WO2020119117A1 - Distributed computing method, apparatus and system, device and readable storage medium - Google Patents

Abstract

A distributed computing method, apparatus and system, a device, and a computer-readable storage medium, wherein same relate to the field of cloud computing, and can effectively improve the utilization rate of computing resources in a distributed computing network. The method comprises: when receiving a registration request sent by each terminal device, registering each terminal device as a task execution node or a task initiation node according to a node tag in the registration request (S101); when a task execution request sent by the task initiation node is received, scheduling, according to a pre-set task scheduling policy, a task to be executed in the task execution request to a corresponding task execution node for execution (S102); and receiving a task execution result returned by the corresponding task execution node, and sending the task execution result to the corresponding task initiation node (S103).

Description

Distributed computing method, device, system, equipment and readable storage medium The

This application requires the priority of the Chinese patent application submitted to the Chinese Patent Office on December 14, 2018, with the application number 201811531908.X and the invention titled "distributed computing methods, devices, systems, equipment, and readable storage media," The entire contents are incorporated into the application by reference.

Technical field

The present application relates to the technical field of distributed computing, and in particular, to a distributed computing method, device, system, device, and readable storage medium.

Background technique

Distributed computing is the use of networks to connect tens of thousands of computers to form a virtual supercomputer to complete ultra-large-scale problem solving that cannot be completed by a single computer. At present, the existing distributed computing framework places high requirements on the environment where the machines are running, and generally requires several types of nodes, such as scheduling nodes, execution nodes, and task nodes are all in the same local area network, which invisibly restricts these machines to only It is the user's own and cannot fully utilize the computing resources on the existing Internet. Therefore, how to increase the utilization rate of computing resources in the distributed computing network is a problem that needs to be solved urgently.

Summary of the invention

The main purpose of the present application is to provide a distributed computing method, device, system, device, and readable storage medium, aiming to improve the utilization rate of computing resources in a distributed computing network.

To achieve the above objective, the present application provides a distributed computing method, which includes the following steps:

When receiving the registration request sent by each terminal device, according to the node label in the registration request, register each terminal device as a task execution node or a task initiation node;

When receiving the task execution request sent by the task initiating node, according to the preset task scheduling strategy, the task to be executed in the task execution request is scheduled to the corresponding task execution node for execution;

Receiving the task execution result returned by the corresponding task execution node, and sending the task execution result to the corresponding task initiation node.

Optionally, the step of registering each terminal device as a task execution node or a task initiation node according to the node label in the registration request includes:

Reading a node label from the registration request, and determining whether the node label is an execution node label or an initiating node label;

If the node label is an execution node label, register the corresponding terminal device as a task execution node;

If the node label is an initiating node label, the corresponding terminal device is registered as a task initiating node.

Optionally, according to a preset task scheduling strategy, the step of scheduling the task to be executed in the task execution request to a corresponding task execution node for execution includes:

Reading the writing language tag of the task to be executed from the task execution request;

Determine all the registered task execution nodes that contain the writing language tags as candidate task execution nodes;

Obtain the current running state and currently available computing resources of each candidate task execution node, and determine the candidate task execution node with the current running state as idle and the most currently available computing resources as the target task execution node;

Scheduling the task to be executed to the target task execution node for execution.

Optionally, according to a preset task scheduling strategy, the step of scheduling the task to be executed in the task execution request to a corresponding task execution node for execution includes:

Determine whether there is a task group to be executed including at least two tasks to be executed in the task execution request;

If there is a task group to be executed including at least two tasks to be executed in the task execution request, it is determined whether there is a dependency relationship between the tasks to be executed in the task group to be executed;

If there is a dependency relationship between the tasks to be executed in the task group to be executed, the target task execution node is determined according to the writing language tags of each task to be executed in the task group to be executed;

All tasks to be executed in the task to-be-executed group are scheduled to be executed by the target task execution node.

Optionally, after the step of determining whether there is a dependency relationship between the tasks to be executed in the task to be executed group, the method further includes:

If there is no dependency relationship between the tasks to be executed in the task group to be executed, then according to the writing language tags of the tasks to be executed in the task group to be executed, each task to be executed in the task group to be executed Dispatched to the corresponding task execution node for execution.

Optionally, the step of registering each terminal device as a task execution node or a task initiation node according to the node label in the registration request includes:

Obtain the current CPU idle resources, and determine whether the current CPU idle resources are greater than or equal to the preset CPU idle resources;

If the current CPU idle resource is greater than or equal to the preset CPU idle resource, the number of synchronized registered devices is determined according to the current CPU idle resource;

According to the node label in the registration request, the registration operation of the terminal devices with the number of synchronously registered devices is simultaneously executed each time to register each terminal device as a task execution node or a task initiation node.

