CN111522636A - Application container adjusting method, application container adjusting system, computer readable medium and terminal device - Google Patents
Application container adjusting method, application container adjusting system, computer readable medium and terminal device Download PDFInfo
- Publication number
- CN111522636A CN111522636A CN202010258218.2A CN202010258218A CN111522636A CN 111522636 A CN111522636 A CN 111522636A CN 202010258218 A CN202010258218 A CN 202010258218A CN 111522636 A CN111522636 A CN 111522636A
- Authority
- CN
- China
- Prior art keywords
- standby node
- target
- application
- container
- capacity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
Abstract
The invention discloses an adjusting method, an adjusting system, a computer readable medium and a terminal device of an application container, wherein the adjusting method of the application container comprises the following steps: acquiring running data of a virtual host corresponding to a target container application, wherein the running data comprises performance data and resource utilization rate; determining metric configuration data for the target container application based on the performance data; and scheduling the capacity of the application container based on the relation between the resource utilization rate and the index configuration data. The method and the system for adjusting the application container flexibly realize the dynamic adjustment of the capacity of the application container, thereby improving the running efficiency of the application program and the utilization rate of resources.
Description
Technical Field
The present invention relates to the technical field of computer resource allocation management, and in particular, to an adjustment method and an adjustment system for an application container, a computer-readable medium, and a terminal device.
Background
Early enterprises deployed applications directly on physical machines. Because resource usage boundaries cannot be defined for applications on a physical machine, it is difficult to reasonably allocate computing resources. For example, when multiple applications run on the same physical machine, one of the applications may consume most of the computing resources, so that the other applications may not run normally. However, if each application program is run on a different physical machine, the application program is too large to be implemented, which results in a low resource utilization rate and a high maintenance cost for the physical machine.
In view of the above, there is a need for an improved running environment technology for application programs in the prior art to solve the above problems.
Disclosure of Invention
The invention aims to disclose an application container adjusting method, an application container adjusting system, a computer readable medium and a terminal device, which are used for flexibly realizing dynamic adjustment of the capacity of an application container so as to improve the running efficiency of an application program and the utilization rate of resources.
In order to solve the technical problem, the invention is realized as follows:
in a first aspect, a method for adjusting an application container is provided, including:
acquiring running data of a virtual host corresponding to a target container application, wherein the running data comprises performance data and resource utilization rate;
determining metric configuration data for the target container application based on the performance data;
and scheduling the capacity of the application container based on the relation between the resource utilization rate and the index configuration data.
As a further improvement of the present invention, the scheduling the capacity of the application container based on the index configuration data comprises:
when the capacity expansion condition is met, determining whether a standby node added to the Kubernetes cluster exists or not;
if a first standby node which is added into a Kubernetes cluster exists, a target container group which has a mapping relation with the target container application is created based on the first standby node;
and if a second standby node which is not added to the Kubernets cluster exists, adding the second standby node to the Kubernets cluster and creating a target container group with a mapping relation with the target container application based on the second standby node.
As a further improvement of the present invention,
creating a target container group having a mapping relationship with the target container application based on the first standby node, including:
traversing the first standby nodes to determine a first target one of the first standby nodes;
creating the target container group on the first target standby node when the resources on the first target standby node satisfy a condition.
As a further improvement of the present invention, traversing the first standby node to determine a first target standby node in the first standby node specifically includes:
traversing the first standby node based on resource levels, wherein the resource levels comprise sufficient resources, general resources and insufficient resources;
and determining the standby node with sufficient resource level in the first standby node as the first target standby node.
As a further improvement of the present invention, traversing the first standby node to determine a first target standby node in the first standby node specifically includes:
traversing the first standby node based on a time order in which the first standby node joins a Kubernets cluster;
and determining the standby node which is added to the Kubernets cluster in the first standby node and has the earliest time as the first target standby node.
As a further improvement of the present invention, the scheduling the capacity of the application container based on the index configuration data comprises:
when capacity reduction conditions are met, determining whether a standby node added to a Kubernetes cluster exists or not;
and if a third standby node added to the Kubernetes cluster exists, selecting a third target standby node in the third standby node, and removing the mapping relation between the target container application and the target container group on the third target standby node.
As a further improvement of the present invention, the index configuration data includes an expansion threshold, a contraction threshold, a first preset ratio and a second preset ratio, the resource utilization includes a first ratio m1 and a second ratio n1, the first ratio m1 is m/t, the second ratio n1 is n/t, t is the number of acquisition times per unit time, m is the number of times exceeding the expansion threshold, and n is the number of times lower than the contraction threshold;
wherein scheduling the capacity of the application container based on the relationship between the resource utilization and the indicator configuration data comprises:
executing capacity expansion logic if the first ratio is higher than a first preset ratio;
and if the second ratio is higher than a second preset ratio, executing the capacity reduction logic.
As a further improvement of the present invention, after obtaining the operation data of the virtual host corresponding to the target container application and before determining the index configuration data of the target container application based on the performance data, the method further includes:
and storing the operation data of the virtual host corresponding to the target container application.
As a further improvement of the invention, the method also comprises the following steps:
saving an event that schedules a capacity of the application container.
In a second aspect, there is provided a tuning system for an application container, comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring operation data of a virtual host corresponding to a target container application, and the operation data comprises performance data and resource utilization rate;
a determining unit, configured to obtain index configuration data of the target container application based on the performance data;
and the scheduling unit is used for scheduling the capacity of the application container based on the relation between the resource utilization rate and the index configuration data.
As a further improvement of the invention, the method also comprises the following steps:
the capacity expansion unit is used for determining whether a standby node added to the Kubernetes cluster exists or not when capacity expansion conditions are met;
a creating unit, configured to create, if there is a first standby node joining a kubernets cluster, a target container group having a mapping relationship with the target container application based on the first standby node;
and if a second standby node which is not added to the Kubernets cluster exists, adding the second standby node to the Kubernets cluster and creating a target container group with a mapping relation with the target container application based on the second standby node.
As a further improvement of the present invention, the creating unit is configured to:
traversing the first standby nodes and determining a first target one of the first standby nodes to create the target container group on the first target standby node when resources on the first target standby node satisfy a condition.
As a further improvement of the present invention, the creating unit is further configured to:
traversing the first standby node based on resource levels, and determining a standby node of the first standby node, of which the resource level is sufficient, as the first target standby node, so as to create the target container group when the resource on the first target standby node meets conditions, wherein the resource levels include sufficient resources, general resources and insufficient resources.
