A cluster resource management method, device, equipment and readable storage medium

Abstract

The present application discloses a cluster resource management method, apparatus, device and readable storage medium, the method comprising: detecting whether the current available resource amount of the cluster is less than a first threshold; if so, expelling the applications in descending order of the expulsion index according to the predetermined expulsion index of each application until the current available resource amount is greater than a second threshold; predetermining the expulsion index of each application comprises: determining the expulsion index of each application according to the acquired importance level and resource allocation amount of each application; the expulsion index of an application with a high importance level is lower than the expulsion index of an application with a low importance level. The above technical solution disclosed in the present application preferentially expels low-importance applications when cluster resources are insufficient according to the predetermined expulsion index of each application, so that cluster resources can be released, thereby meeting the resource usage requirements of high-importance applications, and ensuring the stability and reliability of the operation of high-importance applications.

Description

Technical Field

[0001] The present application relates to, more specifically, a cluster resource management method, apparatus, device and readable storage medium. Background Art

[0002] In the era of cloud computing, more and more business applications are managed uniformly through cloud platforms, and cloud platforms can manage clusters.

[0003] At present, there are more and more application instances running in the clusters managed by cloud platforms. When a cluster managed by a cloud platform runs a large number of application instances and the cluster resources cannot be expanded in time, it is impossible to ensure that important applications can have enough configuration resources to run stably in the cluster.

[0004] In summary, how to ensure the stability of the operation of important applications is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] In view of this, the purpose of the present application is to provide a cluster resource management method, apparatus, device and readable storage medium to ensure the stability of the operation of important applications.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] A cluster resource management method, comprising:

[0008] Detect whether the current available resources of the cluster are less than a first threshold;

[0009] If yes, then according to the predetermined eviction index of each application in the cluster, evict the applications in descending order of the eviction index until the current available resource amount is greater than the second threshold;

[0010] The eviction index of each of the applications is predetermined, including:

[0011] Obtain the importance level and resource allocation amount of each application in the cluster, and determine the eviction index of each application according to the importance level and resource allocation amount of each application; the eviction index of an application with a high importance level is lower than the eviction index of an application with a low importance level.

[0012] Preferably, determining the eviction index of each application according to the importance level and resource allocation amount of each application includes:

[0013] Determine the eviction index range corresponding to each of the applications according to the importance level of each of the applications and a plurality of preset eviction index ranges; wherein the eviction index range of an application with a high importance level is lower than the eviction index range of an application with a low importance level;

[0014] The eviction index of each application in the same eviction index range is determined according to the resource configuration amount of each application in the same eviction index range; wherein the eviction index of the application with a large resource configuration amount is higher than the eviction index of the application with a small resource configuration amount.

[0015] Preferably, when determining the eviction index of each of the applications within the same eviction index range according to the resource allocation amount of each of the applications within the same eviction index range, it further includes:

[0016] If there is an application with unlimited resource configuration within the same eviction index range, the highest eviction index is configured for the application with unlimited resource configuration within the eviction index range.

[0017] Preferably, the applications are evicted in descending order of eviction index, including:

[0018] The application instances of the corresponding applications are evicted in descending order of the eviction index.

[0019] Preferably, it also includes:

[0020] The information of the evicted application instance is recorded.

[0021] Preferably, it also includes:

[0022] The information of the expelled application instance is sent to the mobile terminal.

[0023] A cluster resource management device, comprising:

[0024] A detection module, used to detect whether the current available resources of the cluster are less than a first threshold;

[0025] an eviction module, configured to evict applications in a descending order of eviction indexes according to predetermined eviction indexes of applications in the cluster if the current available resource amount of the cluster is less than the first threshold, until the current available resource amount is greater than a second threshold;

[0026] The cluster resource management device further includes a determination module for predetermining an eviction index of each of the applications, the determination module including:

[0027] The determination unit is used to obtain the importance level and resource allocation amount of each application in the cluster, and determine the eviction index of each application according to the importance level and resource allocation amount of each application; the eviction index of an application with a high importance level is lower than the eviction index of an application with a low importance level.