In addition, to achieve the above object, the present application also provides a distributed computing device, the distributed computing device includes:

The node registration module is used to register each terminal device as a task execution node or a task initiation node according to the node label in the registration request when receiving the registration request sent by each terminal device;

The task scheduling module is used to schedule the task to be executed in the task execution request to the corresponding task execution node for execution according to the preset task scheduling strategy when receiving the task execution request sent by the task initiating node;

The sending module is configured to receive the task execution result returned by the corresponding task execution node, and send the task execution result to the corresponding task initiation node.

In addition, in order to achieve the above purpose, the present application also provides a distributed computing system. The distributed computing system includes a task scheduling node, a task execution node, and a task initiation node. The task scheduling node is deployed on the public network. The task execution node and the task initiation node are deployed on a public network or a private network, where,

The task scheduling node is used to register each terminal device as a task execution node or a task initiation node according to the node label in the registration request when receiving the registration request sent by each terminal device;

The task scheduling node is also used to schedule the task to be executed in the task execution request to the corresponding task execution node for execution according to a preset task scheduling strategy when receiving the task execution request sent by the task initiating node;

The task scheduling node is also used to receive the task execution result returned by the corresponding task execution node, and send the task execution result to the corresponding task initiation node;

The task execution node is configured to receive the task to be executed scheduled by the task scheduling node, execute the task to be executed, and return the task execution result of the task to the task scheduling node;

The task initiation node is used to generate a task execution request carrying a task to be executed and a writing language tag when a triggered task initiation instruction is detected, and send the task execution request to the task scheduling node.

In addition, to achieve the above object, the present application also provides a distributed computing device, the distributed computing device includes a processor, a memory, and computer readable instructions stored on the memory and executable by the processor Where the computer-readable instructions are executed by the processor to implement the steps of the distributed computing method as described above.

In addition, in order to achieve the above object, the present application also provides a readable storage medium on which computer-readable instructions are stored, wherein when the computer-readable instructions are executed by a processor, the distribution as described above is achieved Of the formula calculation method.

This application provides a distributed computing method, device, system, device, and readable storage medium. This application registers each terminal device as a task execution node and a task initiation node, and then receives a task execution request sent by the task initiation node , According to the preset task scheduling strategy, schedule the task to be executed in the task execution request to the corresponding task execution node for execution, and receive the task execution result returned by the corresponding task execution node, and send the task execution result to the corresponding The task initiating node can schedule the task to be executed to the corresponding task execution node in the above manner, and the corresponding task execution node can execute the task to be executed, which can effectively improve the utilization rate of computing resources in the distributed computing network.

BRIEF DESCRIPTION

FIG. 1 is a schematic diagram of a hardware structure of a distributed computing device involved in various embodiments of this application;

2 is a schematic flowchart of a first embodiment of a distributed computing method of this application;

3 is a schematic diagram of functional modules of a first embodiment of a distributed computing device of the present application;

4 is a schematic diagram of functional modules of the first embodiment of the distributed computing system of the present application.

The implementation, functional characteristics and advantages of the present application will be further described in conjunction with the embodiments and with reference to the drawings.

detailed description

It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

The distributed computing method involved in the embodiments of the present application is mainly applied to a distributed computing device, and the distributed computing device may be a PC (personal computer personal computer), portable computers, mobile terminals and other devices with display and processing functions.

Referring to FIG. 1, FIG. 1 is a schematic diagram of a hardware structure of a distributed computing device involved in an embodiment of the present application. In the embodiment of the present application, the distributed computing device may include a processor 1001 (for example, a central processor Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display (Display), an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a wireless interface (Such as WI-FI interface); the memory 1005 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk storage, the storage 1005 may optionally be a storage device independent of the foregoing processor 1001. Those skilled in the art may understand that the hardware structure shown in FIG. 1 does not constitute a limitation on the present application, and may include more or less components than those illustrated, or combine certain components, or arrange different components.

With continued reference to FIG. 1, the memory 1005 in FIG. 1 as a readable storage medium may include an operating system, a network communication module, and computer-readable instructions. In FIG. 1, the network communication module is mainly used to connect to a server and perform data communication with the server; and the processor 1001 can call computer-readable instructions stored in the memory 1005 and execute the distributed computing method provided by the embodiments of the present application.

The embodiments of the present application provide a distributed computing method.

Referring to FIG. 2, FIG. 2 is a schematic flowchart of a first embodiment of a distributed computing method according to this application.