As a further improvement of the present invention, the creating unit is further configured to:
traversing the first standby node based on the time sequence of joining the Kubernets cluster by the first standby node, and determining the standby node which is joined to the Kubernets cluster in the first standby node and has the earliest time as the first target standby node, so as to create the target container group when the resource on the first target standby node meets the condition.
As a further improvement of the invention, the method also comprises the following steps:
the capacity reduction unit is used for determining whether a standby node added to the Kubernetes cluster exists or not when capacity reduction conditions are met;
and the releasing unit is used for selecting a third target standby node in a Kubernetes cluster if a third standby node added to the Kubernetes cluster exists, and releasing the mapping relation between the target container application and the target container group on the standby node.
As a further improvement of the present invention, the index configuration data includes an expansion threshold, a contraction threshold, a first preset ratio and a second preset ratio, the resource utilization includes a first ratio m1 and a second ratio n1, the first ratio m1 is m/t, the second ratio n1 is n/t, t is the number of acquisition times per unit time, m is the number of times exceeding the expansion threshold, and n is the number of times lower than the contraction threshold;
the scheduling unit is configured to:
executing capacity expansion logic if the first ratio is higher than a first preset ratio;
if the second ratio is higher than a second preset ratio, executing capacity reduction logic;
wherein the first preset ratio is lower than the second preset ratio.
As a further improvement of the invention, the method also comprises the following steps:
and the first storage device is used for storing the running data of the virtual host corresponding to the target container application.
As a further improvement of the invention, the method also comprises the following steps:
and the second storage device is used for storing the event for scheduling the capacity of the application container.
In a third aspect, a computer-readable medium is provided, in which computer program instructions are stored, and when the computer program instructions are read and executed by a processor, the steps in the method for adjusting the capacity of an application container according to the first aspect are performed.
In a fourth aspect, a terminal device is provided, which includes a processor, a memory, and a computer program stored on the memory and executable on the processor, and when executed by the processor, the computer program implements the steps of the method for adjusting the capacity of an application container according to the first aspect.
Compared with the prior art, the invention has the following beneficial effects:
the method for adjusting the application container obtains corresponding index configuration data by obtaining performance data in the running data of the virtual host corresponding to the target container application, and adjusts the capacity of the application container according to the relationship between the resource utilization rate in the running data and the index configuration data. Therefore, the method for adjusting the application container can realize the dynamic adjustment of the application container according to the resource utilization rate and the index configuration data of the container application, not only can flexibly realize the dynamic adjustment of the capacity of the application container so as not to influence the normal operation of other application programs, thereby improving the operation efficiency of the application programs, but also does not need to ensure that each application program must operate on different physical machines, thereby improving the utilization rate of resources.
Drawings
FIG. 1 is a flow chart of a method for tuning an application container according to an embodiment of the present invention;
FIG. 2 is a flow chart of an adjustment method for an application container according to another embodiment of the present invention;
FIG. 3 is a flow chart of a tuning method of an application container according to yet another embodiment of the present invention;
FIG. 4 is a flow chart of a tuning method of an application container according to yet another embodiment of the present invention;
FIG. 5 is a topological structure diagram of an adaptation system of an application container according to still another embodiment of the present invention;
FIG. 6 is a topological structure diagram of an adaptation system of an application container according to another embodiment of the present invention;
FIG. 7 is a topology structure diagram of a standby node in the present invention;
FIG. 8 is a block diagram of a topology of a computer readable medium according to the present disclosure;
fig. 9 is a topology structure diagram of a terminal device according to the disclosure.
Detailed Description
The present invention is described in detail with reference to the embodiments shown in the drawings, but it should be understood that these embodiments are not intended to limit the present invention, and those skilled in the art should understand that functional, methodological, or structural equivalents or substitutions made by these embodiments are within the scope of the present invention.
Before describing in detail the various embodiments of the present invention, the core inventive concepts of the present invention are summarized and described in detail by the following several embodiments.
Term "QPS"refers to the query rate per second.
Term "Kubernetes": is an open source for managing containerized applications on multiple hosts in a cloud platform.
Term "Service"refers to a virtual host, which is a Service discovery mechanism in Kubernets, and can provide Pod meeting Service specification conditions to a Service caller as a Service accessible through a network. Each Service in the embodiment of the invention corresponds to a group of Pods containing the same application container.
Term "Pod"refer to a Container group, which is an abstract concept in Kubernets, and is the most basic unit on a cluster, for storing a set of containers (a set of containers contains one or more Container containers), and some shared resources of the containers. The Pod container group of the embodiment of the present invention includes a specific container application (i.e., a service application).
The applicant intends to bring the invention to the details of the specific technical solutions contained in the present invention by showing several examples below.
The first embodiment is as follows:
fig. 1 is a schematic flow chart of an application container adjustment method (hereinafter, referred to as "method" or "adjustment method") according to an embodiment of the present invention, so as to flexibly implement dynamic adjustment of the capacity of an application container. The method for adjusting the application container is applied to an adjustment system of the application container, and the adjustment system of the application container is applied to the field of distributed application systems. The adjusting method of the application container comprises the following steps:
and 102, acquiring the running data of the virtual host (namely Service) corresponding to the target container application. Wherein the operational data includes performance data and resource usage. The performance data includes CPU usage, memory usage, and throughput, among others.
The running data of the Kubernets cluster can be obtained through the Kubernets watch API, and the performance data of the virtual host (Service) is obtained from the running data of the Kubernets cluster.
And 104, determining index configuration data of the target container application based on the performance data.
In the embodiment of the present invention, the index configuration data includes an expansion threshold, a contraction threshold, a first preset ratio, and a second preset ratio. Specifically, the index configuration data mainly includes a capacity reduction threshold of the CPU usage, a capacity expansion threshold of the CPU usage, a capacity reduction threshold of the memory usage, a capacity expansion threshold of the memory usage, a duty ratio of the CPU usage higher than the threshold, a duty ratio of the CPU usage lower than the threshold, a duty ratio of the memory usage higher than the threshold, a duty ratio of the memory usage lower than the threshold, a QPS threshold of the target host POD, a duty ratio of the QPS higher than the threshold, a determination criterion of the index (such as CPU, memory, or QPS), and the like. And the index configuration data is also determined in a manual designation mode.
The resource utilization rate comprises a first ratio m1 and a second ratio n1, wherein the first ratio m1 is m/t, the second ratio n1 is n/t, t is the collection times per unit time, m is the times exceeding the capacity expansion threshold, and n is the times lower than the capacity reduction threshold.
And 106, scheduling the capacity of the application container based on the relation between the resource utilization rate and the index configuration data.