[0028] Preferably, the determining unit includes:

[0029] A first determining subunit is used to determine an eviction index range corresponding to each of the applications according to the importance level of each of the applications and a plurality of preset eviction index ranges; wherein the eviction index range of an application with a high importance level is lower than the eviction index range of an application with a low importance level;

[0030] The second determining subunit is used to determine the eviction index of each of the applications within the same eviction index range according to the resource configuration amount of each of the applications within the same eviction index range; wherein the eviction index of the application with a large resource configuration amount is higher than the eviction index of the application with a small resource configuration amount.

[0031] A cluster resource management device, comprising:

[0032] Memory for storing computer programs;

[0033] A processor is used to implement the steps of the cluster resource management device as described in any one of the above when executing a computer program.

[0034] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the cluster resource management method as described in any one of the above are implemented.

[0035] The present application provides a cluster resource management method, apparatus, device and readable storage medium, wherein the method includes: detecting whether the current available resource amount of the cluster is less than a first threshold; if so, according to the predetermined eviction index of each application in the cluster, eviction of the application in descending order of the eviction index until the current available resource amount is greater than a second threshold; predetermining the eviction index of each application, including: obtaining the importance level and resource allocation amount of each application in the cluster, and determining the eviction index of each application according to the importance level and resource allocation amount of each application; the eviction index of an application with a high importance level is lower than the eviction index of an application with a low importance level.

[0036] The above-mentioned technical solution disclosed in the present application determines the eviction index of each application in advance according to the importance level and resource configuration amount of each application in the cluster obtained, and the eviction index of the application with a high importance level is lower than the eviction index of the application with a low importance level. When it is detected that the current available resource amount of the cluster is less than the first threshold, the applications are evicted in descending order of the eviction index until the current available resource amount of the cluster is greater than the second threshold, so that the resources of the cluster are released by preferentially evicting the applications with low importance levels, so that the current available resources of the cluster are increased, so that the current available resources of the cluster can meet the usage requirements of the applications with high importance levels, so as to ensure the stability and reliability of the applications with high importance levels running in the cluster. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0038] Figure 1 A flow chart of a cluster resource management method provided in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of the structure of a cluster resource management device provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of the structure of a cluster resource management device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The core of this application is to provide a cluster resource management method, device, equipment and readable storage medium to ensure the stability of the operation of important applications in the cluster.

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] See also Figure 1 , which shows a flow chart of a cluster resource management method provided by an embodiment of the present application. The cluster resource management method provided by an embodiment of the present application may include:

[0044] S11: Obtain in advance the importance level and resource allocation amount of each application in the cluster.

[0045] In this application, the cloud platform can obtain in advance the importance level of all applications in the cluster it manages and the resource allocation of all applications. Among them, the importance level of all applications in the cluster can be determined according to the functions implemented by the applications. For example, the importance level of an application that stores data is higher than the importance level of an application that serves as an entry.

[0046] S12: Determine the eviction index of each application according to the importance level and resource allocation amount of each application; the eviction index of an application with a high importance level is lower than the eviction index of an application with a low importance level.

[0047] Based on step S11, the cloud platform can determine the eviction index of each application according to the acquired importance level of each application in the cluster and the resource allocation amount of each application, wherein the higher the eviction index is, the higher the possibility of the application being evicted is. After the above operation, it is determined that the eviction index of the application with a high importance level is lower than the eviction index of the application with a low importance level, that is, the possibility of eviction of the application with a high importance level is lower than the possibility of eviction of the application with a low importance level.

[0048] It should be noted that the above-mentioned steps S11 and S12 are the process of predetermining the eviction index of each application in the cluster. For each cluster, if the applications contained therein remain unchanged, the process can be executed only once, so that it does not need to be executed every time cluster resource management is performed. Of course, if the applications in the cluster increase or the resource configuration changes, the process of steps S11 and S12 can be re-executed to update the eviction index of the application, thereby improving the accuracy of determining the eviction index of each application.

[0049] S13: Detect whether the current available resource amount of the cluster is less than a first threshold; if so, execute step S14.

