CN116302456A - Meta universe computing resource scheduling system - Google Patents
Meta universe computing resource scheduling system Download PDFInfo
- Publication number
- CN116302456A CN116302456A CN202310586512.XA CN202310586512A CN116302456A CN 116302456 A CN116302456 A CN 116302456A CN 202310586512 A CN202310586512 A CN 202310586512A CN 116302456 A CN116302456 A CN 116302456A
- Authority
- CN
- China
- Prior art keywords
- computing
- task
- unit
- scheduling
- response
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000004044 response Effects 0.000 claims abstract description 229
- 238000004364 calculation method Methods 0.000 claims abstract description 181
- 239000000463 material Substances 0.000 claims description 52
- 230000005540 biological transmission Effects 0.000 claims description 19
- 238000012544 monitoring process Methods 0.000 claims description 19
- 239000000725 suspension Substances 0.000 claims description 5
- 239000002699 waste material Substances 0.000 abstract description 5
- 238000009877 rendering Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007334 memory performance Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—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
-
- 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
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5011—Pool
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/502—Proximity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5021—Priority
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a metauniverse computing resource scheduling system, which comprises a metauniverse server, a task management unit, a real-time response computing unit and a scheduling response computing unit, wherein the metauniverse server is used for receiving a request from a user; the meta space server is used for generating a calculation task and sending the calculation task to the task management unit; the task management unit is used for detecting whether each scheduling response calculation unit is idle, and distributing calculation tasks to the idle scheduling response calculation units when the scheduling response calculation units are idle; when there is no idle scheduling response calculation unit, the calculation task is allocated to the real-time response calculation unit. And when the scheduling response computing unit is idle, computing tasks are distributed to the idle scheduling response computing unit, and only when the idle scheduling response computing unit is not available, the computing tasks are distributed to the real-time response computing unit, so that the utilization rate of computing resources of the scheduling response computing unit is improved, long-time waiting tasks of the scheduling response computing unit are avoided, and the waste of computing resources is effectively reduced.
Description
Technical Field
The invention relates to the technical field of metauniverse computing resource processing, in particular to a metauniverse computing resource scheduling system.
Background
The meta-universe (or virtual world) is a simulated environment in which users can live in the form of digital avatars and interact with other users through the avatars. Digital avatars, objects and scenes in the meta-universe are typically three-dimensional models. The virtual environment in the meta-universe is a simulation of a real environment, and thus a user can obtain an immersive application experience. To obtain a virtual environment that approximates a real environment, rendering digital avatars and virtual scenes in real time requires massive computing resources and tremendous network bandwidth. The calculation mode based on cloud computing is difficult to meet the real-time rendering requirements of mass users.
In order to meet the demands of computing resources in the meta universe, one current method is to put part (or all) of rendering computation of a client into an edge computing unit (provided by a user with idle available computing resources) for processing, and return a rendering result to the client after the processing is completed; the client integrates the rendering task done by the edge node with the client's local rendering portion (if needed) and presents the final result to the user. The edge computing unit may obtain incentives based on the intended computing task it is performing.
The quality of the computing service provided cannot be guaranteed due to the uncertainty of the computing resources of the edge computing units themselves, the network bandwidth. Therefore, the edge computing unit resource pool needs to have redundancy, that is, the edge computing unit resource pool should contain as many computing resources as possible, and the destination computing task can select the computing unit with the highest availability from the resource pool, and the rest of computing units are used as backup computing units. The problem is that the computer as the backup computing unit cannot get rewards during waiting for a task, reducing the user's willingness to provide resources.
Disclosure of Invention
In view of the above, it is desirable to provide a metauniverse computing resource scheduling system.