It should be understood that, in the method for adjusting an application container according to the embodiment of the present invention, performance data in running data of a virtual host (Service) corresponding to a target container application is obtained to obtain corresponding index configuration data, and a capacity of the application container is adjusted according to a relationship between a resource usage rate in the running data and the index configuration data. Therefore, the method for adjusting the application container in the embodiment of the invention can realize dynamic adjustment of the application container according to the resource utilization rate and the index configuration data of the container application, not only can flexibly realize dynamic adjustment of the capacity of the application container so as not to influence the normal operation of other application programs, thereby improving the operation efficiency of the application programs, but also does not need to ensure that each application program must operate on different physical machines, thereby improving the utilization rate of resources.
Specifically, in a scenario where a change such as a sudden increase in service request is large, for example, whenever a holiday (for example, a dueleven period, a preferential activity may be shown on a treasure), the access volume or the traffic flow of the e-commerce may increase accordingly, and at this time, the load pressure of the server increases, which may result in a slow response of the service or even an inability to provide the service normally. The method of the embodiment of the invention can adaptively adjust the capacity of the server according to the operation data of the Kubernets cluster, so as to improve the operation efficiency of the application program under the condition of not influencing the normal operation of other application programs in the server and improve the utilization rate of resources. In this embodiment, the "resource" includes, but is not limited to, a computing resource, a storage resource, a network resource, a physical resource, etc. responding to the service request.
Specifically, the scheduling the capacity of the application container based on the relationship between the resource utilization rate and the index configuration data includes:
if the first ratio m1 is higher than a first preset ratio, executing capacity expansion logic; if the second ratio n1 is higher than a second predetermined ratio, the reduction logic is executed.
The calculation rule between the CPU and the memory may specifically be:
taking the CPU as an example, assuming that the capacity expansion threshold of the CPU utilization in the index configuration data is 70%, and the CPU utilization is higher than the threshold percentage by 50%, it can be understood that the capacity expansion condition is reached when the CPU utilization is higher than 70% in a time period exceeding 50%.
The capacity reduction threshold of the CPU utilization is 20%, and the CPU utilization is lower than the threshold percentage by 80%, which can be understood as reaching the capacity reduction condition when the CPU utilization is lower than 20% in the time exceeding 80%.
Therefore, if the calculated result m1 obtained by the percentage value of 50% (namely the first preset percentage value) is more than 50% according to the capacity expansion threshold value (70%) of the CPU utilization rate, capacity expansion logic is executed; if the calculated result n1 obtained according to the shrinkage threshold (20%) of the CPU utilization rate accounts for 80% (i.e., the second preset ratio) is greater than 80%, the shrinkage logic is executed.
Therefore, the method of the embodiment of the invention can rapidly realize the dynamic adjustment of the capacity of the application container according to the resource utilization rate and the index configuration data of the container application without manual intervention, thereby not only improving the running efficiency of the application program, but also avoiding that each application program must run on different physical machines so as to improve the utilization rate of the resource.
As shown in fig. 2, in the foregoing embodiment, in the step of scheduling the capacity of the application container based on the indicator configuration data, the operation when the capacity expansion condition is met to execute the capacity expansion logic may include:
And step 204, if a first standby node which is added into the Kubernets cluster exists, creating a target container group which has a mapping relation with the target container application on the basis of the first standby node. And if a second standby node which is not added to the Kubernets cluster exists, adding the second standby node to the Kubernets cluster and creating a target container group which has a mapping relation with the target container application based on the second standby node.
It can be understood that, in the embodiment of the present invention, a container group including a target container application already exists in the virtual host, and for a situation that the capacity of an application container needs to be scheduled, the method for adjusting an application container in the embodiment of the present invention determines whether the application container needs to perform capacity expansion or capacity reduction by acquiring the operation data of the virtual host corresponding to the target container application. And under the condition that capacity expansion is needed, a target container group containing a target container application (the same as the existing target container application) is created to achieve the purpose of capacity expansion. In the case of capacity reduction, the target container group containing the target container application (the same as the existing target container application) is deleted to achieve the purpose of capacity reduction, and the specific capacity reduction process can be referred to the contents of "capacity reduction" described in the following embodiments.
In step 204, creating a target container group having a mapping relationship with the target container application based on the first standby node, including:
The operation of traversing the first standby node may specifically be: traversing the first standby node based on resource levels, wherein the resource levels comprise sufficient resources, general resources and insufficient resources; and determining the standby node with sufficient resource level in the first standby node as a first target standby node. It can be understood that, selecting a standby node with more sufficient resources to create a target container group can enable the container application opened on the standby node to provide better service, so as to improve the service effect of the container application.
Wherein, the resource grade can be set for the resource on the node according to the artificial mode. For example, the resources on a certain node are divided into three levels according to the proportion of the remaining resources on the node to the total resources, less than or equal to 10% of the remaining resources are set as insufficient resources, more than 10% and less than or equal to 30% of the remaining resources are set as general resources, and more than 30% of the remaining resources are set as sufficient resources. For another example, the resource is set according to the remaining resource amount on a certain node, the remaining resource amount of 1 or less is set as insufficient resource, the remaining resource amount of 1 or more and 5 or less is set as general resource, and the remaining resource amount of 5 or more is set as sufficient resource. Of course, the setting may be performed in other manners as long as the resource on the node can be ranked, and the scope of the present invention is not limited to the scope defined by the embodiment of the present invention.
Alternatively, the operation of traversing the first standby node may specifically be: traversing the first standby node based on the time sequence of the first standby node joining the Kubernets cluster; and determining the standby node which is added to the Kubernets cluster in the first standby node and has the earliest time as a first target standby node. Therefore, the container application can be started on the standby node which is added to the Kubernets cluster at the earliest as possible according to the time priority order, so that the service efficiency of the container application is improved.
Still alternatively, the operation of traversing the first standby node may specifically be: the first standby node is traversed based on the nature of the container application.
Wherein, the usage scenario of the standby node can be defined based on the property of the container application, so as to determine the standby node to create the target container group according to the usage scenario of the standby node. For example, for a container application with high IO, a standby node serving a low IO is not suitable for deploying more container applications with high IO, and thus, when traversing to such a standby node, such a standby node may not be selected as a standby node for creating a target container group. In this way, the service quality of the container application can be improved by traversing the first standby node according to the property of the container application to select the first target standby node from the first standby node for subsequent creation of the target container group.
When all the nodes in the first standby node are traversed in sequence according to the three modes, the standby node can be determined as the first target standby node as long as the standby node meeting the corresponding conditions is traversed.