[0050] The cloud platform can detect in real time or periodically whether the current available resources of the cluster are less than the first threshold, wherein the size of the first threshold can be set according to actual needs. If it is determined that the current available resources of the cluster are less than the first threshold, it indicates that the cluster is short of resources, and at this time, step S14 can be executed. If it is determined that the current available resources of the cluster are not less than the first threshold, it indicates that the cluster is not short of resources, and at this time, step S13 can be returned to implement monitoring of the current available resources of the cluster, so as to promptly discover the shortage of cluster resources.

[0051] S14: according to the predetermined eviction index of each application in the cluster, evict the applications in descending order of the eviction index until the current available resource amount is greater than the second threshold.

[0052] If it is determined that the current available resources of the cluster are less than the first threshold, the eviction index of each application in the cluster can be predetermined, and the applications can be evicted in order of the eviction index from high to low to release the resources occupied by the evicted applications, thereby increasing the current available resources of the cluster, and each time an application is evicted, it is determined whether the current available resources of the cluster are greater than the second threshold. If not, the applications are continued to be evicted in order of the eviction index from high to low. If so, the eviction of the applications is terminated, that is, the applications are evicted in order of the eviction index from high to low until the current available resources of the cluster are greater than the second threshold. Among them, the second threshold is greater than the first threshold, and the second threshold can be specifically set according to the amount of resources required by applications with high importance levels in the cluster, so that after some applications with low eviction indexes are evicted, the current available resources of the cluster can meet the resource usage requirements of applications with high importance levels, so that applications with high importance levels can have sufficient resources in the cluster and run stably.

[0053] The above-mentioned technical solution disclosed in the present application determines the eviction index of each application in advance according to the importance level and resource configuration amount of each application in the cluster obtained, and the eviction index of the application with a high importance level is lower than the eviction index of the application with a low importance level. When it is detected that the current available resource amount of the cluster is less than the first threshold, the applications are evicted in descending order of the eviction index until the current available resource amount of the cluster is greater than the second threshold, so that the resources of the cluster are released by preferentially evicting the applications with low importance levels, so that the current available resources of the cluster are increased, so that the current available resources of the cluster can meet the usage requirements of the applications with high importance levels, so as to ensure the stability and reliability of the applications with high importance levels running in the cluster.

[0054] A cluster resource management method provided in an embodiment of the present application determines the eviction index of each application according to the importance level and resource allocation amount of each application, which may include:

[0055] Determine the eviction index range corresponding to each application according to the importance level of each application and a plurality of preset eviction index ranges; wherein the eviction index range of an application with a high importance level is lower than the eviction index range of an application with a low importance level;

[0056] The eviction index of each application within the same eviction index range is determined according to the resource configuration amount of each application within the same eviction index range; wherein the eviction index of an application with a large resource configuration amount is higher than the eviction index of an application with a small resource configuration amount.

[0057] In the present application, when determining the eviction index of each application according to the importance level and resource allocation amount of each application, the eviction index range corresponding to each application can be determined according to the importance level of each application and a plurality of preset eviction index ranges, and when determining the eviction index range corresponding to each application, the eviction index range of the application with a high importance level is lower than the eviction index range of the application with a low importance level, wherein the eviction index range of the application with a high importance level mentioned here is lower than the eviction index range of the application with a low importance level, that is, the maximum eviction index in the eviction index range of the application with a high importance level is smaller than the maximum eviction index in the eviction index range of the application with a low importance level. The minimum eviction index in the index range, that is, the higher the importance level of the application, the lower the eviction index in the corresponding eviction index range. For example, 10 eviction index ranges are preset: -999 to -800, -799 to -600, ..., 800-999. Assuming that an existing service consists of three applications, namely, portal A, core B, and data storage C, and the importance levels of these three applications increase in sequence, it can be determined that the eviction index range of the data storage C application is -999 to -800, the eviction index range of the core B application is -799 to -600, and the eviction index range of the portal A application is -599 to -400.

[0058] On the basis of the above, if there are multiple applications corresponding to the same eviction index range, the eviction index of each application in the same eviction index range is determined according to the resource allocation of each application in the same eviction index range, and when determining, the eviction index of the application with a large resource allocation is higher than the eviction index of the application with a small resource allocation, that is, the greater the resource allocation, the greater the possibility of being evicted, so that more available resources can be released through eviction. For example, for the eviction index range of -599 to -400, if in addition to the corresponding application entry A, there is also a corresponding application D, then by comparing the resource allocation of the two applications A and D, assuming that the resource allocation of application A is smaller, it can be determined that the eviction index of application A is -599 and the resource allocation of application D is -598.

[0059] It should be noted that if there are multiple applications corresponding to the same eviction index range and there are applications with the same resource configuration amount in the multiple applications, then according to the above process, it can be known that the eviction indexes of the applications in the same eviction index range and with the same resource configuration amount are the same. In addition, if there is only one application corresponding to an eviction index range, any eviction index in the eviction index range can be determined as the eviction index of the application. Of course, for the sake of simplicity, the eviction index corresponding to the left endpoint of the eviction index range can be determined as the eviction index of the application. For example, if there is only one application data storage C in the eviction index range of -999 to -800, -999 can be determined as the eviction index of the application data storage C.

[0060] A cluster resource management method provided by an embodiment of the present application may further include: determining the eviction index of each application within the same eviction index range according to the resource configuration amount of each application within the same eviction index range;

[0061] If there are applications with unlimited resource configuration within the same eviction index range, the highest eviction index is configured for the applications with unlimited resource configuration within the eviction index range.

[0062] In the present application, when determining the eviction index of each application within the same eviction index range according to the resource configuration amount of each application within the same eviction index range, if there is an application with unlimited resource configuration amount within the same eviction index range, then within the eviction index range where the application with unlimited resource configuration amount is located, the highest eviction index is configured for the application with unlimited resource configuration amount. For example, in the eviction index range of -599 to -400, if there is an application with unlimited resource configuration amount, the eviction index of the application is determined to be -400.

[0063] Since the resources of applications with unlimited resource configuration are not limited and may be very low or very high and unstable, a high eviction index is configured for them so that applications with unlimited resource configuration can be given priority when eviction is needed to avoid unstable resource application, thereby ensuring that applications with high importance levels can have sufficient resources to run in the cluster, thereby improving the stability and reliability of the operation of applications with high importance levels.

[0064] A cluster resource management method provided by an embodiment of the present application evicts applications in descending order of eviction index, which may include:

[0065] The application instances of the corresponding applications are evicted in descending order of the eviction index.

[0066] In the present application, when the application is evicted in descending order of the eviction index, the application instances contained in the application can be evicted in descending order of the eviction index, wherein one application corresponds to multiple application instances. By evicting the application instances, the occupation of cluster resources is reduced to increase the current available resources of the cluster.

[0067] A cluster resource management method provided in an embodiment of the present application may further include:

[0068] The information of the evicted application instance is recorded.

[0069] In the present application, when an application instance of an application is expelled, the information of the expelled application instance can be recorded, specifically, the function provided by the expelled application instance, the application to which the expelled application instance belongs, the size of the expulsion index of the application, etc. can be recorded, so that relevant personnel can subsequently query the information of the expelled application instance.

[0070] A cluster resource management method provided in an embodiment of the present application may further include:

[0071] The information of the expelled application instance is sent to the mobile terminal.

[0072] In the present application, when recording the information of the expelled application instance, the information of the expelled application instance can also be sent to the mobile terminal, so that relevant personnel can obtain the expelled application instance in time through the mobile terminal.

[0073] Of course, the information of the expelled application instance can be displayed on the cloud platform, so that relevant personnel can obtain the information of the expelled application instance through the cloud platform.

[0074] The present application also provides a cluster resource management device. Figure 2 , which shows a schematic diagram of the structure of a cluster resource management device provided in an embodiment of the present application, which may include:

[0075] A detection module 21, used to detect whether the current available resources of the cluster are less than a first threshold;

[0076] The eviction module 22 is configured to evict applications in a descending order of eviction indexes according to predetermined eviction indexes of applications in the cluster if the current available resources of the cluster are less than the first threshold, until the current available resources are greater than the second threshold;

[0077] The cluster resource management device may further include a determination module 23 for predetermining an eviction index of each application. The determination module 23 may include:

[0078] The determination unit is used to obtain the importance level and resource allocation amount of each application in the cluster, and determine the eviction index of each application according to the importance level and resource allocation amount of each application; the eviction index of an application with a high importance level is lower than the eviction index of an application with a low importance level.

