CN112286673B - Node resource allocation method and device - Google Patents

Node resource allocation method and device Download PDF

Info

Publication number
CN112286673B
CN112286673B CN201910662019.5A CN201910662019A CN112286673B CN 112286673 B CN112286673 B CN 112286673B CN 201910662019 A CN201910662019 A CN 201910662019A CN 112286673 B CN112286673 B CN 112286673B
Authority
CN
China
Prior art keywords
resource
resources
type
application program
node
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.)
Active
Application number
CN201910662019.5A
Other languages
Chinese (zh)
Other versions
CN112286673A (en
Inventor
马东辉
成彦斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing CHJ Automobile Technology Co Ltd
Original Assignee
Beijing CHJ Automobile Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing CHJ Automobile Technology Co Ltd filed Critical Beijing CHJ Automobile Technology Co Ltd
Priority to CN201910662019.5A priority Critical patent/CN112286673B/en
Publication of CN112286673A publication Critical patent/CN112286673A/en
Application granted granted Critical
Publication of CN112286673B publication Critical patent/CN112286673B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • 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
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
    • G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
    • 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
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention provides a node resource allocation method and a node resource allocation device, wherein the method comprises the following steps: acquiring the resource use condition of each node in the cluster; allocating first type resources and second type resources according to a resource usage scene and the resource usage situation of each node in the cluster, wherein the first type resources are resources used for application programs in the cluster in the node resources of the cluster, and the second type resources are resources used for application programs outside the cluster in the node resources of the cluster; and adjusting a resource scheduler of the Yarn resource manager according to the allocated first-class resources so that the resource scheduler schedules the allocated first-class resources. By the node resource allocation method provided by the invention, the resource allocation of the application program in the cluster and the resource allocation of the application program outside the cluster can be more flexible and reasonable, and the utilization rate of the resource can be further improved.

Description

Node resource allocation method and device
Technical Field
The present invention relates to the field of electronic technologies, and in particular, to a node resource allocation method and apparatus.
Background
To meet the processing requirements of big data, hadoop clusters are generated. A Hadoop cluster may typically include multiple nodes, which may be virtual machines or physical machines, such as servers. Each node in the Hadoop cluster has a certain resource for executing tasks, such as a CPU, a memory, a hard disk, etc., and various tasks can be executed by using the node resource.
Currently, node resources of a Hadoop cluster may be generally used to execute applications within the Hadoop cluster, for example, applications for implementing the business functions of the Hadoop cluster itself; the method can also be used for executing application programs outside the Hadoop cluster, namely application programs which are not used for realizing the self business functions of the Hadoop cluster, such as application programs which interact with the self business functions of the Hadoop cluster. However, in the prior art, the resource manager of the Hadoop cluster can only manage the resources for the application programs in the Hadoop cluster, but cannot effectively manage the resources for the application programs outside the Hadoop cluster. Therefore, in order to avoid resource conflict, resources for executing the application program in the Hadoop cluster and resources for executing the application program outside the Hadoop cluster are usually allocated in advance, but this way is easy to cause insufficient resources in some situations, and more waste of resources exists in other situations.
Therefore, the problem of low node resource utilization rate of the Hadoop cluster exists in the prior art.
Disclosure of Invention
The embodiment of the invention provides a node resource allocation method and device, which are used for solving the problem of low node resource utilization rate of a Hadoop cluster in the prior art.
In a first aspect, an embodiment of the present invention provides a node resource allocation method, where the method includes:
acquiring resource use conditions of all nodes in the Hadoop cluster;
According to a resource usage scene and the resource usage situation of each node in the Hadoop cluster, allocating first type resources and second type resources, wherein the first type resources are resources used for application programs in the Hadoop cluster in the node resources of the Hadoop cluster, and the second type resources are resources used for application programs outside the Hadoop cluster in the node resources of the Hadoop cluster;
and adjusting a resource scheduler of the Yarn resource manager according to the allocated first-class resources so that the resource scheduler schedules the allocated first-class resources.
Optionally, the allocating the first type of resources and the second type of resources according to the resource usage scenario and the resource usage situation of each node in the Hadoop cluster includes:
If the resource usage scenario is that a starting request of a first application program is received, if the second type of resources are determined not to meet the resource requirement of the first application program, allocating the first type of resources and the second type of resources according to the resource usage conditions of all nodes in the Hadoop cluster;
The first application program is an application program outside the Hadoop cluster, and the allocated second type of resources meet the resource requirement of the first application program.
Optionally, the second type of resource does not meet the resource requirement of the first application program, including at least one of:
the hollow resource amount in the second type of resources is smaller than the resource amount required by the first application program;
The second class of resources does not include resources of a first node, wherein the first node is a node designated by the first application program.
Optionally, after allocating the first type of resources and the second type of resources according to the resource usage situation and the resource usage situation of each node in the Hadoop cluster, the method further includes:
starting and operating the first application program by using the allocated second type resource;
And under the condition that the first application program finishes running, releasing node resources occupied by the first application program, and allocating the first type of resources and the second type of resources.
Optionally, the allocating the first type of resources and the second type of resources according to the resource usage situation and the resource usage situation of each node in the Hadoop cluster includes:
under the condition that the resource use scene is that a resource reservation request aiming at a second application program is received, allocating first-class resources and second-class resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster;
The second application program is an application program outside the Hadoop cluster, the resource reservation request comprises resource information for requesting reservation and a reservation time limit, and the resource indicated by the resource information is used for the second application program within the reservation time limit.
Optionally, under the situation that the resource usage scenario is that a resource reservation request for a second application program is received, allocating a first type of resource and a second type of resource according to the resource reservation request and a resource usage situation of each node in the Hadoop cluster, including:
under the condition that the resource usage scenario is that a resource reservation request for a second application program is received, determining whether to reserve resources for the second application program according to the priority of the second application program and the estimated use condition of resources indicated by the resource information within the reservation time limit;
And under the condition that the resources are reserved for the second application program, allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster.
Optionally, in the case that the resource usage scenario is that a resource reservation request for a second application program is received, after allocating a first type of resource and a second type of resource according to the resource reservation request and a resource usage condition of each node in the Hadoop cluster, the method further includes:
and starting and running the second application program by utilizing the resources indicated by the resource information within the reserved time limit.
In a second aspect, an embodiment of the present invention further provides a resource allocation apparatus, where the apparatus includes:
the acquisition module is used for acquiring the resource use condition of each node in the Hadoop cluster;
The first allocation module is used for allocating first type resources and second type resources according to a resource usage scene and resource usage conditions of all nodes in the Hadoop cluster, wherein the first type resources are resources used for application programs in the Hadoop cluster in the node resources of the Hadoop cluster, and the second type resources are resources used for application programs outside the Hadoop cluster in the node resources of the Hadoop cluster;
And the adjusting module is used for adjusting a resource scheduler of the Yarn resource manager according to the allocated first-class resources so that the resource scheduler schedules the allocated first-class resources.
Optionally, the first deployment module includes:
The first allocation unit is used for allocating the first type of resources and the second type of resources according to the resource use condition of each node in the Hadoop cluster if the second type of resources are determined to not meet the resource requirement of the first application program under the condition that the resource use scene is the starting request of the received first application program;
The first application program is an application program outside the Hadoop cluster, and the allocated second type of resources meet the resource requirement of the first application program.
Optionally, the second type of resource does not meet the resource requirement of the first application program, including at least one of:
the hollow resource amount in the second type of resources is smaller than the resource amount required by the first application program;
The second class of resources does not include resources of a first node, wherein the first node is a node designated by the first application program.
Optionally, the apparatus further includes:
The first control module is used for starting and operating the first application program by using the allocated second type resources after allocating the first type resources and the second type resources according to the resource use condition and the resource use condition of each node in the Hadoop cluster;
The second allocation module is used for releasing node resources occupied by the first application program and allocating the first type of resources and the second type of resources under the condition that the first application program finishes running.
Optionally, the first deployment module includes:
The second allocating unit is used for allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster under the condition that the resource use scene is that the resource reservation request for the second application program is received;
The second application program is an application program outside the Hadoop cluster, the resource reservation request comprises resource information for requesting reservation and a reservation time limit, and the resource indicated by the resource information is used for the second application program within the reservation time limit.
Optionally, the second allocating unit is specifically configured to:
under the condition that the resource usage scenario is that a resource reservation request for a second application program is received, determining whether to reserve resources for the second application program according to the priority of the second application program and the estimated use condition of resources indicated by the resource information within the reservation time limit;
And under the condition that the resources are reserved for the second application program, allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster.
Optionally, the apparatus further includes:
And the second control module is used for starting and running the second application program by utilizing the resources indicated by the resource information within the reservation time limit after allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster under the condition that the resource use scene is the resource reservation request for the second application program.
In a third aspect, an embodiment of the present invention further provides a resource allocation apparatus, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, where the computer program when executed by the processor implements the steps of the node resource allocation method described above.
In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the steps of the node resource allocation method described above.
In the embodiment of the invention, the resource for the application program in the Hadoop cluster and the resource for the application program outside the Hadoop cluster are allocated by acquiring the resource use condition of each node in the Hadoop cluster and according to the resource use condition of each node in the Hadoop cluster and the resource use condition of each node in the Hadoop cluster, so that the resource for the application program in the Hadoop cluster and the resource for the application program outside the Hadoop cluster are allocated more flexibly and reasonably, and the utilization rate of the resource can be improved. In addition, the resource scheduler of the Yarn resource manager is adjusted according to the allocated first-class resources, so that the resource scheduler schedules the allocated first-class resources, and resource conflicts can be reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.
FIG. 1 is a flowchart of a node resource allocation method provided by an embodiment of the present invention;
FIG. 2 is a schematic diagram of a network architecture to which embodiments of the present invention are applicable;
FIG. 3 is a block diagram of a resource allocation device according to an embodiment of the present invention;
fig. 4 is a block diagram of a resource allocation apparatus according to another embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention provides a node resource allocation method which can be applied to a resource allocation device, wherein the resource allocation device can be a server. Referring to fig. 1, fig. 1 is a flowchart of a node resource allocation method provided by an embodiment of the present invention, as shown in fig. 1, including the following steps:
and 101, acquiring the resource use condition of each node in the Hadoop cluster.
In the embodiment of the present invention, the Hadoop cluster may include a plurality of nodes, where each node may be a virtual machine or a physical machine, for example, a server. The resources of the node may include resources such as a CPU, a memory, and a hard disk, and the resource usage of the node may include, but is not limited to, a CPU usage rate of the node, a memory usage rate, and a hard disk usage rate.
In the step, the resource utilization condition of each node of the Hadoop cluster can be actively requested by the resource allocation device, or the resource utilization condition can be actively reported by each node to the resource allocation device. For example, the resource allocation device can actively request the resource usage of each node to the Yarn resource manager; or the yan resource manager actively reports the resource use condition of each node to the resource allocation device, for example, the yan resource manager may collect the resource use condition of each node in the Hadoop cluster to the resource allocation device in a heartbeat manner.
102, Allocating a first type of resources and a second type of resources according to a resource usage scene and resource usage conditions of all nodes in the Hadoop cluster;
The first type of resources are resources used for application programs in the Hadoop cluster in node resources of the Hadoop cluster, and the second type of resources are resources used for application programs outside the Hadoop cluster in node resources of the Hadoop cluster.
In the embodiment of the present invention, the above-mentioned resource usage scenario may be determined based on one or more of a size of a resource required by an application program in the Hadoop cluster to be executed, a size of a resource required by an application program outside the Hadoop cluster to be executed, a priority of an application program to be executed, whether an application program requiring a reserved resource exists, and the like. Alternatively, multiple resource usage scenarios may be divided in advance, for example, there are only scenarios in which an application program in the Hadoop cluster needs to execute, scenarios in which an application program outside the Hadoop cluster needs to execute, scenarios in which an application program needing to reserve resources exists, scenarios in which an application program inside the Hadoop cluster needs to execute, and scenarios in which the size of resources required by an application program outside the Hadoop cluster changes, and so on.
The application program in the Hadoop cluster can be understood as an application program for realizing the service function of the Hadoop cluster. For example, if the service function of a certain Hadoop cluster is order processing, that is, the node resource of the Hadoop cluster is mainly used for order processing, the relevant application program for implementing order processing on the Hadoop cluster is an application program in the Hadoop cluster. Applications outside the Hadoop cluster may be understood as applications not used to implement the business functions of the Hadoop cluster itself, or applications other than those within the Hadoop cluster. For example, an application program that interacts with the Hadoop cluster's own business functions.
In practical applications, the node resources of the Hadoop cluster may be used for executing the application program in the Hadoop cluster, or may be used for executing the application program outside the Hadoop cluster, that is, the node resources of the Hadoop cluster may be allocated as the resources for the application program in the Hadoop cluster (i.e., the first type of resources) and the resources for the application program outside the Hadoop cluster (i.e., the second type of resources).
And step 103, adjusting a resource scheduler of the Yarn resource manager according to the allocated first-class resources so that the resource scheduler schedules the allocated first-class resources.
In the embodiment of the invention, after the first type of resources and the second type of resources are allocated each time, the resource scheduler of the Yarn resource manager can be adjusted according to the allocated first type of resources, so that the resource scheduler only schedules the allocated first type of resources, and resource conflict is avoided.
In the embodiment of the invention, the first type of resources and the second type of resources can be dynamically allocated according to the resource usage scene and the resource usage situation of each node in the Hadoop cluster. For example, in the case of initialization, the first type of resources and the second type of resources may be allocated according to a default allocation proportion; under the condition that more resources are required to be used by application programs in the Hadoop cluster is monitored, the size of the first type of resources can be increased and the size of the second type of resources can be decreased based on the resource use condition of each node in the Hadoop cluster; under the condition that more resources are required by application programs outside the Hadoop cluster, the size of the first type of resources can be reduced and the size of the second type of resources can be increased according to the resource use condition of each node in the Hadoop cluster. Because the first type of resources and the second type of resources can be allocated according to the resource usage field Jing Dongtai, the utilization rate of the resources can be effectively improved under the condition of avoiding resource conflict. In addition, the resource scheduler of the Yarn resource manager is adjusted according to the allocated first-class resources, so that the resource scheduler schedules the allocated first-class resources, and resource conflicts can be reduced.
Optionally, the step 102 of allocating the first type of resources and the second type of resources according to the resource usage scenario and the resource usage situation of each node in the Hadoop cluster may include:
if the resource usage scenario is that a starting request of a first application program is received, if the second type of resources are determined not to meet the resource requirement of the first application program, allocating the first type of resources and the second type of resources according to the resource usage conditions of all nodes in the Hadoop cluster;
The first application program is an application program outside the Hadoop cluster, and the allocated second type of resources meet the resource requirement of the first application program.
In the embodiment of the present invention, the first application may be any application outside the Hadoop cluster. The initiation request may include a resource requirement of the first application, for example, a size of the resource required by the first application. For applications that need to execute on a specified node, the resource requirements of the first application may also include specified node information.
Specifically, under the condition that a starting request of the first application program is received, whether the current second type of resources meet the resource requirement of the first application program or not can be judged, for example, whether the amount of idle resources in the second type of resources is larger than or equal to the amount of resources required by the first application program or not is judged; or whether the second type of resource includes a designated node resource, etc.
Optionally, the second type of resource does not meet the resource requirement of the first application program, including at least one of:
the hollow resource amount in the second type of resources is smaller than the resource amount required by the first application program;
The second class of resources does not include resources of a first node, wherein the first node is a node designated by the first application program.
In the embodiment of the invention, under the condition that the current second type resource does not meet the resource requirement of the first application program, the first type resource and the second type resource can be allocated according to the resource use condition of each node in the Hadoop cluster, and the allocated second type resource is utilized to start and operate the first application program.
The above-mentioned free resources may be understood as unoccupied resources, such as unoccupied memory space, unoccupied hard disk space, unoccupied CPU resources, and the like. The amount of hollow resources in the second class of resources is smaller than the amount of resources required by the first application program, and may include, but is not limited to, at least one of the following: the amount of unoccupied memory space in the second class of resources is less than the amount of memory space required by the first application program; the amount of unoccupied hard disk space in the second class of resources is smaller than the amount of hard disk space required by the first application program; the amount of unoccupied CPU resources in the second class of resources is less than the amount of CPU resources required by the first application.
In practical application, if the amount of idle resources in the second type of resources is smaller than the amount of resources required by the first application program, part of idle resources in the first type of resources can be allocated into the second type of resources according to the resource use condition of each node in the Hadoop cluster, so that the amount of idle resources in the allocated second type of resources can be larger than or equal to the amount of resources required by the first application program, and the first application program can be started and operated on the idle resources in the allocated second type of resources. If the second type of resources do not include the resources of the node specified by the first application program, and the specified node resources in the first type of resources are idle, the specified node resources can be allocated to the second type of resources, so that the first application program can be started and operated on the specified node resources. Optionally, if the designated node resource in the first type of resource is occupied, the designated node resource may be allocated as the second type of resource after the designated node has performed the current task.
Alternatively, under the condition that the current second type of resources are determined to meet the resource requirements of the first application program, the first application program can be started and operated by directly utilizing the current second type of resources.
The embodiment of the invention can allocate the first type of resources and the second type of resources based on the resource requirements of the application programs outside the Hadoop cluster and the resource use conditions of all nodes in the Hadoop cluster under the condition that the application programs outside the Hadoop cluster need to be operated, so that the execution of the application programs outside the Hadoop cluster can be ensured, and the flexibility of resource allocation and the utilization rate of resources can be improved.
Optionally, after allocating the first type of resources and the second type of resources according to the resource usage situation and the resource usage situation of each node in the Hadoop cluster, the method may further include:
starting and operating the first application program by using the allocated second type resource;
And under the condition that the first application program finishes running, releasing node resources occupied by the first application program, and allocating the first type of resources and the second type of resources.
In the embodiment of the invention, after the first type of resources and the second type of resources are allocated according to the resource use condition and the resource use condition of each node in the Hadoop cluster, the allocated second type of resources can be utilized to start and operate the first application program. Under the condition that the first application program finishes running, node resources occupied by the first application program can be released, and the first type of resources and the second type of resources can be allocated again. For example, the current first type of resource and second type of resource may be allocated as the first type of resource and second type of resource prior to the first application running.
It should be noted that, in the embodiment of the present invention, after the first type of resources and the second type of resources are allocated, the resource scheduler of the Yarn resource manager may be adjusted according to the first type of resources after being allocated again, so that the resource scheduler only schedules the first type of resources after being allocated again, thereby avoiding resource conflicts.
Under the condition that the first application program finishes running, the embodiment of the invention releases the node resources occupied by the first application program, and allocates the first type of resources and the second type of resources again, so that the occupied resources can be reduced, and the flexibility of resource allocation is improved.
Optionally, the step 102, that is, allocating the first type of resources and the second type of resources according to the resource usage situation and the resource usage scenario of each node in the Hadoop cluster may include:
under the condition that the resource use scene is that a resource reservation request aiming at a second application program is received, allocating first-class resources and second-class resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster;
The second application program is an application program outside the Hadoop cluster, the resource reservation request comprises resource information for requesting reservation and a reservation time limit, and the resource indicated by the resource information is used for the second application program within the reservation time limit.
In the embodiment of the present invention, the second application may be any application program outside the Hadoop cluster that needs to be executed at regular time. The resource information requested to be reserved is used to indicate the resource requested to be reserved, for example, the resource information requested to be reserved may be identification information of a node in the Hadoop cluster, so as to reserve the resource of the node. The reservation time period may be set according to the time for the second application program to be executed, for example, the application program B needs to be executed between 12 to 13 points per day, and the reservation time period may be between 12 to 13 points per day or between 11 to 13 points 30 minutes per day.
In practical application, when there is an application program (i.e., the second application program) outside the Hadoop cluster that needs to be executed at regular time, the resource allocation device may receive a resource reservation request for the second application program input by a user, and allocate resources according to the resource reservation request and resource usage conditions of each node in the Hadoop cluster, so as to ensure that resources indicated by resource information are used for the second application program during reservation time, and further ensure execution of the second application program. Alternatively, the resource allocation device may configure the timing task based on the resource reservation request to start and run the second application program at the timing using the resource indicated by the resource information.
Optionally, in the case that the resource usage scenario is that a resource reservation request for a second application program is received, after allocating the first type of resource and the second type of resource according to the resource reservation request and the resource usage situation of each node in the Hadoop cluster, the method may further include:
and starting and running the second application program by utilizing the resources indicated by the resource information within the reserved time limit.
Optionally, before the second application program is started, a resource scheduler of the Yarn resource manager may be adjusted according to the allocated first type of resources, so as to avoid resource conflicts when the resource scheduler schedules reserved resources (i.e., resources indicated by the resource information). And after the resource scheduler of the Yarn resource manager is adjusted according to the allocated first-class resources, starting and running a second application program by utilizing the reserved resources.
Optionally, under the condition that the second application program finishes running, the resources occupied by the second application program can be released, and the first type of resources and the second type of resources can be allocated again.
In the embodiment of the invention, under the condition that the application program (namely the second application program) outside the Hadoop cluster needing to be executed at fixed time exists, resource allocation is carried out according to the resource reservation request and the resource use condition of each node in the Hadoop cluster, so that the resource indicated by the resource information is used for the second application program in the reservation time limit, thereby ensuring the execution of the second application program.
Optionally, when the resource usage scenario is that a resource reservation request for a second application program is received, allocating a first type of resource and a second type of resource according to the resource reservation request and a resource usage condition of each node in the Hadoop cluster may include:
under the condition that the resource usage scenario is that a resource reservation request for a second application program is received, determining whether to reserve resources for the second application program according to the priority of the second application program and the estimated use condition of resources indicated by the resource information within the reservation time limit;
And under the condition that the resources are reserved for the second application program, allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster.
In practice, for some important services, it is often necessary to ensure that the application program for implementing the service executes preferentially. Therefore, the embodiment of the invention can set the priority of the application program for realizing each service according to the importance degree of each service, so that the application program with higher priority can be preferentially executed under the condition of resource conflict.
For example, in the case where the second application program needs to be executed by using the resource of the node a in the period T, if it is estimated that the resource of the node a is not occupied by other application programs in the period T according to the historical resource usage, it may be determined that the resource is reserved for the second application program; if the resources of the node a are estimated to be occupied by other application programs in the time period T according to the historical resource use condition, whether the resources are reserved for the second application program can be judged according to the priority of the second application program and the estimated priority of the third application program which occupies the resources of the node a in the time period T, if the priority of the second application program is higher than the priority of the third application program, the resources can be determined to be reserved for the second application program, otherwise, the resources are determined not to be reserved for the second application program.
The embodiment of the invention can determine whether to reserve resources for the second application program according to the priority of the second application program and the estimated use condition of the resources indicated by the resource information in the reservation time limit, and allocate the first type of resources and the second type of resources according to the resource reservation request and the use condition of the resources of each node in the Hadoop cluster under the condition that the resources are reserved for the second application program, so that the priority of the application program with higher priority can be ensured to be executed preferentially.
Embodiments of the present invention are described below with reference to examples:
For example, referring to fig. 2, the Hadoop cluster includes node #1, node #2, and node #3, and the yarn resource manager may allocate the node resources of the Hadoop cluster, i.e., the resources of node #1, node #2, and node #3, according to different policies. The resource allocation device can adjust a resource scheduler of the Yarn resource manager according to the allocated first-class resources and can manage application programs outside the Hadoop cluster. The resource allocation device may be a server.
It should be noted that, for each application program executing on the Hadoop cluster (i.e., the application program in the Hadoop cluster), the resource scheduler of the Yarn resource manager may allocate resources for each application program based on the use condition of the resources for the application program in the Hadoop cluster, and may execute the application programs in a distributed manner on different nodes.
In the embodiment of the invention, the Yarn resource manager can summarize the resource use condition of each node in the Hadoop cluster to the resource allocation device in a heartbeat mode, and the resource allocation device can allocate the resources for the application programs in the Hadoop cluster and the application programs outside the Hadoop cluster according to the resource use condition and the resource use condition of each node in the Hadoop cluster so as to improve the utilization rate of the resources.
For example, in the case that an application program a started by a non-Hadoop cluster (i.e., an application program outside the Hadoop cluster) applies for resource execution starting on the resource allocation device, the resource allocation device may adjust the resource scheduler of the Yarn resource manager, and start the application program a to an idle node, such as the node #3, after the execution of the application program a is finished, the node resource may be released, and the resource scheduler of the Yarn resource manager may be adjusted again.
For another example, for the application program B that needs to be executed at regular time, resources may be reserved for the application program B, and a timing task may be configured on the resource allocation device to start the application program B at regular time. Before starting the application program B, the resource scheduler of the Yarn resource manager may be adjusted in advance, and then the application program B is started to a corresponding node, that is, a node reserved for the application program B.
The embodiment of the invention can reasonably allocate the resources under different resource use scenes by allocating the resources through the resource allocation device, ensure the normal execution of the application program, greatly improve the resource utilization rate and further save the expense of the server expense.
Referring to fig. 3, fig. 3 is a block diagram of a resource allocation apparatus according to an embodiment of the present invention. As shown in fig. 3, the resource allocation apparatus 300 includes:
an acquiring module 301, configured to acquire resource usage of each node in the Hadoop cluster;
The first allocating module 302 is configured to allocate a first type of resource and a second type of resource according to a resource usage scenario and a resource usage situation of each node in the Hadoop cluster, where the first type of resource is a resource used for an application program in the Hadoop cluster in the node resources of the Hadoop cluster, and the second type of resource is a resource used for an application program outside the Hadoop cluster in the node resources of the Hadoop cluster;
and the adjusting module 303 is configured to adjust a resource scheduler of the Yarn resource manager according to the allocated first-class resources, so that the resource scheduler schedules the allocated first-class resources.
Optionally, the first deployment module includes:
The first allocation unit is used for allocating the first type of resources and the second type of resources according to the resource use condition of each node in the Hadoop cluster if the second type of resources are determined to not meet the resource requirement of the first application program under the condition that the resource use scene is the starting request of the received first application program;
The first application program is an application program outside the Hadoop cluster, and the allocated second type of resources meet the resource requirement of the first application program.
Optionally, the second type of resource does not meet the resource requirement of the first application program, including at least one of:
the hollow resource amount in the second type of resources is smaller than the resource amount required by the first application program;
The second class of resources does not include resources of a first node, wherein the first node is a node designated by the first application program.
Optionally, the apparatus further includes:
The first control module is used for starting and operating the first application program by using the allocated second type resources after allocating the first type resources and the second type resources according to the resource use condition and the resource use condition of each node in the Hadoop cluster;
The second allocation module is used for releasing node resources occupied by the first application program and allocating the first type of resources and the second type of resources under the condition that the first application program finishes running.
Optionally, the first deployment module includes:
The second allocating unit is used for allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster under the condition that the resource use scene is that the resource reservation request for the second application program is received;
The second application program is an application program outside the Hadoop cluster, the resource reservation request comprises resource information for requesting reservation and a reservation time limit, and the resource indicated by the resource information is used for the second application program within the reservation time limit.
Optionally, the second allocating unit is specifically configured to:
under the condition that the resource usage scenario is that a resource reservation request for a second application program is received, determining whether to reserve resources for the second application program according to the priority of the second application program and the estimated use condition of resources indicated by the resource information within the reservation time limit;
And under the condition that the resources are reserved for the second application program, allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster.
Optionally, the apparatus further includes:
And the second control module is used for starting and running the second application program by utilizing the resources indicated by the resource information within the reservation time limit after allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster under the condition that the resource use scene is the resource reservation request for the second application program.
The resource allocation device 300 can implement each process of the node resource allocation method in the above method embodiment, and achieve the same effect, so as to avoid repetition, and will not be described herein again.
The resource allocation device 300 of the embodiment of the invention is provided with an acquisition module 301, which is used for acquiring the resource use condition of each node in the Hadoop cluster; the first allocating module 302 is configured to allocate a first type of resource and a second type of resource according to a resource usage scenario and a resource usage situation of each node in the Hadoop cluster, where the first type of resource is a resource used for an application program in the Hadoop cluster in the node resources of the Hadoop cluster, and the second type of resource is a resource used for an application program outside the Hadoop cluster in the node resources of the Hadoop cluster; and the adjusting module 301 is configured to adjust a resource scheduler of the Yarn resource manager according to the allocated first type of resources, so that the resource scheduler schedules the allocated first type of resources. Therefore, the resource allocation of the application program in the Hadoop cluster and the resource allocation of the application program outside the Hadoop cluster are more flexible and reasonable, and the utilization rate of the resource can be improved.
The embodiment of the invention also provides a resource allocation device, which comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program realizes each process of the node resource allocation method of any method embodiment when being executed by the processor, can achieve the same technical effect, and is not repeated here for avoiding repetition.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements each process of the node resource allocation method described above, and can achieve the same technical effect, so that repetition is avoided and no further description is given here. The computer readable storage medium is, for example, a Read-Only Memory (ROM), a random access Memory (Random Access Memory RAM), a magnetic disk or an optical disk.
Referring to fig. 4, fig. 4 is a block diagram of a resource allocation apparatus according to still another embodiment of the present invention, and as shown in fig. 4, a resource allocation apparatus 400 includes: a processor 401, a memory 402 and a computer program stored on the memory 402 and executable on the processor, the components of the resource allocation apparatus 400 being coupled together by a bus interface 403, the computer program when executed by the processor 401 implementing the steps of:
acquiring resource use conditions of all nodes in the Hadoop cluster;
According to a resource usage scene and the resource usage situation of each node in the Hadoop cluster, allocating first type resources and second type resources, wherein the first type resources are resources used for application programs in the Hadoop cluster in the node resources of the Hadoop cluster, and the second type resources are resources used for application programs outside the Hadoop cluster in the node resources of the Hadoop cluster;
and adjusting a resource scheduler of the Yarn resource manager according to the allocated first-class resources so that the resource scheduler schedules the allocated first-class resources.
Optionally, the computer program when executed by the processor 401 is further configured to:
If the resource usage scenario is that a starting request of a first application program is received, if the second type of resources are determined not to meet the resource requirement of the first application program, allocating the first type of resources and the second type of resources according to the resource usage conditions of all nodes in the Hadoop cluster;
The first application program is an application program outside the Hadoop cluster, and the allocated second type of resources meet the resource requirement of the first application program.
Optionally, the second type of resource does not meet the resource requirement of the first application program, including at least one of:
the hollow resource amount in the second type of resources is smaller than the resource amount required by the first application program;
The second class of resources does not include resources of a first node, wherein the first node is a node designated by the first application program.
Optionally, the computer program when executed by the processor 401 is further configured to:
after the first type of resources and the second type of resources are allocated according to the resource use condition and the resource use scene of each node in the Hadoop cluster, the allocated second type of resources are utilized to start and operate the first application program;
And under the condition that the first application program finishes running, releasing node resources occupied by the first application program, and allocating the first type of resources and the second type of resources.
Optionally, the computer program when executed by the processor 401 is further configured to:
under the condition that the resource use scene is that a resource reservation request aiming at a second application program is received, allocating first-class resources and second-class resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster;
The second application program is an application program outside the Hadoop cluster, the resource reservation request comprises resource information for requesting reservation and a reservation time limit, and the resource indicated by the resource information is used for the second application program within the reservation time limit.
Optionally, the computer program when executed by the processor 401 is further configured to:
under the condition that the resource usage scenario is that a resource reservation request for a second application program is received, determining whether to reserve resources for the second application program according to the priority of the second application program and the estimated use condition of resources indicated by the resource information within the reservation time limit;
And under the condition that the resources are reserved for the second application program, allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster.
Optionally, the computer program when executed by the processor 401 is further configured to:
And under the condition that the resource use scene is that a resource reservation request aiming at a second application program is received, according to the resource reservation request and the resource use condition of each node in the Hadoop cluster, after the first type of resources and the second type of resources are allocated, starting and operating the second application program by utilizing the resources indicated by the resource information within the reservation time limit.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or units, which may be in electrical, mechanical, or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present invention.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims (12)

1. A method for allocating node resources, comprising:
acquiring resource use conditions of all nodes in the Hadoop cluster;
According to a resource usage scene and the resource usage situation of each node in the Hadoop cluster, allocating first type resources and second type resources, wherein the first type resources are resources used for application programs in the Hadoop cluster in the node resources of the Hadoop cluster, and the second type resources are resources used for application programs outside the Hadoop cluster in the node resources of the Hadoop cluster;
Adjusting a resource scheduler of a Yarn resource manager according to the allocated first type of resources so that the resource scheduler schedules the allocated first type of resources;
The allocating the first type of resources and the second type of resources according to the resource usage scenario and the resource usage situation of each node in the cluster comprises:
If the resource usage scenario is that a starting request of a first application program is received, if the second type of resources are determined not to meet the resource requirement of the first application program, allocating the first type of resources and the second type of resources according to the resource usage condition of each node in the cluster;
Said allocating said first type of resource and said second type of resource comprises: allocating the idle resources in the first type of resources into second type of resources, wherein the allocated second type of resources meet the resource requirements of the first application program;
The first application is an application outside the cluster.
2. The method of claim 1, wherein the second type of resource does not meet the resource requirements of the first application, comprising at least one of:
the hollow resource amount in the second type of resources is smaller than the resource amount required by the first application program;
The second class of resources does not include resources of a first node, wherein the first node is a node designated by the first application program.
3. The method of claim 1, wherein after allocating the first type of resource and the second type of resource according to the resource usage and the resource usage scenario of each node in the cluster, the method further comprises:
starting and operating the first application program by using the allocated second type resource;
And under the condition that the first application program finishes running, releasing node resources occupied by the first application program, and allocating the first type of resources and the second type of resources.
4. The method according to claim 1, wherein allocating the first type of resources and the second type of resources according to the resource usage and the resource usage scenario of each node in the cluster comprises:
Under the condition that the resource use scene is that a resource reservation request aiming at a second application program is received, allocating first-class resources and second-class resources according to the resource reservation request and the resource use condition of each node in the cluster;
The second application program is an application program outside the cluster, the resource reservation request comprises resource information for requesting reservation and a reservation time limit, and the resource indicated by the resource information is used for the second application program within the reservation time limit;
and under the condition that the resource usage scenario is that a resource reservation request for a second application program is received, allocating first-class resources and second-class resources according to the resource reservation request and the resource usage condition of each node in the cluster, including:
under the condition that the resource usage scenario is that a resource reservation request for a second application program is received, determining whether to reserve resources for the second application program according to the priority of the second application program and the estimated use condition of resources indicated by the resource information within the reservation time limit;
And under the condition that the resources are reserved for the second application program, allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the cluster.
5. The method according to claim 4, wherein in the case where the resource usage scenario is that a resource reservation request for a second application is received, after allocating a first type of resource and a second type of resource according to the resource reservation request and the resource usage situation of each node in the cluster, the method further comprises:
and starting and running the second application program by utilizing the resources indicated by the resource information within the reserved time limit.
6. A node resource allocation apparatus, comprising:
the acquisition module is used for acquiring the resource use condition of each node in the Hadoop cluster;
The first allocation module is used for allocating first type resources and second type resources according to a resource usage scene and resource usage conditions of all nodes in the Hadoop cluster, wherein the first type resources are resources used for application programs in the Hadoop cluster in the node resources of the Hadoop cluster, and the second type resources are resources used for application programs outside the Hadoop cluster in the node resources of the Hadoop cluster;
the adjustment module is used for adjusting a resource scheduler of the Yarn resource manager according to the allocated first-class resources so that the resource scheduler schedules the allocated first-class resources;
the first deployment module includes:
The first allocation unit is used for allocating the first type of resources and the second type of resources according to the resource use condition of each node in the Hadoop cluster if the second type of resources are determined to not meet the resource requirement of the first application program under the condition that the resource use scene is the starting request of the received first application program;
Said allocating said first type of resource and said second type of resource comprises: allocating the idle resources in the first type of resources into second type of resources, wherein the allocated second type of resources meet the resource requirements of the first application program;
the first application program is an application program outside the Hadoop cluster.
7. The apparatus of claim 6, wherein the second type of resource does not meet the resource requirements of the first application, comprising at least one of:
the hollow resource amount in the second type of resources is smaller than the resource amount required by the first application program;
The second class of resources does not include resources of a first node, wherein the first node is a node designated by the first application program.
8. The apparatus of claim 6, wherein the apparatus further comprises:
The first control module is used for starting and operating the first application program by using the allocated second type resources after allocating the first type resources and the second type resources according to the resource use condition and the resource use condition of each node in the Hadoop cluster;
The second allocation module is used for releasing node resources occupied by the first application program and allocating the first type of resources and the second type of resources under the condition that the first application program finishes running.
9. The apparatus of claim 6, wherein the first deployment module comprises:
The second allocating unit is used for allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster under the condition that the resource use scene is that the resource reservation request for the second application program is received;
The second application program is an application program outside the Hadoop cluster, the resource reservation request comprises resource information for requesting reservation and reservation time limit, and the resource indicated by the resource information is used for the second application program within the reservation time limit;
and under the condition that the resource usage scenario is that a resource reservation request for a second application program is received, allocating first-class resources and second-class resources according to the resource reservation request and the resource usage condition of each node in the cluster, including:
under the condition that the resource usage scenario is that a resource reservation request for a second application program is received, determining whether to reserve resources for the second application program according to the priority of the second application program and the estimated use condition of resources indicated by the resource information within the reservation time limit;
And under the condition that the resources are reserved for the second application program, allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the cluster.
10. The apparatus of claim 9, wherein the apparatus further comprises:
And the second control module is used for starting and running the second application program by utilizing the resources indicated by the resource information within the reservation time limit after allocating the first type of resources and the second type of resources according to the resource reservation request and the resource use condition of each node in the Hadoop cluster under the condition that the resource use scene is the resource reservation request for the second application program.
11. A resource allocation apparatus 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 node resource allocation method according to any one of claims 1 to 5.
12. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the node resource allocation method according to any of claims 1 to 5.
CN201910662019.5A 2019-07-22 2019-07-22 Node resource allocation method and device Active CN112286673B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910662019.5A CN112286673B (en) 2019-07-22 2019-07-22 Node resource allocation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910662019.5A CN112286673B (en) 2019-07-22 2019-07-22 Node resource allocation method and device

Publications (2)

Publication Number Publication Date
CN112286673A CN112286673A (en) 2021-01-29
CN112286673B true CN112286673B (en) 2024-05-24

Family

ID=74419517

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910662019.5A Active CN112286673B (en) 2019-07-22 2019-07-22 Node resource allocation method and device

Country Status (1)

Country Link
CN (1) CN112286673B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014114163A1 (en) * 2013-01-28 2014-07-31 索尼公司 Apparatus and method for wireless communication system
CN105512083A (en) * 2015-11-30 2016-04-20 华为技术有限公司 YARN based resource management method, device and system
WO2017166803A1 (en) * 2016-03-30 2017-10-05 华为技术有限公司 Resource scheduling method and device
CN107291539A (en) * 2017-06-19 2017-10-24 山东师范大学 Cluster program scheduler method based on resource significance level
CN107567696A (en) * 2015-05-01 2018-01-09 亚马逊科技公司 The automatic extension of resource instances group in computing cluster
CN109783225A (en) * 2018-12-12 2019-05-21 华南理工大学 A kind of tenant's priority management method and system of multi-tenant big data platform

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5370946B2 (en) * 2011-04-15 2013-12-18 株式会社日立製作所 Resource management method and computer system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014114163A1 (en) * 2013-01-28 2014-07-31 索尼公司 Apparatus and method for wireless communication system
CN107567696A (en) * 2015-05-01 2018-01-09 亚马逊科技公司 The automatic extension of resource instances group in computing cluster
CN105512083A (en) * 2015-11-30 2016-04-20 华为技术有限公司 YARN based resource management method, device and system
WO2017166803A1 (en) * 2016-03-30 2017-10-05 华为技术有限公司 Resource scheduling method and device
CN107291546A (en) * 2016-03-30 2017-10-24 华为技术有限公司 A kind of resource regulating method and device
CN107291539A (en) * 2017-06-19 2017-10-24 山东师范大学 Cluster program scheduler method based on resource significance level
CN109783225A (en) * 2018-12-12 2019-05-21 华南理工大学 A kind of tenant's priority management method and system of multi-tenant big data platform

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Hadoop环境下的动态资源管理研究与实现;赵颖;CNKI优秀硕士论文库;全文 *
中国联通容器化大数据云平台的探索与实践;王志军;信息技术与标准化;全文 *

Also Published As

Publication number Publication date
CN112286673A (en) 2021-01-29

Similar Documents

Publication Publication Date Title
CN108667748B (en) Method, device, equipment and storage medium for controlling bandwidth
CN107018091B (en) Resource request scheduling method and device
CN109582447B (en) Computing resource allocation method, task processing method and device
CN109564528B (en) System and method for computing resource allocation in distributed computing
CN110971623B (en) Micro-service instance elastic scaling method and device and storage medium
CN109960591B (en) Cloud application resource dynamic scheduling method for tenant resource encroachment
US11438271B2 (en) Method, electronic device and computer program product of load balancing
CN106878389B (en) Method and device for resource scheduling in cloud system
CN115617497B (en) Thread processing method, scheduling component, monitoring component, server and storage medium
KR20170023280A (en) Multi-core system and Method for managing a shared cache in the same system
EP4007232B1 (en) Resource scheduling method, apparatus and system
CN112286673B (en) Node resource allocation method and device
WO2021002961A1 (en) Harvest virtual machine for utilizing cloud-computing resources
CN117632462A (en) Task resource scheduling method and server
CN114640630B (en) Flow control method, device, equipment and readable storage medium
KR101227885B1 (en) Channel multiplexing method and apparatus in shared memory
CN111813564B (en) Cluster resource management method and device and container cluster management system
CN115378885A (en) Virtual machine service network bandwidth management method and device under super-convergence architecture
CN110955522A (en) Resource management method and system for coordination performance isolation and data recovery optimization
CN111580935A (en) Network communication method, device, equipment and storage medium
US8667492B2 (en) Control of the runtime behavior of processes
KR100471746B1 (en) A soft real-time task scheduling method and the storage media thereof
CN116720179B (en) API interface management method, terminal device and computer readable storage medium
KR20190061241A (en) Mesos process apparatus for unified management of resource and method for the same
CN114390058B (en) Service management system, method, device 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
GR01 Patent grant
GR01 Patent grant