In order to further optimize the determined first target standby node, the resource level can be considered at the same time, the time sequence of the first standby node joining the kubernets cluster is obtained, and the first standby node is traversed in three aspects of the property of container application, so that the optimal first target standby node is selected to be used for creating a target container group in the subsequent steps.
That is, as shown in fig. 3, the operation of traversing the first standby node may specifically include:
and 301, traversing the first standby node based on the time sequence of the first standby node joining the Kubernets cluster.
Therefore, the optimal first target standby node is determined by combining the resource level on the first standby node, the time sequence of the first standby node joining the Kubernets cluster and the property of the container application, and is used for creating the target container group, so that the service efficiency of the container application can be improved on the premise of improving the service effect or quality of the container application. The execution order of step 302 and step 303 may be reversed, and may be determined according to actual use requirements, and is not limited to the execution range defined by the embodiment of the present invention.
It should be noted that the resource level information marked on the first standby node, the time information added to the kubernets cluster, and the property information of the served container application are marked by human before traversing the first standby node. Wherein, for the standby node added to the kubernets cluster, the label information (i.e. resource level, nature of container application, time for joining the kubernets cluster) on the standby node can be updated (usually updated by means of manual label and the like) when the operation data in the kubernets cluster is collected.
It should be noted that, for example, the traversed and determined standby node already satisfies the resource condition for the container application requiring 1G of memory, but the determined standby node does not necessarily satisfy the resource condition for the container applications requiring 5G of memory, 10G of memory, and the like, and therefore, after the standby node on the first standby node is traversed and determined, it is still necessary to determine whether the resource of the standby node satisfies the condition.
The operation data according to the embodiment of the present invention further includes resource configuration data of the container application (name of the container application, and resource required by the container application, such as memory size, hard disk space size, and the like). And judging whether the resources on the standby node meet the conditions or not based on the resource configuration data of the container application. For example, the resource configuration data normally required by the container application is 1G memory, 30G hard disk space, and the like. At this time, the specific process of determining that the resource on the standby node satisfies the condition is that the remaining available resource memory of the standby node is greater than 1G, and the hard disk space is greater than 30G. The determination process as to whether the resource on the standby node satisfies the condition according to the embodiment of the present invention is the same, and is not described here.
It should be understood that each standby node is configured with a label (e.g., label node-bak-1), and when creating the target container group, the target container group is assigned to the corresponding standby node (label node-bak-1), which is equivalent to creating the target container group on the assigned standby node.
and 2044, selecting a second target standby node in the second standby nodes to join the Kubernets cluster. The method for selecting the second target standby node in the second standby node may adopt a method for traversing the first standby node to determine the first target standby node, and a specific implementation process is the same as or similar to an implementation principle for determining the first target standby node, which is not described in detail herein.
And 2046, when the resources on the second target standby node meet the conditions, creating a target container group on the second target standby node to achieve the purpose of capacity expansion.
The execution sequence of step 2044 and step 2045 may be exchanged, that is, when it is determined that there is a second standby node that does not join the kubernets cluster, whether the second standby node meets the resource condition is selected to be determined, and when it is determined that the resource of the second standby node meets the condition, one of the second standby nodes (i.e., a second target standby node) is selected to join the kubernets cluster, so as to create the target container group.
Before the operation of creating the target container group having a mapping relationship with the target container application based on the first standby node in step 204 is performed, the method may include:
Also, before performing the operation of joining the second standby node to the kubernets cluster and creating the target container group having a mapping relationship with the target container application based on the second standby node in step 204, the method may include:
In the above further embodiment, as shown in fig. 4, in the step of scheduling the capacity of the application container based on the indicator configuration data, the operation when the capacity expansion condition is met to execute the capacity expansion logic may include:
And 403, if a third standby node added to the Kubernetes cluster exists, selecting a third target standby node in the third standby node, and removing the mapping relation between the target container application and the target container group on the third target standby node.
Before selecting a third target standby node in the third standby nodes and removing the mapping relationship between the target container application and the target container group on the third target standby node, the operations may further include:
It should be noted that, in the process of executing the capacity reduction logic, when selecting the third target standby node in the third standby node, the rule is generally opposite to the rule for selecting the standby nodes (the first standby node and the second standby node as described in the foregoing embodiment) in the process of executing the capacity expansion logic (the node selection involved in the capacity reduction process is generally selected according to the time of joining the kubernets cluster). Specifically, when the third target standby node is selected from the third standby nodes, the standby node that has the latest time to join the kubernets cluster is selected as the third target standby node, thereby improving the service efficiency of the container application.
In any of the above embodiments, after obtaining the running data of the virtual host corresponding to the target container application, and before determining the metric configuration data of the target container application based on the performance data, the method further includes: and storing the running data of the virtual host corresponding to the target container application. Referring to fig. 5, the run data may be saved to a first storage device 503 (e.g., a database, a file system, a Redis cache, or a distributed storage system, etc.).
In addition, the method for adjusting the application container in the embodiment of the present invention further includes:
and step 108, storing the event for scheduling the capacity of the application container. Specifically, as described with reference to fig. 2, 4, and 5, the event that schedules the capacity of the application container may be stored in the second storage device 516, and the second storage device 516 may be a storage device such as a database or a device that stores the event in a log format.
Wherein, the event for scheduling the capacity of the application container includes but is not limited to: an event for expanding an application container, an event for contracting the application container, a capacity expanding instruction and a capacity contracting instruction issued by the system according to index configuration data, determining whether an event that a first standby node is added to a Kubernets cluster exists or not, determining whether an event that a second standby node is not added to the Kubernets cluster exists or not, determining whether an event that a third standby node is added to the Kubernets cluster exists or not, determining whether an event that a target container group having a mapping relation with a target container application exists or not on the third standby node, removing the event that the target container application and the target container group have a mapping relation on the third standby node, creating the target container group based on the first standby node or the second standby node to establish the event that the target container group and the target container application have a mapping relation, and an event that determines whether resources on the first standby node, the second standby node, the third standby node are sufficient, and the like.
In a specific embodiment, the implementation process of the adjustment method for an application container according to the embodiment of the present invention may be:
firstly, Kubernets cluster operation data are collected and recorded, so that performance data of a virtual host (Service) are obtained from the Kubernets cluster operation data, and index configuration data of target container application are determined according to the performance data of the virtual host. The system to which the method for adjusting an application container according to the embodiment of the present invention is applied is configured with available hosts (e.g., a first standby node, a second standby node, a third standby node, and the like), Kubernets cluster information (i.e., cluster information composed of base nodes), application service information, application service index configuration information, and the like.
Secondly, analyzing the acquired index configuration data to determine whether capacity expansion conditions or capacity reduction conditions are met. When the capacity expansion condition is met, the system can issue a capacity expansion instruction to execute capacity expansion logic. When the capacity reduction condition is met, the system issues a capacity reduction instruction to execute capacity reduction logic.
And when the capacity expansion logic is executed, analyzing whether the index configuration data has a standby node or not, and if not, not processing. If yes, determining whether the standby node is added into the Kubernets cluster, judging whether available resources exist in the current standby node under the condition that the standby node is added into the Kubernets cluster, and modifying the number of pod copies corresponding to Service under the condition that the available resources exist in the current standby node so as to achieve the purpose of capacity expansion.
When the capacity reduction logic is executed, whether the index configuration data has a standby node which is added into a Kubernets cluster or not is analyzed, if yes, whether the application of the current capacity reduction instruction is deployed on the standby node or not is determined, and if yes, the mapping relation between the target container application on the standby node and the target container group is deleted.
Therefore, the method for adjusting the application container can realize dynamic adjustment of the application container according to the resource utilization rate and the index configuration data of the container application, not only can flexibly realize dynamic adjustment of the capacity of the application container so as not to influence the normal operation of other application programs, thereby improving the operation efficiency of the application programs, but also does not need to ensure that each application program must operate on different physical machines, thereby improving the utilization rate of resources.
Example two:
as shown in fig. 5, based on the inventive idea included in the adjustment method of an application container disclosed in the first embodiment, the present embodiment further provides an adjustment system 500 of an application container, including: an obtaining unit 502, configured to obtain operation data of a virtual host corresponding to a target container application, where the operation data includes performance data and a resource utilization rate; a determining unit 504, configured to obtain index configuration data of the target container application based on the performance data; and a scheduling unit 506, configured to schedule the capacity of the application container based on a relationship between the resource usage rate and the index configuration data. The obtaining unit 502 may be a Kubernets watch API, so as to obtain the operation data of the Kubernets cluster 501 through the Kubernets watch API, so as to obtain the performance data of the virtual host 5011 (i.e., Service) from the operation data of the Kubernets cluster 501.
The index configuration data comprises an expansion threshold, a contraction threshold, a first preset ratio and a second preset ratio, the resource utilization rate comprises a first ratio m1 and a second ratio n1, the first ratio m1 is equal to m/t, the second ratio n1 is equal to n/t, t is the collection frequency of unit time, m is the frequency exceeding the expansion threshold, and n is the frequency lower than the contraction threshold. The scheduling unit 506 is configured to: if the first ratio m1 is higher than a first preset ratio, executing capacity expansion logic; if the second ratio n1 is higher than a second predetermined ratio, the reduction logic is executed.
In the system 500 for adjusting an application container according to the embodiment of the present invention, the determining unit 504 obtains corresponding index configuration data according to performance data in the operation data of the virtual host (service) corresponding to the target container application acquired by the acquiring unit 502, so that the scheduling unit 506 adjusts the capacity of the application container according to the resource utilization rate and the index configuration data in the operation data. Thus, the system 500 for adjusting an application container according to the embodiment of the present invention can implement dynamic adjustment of the application container according to the resource utilization rate and the index configuration data of the container application, and not only flexibly implement dynamic adjustment of the capacity of the application container so as not to affect normal operation of other application programs, thereby improving the operation efficiency of the application programs, but also does not need to make each application program operate on different physical machines, thereby improving the utilization rate of resources.
It should be noted that, as shown in fig. 6, the adjustment system 500 of the application container may be configured with a first storage device 503 connected to the obtaining unit 502 and configured to store the operation data, the determining unit 504 may extract performance data in the operation data stored in the first storage device 503 to determine index configuration data of the target container application according to the performance data, and the scheduling unit 506 may extract resource usage in the operation data stored in the first storage device 503 and schedule the capacity of the application container according to a relationship between the resource usage and the index configuration data. The adjustment system 500 in the embodiment of the present invention stores the operation data acquired by the acquisition unit 502 in the form of the first storage device 503, and certainly, the operation data may also be stored in other forms such as a file system, a Redis cache, or a distributed storage system, which is not limited to the specific example defined in the embodiment of the present invention.
Generally, performance data is obtained by performing a pressure test once by using a tool, a script, or the like manually, and the obtained performance data may be directly stored in the first storage device 503, so that when the capacity of the application container is scheduled next time, the scheduling unit 506 may directly schedule the capacity of the application container through the index configuration data determined by the performance data extracted by the determining unit 504 and the resource utilization rate extracted by the scheduling unit 506.
In the above embodiment, as described with reference to fig. 5 and fig. 7, the system 500 for adjusting an application container further includes a capacity expansion unit 508, configured to determine whether there is a standby node 515 that joins the kubernets cluster 501 when a capacity expansion condition is satisfied; a creating unit 512, configured to create, if there is a first standby node 5151 joining the kubernets cluster 501, a target container group 513 having a mapping relationship with a target container application based on the first standby node 5151; if there is a second standby node 5152 that does not join the kubernets cluster 501, the second standby node 5152 is joined to the kubernets cluster 501 and a target container group 513 having a mapping relationship with the target container application is created based on the second standby node 5152. The logic executed by the creating unit 512 includes: the first backup node 5151 is traversed and a first target backup node in the first backup node 5151 is determined to create the target container group 513 on the first target backup node when the resource on the first target backup node satisfies the condition.
Specifically, the creating unit 512 traverses the first backup node 5151 according to the resource levels, and determines a backup node in the first backup node 5151 whose resource level is sufficient as a first target backup node, so as to create the target container group when the resource on the first target backup node satisfies a condition, where the resource levels include sufficient resources, general resources, and insufficient resources. Therefore, the standby node with sufficient resources is selected to create the target container group, so that the container application started on the standby node can provide better service, and the service effect of the container application is improved.
Alternatively, the creating unit 512 traverses the first standby node 5151 according to the time order in which the first standby node 5151 joins the kubernets cluster 501, and determines the earliest standby node in the first standby node 5151 that joins the kubernets cluster 501 as the first target standby node to create the target container group 513 when the resource on the first target standby node satisfies the condition. Therefore, the container application can be started on the standby node which is added to the Kubernets cluster 501 at the earliest as possible according to the time priority order, so that the service efficiency of the container application is improved.
Still alternatively, the creation unit 512 may define a usage scenario of the standby node according to the property of the container application to determine the standby node of the target container group 513 to be created according to the usage scenario of the standby node. In this manner, by traversing the first backup node 5151 according to the property of the container application to select a first target backup node from the first backup node 5151 for subsequent creation of the target container group 513, the quality of service of the container application can be improved.