[0079] In a cluster resource management device provided in an embodiment of the present application, the determining unit may include:

[0080] A first determining subunit is used to determine an eviction index range corresponding to each application according to the importance level of each application and a plurality of preset eviction index ranges; wherein the eviction index range of an application with a high importance level is lower than the eviction index range of an application with a low importance level;

[0081] The second determining subunit is used to determine the eviction index of each application within the same eviction index range according to the resource configuration amount of each application within the same eviction index range; wherein the eviction index of the application with a large resource configuration amount is higher than the eviction index of the application with a small resource configuration amount.

[0082] In a cluster resource management device provided in an embodiment of the present application, the determining unit may further include:

[0083] The configuration subunit is used to determine the eviction index of each application within the same eviction index range according to the resource configuration amount of each application within the same eviction index range, and if there is an application with unlimited resource configuration amount within the same eviction index range, then configure the highest eviction index for the application with unlimited resource configuration amount within the eviction index range.

[0084] In a cluster resource management device provided in an embodiment of the present application, the eviction module 22 may include:

[0085] The eviction unit is used to evict application instances in the corresponding application in descending order of eviction indexes.

[0086] In a cluster resource management device provided in an embodiment of the present application, the eviction module 22 may further include:

[0087] The recording unit is used to record information of the evicted application instance.

[0088] In a cluster resource management device provided in an embodiment of the present application, the eviction module 22 may further include:

[0089] The sending unit is used to send the information of the expelled application instance to the mobile terminal.

[0090] The present application also provides a cluster resource management device. Figure 3, which shows a schematic diagram of the structure of a cluster resource management device provided in an embodiment of the present application, which may include:

[0091] A memory 31, used for storing computer programs;

[0092] The processor 32 can implement the following steps when executing the computer program stored in the memory 31:

[0093] Detect whether the current available resource amount of the cluster is less than a first threshold; if so, evict the applications in descending order of the eviction index according to the predetermined eviction index of each application in the cluster until the current available resource amount is greater than a second threshold; predetermine the eviction index of each application, including: obtain the importance level and resource allocation amount of each application in the cluster, and determine the eviction index of each application according to the importance level and resource allocation amount of each application; the eviction index of an application with a high importance level is lower than the eviction index of an application with a low importance level.

[0094] The present application also provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the following steps can be implemented:

[0095] Detect whether the current available resource amount of the cluster is less than a first threshold; if so, evict the applications in descending order of the eviction index according to the predetermined eviction index of each application in the cluster until the current available resource amount is greater than a second threshold; predetermine the eviction index of each application, including: obtain the importance level and resource allocation amount of each application in the cluster, and determine the eviction index of each application according to the importance level and resource allocation amount of each application; the eviction index of an application with a high importance level is lower than the eviction index of an application with a low importance level.

[0096] The readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0097] For the description of the relevant parts of a cluster resource management apparatus, device and readable storage medium provided in the embodiments of the present application, reference may be made to the detailed description of the relevant parts of a cluster resource management method provided in the embodiments of the present application, which will not be repeated here.

[0098] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment that includes a series of elements are inherent to the elements. In the absence of more restrictions, the elements limited by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or equipment that includes the elements. In addition, the above-mentioned technical solution provided in the embodiment of the present application is consistent with the corresponding technical solution in the prior art in principle, and the part is not described in detail, so as not to repeat too much.