In this embodiment, the distributed computing method includes:

Step S101: When receiving a registration request sent by each terminal device, register each terminal device as a task execution node or a task initiation node according to the node label in the registration request;

In this embodiment, the distributed computing method is applied to a distributed computing system, including a task scheduling node, a task execution node, and a task initiation node. The task scheduling node is deployed on the public network, and the task execution node and task initiation node are deployed on the public network. Internet or private network, the deployment conditions need to meet the task execution node and task initiation node can access the task scheduling node, where the task scheduling node is used to receive the task execution node and task initiation node registration, instruction forwarding, data forwarding, and Each task execution node and task initiation node dynamically generate the ngrok (reverse proxy) subdomain name, and distribute the tasks to be executed to the task execution node; the task execution node contains a virtual machine and a task execution environment, the virtual machine includes but is not limited to JVM (Java Virtual Machine, Java virtual machine), Linux virtual machine and SUN virtual machine, the operating environment includes but is not limited to JS operating environment, JAVA operating environment, Python operating environment and C/C++ language operating environment, task execution node is used to execute task scheduling node The task to be executed is distributed; the task initiating node is used to initiate the task to be executed and send the task to be executed to the task scheduling node.

When the triggered node registration instruction is detected, the terminal device displays a node registration interface that includes the task execution node registration option and the task initiation node registration option, and receives the node registration option selected by the user through the node registration interface, when the selected node registration option When registering options for a task execution node, obtain the execution node label, and generate a registration request containing the execution node label, and send the registration request to the task scheduling node; when the selected node registration option is the task initiating node registration option, Obtain the initiating node label, and generate a registration request containing the initiating node label, and send the registration request to the task scheduling node; when the selected node registration option includes task execution node registration option and task initiation node registration option, generate It contains the registration request of the execution node label and the initiation node label, and sends the registration request to the task scheduling node. The terminal device may be registered as a task execution node and/or a task initiation node.

When receiving the registration request sent by each terminal device, the task scheduling node in the distributed computing system registers each terminal device as a task execution node or a task initiation node according to the node label in the registration request. Specifically, the node label is read from the registration request, and if the node label is the execution node label, the corresponding terminal device is registered as the task execution node, that is, the ngrok (reverse proxy) subdomain name of the terminal device is generated, and the corresponding The ngrok subdomain name of the terminal device is written into the execution node list; if the node label is the initiating node label, the corresponding terminal device is registered as the initiating task node, that is, the ngrok subdomain name of the terminal device is generated, and the ngrok subdomain of the terminal device is generated. The domain name is written into the initiating node list; if there are two node labels, and they are the executing node label and the initiating node label, the corresponding terminal device is registered as a dual-function node, that is, the terminal device is the task execution node, and For the task initiation node, specifically generating the ngrok subdomain name of the terminal device, the ngrok subdomain name of the corresponding terminal device is written into the execution node list and the initiation node list.

Step S102, when a task execution request sent by the task initiating node is received, the task to be executed in the task execution request is scheduled to the corresponding task execution node for execution according to a preset task scheduling strategy;

In this embodiment, when the triggered task initiation instruction is detected, the task initiation node obtains the task to be executed, and obtains the writing language tag corresponding to the task to be executed, and then generates a task execution request including the task to be executed and the writing language tag, And send the task execution request to the task scheduling node, where the writing language tags include but are not limited to JS tags, JAVA tags, and Python tags. When the task scheduling node receives the task execution request sent by the task initiating node, the task to be executed in the task execution request is scheduled to the corresponding task execution node for execution according to a preset task scheduling strategy. It should be noted that the execution environment of the task execution node that executes the task to be executed has a corresponding relationship with the writing language tag. For example, the task execution node with the JS running environment only has the function of executing the to-be-executed task whose writing language tag is JS tag , And the task execution node with JAVA running environment only has the function of executing the task to be executed whose writing language tag is JAVA tag.

Specifically, the preset task scheduling strategy is to read the writing language tag of the task to be executed from the task execution request, and determine the task execution node containing the writing language tag among all registered task execution nodes as the candidate task Execute the node, then obtain the current running state and currently available computing resources of each candidate task executing node, and determine the current running state to be idle, and the candidate task executing node with the most currently available computing resources is determined as the target task executing node. Perform task scheduling to the target task execution node for execution, that is, the task scheduling node obtains the ngrok subdomain name corresponding to the target task execution node by modifying the local host, and schedules the task to be executed to the target task execution node according to the ngrok subdomain name To execute. For example, the ngrok subdomain name is abc.ng.com, the task scheduling node's public domain name is www.my.com, and the ngrok main domain name is ng.com, when the task initiating node sends a task execution request to the task scheduling node through www.my.com/abc, rewrite the task execution request to abc.my.com, and parse abc.my.com to abc .ng.com, and then schedule the task to be executed to the target task execution node through abc.ng.com.

