Management method, device, apparatus, medium and product of computing node

Abstract

The application discloses a kind of management methods, device, equipment, medium and product of computing node, it is related to computer technical field, comprising: in response to the interrupt prompt information of target cloud vendor for target computing node, the node interruption moment corresponding when target cloud vendor executes interrupt operation to target computing node is determined, and node interruption waiting time is determined according to current time and node interruption moment;According to the total time of pre-set proportion value and node interruption waiting time determines the expulsion interval of each candidate container group in turn is expelled;According to the total time of expulsion interval and the container group quantity of candidate container group, the expulsion interval time of each candidate container group in turn is expelled is determined, and expulsion operation is executed to each candidate container group in turn according to expulsion interval time.The application can avoid all the business on target computing node instantaneous interruption in the process that cloud vendor interrupts target computing node, improves the stability of the business that target computing node is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and in particular, to a management method and device of a computing node, equipment, medium and product. BACKGROUND

[0002] With the development of cloud native technology, bidding computing nodes (also known as spot computing nodes) are increasingly used by public cloud vendors / customers due to their same performance but lower price.

[0003] However, bidding computing nodes may be unexpectedly interrupted, and the node fee may change over time, and the node interruption rate may also change, which can easily cause business services to be affected, and in extreme cases, all bidding computing nodes may be interrupted.

[0004] Before interrupting bidding computing nodes, cloud vendors give clients a certain amount of time to evict container groups. Currently, clients mostly directly evict all container groups at once, which can cause all business services on bidding computing nodes to be interrupted at once, which greatly affects the stability of business implementation. SUMMARY

[0005] The present application provides a management method and device of a computing node, equipment, medium and product to improve the stability of business services implemented by the computing node during the process of interrupting the computing node by a cloud vendor.

[0006] According to an aspect of the present application, a management method of a computing node is provided, comprising:

[0007] In response to interruption prompt information of a target cloud vendor for a target computing node, a node interruption time corresponding to an interruption operation performed by the target cloud vendor on the target computing node is determined, and a node interruption waiting time is determined according to a current time and the node interruption time;

[0008] A total eviction interval time for sequentially evicting each candidate container group is determined according to a preset proportion value and the node interruption waiting time, wherein the candidate container group is a container group contained in the target computing node, the preset proportion value is determined according to a total time consumed for evicting each candidate container group, and the preset proportion value is less than 1;

[0009] A eviction interval time for sequentially evicting each candidate container group is determined according to the total eviction interval time and the number of container groups of the candidate container group, and an eviction operation is sequentially performed on each candidate container group according to the eviction interval time.

[0010] According to another aspect of the present application, a management device of a computing node is provided, comprising:

[0011] A time determining module is configured to determine a node interruption time corresponding to an interruption operation performed by the target cloud vendor on the target computing node in response to interruption prompt information of the target cloud vendor for the target computing node, and determine a node interruption waiting time according to a current time and the node interruption time.

[0012] A total eviction interval time determining module is configured to determine a total eviction interval time for sequentially performing eviction on each candidate container group according to a preset ratio value and the node interruption waiting time, wherein the candidate container group is a container group contained in the target computing node, the preset ratio value is determined according to a total time consumption of performing eviction on the each candidate container group, and the preset ratio value is less than 1.

[0013] A container group eviction module is configured to determine an eviction interval time for sequentially performing eviction on each candidate container group according to the total eviction interval time and a container group quantity of the candidate container group, and perform eviction operation on the each candidate container group according to the eviction interval time.

[0014] According to another aspect of the present application, an electronic device is provided, which comprises:

[0015] at least one processor; and

[0016] a memory connected with the at least one processor; wherein

[0017] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the management method of the computing node according to any one of the present application.

[0018] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to execute the management method of the computing node according to any one of the present application.

[0019] According to another aspect of the present application, a computer program product is provided, which comprises a computer program for enabling a processor to execute the management method of the computing node according to any one of the present application.

[0020] The application determines the total expulsion interval time of sequentially expelling each candidate container group according to the preset proportion value and the node interruption waiting time, determines the expulsion interval time of sequentially expelling each candidate container group according to the total expulsion interval time and the container group quantity of the candidate container group, and executes the expulsion operation on each candidate container group according to the expulsion interval time, so that in the process of interrupting the target computing node by the cloud vendor, each candidate container group in the target computing node is sequentially expelled at a certain interval time, rather than all candidate container groups are expelled at one time, so that the instant interruption of all services on the target computing node can be avoided, and the stability of the services implemented by the target computing node is improved.

[0021] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the application, nor is it used to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0023] Figure 1 A flowchart of a management method of a computing node provided for the first embodiment of the application;

[0024] Figure 2 A flowchart of a management method of a computing node provided for the second embodiment of the application;

[0025] Figure 3 A flowchart of a management method of a computing node provided for the third embodiment of the application;

[0026] Figure 4 A structural schematic diagram of a management device of a computing node provided for the fourth embodiment of the application;

[0027] Figure 5 A structural schematic diagram of an electronic device for implementing the management method of the computing node of the embodiment of the application. DETAILED DESCRIPTION

[0028] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work should belong to the protection scope of the present application.

[0029] It should be noted that the terms "candidate", "target", "to be applied", "auxiliary", "first", "second", "other", "to be scheduled", "to be optimized", "current", "optimization" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to the clearly listed steps or units, but can include other steps or units that are not clearly listed or inherent to the process, method, product or device.

[0030] Embodiment one

[0031] Figure 1 A flowchart of a management method of a computing node provided by the first embodiment of the present application, the present embodiment can be applied to the case where each candidate container group contained in the target computing node is evicted in the process of interrupting the target computing node in the target cloud vendor. The method can be executed by a management device of the computing node, which can be realized in the form of hardware and / or software, such as a client, etc. As shown in the figure, the method comprises: Figure 1

[0032] S101, in response to the interruption prompt information of the target cloud vendor for the target computing node, determining the node interruption time corresponding to the interruption operation of the target cloud vendor on the target computing node, and determining the node interruption waiting time according to the current time and the node interruption time.

[0033] The target cloud vendor refers to the provider of cloud computing services, i.e. the holder of the computing node, which builds a data center platform and distributes the computing node to it through the network to provide services for users.

[0034] ​The client applies for a computing node to a target cloud vendor, and the computing node successfully applied for is a candidate computing node. The target computing node refers to a candidate computing node that the target cloud vendor wants to interrupt the service of. The type of the target computing node includes a bidding computing node, that is, a spot computing node, also known as a preemptible instance, a bidding instance, etc. The node interruption moment refers to a moment corresponding to when the target cloud vendor interrupts the client to continue using the target computing node service, for example, at XX day XX hour XX minute XX second, and the target cloud vendor interrupts the client to continue using the target computing node service, and takes "XX day XX hour XX minute XX second" as the node interruption moment.

[0035] In an embodiment, the target cloud vendor sends an interruption prompt information for the target computing node to the client through the constructed data center platform. The client receives the interruption prompt information sent by the data center platform, and parses the node interruption moment from the interruption prompt information. Further, the client obtains the latest current moment at this time, and calculates the time interval between the current moment and the node interruption moment, and then takes the calculated time interval as the node interruption waiting time. The node interruption waiting time can be understood as the waiting time reserved by the target cloud vendor for the client to evict the candidate container group from the current moment.

[0036] For example, assuming that the node interruption moment is "12 day 09 hour 10 minute 01 second", and the current moment is "12 day 09 hour 8 minute 01 second", the node interruption waiting time is "2 minutes", that is, the target cloud vendor reserves "2 minutes" for the client to evict the candidate container group from "12 day 09 hour 8 minute 01 second".

[0037] S102, determining a total eviction interval time for sequentially evicting each candidate container group according to the preset proportion value and the node interruption waiting time.

[0038] The candidate container group is a container group contained in the target computing node. The container group, also known as a POD, is the smallest deployable and manageable computing unit in a cluster. The container group is a combination of one or more containers, which share the same network namespace, storage volume, etc.

[0039] It can be understood that, since the client needs a certain time to perform the eviction operation on the candidate container group, if the eviction interval time for sequentially evicting each candidate container group is determined directly according to the node interruption waiting time and the number of container groups, the determined eviction interval time is unreasonable, and further, the problem that the target computing node has been interrupted when the candidate container group is not evicted completely occurs. For example, assuming that the node interruption waiting time is 120 seconds, and the number of container groups is 3, if the eviction interval time is directly calculated as 120 / 3 = 40 seconds according to the node interruption waiting time and the number of container groups, that is, the first candidate container group is evicted 40 seconds after the current time, the second candidate container group is evicted 40 seconds later, and the third candidate container group is evicted 40 seconds later. However, since the client needs a certain time to perform the eviction operation on the candidate container group, the total time required for the client to evict the third candidate container group is greater than 120 seconds, and at this time, the target computing node has been interrupted.

[0040] To avoid the above problem, a preset proportion value less than 1 needs to be introduced. The preset proportion value is determined according to the total time required for evicting each candidate container group, and specifically, the preset proportion value is determined according to the ratio between the difference between the node interruption waiting time and the total time and the node interruption waiting time. For example, assuming that the node interruption waiting time is 120 seconds, and the total time required for evicting each candidate container group is 30 seconds, the preset proportion value is (120-30) / 120 = 0.75.

[0041] In an embodiment, the client determines the total eviction interval time for sequentially evicting each candidate container group according to the product of the preset proportion value and the node interruption waiting time. The total eviction interval time refers to the sum of the eviction interval times for sequentially evicting each candidate container group. For example, assuming that there are 3 candidate container groups, the total eviction interval time refers to the sum of the eviction interval time 1, the eviction interval time 2, and the eviction interval time. The eviction interval time 1 refers to the eviction interval time from the current time to the start of evicting the candidate container group 1, the eviction interval time 2 refers to the eviction interval time from the completion of evicting the candidate container group 1 to the start of evicting the candidate container group 2, and the eviction interval time 3 refers to the eviction interval time from the completion of evicting the candidate container group 2 to the start of evicting the candidate container group 3.

[0042] S103, determine the eviction interval time for sequentially evicting each candidate container group according to the total eviction interval time and the number of container groups of the candidate container group, and perform the eviction operation on each candidate container group according to the eviction interval time.

[0043] The container group quantity of the candidate container group refers to the total quantity of the candidate container groups, for example, assuming that the target computing node contains candidate container group 1, candidate container group 2 and candidate container group 3, the container group quantity is '3'. The eviction interval time refers to the time interval at which the client performs the eviction operation on each candidate container group. For example, assuming that the eviction interval time is 20 seconds, after the client completes the eviction of candidate container group 1, the client performs the eviction operation on candidate container group 2 after an interval of 20 seconds.

[0044] In an embodiment, the client determines the eviction interval time according to the result of the division operation between the total eviction interval time and the container group quantity, and performs the eviction operation on each candidate container group in turn according to the eviction interval time.

[0045] For example, assuming that the target computing node contains candidate container group 1, candidate container group 2 and candidate container group 3, and the eviction interval time is 30 seconds, the client performs the eviction operation on candidate container group 1 after 30 seconds from the current time; the client performs the eviction operation on candidate container group 2 after 30 seconds from the completion of the eviction of candidate container group 1; and the client performs the eviction operation on candidate container group 3 after 30 seconds from the completion of the eviction of candidate container group 2.

[0046] The embodiment of the application determines the total eviction interval time for performing the eviction on each candidate container group in turn according to the preset proportion value and the node interruption waiting time, determines the eviction interval time for performing the eviction on each candidate container group in turn according to the total eviction interval time and the container group quantity of the candidate container group, and performs the eviction operation on each candidate container group in turn according to the eviction interval time, so that in the process of interruption of the target computing node by the cloud vendor, each candidate container group in the target computing node is evicted in turn at a certain interval time, rather than all candidate container groups being evicted at one time, which can avoid the instantaneous interruption of all services on the target computing node and improve the stability of the services implemented by the target computing node.

[0047] Embodiment two

[0048] Figure 2 A flowchart of a management method of a computing node is provided for the second embodiment of the application, the embodiment further optimizes and extends the above-mentioned embodiments and can be combined with each of the optional embodiments. As shown in Figure 2 The method comprises:

[0049] S201, in response to the interruption prompt information of the target cloud vendor for the target computing node, determining the node interruption time corresponding to the interruption operation of the target cloud vendor on the target computing node, and determining the node interruption waiting time according to the current time and the node interruption time.

[0050] S202, performing a multiplication operation according to the preset proportion value and the node interruption waiting time, and determining the total eviction interval time according to the multiplication operation result.

[0051] For example, assuming that the node interruption waiting time is 120 seconds and the preset proportion value is 75%, the total eviction interval time = 120 seconds x 75% = 90 seconds.

[0052] S203, performing a division operation according to the total eviction interval time and the container group quantity, and determining the eviction interval time according to the division operation result.

[0053] For example, assuming that the container group quantity is 3 and the total eviction interval time is 90 seconds, the eviction interval time = 90 seconds / 3 = 30 seconds.

[0054] By performing a multiplication operation according to the preset proportion value and the node interruption waiting time, and determining the total eviction interval time according to the multiplication operation result, and performing a division operation according to the total eviction interval time and the container group quantity, and determining the eviction interval time according to the division operation result, it can be avoided that the eviction interval time is directly determined according to the node interruption waiting time and the container group quantity, which will lead to unreasonable determination of the eviction interval time, and further lead to the problem that the target computing node has been interrupted for service when the candidate container group is not completed, thereby ensuring the rationality of the determination of the eviction interval time.

[0055] S204, determining the business influence score corresponding to each candidate container group, and determining the eviction priority corresponding to each candidate container group according to the business influence score.

[0056] The business influence score reflects the influence of the candidate container group on the business, that is, the higher the business influence score of any candidate container group, the greater the influence of the candidate container group on the business. The eviction priority of the candidate container group is inversely proportional to the business influence score corresponding thereto, that is, the higher the business influence score of any candidate container group, the lower the eviction priority of the candidate container group, that is, the later the eviction order.

[0057] In an embodiment, the client determines the business influence score corresponding to each candidate container group, sorts the business influence scores from large to small to obtain a business influence score sorting result, and then determines the reverse order of the business influence score sorting result as the eviction priority. For example, assuming that the business influence score sorting result is "candidate container group 3-candidate container group 2-candidate container group 1", the eviction priority is "candidate container group 1-candidate container group 2-candidate container group 3".

[0058] S205, performing the eviction operation on each candidate container group in turn according to the eviction priority and the eviction interval time.

[0059] For example, assuming that the eviction priority is "candidate container group 2-candidate container group 1-candidate container group 3" and the eviction interval time is "30 seconds", the eviction operation on the candidate container group 2 is started 30 seconds after the current time; the eviction operation on the candidate container group 1 is started 30 seconds after the candidate container group 2 is evicted; and the eviction operation on the candidate container group 3 is started 30 seconds after the candidate container group 1 is evicted.

[0060] By determining the service influence scores corresponding to the candidate container groups respectively, and determining the eviction priorities corresponding to the candidate container groups respectively according to the service influence scores, and sequentially performing the eviction operation on the candidate container groups according to the eviction priorities and the eviction interval time, the candidate container group with greater service influence is evicted later, and the stability of the target computing node is further ensured.

[0061] Optionally, in response to the interruption prompt information of the target cloud vendor for the target computing node, before the node interruption time corresponding to the interruption operation performed by the target cloud vendor on the target computing node, the method further includes:

[0062] A1, determining the node machine type corresponding to the to-be-applied computing node as a target node machine type, and determining the number of auxiliary computing nodes among the candidate computing nodes that have been applied.

[0063] The node machine type represents the machine type of the computing node, such as xlarge machine type, etc. The auxiliary computing node is a candidate computing node with the node machine type being the target node machine type.

[0064] For example, assuming that the target node machine type is "machine type 1", the client makes the candidate computing node with the node machine type "machine type 1" among the candidate computing nodes that have been applied as an auxiliary computing node, and then counts the number of auxiliary computing nodes.

[0065] A2, determining the node machine type proportion according to the number of nodes and the total number of nodes of the candidate computing nodes, and applying the to-be-applied computing node to the target cloud vendor in a case where the node machine type proportion is less than or equal to a first proportion threshold.

[0066] The first proportion threshold can be set and adjusted according to actual business needs. The first proportion threshold is used to determine whether the node machine type proportion is too large, that is, when the node machine type proportion is greater than the first proportion threshold, it indicates that the node machine type proportion is too large.

[0067] In an embodiment, a ratio between the number of client computing nodes and a total number of nodes of the candidate computing nodes is taken as a node machine type proportion, and the node machine type proportion is compared with a first proportion threshold value, and in a case where the node machine type proportion is less than or equal to the first proportion threshold value, the to-be-applied computing node is applied to the target cloud vendor; in a case where the node machine type proportion is greater than the first proportion threshold value, the to-be-applied computing node is stopped from being applied to the target cloud vendor.

[0068] A3, in a case where the application is successful, the to-be-applied computing node is taken as a new candidate computing node.

[0069] In an embodiment, in a case where the to-be-applied computing node is successfully applied, the to-be-applied computing node becomes an applied node, and then the client takes the to-be-applied computing node as a new candidate computing node.

[0070] By determining a node machine type corresponding to the to-be-applied computing node as a target node machine type, and determining a number of nodes of auxiliary computing nodes in the applied candidate computing nodes; wherein the auxiliary computing nodes are candidate computing nodes whose node machine types are the target node machine type; according to the number of nodes and a total number of nodes of the candidate computing nodes, a node machine type proportion is determined, and in a case where the node machine type proportion is less than or equal to a first proportion threshold value, the to-be-applied computing node is applied to the target cloud vendor; in a case where the application is successful, the to-be-applied computing node is taken as a new candidate computing node, so that the to-be-applied computing node is applied to the target cloud vendor only when the node machine type proportion is small, thereby avoiding a problem that when the number of candidate computing nodes of the same node machine type is too large, all candidate computing nodes of the same node machine type are easily interrupted at the same time when the computing nodes are interrupted, which seriously affects the stability of business implementation, and further ensuring the stability of business implementation of the computing nodes.

[0071] Optionally, applying the to-be-applied computing node to the target cloud vendor comprises:

[0072] A21, determining a node type corresponding to the to-be-applied computing node.

[0073] The node type comprises a first node type and a second node type, and a node fee of the first node type is lower than a node fee of the second node type. For example, the first node type can be a spot node type, and the second node type can be an on-demand node type.

[0074] A22, applying the to-be-applied computing node of the first node type to the target cloud vendor, and in a case where the application fails, applying the to-be-applied computing node of the second node type to the target cloud vendor.

[0075] For example, assume that the first node type is a spot node type and the second node type is an on-demand node type. The client first applies to the target cloud vendor for the to-be-applied computing node of the spot node type. If the application for the to-be-applied computing node of the spot node type fails, the client then applies to the target cloud vendor for the to-be-applied computing node of the on-demand node type.

[0076] It can be understood that the node cost of the first node type is lower than the node cost of the second node type, and accordingly, the application difficulty of the first node type is greater than the application difficulty of the second node type.

[0077] A23, in the case of successful application, the to-be-applied computing node of the second node type is taken as the first candidate computing node, and the application for the to-be-applied computing node of the first node type is continued.

[0078] For example, if the to-be-applied computing node of the on-demand node type is successfully applied, the to-be-applied computing node of the on-demand node type that is successfully applied is taken as the first candidate computing node. At the same time, the client still continues to apply to the target cloud vendor for the to-be-applied computing node of the spot node type.

[0079] A24, in the case of successful application, the to-be-applied computing node of the first node type is taken as the second candidate computing node, and the first candidate computing node is returned to the target cloud vendor.

[0080] For example, if the to-be-applied computing node of the spot node type is successfully applied, the client takes the to-be-applied computing node of the spot node type that is successfully applied as the second candidate computing node, and returns the first candidate computing node (the to-be-applied computing node of the on-demand node type that is successfully applied) to the target cloud vendor, so as to realize the effect of replacing the first candidate computing node with the second candidate computing node.

[0081] The application further provides a computing node management method, which comprises the following steps: determining a node type corresponding to the to-be-applied computing node; the node type comprises a first node type and a second node type, and the node cost of the first node type is lower than that of the second node type; applying the to-be-applied computing node of the first node type to the target cloud manufacturer, and in the case of application failure, applying the to-be-applied computing node of the second node type to the target cloud manufacturer; in the case of application success, taking the to-be-applied computing node of the second node type as a first candidate computing node, and continuing to apply the to-be-applied computing node of the first node type to the target cloud manufacturer; and in the case of application success, taking the to-be-applied computing node of the first node type as a second candidate computing node, and returning the first candidate computing node to the target cloud manufacturer. On the one hand, the to-be-applied computing node of the second node type is applied when the to-be-applied computing node of the first node type fails to be applied, thereby ensuring the redundancy of the application of the computing node; on the other hand, the to-be-applied computing node of the first node type is still applied when the to-be-applied computing node of the second node type is successfully applied, so that the to-be-applied computing node of the second node type is replaced by the to-be-applied computing node of the first node type when the to-be-applied computing node of the first node type is successfully applied, thereby further reducing the computing cost.

[0082] Optionally, all container groups in a pending state (waiting for scheduling) are scanned and resource requirements are calculated at intervals, such as 10s, for example, 2 container groups of 2 cores / 4 GB require a computing node of 4 cores / 8 G, and at this time, the cloud manufacturer API is called to apply for a computing node with the lowest price.

[0083] Optionally, the client will apply for 10% more computing resources as a backup according to the user's configuration, such as the desire to reserve 10% of the computing resources, which can effectively improve the startup speed of the container group.

[0084] Embodiment three

[0085] Figure 3 A flowchart of a computing node management method provided by the third embodiment of the application, which further optimizes and extends the above-mentioned embodiments and can be combined with the above-mentioned optional embodiments. As shown in the figure, the method comprises the following steps: Figure 3

[0086] S301, in response to the interruption prompt information of the target cloud manufacturer for the target computing node, determining the node interruption time corresponding to the interruption operation of the target cloud manufacturer on the target computing node, and determining the node interruption waiting time according to the current time and the node interruption time.

[0087] S302, performing a product operation according to the preset proportion value and the node interruption waiting time, and determining the total expulsion interval time according to the product operation result.

[0088] ​S303, performing division operation according to the total time of the eviction interval and the number of the container groups, and determining the eviction interval time according to the result of the division operation.

[0089] S304, determining the service types of the services to which the candidate container groups respectively belong, and determining the target eviction order of performing the eviction operation on the candidate container groups according to the service types.

[0090] The service types of the services to which the candidate container groups respectively belong indicate the classification of the services to which the candidate container groups belong. It can be understood that the services to which different candidate container groups belong can be of the same service type or different service types.

[0091] Since the candidate container groups corresponding to the same service type are continuously evicted, the stability of the services of the same service type can be greatly affected. Therefore, the candidate container groups corresponding to the same service type in the target eviction order should not be adjacent.

[0092] S305, performing the eviction operation on the candidate container groups according to the target eviction order and the eviction interval time in sequence.

[0093] In an embodiment, the client performs the eviction operation on the candidate container groups according to the target eviction order and the eviction interval time in sequence.

[0094] By determining the service types of the services to which the candidate container groups respectively belong, and determining the target eviction order of performing the eviction operation on the candidate container groups according to the service types, and performing the eviction operation on the candidate container groups according to the target eviction order and the eviction interval time in sequence, the problem that the candidate container groups corresponding to the same service type are continuously evicted, which can greatly affect the stability of the services of the same service type, can be avoided, and the stability of the services implemented by the target computing node is further ensured.

[0095] Optionally, the method further comprises:

[0096] B1, determining the total amount of node resources corresponding to each candidate computing node, and the amount of used resources corresponding to each container group in each candidate computing node, and determining the resource usage proportion corresponding to each candidate computing node according to the total amount of node resources and the amount of used resources.

[0097] The total amount of node resources refers to the total amount of resources that can be controlled by the candidate computing node, and the amount of used resources refers to the amount of resources used by the container group.

[0098] In an implementation, the client determines the total amount of node resources corresponding to each candidate computing node respectively, and the amount of used resources corresponding to each container group in each candidate computing node. Further, the client determines the ratio between the amount of used resources and the total amount of node resources as the resource usage ratio corresponding to each candidate computing node respectively.

[0099] B2, the candidate computing node with the resource usage ratio less than or equal to the second ratio threshold is taken as a to-be-scheduled computing node, and whether there is another computing node that can place the to-be-scheduled container group is determined according to the node scheduling strategy.

[0100] The to-be-scheduled container group is a container group contained in any to-be-scheduled computing node, and the other computing node is any candidate computing node except the to-be-scheduled computing node. The second ratio threshold can be set and adjusted according to actual business needs.

[0101] In an implementation, the client compares the resource usage ratio corresponding to each candidate computing node respectively with the second ratio threshold, and takes the candidate computing node with the resource usage ratio less than or equal to the second ratio threshold as a to-be-scheduled computing node. Further, the client determines whether there is another computing node that can place the to-be-scheduled container group according to the node scheduling strategy.

[0102] B3, if there is, the to-be-scheduled container group is scheduled in the other computing node, and the to-be-scheduled computing node is returned to the cloud vendor to which the to-be-scheduled computing node belongs.

[0103] In an implementation, if there is another computing node that can place the to-be-scheduled container group, the client schedules the to-be-scheduled container group in the other computing node, and returns the to-be-scheduled computing node to the cloud vendor to which the to-be-scheduled computing node belongs.

[0104] By determining the total amount of node resources corresponding to each candidate computing node respectively, and the amount of used resources corresponding to each container group in each candidate computing node, and determining the resource usage ratio corresponding to each candidate computing node respectively according to the total amount of node resources and the amount of used resources, the candidate computing node with the resource usage ratio less than or equal to the second ratio threshold is taken as a to-be-scheduled computing node, and whether there is another computing node that can place the to-be-scheduled container group is determined according to the node scheduling strategy. The to-be-scheduled container group is a container group contained in any to-be-scheduled computing node, and the other computing node is any candidate computing node except the to-be-scheduled computing node. If there is, the to-be-scheduled container group is scheduled in the other computing node, and the to-be-scheduled computing node is returned to the cloud vendor to which the to-be-scheduled computing node belongs. The effect that the container group in the computing node with low resource utilization is scheduled in another computing node, and the computing node with low resource utilization is actively returned to the cloud vendor is achieved, and the computing cost is further reduced.

[0105] Optionally, further comprising:

[0106] C1, determine the candidate CPU utilization corresponding to each candidate computing node respectively, and take the candidate computing node with the candidate CPU utilization less than the utilization threshold as the to-be-optimized computing node.

[0107] The utilization threshold is used to determine whether the candidate CPU utilization is too low, that is, when the candidate CPU utilization of any candidate computing node is less than the utilization threshold, it indicates that the candidate CPU utilization of the candidate computing node is too low, and the candidate computing node is taken as the to-be-optimized computing node. The to-be-optimized computing node can be understood as a candidate computing node that needs to improve the candidate CPU utilization.

[0108] C2, according to the candidate CPU utilization corresponding to the to-be-optimized computing node and the correlation between the CPU utilization and the CPU scheduling coefficient, determine the target CPU scheduling coefficient corresponding to the to-be-optimized computing node.

[0109] The CPU scheduling coefficient is a coefficient for expanding the scheduling capability of the CPU. For example, assuming that the CPU scheduling coefficient is 1.5, the 2-core CPU originally schedules a 2-core container group, and through the optimization of the CPU scheduling coefficient, the 2-core CPU can schedule a 3-core container group, so as to further improve the CPU utilization.

[0110] The CPU utilization and the CPU scheduling coefficient are inversely proportional, that is, the lower the CPU utilization, the larger the CPU scheduling coefficient; the higher the CPU utilization, the smaller the CPU scheduling coefficient. The CPU scheduling coefficient is greater than or equal to 1.

[0111] In an embodiment, the client matches the candidate CPU utilization corresponding to the to-be-optimized computing node with the correlation between the CPU utilization and the CPU scheduling coefficient, and determines the CPU scheduling coefficient associated with the candidate CPU utilization as the target CPU scheduling coefficient. For example, assuming that the candidate CPU utilization is "30%", and the CPU utilization "30%" and the CPU scheduling coefficient "1.5" have a correlation in the correlation between the CPU utilization and the CPU scheduling coefficient, then the CPU scheduling coefficient "1.5" is taken as the target CPU scheduling coefficient.

[0112] C3, according to the CPU core number of the to-be-optimized computing node, determine the current core number of the container group currently schedulable by the CPU of the to-be-optimized computing node, and according to the product result between the target CPU scheduling coefficient and the current core number, determine the optimization core number.

[0113] In an embodiment, the client determines the CPU core number of the to-be-optimized computing node as the current core number of the container group currently schedulable by the CPU of the to-be-optimized computing node. For example, assuming that the CPU core number of the to-be-optimized computing node is “2”, the current core number of the container group currently schedulable by the CPU of the to-be-optimized computing node is also “2”, that is, a 2-core CPU schedules a 2-core container group.

[0114] The client performs a multiplication operation on the current core number and the target CPU scheduling coefficient, and determines the optimized core number of the container group schedulable by the CPU of the to-be-optimized computing node after optimization according to the multiplication operation result. For example, assuming that the current core number is “2” and the target CPU scheduling coefficient is “1.5”, the optimized core number is 1.5×2=3, that is, a 2-core CPU can schedule a 3-core container group.

[0115] C4, control the CPU of the to-be-optimized computing node to schedule a container group with the optimized core number.

[0116] By determining the candidate CPU utilization corresponding to each candidate computing node, and taking the candidate computing node with a candidate CPU utilization less than the utilization threshold as the to-be-optimized computing node; according to the candidate CPU utilization corresponding to the to-be-optimized computing node, and the correlation between the CPU utilization and the CPU scheduling coefficient, determining the target CPU scheduling coefficient corresponding to the to-be-optimized computing node; wherein the CPU utilization and the CPU scheduling coefficient are inversely proportional, and the CPU scheduling coefficient is greater than or equal to 1; according to the CPU core number of the to-be-optimized computing node, determining the current core number of the container group currently schedulable by the CPU of the to-be-optimized computing node, and according to the multiplication result between the target CPU scheduling coefficient and the current core number, determining the optimized core number; controlling the CPU of the to-be-optimized computing node to schedule a container group with the optimized core number, thereby improving the CPU utilization of the low-CPU-utilization computing node and ensuring the computing task processing efficiency of the computing node.

[0117] Embodiment four

[0118] Figure 4 A structural schematic diagram of a computing node management device provided by the fourth embodiment of the present application is shown in FIG. 4. As shown in the figure, the device comprises: Figure 4

[0119] The time determination module 41 is configured to determine the node interruption time corresponding to the interruption operation performed by the target cloud vendor on the target computing node in response to the interruption prompt information of the target cloud vendor for the target computing node, and determine the node interruption waiting time according to the current time and the node interruption time.

[0120] ​The eviction interval total time determination module 42 is configured to determine an eviction interval total time for sequentially evicting each candidate container group according to a preset ratio value and a node interruption waiting time, wherein the candidate container group is a container group contained in the target computing node, the preset ratio value is determined according to a total time consumption of evicting each candidate container group, and the preset ratio value is less than 1.

[0121] The container group eviction module 43 is configured to determine an eviction interval time for sequentially evicting each candidate container group according to the eviction interval total time and a container group quantity of the candidate container group, and perform an eviction operation on each candidate container group according to the eviction interval time.

[0122] Optionally, the eviction interval total time determination module 42 is specifically configured to:

[0123] perform a multiplication operation according to the preset ratio value and the node interruption waiting time, and determine the eviction interval total time according to a multiplication operation result;

[0124] The eviction interval total time determination module 42 is specifically further configured to:

[0125] perform a division operation according to the eviction interval total time and the container group quantity, and determine the eviction interval time according to a division operation result.

[0126] Optionally, the container group eviction module 43 is specifically configured to:

[0127] determine a business influence score corresponding to each candidate container group respectively, and determine an eviction priority corresponding to each candidate container group respectively according to the business influence score;

[0128] perform an eviction operation on each candidate container group according to the eviction priority and the eviction interval time.

[0129] Optionally, the container group eviction module 43 is specifically configured to:

[0130] determine a business type of a business to which each candidate container group respectively belongs, and determine a target eviction order of performing an eviction operation on each candidate container group according to the business type, wherein the candidate container groups corresponding to a same business type in the target eviction order are not adjacent;

[0131] perform an eviction operation on each candidate container group according to the eviction interval time in the target eviction order.

[0132] Optionally, the apparatus further includes a computing node application module, which is specifically configured to:

[0133] determine a node machine type corresponding to the to-be-applied computing node as a target node machine type, and determine a number of auxiliary computing nodes in the applied candidate computing nodes; the auxiliary computing nodes are the candidate computing nodes whose node machine types are the target node machine type;

[0134] determine a node machine type proportion according to the number and a total number of nodes of the candidate computing nodes, and apply the to-be-applied computing node to a target cloud vendor when the node machine type proportion is less than or equal to a first proportion threshold;

[0135] in a case of successful application, the to-be-applied computing node is used as a new candidate computing node.

[0136] Optionally, the computing node application module is specifically configured to:

[0137] determine a node type corresponding to the to-be-applied computing node; the node type includes a first node type and a second node type, and a node cost of the first node type is lower than a node cost of the second node type;

[0138] apply the to-be-applied computing node of the first node type to a target cloud vendor, and apply the to-be-applied computing node of the second node type to the target cloud vendor in a case of failed application;

[0139] in a case of successful application, the to-be-applied computing node of the second node type is used as a first candidate computing node, and the to-be-applied computing node of the first node type is continuously applied to the target cloud vendor;

[0140] in a case of successful application, the to-be-applied computing node of the first node type is used as a second candidate computing node, and the first candidate computing node is returned to the target cloud vendor.

[0141] Optionally, the device further includes a container group scheduling module, which is specifically configured to:

[0142] determine a total amount of node resources corresponding to each candidate computing node, and an amount of used resources corresponding to each container group in each candidate computing node, and determine a resource amount use proportion corresponding to each candidate computing node according to the total amount of node resources and the amount of used resources;

[0143] the candidate computing node whose resource quantity usage proportion is less than or equal to the second proportion threshold value is taken as a to-be-scheduled computing node, and it is determined according to a node scheduling strategy whether there is another computing node that can place a to-be-scheduled container group; the to-be-scheduled container group is a container group contained by any of the to-be-scheduled computing nodes, and the another computing node is any of the candidate computing nodes other than the to-be-scheduled computing node;

[0144] If there is, the to-be-scheduled container group is scheduled in the another computing node, and the to-be-scheduled computing node is returned to the cloud vendor to which the to-be-scheduled computing node belongs.

[0145] Optionally, the device further comprises a CPU scheduling optimization module, which is specifically configured to:

[0146] determine candidate CPU utilization rates corresponding to the candidate computing nodes respectively, and take the candidate computing node whose candidate CPU utilization rate is less than a utilization rate threshold value as a to-be-optimized computing node;

[0147] determine a target CPU scheduling coefficient corresponding to the to-be-optimized computing node according to the candidate CPU utilization rate corresponding to the to-be-optimized computing node and an association relationship between a CPU utilization rate and a CPU scheduling coefficient; the CPU utilization rate is inversely proportional to the CPU scheduling coefficient, and the CPU scheduling coefficient is greater than or equal to 1;

[0148] determine a current core number of a container group that can be currently scheduled by a CPU of the to-be-optimized computing node according to a CPU core number of the to-be-optimized computing node, and determine an optimized core number according to a product result between the target CPU scheduling coefficient and the current core number;

[0149] control a CPU scheduling core number of the to-be-optimized computing node to be the optimized core number of the container group.

[0150] The computing node management device provided in the embodiments of the application can execute the computing node management method provided in any of the embodiments of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0151] Embodiment five

[0152] Figure 5A schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0153] like Figure 5 As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded into the RAM 53 from storage unit 58. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0154] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0155] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as methods for managing computing nodes.

[0156] In some embodiments, the management method of the computing node can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 58. In some embodiments, parts or all of the computer program can be loaded onto the electronic device 50 via, e.g., ROM 52 and / or communication unit 59. When the computer program is loaded onto RAM 53 and executed by processor 51, one or more steps of the above-described management method of the computing node can be performed. Alternatively, in other embodiments, processor 51 can be configured to perform the management method of the computing node by any other suitable means, e.g., by means of firmware.

[0157] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0158] Computer programs used to implement the processes of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as part of a separate software package, or entirely on a remote machine or server.

[0159] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0160] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0161] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0162] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0163] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0164] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A management method of a computing node, characterized by, The method comprises the following steps: in response to the target cloud vendor interrupt prompt information for the target computing node, determining the node interrupt time corresponding to the interrupt operation performed by the target cloud vendor on the target computing node, and determining the node interrupt waiting time according to the current time and the node interrupt time; determining the total eviction interval time of the candidate container groups according to the preset proportion value and the node interrupt waiting time; wherein, the candidate container groups are the container groups contained in the target computing node, the preset proportion value is determined according to the total time consumption of the eviction of the candidate container groups, and the preset proportion value is less than 1; determining the eviction interval time of the candidate container groups according to the total eviction interval time and the number of container groups of the candidate container groups, and performing the eviction operation on the candidate container groups according to the eviction interval time; wherein, the total eviction interval time of the candidate container groups according to the preset proportion value and the node interrupt waiting time comprises: performing multiplication operation according to the preset proportion value and the node interrupt waiting time, and determining the total eviction interval time according to the multiplication operation result; the total eviction interval time and the number of container groups of the candidate container groups, and determining the eviction interval time of the candidate container groups according to the total eviction interval time and the number of container groups of the candidate container groups. the eviction operation on the candidate container groups according to the eviction interval time comprises:

2. The method of claim 1, wherein, determining the business influence score corresponding to each candidate container group respectively, and determining the eviction priority of each candidate container group according to the business influence score; performing the eviction operation on the candidate container groups according to the eviction priority and the eviction interval time. the eviction operation on the candidate container groups according to the eviction interval time comprises:

3. The method of claim 1, wherein, determining the business type of the business to which each candidate container group belongs respectively, and determining the target eviction order of the eviction operation on the candidate container groups according to the business type; wherein, the candidate container groups corresponding to the same business type in the target eviction order are not adjacent; performing the eviction operation on the candidate container groups according to the target eviction order and the eviction interval time.

4. The method of claim 1, wherein, before the step of determining the node interrupt time corresponding to the interrupt operation performed by the target cloud vendor on the target computing node in response to the target cloud vendor interrupt prompt information for the target computing node, the method further comprises: determining the node machine type corresponding to the to-be-applied computing node as the target node machine type, and determining the number of auxiliary computing nodes in the candidate computing nodes that have been applied; wherein, the auxiliary computing nodes are the candidate computing nodes whose node machine type is the target node machine type. ​ determine a node machine type proportion according to the number of nodes and a total number of nodes of the candidate computing nodes, and apply the to-be-applied computing nodes to a target cloud vendor if the node machine type proportion is less than or equal to a first proportion threshold; return the to-be-applied computing nodes to the target cloud vendor if the application is successful.

5. The method of claim 4, wherein the applying the to-be-applied computing nodes to the target cloud vendor comprises: determining a node type corresponding to the to-be-applied computing nodes; wherein the node type comprises a first node type and a second node type, and a node fee of the first node type is lower than a node fee of the second node type; applying the to-be-applied computing nodes of the first node type to the target cloud vendor, and applying the to-be-applied computing nodes of the second node type to the target cloud vendor if the application is unsuccessful; returning the to-be-applied computing nodes of the second node type to the target cloud vendor if the application is successful, and continuing to apply the to-be-applied computing nodes of the first node type to the target cloud vendor; returning the to-be-applied computing nodes of the first node type to the target cloud vendor if the application is successful.

6. The method of claim 4, further comprising: determining a total amount of node resources corresponding to each of the candidate computing nodes, and an amount of used resources corresponding to each container group in each of the candidate computing nodes, and determining a resource amount usage proportion corresponding to each of the candidate computing nodes according to the total amount of node resources and the amount of used resources; returning the candidate computing nodes with a resource amount usage proportion less than or equal to a second proportion threshold as to-be-scheduled computing nodes, and determining whether there is another computing node that can place a to-be-scheduled container group according to a node scheduling strategy; wherein the to-be-scheduled container group is a container group contained in any of the to-be-scheduled computing nodes, and the another computing node is any of the candidate computing nodes other than the to-be-scheduled computing nodes; if there is, scheduling the to-be-scheduled container group in the another computing node, and returning the to-be-scheduled computing node to a cloud vendor to which the to-be-scheduled computing node belongs.

7. The method of claim 4, further comprising: determining a candidate CPU utilization corresponding to each of the candidate computing nodes, and returning the candidate computing nodes with a candidate CPU utilization less than a utilization threshold as to-be-optimized computing nodes; determining a target CPU scheduling coefficient corresponding to the to-be-optimized computing nodes according to the candidate CPU utilization corresponding to the to-be-optimized computing nodes and an association between a CPU utilization and a CPU scheduling coefficient; wherein the CPU utilization and the CPU scheduling coefficient are inversely proportional, and the CPU scheduling coefficient is greater than or equal to 1. determining a current core number of a container group currently schedulable by a CPU of the to-be-optimized computing node according to a number of CPU cores of the to-be-optimized computing node, and determining an optimized core number according to a product result between the target CPU scheduling coefficient and the current core number; controlling the CPU scheduling core number of the to-be-optimized computing node to be the optimized core number of the container group.

8. A management apparatus of a computing node, characterized by, comprise: a time determining module configured to, in response to interrupt prompt information of a target cloud vendor for a target computing node, determine a node interrupt time corresponding to an interrupt operation performed by the target cloud vendor on the target computing node, and determine a node interrupt waiting time according to a current time and the node interrupt time; an eviction interval total time determining module configured to determine an eviction interval total time for sequentially performing eviction on each candidate container group according to a preset proportion value and the node interrupt waiting time, wherein the candidate container groups are container groups contained in the target computing node, the preset proportion value is determined according to a total time consumption of performing eviction on the each candidate container group, and the preset proportion value is less than 1; a container group eviction module configured to determine an eviction interval time for sequentially performing eviction on each candidate container group according to the eviction interval total time and a container group number of the candidate container group, and perform eviction operation on the each candidate container group according to the eviction interval time; wherein the eviction interval total time determining module is specifically configured to: perform multiplication operation according to the preset proportion value and the node interrupt waiting time, and determine the eviction interval total time according to a multiplication operation result; the container group eviction module is specifically configured to: perform division operation according to the eviction interval total time and the container group number, and determine the eviction interval time according to a division operation result.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the management method of the computing node in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the management method of the computing node in any one of claims 1-7.

11. A computer program product comprising a computer program which, when executed by a processor, implements the management method of the computing node according to any one of claims 1-7.

Images