CN115834329B

CN115834329B - resource management system

Info

Publication number: CN115834329B
Application number: CN202211373532.0A
Authority: CN
Inventors: 张晗; 王继龙; 沈俊贤
Original assignee: Tsinghua University
Current assignee: Tsinghua University
Priority date: 2022-11-04
Filing date: 2022-11-04
Publication date: 2023-08-25
Anticipated expiration: 2042-11-04
Also published as: CN115834329A

Abstract

The present application relates to a resource management system. The resource management system comprises an orchestrator, a first controller and a second controller; the first controller is deployed in a backbone network in a future network test facility platform, so that the orchestrator performs resource data interaction with the backbone network through the first controller; the second controller is deployed in each test site in the future network test facility platform, so that the scheduler performs resource data interaction with the test site through the second controller; the scheduler is used for performing resource data interaction with the backbone network or the test site according to the resource requirement of the user, and scheduling and managing the resource data in the backbone network or the test site. By adopting the resource management system, the resource data in the future network test facility platform can be managed, unified coordination and management scheduling are realized from top to bottom, and the stable and reliable operation of the future network test facility platform is ensured.

Description

Resource management system

Technical Field

The application relates to the technical field of Internet information, in particular to a resource management system.

Background

The future network test facility platform is an open, easy-to-use and sustainable development large-scale universal test facility, and can provide a simple, efficient and low-cost test verification environment for researching future network innovation architecture. Future network test facility platforms include a plurality of test sites and a backbone network for linking the sites.

Currently, various types of resource management systems typically only cover the resources of a single test site, lacking effective visual management and control across multiple test sites. And the various existing technical routes are typically combinations of independent systems.

For future network test facility platforms, which cover tens of test sites altogether, network administrators need a system that orchestrates different functions from design considerations and provides unified coordination and management of the whole network. Therefore, a solution is needed to the problem of providing a resource arrangement and management system which is easy to manage, safe, reliable, flexible and controllable for future network test facility platforms.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a resource management system capable of managing resource data in a future network test facility platform.

In a first aspect, the present application provides a resource management system. The resource management system comprises an orchestrator, a first controller and a second controller;

the first controller is deployed in a backbone network in a future network test facility platform, so that the orchestrator performs resource data interaction with the backbone network through the first controller;

The second controller is deployed in each test site in the future network test facility platform, so that the scheduler performs resource data interaction with the test site through the second controller;

the scheduler is used for performing resource data interaction with the backbone network or the test site according to the resource requirement of the user, and scheduling and managing the resource data in the backbone network or the test site.

In one embodiment, the orchestrator comprises a service abstraction layer, a network element abstraction layer, and a network device layer;

the service abstraction layer is used for providing network connection service and network configuration service for the user according to the user requirement; the network element abstract layer is used for carrying out configuration management on the network element in the backbone network or the test site, and the configuration management at least comprises network element life cycle management and network element basic configuration management; the network element is not a physical network element or a virtualized network element; the network equipment layer is used for carrying out resource data interaction with each network equipment in the future network test facility platform.

In one embodiment, the first controller is a backbone slice controller;

the first controller is further used for connecting with each network device in the backbone network based on a corresponding communication protocol and acquiring resource data in each network device in the backbone network; the first controller is further used for acquiring and displaying the topological relation of each network device in the backbone network; the first controller is further configured to send a first configuration instruction to each network device in the backbone network, so that the network device that receives the first configuration instruction updates configuration information based on the first configuration instruction.

In one embodiment, the first controller is further configured to monitor an operation state of each network device in the backbone network, and alarm when the network device in the backbone network fails, where the operation state includes at least a network state, a connectivity state, an underway network state, and an alarm state.

In one embodiment, the second controller is a test site controller; the second controller is further configured to manage cloud host configuration parameters in the test site according to the second configuration request after receiving the second configuration request of the test site; the second controller is further configured to manage cloud host configuration parameters of the user according to a third configuration request sent by the user after receiving the third configuration request; the second controller is further used for sending a cloud hard disk configuration instruction to the test site so that the test site changes cloud hard disk configuration information according to the cloud hard disk configuration instruction; the second controller is also used for carrying out network monitoring and management on each network device in the test site; the second controller is further configured to send a fourth configuration request to each network device in the test site, so that the network device that receives the fourth configuration request updates firewall configuration parameters according to the fourth configuration request; the second controller is further configured to send a fifth configuration request to each network device in the test site, so that the network device that receives the fifth configuration request updates DCI configuration parameters according to the fifth configuration request.

In one embodiment, the second controller is further configured to provide a network configuration interface for the user based on a different network configuration environment, so that the user changes a corresponding network configuration parameter based on the network configuration interface; the second controller is further configured to provide network services to the user based on the SDN controller; the second controller is also used for sending an operation and maintenance instruction to each network device in the test site so that the network device receiving the operation and maintenance instruction changes operation and maintenance configuration according to the operation and maintenance instruction; the second controller is also configured to isolate and protect resource data in the network device in the test site based on a preset security rule.

In one embodiment, the orchestrator comprises a web services design module and a web services operation and maintenance module; the process of the orchestrator for orchestrating resources according to the resource requirements of the users comprises: the network service design module carries out data modeling according to the resource requirement of the user to obtain a requirement model, and sends the requirement model to the network service operation and maintenance module; and the network service operation and maintenance module correspondingly distributes network resources to each network device in the future network test facility platform after verifying the demand model.

In one embodiment, the process of the web service design module obtaining the demand model includes: designing a resource allocation path corresponding to the backbone network according to the resource requirement of the user by utilizing a path design module; designing a resource allocation path corresponding to the test site according to the resource requirement of the user by utilizing a service detection design module; and carrying out data modeling according to the results of the path design module and the service detection design module to obtain the demand model.

In one embodiment, the process of allocating network resources correspondingly by the network service operation and maintenance module includes: after verifying the demand model by using a verification module, deploying the network resource by using a deployment module according to the demand model to obtain a deployment result; and correspondingly distributing the network resources to each network device by utilizing a distribution module according to the deployment result.

In one embodiment, the network service operation and maintenance module is further configured to monitor network resources of each network device by using the status monitoring module, and update the deployment result according to the monitoring result.

In a second aspect, the present application also provides a computer device comprising a memory storing a computer program and a processor implementing the steps performed by the resource management system of any of the first aspects when the computer program is executed by the processor.

In a third aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps performed by the resource management system of any of the first aspects above.

The resource management system comprises an orchestrator, a first controller and a second controller; specifically, the first controller is deployed in a backbone network in a future network test facility platform, so that the orchestrator performs resource data interaction with the backbone network through the first controller; the second controller is deployed in each test site in the future network test facility platform, so that the scheduler performs resource data interaction with the test site through the second controller; the scheduler is used for performing resource data interaction with the backbone network or the test site according to the resource requirements of users, and scheduling and managing the resource data in the backbone network or the test site. Therefore, a distributed cloud platform is provided for a future network test facility platform, so that flexible management and arrangement of resource data of a backbone network in the future network test facility platform or each network device in a test site are realized safely and reliably; based on the orchestrator, the first controller and the second controller, unified coordination and management of resource data of the whole network are realized from top to bottom, and stable and reliable operation of infrastructure and upper layer tests of a future network test facility platform is ensured.

Drawings

FIG. 1 is a schematic diagram of a resource management system in one embodiment;

FIG. 2 is a schematic diagram of an orchestrator hierarchy in one embodiment;

FIG. 3 is a diagram of resource management system data interactions, in one embodiment;

FIG. 4 is a flow diagram of resource orchestration in one embodiment;

FIG. 5 is a flow diagram of a process for obtaining a demand model in one embodiment;

FIG. 6 is a flow diagram of allocating network resources in one embodiment;

FIG. 7 is a flow chart illustrating a process for allocating network resources based on network service requirements in one embodiment;

FIG. 8 is a schematic diagram of a deployment architecture of a test site in one embodiment;

FIG. 9 is a diagram of a disaster recovery architecture for a test site in one embodiment;

FIG. 10 is a schematic diagram of the overall architecture connection of a future network test facility platform in one embodiment;

FIG. 11 is an internal block diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The existing internet architecture has significant technical challenges in terms of expansibility, security, instantaneity, mobility, manageability, and the like. Future network test facility projects aim at providing a test verification platform for basic theory and core networking mechanism research of a novel network architecture, and providing a test verification platform for basic theory and key technology innovation research of a corresponding 7-class network architecture which can be formed by changing one, two or three of three major core elements by changing core elements such as data transmission formats, node forwarding modes, routing control strategies and the like of a network layer and evolving or generating the novel network architecture.

The future network test facility aims to break through the technical difficulty existing in verifying the novel network architecture, keep the basic advantages of the existing Internet, realize stable transition, overcome the core equipment, system and business core technology and support the research of network science and network space technology in China. Future network test facilities support core technical researches on core chips and key equipment, routing control technology, network virtualization technology, safe and reliable mechanism, large-scale networking test, innovative service system and the like. Has great effect on exploring the technical route and development road of future network development.

Based on this background, the applicant has found that in conventional networks, data centers are interconnected by physical networks deployed by operators through long-term research and collection, demonstration and verification of experimental data, and users use computing resources, storage resources located at the data centers, and network resources located at the underlying network in a fixed form. However, conventional networks have a series of problems in terms of flexibility and manageability. First, the underlying physical network carries network functions such as network security, network management, network measurement, network optimization, etc. with proprietary hardware, and maintenance, learning, and updating of proprietary hardware devices place a significant burden on network management. Secondly, the traditional network can only realize relatively simple intensification of computing and storage resources, the intensification is usually based on a single hardware server, when the workload fluctuates greatly, users and data center administrators cannot dynamically deploy and expand and contract at any time, and peak load processing can be realized only by pre-deploying redundant equipment. Finally, in conventional networks, the resource monitoring functionality is often separate from the physical devices, making it difficult for administrators to monitor the resources in real-time and globally. Cloud computing provides users with their required computing and storage resources through resource pooling and resource abstraction based on traditional data centers. Cloud computing achieves fine granularity on management and coarse granularity on abstraction, supports most management, deployment and configuration work to a platform to achieve automatic operation and maintenance, and provides a unified resource interface for users without losing specificity. However, cloud computing only provides a viable solution to computing and storage resources within a data center, but does not address many of the problems with the underlying network.

The inter-cloud interconnection and the telecommunication cloud are two scenes of cloud network fusion, and represent two technical routes with the cloud as a core, the network as an auxiliary and the network as a core and the cloud as an auxiliary respectively. The inter-cloud interconnection refers to interconnection and intercommunication among multiple clouds (or multiple data centers), which mainly takes strong network capacity as support, and maintains the relevant characteristics of cloud computing. The current method for realizing the interconnection between clouds is mainly a physical splicing means, and supports the network intercommunication between different data center resource pools by using VPN (Virtual Private Network ) slices or SD-WAN (Software Defined Wide Area Network, software defined wide area network) on the bottom network. The physical splicing mode can better process heterogeneous DCN/WAN (Data Center Network/Wide Area Network ) manufacturers, but the splicing mode breaks the flexibility of cloud computing and cannot process the fluctuation of network load. The telecom cloud extends the logical boundaries of the data center, and applies the concept of virtualization to the underlying physics. But doing so also presents new problems such as cost issues, reliability of the network resource pool, accessibility for monitoring and management, etc.

In various resource arrangement and management systems nowadays, the concept of cloud network depth fusion is not really realized. First, in processing computing, storage resources within a data center and network resources of an underlying physical network, the dominant technical route is typically a means of physical stitching. This approach effectively creates a barrier for the unified orchestration and management of resources. Second, current various resource management systems typically cover the resources of a single data center, lacking detailed and effective visual management and control across multiple data centers. Finally, the various technical routes available are generally combinations of independent systems. For future network test facilities, an administrator needs a system that orchestrates the different functions from a design perspective and provides unified coordination and management of the whole network. In the future, the network test facilities cover tens of test sites, so that a resource arrangement and management system with high performance, easy management, safety, reliability, flexibility and controllability is urgently needed.

In view of this, the embodiment of the application provides a resource management system for a future network test facility platform. The method provides a deep cloud network integration concept aiming at multiple scenes of cloud, network and edge, and replaces physical splicing of a traditional technical route by network follow-up cloud through the combination of SDN (Software Defined Network ) gateways and WAN access router (Wide Area Network access router ) in a resource pool in the sense of physical equipment. Meanwhile, according to the use requirements of users, automatic and templated resource management is realized, and the test and management requirements of a cross-data center are met; in addition, the application also realizes unified coordination and management of the whole network from top to bottom by integrating the functions of the main network slice controller and the test station, and simultaneously reserves the flexibility and expansibility of cloud computing, the robustness and the stability of the traditional data center and the monitorability of the end-to-end physical network.

In one embodiment, as shown in FIG. 1, a resource management system is provided that includes an orchestrator 101, a first controller 102, and a second controller 103. The orchestrator 101, the first controller 102, and the second controller terminal 102 may be, but not limited to, various switches, routers, personal computers, notebook computers, terminals, or servers, and the servers may be implemented as a stand-alone server or a server cluster composed of a plurality of servers. Two second controllers are disposed at two test sites in fig. 1, but the number of the second controllers is not limited.

Specifically, the first controller is deployed in a backbone network in a future network test facility platform, so that the orchestrator performs resource data interaction with the backbone network through the first controller; the second controller is deployed in each test site in the future network test facility platform, so that the scheduler performs resource data interaction with the test sites through the second controller; the scheduler is used for performing resource data interaction with the backbone network or the test site according to the resource requirement of the user, and scheduling and managing the resource data in the backbone network or the test site.

The future network test facility platform not only ensures stable, safe and reliable operation of test facilities, but also has the capability of providing convenient and flexible test resource scheduling and management for various test user requirements. Therefore, the embodiment of the application provides a resource management system, which constructs a relatively perfect operation management and test service system for a future network test facility platform and realizes the management and arrangement functions of resource data. The resource scheduling management system is called by the test service system, and is oriented to cross-node test users, and dynamic network resources of the test facilities, namely L3 (network layer) and dynamic L2 (data link layer) are uniformly scheduled and managed. The system is matched with a node resource scheduling management system distributed on the test facility, and is used for managing static network resources (static L2 (data link layer), L1 (physical layer/optical channel) and L0 (bare optical fiber)) and programmable resources (including computing resources and storage resources) at each test site in a coordinated mode.

Aiming at the cloud network convergence scene, the resource management system is positioned on the control plane of a future network test facility platform, adopts the thought of cloud network depth convergence, and innovatively combines SDN gateway (Software Defined Network gateway ) and WAN access router in a resource pool with physical equipment. The resource management system exposes management interfaces of L2VPN, L3VPN, NFV (Network Function Virtualization ), security, BOD (Bandwidth on Demand, on-demand bandwidth allocation), service X and the like to a network administrator through a network Service platform NSP-O (Network Service Platform-organization), and uniformly manages and schedules edge application, access network and core network through a southbound interface through a network Service abstraction layer NSP-C (Network Service Platform-Control). Resource data is arranged and managed on the FITI backbone network and the test sites while resource data feedback from the FITI (Future Internet Technology Infrastructure, future network test facilities) backbone network and the test sites is received.

The resource data interacted between the backbone network and the test site and the orchestrator includes, for example, various manageable resource data such as network resources, computing resources, storage resources, or network device information, which is not fully exemplified herein.

The resource management system has the following five advantages: 1. and (5) automatization. The future network infrastructure nanotubes cloud, network and edge multiple scenes, and the system realizes automation and mastering aiming at the characteristics of large-scale and complex scenes. 2. Flexibility. Network connection and network service need to realize linkage mechanism, and the system has the capability of flexible definition and combination according to requirements. 3. And (5) expansibility. The system can be laterally expanded from a network service configuration level. 4. Robustness. The system realizes real-time monitoring of the whole network resources and the network element states, can dynamically adjust the equipment configuration according to the network element states, and ensures the service stability. 5. And (5) visualizing. The system provides service end-to-end link status, configuration viewing capabilities, and network quality and failure analysis capabilities.

The resource management system is located above a backbone network and an edge cloud site (test site), and is connected with the backbone network through a first controller and is connected with the test site through a second controller. The resource management system provides corresponding services for an upper network manager and users, specifically, receives the resource demands of the users through the orchestrator, and performs resource data interaction with the backbone network or the test site based on the resource demands, so as to allocate corresponding resources, such as network resources or storage resources, for the users. And meanwhile, the resource data in the backbone network or the test site is arranged and managed by the arrangement device. Furthermore, the controllers deployed on the FITIS backbone network and the edge cloud sites are used for corresponding resource arrangement and coordination, and the design mode fully embodies the idea of cloud network fusion.

It should be noted that, the orchestrator, the first controller, and the second controller in the resource management system may be implemented through software algorithms, where the algorithm corresponding to the first controller may be deployed in the backbone network to implement a corresponding function, and the algorithm corresponding to the second controller may be deployed in the test site to implement a corresponding function. The orchestrator may be deployed in a network device independent of the backbone and the trial site, or the orchestrator may be deployed directly in either device of the backbone or the trial site.

In one embodiment, the orchestrator comprises a service abstraction layer, a network element abstraction layer, and a network device layer; the service abstraction layer is used for providing network connection service and network configuration service for the user according to the user requirement; the network element abstract layer is used for carrying out configuration management on network elements in a backbone network or a test site, and the configuration management at least comprises network element life cycle management and network element basic configuration management; the network element is not a physical network element or a virtualized network element; the network equipment layer is used for carrying out resource data interaction with each network equipment in the future network test facility platform.

Wherein, divide from the logic level, the orchestrator mainly includes the following three levels: a service abstraction layer, a network element abstraction layer, and a network device layer. Referring to fig. 2, a schematic diagram of an orchestrator hierarchy according to an embodiment of the present application is shown.

The service abstraction layer (NSD, network Service Descriptor) is located at the uppermost layer and is intended to provide network connection services and configuration services for network functions, in other words, it is used to provide network connection services and network configuration services for users according to their needs.

Configuration services provided by the orchestrator can be specifically classified into intra-cloud/inter-cloud connection services, wide area network connection services, entity device services, mirror resource services, and cloud resource services. Wherein the intra-cloud/inter-cloud connection services include VLAN (Virtual Local Area Network ) and VxLAN (Virtual Extensible Local Area Network, virtual extended local area network) services; wide area network connection services include MPLS (Multi-Protocol Label Switching, multiprotocol label switching), SRv6 (Segment Routing IPv6, segment routing based on IPv6 forwarding plane), ipsec vpn (Internet Protocol Security Virtual Private Network, virtual private network based on internet security protocol) services; the entity equipment service is responsible for providing entity security equipment and entity industrial equipment; the mirror resource service is responsible for providing mirrors and templates; the cloud resource service provides services such as topology management, quota management, cloud hosts and the like.

The network element abstract layer (NFD, network Function Descriptor) is located in the middle layer, provides a network service instance management function, and can perform configuration management on network elements in a backbone network or a test site. For example, network element lifecycle management and basic configuration management may be performed on physical network elements or virtualized network elements, such as firewall instances, LB instances, IPS instances, router instances, and VPN instances.

The network device layer (NDD, network Device Descriptor) is located at the bottom layer, and performs resource data interaction with each network device of the backbone network or the test site in the future network test facility platform, where the nanotubes include network devices of multiple dimensions of cloud, network, edge, and end or Edge servers that generate VNF (Virtual Network Function ) network elements, that is, can manage and interact resource data of CPE (Customer Premise Equipment, customer premises equipment), edge cloud network, access network, backbone network, and the like of the future network test facility platform.

In the embodiment of the application, an innovative organization concept of a service abstraction layer, a network element abstraction layer and a network equipment layer is provided, and support can be provided for flexible adjustment of a resource management system architecture, flexible expansion and contraction of resources, visual high efficiency of operation and maintenance and global control of a network based on the concept.

In one embodiment, please refer to fig. 3, which illustrates a data interaction diagram of a resource management system according to an embodiment of the present application. The architecture of the future network test facility platform and the data interaction connection relationship with the resource management system are shown in fig. 3.

For a future network test facility platform, data traffic enters a FITIbackbone network from PE (provider edge) between test sites, and an end-to-end L2/L3 network private line is formed through an L2/L3 private line and a SRv protocol which are erected in the FITIbackbone network. In the test site, the server, the virtualization platform, the Spine/Border router and the PE are connected with each other through VLAN and VxLAN to form a network in the test site.

The resource management system obtains resource data of the backbone network and the test site from the physical layer by simultaneously controlling the first controller, the second controller, the router, the backbone network and the infrastructure equipment in the test site, and performs unified arrangement and management.

The following describes the overall resource data arrangement flow.

In one embodiment, as shown in fig. 4, a schematic flow chart of resource scheduling is shown. The orchestrator comprises a network service design module and a network service operation and maintenance module; the process of the orchestrator for resource orchestration according to the resource requirements of the users comprises:

In step 401, the network service design module performs data modeling according to the resource requirement of the user to obtain a requirement model, and sends the requirement model to the network service operation and maintenance module.

The resource requirement of the user is, for example, a service requirement of the user on network resources or storage resources.

The network service design module can mainly conduct demand modeling based on the resource demands of users, so that the network service operation and maintenance module can meet the network demands of the users based on the established demand model.

Fig. 5 is a schematic flow chart of obtaining a demand model according to an embodiment of the application. The process of obtaining the demand model by the network service design module comprises the following steps:

step 501, a path design module is utilized to perform resource allocation path design corresponding to the backbone network according to the resource requirement of the user.

Step 502, a service detection design module is utilized to design a resource allocation path corresponding to the test site according to the resource requirement of the user.

And step 503, performing data modeling according to the results of the path design module and the service detection design module to obtain a demand model.

The whole resource data arranging process is divided into two parts of network service design and network service operation and maintenance. When the user puts forward the network service demand, the network service design module carries out the switch and path design through the path design module so as to determine the resource allocation path design corresponding to the backbone network. Meanwhile, the service detection design module is also utilized to carry out service monitoring design so as to determine the resource allocation path design corresponding to the test site. Further, the result of the composer path design module and the service detection design module is subjected to data modeling to obtain a demand model. Among them, the demand modeling can be performed based on the network of YANG (Yet Another Next Generation, "another next generation" modeling language), and a web service modeling model based on YANG, that is, the demand model, is obtained.

And step 402, after verifying the demand model, the network service operation and maintenance module correspondingly distributes network resources to each network device in the future network test facility platform.

Fig. 6 is a schematic flow chart of allocating network resources according to an embodiment of the present application. The process of correspondingly allocating network resources by the network service operation and maintenance module comprises the following steps:

and step 601, after the verification module is used for verifying the demand model, the deployment module is used for deploying the network resources according to the demand model, and a deployment result is obtained.

Step 602, using an allocation module to allocate network resources to each network device according to the deployment result.

The network service deployment module deploys network resources according to the demand model to obtain deployment results. And according to the deployment result, the distribution module distributes network resources based on the SDN controller. In addition, the network service operation and maintenance module also performs automatic dynamic scheduling control on the network service.

In one embodiment, the network service operation and maintenance module is further configured to monitor network resources of each network device by using the state monitoring module, and update the deployment result according to the monitoring result.

The state monitoring module is mainly used for monitoring physical network resources and states, monitoring network service states and analyzing the network resources and the states of the network devices. Each network device refers to a router, a switch, a firewall, or the like. Based on feedback transmitted by the state monitoring module, the network service operation and maintenance module performs automatic dynamic scheduling control based on the deployment module, and feeds back a result to the SDN controller, namely the distribution module, and updates a resource distribution result.

In addition, in the embodiment of the application, the orchestrator monitors the Overlay and underway layers simultaneously on the network resources and the service states of the top layer. The monitoring at the Overlay level depends on the monitoring of network states by Openstack (cloud computing management platform project) and SRv6, while the Underlay level depends on the direct feedback of resource use conditions by Openstack, routers, switches and specific servers. In order to facilitate the understanding of the resource scheduling deployment process, the embodiment of the present application further provides a process flow diagram for allocating network resources based on network service requirements as shown in fig. 7. The network service design module performs YANG-based demand modeling, the network service operation and maintenance module performs network resource allocation based on the SDN controller, and meanwhile monitors network resource states of devices such as routers, switches or firewalls, and the network service operation and maintenance module updates deployment of resource allocation based on monitoring results.

In the embodiment of the application, the resource scheduling and management system is realized based on the distributed cloud platform, so that open and flexible test service is provided for users.

In one embodiment, the resource management system, in addition to orchestrating and managing resource data, has sophisticated system-platform level high availability functions including monitoring, quarantining, evacuating, and restoring of system resources. The monitoring function monitors the node state from three dimensions of calculation, storage and network. Aiming at the state of the computing resources, the system monitors the utilization rate of the computing resources including a CPU (central processing unit ) and a memory; aiming at the storage state, the system monitors the use condition of the total disk of the cluster and the read-write speed condition of a single disk; for network status, the system monitors the up-down speed and flow of network equipment and also monitors the accessibility of three networks of a management plane, a data plane and a storage plane. Once the abnormal situation is found, the abnormal situation is isolated, evacuated or recovered according to the specific scene, and the manager is informed to process in the form of mail alarm and WeChat alarm. In particular, the resource management system may implement functions based on the first controller or the second controller.

As described above, the resource management system includes a first controller for interfacing with a backbone network. The specific functions that can be implemented by the first controller will be described below.

In one embodiment, the first controller is a backbone slice controller; the first controller is further used for connecting with each network device in the backbone network based on a corresponding communication protocol, and acquiring resource data in each network device in the backbone network; the first controller is also used for acquiring and displaying the topological relation of each network device in the backbone network; the first controller is further configured to send a first configuration instruction to each network device in the backbone network, so that the network device that receives the first configuration instruction updates configuration information based on the first configuration instruction.

The first controller provided by the embodiment of the application is a multi-manufacturer compatible backbone network slice controller, and can realize 14 primary functions and 36 secondary functions. The functions realized by the backbone slice controller can be particularly divided into three types of a butt joint function, a management and arrangement function and a monitoring and alarming function.

The docking function includes connecting with each network device in the backbone network based on a corresponding communication protocol, and acquiring resource data in each network device in the backbone network. Each network device in the backbone network, such as a pointing device, a northbound device, a router, and the like. The communication protocol is a communication protocol corresponding to each network device.

Specifically, the docking function is mainly composed of three primary functions, namely a south device docking function, a north orchestrator docking function and a business system docking function. The southbound equipment docking function is mainly responsible for southbound docking core routers, aggregation routers and access routers, and supports southbound Interface protocols such as Netconf (Network Configuration Protocol ), SNMP (Simple Network Management Protocol, simple network management protocol), CLI (Command-Line Interface) and other protocols through industry standards, so as to realize docking pipes for different types of router equipment. The northbound orchestrator docking function supports providing an abstraction of underlying network devices and network services up in addition to northbound docking of upper-level orchestrators via a Restful API (application program interface) and responding to orchestrator API (Application Programming Interface, application program interface) call instructions. The service docking function is mainly responsible for supporting service system abstract template definition, such as template definition based on a TOSCA (Topology and Orchestration Specification for Cloud Applications, cloud application topology layout specification) model; supporting the instantiation execution according to the business system template; and supporting real-time monitoring of the state of the service system instance.

The management and arrangement functions comprise obtaining and displaying topological relations of all network devices in the backbone network; and sending the first configuration instruction to each network device in the backbone network, so that the network device receiving the first configuration instruction performs functions such as configuration information updating based on the first configuration instruction. The configuration instruction includes configuration information to be updated, such as network parameter configuration information, and the update instruction performs operations such as modification, addition or deletion.

Specifically, the management and orchestration functions consist of topology management, configuration management, L2/L3VPN orchestration, and support for both TE/BE (Traffic Engineering/Best effect, traffic engineering/Best Effort) modes. First, topology management is mainly responsible for topology connection relation collection and topology presentation. The topology connection collection requires that the network physical connection relation is displayed through BGP-LS (Border Gateway Protocol Link-State, border gateway protocol-link State extension protocol) and other protocols; the topology presentation requires the system to present the physical network topology including the network elements and the links in real time according to the acquired complete networking information. Secondly, the configuration management is mainly responsible for supporting automatic issuing, modification and deletion of configuration of the southbound physical device in real time through protocols such as Netconf. In addition, the operation and maintenance personnel can check the whole network configuration through the functional module, so that the network equipment is prevented from logging in one by one, the equipment configuration checking time is shortened, and meanwhile, the possibility of manual misoperation is avoided. Secondly, the L2/L3VPN function is responsible for supporting VPNv4/VPNv6/L2VPN template configuration, so that VPNv4/VPNv6/EVPN/VPWS over SRv6 is realized (Virtual Private Wire Service, virtual private line service). Finally, the system also supports soft slice definition, multi-path slice definition, primary-backup multi-path priority selection, etc., and implements application policy and SR best effort based slice selection by providing application policy based slice selection and adjustment, SR (Service Router) based best effort forwarding mechanisms.

Among the other types of functions implemented by the first controller are monitoring and alarm functions. The monitoring and alarming function includes monitoring the network state, connectivity state, underway network state, alarming state and other running states of each network device in the main network, and alarming when the network device in the main network fails.

Specifically, the monitoring and alarm functions include several sub-functions of network state sensing, connectivity detection, underway state monitoring, device monitoring, alarm management and operation visualization. 1. The network state sensing is responsible for automatically collecting the whole network equipment information and link information through BGP-LS, and constructing the whole network topology based on a network map. Meanwhile, the sub-function also supports network element equipment display and inter-equipment connection state information display related to an overlay channel, and can sense slice network quality and state through SRv Ping or Tracert. 2. Connectivity measurements are responsible for providing Ping (Packet Internet Groper, internet packet explorer) and Tracert diagnostic tools in a Web (Web page) graphical manner, detecting link reachability in real time, and exposing network element devices traversed in the path. 3. The underway state monitoring is responsible for monitoring router device and interface states, router device interface rates, router entries, and underway network links. The router equipment and the interface state provide relevant data for the router equipment of the platform nano tube; the router device interface rate is responsible for collecting information such as bps (bit per second), pps (packet per second packets per second) and the like of the underlying router device interface; the routing table entry monitoring acquires information such as MAC (Media Access Control ) address table, FIB (Forwarding Information Base, forwarding) table, ARP (Address Resolution Protocol ) table entry and the like of the router equipment in real time; the underway network link monitoring support obtains the network link bandwidth utilization rate, the network and service time delay and packet loss performance information in real time through SNMP, telemetry and other related protocols. 4. The device monitoring utilizes intelligent operation and maintenance device, the detailed information of the device data is collected through a telemet (network monitoring technology), the real-time information of the device can be checked by hovering on the device, and meanwhile, the statistical data of the device can be stored in a database and displayed on an operation and maintenance interface. 5. Alarm management is responsible for triggering, sending and recovering alarms. The system triggers alarm according to the real-time monitoring information of the underway state at the router equipment level and the interface level, automatically sends alarm information in a mail mode and supports automatic recovery of alarm events after abnormal recovery. 6. The operation visualization function supports the visualization functions of two aspects, namely application and underway network monitoring. In the application level, the system realizes the real-time path visualization, the flow size visualization and the network quality visualization based on the application; in the aspect of underway network monitoring, the system supports topology/equipment/link visualization based on the underlying network, and can help operation and maintenance personnel to monitor the real-time state of the network conveniently and rapidly and quickly and locate faults.

As mentioned above, the resource management system further comprises a second controller for interfacing with each of the experiment sites. The specific functions that can be achieved by the second controller will be described below.

In one embodiment, the second controller is a test site controller; the second controller is further used for managing cloud host configuration parameters in the test site according to the second configuration request after receiving the second configuration request of the test site; the second controller is further configured to manage cloud host configuration parameters of the user according to the third configuration request after receiving the third configuration request sent by the user. The second controller is also used for sending a cloud hard disk configuration instruction to the test site so that the test site changes cloud hard disk configuration information according to the cloud hard disk configuration instruction; the second controller is also used for carrying out network monitoring and management on each network device in the test site; the second controller is further configured to send a fourth configuration request to each network device in the test site, so that the network device that receives the fourth configuration request updates firewall configuration parameters according to the fourth configuration request; the second controller is further configured to send a fifth configuration request to each network device in the test site, so that the network device that receives the fifth configuration request updates the DCI configuration parameters according to the fifth configuration request.

The test sites in the future network test facility platform can be divided into three types of main nodes, one type of sites and two types of sites. Taking a master node as an example, the deployment architecture of the test site is shown in fig. 8, and the disaster recovery architecture of the test site is shown in fig. 9. Specifically, the test site builds a programmable NFVi system by using Openstack and Tungsten Fabric, so that the creation and deployment of each VNF in a single domain and multiple domains and the pull-through of a bottom layer VPC/DCI (Virtual Private Cloud, virtual private cloud; data Center Interconnect, data center interconnection) network are satisfied. A second controller in the resource management system provides support for five primary functions and 18 secondary functions, such as calculation virtualization, storage virtualization, network virtualization, operation and maintenance management and security requirements.

The second controller may manage cloud host configuration parameters related to the user or related to the test site, for example, configuration of parameters such as a cloud host network, a cloud host image, an IP address, and the like. Specifically, the calculation virtualization function of the second controller includes managing cloud host configuration parameters in the test site according to the second configuration request after receiving the second configuration request of the test site; and after receiving a third configuration request sent by the user, managing cloud host configuration parameters of the user according to the third configuration request.

Specifically, the computing virtualization mainly comprises functions of cloud host network management, mirror image management, PCI device transparent transmission and cloud host management. Cloud host network management is responsible for supporting network operations of accessing multiple networks, removing added networks, custom use of IP addresses, binding of Floating IP, etc. The mirror image management is responsible for supporting creation of a cloud host through a mirror image, supporting configuration attributes, setting the mirror image to be private, sharing, setting protection and other attributes. PCI (Peripheral Component Interconnect ) device transparent is responsible for supporting transparent transmission of physical device PCI devices into the cloud host. The cloud host management module in the computing virtualization has wide support functions and can be further divided into three dimensions of a basic function, an advanced service function and a management function. 1. The basic function is mainly responsible for providing basic services related to the cloud host for a user, and comprises the steps of starting up and shutting down the cloud host, restarting, suspending, mounting and unloading a network card, mounting and unloading a cloud hard disk and locking and unlocking; adjusting the configuration of the cloud host (CPU, memory and disk); support a specified system administrator password or a specified SSH key (Secure Shell key, key-based encrypted network transport protocol) when creating a cloud host; simultaneously mounting a plurality of cloud hard disks; and realizing operation management on the cloud host through the webpage Console Console. 2. Advanced configuration functionality on the basis of basic services, the user is mainly faced with providing highly free cloud host resource configuration services. The method comprises the steps of carrying out network security reinforcement on a cloud host and configuring a security group; the configuration type of the cloud host is customized (information such as CPU, memory, disk and the like is defined), and advanced attributes such as NUMA (Non-Uniform Memory Access, non-uniform access model), CPU thread policy, GPU and the like are supported; providing an online migration function of the cloud host, realizing migration of the cloud host among different hosts, and guaranteeing service continuity; creating a cloud host by designating an available domain and a specific physical host; the CPU is supported by the single cloud host to reach 4 paths of 32 cores, and the maximum memory reaches 1TB; rebuilding a virtual machine supporting Boot from Volume (started from a cloud disk); the snapshot can be converted to a mirror or cloud hard disk. 3. The management function module is responsible for providing a high level of differentiation and management for the administrator. Supporting division of the available domain from the host set; and whether the cloud host in the cloud host set starts affinity/anti-affinity configuration is supported, and the cloud host can be distributed to the same host or different hosts according to requirements.

In addition, the storage virtualization function of the second controller comprises sending cloud hard disk configuration instructions to the test site, so that the test site changes cloud hard disk configuration information according to the cloud hard disk configuration instructions.

Specifically, the storage virtualization function is mainly focused on management and configuration services of the cloud hard disk. The following functions are supported: creating a cloud hard disk with a custom size; expanding the capacity of the created cloud hard disk; mounting to a cloud host, and unloading from the cloud host; simultaneously using a plurality of storage back ends; configuring QoS (Quality of Service ) rules for the cloud hard disk type; snapshot and backup functions; multiple mount (multistatach); the shooting process can not influence the snapshot function of the normal operation of the cloud host; the backup operation of the cloud hard disk is realized, so that full-quantity or incremental differential backup is realized; restoring data by using the backup; the cloning function can realize complete cloning and linked cloning; hypervisor front-end QoS configuration and Ceph back-end QoS configuration.

The network virtualization function of the second controller includes network monitoring and management on each network device in the test site, and may further send a fourth configuration request or a fifth configuration request to each network device in the test site, so that the corresponding network device performs updating of firewall configuration parameters or updating of DCI configuration parameters.

Specifically, the network virtualization function provides services based on network management, load balancing, firewalls, SDNGWs, DCI management. Load balancing supports ECMP (Equal-Cost Multi-Path, equivalent routing) and LBaaS (Load Balance as a Service, load balancing is a service) for each virtual network (including software implementation, or hardware implementation of mainstream load balancing vendors F5, A10, avi, etc.); the firewall module supports an application policy set of Tag-base, supports dynamic addition/deletion of firewall policies capable of setting sharing and auditing attributes, can add/delete rules (rules support specified names, protocol types, actions, source-destination addresses, source port/port ranges, destination port/port ranges, IP version and description), and supports setting rules with sharing and enabling attributes; the SDNTGW module supports L2 (VPLS (Virtual Private LAN Service, virtual private LAN service), L2 circuits, L2VPN and EVPN), L2.5/MPLS (LDP (Label Distribution Protocol, label distribution protocol), RSVP (Resource Reservation Protocol ), P2MP (Point 2 Multi-Point-to-multipoint Master) LDP and RSVP), L3 (unicast and multicast L3 VPN), multicast technology (PIM (Protocol Independent Multicast, protocol independent multicast), IGMP (Internet Group Management Ptotocol, internet group management protocol), MLD (Multicast Listener Discover, multicast interception discovery protocol), multicast GRE (Generic Routing Encapsulation, general routing encapsulation protocol)), BNG (Broadband Network Gateway ) including LNS/L2TP (L2 TP Network Server, L2TP network server; layer Two Tunneling Protocol, second layer tunneling protocol), PPPoE (Point-to-Point Protocol over Ethernet, ethernet Point protocol), DHCP (Dynamic Host Configuration Protocol, dynamic host configuration) v4/v6, PWHT, static and dynamic user interface, protocol for supporting Pcloud, and dynamic user interface, protocol for high-quality of service, pcloud, high-class, high-speed security, high-integrated, high-speed security, high-level, RPQFN, and RPG, and RPG-level; the DCI management module supports inventory state management of the cross-domain DCI link resources and simultaneously supports automatic creation, acquisition, updating and deletion of the cross-domain DCI link resources.

In one embodiment, the second controller is further configured to provide a network configuration interface to the user based on a different network configuration environment, so that the user changes the corresponding network configuration parameters based on the network configuration interface; the second controller is further used for providing network services for users based on the SDN controller; the second controller is also used for sending operation and maintenance instructions to each network device in the test site so that the network device receiving the operation and maintenance instructions changes operation and maintenance configuration according to the operation and maintenance instructions; the second controller is also configured to isolate and protect resource data in the network device in the test site based on a preset security rule.

The network virtualization function of the second controller may provide a network configuration interface for the user based on different network configuration environments, so that the user changes corresponding network configuration parameters based on the network configuration interface. For example, network management modules in network virtualization mainly provide support for different scenarios and technologies, provide service support for fortune and manager, and provide support related to SDN controllers. First, the network management module supports various network scenarios, network technologies, and network devices, such as: IPv4/IPv6 dual stack; DPDK, SRIOV, smartNIC, etc.; centralized/distributed snap, streaming IP; a Service-Chain (VNF/PNF); various data plane encapsulation models including VxLAN and MPLS over GRE/UDP; seamless integration with bare metal networks; l3 VPN, EVPN, site-to-site IPSec is completed in a software mode; a deployment model of Remote computer is supported to adapt the scenarios of Edge clouds. Secondly, the network management module provides a subnet selection service, supports network QoS speed limit and supports virtual machine scheduling of minimum bandwidth QoS based on the network for users. The user can create private network functions isolated from each other among the items through the network management module, and can manage, modify, add subnets and ports, etc. the private network functions. For operation and management personnel, the network management module supports a distributed gateway deployment mode, supports high availability of a control platform, supports double main redundancy, and comprises expansibility support. The module also provides virtual router functionality that supports management of virtual routers through a management interface, including adding/deleting networks for routers, binding/unbinding router gateways. In addition, the network management module also provides a dynamic real-time network topological graph, and an administrator can quickly create resources (cloud hosts, routers and networks) through dragging of a topological interface.

The network virtualization function of the second controller may also provide network services to the user based on the SDN controller. For example, SDN controller related functions in network virtualization functions mainly include the following four points: the SDN controller can provide a visual interface to display the network connection condition of the Overlay network and the cloud platform, the resource occupation condition and simple site and application functions; the SDN controller supports RESTful API, can be seamlessly combined with an OSS/BSS system of an OpenStack or other service providers, and supports mixed environment deployment; the high availability support of the SDN control plane is provided, the HA double-machine redundancy deployment can be realized, and the expansion can be carried out; the SDN controller supports seamless connection with Kubernetes, openShift and VMware vCenter networks; the SDN controller supports seamless network opening from private Cloud to public Cloud (AWS (Amazon Web Services, amazon webpage service), azure, google Cloud (Gu Geyun)) and unified security policy issuing.

The operation and maintenance management module of the second controller can send operation and maintenance instructions to each network device in the test site, so that the network device receiving the operation and maintenance instructions changes operation and maintenance configuration according to the operation and maintenance instructions. Specifically, the operation and maintenance management module provides an automation tool, a compatibility module, a user authentication and authorization module, a resource metering and quota module and a system design module. 1. The automation tool is responsible for providing batch deployment and management tools, and realizing automatic and rapid deployment, installation and capacity expansion of the cloud platform. An administrator can realize the operations of configuration change, modification and the like of the cloud platform cluster through the management function. In addition, each component adopts a containerization technology, so that version upgrading and degradation can be conveniently carried out, and the operation of the whole cloud platform is not influenced. 2. The compatibility module supports KVM (Kernel-based virtual machine) virtualization software, open source OpenStack all RESTful API standards, heterogeneous hardware environments (including server devices, network devices, storage devices, etc.), and the like. 3. The user authentication and authorization module is responsible for carrying out operations such as creation/inquiry/management operation and the like on the project, and supports management on contents such as members, member rights and the like in the project. The module can also perform operations such as creating, deleting, editing, modifying passwords, modifying mailboxes and the like on the user account, provides a role management function, and defines the authority of the account by the role, wherein the default roles comprise an administrator, a domain administrator, a common user, a read-only user, a project administrator and a financial administrator. And supporting the custom roles and the corresponding rights. 4. The resource metering and quota provides a graphical interface for a user, and the user can view the storage capacity, the hardware information, the cluster CPU utilization rate, the cluster memory utilization rate, the cluster IOPS (input/outputoperations per second input/output operand per second) and the cluster IO (input/output interface) bandwidth through the interface. In addition, the system also supports a user work order and provides a resource quota function, and all items have default resource quota (VCPU, memory, hard disk size, hard disk number, network number and the like). 5. The system setting provides cloud platform global setting service for an administrator, and supports platform operation parameter default setting, including parameter default values of a cloud host, storage, a network, a memory, a key pair, a virtual kernel, a storage size, a backup size, a network bandwidth, a snapshot and the like.

The security monitoring function of the second controller is also used for isolating and protecting resource data in the network equipment in the test site based on preset security rules. Specifically, the security monitoring function may provide security management, network isolation and user data protection of the test site, which supports setting of security group functions and security group default rules; supporting setting of a firewall, and realizing policy management through rules; supporting a resource operation log; supporting RBAC (Role-Based Access Control ); support forwarding plane encryption; and supporting SSH key unified management. The security monitoring function also provides security isolation between the cloud host networks, within the networks and between the cloud host and the external network, and the cloud host cannot receive non-broadcast messages of which the destination address is not self. Meanwhile, the security monitoring function also encrypts and protects user data in the cloud operating system, and only the user can access the security monitoring function.

In the embodiment of the application, three main network slice controller functions of a docking function, a management and arrangement function and a monitoring and warning function are innovatively integrated, and five test site functions of calculation virtualization, storage virtualization, network virtualization, operation and maintenance management and safety monitoring are innovatively integrated. The test resource platform of the whole network is uniformly coordinated, managed and scheduled from top to bottom, and stable and reliable operation of the infrastructure and the upper layer test is ensured.

In one embodiment, as shown in fig. 10, a schematic diagram of the overall architecture connection of a future network test facility platform according to an embodiment of the present application is shown. The resource management system is connected and interacted with a backbone network or an edge cloud site of a future network test facility platform through a controller, wherein the edge cloud site comprises a main site, a class-one site, a class-two site and the like, and the controller can acquire resource data, such as network data, storage data and the like, of each network device of the backbone network or the edge cloud site and send the resource data to a composer of the resource management system. Edge cloud sites include PE, openstack devices, BYOE (Bring Your Own Encryption, self-contained encryption) devices, and the like. The backbone network frame is provided with an L2/L3 special line and a SRv protocol, and can form an end-to-end L2/L3 network special line with the edge cloud station.

The orchestrator may provide intra-cloud/inter-cloud connection services, wide area network connection services, entity device services, mirror resource services, cloud resource services, etc., and specific information of each service is not described herein. The orchestrator is also interacted with the user to provide corresponding services for the user, for example, the orchestrator can provide corresponding cross-region simulation video conference test, virtual-real hybrid orchestration, network data support based on media stream communication efficiency evaluation under different lines and the like in the stream communication simulation efficiency test process for the user, and the orchestrator can also provide relevant support for a scientific research experiment bed.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 11. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing data of the resource management system. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, performs the steps performed by the resource management system.

It will be appreciated by those skilled in the art that the structure shown in FIG. 11 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, the application also provides a computer device comprising a memory storing a computer program and a processor implementing the steps performed by the resource management system of any of the embodiments described above when the computer program is executed by the processor.

In one embodiment, the application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps performed by the resource management system of any of the embodiments described above.

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, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

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 foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. A resource management system, the system comprising an orchestrator, a first controller, and a second controller;

the second controller is deployed in each test site in the future network test facility platform, so that the scheduler performs resource data interaction with the test sites through the second controller;

The scheduler is used for performing resource data interaction with the backbone network or the test site according to the resource requirement of a user, and scheduling and managing the resource data in the backbone network or the test site;

the second controller is a test site controller;

the second controller is further configured to manage cloud host configuration parameters in the test site according to the second configuration request after receiving the second configuration request of the test site;

the second controller is further configured to manage cloud host configuration parameters of the user according to a third configuration request after receiving the third configuration request sent by the user;

the second controller is further configured to send a cloud hard disk configuration instruction to the test site, so that the test site changes cloud hard disk configuration information according to the cloud hard disk configuration instruction;

the second controller is further used for carrying out network monitoring and management on each network device in the test site;

the second controller is further configured to send a fourth configuration request to each network device in the test site, so that the network device that receives the fourth configuration request updates firewall configuration parameters according to the fourth configuration request;

The second controller is further configured to send a fifth configuration request to each network device in the test site, so that the network device that receives the fifth configuration request updates DCI configuration parameters according to the fifth configuration request.

2. The system of claim 1, wherein the orchestrator comprises a service abstraction layer, a network element abstraction layer, and a network device layer;

the service abstraction layer is used for providing network connection service and network configuration service for the user according to the user demand;

the network element abstract layer is used for carrying out configuration management on network elements in the backbone network or the test site, and the configuration management at least comprises network element life cycle management and network element basic configuration management; the network element is not a physical network element or a virtualized network element;

and the network equipment layer is used for carrying out resource data interaction with each network equipment in the future network test facility platform.

3. The system of claim 1, wherein the first controller is a backbone slice controller;

the first controller is further configured to connect with each network device in the backbone network based on a corresponding communication protocol, and obtain resource data in each network device in the backbone network;

The first controller is further configured to acquire and display a topology relationship of each network device in the backbone network;

the first controller is further configured to send a first configuration instruction to each network device in the backbone network, so that the network device that receives the first configuration instruction updates configuration information based on the first configuration instruction.

4. The system of claim 3, wherein the system further comprises a controller configured to control the controller,

the first controller is further configured to monitor an operation state of each network device in the backbone network, and alarm when a network device in the backbone network fails, where the operation state at least includes a network state, a connectivity state, an underway network state, and an alarm state.

5. The system of claim 1, wherein the resource data of interactions between the backbone network and the test sites and the orchestrator comprises network resources, computing resources, storage resources, or network device information.

6. The system of claim 1, wherein the system further comprises a controller configured to control the controller,

the second controller is further configured to provide a network configuration interface for the user based on different network configuration environments, so that the user changes corresponding network configuration parameters based on the network configuration interface;

The second controller is further configured to provide network services for the user based on the SDN controller;

the second controller is further configured to send an operation and maintenance instruction to each network device in the test site, so that the network device that receives the operation and maintenance instruction changes operation and maintenance configuration according to the operation and maintenance instruction;

the second controller is further configured to isolate and protect resource data in the network device in the test site based on a preset security rule.

7. The system of claim 1, wherein the orchestrator comprises a web services design module and a web services operation module; the process of the orchestrator for orchestrating the resources according to the resource requirements of the users comprises the following steps:

the network service design module carries out data modeling according to the resource demands of the users to obtain a demand model, and sends the demand model to the network service operation and maintenance module;

and the network service operation and maintenance module correspondingly distributes network resources to each network device in the future network test facility platform after verifying the demand model.

8. The system of claim 7, wherein the process of the web service design module obtaining the demand model comprises:

A path design module is utilized to carry out resource allocation path design corresponding to the backbone network according to the resource requirements of the users;

designing a resource allocation path corresponding to the test site according to the resource requirement of the user by utilizing a service detection design module;

and carrying out data modeling according to the results of the path design module and the service detection design module to obtain the demand model.

9. The system of claim 7, wherein the network service operation and maintenance module corresponds to a process of allocating network resources comprising:

after the demand model is verified by the verification module, the network resources are deployed by the deployment module according to the demand model, and a deployment result is obtained;

and correspondingly distributing the network resources to each network device by utilizing a distribution module according to the deployment result.

10. The system of claim 9, wherein the web service operation and maintenance module is further configured to monitor a network resource of each of the network devices using the status monitoring module, and update the deployment result according to the monitoring result.