A metauniverse computing resource scheduling system comprising: the system comprises a meta space server, a task management unit, a plurality of real-time response calculation units and a plurality of scheduling response calculation units;
the meta space server is used for generating a target computing task and sending the target computing task to the task management unit;
the task management unit is used for detecting whether each scheduling response calculation unit is idle, and distributing the target calculation task to the idle scheduling response calculation unit when at least one scheduling response calculation unit is idle; when the idle scheduling response calculation unit does not exist, the target calculation task is distributed to the real-time response calculation unit;
the real-time response calculation unit is used for receiving the target calculation task and executing the target calculation task;
the scheduling response calculation unit is used for receiving the target calculation task and executing the target calculation task.
In one embodiment, the task management unit is configured to, when there is no idle scheduling response calculation unit, allocate the destination calculation task to the real-time response calculation unit, and detect whether there is the scheduling response calculation unit meeting a task condition, if there is the scheduling response calculation unit meeting a task condition, send a suspension instruction to the scheduling response calculation unit, and send the destination calculation task to the scheduling response calculation unit meeting the task condition;
the scheduling response calculating unit is used for suspending or stopping the current calculating task after a preset time after receiving the suspending instruction, and starting to execute the target calculating task.
In one embodiment, the real-time response calculating unit is configured to stop executing the destination computing task when the scheduling response calculating unit starts executing the destination computing task.
In one embodiment, the number of real-time response calculation units is smaller than the number of scheduling response calculation units.
In one embodiment, the meta-universe server is configured to generate a destination computing task, and send the destination computing task and computing materials required by the destination computing task to the task management unit;
the task management unit is used for distributing the computing materials to the idle scheduling response computing unit or the real-time response computing unit;
the real-time response calculation unit is used for receiving the target calculation task and executing the target calculation task based on the calculation material;
the real-time response calculation unit is used for receiving the target calculation task and executing the target calculation task based on the calculation material.
In one embodiment, the task management unit includes a scheduling module, a message module, and a transmission module;
the scheduling module is used for receiving the target computing task and computing materials required by the target computing task sent by the meta space server, controlling the message module to send and receive messages to the real-time response computing unit or the scheduling response computing unit, and controlling the transmission module to send the target computing task and the computing materials to the real-time response computing unit or the scheduling response computing unit;
the real-time response calculation unit is used for responding to the received message, receiving the target calculation task and the calculation material, and executing the target calculation task based on the calculation material;
the scheduling response calculating unit is used for responding to the received message, receiving the target calculating task and the calculating material, and executing the target calculating task based on the calculating material.
In one embodiment, the task management unit further comprises a decision module;
the scheduling module is used for receiving the task strategy sent by the meta-universe server and sending the task strategy to the decision module;
the decision module is used for acquiring the task strategy from the scheduling module, acquiring the current resource pool states of the real-time response computing units and the scheduling response computing units based on the task strategy, and generating an execution strategy based on the resource pool states;
the scheduling module is also used for controlling the transmission module to send the target computing task and the computing material to the real-time response computing unit or the scheduling response computing unit according to the execution strategy.
In one embodiment, the task management unit further comprises a monitoring module;
the monitoring module is used for monitoring the idle state and the occupied state of each real-time response computing unit and each scheduling response computing unit, and obtaining the resource pool state.
In one embodiment, the monitoring module is further configured to monitor performance parameters of each of the real-time response calculation units and each of the scheduling response calculation units;
the decision module is configured to generate an execution policy based on the performance parameter and the resource pool state.
In one embodiment, the task management unit further comprises a history database;
the history database is used for storing performance parameters of each real-time response computing unit and each scheduling response computing unit and the resource pool state.
According to the meta-universe computing resource scheduling system, the task management unit distributes the target computing task to the idle scheduling response computing unit when the scheduling response computing unit is idle, and distributes the target computing task to the real-time response computing unit only when the scheduling response computing unit is not idle, so that the utilization rate of computing resources of the scheduling response computing unit is effectively improved, long-time waiting tasks of the scheduling response computing unit are avoided, and the waste of computing resources can be effectively reduced.
Drawings
FIG. 1 is a schematic diagram of a system framework of a metauniverse computing resource scheduling system in one embodiment;
FIG. 2 is a schematic diagram of a framework of a task management unit in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Example 1
In this embodiment, as shown in fig. 1, a metauniverse computing resource scheduling system is provided, which includes: the system comprises a meta space server, a task management unit, a plurality of real-time response calculation units and a plurality of scheduling response calculation units;
the meta space server is used for generating a target computing task and sending the target computing task to the task management unit; the task management unit is used for detecting whether each scheduling response calculation unit is idle, and distributing the target calculation task to the idle scheduling response calculation unit when at least one scheduling response calculation unit is idle; when the idle scheduling response calculation unit does not exist, the target calculation task is distributed to the real-time response calculation unit; the real-time response calculation unit is used for receiving the target calculation task and executing the target calculation task; the scheduling response calculation unit is used for receiving the target calculation task and executing the target calculation task.
In this embodiment, the metauniverse server communicates with the task management unit via a network. The real-time response calculating unit and the dispatch response calculating unit may be, but not limited to, various personal computers, servers, notebook computers, smartphones, tablet computers or portable wearable devices, the task management unit and the metauniverse server may be implemented by independent servers or a server cluster formed by a plurality of servers, and the metauniverse server may include one or a plurality of servers or a plurality of cloud computing servers, and the metauniverse server stores various types of software required by the metauniverse and various computing materials required by executing computing tasks.
The task management unit, the real-time response computing units and the scheduling response computing units belong to an edge computing unit resource pool, are computing units of the edge computing resource pool, can realize distributed computing, and the computing resources of the real-time response computing units and the scheduling response computing units are scheduled by the task management unit. According to the computing, storage, network resources and user usage modes of the computing device, the user usage modes comprise part-time and full-time, and the computing device can be divided into a real-time response computing unit and a scheduling response computing unit. The real-time response computing unit is a computing device which has high performance and can complete computing tasks in full time, and can receive and execute the computing tasks issued from the meta-universe computing unit in real time, and the real-time response computing unit can execute the computing tasks in meta-universe in full time; the dispatching response computing unit completes the self business at ordinary times, completes the computing task of the virtual world when needed, and performs the computing task of the meta universe for the part-time role of the corresponding dispatching computing unit.
In this embodiment, the destination computing task is a computing task that needs to be completed in the meta universe, and after the task management unit acquires the destination computing task, it detects whether there is an idle scheduling response computing unit, if yes, the destination computing task is allocated to the idle scheduling response computing unit, if no, the destination computing task is allocated to the real-time response computing unit, and the real-time response computing unit acquires and starts executing the computing task. In this embodiment, by allocating the destination computing task to the scattered idle resources in the computing resource pool for computing, the utilization rate of the computing resources of the scheduling response computing unit can be effectively improved, long-time waiting tasks of the scheduling response computing unit are avoided, and the waste of the computing resources can be effectively reduced.
In one embodiment, the task management unit is configured to, when there is no idle scheduling response calculation unit, allocate the destination calculation task to the real-time response calculation unit, and detect whether there is the scheduling response calculation unit meeting a task condition, if there is the scheduling response calculation unit meeting a task condition, send a suspension instruction to the scheduling response calculation unit, and send the destination calculation task to the scheduling response calculation unit meeting the task condition; the scheduling response calculating unit is used for suspending or stopping the current calculating task after a preset time after receiving the suspending instruction, and starting to execute the target calculating task.
In this embodiment, when there is no idle scheduling response calculation unit, the real-time response calculation unit acquires the destination calculation task, and executes the destination calculation task. Meanwhile, the task management unit searches a scheduling response calculation unit meeting the task requirements, if the scheduling response calculation unit meeting the task conditions exists, the scheduling response calculation unit is informed to suspend or stop the current calculation task after a preset time through a suspension instruction, and the target calculation task starts to be executed; if there is an idle schedule response calculation unit, the scheduling module directly allocates the calculation task to the schedule response calculation unit. Therefore, the utilization rate of the computing resources of the scheduling response computing unit can be further improved, long-time waiting tasks of the scheduling response computing unit are further avoided, and the waste of the computing resources can be effectively reduced.
In one embodiment, the real-time response calculating unit is configured to stop executing the destination computing task when the scheduling response calculating unit starts executing the destination computing task.
In this embodiment, when there is no idle schedule response computing unit, the real-time response computing unit executes the destination computing task, where the execution of the destination computing task by the real-time response computing unit is performed temporarily, and when there is a schedule response computing unit meeting the task condition, the destination computing task is transferred from the current real-time response computing unit to the schedule response computing unit meeting the task condition after a predetermined time, the schedule response computing unit suspends the current computing task and starts to execute the destination computing task, and the real-time response computing unit stops executing the destination computing task. In this way, the utilization rate of the computing resources of the scheduling response computing unit can be further improved.
In one embodiment, the number of real-time response calculation units is smaller than the number of scheduling response calculation units.
In this embodiment, the number of the scheduling response calculation units is large, so that the requirement of edge calculation can be fully satisfied, and the calculation resources of the resource pool of the edge calculation units are richer. The number of the real-time response computing units is small, so that the occupation of more computing resources of the full-time real-time response computing units can be effectively avoided. Thereby effectively improving the resource utilization rate.
In one embodiment, the meta-universe server is configured to generate a destination computing task, and send the destination computing task and computing materials required by the destination computing task to the task management unit; the task management unit is used for distributing the computing materials to the idle scheduling response computing unit or the real-time response computing unit; the real-time response calculation unit is used for receiving the target calculation task and executing the target calculation task based on the calculation material; the real-time response calculation unit is used for receiving the target calculation task and executing the target calculation task based on the calculation material.
In this embodiment, the computing material is a computing object or material required for executing a target computing task, and the computing material is used for implementing the target computing task. Therefore, in this embodiment, when the task management unit sends the target computing task to the computing unit, the computing material is sent to the computing unit. In one embodiment, the task management unit is configured to detect whether each of the schedule response calculation units is idle, and when at least one of the schedule response calculation units is idle, assign the destination calculation task to the idle schedule response calculation unit, and send the calculation material to the idle schedule response calculation unit; when the idle scheduling response calculation unit does not exist, the target calculation task is distributed to the real-time response calculation unit, and the calculation material is sent to the real-time response calculation unit; in one embodiment, the task management unit is further configured to, when there is no idle scheduling response computing unit, allocate the destination computing task to the real-time response computing unit, and detect whether there is the scheduling response computing unit meeting a task condition, if there is the scheduling response computing unit meeting a task condition, send a suspension instruction to the scheduling response computing unit, and send the destination computing task and the computing material to the scheduling response computing unit meeting the task condition.
In one embodiment, as shown in fig. 2, the task management unit includes a scheduling module, a message module, and a transmission module; the scheduling module is used for receiving the target computing task and computing materials required by the target computing task sent by the meta space server, controlling the message module to send and receive messages to the real-time response computing unit or the scheduling response computing unit, and controlling the transmission module to send the target computing task and the computing materials to the real-time response computing unit or the scheduling response computing unit; the real-time response calculation unit is used for responding to the received message, receiving the target calculation task and the calculation material, and executing the target calculation task based on the calculation material; the scheduling response calculating unit is used for responding to the received message, receiving the target calculating task and the calculating material, and executing the target calculating task based on the calculating material.
In various embodiments, the modules of the task management unit may be implemented by a single computer or by multiple computers. For example, the scheduling module, the message module and the transmission module are independent computers. The scheduling module receives the destination computing task and the computing material sent by the meta space server, the message module informs the computing unit of receiving the message, and the computing unit receiving the message receives the destination computing task and the computing material corresponding to the message and executes the destination computing task. Likewise, the transmission module sends the destination computing task and the computing material to the real-time response computing unit or the dispatch response computing unit, which is also implemented according to the manner in which the computing unit that performs the destination computing task is selected in the above-described embodiment.
In one embodiment, when the idle scheduling response calculating unit exists, the message module sends the message to the idle scheduling response calculating unit, and the transmission module sends the target computing task and the computing material to the idle scheduling response calculating unit; when the idle scheduling response calculating unit does not exist, the message module sends the message to the real-time response calculating unit, and the transmission module sends the target calculating task and the calculating material to the real-time response calculating unit. In one embodiment, when there is no idle dispatch response calculation unit and there is a dispatch response calculation unit meeting a task condition, a message module sends a suspend instruction to the dispatch response calculation unit and a transmission module sends the destination computing task and the computing material to the dispatch response calculation unit meeting the task condition.
In one embodiment, the task management unit further comprises a decision module; the scheduling module is used for receiving the task strategy sent by the meta-universe server and sending the task strategy to the decision module; the decision module is used for acquiring the task strategy from the scheduling module, acquiring the current resource pool states of the real-time response computing units and the scheduling response computing units based on the task strategy, and generating an execution strategy based on the resource pool states; the scheduling module is also used for controlling the transmission module to send the target computing task and the computing material to the real-time response computing unit or the scheduling response computing unit according to the execution strategy.
In this embodiment, the task policy is a task requirement for executing a target computing task, where the task requirement includes a task priority, that is, the target computing task may be assigned a priority, and the decision module formulates the task execution policy according to the priority, and may collect a corresponding fee from the user based on the priority. The decision module obtains task demands from the scheduling module, obtains the current resource pool state from the monitoring module, and makes task execution strategies with reference to data provided by the historical database, so that the scheduling module can control the message module to send messages based on the execution strategies, and the transmission module is controlled to send target calculation tasks and calculation materials.
In one embodiment, the task management unit further comprises a monitoring module; the monitoring module is used for monitoring the idle state and the occupied state of each real-time response computing unit and each scheduling response computing unit, and obtaining the resource pool state. In one embodiment, the monitoring module is further configured to monitor performance parameters of each of the real-time response calculation units and each of the scheduling response calculation units; the decision module is configured to generate an execution policy based on the performance parameter and the resource pool state.
In this embodiment, the edge computing resource pool includes a plurality of computing units, where the computing units include a real-time response computing unit and a scheduling response computing unit, and the monitoring module is configured to monitor whether each computing unit in the resource pool is in an idle state or an occupied state, so as to obtain a resource pool state of each computing unit in the whole resource pool. In addition, the monitoring module is further configured to monitor and obtain performance parameters of each computing unit, where the performance parameters include a CPU (Central Processing Unit ) performance parameter, a memory performance parameter, a CPU occupancy rate, a memory occupancy rate, a storage space occupancy rate, a network bandwidth occupancy rate, and the like. By acquiring the resource pool state and the performance parameters of each computing unit, the decision module can determine whether the computing unit is idle or not based on the resource pool state and the performance parameters of each computing unit, whether the computing unit has a condition for executing a target computing task or not, and the computing unit can execute the target computing task or the like, so that the decision module can generate an execution strategy based on the resource pool state and the performance parameters of each computing unit, and the scheduling module can control the message module to send a message based on the execution strategy, and control the transmission module to send the target computing task and the computing material.
In one embodiment, the task management unit further comprises a history database; the history database is used for storing performance parameters of each real-time response computing unit and each scheduling response computing unit and the resource pool state.
In this embodiment, the history database stores the performance parameters of each computing unit, so that the decision module can read the performance parameters of each computing unit from the history database, thereby generating the execution policy according to the performance parameters.
Example two
In this embodiment, the metauniverse computing resource scheduling system is also referred to as a virtual world system, and as shown in fig. 1, includes one or more metauniverse servers, i.e., servers hosting metauniverse, which are associated with metauniverse clients. A metauniverse server is a server or cluster of servers that stores and initiates the various types of software needed to manage Metaverse.
The edge computing unit resource pool contains computing devices provided by a plurality of users who receive rewards by providing free computing resources for completing the computing tasks of virtual world allocation. The computing devices may be divided into a real-time response computing unit and a dispatch response computing unit according to computing/storage/network resources of the computing devices and a user usage pattern (part-time/full-time). The real-time response computing unit is a computing device which has high performance and can complete computing tasks in full time, and can receive and execute the computing tasks issued from the meta-universe computing unit in real time; the dispatching response calculation unit completes the service of the dispatching response calculation unit at ordinary times, and completes the calculation task of the virtual world when needed.
