiments, when using a second usage threshold to evaluate specific node parameters, the "second usage threshold" can also be configured from a "time" perspective, similar to what was discussed above. For example, the second usage threshold can be configured for a "first time interval" so that, when evaluating specific node parameters, the evaluation can be more granular, targeting peak and off-peak scenarios, as discussed above. Similarly, a third usage threshold greater than the second usage threshold can also be configured so that, using both the second and third usage thresholds, the goal of either taking the node offline within the first time interval or within the second time interval to provide more time for "mitigation" can be achieved, as discussed above. This will not be repeated here.

[0067] In some embodiments, in order to manage computing nodes more intelligently, in addition to taking offline (first) computing nodes, the execution entity can also choose to bring offline computing nodes back online, so that the execution entity can dynamically adjust the online and offline status of computing nodes based on the status of computing nodes, thereby achieving effective management of the system.

[0068] Accordingly, in such a case, for ease of description, the computing node that has been taken offline and is in an offline state can be described as the second computing node, in order to distinguish it from the first computing node mentioned above.

[0069] Similarly, to better understand the process of deploying computing nodes, you can refer to [the relevant documentation / reference]. Figure 2 . Figure 2 A flowchart of a process 200 for bringing a computing node online according to an embodiment of this application is shown. Process 200 may specifically include the following steps:

[0070] S201, Obtain the second node parameter set of the second computing node that is already offline;

[0071] Specifically, similar to S101 in process 100, the executing entity can obtain the node parameters (set) of the second computing node. Similarly, for descriptive purposes, these "node parameters" can be described as second node parameters. The second node parameters involved in this set of second node parameters can be the same as those involved in the first parameter node set mentioned above, or they can differ based on the differences in the "re-online" criteria.

[0072] S202, Based on the node type of the second computing node, obtain the state evaluation rules;

[0073] Specifically, similar to S101 above, the executing entity can obtain the state evaluation rule based on the node type of the second computing node in this step. The state evaluation rule can be the same as that discussed in process 100 above, and will not be repeated here.

[0074] Then, the executing entity can also process the second node parameter set based on the state evaluation rules by executing S203, and generate the second node state evaluation score.

[0075] S203, Process the second node parameter set based on the state assessment rules to generate the second node state assessment score;

[0076] After generating the second node status assessment score, the executing entity can also compare the second status assessment score with the aforementioned first score threshold. If the second status assessment score is less than the first score threshold, that is, the "overload" state corresponding to the second computing node has been successfully alleviated, the executing entity can respond by executing S204 to adjust the second computing node from the offline state to the online state.

[0077] S204, in response to the second state evaluation score being less than the first score threshold, the second computing node is adjusted from the offline state to the online state.

[0078] In some embodiments, also for the purpose of more intelligent management of computing nodes, the executing entity may also choose to perform the process of managing computing nodes as discussed in process 100 above by periodic inspection. For example, for S101 in the process, the executing entity may, as an alternative or additional option, periodically obtain the first node parameter set of the first computing node in the online state in the first period to periodically start and execute process 100 to achieve "periodic inspection".

[0079] In such a case, if the executing entity can also "bring the second computing node online", the executing entity can also choose to periodically execute S201 to similarly periodically bring those computing nodes that have completed "mitigation" online. That is, when executing S201, the executing entity can, as an alternative or additional option, periodically obtain the second node parameter set of the second computing node that is in the offline state in the second cycle.

[0080] In some embodiments, the length of the second cycle can be shorter than that of the first cycle, so that such online inspections can be more frequent than offline inspections, in order to help and assist computing nodes to be restored to use earlier and improve the overall computing power of the system.

[0081] In some embodiments, the first and second cycles can be configured individually or collectively with reference to peak and off-peak times, so that, for example, online and / or offline checks can be performed more frequently during peak hours (e.g., offline checks can be performed at a 1-hour cycle during peak hours and at a 2-hour cycle during off-peak hours). This ensures system performance during peak hours.