[0099] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A cluster resource management method, characterized in that: include: Detect whether the current available resources of the cluster are less than a first threshold; If yes, then according to the predetermined eviction index of each application in the cluster, evict the applications in descending order of the eviction index until the current available resource amount is greater than the second threshold; The eviction index of each of the applications is predetermined, including: Obtaining the importance level and resource allocation amount of each application in the cluster, and determining the eviction index of each application according to the importance level and resource allocation amount of each application; the eviction index of an application with a high importance level is lower than the eviction index of an application with a low importance level; The second threshold is a threshold set according to the amount of resources required by applications with high importance levels in the cluster, and the second threshold is greater than the first threshold; The eviction index of each application is determined according to the importance level and resource allocation amount of each application, including: Determine the eviction index range corresponding to each of the applications according to the importance level of each of the applications and a plurality of preset eviction index ranges; wherein the eviction index range of an application with a high importance level is lower than the eviction index range of an application with a low importance level; Determining the eviction index of each of the applications within the same eviction index range according to the resource configuration amount of each of the applications within the same eviction index range; wherein the eviction index of the application with a large resource configuration amount is higher than the eviction index of the application with a small resource configuration amount; Among them, the applications are evicted in descending order of eviction index, including: Evict application instances from the corresponding application in descending order of eviction index; Wherein, the cluster resource management method further includes: Recording information of the evicted application instance; wherein the information of the application instance includes a function provided by the application instance, an application to which the application instance belongs, and an eviction index corresponding to the application to which the application belongs; Wherein, the cluster resource management method further includes: Sending information of the expelled application instance to a mobile terminal; Wherein, the cluster resource management method further includes: If multiple applications in the same eviction index range have the same resource configuration, the eviction indexes of the multiple applications are the same; if the same eviction index range corresponds to only one application, any eviction index in the eviction index range is determined as the eviction index of the application; Wherein, the cluster resource management method further includes: If there are changes such as an increase in applications within the cluster or a change in resource allocation, the step of obtaining the importance level and resource allocation of each application in the cluster and determining the eviction index of each application based on the importance level and resource allocation of each application is executed.

2. The cluster resource management method according to claim 1, characterized in that: When determining the eviction index of each of the applications within the same eviction index range according to the resource allocation amount of each of the applications within the same eviction index range, the method further includes: If there is an application with unlimited resource configuration within the same eviction index range, the highest eviction index is configured for the application with unlimited resource configuration within the eviction index range.

3. A cluster resource management device, characterized in that: include: A detection module, used to detect whether the current available resources of the cluster are less than a first threshold; an eviction module, configured to evict applications in a descending order of eviction indexes according to predetermined eviction indexes of applications in the cluster if the current available resource amount of the cluster is less than the first threshold, until the current available resource amount is greater than a second threshold; The cluster resource management device further includes a determination module for predetermining an eviction index of each of the applications, the determination module including: a determination unit, configured to obtain the importance level and resource allocation amount of each application in the cluster, and determine the eviction index of each application according to the importance level and resource allocation amount of each application; the eviction index of an application with a high importance level is lower than the eviction index of an application with a low importance level; The second threshold is a threshold set according to the amount of resources required by applications with high importance levels in the cluster, and the second threshold is greater than the first threshold; Wherein, the determining unit includes: A first determining subunit is used to determine an eviction index range corresponding to each of the applications according to the importance level of each of the applications and a plurality of preset eviction index ranges; wherein the eviction index range of an application with a high importance level is lower than the eviction index range of an application with a low importance level; A second determining subunit is used to determine the eviction index of each of the applications within the same eviction index range according to the resource configuration amount of each of the applications within the same eviction index range; wherein the eviction index of the application with a large resource configuration amount is higher than the eviction index of the application with a small resource configuration amount; Wherein, the expulsion module includes: An eviction unit, used to evict application instances in the corresponding application in descending order of eviction index; Wherein, the expulsion module further includes: A recording unit, configured to record information of the evicted application instance; wherein the information of the application instance includes a function provided by the application instance, an application to which the application instance belongs, and an evicting index corresponding to the application to which the application belongs; Wherein, the expulsion module further includes: a sending unit, configured to send information of the expelled application instance to a mobile terminal; Wherein, the cluster resource management device is specifically used for: If multiple applications in the same eviction index range have the same resource configuration, the eviction indexes of the multiple applications are the same; if the same eviction index range corresponds to only one application, any eviction index in the eviction index range is determined as the eviction index of the application; Wherein, the cluster resource management device is specifically used for: If there are changes such as an increase in applications within the cluster or a change in resource allocation, the step of obtaining the importance level and resource allocation of each application in the cluster and determining the eviction index of each application based on the importance level and resource allocation of each application is executed.

4. A cluster resource management device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the cluster resource management device as claimed in any one of claims 1 to 2 when executing a computer program.

5. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the cluster resource management method according to any one of claims 1 to 2 are implemented.

Images