After the task management unit acquires the calculation task, determining whether an idle scheduling response calculation unit exists, if not, acquiring and starting to execute the calculation task by the real-time response calculation unit, searching a scheduling response calculation unit meeting the task requirement by a scheduling module, suspending or stopping the current calculation task by the scheduling response calculation unit, and starting to execute the allocation calculation task after a preset time; if there is an idle schedule response calculation unit, the scheduling module directly allocates the calculation task to the schedule response calculation unit.
This approach may reduce the waste of computing resources. In theory, the number of real-time response calculation units should be smaller than the number of scheduling response calculation units.
The meta space computing unit uploads the computing task and materials required by the computing task to a task management unit of an edge computing unit resource pool after generating the computing task, the scheduling module selects an idle real-time response computing unit to temporarily complete the computing task, and simultaneously, the scheduling module selects a scheduling response computing unit according to a strategy to inform the scheduling response computing unit of suspending (saving intermediate results and current states) or stopping the current task within a preset time. After the time arrives, the calculation task is transferred to the selected dispatch response calculation unit by the current real-time response calculation unit.
As shown in fig. 2, the task management unit includes a scheduling module, a decision module, a monitoring module, a message module, a transmission module, and a history database.
The scheduling module is responsible for receiving the calculation tasks and related calculation materials sent by the meta space server, sending task demands to the decision module, obtaining calculation task strategies and execution equipment, sending and receiving messages to the real-time response calculation unit and the scheduling response calculation unit by the management message module, and sending the related calculation materials to the real-time response calculation unit and the scheduling response calculation unit by the management transmission module.
The message module is responsible for message transmission between the scheduling module and the computing unit, such as notifying the scheduling response computing unit of the preparation time of the next task, obtaining the ready message of the response computing unit, notifying the real-time response computing unit that the task can be transferred, and the like.
The decision module obtains task demands from the scheduling module, obtains the current resource pool state from the monitoring module, and makes a task execution strategy by referring to historical database data.
The monitoring module may actively query the current state (idle/occupied) of the computing units or passively receive the state information reported by the computing units, as well as the computing/storage/network performance parameters and real-time data of the respective computing units. While the monitoring data is stored in a historical database.
The historical database records data such as calculation/storage/network performance data of the calculation unit, task completion ratings and the like, and can set use priority for the calculation unit according to the data so as to enable the decision-making module to make an execution strategy.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A meta-universe computing resource scheduling system, comprising: the system comprises a meta space server, a task management unit, a plurality of real-time response calculation units and a plurality of scheduling response calculation units;
the meta space server is used for generating a target computing task and sending the target computing task to the task management unit;
the task management unit is used for detecting whether each scheduling response calculation unit is idle, and distributing the target calculation task to the idle scheduling response calculation unit when at least one scheduling response calculation unit is idle; when the idle scheduling response calculation unit does not exist, the target calculation task is distributed to the real-time response calculation unit;
the real-time response calculation unit is used for receiving the target calculation task and executing the target calculation task;
the scheduling response calculation unit is used for receiving the target calculation task and executing the target calculation task.
2. The meta space computing resource scheduling system according to claim 1, wherein the task management unit is configured to, when there is no idle scheduling response computing unit, allocate the destination computing task to the real-time response computing unit, and detect whether there is the scheduling response computing unit conforming to a task condition, if there is the scheduling response computing unit conforming to a task condition, send a suspension instruction to the scheduling response computing unit, and send the destination computing task to the scheduling response computing unit conforming to the task condition;
the scheduling response calculating unit is used for suspending or stopping the current calculating task after a preset time after receiving the suspending instruction, and starting to execute the target calculating task.
