WO2021190360A1 - 汽车诊断云平台中的虚拟化资源调度系统、方法 - Google Patents

汽车诊断云平台中的虚拟化资源调度系统、方法 Download PDF

Info

Publication number
WO2021190360A1
WO2021190360A1 PCT/CN2021/081129 CN2021081129W WO2021190360A1 WO 2021190360 A1 WO2021190360 A1 WO 2021190360A1 CN 2021081129 W CN2021081129 W CN 2021081129W WO 2021190360 A1 WO2021190360 A1 WO 2021190360A1
Authority
WO
WIPO (PCT)
Prior art keywords
resource
virtualized
service
scheduling
module
Prior art date
Application number
PCT/CN2021/081129
Other languages
English (en)
French (fr)
Inventor
张良
Original Assignee
深圳市道通科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市道通科技股份有限公司 filed Critical 深圳市道通科技股份有限公司
Publication of WO2021190360A1 publication Critical patent/WO2021190360A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • 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]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals

Definitions

  • This application relates to the technical field of data resources in a cloud computing platform, and in particular to a virtualized resource scheduling system, method, and virtualized resource scheduling device in an automobile diagnostic cloud platform.
  • the resources required by a service application are usually not static. For example, due to the logic of the service application itself, there are repeated iterations of a small amount of data in a period of time, and a large amount of data in another period of time. Access to external storage data or communication, which leads to changes in resource requirements. Therefore, it is of great significance to realize the on-demand allocation of resources in the cloud platform architecture, especially when the number of service applications increases, it is of great significance to configure corresponding resources for them.
  • the technical problem to be solved by the present invention is to provide a virtualized resource scheduling system, method, and virtualized resource scheduling equipment in an automobile diagnostic cloud platform, which solves how to configure the corresponding virtualized resource technology when the number of service applications increases problem.
  • a virtualized resource scheduling system in an automobile diagnostic cloud platform includes: a scheduling service core module, a resource management module, and a virtualized resource module,
  • the virtualized resource module is obtained by virtualizing data resources and service resources in the car diagnostic cloud platform;
  • the scheduling service core module is configured to receive a resource request of the car diagnostic cloud platform service application, and obtain the mapping relationship between the service application and the virtualized resource according to the resource request;
  • the resource management module is configured to obtain the virtualized resource corresponding to the service application from the virtualized resource module according to the mapping relationship, and couple the virtualized resource with the service application.
  • the dispatch service core module includes a dispatcher interface
  • the dispatcher interface is used to receive the resource request of the automobile diagnosis cloud platform service application, and is also used to send the mapping relationship to the resource management module.
  • the dispatch service core module further includes: an interface server, a dispatcher processing unit, a dispatcher cache unit, a program dispatch and preemption unit,
  • the interface server is configured to obtain the resource request through the dispatcher interface, and write the resource request into the dispatcher processing unit;
  • the program scheduling and preemption unit is configured to make a scheduling or preemption decision after monitoring that the scheduling program processing unit receives the resource request;
  • the scheduler processing unit is configured to process the resource request according to the scheduling or preemption decision, and obtain the mapping relationship between the service application and the virtualized resource corresponding to the resource request from the scheduler cache unit .
  • the interface server is also used to manage the communication between the dispatcher interface and the resource management module and the virtualized resource module.
  • the scheduler cache unit is used to cache data associated with the scheduler, and the data includes resource status information and resource usage status information that have been laid out.
  • the scheduling service core module further includes an administrator service unit, the administrator service unit is used to process requests from an administrator, and is also used to update the scheduling or preemption decision according to the administrator's request .
  • the resource management module includes a dispatcher processing unit and a dispatcher interaction unit,
  • the dispatcher processing unit is used to send the resource request to the dispatch service core module and provide resource information, and is also used to bind the resource and the container according to the mapping relationship;
  • the scheduler interaction unit is used to display resource scheduling distribution status and service request status, and is also used to receive administrator operations.
  • the virtualized resource module includes a physical server cluster and a virtual machine cluster
  • Both the physical server cluster and the virtual machine cluster are used to carry the data resource and the service resource.
  • the resource management module is further used for:
  • the adjusting the resource capacity includes adjusting the node scales of the physical server cluster and the virtual machine cluster.
  • a virtualized resource scheduling method in an automobile diagnosis cloud platform is executed by the above-mentioned system, and the method includes:
  • the system virtualizes the data resources and service resources in the car diagnostic cloud platform through the virtualized resource module to obtain virtualized resources;
  • the system receives the resource request of the automobile diagnosis cloud platform service application through the dispatch service core module, and obtains the mapping relationship between the service application and the virtualized resource according to the resource request;
  • the system obtains the virtualized resource corresponding to the service application based on the virtualized resource and the mapping relationship through the resource management module, and couples the virtualized resource with the service application.
  • the system receives the resource request of the car diagnostic cloud platform service application through the dispatch service core module, and obtains the mapping relationship between the service application and the virtualized resource according to the resource request, including:
  • the system obtains the resource request through the dispatcher interface and the interface server, and writes the resource request into the dispatcher processing unit;
  • the system monitors the scheduler processing unit through the program scheduling and preemption unit, and makes a scheduling or preemption decision after monitoring that the scheduler processing unit receives the resource request;
  • the system uses the scheduler processing unit to process the resource request according to the scheduling or preemption decision, and obtains from the scheduler cache unit the information between the service application and the virtualized resource corresponding to the resource request. Mapping relations.
  • the method further includes:
  • the system manages the communication between the dispatcher interface and the resource management module and the virtualized resource module through the interface server.
  • the method further includes:
  • the system caches the data associated with the scheduler through the scheduler cache unit, and the data includes the resource status information and resource usage status information that have been deployed.
  • the method further includes:
  • the system processes the request from the administrator through the administrator service unit, and updates the scheduling or preemption decision according to the administrator's request.
  • the method further includes:
  • the system adjusts the resource capacity of the virtualized resource module according to the number of received resource requests through the resource management module, so that the resources provided by the virtualized resource module match the service request.
  • the virtualized resource module includes a physical server cluster and a virtual machine cluster
  • the system adjusting the resource capacity of the virtualized resource module according to the received resource request quantity through the resource management module includes: the system adjusting the physical server according to the received resource request quantity through the resource management module The cluster and the node scale of the virtual machine cluster.
  • a virtualized resource scheduling device including:
  • At least one processor At least one processor
  • the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the aforementioned automobile diagnostic cloud The steps of the virtualized resource scheduling method in the platform.
  • the virtualized resource scheduling system, method, and virtualized resource scheduling device in the automobile diagnosis cloud platform can virtualize the data resources and service resources in the automobile diagnosis cloud platform into a unified It also establishes the mapping relationship between virtualized resources and service applications, so that it can be responsible for the scheduling of microservice application resources in a unified manner, making the scheduling more flexible.
  • this unified scheduling mechanism can be used to configure appropriate virtualized resources for service applications.
  • the ability to combine the business characteristics of the automobile diagnostic cloud platform at the same time improves the containerization of big data services and the management efficiency of unified service operation and maintenance management.
  • FIG. 1 is a schematic diagram of the system structure of an automobile diagnosis cloud platform provided by an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of a virtualized resource scheduling system in an automobile diagnosis cloud platform provided by an embodiment of the present invention
  • Fig. 3 is a schematic structural diagram of a dispatch service core module provided by an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of resource scheduling based on the virtualized resource scheduling system provided by an embodiment of the present invention.
  • FIG. 5 is a flowchart of a virtualized resource scheduling method in an automobile diagnosis cloud platform provided by an embodiment of the present invention
  • Fig. 6 is a schematic diagram of the hardware structure of a virtualized resource scheduling device provided by an embodiment of the present invention.
  • FIG. 1 is a schematic diagram of the system structure of an automobile diagnosis cloud platform provided by an embodiment of the present invention.
  • the virtualized resource scheduling system and method can be applied to the automobile diagnosis cloud platform.
  • the automotive diagnostic cloud platform system is designed with a "vertical layered and horizontally divided" cloud computing SOA architecture to provide service definition, development, deployment, and operation.
  • the various layers are implemented through loose coupling.
  • Logic reuse through the way of services to achieve the loose coupling of modules between the same layer, so that the platform has good scalability.
  • the system provides SOA-based mass data integration services, including unified data model and management, heterogeneous data collection and integration, and mass data organization and storage, sharing and release, analysis and mining, etc., so that data storage can be based on the architecture It has the ability to adapt to future data volume, storage volume and business changes, supports the storage and efficient use of future massive data, and supports horizontal expansion to support business development. At the same time, the system architecture and software design fully consider the actual situation of users and meet the actual requirements of industry personnel.
  • the system can be constructed with PC servers, with less or no array storage, to achieve system high performance and low cost.
  • the core database software of the system adopts ACID (Atomicity, Consistency, Isolation, Durability) protection mechanism to ensure transaction integrity and data consistency;
  • the collection adopts a mechanism based on database log backup and recovery to ensure data integrity and data consistency;
  • data transmission adopts reliable and stable open bus technology to ensure the stability and reliability of data transmission;
  • each application service system adopts multi-instance nodes Cluster deployment ensures that the system can continue to work stably and uninterruptedly.
  • the system modules all adopt the cluster architecture to eliminate Single point of failure;
  • the network switch adopts two machines, and the network link adopts two-wire redundancy to ensure network link redundancy.
  • the automobile diagnostic cloud platform system includes a business bus, a data bus, an infrastructure layer, a data processing and data platform layer, an interface layer, and an application layer.
  • the infrastructure layer is used to construct the basic operating environment of the automobile diagnostic cloud platform system;
  • the data processing and data platform layer is constructed based on the infrastructure layer, which provides data cleaning, analysis and mining services, and provides industry Data collection, data caching service, data access service;
  • the interface layer is constructed based on the data processing and data platform layer, and it is used to provide open interface services for external application systems and upper-layer applications;
  • the business bus passes The interface layer transmits business services to the cloud platform system;
  • the data bus transmits data to the automobile diagnostic cloud platform system through the data processing and data platform layer;
  • the application layer communicates with the interface layer, It is used to realize the separation of the front and back ends of the automobile diagnosis cloud platform system, and is also used to carry third-party applications.
  • the data processing and data platform layer is constructed based on the infrastructure layer
  • the interface layer is constructed based on the data processing and data platform layer, which refers to the infrastructure layer
  • the data processing and data platform The layer and the interface layer are from bottom to top, and the next layer is used as the basis to build the upper layer, and the upper layer can be built only after the next layer is built first.
  • the business bus may specifically be a business service bus (BSB, Business Service Bus), which may be a pipe for connecting various business service nodes in order to integrate different business systems and services of different protocols.
  • BBB Business Service Bus
  • the business service bus realizes the transformation, interpretation and routing of messages, allowing different business services to be interconnected.
  • the data bus supports at least two data communication protocols to support communication between the at least two data service nodes and the automobile diagnosis cloud platform system.
  • the data communication protocol can be set according to the type of the data source, data content, and the like.
  • the communication link between the data service node and the automobile diagnosis cloud platform system may be based on one data communication protocol for communication, or may be based on multiple data communication protocols for communication.
  • the data bus may specifically be a data service bus (DSB, Data Service Bus), which may be another pipe, which is used to connect various data service nodes and is also used to integrate different data sources.
  • the data service bus realizes the formatting and routing of data, enables the interconnection of different business services, and can be understood as an adapter gateway for data.
  • Both the service bus and the data bus establish a connection relationship with the automobile diagnosis cloud platform system through the interface layer.
  • the infrastructure layer is used to construct the basic operating environment of the automobile diagnostic cloud platform system, and the basic operating environment includes the software operating environment and the hardware operating environment of the automobile diagnostic cloud platform system.
  • the infrastructure layer is the basic guarantee for the realization of the automobile diagnosis cloud platform system.
  • the infrastructure layer includes an infrastructure layer and a basic platform layer.
  • the infrastructure layer is used to construct hardware devices and establish a virtual system based on the hardware devices; the basic platform layer is used to implement the interface layer and the The communication between the infrastructure layers is described.
  • the basic platform layer includes a container management platform, the container management platform includes at least two containers, the at least two containers are used to carry processing resources of automobile diagnosis-related services, and the at least two containers are based on the automobile diagnosis
  • the cloud platform system allocates processing resources required for each car diagnosis-related business to be processed, and each car diagnosis-related business corresponds to one or more of the at least two containers.
  • the container is essentially a process, but it is different from the process executed by the host.
  • the container process runs in its own independent namespace, so the container can have its own root file system, network configuration, process space, and user ID space.
  • the capacities of the at least two containers may be the same or different.
  • the data processing and data platform layer is constructed based on the infrastructure layer, and the data processing and data platform layer obtains the at least two vehicle diagnostic related data through the data bus, and is used to compare the at least two vehicle diagnosis related data.
  • Car diagnostic-related data is processed and access or storage services are provided.
  • the data processing and data platform layer mainly includes a data analysis and mining module, a data cleaning module, an industry data attribution module, and a data access service module.
  • the data analysis and mining module is used to analyze and mine the collected data.
  • each brand of car has its own communication protocol.
  • the car diagnosis cloud platform system first communicates with the car. Carry on communication, obtain car diagnosis related data through the data bus, and then according to the car diagnosis related data and the vehicle communication protocol, the car diagnosis cloud platform system uses machine learning methods (such as neural network) to perform learning calculations, and analyzes the best match for the car Communication protocol to prepare for the car diagnosis.
  • the data cleaning module is used to clean the collected data.
  • the data cleaning includes data cleaning, missing data processing, and noise data processing.
  • the industry data attribution module is used to collect related industry data and perform collection and reconciliation services on the collected industry data.
  • the data access service is used to manage data access requests, which mainly include data source management (such as managing which types of data are stored in which database on which machine), data connection pool management (such as Database connection management), unified transaction management (such as the management of operations such as adding, deleting, modifying, and checking the requests that need to be processed in the database cluster).
  • the interface layer is constructed based on the data processing and data platform layer.
  • the interface layer is used to provide open interface services for the application layer and receive data uploaded by external systems.
  • the interface layer implements different business interfaces for external calls through the received data.
  • the interface layer realizes the transmission of the business service with the at least two business service nodes through the business bus.
  • the business services include automobile diagnosis, recommendation and sales of automobile parts, automobile insurance, automobile residual value assessment, automobile finance, and other business services related to automobile diagnosis.
  • the application layer is in communication connection with the interface layer, and the application layer is used to realize the separation of the front and back ends of the automobile diagnosis cloud platform system, and is also used to carry third-party applications based on service terminals.
  • the service terminal includes a Web terminal, an APP terminal, a PDA terminal, and so on.
  • the third-party applications include automobile diagnosis, recommendation and sales of automobile accessories, automobile insurance, automobile residual value assessment, and automobile finance.
  • cloud platform system provided in Figure 1 can also be applied to other fields in addition to being applied to the field of automotive diagnosis.
  • the cloud platform system architecture diagram provided in FIG. 1 can also add or delete modules as needed, and is not limited to FIG. 1.
  • FIG. 2 is a schematic structural diagram of a virtualized resource scheduling system provided by an embodiment of the present invention.
  • the virtualized resource scheduling system is applied to the above-mentioned automobile diagnosis cloud platform.
  • the system includes: a scheduling service core module 10, a resource management module 20, and a virtualized resource module 30.
  • the resource management module 20 is in communication connection with the scheduling service core module 10 and the virtualized resource module 30 respectively.
  • the scheduling service core module 10 is the core of the virtualized resource scheduling system, which encapsulates all scheduling algorithms.
  • the scheduling service core module 10 can collect resources from the resource management module 20 and is responsible for resource allocation requests.
  • the scheduling service core module 10 can determine the best deployment location for each service request, and feed back the best deployment location for each request to the resource management module 20, so that the service application can obtain information from the resource management module 20 The right resources.
  • the resource management module 20 may specifically be a container orchestration system, such as Kubernetes.
  • the resource management module 20 may provide functions such as application deployment, maintenance, and expansion mechanisms, and can conveniently manage containerized applications running across machines.
  • the virtualized resource module 30 is the IT resource center, and the resources of the virtualized resource module 30 are virtualized to virtualize the physical server cluster and virtual machine cluster in the resource center into a unified microservice fine-grained resource Pool.
  • the virtualized resource module 30 is obtained by virtualizing data resources and service resources in the car diagnostic cloud platform.
  • the scheduling service core module 10 is configured to receive a resource request of the automobile diagnosis cloud platform service application, and obtain the mapping relationship between the service application and the virtualized resource according to the resource request.
  • the resource management module 20 is configured to obtain the virtualized resource corresponding to the service application from the virtualized resource module 30 according to the mapping relationship, and couple the virtualized resource with the service application.
  • the data resources in the automobile diagnosis cloud platform refer to data stored in the IT resource center, and the service resources are services running in the IT resource center.
  • the IT resource center includes a physical server cluster and a virtual machine cluster, and both the physical server cluster and the virtual machine cluster are used to carry the data resource and the service resource.
  • the data of the IT resource center refers to data related to service applications, such as car diagnostic data, car financial data, car insurance data, and so on.
  • the services of the IT resource center refer to services related to service applications, such as car diagnostic services, car financial services, and car insurance services.
  • the resource request is used to request a virtualized resource for processing the service application, and the virtualized resource may be a hardware resource.
  • the dispatch service core module 10 includes a dispatcher interface 101, an interface server 102, a dispatcher processing unit 103, a dispatcher cache unit 104, a program dispatch and preemption unit 105, and an administrator service Unit 106.
  • the dispatcher interface 101 is the external communication interface of the dispatch service core module 10, and all communications of the dispatch service core module 10 pass through the dispatcher interface 101, for example, the dispatcher interface 101 receives the car Diagnose the resource request of the cloud platform service application, and send the mapping relationship to the resource management module 20.
  • the interface server 102 is used to manage all the interfaces of the dispatching service core module 10 (including the dispatcher interface 101), and is responsible for the communication between the dispatching service core module 10 and external devices.
  • the dispatcher interface 101 supports GRPC (Google Remote Procedure Call, Google remote procedure call) protocol.
  • the dispatcher processing unit 103 is used to process all write operations input by the interface server 102, such as processing events that require updating the internal state of the dispatcher.
  • the scheduler cache unit 104 is used to cache all data related to the scheduler state, such as each queue and node, allocated used resources, the relationship between allocated used resources and nodes, and so on.
  • the dispatcher buffer unit 104 can improve the efficiency of resource allocation.
  • the program scheduling and preemption unit 105 is used to process the internal state of the scheduler.
  • the scheduler and the preemptor will work together to make scheduling or preemption decisions, and the scheduling or preemption decisions will be processed by the scheduler processing unit 103 .
  • the administrator service unit 106 is used to process a request from an administrator, and the request may be to update the scheduling or preemption decision.
  • the administrator service unit 106 can also load the configuration from the storage and update the scheduler policy.
  • the scheduler is used to manage the resource requests, for example, when there are multiple resource requests currently, the multiple resource requests correspond to a sort, and the scheduler is used to manage the sort.
  • the scheduling and preemption decisions refer to events that deal with the internal state of the scheduler, for example, scheduling one of the resource requests, or adjusting the resource requests in the back in the queue to the first order, so that Give priority to processing the resource request.
  • the scheduling program may be processed by the program scheduling and preemption unit 105, or an administrator may perform manual intervention through the administrator service unit 106.
  • the service application and the virtualization corresponding to the resource request can be obtained through the interface server 102, the dispatcher processing unit 103, the dispatcher cache unit 104, and the program scheduling and preemption unit 105.
  • the mapping relationship of resources Specifically, the interface server 102 is configured to obtain the resource request through the scheduler interface, and write the resource request to the scheduler processing unit 103; the program scheduling and preemption unit 105 is used to monitor After the scheduler processing unit 103 receives the resource request, it makes a scheduling or preemption decision; the scheduler processing unit 103 is configured to process the resource request according to the scheduling or preemption decision, and obtain information from the scheduling
  • the program cache unit 104 obtains the mapping relationship between the service application and the virtualized resource corresponding to the resource request.
  • the scheduler cache unit 104 may also cache the deployed resource status information and resource usage status information. Therefore, the mapping relationship between the service application and the virtualized resource can be established according to the deployed resource status information and the resource usage status information, and the mapping relationship can be stored in the scheduler cache unit 104.
  • the scheduling service core module 10 may obtain a virtualized resource suitable for the service application from existing resources according to a preset algorithm (such as a hash scheduling algorithm), and obtain the virtualized resource.
  • the container corresponding to the resource is changed, so as to establish a mapping relationship between the location identification information of the container and the service application.
  • virtualized resources can be allocated for each resource request according to the size of the virtualized resource required for each resource request, or the priority of each resource request, etc., and the virtualized resource and service application can be established. Mapping relations.
  • the mapping relationship data can be used to save the virtualized resource layout of existing service applications, so as to ensure that new microservices can be scheduled to appropriate virtualized resources.
  • the functional characteristics of the dispatch service core module 10 mainly include:
  • the scheduling function supports batch processing and long-term operation, as well as stateful services
  • the incoming container request can be automatically mapped to the queue according to the strategy
  • the resource management module 20 includes a dispatcher processing unit and a dispatcher interaction unit.
  • the dispatcher processing unit is used to provide resource information to the dispatch service core module 10; it is also used to bind virtualized resources and containers according to the mapping relationship data.
  • the scheduler interaction unit is used to display resource scheduling distribution status and service request status, and is also used to receive administrator operations.
  • the scheduler processing unit can be understood as the scheduler Shim Layers, and the scheduler skim runs in the host system (such as YARN (Yet Another Resource Negotiator), K8S, etc.), which is used to pass the scheduler
  • the interface converts host system resources and resource requests, and sends the system resources and resource requests to the scheduling service core module 10.
  • the dispatcher processing unit may be responsible for the actual binding of pods or containers.
  • the scheduler interaction unit may specifically be a scheduler UI (Scheduler UI), and the scheduler user interface may provide simple views for managed nodes, computing resources, applications, queues, and the like. Wherein, the administrator can adjust resource allocation, the mapping relationship between service requests and virtualized resources, etc. through the scheduler interaction unit.
  • the virtualized resource module 30 is obtained by virtualizing data resources and service resources in the car diagnostic cloud platform, and the virtualized resources form a unified and fine-grained resource pool.
  • the virtualized resource module 30 may include a physical server cluster and a virtual machine cluster, and both the physical server cluster and the virtual machine cluster are used to carry the data resource and the service resource. As long as the total IT resources in the resource pool are sufficient, virtualized resources can be allocated to each service application.
  • the physical server cluster and the virtual machine cluster can adopt a distributed cluster structure.
  • the IT capacity can be increased by means of horizontal expansion, so as to achieve an unlimited logical resource capacity.
  • you can also reduce the IT capacity in the resource pool to release resources for other uses and improve the utilization of unit system resources.
  • the resource management module 20 is further configured to: adjust the resource capacity of the virtualized resource module 30 according to the number of service requests; wherein, the adjusting the resource capacity includes adjusting the physical server The cluster and the node scale of the virtual machine cluster.
  • the system virtualizes the physical server cluster and virtual machine cluster in the resource center into a unified microservice fine-grained resource pool, and establishes a resource/microservice mapping, which reflects the resource pool where the microservice is located.
  • Location and the resource dynamic scheduling module is responsible for the unified resource scheduling of multiple microservice applications.
  • the specific process includes: (1) Collect resource usage information from the micro-service fine-grained resource pool; (2) Micro-service applications initiate micro-service resource requests; (3) The resource dynamic scheduling module reads fine-grained virtualized resources and micro-service applications Mapping information, acquiring the resource layout of existing microservice applications, integrating resource usage information, and assigning a virtualized resource that can be used to the microservice application that initiates the resource request according to the hash scheduling algorithm, and the resource granularity can be a container; (4) The resource scheduling module returns the mapping relationship data to the microservice application that initiated the resource request; (5) The microservice application directly communicates with the fine-grained resource pool, and according to the mapping relationship data, directly uses the corresponding physical server cluster or IT resource center Virtual machine cluster resources.
  • the embodiment of the present invention provides a virtualized resource scheduling system in an automobile diagnosis cloud platform, which can virtualize the data resources and service resources in the automobile diagnosis cloud platform into a unified service resource pool, and establish virtualized resources and services
  • the mapping relationship of the application can be responsible for the scheduling of microservice application resources in a unified manner, making the scheduling more flexible.
  • this unified scheduling mechanism can be used to configure appropriate virtualized resources for service applications.
  • the ability to combine the business characteristics of the automobile diagnostic cloud platform at the same time improves the containerization of big data services and the management efficiency of unified service operation and maintenance management.
  • FIG. 5 is a flowchart of a virtualized resource scheduling method in an automobile diagnosis cloud platform provided by an embodiment of the present invention.
  • the method may be executed by the virtualized resource scheduling system of the foregoing embodiment, and the method includes:
  • S101 The system virtualizes the data resources and service resources in the car diagnostic cloud platform through the virtualized resource module to obtain virtualized resources;
  • S102 The system receives the resource request of the automobile diagnosis cloud platform service application through the dispatch service core module, and obtains the mapping relationship between the service application and the virtualized resource according to the resource request;
  • the system obtains a virtualized resource corresponding to the service application based on the virtualized resource and the mapping relationship through the resource management module, and couples the virtualized resource with the service application.
  • the system receives the resource request of the automobile diagnosis cloud platform service application through the dispatch service core module, and obtains the mapping relationship between the service application and the virtualized resource according to the resource request, including:
  • the system obtains the resource request through the dispatcher interface and the interface server, and writes the resource request into the dispatcher processing unit;
  • the system monitors the scheduler processing unit through the program scheduling and preemption unit, and after monitoring that the scheduler processing unit receives the resource request, makes a scheduling or preemption decision;
  • the system uses the scheduler processing unit to process the resource request according to the scheduling or preemption decision, and obtains from the scheduler cache unit the information between the service application and the virtualized resource corresponding to the resource request. Mapping relations.
  • the method further includes:
  • the system manages the communication between the dispatcher interface and the resource management module and the virtualized resource module through the interface server.
  • the method further includes:
  • the system caches the data associated with the scheduler through the scheduler cache unit, and the data includes the resource status information and resource usage status information that have been deployed.
  • the method further includes:
  • the system processes the request from the administrator through the administrator service unit, and updates the scheduling or preemption decision according to the administrator's request.
  • the method further includes:
  • the system adjusts the resource capacity of the virtualized resource module according to the number of received resource requests through the resource management module, so that the virtualized resource provided by the virtualized resource module matches the service request.
  • the virtualized resource module includes a physical server cluster and a virtual machine cluster
  • the system adjusts the resource capacity of the virtualized resource module according to the number of received resource requests through the resource management module, including: the system passes The resource management module adjusts the node scales of the physical server cluster and the virtual machine cluster according to the number of received resource requests.
  • the method provided by the embodiment of the present invention has the same functions and beneficial effects as the above-mentioned system.
  • FIG. 6 is a schematic diagram of the hardware structure of a virtualized resource scheduling device provided by an embodiment of the present invention.
  • the virtualized resource scheduling device may be used to execute the above-mentioned virtualized resource scheduling method.
  • the system can be applied to the virtualized resource scheduling device.
  • the service resource scheduling device 40 includes:
  • One processor 401 is taken as an example in FIG. 6.
  • the processor 401 and the memory 402 may be connected through a bus or in other ways.
  • the connection through a bus is taken as an example.
  • the memory 402 as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules.
  • the processor 401 executes various functional applications and data processing of the service resource scheduling system by running non-volatile software programs, instructions, and modules stored in the memory 402, that is, implements the service resource scheduling method of the foregoing method embodiment.
  • the memory 402 may include a program storage area and a data storage area, where the program storage area may store an operating system and an application program required by at least one function.
  • the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the one or more modules are stored in the memory 402, and when executed by the one or more processors 401, the service resource scheduling method in any of the foregoing method embodiments is executed, for example, the above-described FIG. 5 is executed. In the method.
  • the virtualized resource scheduling equipment includes, but is not limited to, servers, server clusters and other equipment.
  • the embodiment of the present invention provides a non-volatile computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, for example, as shown in FIG. 6
  • a processor 401 of may enable the foregoing one or more processors to execute the virtualized resource scheduling method in any of the foregoing method embodiments, for example, execute the method in FIG. 5 described above.
  • the embodiment of the present invention provides a computer program product, which includes a calculation program stored on a non-volatile computer-readable storage medium.
  • the computer program includes program instructions.
  • the program instructions When the program instructions are executed by a computer, the The computer executes the virtualized resource scheduling method in any of the foregoing method embodiments, for example, executes the method in FIG. 5 described above.
  • the device embodiments described above are merely illustrative.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • each implementation manner can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware.
  • a person of ordinary skill in the art can understand that all or part of the processes in the method of the foregoing embodiments can be implemented by instructing relevant hardware through a computer program.
  • the program can be stored in a computer readable storage medium. When executed, it may include the procedures of the above-mentioned method embodiments.
  • the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Debugging And Monitoring (AREA)

Abstract

本发明涉及云计算平台中的数据资源技术领域，尤其涉及一种汽车诊断云平台中的虚拟化资源调度系统、方法以及虚拟化资源调度设备。该系统包括：调度服务核心模块、资源管理模块以及虚拟化资源模块，所述虚拟化资源模块是由所述汽车诊断云平台中的数据资源和服务资源虚拟化得到的；所述调度服务核心模块，用于接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系；所述资源管理模块，用于根据所述映射关系从所述虚拟化资源模块获取所述服务应用对应的虚拟化资源，并将所述虚拟化资源与所述服务应用耦合。该系统能够统一负责微服务应用资源的调度，使调度更灵活。

Description

汽车诊断云平台中的虚拟化资源调度系统、方法
本申请要求于2020年3月23日提交中国专利局、申请号为202010207824.1、申请名称为“汽车诊断云平台中的虚拟化资源调度系统、方法”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及云计算平台中的数据资源技术领域，尤其涉及一种汽车诊断云平台中的虚拟化资源调度系统、方法以及虚拟化资源调度设备。
背景技术
在云计算环境中，一个服务应用所需的资源通常并不是一成不变的，比如，由于服务应用程序自身逻辑，导致在一时间内存在少量数据的重复迭代，而在另一时间段内又有大量的访问外存数据或进行通信，由此导致资源需求变化。因此，在云平台架构中实现资源的按需分配具有重要意义，特别是在服务应用数量增加时，为其配置对应的资源具有重要意义。
发明内容
本发明要解决的技术问题是提供一种汽车诊断云平台中的虚拟化资源调度系统、方法及虚拟化资源调度设备，解决如何在服务应用数量增加时，为其配置对应的虚拟化资源的技术问题。
本发明实施例的第一方面，提供一种汽车诊断云平台中的虚拟化资源调度系统，所述系统包括：调度服务核心模块、资源管理模块以及虚拟化资源模块，
所述虚拟化资源模块是由所述汽车诊断云平台中的数据资源和服务资源虚拟化得到的；
所述调度服务核心模块，用于接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系；
所述资源管理模块，用于根据所述映射关系从所述虚拟化资源模块获取所述服务应用对应的虚拟化资源，并将所述虚拟化资源与所述服务应用耦合。
可选地，所述调度服务核心模块包括调度程序接口，
所述调度程序接口，用于接收所述汽车诊断云平台服务应用的资源请求，并还用于发送所述映射关系至所述资源管理模块。
可选地，所述调度服务核心模块还包括：接口服务器、调度程序处理单元、调度程序缓存单元、程序调度和抢占单元，
所述接口服务器用于通过所述调度程序接口获得所述资源请求，并将所述资源请求写入所述调度程序处理单元；
所述程序调度和抢占单元用于在监听到所述调度程序处理单元接收到所述资源请求后，做出调度或抢占决策；
所述调度程序处理单元用于根据所述调度或抢占决策处理所述资源请求，并从所述调度程序缓存单元中获得所述资源请求对应的所述服务应用与所述虚拟化资源的映射关系。
可选地，所述接口服务器还用于管理所述调度程序接口与所述资源管理模块、所述虚拟化资源模块的通讯。
可选地，所述调度程序缓存单元用于缓存与调度程序关联的数据，所述数据包括已布局的资源状态信息和资源使用状态信息。
可选地，所述调度服务核心模块还包括管理员服务单元，所述管理员服务单元用于处理来自管理员的请求，并且还用于根据所述管理员的请求更新所述调度或抢占决策。
可选地，所述资源管理模块包括调度程序处理单元和调度程序交互单元，
所述调度程序处理单元，用于向所述调度服务核心模块发送所述资源请求，并提供资源信息，还用于根据所述映射关系绑定资源和容器；
所述调度程序交互单元，用于显示资源调度分布状态和服务请求状态，还用于接收管理员的操作。
可选地，所述虚拟化资源模块包括物理服务器集群和虚拟机集群，
所述物理服务器集群和所述虚拟机集群均用于承载所述数据资源和所述服务资源。
可选地，所述资源管理模块还用于：
根据资源请求的数量调整所述虚拟化资源模块的资源容量；
其中，所述调整所述资源容量包括调整所述物理服务器集群和所述虚拟机集群的节点规模。
本发明实施例的第二方面，提供一种汽车诊断云平台中的虚拟化资源调度方法，所述方法由如上所述的系统执行，所述方法包括：
所述系统通过所述虚拟化资源模块将所述汽车诊断云平台中的数据资源和服务资源进行虚拟化，以获得虚拟化资源；
所述系统通过所述调度服务核心模块接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系；
所述系统通过所述资源管理模块，基于所述虚拟化资源和所述映射关系获取所述服务应用对应的虚拟化资源，并将所述虚拟化资源与所述服务应用耦合。
可选地，所述系统通过所述调度服务核心模块接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系，包括：
所述系统通过所述调度程序接口和所述接口服务器获取所述资源请求，并将所述资源请求写入所述调度程序处理单元；
所述系统通过所述程序调度和抢占单元监听所述调度程序处理单元，在监听到所述调度程序处理单元接收到所述资源请求后，做出调度或抢占决策；
所述系统通过所述调度程序处理单元根据所述调度或抢占决策处理所述资源请求，并从所述调度程序缓存单元中获得所述资源请求对应的所述服务应用与所述虚拟化资源的映射关系。
可选地，所述方法还包括：
所述系统通过所述接口服务器管理所述调度程序接口与所述资源管理模块、所述虚拟化资源模块的通讯。
可选地，所述方法还包括：
所述系统通过所述调度程序缓存单元缓存与调度程序关联的数据，所述数据包括已布局的资源状态信息和资源使用状态信息。
可选地，所述方法还包括：
所述系统通过所述管理员服务单元处理来自管理员的请求，并且根据所述管理员的请求更新所述调度或抢占决策。
可选地，所述方法还包括：
所述系统通过所述资源管理模块根据接收到的资源请求数量调整所述虚拟化资源模块的资源容量，以使所述虚拟化资源模块提供的资源匹配所述服务请求。
可选地，所述虚拟化资源模块包括物理服务器集群和虚拟机集群，
所述系统通过所述资源管理模块根据接收到的资源请求数量调整所述虚拟化资源模块的资源容量，包括：所述系统通过所述资源管理模块根据接收到的资源请求数量调整所述物理服务器集群和所述虚拟机集群的节点规模。
本发明实施例的第三方面，提供一种虚拟化资源调度设备，包括：
至少一个处理器；
以及与所述至少一个处理器通信连接的存储器；
其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如上所述的一种汽车诊断云平台中的虚拟化资源调度方法的步骤。
区别于现有技术，本发明实施例提供的汽车诊断云平台中的虚拟化资源调度系统、方法及虚拟化资源调度设备，能够将汽车诊断云平台中的数据资源和服务资源虚拟化为一个统一的服务资源池，并建立虚拟化资源与服务应用的映射关系，从而能够统一负责微服务应用资源的调度，使调度更灵活。当服务应用增加时，能够通过这种统一调度机制为服务应用配置合适的虚拟化资源。此外，能够同时结合汽车诊断云平台的业务特点，提升了大数据服务的容器化和统一服务运维管理的管理效率。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定，附图中具有相同参考数字标号的元件表示为类似的元件，除非有特别申明，附图中的图不构成比例限制。
图1是本发明实施例提供的一种汽车诊断云平台的系统结构示意图；
图2是本发明实施例提供的一种汽车诊断云平台中的虚拟化资源调度系统的结构示意图；
图3是本发明实施例提供的调度服务核心模块的结构示意图；
图4是本发明实施例提供的基于所述虚拟化资源调度系统进行资源调度的示意图；
图5是本发明实施例提供的一种汽车诊断云平台中的虚拟化资源调度方法的流程图；
图6是本发明实施例提供的一种虚拟化资源调度设备的硬件结构示意图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。
需要说明的是，如果不冲突，本发明实施例中的各个特征可以相互组合，均在本发明的保护范围之内。另外，虽然在装置示意图中进行了功能模块的划分，在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于装置示意图中的模块划分，或流程图中的顺序执行所示出或描述的步骤。
请参阅图1，图1是本发明实施例提供的一种汽车诊断云平台的系统结构示意图，所述虚拟化资源调度系统和方法可以应用于该汽车诊断云平台。如图1所示，该汽车诊断云平台系统采用“纵向分层、横向分割”的云计算SOA架构进行设计，提供服务的定义、开发、部署和运行等功能，各层之间通过松散耦合实现逻辑复用，通过服务方式实现同层之间模块的松耦合，使得平台具备良好的扩展能力。该系统提供基于SOA的海量数据集成服务，包括统一数据模型与管理、异构数据采集与整合、以及海量数据的组织与存储、共享与发布、分析与挖掘等，使数据存储可根据在架构上具备适应未来数据量、存储量及业务变化的能力，支持对未来海量数据的存储和高效使用，支持以横向扩展的方式实现对业务发展的支撑。同时，系统架构和软件设计充分考虑用户的实际情况，满足行业人员的实际要求，系统可采用PC服务器构建，少用或者不用阵列存储，实现系统高性能与低成本。
其中，该系统核心数据库软件采用ACID(即原子性(Atomicity)、一致性(Consistency)、隔离性(Isolation)、持久性(Durability))保护机制，确保事务的完整性和数据的一致性；数据采集采用基于数据库日志备份恢复的机制采集，确保数据的完整性和数据一致性；数据的传输采用可靠稳定的开放总线技术，确保数据传输的稳定性和可靠性；各应用服务系统采用多实例节点集群部署，确保系统能持续稳定不间断地工作，应用系统中的任意构件更新、加载时，在不更新与上下构件接口的前提下，不影响业务运转和服务；系统模块都采用集群架构，消除单点故障；网络交换机采用双机，网络链路采用双线 冗余，确保网络链路冗余。
具体地，请参阅图1，该汽车诊断云平台系统包括业务总线、数据总线、基础架构层、数据处理与数据平台层、接口层以及应用层。所述基础架构层用于构建所述汽车诊断云平台系统的基础运行环境；所述数据处理与数据平台层基于所述基础架构层而构建，其提供对数据清洗、分析挖掘服务，以及提供行业数据归集、数据缓存服务、数据访问接入服务；所述接口层基于所述数据处理与数据平台层而构建，其用于为外部应用系统和上层应用提供开放接口服务；所述业务总线通过所述接口层向所述云平台系统传输业务服务；所述数据总线通过所述数据处理与数据平台层向所述汽车诊断云平台系统传输数据；所述应用层与所述接口层通讯连接，其用于实现所述汽车诊断云平台系统的前后端分离，并且还用于承载第三方应用。
其中，所述数据处理与数据平台层基于所述基础架构层而构建，所述接口层基于所述数据处理与数据平台层而构建，是指所述基础架构层、所述数据处理与数据平台层、所述接口层从下至上，依次以下一层为基础来建立上一层，只有在先建立好下一层后才能构建上一层。
所述业务总线具体可以是业务服务总线(BSB，Business Service Bus)，其可以是一根管道，用于连接各个业务服务节点，为了集成不同的业务系统和不同协议的服务。所述业务服务总线实现了消息的转化解释和路由，让不同的业务服务互联互通。
所述数据总线支持至少两个数据通信协议，以支持所述至少两个数据服务节点与所述汽车诊断云平台系统之间的通信。所述数据通信协议可以根据所述数据源的类型、数据内容等来进行设定。所述数据服务节点与所述汽车诊断云平台系统之间的通信链路可以基于一条数据通信协议来进行通信，也可以基于多条数据通信协议来进行通信。所述数据总线具体可以是数据服务总线(DSB，Data Service Bus)，其可以是另一根管道，其用于连接各个数据服务节点，还用于集成不同的数据源。所述数据服务总线实现了数据的格式化和路由，能让不同的业务服务互联互通，可以将其理解为数据的适配器网关。
上述业务总线和上述数据总线均是通过所述接口层与所述汽车诊断云平台系统建立连接关系的。
所述基础架构层用于构建所述汽车诊断云平台系统的基础运行环境，该基础运行环境包括所述汽车诊断云平台系统的软件运行环境和硬件运行环境。所述基础架构层是所述汽车诊断云平台系统实现的基本保障。
其中，所述基础架构层包括基础设施层和基础平台层，所述基础设施层用于建构硬件设备以及基于所述硬件设备建立虚拟系统；所述基础平台层用于实现所述接口层与所述基础架构层之间的通信。所述基础平台层包括容器管理平台，所述容器管理平台包括至少两个容器，所述至少两个容器用于承载汽车诊断相关业务的处理资源，所述至少两个容器是基于所述汽车诊断云平台系统所要处理的各汽车诊断相关业务所需的处理资源分配的，所述各汽车诊断相关业 务对应所述至少两个容器中的一个或多个容器。
其中，所述容器实质是进程，但其不同于宿主执行的进程，容器进程运行于属于自己的独立的命名空间，因此容器可以拥有自己的root文件系统、网络配置、进程空间以及用户ID空间。所述至少两个容器的容量可以是相同的也可以是不同的。
所述数据处理与数据平台层是基于所述基础架构层构建的，所述数据处理与数据平台层通过所述数据总线获取所述至少两个汽车诊断相关数据，并用于对所述至少两个汽车诊断相关数据进行处理及提供接入或存储服务。
其中，所述数据处理与数据平台层主要包括数据分析挖掘模块、数据清洗模块、行业数据归属模块以及数据访问接入服务模块。所述数据分析挖掘模块用于对采集的数据进行分析、挖掘，比如，每个品牌的汽车都有自己的通讯协议，当需要对汽车进行智能诊断时，所述汽车诊断云平台系统首先与汽车进行通信，通过数据总线获取汽车诊断相关数据，然后根据汽车诊断相关数据和车辆通讯协议，该汽车诊断云平台系统通过机器学习的方法(比如神经网络)进行学习计算，分析出与该汽车最匹配的通讯协议，从而为所述汽车诊断做准备。所述数据清洗模块用于对采集到的数据进行清洗，所述数据清洗包括数据净化、遗漏数据处理，噪声数据处理等，所述数据清洗的具体过程可以参考相关技术的记载。所述行业数据归属模块用于对采集相关行业数据以及对采集的行业数据进行归集对账服务。所述数据访问接入服务用于将访问数据的请求进行管理，其主要包括数据源管理(比如对存储了哪些类别的数据存放在哪个机器的哪个数据库进行管理)、数据连接池管理(比如对数据库的连接进行管理)、统一事务管理(比如对数据库集群中所需要处理的请求所进行的增删改查等操作进行管理)。
所述接口层是基于所述数据处理与数据平台层构建的，就技术层面上来讲，所述接口层用于为所述应用层提供开放接口服务，并且接收外部系统上传来的数据。就业务层面来讲，所述接口层通过接收到的数据，实现不同的业务接口供外部调用。其中，所述接口层通过所述业务总线实现与所述至少两个业务服务节点传输所述业务服务。所述业务服务包括汽车诊断、汽车配件的推荐与销售、汽车保险、汽车残值评估、汽车金融以及其他与汽车诊断相关的业务服务。
所述应用层与所述接口层通信连接，所述应用层用于实现所述汽车诊断云平台系统的前后端分离，并且还用于承载基于服务终端的第三方应用。其中，所述服务终端包括Web终端、APP终端、PDA终端等。其中，所述第三方应用包括汽车诊断、汽车配件的推荐与销售、汽车保险、汽车残值评估以及汽车金融等。
需要说明的是，图1提供的云平台系统除了应用于汽车诊断领域，还可以应用于其他领域。此外，图1所提供的云平台系统架构图还可以根据需要增加或删除模块，而不仅限于图1。
结合上述图1所提供的应用环境，下面给出了应用于该汽车诊断云平台系统的虚拟化资源调度系统和虚拟化资源调度方法的实施例。
请参阅图2，图2是本发明实施例提供的一种虚拟化资源调度系统的结构示意图。所述虚拟化资源调度系统应用于上述汽车诊断云平台。如图2所示，该系统包括：调度服务核心模块10、资源管理模块20以及虚拟化资源模块30。所述资源管理模块20分别与所述调度服务核心模块10、所述虚拟化资源模块30通信连接。
所述调度服务核心模块10是所述虚拟化资源调度系统的核心，其封装了所有的调度算法。所述调度服务核心模块10可以从资源管理模块20收集资源，并负责资源分配请求。所述调度服务核心模块10可以决定每个服务请求的最佳部署位置，并将每个请求的最佳部署位置反馈给资源管理模块20，以使服务应用可以从所述资源管理模块20获取到合适的资源。所述资源管理模块20具体可以是容器编排系统，比如Kubernetes，所述资源管理模块20可以提供应用部署、维护、扩展机制等功能，能方便地管理跨机器运行容器化的应用。所述虚拟化资源模块30即是IT资源中心，所述虚拟化资源模块30的资源进行了虚拟化处理，将资源中心的物理服务器集群和虚拟机集群虚拟化为一个统一的微服务细粒度资源池。
在本实施例中，所述虚拟化资源模块30是由所述汽车诊断云平台中的数据资源和服务资源虚拟化得到的。所述调度服务核心模块10用于接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系。所述资源管理模块20用于根据所述映射关系从所述虚拟化资源模块30获取所述服务应用对应的虚拟化资源，并将所述虚拟化资源与所述服务应用耦合。
其中，所述汽车诊断云平台中的数据资源指的是保存在IT资源中心的数据，所述服务资源是运行在IT资源中心的服务。所述IT资源中心包括物理服务器集群和虚拟机集群，所述物理服务器集群和所述虚拟机集群均用于承载所述数据资源和所述服务资源。所述IT资源中心的数据指的是与服务应用相关的数据，比如汽车诊断数据、汽车金融数据、汽车保险数据等。所述IT资源中心的服务指的是与服务应用相关的服务，比如汽车诊断服务、汽车金融服务、汽车保险服务等。
其中，所述资源请求用于请求对所述服务应用进行处理的虚拟化资源，所述虚拟化资源可以是硬件资源。
其中，一并参阅图2和图3，所述调度服务核心模块10包括调度程序接口101、接口服务器102、调度程序处理单元103、调度程序缓存单元104、程序调度和抢占单元105以及管理员服务单元106。所述调度程序接口101是所述调度服务核心模块10对外的通讯接口，所述调度服务核心模块10的所有通信都通过该调度程序接口101，比如，通过所述调度程序接口101接收所述汽车诊断云平台服务应用的资源请求，以及发送所述映射关系至所述资源管理模 块20。所述接口服务器102用于管理所述调度服务核心模块10的全部接口(包括调度程序接口101)，负责所述调度服务核心模块10与外部设备的通信，其实现了调度程序接口101支持GRPC(Google Remote Procedure Call，Google远程程序调用)协议。所述调度程序处理单元103用于处理所述接口服务器102输入的所有写操作，比如处理需要更新调度程序内部状态的事件。所述调度程序缓存单元104用于缓存与调度程序状态相关的全部数据，例如每一个队列和节点，分配的已用资源，分配的已用资源与节点之间的关系等。通过所述调度程序缓存单元104可以提高资源分配的效率。所述程序调度和抢占单元105用于处理调度程序的内部状态，调度程序和抢占者将一起工作，做出调度或抢占决策，所述调度或抢占决策将由所述调度程序处理单元103来进行处理。所述管理员服务单元106用于处理来自管理员的请求，该请求可以是更新所述调度或抢占决策。所述管理员服务单元106还可以从存储中加载配置并更新调度程序策略。
其中，所述调度程序用于管理所述资源请求，比如，当前有多个资源请求时，所述多个资源请求对应一个排序，所述调度程序用于管理该排序。
其中，所述调度和抢占决策指的是对所述调度程序内部状态做出处理的事件，比如，调度其中某一个资源请求，或者将队列中排在后面的资源请求调整到第一顺序，以便优先处理该资源请求。值得说明的是，所述调度程序可以由所述程序调度和抢占单元105来处理，也可以由管理员通过所述管理员服务单元106进行人工干预。
其中，可以通过所述接口服务器102、所述调度程序处理单元103、所述调度程序缓存单元104、所述程序调度和抢占单元105获得所述资源请求对应的所述服务应用与所述虚拟化资源的映射关系。具体地，所述接口服务器102用于通过所述调度程序接口获得所述资源请求，并将所述资源请求写入所述调度程序处理单元103；所述程序调度和抢占单元105用于在监听到所述调度程序处理单元103接收到所述资源请求后，做出调度或抢占决策；所述调度程序处理单元103用于根据所述调度或抢占决策处理所述资源请求，并从所述调度程序缓存单元104中获得所述资源请求对应的所述服务应用与所述虚拟化资源的映射关系。
其中，所述调度程序缓存单元104还可以缓存已布局的资源状态信息和资源使用状态信息。从而可以根据所述已布局的资源状态信息和资源使用状态信息建立服务应用与虚拟化资源的映射关系，并且在所述调度程序缓存单元104保存所述映射关系。
在建立所述映射关系时，所述调度服务核心模块10可以根据预设的算法(比如哈希调度算法)，从现有的资源中获取适合所述服务应用的虚拟化资源，并获取该虚拟化资源对应的容器，从而将容器的位置标识信息与所述服务应用建立映射关系。其中，当存在多个资源请求时，可以根据每个资源请求所需的虚拟化资源的大小，或者每个资源请求的优先级等为其分配虚拟化资源，并建 立虚拟化资源和服务应用的映射关系。所述映射关系数据可以用于保存现有的服务应用的虚拟化资源布局情况，从而确保新的微服务可以调度到合适的虚拟化资源。
综上，所述调度服务核心模块10的功能特性主要包括：
(1)调度功能支持批处理作业和长期运行，以及有状态服务；
(2)具有最小、最大资源配额的分层池或对列；
(3)队列，用户以及应用程序之间的资源公平竞争；
(4)能够基于公平竞争的跨队列抢占资源；
(5)能够自定义资源类型调度支持；
(6)能根据策略自动将传入的容器请求映射至队列中；
(7)对服务节点使用专用配额或ACL(Access Control Lists，访问控制列表)管理，将大的集群拆分成若干子集群。同时，还可以作为统一的调度程序，支持K8S谓词，比如pod亲和/反亲和，节点选择器支持持久化存储和配额申请等。
所述资源管理模块20包括调度程序处理单元和调度程序交互单元。所述调度程序处理单元，用于向所述调度服务核心模块10提供资源信息；还用于根据所述映射关系数据绑定虚拟化资源和容器。所述调度程序交互单元，用于显示资源调度分布状态和服务请求状态，还用于接收管理员的操作。其中，所述调度程序处理单元可以理解为调度程序填充层(Scheduler Shim Layers)，调度程序skim在主机系统(比如YARN(Yet Another Resource Negotiator)、K8S等)内运行，其用于负责通过调度程序接口转换主机系统资源和资源请求，并将系统资源和资源请求发送给所述调度服务核心模块10。在所述调度服务核心模块10确定所述映射关系数据后，所述调度程序处理单元可以负责实际的pod或者容器的绑定。所述调度程序交互单元具体可以是调度程序用户界面(Scheduler UI)，所述调度程序用户界面可以为已托管的节点、计算资源、应用程序和队列等提供简单试图。其中，管理员可以通过所述调度程序交互单元调整资源分配，服务请求和虚拟化资源的映射关系，等。
所述虚拟化资源模块30是由所述汽车诊断云平台中的数据资源和服务资源进行虚拟化后得到的，虚拟化后的资源形成一个统一的细粒度的资源池。其中，所述虚拟化资源模块30可以包括物理服务器集群和虚拟机集群，所述物理服务器集群和所述虚拟机集群均用于承载所述数据资源和所述服务资源。只要所述资源池中总的IT资源足够，就可以为每个服务应用分配到虚拟化资源。
此外，所述物理服务器集群和所述虚拟机集群可以采用分布式集群结构，当细粒度资源池资源不足时，可以通过横向扩展等方式增加IT容量，从而实现在逻辑上的资源容量无上限，当然，还可以减少资源池中的IT容量，以释放资源用于他用，并提高单位系统资源的利用率。
因此，在一些实施例中，所述资源管理模块20还用于：根据服务请求的数量调整所述虚拟化资源模块30的资源容量；其中，所述调整所述资源容量 包括调整所述物理服务器集群和所述虚拟机集群的节点规模。
下面通过举例说明基于所述虚拟化资源调度系统实现细粒度资源的动态调度和弹性拓展。例如，如图4所示，系统将资源中心的物理服务器集群和虚拟机集群虚拟化为一个统一的微服务细粒度资源池，建立资源/微服务映射，该映射体现了微服务所在资源池的位置，并由资源动态调度模块来统一负责多个微服务应用的资源的调度。具体地流程包括：(1)从微服务细粒度资源池采集资源使用信息；(2)微服务应用发起微服务资源请求；(3)资源动态调度模块读取细粒度虚拟化资源和微服务应用映射信息，获取现有的微服务应用资源布局，融合资源使用状况信息，根据哈希调度算法，为发起所述资源请求的微服务应用分配一个可以使用的虚拟化资源，资源粒度可以是容器；(4)资源调度模块将映射关系数据返回给发起资源请求的微服务应用；(5)微服务应用直接和细粒度资源池通信，根据映射关系数据，直接使用IT资源中心相应的物理服务器集群或虚拟机集群资源。
本发明实施例提供了一种汽车诊断云平台中的虚拟化资源调度系统，能够将汽车诊断云平台中的数据资源和服务资源虚拟化为一个统一的服务资源池，并建立虚拟化资源与服务应用的映射关系，从而能够统一负责微服务应用资源的调度，使调度更灵活。当服务应用增加时，能够通过这种统一调度机制为服务应用配置合适的虚拟化资源。此外，能够同时结合汽车诊断云平台的业务特点，提升了大数据服务的容器化和统一服务运维管理的管理效率。
请参阅图5，图5是本发明实施例提供的一种汽车诊断云平台中的虚拟化资源调度方法的流程图。该方法可以由上述实施例的虚拟化资源调度系统来执行，该方法包括：
S101、所述系统通过所述虚拟化资源模块将所述汽车诊断云平台中的数据资源和服务资源进行虚拟化，以获得虚拟化资源；
S102、所述系统通过所述调度服务核心模块接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系；
S103、所述系统通过所述资源管理模块，基于所述虚拟化资源和所述映射关系获取所述服务应用对应的虚拟化资源，并将所述虚拟化资源与所述服务应用耦合。
上述步骤S101至步骤S103具体可以参考上述虚拟化资源调度系统实施例，在此不再详述。
其中，所述系统通过所述调度服务核心模块接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系，包括：
所述系统通过所述调度程序接口和所述接口服务器获取所述资源请求，并将所述资源请求写入所述调度程序处理单元；
所述系统通过所述程序调度和抢占单元监听所述调度程序处理单元，在监 听到所述调度程序处理单元接收到所述资源请求后，做出调度或抢占决策；
所述系统通过所述调度程序处理单元根据所述调度或抢占决策处理所述资源请求，并从所述调度程序缓存单元中获得所述资源请求对应的所述服务应用与所述虚拟化资源的映射关系。
在一些实施例中，所述方法还包括：
所述系统通过所述接口服务器管理所述调度程序接口与所述资源管理模块、所述虚拟化资源模块的通讯。
在一些实施例中，所述方法还包括：
所述系统通过所述调度程序缓存单元缓存与调度程序关联的数据，所述数据包括已布局的资源状态信息和资源使用状态信息。
在一些实施例中，所述方法还包括：
所述系统通过所述管理员服务单元处理来自管理员的请求，并且根据所述管理员的请求更新所述调度或抢占决策。
在一些实施例中，所述方法还包括：
所述系统通过所述资源管理模块根据接收到的资源请求数量调整所述虚拟化资源模块的资源容量，以使所述虚拟化资源模块提供的虚拟化资源匹配所述服务请求。
其中，所述虚拟化资源模块包括物理服务器集群和虚拟机集群，所述系统通过所述资源管理模块根据接收到的资源请求数量调整所述虚拟化资源模块的资源容量，包括：所述系统通过所述资源管理模块根据接收到的资源请求数量调整所述物理服务器集群和所述虚拟机集群的节点规模。
本发明实施例提供的方法具有与上述系统相同的功能和有益效果。未在本实施例中详尽描述的技术细节，可参见本发明实施例所提供的系统。
请参阅图6，图6是本发明实施例提供的一种虚拟化资源调度设备的硬件结构示意图，所述虚拟化资源调度设备可以用于执行上述虚拟化资源调度方法，所述虚拟化资源调度系统可以应用于所述虚拟化资源调度设备上。如图6所示，所述服务资源调度设备40包括：
一个或多个处理器401以及存储器402，图6中以一个处理器401为例。
处理器401和存储器402可以通过总线或其他方式连接，图6中以通过总线连接为例。
存储器402作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块。处理器401通过运行存储在存储器402中的非易失性软件程序、指令以及模块，从而执行服务资源调度系统的各种功能应用以及数据处理，即实现上述方法实施例的服务资源调度方法。
存储器402可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序。此外，存储器402可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、 闪存器件、或其他非易失性固态存储器件。
所述一个或者多个模块存储在所述存储器402中，当被所述一个或者多个处理器401执行时，执行上述任意方法实施例中的服务资源调度方法，例如，执行以上描述的图5中的方法。
上述产品可执行本发明实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本发明实施例所提供的方法。
所述虚拟化资源调度设备包括但不限于服务器、服务器集群等设备。
本发明实施例提供了一种非易失性计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个处理器执行，例如图6中的一个处理器401，可使得上述一个或多个处理器可执行上述任意方法实施例中的虚拟化资源调度方法，例如，执行以上描述的图5中的方法。
本发明实施例提供了一种计算机程序产品，包括存储在非易失性计算机可读存储介质上的计算程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行上述任意方法实施例中的虚拟化资源调度方法，例如，执行以上描述的图5中的方法。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
通过以上的实施方式的描述，本领域普通技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现，当然也可以通过硬件来实现。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；在本发明的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本发明的不同方面的许多其它变化，为了简明，它们没有在细节中提供；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (17)

  1. 一种汽车诊断云平台中的虚拟化资源调度系统，其特征在于，所述系统包括：调度服务核心模块、资源管理模块以及虚拟化资源模块，所述虚拟化资源模块是由所述汽车诊断云平台中的数据资源和服务资源虚拟化得到的；
    所述调度服务核心模块，用于接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系；
    所述资源管理模块，用于根据所述映射关系从所述虚拟化资源模块获取所述服务应用对应的虚拟化资源，并将所述虚拟化资源与所述服务应用耦合。
  2. 根据权利要求1所述的系统，其特征在于，所述调度服务核心模块包括调度程序接口，
    所述调度程序接口，用于接收所述汽车诊断云平台服务应用的资源请求，并还用于发送所述映射关系至所述资源管理模块。
  3. 根据权利要求2所述的系统，其特征在于，所述调度服务核心模块还包括：接口服务器、调度程序处理单元、调度程序缓存单元、程序调度和抢占单元，
    所述接口服务器用于通过所述调度程序接口获得所述资源请求，并将所述资源请求写入所述调度程序处理单元；
    所述程序调度和抢占单元用于在监听到所述调度程序处理单元接收到所述资源请求后，做出调度或抢占决策；
    所述调度程序处理单元用于根据所述调度或抢占决策处理所述资源请求，并从所述调度程序缓存单元中获得所述资源请求对应的所述服务应用与所述虚拟化资源的映射关系。
  4. 根据权利要求3所述的系统，其特征在于，所述接口服务器还用于管理所述调度程序接口与所述资源管理模块、所述虚拟化资源模块的通讯。
  5. 根据权利要求3所述的系统，其特征在于，所述调度程序缓存单元用于缓存与调度程序关联的数据，所述数据包括已布局的资源状态信息和资源使用状态信息。
  6. 根据权利要求3所述的系统，其特征在于，所述调度服务核心模块还包括管理员服务单元，所述管理员服务单元用于处理来自管理员的请求，并且还用于根据所述管理员的请求更新所述调度或抢占决策。
  7. 根据权利要求1至6任一项所述的系统，其特征在于，所述资源管理模块包括调度程序处理单元和调度程序交互单元，
    所述调度程序处理单元，用于向所述调度服务核心模块发送所述资源请求，并提供资源信息，还用于根据所述映射关系绑定资源和容器；
    所述调度程序交互单元，用于显示资源调度分布状态和服务请求状态，还用于接收管理员的操作。
  8. 根据权利要求1至6任一项所述的系统，其特征在于，所述虚拟化资 源模块包括物理服务器集群和虚拟机集群，
    所述物理服务器集群和所述虚拟机集群均用于承载所述数据资源和所述服务资源。
  9. 根据权利要求8所述的系统，其特征在于，所述资源管理模块还用于：
    根据资源请求的数量调整所述虚拟化资源模块的资源容量；
    其中，所述调整所述资源容量包括调整所述物理服务器集群和所述虚拟机集群的节点规模。
  10. 一种汽车诊断云平台中的虚拟化资源调度方法，其特征在于，所述方法由权利要求1至9任一项所述的系统执行，所述方法包括：
    所述系统通过所述虚拟化资源模块将所述汽车诊断云平台中的数据资源和服务资源进行虚拟化，以获得虚拟化资源；
    所述系统通过所述调度服务核心模块接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系；
    所述系统通过所述资源管理模块，基于所述虚拟化资源和所述映射关系获取所述服务应用对应的虚拟化资源，并将所述虚拟化资源与所述服务应用耦合。
  11. 根据权利要求10所述的方法，其特征在于，所述系统通过所述调度服务核心模块接收所述汽车诊断云平台服务应用的资源请求，根据所述资源请求得到所述服务应用与虚拟化资源的映射关系，包括：
    所述系统通过所述调度程序接口和所述接口服务器获取所述资源请求，并将所述资源请求写入所述调度程序处理单元；
    所述系统通过所述程序调度和抢占单元监听所述调度程序处理单元，在监听到所述调度程序处理单元接收到所述资源请求后，做出调度或抢占决策；
    所述系统通过所述调度程序处理单元根据所述调度或抢占决策处理所述资源请求，并从所述调度程序缓存单元中获得所述资源请求对应的所述服务应用与所述虚拟化资源的映射关系。
  12. 根据权利要求11所述的方法，其特征在于，所述方法还包括：
    所述系统通过所述接口服务器管理所述调度程序接口与所述资源管理模块、所述虚拟化资源模块的通讯。
  13. 根据权利要求11所述的方法，其特征在于，所述方法还包括：
    所述系统通过所述调度程序缓存单元缓存与调度程序关联的数据，所述数据包括已布局的资源状态信息和资源使用状态信息。
  14. 根据权利要求11所述的方法，其特征在于，所述方法还包括：
    所述系统通过所述管理员服务单元处理来自管理员的请求，并且根据所述管理员的请求更新所述调度或抢占决策。
  15. 根据权利要求10至14任一项所述的方法，其特征在于，所述方法还包括：
    所述系统通过所述资源管理模块根据接收到的资源请求数量调整所述虚拟化资源模块的资源容量，以使所述虚拟化资源模块提供的虚拟化资源匹配所述服务请求。
  16. 根据权利要求15所述的方法，其特征在于，所述虚拟化资源模块包括物理服务器集群和虚拟机集群，
    所述系统通过所述资源管理模块根据接收到的资源请求数量调整所述虚拟化资源模块的资源容量，包括：所述系统通过所述资源管理模块根据接收到的资源请求数量调整所述物理服务器集群和所述虚拟机集群的节点规模。
  17. 一种虚拟化资源调度设备，其特征在于，包括：
    至少一个处理器；
    以及与所述至少一个处理器通信连接的存储器；
    其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求10至16中任一项所述的方法。
PCT/CN2021/081129 2020-03-23 2021-03-16 汽车诊断云平台中的虚拟化资源调度系统、方法 WO2021190360A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010207824.1A CN111427678A (zh) 2020-03-23 2020-03-23 汽车诊断云平台中的虚拟化资源调度系统、方法
CN202010207824.1 2020-03-23

Publications (1)

Publication Number Publication Date
WO2021190360A1 true WO2021190360A1 (zh) 2021-09-30

Family

ID=71549027

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/081129 WO2021190360A1 (zh) 2020-03-23 2021-03-16 汽车诊断云平台中的虚拟化资源调度系统、方法

Country Status (2)

Country Link
CN (1) CN111427678A (zh)
WO (1) WO2021190360A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114363142A (zh) * 2022-01-12 2022-04-15 浙江大学 一种基于微服务架构的服务管控系统
CN115309124A (zh) * 2022-09-13 2022-11-08 广州港股份有限公司 一种散货码头关于皮带秤统筹协助的控制方法及系统
CN117240838A (zh) * 2023-11-14 2023-12-15 富钛字节车载软件(长春)有限公司 一种基于云原生can调试系统

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111427678A (zh) * 2020-03-23 2020-07-17 深圳市道通科技股份有限公司 汽车诊断云平台中的虚拟化资源调度系统、方法
CN114528032A (zh) * 2020-10-30 2022-05-24 华为云计算技术有限公司 一种服务器系统以及数据处理的方法
CN113406946B (zh) * 2021-05-28 2022-08-02 深圳市道通科技股份有限公司 汽车诊断方法及装置、汽车诊断设备
CN113961356B (zh) * 2021-10-29 2024-10-01 重庆长安汽车股份有限公司 一种车辆单通道和多通道并行诊断方法及系统
CN114415619B (zh) * 2021-11-29 2024-06-11 浙江吉利控股集团有限公司 一种车辆诊断方法及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104601664A (zh) * 2014-12-22 2015-05-06 西安电子科技大学 一种云计算平台资源管理与虚拟机调度的控制系统
US20170060642A1 (en) * 2015-08-28 2017-03-02 Vmware, Inc. Constrained placement in hierarchical randomized schedulers
CN107404523A (zh) * 2017-07-21 2017-11-28 中国石油大学(华东) 云平台自适应资源调度系统和方法
CN107547595A (zh) * 2016-06-27 2018-01-05 腾讯科技（深圳）有限公司 云资源调度系统、方法及装置
CN109951545A (zh) * 2019-03-14 2019-06-28 广州云晫信息科技有限公司 自适应的容器和云桌面的融合系统及其获取云资源的方法
CN111427678A (zh) * 2020-03-23 2020-07-17 深圳市道通科技股份有限公司 汽车诊断云平台中的虚拟化资源调度系统、方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104601664A (zh) * 2014-12-22 2015-05-06 西安电子科技大学 一种云计算平台资源管理与虚拟机调度的控制系统
US20170060642A1 (en) * 2015-08-28 2017-03-02 Vmware, Inc. Constrained placement in hierarchical randomized schedulers
CN107547595A (zh) * 2016-06-27 2018-01-05 腾讯科技（深圳）有限公司 云资源调度系统、方法及装置
CN107404523A (zh) * 2017-07-21 2017-11-28 中国石油大学(华东) 云平台自适应资源调度系统和方法
CN109951545A (zh) * 2019-03-14 2019-06-28 广州云晫信息科技有限公司 自适应的容器和云桌面的融合系统及其获取云资源的方法
CN111427678A (zh) * 2020-03-23 2020-07-17 深圳市道通科技股份有限公司 汽车诊断云平台中的虚拟化资源调度系统、方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114363142A (zh) * 2022-01-12 2022-04-15 浙江大学 一种基于微服务架构的服务管控系统
CN115309124A (zh) * 2022-09-13 2022-11-08 广州港股份有限公司 一种散货码头关于皮带秤统筹协助的控制方法及系统
CN117240838A (zh) * 2023-11-14 2023-12-15 富钛字节车载软件(长春)有限公司 一种基于云原生can调试系统
CN117240838B (zh) * 2023-11-14 2024-01-26 富钛字节车载软件(长春)有限公司 一种基于云原生can调试系统

Also Published As

Publication number Publication date
CN111427678A (zh) 2020-07-17

Similar Documents

Publication Publication Date Title
WO2021190360A1 (zh) 汽车诊断云平台中的虚拟化资源调度系统、方法
CN109565515B (zh) 分布式资源管理系统中的动态租户结构调整的系统、设备和过程
US11947697B2 (en) Method and system to place resources in a known state to be used in a composed information handling system
US11928506B2 (en) Managing composition service entities with complex networks
KR102013005B1 (ko) 확장 가능한 환경에서의 파티션 관리 기법
CN102103518B (zh) 一种在虚拟化环境中管理资源的系统及其实现方法
JP6185486B2 (ja) 分散型計算環境において負荷均衡化を実行する方法
US9053167B1 (en) Storage device selection for database partition replicas
CN109803018A (zh) 一种基于Mesos和YARN结合的DCOS云管理平台
WO2021031983A1 (zh) 一种汽车诊断云平台系统、业务实现方法
CN110247954A (zh) 一种分布式任务的调度方法及系统
US20230020330A1 (en) Systems and methods for scalable database hosting data of multiple database tenants
CN109542611A (zh) 数据库即服务系统、数据库调度方法、设备及存储介质
CN108701132B (zh) 资源管理系统和方法
US20190324821A1 (en) Method, device and computer program product for managing dedicated processing resources
CN104573428B (zh) 一种提高服务器集群资源有效性的方法及系统
CN109873714A (zh) 云计算节点配置更新方法及终端设备
CN106790403B (zh) 实现移动云计算中间平台的方法及实现分布式的方法
CN114448983A (zh) 基于ZooKeeper的分布式数据交换方法
CN103500126B (zh) 一种云计算平台的自动化容错配置方法
JP2024501005A (ja) コンテナクラスタのための管理方法および装置
US20220383219A1 (en) Access processing method, device, storage medium and program product
US20220237036A1 (en) System and method for operation analysis
US11809911B2 (en) Resuming workload execution in composed information handling system
US11704159B2 (en) System and method for unified infrastructure architecture

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21775425

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21775425

Country of ref document: EP

Kind code of ref document: A1