Step S103: Receive the task execution result returned by the corresponding task execution node, and send the task execution result to the corresponding task initiation node.

In this embodiment, when the task execution node receives the pending task distributed by the task scheduling node, the task execution node starts the virtual machine and the running environment, executes the pending task, and returns the task execution result to the task scheduling node, task scheduling The node receives the task execution result returned by the task execution node, and sends the task execution result to the task initiation node, and the task initiation node displays the task execution result. In specific implementation, if the task to be executed is split into several subtasks, each task execution node sends the execution result of each subtask to the task scheduling node after executing each subtask, and the task scheduling node summarizes the Execution results, thus waiting for the total execution results.

In this embodiment, each terminal device is registered as a task execution node and a task initiation node, and then when a task execution request sent by the task initiation node is received, the task to be executed in the task execution request is scheduled according to a preset task scheduling strategy Go to the corresponding task execution node for execution, and receive the task execution result returned by the corresponding task execution node, and send the task execution result to the corresponding task initiation node. In the above manner, the task to be executed can be scheduled to the corresponding task Execution node, the corresponding task execution node executes the task to be executed, which can effectively improve the utilization rate of computing resources in the distributed computing network.

Further, based on the above first embodiment, a second embodiment of the distributed computing method of the present application is proposed. The difference from the foregoing embodiment is that when a task initiating node initiates multiple tasks to be executed, the task scheduling node is based on the tasks to be executed Whether there is a dependency relationship, determine different task scheduling strategies, specifically, when the task scheduling node receives the task execution request sent by the task initiating node, determine whether the task execution request contains at least two tasks to be executed If there is only one task to be executed in the task execution request, the task to be executed will be scheduled to the corresponding task execution node for execution according to the writing language tag of the task to be executed; if the task execution request contains at least Two task groups to be executed, to determine whether there is a dependency relationship between tasks to be executed in the task group to be executed, if there is a dependency relationship between tasks to be executed in the task group to be executed, according to the to be executed Write language tags for each task to be executed in the task group, determine the target task execution node, and schedule each task to be executed in the task group to be executed to the target task execution node; if the task to be executed in the task group to be executed There is no dependency relationship, and each task to be executed in the task group to be executed is scheduled to the corresponding task execution node for execution according to the writing language tags of each task to be executed in the task group to be executed. When there are multiple tasks to be executed, when there are dependencies between the multiple tasks to be executed, the multiple tasks to be executed can be scheduled to be executed by the same task execution node, and there is no dependency relationship between the multiple tasks to be executed At this time, multiple tasks to be executed can be scheduled to be executed by different task execution nodes to improve the efficiency of task execution.

Further, based on the above first or second embodiment, a third embodiment of the distributed computing method of the present application is proposed. The difference from the foregoing embodiment is that when the CPU idle resources of the task scheduling node are sufficient, multiple executions can be performed simultaneously. The registration operation of each terminal device, specifically, the task scheduling node obtains the current CPU idle resource and determines whether the current CPU idle resource is greater than or equal to the preset CPU idle resource, if the current CPU idle resource is greater than or equal to the preset CPU idle resource, then According to the current CPU idle resources, determine the number of synchronized registered devices, that is, the number of terminal devices that the CPU can register at the same time, and according to the node label in the registration request, perform the simultaneous registration operation of the terminal devices with the number of synchronized registered devices each time The terminal device is registered as a task execution node or a task initiation node. The mapping relationship between the CPU idle resources and the number of synchronized registered devices can be set by those skilled in the art based on actual conditions, and this patent proposal does not specifically limit this. For example, when the CPU idle resource is less than A, the number of terminal devices that the corresponding CPU can simultaneously register is 2; when the CPU idle resource is greater than or equal to A and less than B, the number of terminal devices that the corresponding CPU can simultaneously register is 3; when the CPU is idle When the resource is greater than or equal to B and less than C, the corresponding number of terminal devices that the corresponding CPU can simultaneously register is 4, where A<B<C. It should be noted that the above-mentioned preset CPU idle resources can be set by those skilled in the art based on actual conditions, which is not specifically limited in this embodiment. In the above manner, registration operations of multiple terminal devices can be performed simultaneously, improving registration efficiency.

In addition, embodiments of the present application also provide a distributed computing device.