3. The metauniverse computing resource scheduling system of claim 2 wherein the real-time response computing unit is configured to stop executing the destination computing task when the scheduling response computing unit starts executing the destination computing task.
4. The metauniverse computing resource scheduling system of claim 1 wherein the number of real-time response computing units is less than the number of scheduling response computing units.
5. The metauniverse computing resource scheduling system of claim 1 wherein the metauniverse server is configured to generate a destination computing task, and send the destination computing task and computing materials required by the destination computing task to the task management unit;
the task management unit is used for distributing the computing materials to the idle scheduling response computing unit or the real-time response computing unit;
the real-time response calculation unit is used for receiving the target calculation task and executing the target calculation task based on the calculation material;
the real-time response calculation unit is used for receiving the target calculation task and executing the target calculation task based on the calculation material.
6. The metauniverse computing resource scheduling system of any one of claims 1-5, wherein the task management unit includes a scheduling module, a message module, and a transmission module;
the scheduling module is used for receiving the target computing task and computing materials required by the target computing task sent by the meta space server, controlling the message module to send and receive messages to the real-time response computing unit or the scheduling response computing unit, and controlling the transmission module to send the target computing task and the computing materials to the real-time response computing unit or the scheduling response computing unit;
the real-time response calculation unit is used for responding to the received message, receiving the target calculation task and the calculation material, and executing the target calculation task based on the calculation material;
the scheduling response calculating unit is used for responding to the received message, receiving the target calculating task and the calculating material, and executing the target calculating task based on the calculating material.
7. The metauniverse computing resource scheduling system of claim 6 wherein the task management unit further comprises a decision module;
the scheduling module is used for receiving the task strategy sent by the meta-universe server and sending the task strategy to the decision module;
the decision module is used for acquiring the task strategy from the scheduling module, acquiring the current resource pool states of the real-time response computing units and the scheduling response computing units based on the task strategy, and generating an execution strategy based on the resource pool states;
the scheduling module is also used for controlling the transmission module to send the target computing task and the computing material to the real-time response computing unit or the scheduling response computing unit according to the execution strategy.
8. The metauniverse computing resource scheduling system of claim 7 wherein the task management unit further comprises a monitoring module;
the monitoring module is used for monitoring the idle state and the occupied state of each real-time response computing unit and each scheduling response computing unit, and obtaining the resource pool state.
9. The metauniverse computing resource scheduling system of claim 8 wherein the monitoring module is further configured to monitor performance parameters of each of the real-time response computing units and each of the schedule response computing units;
the decision module is configured to generate an execution policy based on the performance parameter and the resource pool state.
10. The metauniverse computing resource scheduling system of claim 9 wherein the task management unit further comprises a history database;
the history database is used for storing performance parameters of each real-time response computing unit and each scheduling response computing unit and the resource pool state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310586512.XA CN116302456B (en) | 2023-05-24 | 2023-05-24 | Meta universe computing resource scheduling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310586512.XA CN116302456B (en) | 2023-05-24 | 2023-05-24 | Meta universe computing resource scheduling system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116302456A true CN116302456A (en) | 2023-06-23 |
| CN116302456B CN116302456B (en) | 2023-08-29 |
Family
ID=86787333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310586512.XA Active CN116302456B (en) | 2023-05-24 | 2023-05-24 | Meta universe computing resource scheduling system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116302456B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110647391A (en) * | 2019-09-27 | 2020-01-03 | 北京邮电大学 | Edge computing method and system for satellite-ground cooperative network |
| US10698879B1 (en) * | 2017-10-12 | 2020-06-30 | EMC IP Holding Company LLC | Data management for extended multi-cloud environment |
| CN112491742A (en) * | 2020-11-16 | 2021-03-12 | 广东电网有限责任公司电力调度控制中心 | Method and device for scheduling edge computing terminal resources |
| US20210096911A1 (en) * | 2020-08-17 | 2021-04-01 | Essence Information Technology Co., Ltd | Fine granularity real-time supervision system based on edge computing |
| CN112671830A (en) * | 2020-12-02 | 2021-04-16 | 武汉联影医疗科技有限公司 | Resource scheduling method, system, device, computer equipment and storage medium |
| CN115269757A (en) * | 2022-07-29 | 2022-11-01 | 北京地林伟业科技股份有限公司 | Cloud data integration system based on edge calculation |
| CN115904671A (en) * | 2023-02-20 | 2023-04-04 | 中国华能集团清洁能源技术研究院有限公司 | Task scheduling method, device, equipment and medium in edge computing environment |
-
2023
- 2023-05-24 CN CN202310586512.XA patent/CN116302456B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10698879B1 (en) * | 2017-10-12 | 2020-06-30 | EMC IP Holding Company LLC | Data management for extended multi-cloud environment |
| CN110647391A (en) * | 2019-09-27 | 2020-01-03 | 北京邮电大学 | Edge computing method and system for satellite-ground cooperative network |
| US20210096911A1 (en) * | 2020-08-17 | 2021-04-01 | Essence Information Technology Co., Ltd | Fine granularity real-time supervision system based on edge computing |
| CN112491742A (en) * | 2020-11-16 | 2021-03-12 | 广东电网有限责任公司电力调度控制中心 | Method and device for scheduling edge computing terminal resources |
| CN112671830A (en) * | 2020-12-02 | 2021-04-16 | 武汉联影医疗科技有限公司 | Resource scheduling method, system, device, computer equipment and storage medium |
| CN115269757A (en) * | 2022-07-29 | 2022-11-01 | 北京地林伟业科技股份有限公司 | Cloud data integration system based on edge calculation |
| CN115904671A (en) * | 2023-02-20 | 2023-04-04 | 中国华能集团清洁能源技术研究院有限公司 | Task scheduling method, device, equipment and medium in edge computing environment |
Non-Patent Citations (1)
| Title |
|---|
| 刘伟;: "5G时代运营商边缘算力部署浅析", 中国新通信, no. 18, pages 7 - 8 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116302456B (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110858161B (en) | Resource allocation method, device, system, equipment and medium | |
| US10838777B2 (en) | Distributed resource allocation method, allocation node, and access node | |
| CN110647394B (en) | Resource allocation method, device and equipment | |
| CN106919445B (en) | Method and device for scheduling containers in cluster in parallel | |
| US8656404B2 (en) | Statistical packing of resource requirements in data centers | |
| CN111427675B (en) | Data processing method and device and computer readable storage medium | |
| US20200174844A1 (en) | System and method for resource partitioning in distributed computing | |
| JP2015011716A (en) | Task execution by idle resources in grid computing system | |
| CN111338791A (en) | Method, device and equipment for scheduling cluster queue resources and storage medium | |
| US11838384B2 (en) | Intelligent scheduling apparatus and method | |
| CN108121599A (en) | A kind of method for managing resource, apparatus and system | |
| Garala et al. | A performance analysis of load balancing algorithms in cloud environment | |
| CN112905334A (en) | Resource management method, device, electronic equipment and storage medium | |
| CN109992373B (en) | Resource scheduling method, information management method and device and task deployment system | |
| Balla et al. | Reliability enhancement in cloud computing via optimized job scheduling implementing reinforcement learning algorithm and queuing theory | |
| CN110231915B (en) | Data management method, system, device, computer equipment and storage medium | |
| CN113760549B (en) | Pod deployment method and device | |
| CN111163140A (en) | Method, apparatus and computer readable storage medium for resource acquisition and allocation | |
| Shukla et al. | Survey on Importance of Load Balancing for Cloud Computing | |
| CN116302456B (en) | Meta universe computing resource scheduling system | |
| CN110955504B (en) | Method, server, system and storage medium for intelligently distributing rendering tasks | |
| CN111556126B (en) | Model management method, system, computer device and storage medium | |
| CN116263715A (en) | Automatic scaling system and method for cloud native intelligent typesetting service | |
| CN111435319A (en) | Cluster management method and device | |
| CN114489978A (en) | Resource scheduling method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |