CN112783607A - Task deployment method and device in container cluster - Google Patents
Task deployment method and device in container cluster Download PDFInfo
- Publication number
- CN112783607A CN112783607A CN202110124547.2A CN202110124547A CN112783607A CN 112783607 A CN112783607 A CN 112783607A CN 202110124547 A CN202110124547 A CN 202110124547A CN 112783607 A CN112783607 A CN 112783607A
- Authority
- CN
- China
- Prior art keywords
- value
- target
- child node
- available resource
- container
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000004364 calculation method Methods 0.000 claims abstract description 64
- 230000004048 modification Effects 0.000 claims description 21
- 238000012986 modification Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G06F9/44—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
-
- 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
- G06F2009/45575—Starting, stopping, suspending or resuming virtual machine instances
-
- 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
- G06F2009/45595—Network integration; Enabling network access in virtual machine instances
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application provides a task deployment method and device in a container cluster, wherein the task deployment method in the container cluster comprises the following steps: receiving a task request of a target task; responding to the task request to create a target container for the target task, wherein the target container comprises a target resource value corresponding to the target container; calculating an available resource value of each child node in the container cluster according to a preset resource calculation strategy; determining a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value; and deploying the target container corresponding to the target task at the target child node. By the method for task deployment in the container cluster, the target container corresponding to the target task can be scheduled according to the available resource value of each child node, task deployment is completed, and the utilization rate and the working efficiency of the container cluster are improved.
Description
Technical Field
The application relates to the technical field of computers, in particular to a task deployment method in a container cluster. The application also relates to a task deployment device in the container cluster, a computing device and a computer readable storage medium.
Background
In daily life, computing tasks of users are generally divided into online tasks and offline tasks, and the online tasks have high requirements on usability and stability, such as website services. The offline task usually allows a certain failure rate, such as data statistics, and the user usually deploys the online task and the offline task separately to avoid the two tasks from affecting each other. In addition, the respective use time of the on-line task and the off-line task generally has some differences, for example, the on-line task is in a resource use peak in the daytime, and the off-line task is in a resource use peak in the same row at night, so that when the on-line task is in a valley, some off-line tasks are mixedly deployed, and the utilization rate of the distributed cluster can be effectively improved. Based on this, two major systems, i.e., Docker (a container technology in Linux) and Kubernetes (an orchestration management system of containers, k8s for short), have been widely applied to cloud computing platforms of various large companies, and have better isolation when mixed deployment is performed in a container environment.
The pod is the minimum unit managed in k8s, is a combination of one or more containers, and is usually a container, and the current hybrid deployment scheme of k8s only considers the resource quota (CPU request) of the pod, which is set by a user, and the set resource quota usually cannot represent the actual processor (CPU) usage of the pod.
Disclosure of Invention
In view of this, an embodiment of the present application provides a task deployment method in a container cluster. The application also relates to a task deployment device in the container cluster, a computing device and a computer readable storage medium, so as to solve the problems that the task can not be deployed according to the actual use condition of the child nodes and the utilization rate of the container cluster resources is low in the prior art.
According to a first aspect of embodiments of the present application, a method for task deployment in a container cluster is provided, including:
receiving a task request of a target task;
responding to the task request to create a target container for the target task, wherein the target container comprises a target resource value corresponding to the target container;
calculating an available resource value of each child node in the container cluster according to a preset resource calculation strategy;
determining a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value;
and deploying the target container corresponding to the target task at the target child node.
According to a second aspect of the embodiments of the present application, there is provided a task deployment apparatus in a container cluster, including:
a first receiving module configured to receive a task request of a target task;
a creating module configured to create a target container for the target task in response to the task request, wherein the target container includes a target resource value corresponding to the target container;
the computing module is configured to compute an available resource value of each child node in the container cluster according to a preset resource computing strategy;
a determining module configured to determine a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value;
and the deployment module is configured to deploy the target container corresponding to the target task at the target child node.
According to a third aspect of embodiments of the present application, there is provided a computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, the processor implementing the steps of the method for task deployment in a container cluster when executing the computer instructions.
According to a fourth aspect of embodiments herein, there is provided a computer-readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the task deployment method in the container cluster.
The task deployment method in the container cluster receives a task request of a target task; responding to the task request to create a target container for the target task, wherein the target container comprises a target resource value corresponding to the target container; calculating an available resource value of each child node in the container cluster according to a preset resource calculation strategy; determining a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value; and deploying the target container corresponding to the target task at the target child node. According to the embodiment of the application, the available resource value of each child node is dynamically calculated according to the processor load condition of each child node, the target container corresponding to the target task is scheduled according to the available resource value of each child node, the deployment of the target task is completed, and the utilization rate and the working efficiency of the container cluster are improved.
Drawings
Fig. 1 is a flowchart of a task deployment method in a container cluster according to an embodiment of the present application;
FIG. 2 is a block diagram illustrating an example of an arrangement for deploying offline tasks in a container cluster according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a resident node offline task deployment according to an embodiment of the present application;
FIG. 4 is a schematic structural diagram of a computing policy for automatically managing node resources in a container cluster according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a task deployment device in a container cluster according to an embodiment of the present application;
fig. 6 is a block diagram of a computing device according to an embodiment of the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.
The terminology used in the one or more embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the present application. As used in one or more embodiments of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present application refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments of the present application to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first aspect may be termed a second aspect, and, similarly, a second aspect may be termed a first aspect, without departing from the scope of one or more embodiments of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
First, the noun terms to which one or more embodiments of the present application relate are explained.
A container: a virtualization technology enables resources to be isolated by deploying services in containers.
Kubernetes: and (5) arranging and managing the containers, which are abbreviated as k8 s.
API-server: and the components of the k8s provide an API call interface of the related operations of the k8s cluster.
k8s scheduler: and the component of the k8s is responsible for selecting a proper k8s node for a certain pod to be deployed.
Kubelet: the component of k8s manages a certain node of k8 s.
pod: the minimum unit level managed in k8s, which is a combination of one or more containers.
CPU request: the CPU quota set when the container is created can be understood as the lower CPU limit that can be used by the container.
The present application also relates to a task deployment apparatus in a container cluster, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments one by one.
Fig. 1 shows a flowchart of a task deployment method in a container cluster according to an embodiment of the present application, which specifically includes the following steps:
step 102: a task request of a target task is received.
In daily application, computing tasks of a user are generally divided into online tasks and offline tasks, the availability, stability and other requirements of the online tasks are high, such as website services, interactive access and other user-oriented tasks, and the online tasks are usually in a resource use peak period in the daytime; the offline task generally has a low requirement on stability, and allows certain errors, such as tasks of big data statistics, data analysis and the like, to occur, and the offline task usually occupies a large resource value during operation, so that the load of the child node deploying the offline task is high, therefore, if the online task is in a valley, some offline tasks are deployed, the overall utilization rate of the container cluster can be improved, and the purchase cost for deploying the container cluster is saved.
The target task is a task that needs to be deployed in the container cluster, and may be an online task or an offline task in general, but is preferably an offline task. The task requests a request to deploy a target task in a container cluster.
In a specific embodiment provided by the present application, an offline task T that creates a statistical datum is taken as an example for explanation, and the container cluster receives a task request that the offline task T is deployed into the container cluster.
Step 104: and creating a target container for the target task in response to the task request, wherein the target container comprises a target resource value corresponding to the target container.
In practical application, after a task request is received, a corresponding container is created for a target task, the container is a virtualization technology, resources of a single operating system can be effectively divided into independent groups, and resources can be isolated without mutual influence when services are deployed in the container.
The default scheduling rule of the existing container cluster is scheduled according to a processor quota (CPU Request) of a container, after the CPU Request corresponding to the container deployed on a current child node is used up, a new container cannot be scheduled and deployed any more, in order to enable the container cluster to deploy a target task to the child node, an available resource value of each child node needs to be calculated first, the available resource value is registered in state information of the node as an extended resource (coordination-CPU), as long as the created target container sets a quota of the extended resource, the container cluster can search for a node meeting the extended resource quota in the child node, and therefore, the target resource value is the extended resource quota of the target container.
In a specific embodiment provided by the present application, following the above example, in response to a task request, a target container B is created for an offline task T, where an expansion-cpu (collision-cpu) quota of the target container B is 6 cores.
Step 106: and calculating the available resource value of each child node in the container cluster according to a preset resource calculation strategy.
The preset resource calculation strategy is a calculation strategy for calculating an available resource value of each child node in the container cluster. And calculating the available resource value of each child node in the container cluster based on the resource calculation strategy, and registering the available resource value of each child node as an extended resource in the state information of the current child node after obtaining the available resource value of each child node.
Specifically, the preset resource calculation strategy includes resource calculation parameters;
calculating an available resource value of each child node in the container cluster according to a preset resource calculation strategy, wherein the method comprises the following steps:
acquiring the processor utilization rate and the processor load value of the current child node in a preset time interval;
and determining the available resource value of the current child node according to the processor utilization rate, the processor load value and the resource calculation parameter.
In the resource calculation strategy, resource calculation parameters and information required to be acquired for calculating the available resource value of the current child node are included.
The information required for calculating the available resource value of the current child node comprises a processor utilization rate (CPU utilization rate) and a processor load value (CPU load value), wherein the processor utilization rate refers to the percentage of CPU occupied by a program during the running process; the processor load value refers to the average number of tasks of the CPU which are used and wait for use in a period of time, the utilization rate of the CPU is high, and the load is not necessarily large.
The resource calculation parameter refers to a parameter used when an available resource value of a current child node is determined through specific calculation. After the processor utilization rate and the processor load are obtained, the available resource value of the current child node can be calculated according to the corresponding resource calculation parameters.
Specifically, obtaining the processor utilization rate and the processor load value of the current child node within the preset time interval includes:
and acquiring the average processor utilization rate and the average processor load value of the current child node in a preset time interval.
The preset time interval is a time interval determined according to the resource calculation policy, and is used for counting the CPU utilization and the CPU load value in the time interval, and in order to better obtain the CPU utilization of the current child node, the average processor utilization (CPU _ average) and the average processor load value (load _ average) of the CPU of the current child node in the preset time interval are usually obtained. In general, the higher the cpu _ average and the load _ average, the less the available resource value of the current child node.
In practical application, the resource calculation parameters comprise a first parameter and a second parameter;
determining the available resource value of the current child node according to the processor utilization, the processor load value and the resource calculation parameter, including the following steps S1062 to S1066:
s1062, determining a first reference available resource value according to the processor utilization rate and the first parameter.
The first parameter is a resource calculation parameter for a processor utilization rate (cpu _ average), and the first reference available resource is an available resource value corresponding to the processor utilization rate (cpu _ average). The first reference available resource value can be determined according to the cpu _ average and the first parameter. Specifically, the first parameter includes a first weight value and a first threshold interval;
determining a first reference available resource value based on the processor utilization and the first parameter, comprising:
determining an initial first reference available resource value according to the processor utilization and the first threshold interval;
determining a first reference available resource value as a function of the initial first reference available resource value and the first weight value.
The first weight value specifically refers to a weight value occupied by the utilization rate of the processor in the resource calculation policy, the first weight value and a subsequent second weight value have a corresponding relationship, and the sum of the first weight value and the second weight value should be 1.
The first threshold interval represents a value range corresponding to the processor utilization rate (cpu _ average), when the processor utilization rate (cpu _ average) is at different values, an initial reference available resource value corresponding to the processor utilization rate can be calculated according to the first threshold interval according to a corresponding calculation strategy, the initial first reference available resource value is an initial reference available value determined according to the processor utilization rate and the first threshold interval, and the first reference available resource value can be determined by combining the first weight after the initial first reference available resource value corresponding to the cpu _ average is determined.
Specifically, the first threshold interval includes a first threshold minimum value and a first threshold maximum value;
determining an initial first reference available resource value based on the processor utilization and the first threshold interval, comprising:
determining an initial first reference available resource value to be 1 if the processor usage is less than or equal to the first threshold minimum value;
determining an initial first reference available resource value to be 0 if the processor usage is greater than or equal to the first threshold maximum value;
determining an initial first reference available resource value as a function of the processor usage, the first threshold minimum value, and the first threshold maximum value if the processor usage is less than the first threshold maximum value and greater than the first threshold minimum value.
The first threshold interval is a value range, and therefore the first threshold interval includes a first threshold minimum value and a first threshold maximum value, and the initial first reference available resource value is determined by determining which range of the first threshold interval the processor utilization (cpu _ average) conforms to.
Specifically, when the processor utilization (cpu _ average) is less than or equal to the first threshold minimum value, it indicates that the current processor utilization is low and can provide all services, and the initial first reference available resource value is 1; when the processor utilization (cpu _ average) is greater than or equal to the first threshold maximum value, it indicates that the current processor utilization is high and cannot provide service any more, and therefore the initial first reference available resource value is 0; when the processor utilization (cpu _ average) is within the first threshold interval, specifically, an initial first reference available resource value may be determined according to the processor utilization, the first threshold minimum value, and the first threshold maximum value, so as to calculate and determine the initial first reference available resource value, where a specific calculation method is as shown in the following formula 1:
ratio1 ═ by (HL1-cpu _ average)/(HL1-TH1) formula 1
Wherein Ratio1 is an initial first reference available resource value, HL1 is a first threshold maximum value, TH1 is a first threshold minimum value, and cpu _ average is a processor utilization.
After the initial first reference available resource value is determined, the first reference available resource value can be determined by multiplying the initial first reference available resource value by the first weight value.
In an embodiment provided by the present application, it is assumed that the processor utilization (cpu _ average) of the current child node is 50%, the first weight value is 0.6, the first threshold minimum value is 40%, and the first threshold maximum value is 70%. According to the above formula 1, it may be calculated to determine that the initial first reference available resource value of the current child node is (70-50)/(70-40) ═ 0.67, and then the first reference available resource value is determined to be 0.402 by multiplying the initial first reference available resource value by the first weight value of 0.6.
S1064, determining a second reference available resource value according to the processor load value and the second parameter.
The second parameter is specifically a resource calculation parameter for a processor load value (load _ average), the second reference available resource is specifically an available resource value corresponding to the processor load value (load _ average), and the second reference available resource value can be determined according to the processor load value (load _ average) and the second parameter, specifically, the second parameter includes a second weight value and a second threshold interval;
determining a second reference available resource value based on the processor load value and the second parameter, comprising:
determining an initial second reference available resource value according to the processor load value and the second threshold interval;
determining a second reference available resource value according to the initial second reference available resource value and the second weight value.
The second weight value specifically refers to a weight value occupied by the processor load value in the resource calculation policy, and the sum of the second weight value and the first weight value is 1.
The second threshold interval represents a value range corresponding to the processor load value (load _ average), when the processor load value (load _ average) is at different values, an initial reference available resource value corresponding to the processor load value can be calculated according to the second threshold interval according to a corresponding calculation strategy, the initial second reference available resource value is an initial reference available resource value determined according to the processor load value and the second threshold interval, and after the initial second reference available resource value corresponding to the processor load value (load _ average) is determined, the first reference available resource value can be determined by combining the second weight.
The second threshold interval comprises a second threshold minimum value and a second threshold maximum value;
determining an initial second reference available resource value based on the processor load value and the second threshold interval, comprising:
determining an initial second reference available resource value to be 1 if the processor load value is less than or equal to the second threshold minimum value;
determining an initial second reference available resource value to be 0 if the processor load value is greater than or equal to the second threshold maximum value;
determining an initial second reference available resource value as a function of the processor usage, the second threshold minimum, and the second threshold maximum, if the processor load value is less than the second threshold maximum and greater than the second threshold minimum.
The second threshold interval is also a value range, and therefore, the second threshold interval also includes a second threshold minimum value and a second threshold maximum value, and the initial second reference available resource value is determined by determining which range of the second threshold interval the processor load value (load _ average) conforms to.
Specifically, when the processor load value (load _ average) is less than or equal to the second threshold minimum value, it indicates that the current processor utilization is low and can provide all services, and the initial second reference available resource value is 1; when the processor load value (load _ average) is greater than or equal to the second threshold maximum value, it indicates that the current processor utilization is high and cannot provide service any more, and therefore the initial second reference available resource value is 0; when the processor load value (load _ average) is within the second threshold interval, specifically, an initial second reference available resource value may be determined according to the processor load value, the second threshold minimum value, and the second threshold maximum value, so as to calculate and determine the initial second reference available resource value, where the specific calculation method is as follows in equation 2:
ratio2 ═ h 2-load _ average)/(HL2-TH2) formula 2
Wherein Ratio2 is an initial second reference available resource value, HL2 is a second threshold maximum value, TH2 is a second threshold minimum value, and load _ average is a processor load value.
After the initial second reference available resource value is determined, the second reference available resource value can be determined by multiplying the initial second reference available resource value by the second weight value.
In an embodiment provided by the present application, assuming that the processor load value (load _ average) of the current child node is 40, the second weight value is 0.4, the second threshold minimum value is 30, and the second threshold maximum value is 60, according to the above formula 2, the initial second reference available resource value of the current child node may be calculated and determined to be (60-40)/(60-30) ═ 0.67, and then the initial second reference available resource value is multiplied by 0.67 according to the second weight value of 0.4, so as to determine the second reference available resource value to be 0.268.
S1066, determining an available resource value of the current child node according to the first reference available resource value and the second reference available resource value.
After obtaining the first reference available resource value and the second reference available resource value, the available resource value of the current child node may be determined, and specifically, determining the available resource value of the current child node according to the first reference available resource value and the second reference available resource value includes:
determining an initial available resource value of the current child node according to the first reference available resource value and the second reference available resource value;
and determining the available resource value of the current child node according to the processor core number of the current child node and the initial available resource value.
The first reference resource value and the second reference resource value are added to determine an initial available resource value of the current child node, and then the available resource value of the current child node can be determined by multiplying the upper limit of the processor core number (resource upper limit) of the current child node by the initial available resource value.
In an embodiment provided by the present application, along the above example, if the first reference available resource value is 0.402 and the second reference available resource value is 0.268, the initial available resource value of the current child node is 0.402+0.268 — 0.67, the upper limit of the CPU resource of the current child node is 18 cores, and the available resource value of the current child node is 18 × 0.67 — 12.06 cores.
After the available resource value of the current child node is calculated and determined, the available resource value is registered in the state information of the current child node, and the current child node can provide the extended resource with the size of the available resource value.
Step 108: and determining a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value.
After the available resource value of each child node is determined, the child node to which the target container is deployed can be determined by combining the target resource value, the child node to which the target container is deployed is the target child node, and the available resource value of the target child node is larger than the target resource value.
Optionally, determining a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value, includes:
determining an initial target child node set, wherein an available resource value of each initial target child node in the initial target child node set is greater than the target resource value;
a target child node is determined in the initial set of target child nodes.
In practical application, the child nodes are screened according to the available resource value and the target resource value, the child nodes with the available resource value larger than the target resource value form an initial target child node set, and then a target child node is determined from the initial target child node set and used for deploying the target container to the target child node.
Specifically, determining a target child node in the initial target child node set includes:
determining an initial target child node with the minimum processor load value in the initial target child node set as a target child node; or
Determining an initial target child node with the minimum difference value between the available resource value and the target resource value in the initial target child node set as a target child node; or
And randomly determining an initial target child node as a target child node in the initial target child node set.
For example, the child node with the minimum processor load value in the initial target child node set can be determined as the target child node, and the minimum processor load value indicates that the task ratio of the child node is smaller and the processing speed is higher; the child node with the minimum difference value between the available resource value and the target resource value can be selected as the target child node, so that the available resource value of the child node can be fully utilized, and the utilization rate of the container cluster is improved; and randomly selecting one initial target child node from the initial target child node set as a target child node. In the present application, the specific manner how to select the target child node from the initial target child node set is not limited, and the actual application is mainly used.
In a specific embodiment provided by the present application, following the above example, if the target resource value of the target container B is 6 cores, there are 3 child nodes in the container cluster, the available resource value of the child node 1 is 7 cores, the available resource value of the child node 2 is 12.08 cores, and the available resource value of the child node 3 is 3 cores, it may be determined that the child node 1 and the child node 2 are initial target child nodes, at this time, the processor load value of the child node 1 is 40, and the processor load value of the child node 2 is 25, and it is determined that the child node 2 is a target child node.
Step 110: and deploying the target container corresponding to the target task at the target child node.
And after the target child node is determined, scheduling the target container corresponding to the target task to the target child node for execution, and finishing the deployment of the target task.
In a specific embodiment provided by the present application, following the above example, the child node 2 is determined to be a target child node, the target container B is scheduled to the child node 2, and the corresponding offline task T is executed in the child node 2.
Optionally, the target task includes a task type;
before deploying the target container corresponding to the target task at the target child node, the method further includes:
and under the condition that the task type of the target task is a resident node offline task, setting a container quota value corresponding to the target container to be smaller than a preset threshold value.
Specifically, the container quota value corresponding to the target container comprises a first quota value and a second quota value;
setting the container quota value corresponding to the target container to be smaller than a preset threshold value, specifically including:
and setting a first quota value and a second quota value corresponding to the target container to be smaller than a preset threshold value.
Correspondingly, the method further comprises the following steps:
acquiring an available resource value of the target child node;
and updating a second quota value corresponding to the target container according to the available resource value.
In practical applications, some offline tasks are often required to reside on a certain node, such as model training tasks, such offline tasks that need to reside on a certain node are called node-resident offline tasks, in the prior art, if the node is in a resource utilization peak period, the long-node offline tasks are usually turned off, and in order to ensure that a target container corresponding to the task may not be turned off, when the target container is created, both a quota value (CPU Request) and a processor upper Limit (CPU Limit) of the target container are set to a smaller value, where the specific value is based on the practical application.
The first quota value is the CPU Request, the second quota value is the CPU Limit, the CPU Request and the CPU Limit are set to be smaller values, the target container can be dispatched to the child node by the container cluster, the available resource value of the current child node is obtained at fixed intervals, and the CPU Limit is dynamically adjusted according to the available resource value of the current child node, so that the CPU Limit of the target container can be expanded or reduced along with the available resource value of the current child node, and the resident node offline task cannot be closed during the CPU resource use peak period.
Optionally, each child node in the container cluster is configured with a node label;
the method further comprises the following steps:
receiving a modification instruction aiming at a preset resource calculation strategy, wherein the modification instruction carries a modification node label;
and responding to the modification instruction, and modifying the resource calculation strategy in the child node corresponding to the modification node label.
In order to facilitate management, corresponding node labels can be configured for each child node, policy matching rules are set, different node labels are mapped to different resource calculation policies, when a modification instruction of the resource calculation policy for a certain node label is received, the resource calculation policy in each child node with the same node label can be modified, the modification efficiency and accuracy are improved, and unified management is facilitated.
The task deployment method in the container cluster comprises the steps of receiving a task request of a target task; responding to the task request to create a target container for the target task, wherein the target container comprises a target resource value corresponding to the target container; calculating an available resource value of each child node in the container cluster according to a preset resource calculation strategy; determining a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value; the target container corresponding to the target task is deployed at the target child node, and by the task deployment method in the container cluster, the available resource value can be dynamically calculated according to the actual load condition of each child node in the container cluster, the target container is scheduled according to the available resource value, the target task is deployed, the resource utilization rate of the container cluster is improved, and the hardware cost for deploying the container cluster is reduced.
Secondly, for the resident node offline task, the CPU Limit of the target container can be dynamically expanded and contracted according to the available resource value of the child node, the resident node offline task is not closed, and the CPU usage amount of the resident node offline task can be dynamically limited.
Finally, the resource calculation strategies of the nodes can be automatically configured in batch in a mode of setting the node labels, the workload of manual node-by-node setting is reduced, the probability of possible errors caused by manual processing is reduced, and the working efficiency is improved.
Referring to fig. 2, fig. 2 shows a schematic structural diagram for deploying an offline task in a container cluster provided by the present application, as shown in fig. 2, an available resource value calculation component in a child node 202 of the container cluster calculates an available resource value of a current child node, and reports the available resource value as an extended resource to an api-server 204, the api-server 204 receives the created offline task, after acquiring an available resource value of each child node, schedules a container of the online task according to a CPU Request of each node according to a container cluster scheduler, and schedules a container of the offline task according to an extended resource (coordination-CPU) of each node. The offline tasks can be dynamically scheduled to the target child nodes according to the available resource values of the child nodes, and the utilization rate of container cluster resources is maximized.
Referring to fig. 3, fig. 3 is a schematic structural diagram illustrating a resident node offline task deployment according to an embodiment of the present application, as shown in fig. 3, the resident node offline task is scheduled on the container cluster sub-node 302, the container cluster sub-node 302 calculates the available resource value of the current sub-node through the available resource value calculation component, and uses the available resource value as the extended resource of the current sub-node, meanwhile, the cpu limit of the offline task is modified according to the available resource value and reported to the api-server 304, after the api-server 304 obtains the cpu limit of the offline task and changes, informing the kubel component in the container cluster child node 302 that the cpu limit value of the container corresponding to the offline task is directly modified by the kubel component without restarting the target container corresponding to the offline task, and under the condition of no sense of the user, dynamically adjusting the upper limit of the available resources of the container according to the available resource value of the current child node. The offline task is ensured not to be closed by the node when the current node resource occupies a higher amount.
Referring to fig. 4, fig. 4 is a schematic structural diagram illustrating a computing policy for automatically managing node resources in a container cluster according to an embodiment of the present application, as shown in fig. 4, in an actual application, a user invokes the available resource value configuration management module 406 to add a rule: the node labeled with pool ═ main is mapped to the available resource value configuration management module 406, the user adds the label pool ═ main to the container cluster sub-nodes 4022, 4024, etc., the kubel component in the sub-node reports the node modification event to the api-server 404, the available resource value configuration management module 406 monitors the node modification event through the api-server 404 and extracts the node label "pool ═ main" of each sub-node, matches the corresponding resource calculation policy T according to the label, and pushes the resource calculation policy T to the container cluster sub-node 4022 and the container cluster sub-node 4024. When a user modifies the resource calculation strategy T and modifies the resource calculation strategy T into a resource calculation strategy P, the available resource value configuration management module 406 finds out all sub-nodes with node labels of "pool ═ main" and pushes the resource calculation strategy P to the sub-nodes, thereby achieving the purpose of automatic joint node resource calculation strategy.
Corresponding to the embodiment of the task deployment method in the container cluster, the present application further provides an embodiment of a task deployment device in the container cluster, and fig. 5 shows a schematic structural diagram of the task deployment device in the container cluster according to an embodiment of the present application. As shown in fig. 5, the apparatus includes:
a first receiving module 502 configured to receive a task request of a target task;
a creating module 504 configured to create a target container for the target task in response to the task request, wherein the target container includes a target resource value corresponding to the target container;
a calculating module 506, configured to calculate an available resource value of each child node in the container cluster according to a preset resource calculation policy;
a determining module 508 configured to determine a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value;
a deployment module 510 configured to deploy the target container corresponding to the target task at the target child node.
Optionally, the preset resource calculation policy includes a resource calculation parameter;
the calculation module 506, further configured to:
acquiring the processor utilization rate and the processor load value of the current child node in a preset time interval;
and determining the available resource value of the current child node according to the processor utilization rate, the processor load value and the resource calculation parameter.
Optionally, the resource calculation parameters include a first parameter and a second parameter;
the calculation module 506, further configured to:
determining a first reference available resource value according to the processor utilization and the first parameter;
determining a second reference available resource value based on the processor load value and the second parameter;
determining an available resource value for the current child node based on the first reference available resource value and the second reference available resource value.
Optionally, the first parameter includes a first weight value and a first threshold interval;
the calculation module 506, further configured to:
determining an initial first reference available resource value according to the processor utilization and the first threshold interval;
determining a first reference available resource value as a function of the initial first reference available resource value and the first weight value.
Optionally, the first threshold interval includes a first threshold minimum value and a first threshold maximum value;
the calculation module 506, further configured to:
determining an initial first reference available resource value to be 1 if the processor usage is less than or equal to the first threshold minimum value;
determining an initial first reference available resource value to be 0 if the processor usage is greater than or equal to the first threshold maximum value;
determining an initial first reference available resource value as a function of the processor usage, the first threshold minimum value, and the first threshold maximum value if the processor usage is less than the first threshold maximum value and greater than the first threshold minimum value.
Optionally, the second parameter includes a second weight value and a second threshold interval;
the calculation module 506, further configured to:
determining an initial second reference available resource value according to the processor load value and the second threshold interval;
determining a second reference available resource value according to the initial second reference available resource value and the second weight value.
Optionally, the second threshold interval includes a second threshold minimum value and a second threshold maximum value;
the calculation module 506, further configured to:
determining an initial second reference available resource value to be 1 if the processor load value is less than or equal to the second threshold minimum value;
determining an initial second reference available resource value to be 0 if the processor load value is greater than or equal to the second threshold maximum value;
determining an initial second reference available resource value as a function of the processor usage, the second threshold minimum, and the second threshold maximum, if the processor load value is less than the second threshold maximum and greater than the second threshold minimum.
Optionally, the calculating module 506 is further configured to:
determining an initial available resource value of the current child node according to the first reference available resource value and the second reference available resource value;
and determining the available resource value of the current child node according to the processor core number of the current child node and the initial available resource value.
Optionally, the calculating module 506 is further configured to:
and acquiring the average processor utilization rate and the average processor load value of the current child node in a preset time interval.
Optionally, the determining module 508 is further configured to:
determining an initial target child node set, wherein an available resource value of each initial target child node in the initial target child node set is greater than the target resource value;
a target child node is determined in the initial set of target child nodes.
Optionally, the determining module 508 is further configured to:
determining an initial target child node with the minimum processor load value in the initial target child node set as a target child node; or
Determining an initial target child node with the minimum difference value between the available resource value and the target resource value in the initial target child node set as a target child node; or
And randomly determining an initial target child node as a target child node in the initial target child node set.
Optionally, the target task includes a task type;
the device further comprises:
the setting module is configured to set a container quota value corresponding to the target container to be smaller than a preset threshold value under the condition that the task type of the target task is a resident node offline task.
Optionally, the container quota value corresponding to the target container includes a first quota value and a second quota value;
the setting module is further configured to set a first quota value and a second quota value corresponding to the target container to be smaller than a preset threshold value.
Optionally, the apparatus further comprises:
an obtaining module configured to obtain an available resource value of the target child node;
an updating module configured to update a second quota value corresponding to the target container according to the available resource value.
Optionally, each child node in the container cluster is configured with a node label;
the device further comprises:
the second receiving module is configured to receive a modification instruction aiming at a preset resource calculation strategy, wherein the modification instruction carries a modification node label;
and the modification module is configured to respond to the modification instruction and modify the resource calculation strategy in the child node corresponding to the modification node label.
The task deployment device in the container cluster comprises a task request receiving a target task; responding to the task request to create a target container for the target task, wherein the target container comprises a target resource value corresponding to the target container; calculating an available resource value of each child node in the container cluster according to a preset resource calculation strategy; determining a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value; the target container corresponding to the target task is deployed at the target child node, the task deployment device in the container cluster can dynamically calculate the available resource value according to the actual load condition of each child node in the container cluster, and the target container is scheduled according to the available resource value, so that the target task is deployed, the resource utilization rate of the container cluster is improved, and the hardware cost for deploying the container cluster is reduced.
Secondly, for the resident node offline task, the CPU Limit of the target container can be dynamically expanded and contracted according to the available resource value of the child node, the resident node offline task is not closed, and the CPU usage amount of the resident node offline task can be dynamically limited.
Finally, the resource calculation strategies of the nodes can be automatically configured in batch in a mode of setting the node labels, the workload of manual node-by-node setting is reduced, the probability of possible errors caused by manual processing is reduced, and the working efficiency is improved.
The above is an exemplary scheme of a task deployment device in a container cluster according to this embodiment. It should be noted that the technical solution of the task deployment device in the container cluster and the technical solution of the task deployment method in the container cluster belong to the same concept, and details of the technical solution of the task deployment device in the container cluster, which are not described in detail, can be referred to the description of the technical solution of the task deployment method in the container cluster.
Fig. 6 illustrates a block diagram of a computing device 600 provided according to an embodiment of the present application. The components of the computing device 600 include, but are not limited to, a memory 610 and a processor 620. The processor 620 is coupled to the memory 610 via a bus 630 and a database 650 is used to store data.
Computing device 600 also includes access device 640, access device 640 enabling computing device 600 to communicate via one or more networks 660. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. Access device 640 may include one or more of any type of network interface (e.g., a Network Interface Card (NIC)) whether wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.
In one embodiment of the present application, the above-described components of computing device 600, as well as other components not shown in FIG. 6, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 6 is for purposes of example only and is not limiting as to the scope of the present application. Those skilled in the art may add or replace other components as desired.
Computing device 600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smartphone), wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 600 may also be a mobile or stationary server.
Wherein, the processor 620 implements the steps of the task deployment method in the container cluster when executing the computer instructions.
The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the task deployment method in the container cluster belong to the same concept, and details that are not described in detail in the technical solution of the computing device can be referred to the description of the technical solution of the task deployment method in the container cluster.
An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions, and the computer instructions, when executed by a processor, implement the steps of the task deployment method in the container cluster as described above.
The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same concept as the technical solution of the task deployment method in the container cluster, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the task deployment method in the container cluster.
The foregoing description of specific embodiments of the present application has been presented. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that, for the sake of simplicity, the above-mentioned method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The preferred embodiments of the present application disclosed above are intended only to aid in the explanation of the application. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the application and its practical applications, to thereby enable others skilled in the art to best understand and utilize the application. The application is limited only by the claims and their full scope and equivalents.
Claims (18)
1. A task deployment method in a container cluster is characterized by comprising the following steps:
receiving a task request of a target task;
responding to the task request to create a target container for the target task, wherein the target container comprises a target resource value corresponding to the target container;
calculating an available resource value of each child node in the container cluster according to a preset resource calculation strategy;
determining a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value;
and deploying the target container corresponding to the target task at the target child node.
2. The method for task deployment in a container cluster according to claim 1, wherein the preset resource computation policy includes a resource computation parameter;
calculating an available resource value of each child node in the container cluster according to a preset resource calculation strategy, wherein the method comprises the following steps:
acquiring the processor utilization rate and the processor load value of the current child node in a preset time interval;
and determining the available resource value of the current child node according to the processor utilization rate, the processor load value and the resource calculation parameter.
3. The method for task deployment in a container cluster according to claim 2, wherein the resource computation parameters include a first parameter and a second parameter;
determining an available resource value of the current child node according to the processor utilization, the processor load value, and the resource calculation parameter, including:
determining a first reference available resource value according to the processor utilization and the first parameter;
determining a second reference available resource value based on the processor load value and the second parameter;
determining an available resource value for the current child node based on the first reference available resource value and the second reference available resource value.
4. The method for task deployment in a container cluster according to claim 3, wherein the first parameter comprises a first weight value, a first threshold interval;
determining a first reference available resource value based on the processor utilization and the first parameter, comprising:
determining an initial first reference available resource value according to the processor utilization and the first threshold interval;
determining a first reference available resource value as a function of the initial first reference available resource value and the first weight value.
5. The method for task deployment in a container cluster according to claim 4, wherein the first threshold interval comprises a first threshold minimum value and a first threshold maximum value;
determining an initial first reference available resource value based on the processor utilization and the first threshold interval, comprising:
determining an initial first reference available resource value to be 1 if the processor usage is less than or equal to the first threshold minimum value;
determining an initial first reference available resource value to be 0 if the processor usage is greater than or equal to the first threshold maximum value;
determining an initial first reference available resource value as a function of the processor usage, the first threshold minimum value, and the first threshold maximum value if the processor usage is less than the first threshold maximum value and greater than the first threshold minimum value.
6. The method for task deployment in a container cluster according to claim 3, wherein the second parameter comprises a second weight value, a second threshold interval;
determining a second reference available resource value based on the processor load value and the second parameter, comprising:
determining an initial second reference available resource value according to the processor load value and the second threshold interval;
determining a second reference available resource value according to the initial second reference available resource value and the second weight value.
7. The method for task deployment in a container cluster according to claim 6, wherein the second threshold interval comprises a second threshold minimum value and a second threshold maximum value;
determining an initial second reference available resource value based on the processor load value and the second threshold interval, comprising:
determining an initial second reference available resource value to be 1 if the processor load value is less than or equal to the second threshold minimum value;
determining an initial second reference available resource value to be 0 if the processor load value is greater than or equal to the second threshold maximum value;
determining an initial second reference available resource value as a function of the processor usage, the second threshold minimum, and the second threshold maximum, if the processor load value is less than the second threshold maximum and greater than the second threshold minimum.
8. The method for task deployment in a container cluster according to claim 3, wherein determining the available resource value of the current child node according to the first reference available resource value and the second reference available resource value comprises:
determining an initial available resource value of the current child node according to the first reference available resource value and the second reference available resource value;
and determining the available resource value of the current child node according to the processor core number of the current child node and the initial available resource value.
9. The method for deploying tasks in a container cluster according to any one of claims 2 to 8, wherein the obtaining of the processor utilization rate and the processor load value of the current child node in the preset time interval comprises:
and acquiring the average processor utilization rate and the average processor load value of the current child node in a preset time interval.
10. The method for task deployment in a container cluster according to claim 1, wherein determining the target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value comprises:
determining an initial target child node set, wherein an available resource value of each initial target child node in the initial target child node set is greater than the target resource value;
a target child node is determined in the initial set of target child nodes.
11. The method for task deployment in a container cluster of claim 10, wherein determining a target child node in the initial set of target child nodes comprises:
determining an initial target child node with the minimum processor load value in the initial target child node set as a target child node; or
Determining an initial target child node with the minimum difference value between the available resource value and the target resource value in the initial target child node set as a target child node; or
And randomly determining an initial target child node as a target child node in the initial target child node set.
12. The method for task deployment in a container cluster according to claim 1, wherein the target task comprises a task type;
the method further comprises the following steps:
and under the condition that the task type of the target task is a resident node offline task, setting a container quota value corresponding to the target container to be smaller than a preset threshold value.
13. The method for task deployment in a container cluster according to claim 12, wherein the container quota value corresponding to the target container comprises a first quota value and a second quota value;
setting a container quota value corresponding to the target container to be smaller than a preset threshold value, including:
and setting a first quota value and a second quota value corresponding to the target container to be smaller than a preset threshold value.
14. The method for task deployment in a container cluster according to claim 13, the method further comprising:
acquiring an available resource value of the target child node;
and updating a second quota value corresponding to the target container according to the available resource value.
15. The method for task deployment in a container cluster according to claim 1, wherein each child node in the container cluster is configured with a node label;
the method further comprises the following steps:
receiving a modification instruction aiming at a preset resource calculation strategy, wherein the modification instruction carries a modification node label;
and responding to the modification instruction, and modifying the resource calculation strategy in the child node corresponding to the modification node label.
16. A task deployment apparatus in a container cluster, comprising:
a first receiving module configured to receive a task request of a target task;
a creating module configured to create a target container for the target task in response to the task request, wherein the target container includes a target resource value corresponding to the target container;
the computing module is configured to compute an available resource value of each child node in the container cluster according to a preset resource computing strategy;
a determining module configured to determine a target child node corresponding to the target container according to the available resource value of each child node in the container cluster and the target resource value;
and the deployment module is configured to deploy the target container corresponding to the target task at the target child node.
17. A computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-15 when executing the computer instructions.
18. A computer-readable storage medium storing computer instructions, which when executed by a processor, perform the steps of the method of any one of claims 1 to 15.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110124547.2A CN112783607A (en) | 2021-01-29 | 2021-01-29 | Task deployment method and device in container cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110124547.2A CN112783607A (en) | 2021-01-29 | 2021-01-29 | Task deployment method and device in container cluster |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112783607A true CN112783607A (en) | 2021-05-11 |
Family
ID=75759705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110124547.2A Pending CN112783607A (en) | 2021-01-29 | 2021-01-29 | Task deployment method and device in container cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112783607A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113312153A (en) * | 2021-06-25 | 2021-08-27 | 深信服科技股份有限公司 | Cluster deployment method and device, electronic equipment and storage medium |
| CN113419818A (en) * | 2021-06-23 | 2021-09-21 | 北京达佳互联信息技术有限公司 | Basic component deployment method, device, server and storage medium |
| CN113590317A (en) * | 2021-07-27 | 2021-11-02 | 杭州朗和科技有限公司 | Scheduling method, device, medium and computing equipment of offline service |
| CN113760549A (en) * | 2021-08-30 | 2021-12-07 | 聚好看科技股份有限公司 | Pod deployment method and device |
| CN113886050A (en) * | 2021-10-21 | 2022-01-04 | 中国联合网络通信集团有限公司 | Pressure testing method, device, equipment and storage medium |
| CN116954869A (en) * | 2023-09-18 | 2023-10-27 | 武汉信安珞珈科技有限公司 | Task scheduling system, method and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110221915A (en) * | 2019-05-21 | 2019-09-10 | 新华三大数据技术有限公司 | Node scheduling method and apparatus |
| CN110597623A (en) * | 2019-08-13 | 2019-12-20 | 平安普惠企业管理有限公司 | Container resource allocation method and device, computer equipment and storage medium |
| CN111464616A (en) * | 2020-03-30 | 2020-07-28 | 招商局金融科技有限公司 | Method, server and storage medium for automatically adjusting number of application load services |
| CN112015536A (en) * | 2020-08-28 | 2020-12-01 | 北京浪潮数据技术有限公司 | Kubernetes cluster container group scheduling method, device and medium |
| CN112217676A (en) * | 2020-10-13 | 2021-01-12 | 北京工业大学 | Kubernetes container cluster node selection method based on mixed element heuristic algorithm |
-
2021
- 2021-01-29 CN CN202110124547.2A patent/CN112783607A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110221915A (en) * | 2019-05-21 | 2019-09-10 | 新华三大数据技术有限公司 | Node scheduling method and apparatus |
| CN110597623A (en) * | 2019-08-13 | 2019-12-20 | 平安普惠企业管理有限公司 | Container resource allocation method and device, computer equipment and storage medium |
| CN111464616A (en) * | 2020-03-30 | 2020-07-28 | 招商局金融科技有限公司 | Method, server and storage medium for automatically adjusting number of application load services |
| CN112015536A (en) * | 2020-08-28 | 2020-12-01 | 北京浪潮数据技术有限公司 | Kubernetes cluster container group scheduling method, device and medium |
| CN112217676A (en) * | 2020-10-13 | 2021-01-12 | 北京工业大学 | Kubernetes container cluster node selection method based on mixed element heuristic algorithm |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113419818A (en) * | 2021-06-23 | 2021-09-21 | 北京达佳互联信息技术有限公司 | Basic component deployment method, device, server and storage medium |
| CN113312153A (en) * | 2021-06-25 | 2021-08-27 | 深信服科技股份有限公司 | Cluster deployment method and device, electronic equipment and storage medium |
| CN113590317A (en) * | 2021-07-27 | 2021-11-02 | 杭州朗和科技有限公司 | Scheduling method, device, medium and computing equipment of offline service |
| CN113760549A (en) * | 2021-08-30 | 2021-12-07 | 聚好看科技股份有限公司 | Pod deployment method and device |
| CN113760549B (en) * | 2021-08-30 | 2024-03-15 | 聚好看科技股份有限公司 | Pod deployment method and device |
| CN113886050A (en) * | 2021-10-21 | 2022-01-04 | 中国联合网络通信集团有限公司 | Pressure testing method, device, equipment and storage medium |
| CN116954869A (en) * | 2023-09-18 | 2023-10-27 | 武汉信安珞珈科技有限公司 | Task scheduling system, method and equipment |
| CN116954869B (en) * | 2023-09-18 | 2023-12-19 | 武汉信安珞珈科技有限公司 | Task scheduling system, method and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112783607A (en) | Task deployment method and device in container cluster | |
| CN111897654B (en) | Method and device for migrating application to cloud platform, electronic equipment and storage medium | |
| CN102591921A (en) | Scheduling and management in a personal datacenter | |
| CN111949324A (en) | Distributed serial number generation method and device | |
| CN115134371A (en) | Scheduling method, system, equipment and medium containing edge network computing resources | |
| CN111796933A (en) | Resource scheduling method, device, storage medium and electronic equipment | |
| CN114546646A (en) | Processing method and processing apparatus | |
| CN112948088A (en) | Cloud workflow intelligent management and scheduling system in cloud computing platform | |
| CN113434591B (en) | Data processing method and device | |
| Raj et al. | Load balancing for resource provisioning using batch mode heuristic priority in round robin (pbrr) scheduling | |
| CN114253708A (en) | Load scheduling method and system | |
| CN114546647A (en) | Scheduling method and scheduling device | |
| CN114466365A (en) | Spectrum resource acquisition method, spectrum resource acquisition device and computer readable storage medium | |
| CN113687952A (en) | Information processing method, device, equipment and storage medium | |
| CN111324444A (en) | Cloud computing task scheduling method and device | |
| CN112579246A (en) | Virtual machine migration processing method and device | |
| CN113296870B (en) | Method and device for predicting Kubernetes cluster configuration | |
| CN116909758B (en) | Processing method and device of calculation task and electronic equipment | |
| CN114710485B (en) | Processing method and processing device | |
| CN117707797B (en) | Task scheduling method and device based on distributed cloud platform and related equipment | |
| Aljabri et al. | Scheduling manager for mobile cloud using multi-agents | |
| CN117221326A (en) | Software load balancing scheduling method, system, electronic equipment and storage medium | |
| CN112783608A (en) | Method and device for adjusting container resources in container cluster | |
| CN115277862A (en) | Container-based resource scheduling method and device | |
| CN115237005A (en) | Control method and device for powering on equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210511 |