Referring to FIG. 3, FIG. 3 is a schematic diagram of functional modules of a first embodiment of a distributed computing device of the present application.

The distributed computing device of the present application is a virtual device, which is stored in the memory 1005 of the distributed computing device shown in FIG. 1 and is used to implement all functions of the distributed computer-readable instructions; when a registration request sent by each terminal device is received, According to the node label in the registration request, register each terminal device as a task execution node or a task initiation node; when receiving a task execution request sent by the task initiation node, according to a preset task scheduling strategy, the task The task to be executed in the execution request is scheduled to the corresponding task execution node for execution; the task execution result returned by the corresponding task execution node is received, and the task execution result is sent to the corresponding task initiation node. .

Specifically, in this embodiment, the distributed computing device includes:

The node registration module 101 is configured to, when receiving the registration request sent by each terminal device, register each terminal device as a task execution node or a task initiation node according to the node label in the registration request;

The task scheduling module 102 is configured to, when receiving the task execution request sent by the task initiating node, schedule the tasks to be executed in the task execution request to the corresponding task execution node for execution according to a preset task scheduling strategy;

The sending module 103 is configured to receive the task execution result returned by the corresponding task execution node, and send the task execution result to the corresponding task initiation node.

Further, the node registration module 101 is also used to:

Reading a node label from the registration request, and determining whether the node label is an execution node label or an initiating node label;

If the node label is an execution node label, register the corresponding terminal device as a task execution node;

If the node label is an initiating node label, the corresponding terminal device is registered as a task initiating node.

Further, the task scheduling module 102 is also used to:

Reading the writing language tag of the task to be executed from the task execution request;

Determine all the registered task execution nodes that contain the writing language tags as candidate task execution nodes;

Obtain the current running state and currently available computing resources of each candidate task execution node, and determine the candidate task execution node with the current running state as idle and the most currently available computing resources as the target task execution node;

Scheduling the task to be executed to the target task execution node for execution.

Further, the task scheduling module 102 is also used to:

Determine whether there is a task group to be executed including at least two tasks to be executed in the task execution request;

If there is a task group to be executed including at least two tasks to be executed in the task execution request, it is determined whether there is a dependency relationship between the tasks to be executed in the task group to be executed;

If there is a dependency relationship between the tasks to be executed in the task group to be executed, the target task execution node is determined according to the writing language tags of each task to be executed in the task group to be executed;

All the tasks to be executed in the task group to be executed are scheduled to be executed by the target task execution node.

Further, the task scheduling module 102 is also used to:

If there is no dependency relationship between the tasks to be executed in the task group to be executed, then according to the writing language tags of the tasks to be executed in the task group to be executed, each task to be executed in the task group to be executed Dispatched to the corresponding task execution node for execution.

Further, the node registration module 101 is also used to:

Obtain the current CPU idle resources, and determine whether the current CPU idle resources are greater than or equal to the preset CPU idle resources;

If the current CPU idle resource is greater than or equal to the preset CPU idle resource, the number of synchronized registered devices is determined according to the current CPU idle resource;

According to the node label in the registration request, the registration operation of the terminal devices with the number of synchronously registered devices is simultaneously executed each time to register each terminal device as a task execution node or a task initiation node.

Wherein, the function realization of each module in the above-mentioned distributed computing device corresponds to each step in the above-mentioned embodiment of the distributed computing method, and its function and implementation process will not be repeated here one by one.

In addition, the embodiments of the present application also provide a distributed computing system.

Referring to FIG. 4, FIG. 4 is a schematic diagram of functional modules of the first embodiment of the distributed computing system of the present application.

The distributed computing system includes a task scheduling node 201, a task execution node 202, and a task initiation node 203, the task scheduling node is deployed on a public network, the task execution node and the task initiation node are deployed on a public network or a private network, among them,

The task scheduling node 201 is configured to, when receiving a registration request sent by each terminal device, register each terminal device as a task execution node or a task initiation node according to the node label in the registration request;

The task scheduling node 201 is also used to schedule the task to be executed in the task execution request to the corresponding task execution node for execution according to a preset task scheduling strategy when receiving the task execution request sent by the task initiating node ;

The task scheduling node 201 is also used to receive the task execution result returned by the corresponding task execution node, and send the task execution result to the corresponding task initiation node;

The task execution node 202 is configured to receive the task to be executed scheduled by the task scheduling node, execute the task to be executed, and return the task execution result of the task to be executed to the task scheduling node;

The task initiating node 203 is configured to generate a task execution request carrying a task to be executed and writing language tags when a triggered task initiation instruction is detected, and send the task execution request to the task scheduling node.

Further, the task scheduling node 201 is also used to:

Reading a node label from the registration request, and determining whether the node label is an execution node label or an initiating node label;

If the node label is an execution node label, register the corresponding terminal device as a task execution node;

If the node label is an initiating node label, the corresponding terminal device is registered as a task initiating node.

Further, the task scheduling node 201 is also used to:

Reading the writing language tag of the task to be executed from the task execution request;

Determine all the registered task execution nodes that contain the writing language tags as candidate task execution nodes;

Obtain the current running state and currently available computing resources of each candidate task execution node, and determine the candidate task execution node with the current running state as idle and the most currently available computing resources as the target task execution node;

Scheduling the task to be executed to the target task execution node for execution.

Further, the task scheduling node 201 is also used to:

Determine whether there is a task group to be executed including at least two tasks to be executed in the task execution request;

If there is a task group to be executed including at least two tasks to be executed in the task execution request, it is determined whether there is a dependency relationship between the tasks to be executed in the task group to be executed;

If there is a dependency relationship between the tasks to be executed in the task group to be executed, the target task execution node is determined according to the writing language tags of each task to be executed in the task group to be executed;

All the tasks to be executed in the task group to be executed are scheduled to be executed by the target task execution node.

Further, the task scheduling node 201 is also used to:

If there is no dependency relationship between the tasks to be executed in the task group to be executed, then according to the writing language tags of the tasks to be executed in the task group to be executed, each task to be executed in the task group to be executed Dispatched to the corresponding task execution node for execution.

Further, the task scheduling node 201 is also used to:

Obtain the current CPU idle resources, and determine whether the current CPU idle resources are greater than or equal to the preset CPU idle resources;

If the current CPU idle resource is greater than or equal to the preset CPU idle resource, the number of synchronized registered devices is determined according to the current CPU idle resource;

According to the node label in the registration request, the registration operation of the terminal devices with the number of synchronized registered devices is simultaneously executed each time to register each terminal device as a task execution node or a task initiation node.

Wherein, the function implementation of each module in the above-mentioned distributed computing system corresponds to each step in the above-mentioned embodiment of the distributed computing method, and its function and implementation process will not be repeated here one by one.

In addition, the embodiments of the present application further provide a readable storage medium, and the readable storage medium may be a non-volatile readable storage medium.

Computer-readable instructions are stored on a readable storage medium of the present application, where the computer-readable instructions are executed by a processor to implement the steps of the distributed computing method as described above.

The method implemented when the computer-readable instructions are executed can refer to various embodiments of the distributed computing method of the present application, and details are not described herein again.

It should be noted that in this article, the terms "include", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, It also includes other elements that are not explicitly listed, or include elements inherent to this process, method, article, or system. Without more restrictions, the element defined by the sentence "include one..." does not exclude that there are other identical elements in the process, method, article or system that includes the element.

The sequence numbers of the above embodiments of the present application are for description only, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods in the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware, but in many cases the former is better Implementation. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence or part that contributes to the existing technology, and the computer software product is stored in a storage medium (such as ROM/RAM as described above) , Magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, computer, server, air conditioner, or network equipment, etc.) to perform the method described in each embodiment of the present application.

The above are only the preferred embodiments of the present application, and do not limit the scope of the patent of the present application. Any equivalent structure or equivalent process transformation made by the description and drawings of this application, or directly or indirectly used in other related technical fields , The same reason is included in the scope of patent protection in this application.

Claims (20)

1. A distributed computing method, characterized in that the distributed computing method includes the following steps:

   When receiving the registration request sent by each terminal device, according to the node label in the registration request, register each terminal device as a task execution node or a task initiation node;

   When receiving the task execution request sent by the task initiating node, according to the preset task scheduling strategy, the task to be executed in the task execution request is scheduled to the corresponding task execution node for execution;

   Receiving the task execution result returned by the corresponding task execution node, and sending the task execution result to the corresponding task initiation node.
2. The distributed computing method according to claim 1, wherein the step of registering each terminal device as a task execution node or a task initiation node according to the node label in the registration request includes:

   Reading a node label from the registration request, and determining whether the node label is an execution node label or an initiating node label;

   If the node label is an execution node label, register the corresponding terminal device as a task execution node;

   If the node label is an initiating node label, the corresponding terminal device is registered as a task initiating node.
3. The distributed computing method according to claim 1, wherein the step of scheduling the task to be executed in the task execution request to the corresponding task execution node for execution according to a preset task scheduling strategy includes:

   Reading the writing language tag of the task to be executed from the task execution request;

   Determine all the registered task execution nodes that contain the writing language tags as candidate task execution nodes;

   Obtain the current running state and currently available computing resources of each candidate task execution node, and determine the candidate task execution node with the current running state as idle and the most currently available computing resources as the target task execution node;

   Scheduling the task to be executed to the target task execution node for execution.
4. The distributed computing method according to claim 1, wherein the step of scheduling the task to be executed in the task execution request to a corresponding task execution node for execution according to a preset task scheduling strategy includes:

   Determine whether there is a task group to be executed including at least two tasks to be executed in the task execution request;

   If there is a task group to be executed including at least two tasks to be executed in the task execution request, it is determined whether there is a dependency relationship between the tasks to be executed in the task group to be executed;

   If there is a dependency relationship between the tasks to be executed in the task group to be executed, the target task execution node is determined according to the writing language tags of each task to be executed in the task group to be executed;

   All the tasks to be executed in the task group to be executed are scheduled to be executed by the target task execution node.
5. The distributed computing method according to claim 4, wherein after the step of determining whether there is a dependency relationship between the tasks to be executed in the task group to be executed, the method further includes:

   If there is no dependency relationship between the tasks to be executed in the task group to be executed, then according to the writing language tags of the tasks to be executed in the task group to be executed, each task to be executed in the task group to be executed Dispatched to the corresponding task execution node for execution.
6. The distributed computing method according to claim 1, wherein the step of registering each terminal device as a task execution node or a task initiation node according to the node label in the registration request includes:

   Obtain the current CPU idle resources, and determine whether the current CPU idle resources are greater than or equal to the preset CPU idle resources;

   If the current CPU idle resource is greater than or equal to the preset CPU idle resource, the number of synchronized registered devices is determined according to the current CPU idle resource;

   According to the node label in the registration request, the registration operation of the terminal devices with the number of synchronized registered devices is simultaneously executed each time to register each terminal device as a task execution node or a task initiation node.
7. A distributed computing device, characterized in that the distributed computing device includes:

   The node registration module is used to register each terminal device as a task execution node or a task initiation node according to the node label in the registration request when receiving the registration request sent by each terminal device;

   The task scheduling module is used to schedule the task to be executed in the task execution request to the corresponding task execution node for execution according to the preset task scheduling strategy when receiving the task execution request sent by the task initiating node;

   The sending module is configured to receive the task execution result returned by the corresponding task execution node, and send the task execution result to the corresponding task initiation node.
8. The distributed computing device according to claim 7, wherein the node registration module is further used to:

   Reading a node label from the registration request, and determining whether the node label is an execution node label or an initiating node label;

   If the node label is an execution node label, register the corresponding terminal device as a task execution node;

   If the node label is an initiating node label, the corresponding terminal device is registered as a task initiating node.
9. The distributed computing device according to claim 7, wherein the task scheduling module is further used to:

   Reading the writing language tag of the task to be executed from the task execution request;

   Determine all the registered task execution nodes that contain the writing language tags as candidate task execution nodes;

   Obtain the current running state and currently available computing resources of each candidate task execution node, and determine the candidate task execution node with the current running state as idle and the most currently available computing resources as the target task execution node;

   Scheduling the task to be executed to the target task execution node for execution.
10. The distributed computing device according to claim 7, wherein the task scheduling module is further used to:

    Determine whether there is a task group to be executed including at least two tasks to be executed in the task execution request;

    If there is a task group to be executed including at least two tasks to be executed in the task execution request, it is determined whether there is a dependency relationship between the tasks to be executed in the task group to be executed;

    If there is a dependency relationship between the tasks to be executed in the task group to be executed, the target task execution node is determined according to the writing language tags of each task to be executed in the task group to be executed;

    All the tasks to be executed in the task group to be executed are scheduled to be executed by the target task execution node.
11. The distributed computing device of claim 10, wherein the task scheduling module is further configured to:

    If there is no dependency relationship between the tasks to be executed in the task group to be executed, then according to the writing language tags of the tasks to be executed in the task group to be executed, each task to be executed in the task group to be executed Dispatched to the corresponding task execution node for execution.
12. A distributed computing system, characterized in that the distributed computing system includes a task scheduling node, a task execution node and a task initiation node, the task scheduling node is deployed on the public network, the task execution node and the task initiation Nodes are deployed on public or private networks, where,

    The task scheduling node is used to register each terminal device as a task execution node or a task initiation node according to the node label in the registration request when receiving the registration request sent by each terminal device;

    The task scheduling node is also used to schedule the task to be executed in the task execution request to the corresponding task execution node for execution according to a preset task scheduling strategy when receiving the task execution request sent by the task initiating node;

    The task scheduling node is also used to receive the task execution result returned by the corresponding task execution node, and send the task execution result to the corresponding task initiation node;

    The task execution node is configured to receive the task to be executed scheduled by the task scheduling node, execute the task to be executed, and return the task execution result of the task to the task scheduling node;

    The task initiation node is used to generate a task execution request carrying a task to be executed and a writing language tag when a triggered task initiation instruction is detected, and send the task execution request to the task scheduling node.
13. A distributed computing device, characterized in that the distributed computing device includes a processor, a memory, and computer readable instructions stored on the memory and executable by the processor, wherein the computer is readable When the instruction is executed by the processor, the following steps are implemented:

    When receiving the registration request sent by each terminal device, according to the node label in the registration request, register each terminal device as a task execution node or a task initiation node;

    When receiving the task execution request sent by the task initiating node, according to the preset task scheduling strategy, the task to be executed in the task execution request is scheduled to the corresponding task execution node for execution;

    Receiving the task execution result returned by the corresponding task execution node, and sending the task execution result to the corresponding task initiation node.
14. The distributed computing device according to claim 13, wherein the step of registering each terminal device as a task execution node or a task initiation node according to the node label in the registration request includes:

    Reading a node label from the registration request, and determining whether the node label is an execution node label or an initiating node label;

    If the node label is an execution node label, register the corresponding terminal device as a task execution node;

    If the node label is an initiating node label, the corresponding terminal device is registered as a task initiating node.
15. The distributed computing device according to claim 13, wherein the step of scheduling the task to be executed in the task execution request to a corresponding task execution node for execution according to a preset task scheduling strategy includes:

    Reading the writing language tag of the task to be executed from the task execution request;

    Determine all the registered task execution nodes that contain the writing language tags as candidate task execution nodes;

    Obtain the current running state and currently available computing resources of each candidate task execution node, and determine the candidate task execution node with the current running state as idle and the most currently available computing resources as the target task execution node;

    Scheduling the task to be executed to the target task execution node for execution.
16. The distributed computing device according to claim 13, wherein the step of scheduling the task to be executed in the task execution request to a corresponding task execution node for execution according to a preset task scheduling strategy includes:

    Determine whether there is a task group to be executed including at least two tasks to be executed in the task execution request;

    If there is a task group to be executed including at least two tasks to be executed in the task execution request, it is determined whether there is a dependency relationship between the tasks to be executed in the task group to be executed;

    If there is a dependency relationship between the tasks to be executed in the task group to be executed, the target task execution node is determined according to the writing language tags of each task to be executed in the task group to be executed;

    All the tasks to be executed in the task group to be executed are scheduled to be executed by the target task execution node.
17. The distributed computing device according to claim 16, wherein after the step of determining whether there is a dependency relationship between tasks to be executed in the task group to be executed, the method further includes:

    If there is no dependency relationship between the tasks to be executed in the task group to be executed, then according to the writing language tags of the tasks to be executed in the task group to be executed, each task to be executed in the task group to be executed Dispatched to the corresponding task execution node for execution.
18. A readable storage medium, characterized in that computer readable instructions are stored on the readable storage medium, wherein when the computer readable instructions are executed by a processor, the following steps are implemented:

    When receiving the registration request sent by each terminal device, according to the node label in the registration request, register each terminal device as a task execution node or a task initiation node;

    When receiving the task execution request sent by the task initiating node, according to the preset task scheduling strategy, the task to be executed in the task execution request is scheduled to the corresponding task execution node for execution;

    Receiving the task execution result returned by the corresponding task execution node, and sending the task execution result to the corresponding task initiation node.
19. The readable storage medium according to claim 18, wherein the step of registering each terminal device as a task execution node or a task initiation node according to the node label in the registration request includes:

    Reading a node label from the registration request, and determining whether the node label is an execution node label or an initiating node label;

    If the node label is an execution node label, register the corresponding terminal device as a task execution node;

    If the node label is an initiating node label, the corresponding terminal device is registered as a task initiating node.
20. The readable storage medium according to claim 18, wherein the step of scheduling the task to be executed in the task execution request to a corresponding task execution node for execution according to a preset task scheduling strategy includes:

    Reading the writing language tag of the task to be executed from the task execution request;

    Determine all the registered task execution nodes that contain the writing language tags as candidate task execution nodes;

    Obtain the current running state and currently available computing resources of each candidate task execution node, and determine the candidate task execution node with the current running state as idle and the most currently available computing resources as the target task execution node;

    Scheduling the task to be executed to the target task execution node for execution.