[0082] In some embodiments, the executing entity may also continuously monitor the number of currently online first computing nodes. If the number of the first computing nodes is less than or equal to a number threshold (which can typically be set based on the assumption that the number of computing nodes currently providing services may be insufficient), the executing entity may respond by choosing to immediately perform an online inspection of the second computing nodes (e.g., starting an action to obtain the second node parameter set of the second computing nodes that are already offline), or by reducing or shortening the second period to obtain an updated second period. Then, when periodically obtaining the second node parameter set of the second computing nodes that are already offline in the second period, the executing entity may further choose to periodically obtain the second node parameter set of the second computing nodes that are already offline in the updated second period.

[0083] This allows for more frequent online inspections when there may be a shortage of computing nodes, enabling second computing nodes that meet the usage requirements to be brought online earlier, thereby improving the overall computing power of the system.

[0084] In some embodiments, if the execution entity performs online inspection in the first cycle, the execution entity may also choose to take the first computing node offline by detecting and obtaining "mutations". For example, if the change in a specific node parameter is greater than or equal to the magnitude threshold in two cycles, the execution entity may also respond by taking the first computing node offline, so as to achieve the purpose of more effective control over computing nodes.

[0085] Based on any of the above embodiments, in order to facilitate users in managing computing nodes to understand and be aware of the status of each computing node, an interface can be configured to provide feedback on the status of the computing nodes to the user, and allow the user to manage the computing nodes conveniently and efficiently by interacting with the interface.

[0086] Accordingly, in such a scenario, the executing entity can present the computing nodes on the target interface (or, in other words, provide and present the corresponding graphical and visual elements on the target interface to indicate and represent each computing node). Consequently, the computing nodes presented on the target interface can include a first computing node currently online and a second computing node that is offline. This allows the user to intuitively view and obtain the status of each computing node.

[0087] In some embodiments, the executing entity may also choose to configure a control component (e.g., an online / offline switching component) in the target interface so that the user can interact with the control component to take the first computing node offline and / or bring the second computing node online.

[0088] Accordingly, in some embodiments, the target interface may also be configured with an inspection control for triggering inspections, so that users can use the inspection control to trigger online and / or offline inspections in real time as needed.

[0089] In some embodiments, the executing entity may also choose to present in the target interface the time when the second computing node was taken offline, and the first node status assessment score that the second computing node had when it was taken offline (typically the first node status assessment score and the score details of the first node status assessment score, such as the "contribution score" corresponding to each node parameter can be provided).

[0090] In some embodiments, the implementing entity may also provide more specific parameter values ​​for those nodes that have "contributed". This allows users to better understand the offline time and reasons for the offline of compute nodes, facilitating user management of compute nodes.

[0091] In some embodiments, if the first computing node is only offline within a "first time interval", the executing entity may also provide the end time of the first time interval as the "expected re-on time" to the target interface in order to provide users with more reference information.

[0092] In some embodiments, when performing online or offline actions on computing nodes, the executing entity may also choose to present or pop up corresponding prompts on the target interface in order to provide users with more reference information.

[0093] In some embodiments, when the executing entity performs online or offline actions on a compute node, it can also generate an execution log based on the node parameters of the compute node at the time of the action and the actions performed, so that the executing entity can be used to backtrack these processes later. For example, the log can record the compute node's name (primary key), node type, hardware configuration (total storage capacity, memory disk capacity, bandwidth limit, number of CPU cores), cluster to which it belongs, status (online / offline), actions performed, action time, etc.

[0094] In some embodiments, if the execution subject fails to obtain the first node parameter set multiple times during the process of obtaining the first node parameter set (for example, the number of failures is greater than or equal to the number of failures threshold), the execution subject may also choose to directly take the first computing node offline to avoid risks caused by the inability to obtain node parameters and node status.

[0095] To enhance understanding, this application also provides a specific implementation scheme based on a particular application scenario. Please refer to it. Figure 3 , Figure 3 This is a flowchart of a process 300 for managing computing nodes in a specific application scenario, provided as an embodiment of this application.

[0096] In process 300, the “management node 310” can be used as the execution subject of process 300. In process 300, the management node 310 can manage computing nodes 311, 312...31N (where N is a positive integer).

[0097] Accordingly, in different scenarios, the management node 310 can be combined with the computing nodes 311, 312...31N to form a "system" (e.g., an edge computing system), or it can be composed of computing nodes 311, 312...31N to form a "system", while the management node 310, which is independent of the system, is used to manage the system.

[0098] In process 300, exemplarily, at least compute nodes 311 and 312 are in an "online" state in the current state to accept and respond to new processing tasks (e.g., processing tasks provided by terminal devices not shown in the diagram). In this case, for the purpose of clarity and ease of understanding, process 300 may only use management node 310 as an example to illustrate the management process of compute node 311. For other compute nodes, such as compute node 312, management node 310 can achieve a similar management purpose by reusing and reproducing related actions.

[0099] In process 300, the management node 310 can first obtain node parameters from the computing node 311 by executing S301. For example, it can obtain node parameters 321, 322...32N (where N is also a positive integer, but there is no direct numerical correspondence or association between the “N” here and the “N” in 31N above).

[0100] Then, the management node 310 can continue to execute S302 to obtain the state evaluation rule 331 for the computing node 311 based on the node type of the computing node 311. For example, the state evaluation rule 331 may record the first utilization threshold corresponding to each of the node parameters 321, 322...32N, the contribution score of the node parameters 321, 322...32N (parameter values) to the node state evaluation score (e.g., node state evaluation score 341) when the parameter values ​​of the node parameters 321, 322...32N are greater than or equal to their respective utilization thresholds, and the second utilization threshold corresponding to each of the node parameters 321, 322...32N.

[0101] Next, the management node 310 can continue to process node parameters 321, 322...32N based on the status assessment rule 331 by executing S303, and generate a node status assessment score 341.

[0102] Additionally, in process 300, when the management node 310 executes S303, it can execute S304 simultaneously with S303, or one after the other (either can be executed first), to determine whether there is a target node parameter (i.e., a node parameter whose corresponding parameter value is greater than or equal to the second usage threshold) among the node parameters 321, 322...32N based on the state evaluation rule 331, so as to simultaneously "evaluate" each of the node parameters 321, 322...32N (or their "individuals"), as well as the whole they form.

[0103] For example, in process 300, the state evaluation score 341 is greater than or equal to the first score threshold, and there is no target node parameter among the node parameters 321, 322...32N.

[0104] In this situation, management node 310 can respond by choosing to continue executing S305 and adjusting compute node 311 from an online state to an offline state (because the status evaluation score 341 is greater than or equal to the first score threshold).

[0105] Similarly, if after executing S304, the management node 310 finds that "target node parameters" also exist alone or together, the management node 310 can also respond similarly by executing S305 to adjust the compute node 311 from the online state to the offline state.

[0106] This application also provides an apparatus for managing computing nodes, the structure of which is as follows: Figure 4 The apparatus 400 shown includes: a first node parameter acquisition module 410, configured to acquire a first node parameter set of a first computing node in an online state; a first evaluation rule acquisition module 420, configured to acquire a state evaluation rule for the first computing node based on the node type of the first computing node, wherein the state evaluation rule records a first usage threshold corresponding to each first node parameter in the first node parameter set, and a contribution score to the first node state evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first usage threshold; a first state evaluation module 430, configured to process the first node parameter set based on the state evaluation rule to generate a first node state evaluation score; and a first node state adjustment module 440, configured to adjust the first computing node from an online state to an offline state in response to the first state evaluation score being greater than or equal to the first score threshold.

[0107] This embodiment exists as a device embodiment corresponding to the above method embodiment. The device for managing computing nodes provided in this embodiment achieves accurate assessment of the operating status of computing nodes by dynamically configuring targeted status assessment rules according to the type of computing nodes. This effectively prevents business interruption or performance degradation caused by computing node overload, resource exhaustion or potential failure, and improves the overall service availability and reliability of the system composed of computing nodes.

[0108] In some embodiments, the state evaluation rule also records the second usage threshold corresponding to each first node parameter in the first node parameter set, wherein the value of the second usage threshold is greater than the first usage threshold, and the device 400 further includes: a second node state adjustment module, configured to adjust the first computing node from an online state to an offline state in response to determining the existence of a target first node parameter based on the state evaluation rule, wherein the parameter value of the target first node parameter is greater than or equal to the corresponding second usage threshold.

[0109] In some embodiments, the state evaluation rules record the first usage threshold corresponding to each first node parameter in the first node parameter set within the current first time interval, and the contribution score of the first node parameter to the first node state evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first usage threshold; and the first node state adjustment module 440 is further configured to adjust the first computing node from an online state to an offline state within the first time interval in response to the first state evaluation score being greater than or equal to the first score threshold.

[0110] In some embodiments, the device 400 further includes a third node state adjustment module, configured to adjust the first computing node from an online state to an offline state within a second time interval in response to a first state evaluation score being greater than or equal to a second score threshold, wherein the value of the second score threshold is greater than the first score threshold, and the length of the second time interval is greater than the first time length.

[0111] In some embodiments, the apparatus 400 further includes: a second node parameter acquisition module configured to acquire a second node parameter set of a second computing node that is in an offline state; a second evaluation rule acquisition module configured to acquire a state evaluation rule based on the node type of the second computing node; a second state evaluation module configured to process the second node parameter set based on the state evaluation rule and generate a second node state evaluation score; and a fourth node state adjustment module configured to adjust the second computing node from an offline state to an online state in response to the second state evaluation score being less than a first score threshold.

[0112] In some embodiments, the first node parameter acquisition module 410 is further configured to periodically acquire the first node parameter set of the first computing node in the online state in a first cycle; the second node parameter acquisition module is further configured to periodically acquire the second node parameter set of the second computing node in the offline state in a second cycle, wherein the length of the second cycle is shorter than that of the first cycle.

[0113] In some embodiments, the apparatus 400 further includes: a period adjustment module configured to shorten the second period in response to the current number of first computing nodes being less than or equal to a number threshold, thereby obtaining an updated second period; and a second node parameter acquisition module further configured to periodically acquire the second node parameter set of the second computing nodes that are already offline in the updated second period.

[0114] In some embodiments, the apparatus 400 further includes: a computing node presentation module configured to present computing nodes on a target interface, wherein the computing nodes include a first computing node and a second computing node that is offline; and an associated information presentation module configured to present, in the target interface, the time when the second computing node was offline, and a first node status evaluation score that the second computing node had when it was offline.

[0115] Based on the same concept, this application also provides an electronic device, a readable storage medium, and a computer program product. The method corresponding to the electronic device can be the method for managing computing nodes in the foregoing embodiments, and its problem-solving principle is similar to that method. The electronic device provided in this application includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the methods and / or technical solutions of the foregoing embodiments of this application.

[0116] Electronic devices can be user devices, or devices composed of user devices and network devices integrated through a network, or applications running on the aforementioned devices. User devices include, but are not limited to, various terminal devices such as computers, mobile phones, tablets, smartwatches, and wristbands. Network devices include, but are not limited to, network hosts, single network servers, multiple network server sets, or cloud computing-based computer sets, and can be used to implement some processing functions when setting an alarm clock. Here, the cloud consists of a large number of hosts or network servers based on cloud computing. Cloud computing is a type of distributed computing, consisting of a virtual computer composed of a group of loosely coupled computer sets.

[0117] Figure 5 The diagram illustrates the structure of an electronic device suitable for implementing the methods and / or technical solutions in the embodiments of this application. The electronic device 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes based on a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage portion 508 into a Random Access Memory (RAM) 503. The RAM 503 also stores various programs and data required for system operation. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An Input / Output (I / O) interface 505 is also connected to the bus 504.

[0118] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, touchscreen, microphone, infrared sensor, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), LED display, OLED display, etc., and speakers, etc.; a storage section 508 including one or more computer-readable media such as hard disk, optical disk, magnetic disk, semiconductor memory, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet.

[0119] In particular, the methods and / or embodiments in this application can be implemented as computer software programs. For example, the embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. When the computer program is executed by the central processing unit (CPU) 501, it performs the functions defined in the methods of this application.

[0120] Another embodiment of this application provides a computer-readable storage medium and a computer program product having computer program instructions stored thereon, which can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of this application described above.

[0121] Specifically, this embodiment may employ any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, a system, apparatus, or device that is, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0122] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0123] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0124] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0125] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-specific system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0126] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules and units is only a logical functional division, and in actual implementation, there may be other division methods. Taking units as examples, multiple units or page components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0128] The units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0129] Furthermore, the functional modules and units in the various embodiments of this application can be integrated into one processing module or unit, or each module or unit can exist physically separately, or two or more units can be integrated into one module or unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules and units.

[0130] The integrated modules and units implemented as software functional modules and units described above can be stored in a computer-readable storage medium. These software functional modules and units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0132] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a device claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

Claims

1. A method for managing computing nodes, characterized in that, include: Get the first node parameter set of the first compute node that is online; Based on the node type of the first computing node, a state evaluation rule for the first computing node is obtained. The state evaluation rule records the first usage threshold corresponding to each first node parameter in the first node parameter set, and the contribution score of the first node state evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first usage threshold. Based on the state evaluation rules, the parameter set of the first node is processed to generate a state evaluation score for the first node. In response to the first state evaluation score being greater than or equal to the first score threshold, the first computing node is adjusted from the online state to the offline state.

2. The method according to claim 1, characterized in that, The state evaluation rule also records the second usage threshold corresponding to each first node parameter in the first node parameter set, wherein the value of the second usage threshold is greater than the first usage threshold, and the method further includes: In response to determining the existence of a target first node parameter based on the state evaluation rule, the first computing node is adjusted from the online state to the offline state, wherein the parameter value of the target first node parameter is greater than or equal to the corresponding second usage threshold.

3. The method according to claim 1, characterized in that, The state evaluation rule records the first usage threshold corresponding to each first node parameter in the first node parameter set within the current first time interval, and the contribution score of the first node parameter to the first node state evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first usage threshold. as well as In response to the first state evaluation score being greater than or equal to a first score threshold, adjusting the first computing node from the online state to the offline state includes: In response to the first state evaluation score being greater than or equal to the first score threshold, the first computing node is adjusted from the online state to the offline state within the first time interval.

4. The method according to claim 3, characterized in that, The method further includes: In response to the first state evaluation score being greater than or equal to the second score threshold, the first computing node is adjusted from the online state to the offline state within the second time interval, wherein the value of the second score threshold is greater than the first score threshold, and the length of the second time interval is greater than the first time length.

5. The method according to claim 1, characterized in that, The method further includes: Obtain the second node parameter set of the second compute node that is currently offline; Based on the node type of the second computing node, the state evaluation rule is obtained; The second node parameter set is processed based on the state evaluation rules to generate a state evaluation score for the second node. In response to the second state evaluation score being less than the first score threshold, the second computing node is adjusted from the offline state to the online state.

6. The method according to claim 5, characterized in that, The step of obtaining the first node parameter set of the first computing node that is online includes: In the first cycle, periodically obtain the first node parameter set of the first computing node that is online; as well as The step of obtaining the second node parameter set of the second computing node that is already offline includes: In the second cycle, the second node parameter set of the second computing node that is offline is periodically acquired, wherein the length of the second cycle is shorter than that of the first cycle.

7. The method according to claim 6, characterized in that, The method further includes: In response to the current number of the first computing nodes being less than or equal to a threshold, the second cycle is shortened to obtain an updated second cycle; and The process of periodically acquiring the second node parameter set of the second computing node that is already offline in the second cycle includes: In the updated second cycle, the second node parameter set of the second computing node that is offline is periodically obtained.

8. The method according to claim 1, characterized in that, The method further includes: The computing nodes are presented on the target interface, wherein the computing nodes include the first computing node and the second computing node that is offline; The target interface displays, in association with the second computing node, the time when the second computing node was taken offline, and the first node status evaluation score at the time the second computing node was taken offline.

9. A device for managing computing nodes, characterized in that, include: The first node parameter acquisition module is configured to acquire the first node parameter set of the first computing node that is online. The first evaluation rule acquisition module is configured to acquire a state evaluation rule for the first computing node based on the node type of the first computing node. The state evaluation rule records the first usage threshold corresponding to each first node parameter in the first node parameter set, and the contribution score of the first node state evaluation score of the first computing node when the parameter value of the first node parameter is greater than or equal to the first usage threshold. The first state assessment module is configured to process the first node parameter set based on the state assessment rules and generate a first node state assessment score. The first node state adjustment module is configured to adjust the first computing node from the online state to the offline state in response to the first state evaluation score being greater than or equal to the first score threshold.

10. An electronic device, the electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.

11. A computer-readable medium having stored thereon computer program instructions that can be executed by a processor to implement the method as described in any one of claims 1 to 8.

12. A computer program product comprising a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 8.

Images