In order to further optimize the determined first target standby node, the resource level may be considered at the same time, the time sequence of the first standby node 5151 joining the kubernets cluster 501, and the nature of the container application traverse the first standby node 5151 in three aspects, so as to select the optimal first target standby node. That is, the creating unit 512 sequentially traverses the first standby node 5151 according to the time sequence of the first standby node 5151 joining the kubernets cluster 501, so as to improve the service efficiency of the container application on the premise of improving the service effect or quality of the container application.
When there is a second standby node 5152 that does not join the kubernets cluster 501, the creating unit 512 is then configured to: a second target standby node in the second standby node 5152 is selected to join the kubernets cluster 501, so that when the resource on the second target standby node meets the condition, a target container group 513 is created on the second target standby node, thereby achieving the purpose of capacity expansion.
The adaptation system 500 of the application container further comprises: a capacity reduction unit 510, configured to determine whether there is a standby node 515 added to the kubernets cluster 501 when a capacity reduction condition is satisfied; a releasing unit 514, configured to select a third target standby node in the third standby node 5153 if there is a third standby node 5153 that joins the kubernets cluster 501, and release the mapping relationship between the target container application on the third target standby node and the target container group 513.
Therefore, the adjustment system 500 (or simply referred to as "adjustment system 500") of the application container according to the embodiment of the present invention can rapidly implement dynamic adjustment of the capacity of the application container according to the resource utilization rate and the index configuration data of the container application without manual intervention, which not only improves the running efficiency of the application program, but also does not require that each application program must run on a different physical machine to improve the utilization rate of the resource.
In any of the above embodiments, the adaptation system 500 of the application container further comprises: and a second storage device 516 for storing events for scheduling the capacity of the application container. Specifically, events that schedule the capacity of the application container may be saved to a log.
Wherein, the event for scheduling the capacity of the application container includes but is not limited to: an event for expanding an application container, an event for contracting the application container, an adjustment system 500 according to an expansion instruction and a contraction instruction issued by index configuration data, determining whether an event that a first standby node 5151 has joined the kubernets cluster 501 exists, determining whether an event that a second standby node 5152 does not join the kubernets cluster 501 exists, determining whether an event that a third standby node 5153 joins the kubernets cluster 501 exists, determining whether an event that a target container group 513 having a mapping relationship with a target container application exists on the third standby node 5153, releasing the mapping relationship between the target container application on the third standby node 5153 and the target container group 513, creating the target container group 513 based on the first standby node 5151 or the second standby node 5152 to establish the mapping relationship between the target container group 513 and the target container application, and determining that the first standby node 5151, the second standby node 5152, and the event that the target container group 513 has a mapping relationship with the target container application exists, Events of whether resources are sufficient on the second backup node 5152, the third backup node 5153, etc.
Please refer to the description of the first embodiment, and further description thereof is omitted.
Example three:
referring to FIG. 8, the present embodiment discloses an embodiment of a computer-readable medium 800. The computer-readable medium 800 may be disposed in whole or in part in a physical form of a computer, server, cluster server, or data center.
In the present embodiment, a computer-readable medium 800 is provided, in which computer program instructions 801 are stored in the computer-readable medium 800, and when the computer program instructions 801 are read and executed by a processor 802, the steps in the method for adjusting an application container according to an embodiment of the present invention are performed.
Alternatively, the computer-readable medium 800 may be configured as a server and the server is run on a physical device that constructs a private cloud, a hybrid cloud, or a public cloud. Meanwhile, the computer-readable medium 800 may also be configured as a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The computer readable medium 800 is used for storing a program, and the processor 802 executes the method for adjusting an application container according to an embodiment of the disclosure after receiving an execution instruction.
Meanwhile, the processor 802 disclosed in this embodiment may be an integrated circuit chip having signal processing capability. The Processor 802 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. The general purpose processor may be a microprocessor or the general purpose processor may be any conventional processor.
For a technical solution of a portion of the computer-readable medium 800 disclosed in this embodiment that is the same as that in the first embodiment and/or the second embodiment, please refer to the description in the first embodiment and/or the second embodiment, which is not repeated herein.
Example four:
referring to fig. 9 in combination, the present embodiment discloses a terminal device 100, which includes a processor 51, a memory 52, and a computer program stored on the memory 52 and operable on the processor 51, and when the computer program is executed by the processor 51, the steps of the method for adjusting the capacity of an application container according to the first embodiment are implemented. At the same time, a communication bus 53 is established for communication between the processor 51 and the memory device 52. The processor 51 is configured to execute one or more programs stored in the storage device 52, where the programs are the capacity adjustment method for the application container according to the first embodiment.
In the present embodiment, the storage device 52 is composed of a storage unit 521 to a storage unit 52i, and the parameter i is a positive integer greater than or equal to 1. The terminal device 100 may be understood as a computer, a cluster server, or a cloud platform.
Please refer to the description of the first embodiment, which will not be repeated herein, for a specific technical solution of the method for adjusting the capacity of the application container relied on/included by the terminal device 100 in this embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable medium. Based on such understanding, the technical solution of the present invention may be substantially implemented or contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-listed detailed description is only a specific description of a possible embodiment of the present invention, and they are not intended to limit the scope of the present invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention should be included in the scope of the present invention.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (20)
1. A method of tuning an application container, comprising:
acquiring running data of a virtual host corresponding to a target container application, wherein the running data comprises performance data and resource utilization rate;
determining metric configuration data for the target container application based on the performance data;
and scheduling the capacity of the application container based on the relation between the resource utilization rate and the index configuration data.
2. The method of claim 1, wherein scheduling the capacity of the application container comprises:
when the capacity expansion condition is met, determining whether a standby node added to the Kubernetes cluster exists or not;
if a first standby node which is added into a Kubernetes cluster exists, a target container group which has a mapping relation with the target container application is created based on the first standby node;
and if a second standby node which is not added to the Kubernets cluster exists, adding the second standby node to the Kubernets cluster and creating a target container group with a mapping relation with the target container application based on the second standby node.
3. The method according to claim 2, wherein creating a target container group having a mapping relationship with the target container application based on the first standby node comprises:
traversing the first standby nodes to determine a first target one of the first standby nodes;
creating the target container group on the first target standby node when the resources on the first target standby node satisfy a condition.
4. The adjustment method according to claim 3, wherein traversing the first standby node to determine a first target one of the first standby nodes is specifically:
traversing the first standby node based on resource levels, wherein the resource levels comprise sufficient resources, general resources and insufficient resources;
and determining the standby node with sufficient resource level in the first standby node as the first target standby node.
5. The adjustment method according to claim 3, wherein traversing the first standby node to determine a first target one of the first standby nodes is specifically:
traversing the first standby node based on a time order in which the first standby node joins a Kubernets cluster;
and determining the standby node which is added to the Kubernets cluster in the first standby node and has the earliest time as the first target standby node.
6. The method of claim 1, wherein scheduling the capacity of the application container comprises:
when capacity reduction conditions are met, determining whether a standby node added to a Kubernetes cluster exists or not;
and if a third standby node added to the Kubernetes cluster exists, selecting a third target standby node in the third standby node, and removing the mapping relation between the target container application and the target container group on the third target standby node.
7. The adjustment method according to claim 1, wherein the index configuration data includes an expansion threshold, a contraction threshold, a first preset ratio, and a second preset ratio, the resource utilization includes a first ratio m1 and a second ratio n1, the first ratio m1 is m/t, the second ratio n1 is n/t, t is the number of times of collection per unit time, m is the number of times of exceeding the expansion threshold, and n is the number of times of being lower than the contraction threshold;
wherein scheduling the capacity of the application container based on the relationship between the resource utilization and the indicator configuration data comprises:
executing capacity expansion logic if the first ratio is higher than a first preset ratio;
and if the second ratio is higher than a second preset ratio, executing the capacity reduction logic.
8. The tuning method according to any one of claims 1-7, further comprising, after obtaining the running data of the virtual host corresponding to the target container application and before determining the metric configuration data of the target container application based on the performance data:
and storing the operation data of the virtual host corresponding to the target container application.
9. The adjustment method according to any one of claims 1-7, further comprising:
saving an event that schedules a capacity of the application container.
10. A system for regulating the volume of a container, comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring operation data of a virtual host corresponding to a target container application, and the operation data comprises performance data and resource utilization rate;
a determining unit, configured to obtain index configuration data of the target container application based on the performance data;
and the scheduling unit is used for scheduling the capacity of the application container based on the relation between the resource utilization rate and the index configuration data.
11. The adjustment system of claim 10, further comprising:
the capacity expansion unit is used for determining whether a standby node added to the Kubernetes cluster exists or not when capacity expansion conditions are met;
a creating unit, configured to create, if there is a first standby node joining a kubernets cluster, a target container group having a mapping relationship with the target container application based on the first standby node;
and if a second standby node which is not added to the Kubernets cluster exists, adding the second standby node to the Kubernets cluster and creating a target container group with a mapping relation with the target container application based on the second standby node.
12. The adaptation system according to claim 11, characterized in that the creation unit is configured to:
traversing the first standby nodes and determining a first target one of the first standby nodes to create the target container group on the first target standby node when resources on the first target standby node satisfy a condition.
13. The adaptation system according to claim 12, wherein the creation unit is further configured to:
traversing the first standby node based on resource levels, and determining a standby node of the first standby node, of which the resource level is sufficient, as the first target standby node, so as to create the target container group when the resource on the first target standby node meets conditions, wherein the resource levels include sufficient resources, general resources and insufficient resources.
14. The adaptation system according to claim 12, wherein the creation unit is further configured to:
traversing the first standby node based on the time sequence of joining the Kubernets cluster by the first standby node, and determining the standby node which is joined to the Kubernets cluster in the first standby node and has the earliest time as the first target standby node, so as to create the target container group when the resource on the first target standby node meets the condition.
15. The adjustment system of claim 10, further comprising:
the capacity reduction unit is used for determining whether a standby node added to the Kubernetes cluster exists or not when capacity reduction conditions are met;
and the releasing unit is used for selecting a third target standby node in a Kubernetes cluster if a third standby node added to the Kubernetes cluster exists, and releasing the mapping relation between the target container application and the target container group on the third target standby node.
16. The adjustment system according to claim 10, wherein the index configuration data includes an expansion threshold, a contraction threshold, a first predetermined ratio, a second predetermined ratio, the resource utilization includes a first ratio m1 and a second ratio n1, the first ratio m1 is m/t, the second ratio n1 is n/t, t is the number of acquisitions per unit time, m is the number of times that the expansion threshold is exceeded, and n is the number of times that the contraction threshold is fallen below;
the scheduling unit is configured to:
executing capacity expansion logic if the first ratio is higher than a first preset ratio;
if the second ratio is higher than a second preset ratio, executing capacity reduction logic;
wherein the first preset ratio is lower than the second preset ratio.
17. The adjustment system according to any one of claims 10-16, further comprising:
and the first storage device is used for storing the running data of the virtual host corresponding to the target container application.
18. The adjustment system according to any one of claims 10-16, further comprising:
and the second storage device is used for storing the event for scheduling the capacity of the application container.
19. A computer-readable medium, in which computer program instructions are stored, which, when read and executed by a processor, perform the steps of the method for adjusting the capacity of an application container according to any one of claims 1 to 9.
20. A terminal device, comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the capacity adjustment method for an application container according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010258218.2A CN111522636B (en) | 2020-04-03 | 2020-04-03 | Application container adjusting method, application container adjusting system, computer readable medium and terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010258218.2A CN111522636B (en) | 2020-04-03 | 2020-04-03 | Application container adjusting method, application container adjusting system, computer readable medium and terminal device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111522636A true CN111522636A (en) | 2020-08-11 |
| CN111522636B CN111522636B (en) | 2023-03-14 |
Family
ID=71902510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010258218.2A Active CN111522636B (en) | 2020-04-03 | 2020-04-03 | Application container adjusting method, application container adjusting system, computer readable medium and terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111522636B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966305A (en) * | 2020-10-22 | 2020-11-20 | 腾讯科技（深圳）有限公司 | Persistent volume allocation method and device, computer equipment and storage medium |
| CN112000574A (en) * | 2020-08-18 | 2020-11-27 | 中国建设银行股份有限公司 | Pressure testing method, device, equipment and storage medium |
| CN112202860A (en) * | 2020-09-22 | 2021-01-08 | 广州品唯软件有限公司 | Container flow adjusting method, device and system |
| CN112783608A (en) * | 2021-01-29 | 2021-05-11 | 上海哔哩哔哩科技有限公司 | Method and device for adjusting container resources in container cluster |
| CN113222174A (en) * | 2021-04-23 | 2021-08-06 | 万翼科技有限公司 | Model management method and device |
| CN113342463A (en) * | 2021-06-16 | 2021-09-03 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for adjusting capacity of computer program module |
| CN113434253A (en) * | 2021-06-29 | 2021-09-24 | 平安科技（深圳）有限公司 | Cluster resource scheduling method, device, equipment and storage medium |
| CN114979276A (en) * | 2022-05-13 | 2022-08-30 | 深信服科技股份有限公司 | Resource dynamic scheduling method, device, equipment and storage medium |
| CN117421123A (en) * | 2023-11-03 | 2024-01-19 | 摩尔线程智能科技(上海)有限责任公司 | GPU resource adjustment method and system, electronic equipment and storage medium |
| CN117421123B (en) * | 2023-11-03 | 2024-04-19 | 摩尔线程智能科技(上海)有限责任公司 | GPU resource adjustment method and system, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9122562B1 (en) * | 2014-06-19 | 2015-09-01 | Amazon Technologies, Inc. | Software container recommendation service |
| CN109150987A (en) * | 2018-07-27 | 2019-01-04 | 北京友普信息技术有限公司 | The two-layer container cluster elasticity expansion method of Intrusion Detection based on host layer and container floor |
| CN109525590A (en) * | 2018-12-11 | 2019-03-26 | 中科曙光国际信息产业有限公司 | The transmission method and device of data packet |
| CN110515704A (en) * | 2019-08-30 | 2019-11-29 | 广东浪潮大数据研究有限公司 | Resource regulating method and device based on Kubernetes system |
-
2020
- 2020-04-03 CN CN202010258218.2A patent/CN111522636B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9122562B1 (en) * | 2014-06-19 | 2015-09-01 | Amazon Technologies, Inc. | Software container recommendation service |
| CN109150987A (en) * | 2018-07-27 | 2019-01-04 | 北京友普信息技术有限公司 | The two-layer container cluster elasticity expansion method of Intrusion Detection based on host layer and container floor |
| CN109525590A (en) * | 2018-12-11 | 2019-03-26 | 中科曙光国际信息产业有限公司 | The transmission method and device of data packet |
| CN110515704A (en) * | 2019-08-30 | 2019-11-29 | 广东浪潮大数据研究有限公司 | Resource regulating method and device based on Kubernetes system |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112000574A (en) * | 2020-08-18 | 2020-11-27 | 中国建设银行股份有限公司 | Pressure testing method, device, equipment and storage medium |
| CN112202860A (en) * | 2020-09-22 | 2021-01-08 | 广州品唯软件有限公司 | Container flow adjusting method, device and system |
| CN112202860B (en) * | 2020-09-22 | 2023-07-14 | 广州品唯软件有限公司 | Container flow adjustment method, device and system |
| CN111966305B (en) * | 2020-10-22 | 2021-02-09 | 腾讯科技（深圳）有限公司 | Persistent volume allocation method and device, computer equipment and storage medium |
| CN111966305A (en) * | 2020-10-22 | 2020-11-20 | 腾讯科技（深圳）有限公司 | Persistent volume allocation method and device, computer equipment and storage medium |
| CN112783608A (en) * | 2021-01-29 | 2021-05-11 | 上海哔哩哔哩科技有限公司 | Method and device for adjusting container resources in container cluster |
| CN113222174B (en) * | 2021-04-23 | 2024-04-26 | 万翼科技有限公司 | Model management method and device |
| CN113222174A (en) * | 2021-04-23 | 2021-08-06 | 万翼科技有限公司 | Model management method and device |
| CN113342463A (en) * | 2021-06-16 | 2021-09-03 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for adjusting capacity of computer program module |
| CN113342463B (en) * | 2021-06-16 | 2024-01-09 | 北京百度网讯科技有限公司 | Capacity adjustment method, device, equipment and medium of computer program module |
| CN113434253A (en) * | 2021-06-29 | 2021-09-24 | 平安科技（深圳）有限公司 | Cluster resource scheduling method, device, equipment and storage medium |
| CN113434253B (en) * | 2021-06-29 | 2023-08-25 | 平安科技（深圳）有限公司 | Cluster resource scheduling method, device, equipment and storage medium |
| CN114979276A (en) * | 2022-05-13 | 2022-08-30 | 深信服科技股份有限公司 | Resource dynamic scheduling method, device, equipment and storage medium |
| CN114979276B (en) * | 2022-05-13 | 2024-02-23 | 深信服科技股份有限公司 | Dynamic scheduling method, device, equipment and storage medium for resources |
| CN117421123B (en) * | 2023-11-03 | 2024-04-19 | 摩尔线程智能科技(上海)有限责任公司 | GPU resource adjustment method and system, electronic equipment and storage medium |
| CN117421123A (en) * | 2023-11-03 | 2024-01-19 | 摩尔线程智能科技(上海)有限责任公司 | GPU resource adjustment method and system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111522636B (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111522636B (en) | Application container adjusting method, application container adjusting system, computer readable medium and terminal device | |
| US11573725B2 (en) | Object migration method, device, and system | |
| CN108683720B (en) | Container cluster service configuration method and device | |
| CN111796908B (en) | System and method for automatic elastic expansion and contraction of resources and cloud platform | |
| CN109981702B (en) | File storage method and system | |
| JP2012118987A (en) | Computer implementation method, computer program, and system for memory usage query governor (memory usage query governor) | |
| EP2898412B1 (en) | Adaptive service timeouts | |
| WO2020042612A1 (en) | Method and device for storing and reading a message, server, and storage medium | |
| CN108243239A (en) | A kind of method, apparatus, electronic equipment and system that web application service is provided | |
| CN111966289A (en) | Partition optimization method and system based on Kafka cluster | |
| CN112698952A (en) | Unified management method and device for computing resources, computer equipment and storage medium | |
| CN112486634A (en) | Method for realizing integral monitoring of container cloud platform | |
| CN111400241B (en) | Data reconstruction method and device | |
| EP2866403B1 (en) | Resource management method and management server | |
| CN112860387A (en) | Distributed task scheduling method and device, computer equipment and storage medium | |
| CN114900449B (en) | Resource information management method, system and device | |
| CN116389591A (en) | Cross-domain-based distributed processing system and scheduling optimization method | |
| CN115604294A (en) | Method and device for managing storage resources | |
| CN115525603A (en) | Storage statistics method and device, computer readable storage medium and AI device | |
| CN114625474A (en) | Container migration method and device, electronic equipment and storage medium | |
| CN114296891A (en) | Task scheduling method, system, computing device, storage medium and program product | |
| CN116166181A (en) | Cloud monitoring method and cloud management platform | |
| CN112328387A (en) | Multi-tenant-oriented micro-service resource scheduling method | |
| WO2019196595A1 (en) | Method and apparatus for managing application program | |
| CN117148705B (en) | Equipment running state detection method and system based on data monitoring analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |