Edge vCDN scene resource scheduling method, system, device and medium

Abstract

The invention discloses an edge vCDN scene resource scheduling method, system, device and medium, and the method is applied to a hybrid cloud environment system comprising a container arrangement platform and a cloud management platform, and comprises the steps: firstly collecting a plurality of resource use indexes of a vCDN service container running on the container arrangement platform and the resource state of a host machine where the vCDN service container is located; when the resource use index meets a preset capacity expansion triggering condition, whether the resource state of a host machine where the vCDN service container is located meets a preset resource sufficiency condition or not is judged; if yes, executing a resource expansion operation on the vCDN service container; otherwise, after the non-vCDN service load borne by the host machine is migrated to other nodes except the current host machine, resource capacity expansion operation is executed on the vCDN service container. By adopting the method and the device, the problem of shortage of edge vCDN node resources can be effectively solved, and the utilization rate of the edge node resources is improved while stable operation of vCDN services is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of content delivery network technology, and in particular to a resource scheduling method, system, device and medium for edge vCDN scenarios. Background Technology

[0002] A CDN (Content Delivery Network) is a network of servers distributed across different geographical locations to more efficiently distribute internet content to users. A vCDN (Virtual Content Delivery Network) is a virtualized CDN software application that can run CDN workloads on dedicated, bare-metal, virtualized, or container-based infrastructure. Deploying vCDNs on edge computing nodes has become a new form of CDN service. While it improves server performance utilization and service flexibility compared to traditional CDNs, the physical servers in edge computing scenarios are inherently lightweight and lack physical resources. When vCDNs are deployed on these edge nodes, resource utilization can become excessively high when vCDN workloads increase. This can not only hinder the operation of the vCDN's own content delivery services but also affect the normal operation of other public cloud services running simultaneously on the nodes.

[0003] Existing solutions for edge vCDN node resource shortages are based on traditional CDN node designs. When faced with excessive load, they simply transfer traffic to other nodes, making them susceptible to interference from network and distance factors, leading to a decrease in CDN service hit rate and availability. Monitoring focuses on upper-level indicators such as user service quality and video service quality, which have poor real-time performance. When vCDN services become unstable, it is difficult to quickly issue early warnings and accurately find the root cause of the problem. Summary of the Invention

[0004] The purpose of this invention is to provide a resource scheduling method, system, device and medium for edge vCDN scenarios, which effectively solves the problem of resource shortage of edge vCDN nodes, and improves the resource utilization rate of edge nodes while ensuring the stable operation of vCDN services.

[0005] To achieve the above objectives, the present invention provides a resource scheduling method for edge vCDN scenarios, which is applied to a hybrid cloud environment system. The hybrid cloud environment system includes a container orchestration platform and a cloud management platform. The management components of the cloud management platform are containerized and scheduled by the container orchestration platform. The method includes: Collect multiple resource usage metrics of vCDN service containers running on the container orchestration platform and the resource status of the host machine where the vCDN service containers are located; When the resource usage index meets the preset expansion trigger condition, it is determined whether the resource status of the host machine where the vCDN service container is located meets the preset resource sufficiency condition; if yes, a resource expansion operation is performed on the vCDN service container; if no, the non-vCDN service load carried on the host machine is migrated to other nodes other than the current host machine, and then a resource expansion operation is performed on the vCDN service container.

[0006] Optionally, the edge vCDN scenario resource scheduling method further includes: When the resource usage metric meets the preset overload triggering condition, a portion of the service traffic of the vCDN service container is scheduled to other vCDN service containers.

[0007] Optionally, the edge vCDN scenario resource scheduling method further includes: Determine peak periods for CDN services based on historical business data; Before the start of the high-incidence period, proactively migrate the non-vCDN service load on at least one target host to other nodes besides the target host. After the peak period ends, if the resource usage metrics of the vCDN service containers on the target host return to a safe range, the migrated non-vCDN service load will be migrated back to the original target host.

[0008] Optionally, redirecting a portion of the service traffic of the vCDN service container to other vCDN service containers includes: According to the pre-configured static scheduling policy, a portion of the service traffic of the vCDN service container is scheduled to other vCDN service containers; The static scheduling strategy is configured based on at least one dimension, including traffic load, disk status, number of connections, and geographical location.

[0009] Optionally, the resource usage metrics include CPU utilization, memory utilization, disk utilization, and network input / output.

[0010] Optionally, the preset expansion trigger condition is that at least one of the CPU utilization rate, memory utilization rate, and disk utilization rate exceeds a preset expansion trigger threshold; the preset overload trigger condition is that the network input / output of the vCDN service container exceeds a preset overload trigger threshold.

[0011] Optionally, the non-vCDN service load includes storage virtual machines below a preset threshold and containerized cloud management platform management components.

[0012] To achieve the above objectives, the present invention also provides an edge vCDN scenario resource scheduling system applied to a hybrid cloud environment system, wherein the hybrid cloud environment system includes a container orchestration platform and a cloud management platform, and the management components of the cloud management platform are containerized and scheduled by the container orchestration platform; The edge vCDN scenario resource scheduling system includes: The resource information collection module is used to collect multiple resource usage indicators of the vCDN service containers running on the container orchestration platform and the resource status of the host machine where the vCDN service containers are located. The resource scheduling module is used to determine whether the resource status of the host machine where the vCDN service container is located meets the preset resource sufficiency condition when the resource usage index meets the preset expansion trigger condition; if yes, then perform a resource expansion operation on the vCDN service container; if no, then migrate the non-vCDN service load carried on the host machine to other nodes other than the current host machine, and then perform a resource expansion operation on the vCDN service container.

[0013] To achieve the above objectives, the present invention also provides an edge vCDN scene resource scheduling device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the edge vCDN scene resource scheduling method as described above.

[0014] To achieve the above objectives, the present invention also provides a computer-readable storage medium storing a computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the edge vCDN scenario resource scheduling method as described above.

[0015] Compared to existing technologies, the resource scheduling method, system, device, and medium provided in this invention for edge vCDN scenarios, by collecting the underlying resource usage indicators of vCDN service containers and the resource status of the host machine in real time, when the expansion condition is triggered, it first determines whether the host machine resources are sufficient. If sufficient, it directly performs elastic expansion of the vCDN container; if insufficient, it first migrates the non-vCDN service load on the host machine before completing the expansion. This avoids the problem of decreased service hit rate and availability caused by simply relying on traffic transfer. Secondly, by monitoring and triggering thresholds for multi-dimensional underlying resource indicators of vCDN containers and the host machine, it can accurately perceive resource bottlenecks and quickly issue early warnings. Combined with the collaborative scheduling capabilities of the hybrid cloud architecture, it can ensure the stable operation of core vCDN services while avoiding interference with other public cloud services on the nodes, thereby improving the resource utilization of edge nodes. Attached Figure Description

[0016] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a resource scheduling method for an edge vCDN scenario provided by an embodiment of the present invention; Figure 2 This is a vCDN node architecture diagram provided in an embodiment of the present invention; Figure 3 This is another flowchart illustrating a resource scheduling method for an edge vCDN scenario provided by an embodiment of the present invention; Figure 4 This is a structural block diagram of an edge vCDN scenario resource scheduling system provided in an embodiment of the present invention; Figure 5 This is a structural block diagram of an edge vCDN scenario resource scheduling device provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] See Figure 1 , Figure 1 This is a flowchart illustrating a resource scheduling method for an edge vCDN scenario provided by an embodiment of the present invention. The resource scheduling method for an edge vCDN scenario is applied to a hybrid cloud environment system, which includes a container orchestration platform and a cloud management platform. The management components of the cloud management platform are containerized and scheduled by the container orchestration platform. It's important to note that a CDN (Content Delivery Network) is a distributed content acceleration network. Its core function is to cache content such as videos, web pages, and files from the origin server to nodes closer to the user by deploying edge node clusters within a region. A vCDN (Virtual Content Deliver Network), on the other hand, is a virtualized CDN software application that can run CDN workloads on dedicated, bare-metal, virtualized, or container-based infrastructure.

[0020] Specifically, the hybrid cloud environment system includes a container orchestration platform that provides shared container services and a cloud management platform that provides virtual machine services. The management components of the cloud management platform are containerized and then uniformly scheduled by the container orchestration platform.

[0021] For example, the container orchestration platform is Kubernetes (also known as K8S), an open-source system for automatically deploying, scaling, and managing containerized applications. The cloud management platform is OpenStack, an open-source cloud computing management platform project.

[0022] In practice, a CDN (Content Delivery Network) node service underlying architecture can be built around the above-mentioned hybrid cloud environment, mainly including four core modules: virtual machine service, container service, vCDN software, and full-level monitoring system.

[0023] The virtual machine service is managed uniformly by the OpenStack cluster, while the container service is orchestrated and managed uniformly through the K8S Master node of the K8S cluster. To further improve server space utilization, this embodiment of the invention adopts a layered deployment optimization for OpenStack components. Core virtual machine management components such as Nova (compute service), Neutron (network service), Cinder (block storage service), and Ceilometer (metering and monitoring service) are containerized and deployed as container applications on the K8S Master node. At the same time, the Master node is configured in high availability mode to form a Master cluster. For other OpenStack components with lower resource requirements, such as Keystone, they are directly deployed as services and high availability management is achieved through high-performance open-source load balancers and proxy server software (such as the HAProxy component).

[0024] The vCDN service runs as a containerized application on the worker nodes of the Kubernetes cluster. It's important to note that the host machine is the physical server that hosts the aforementioned virtual resources and is also the physical entity of the worker nodes in the Kubernetes cluster. The vCDN service does not run directly on the abstract worker nodes, but rather as a containerized application deployed within the corresponding Kubernetes worker nodes on the host machine. The host machine provides the CPU, memory, disk, network, and other hardware resources to support the operation of the vCDN containers. Simultaneously, the virtual machines managed by OpenStack and some containerized OpenStack components also run on the host machine, making the host machine an intermediary between the virtual resources and the underlying physical hardware.

[0025] At the monitoring level, a collaborative solution of "monitoring software + Ceilometer component" can be adopted. Ceilometer is an open-source monitoring and metering component for the OpenStack platform. The monitoring software is responsible for covering containers / virtual machines belonging to vCDN services in the edge node cluster, as well as containers / virtual machines in other public cloud services, to achieve cross-scenario resource monitoring. The Ceilometer component deployed in OpenStack is specifically for monitoring virtual machine resources, with core monitoring items including CPU utilization, memory usage, network throughput, and disk utilization.

[0026] For example, see Figure 2 , Figure 2 This is a vCDN node architecture diagram provided in an embodiment of the present invention. Figure 2 As shown, the vCDN node architecture includes Kubernetes Master nodes A and B (which serve as a unified orchestration hub, responsible for scheduling containerized OpenStack core components and container services) forming a high-availability cluster, vCDN service containers running on K8S worker nodes (carrying the core business of vCDN content distribution), OpenStack for managing virtual machines A and B (whose core components such as Nova and Neutron have been containerized and incorporated into K8S management), and monitoring software that enables real-time monitoring of physical machines, virtual machines A / B, and vCDN service containers. Together with the Ceilometer component in OpenStack, it collects resource data and completes the vCDN node operating architecture.

[0027] Furthermore, the edge vCDN scenario resource scheduling method includes steps S1 to S2: Step S1: Collect multiple resource usage metrics of the vCDN service containers running on the container orchestration platform and the resource status of the host machine where the vCDN service containers are located; In one alternative embodiment, the resource usage metrics include CPU utilization, memory utilization, disk utilization, and network input / output.

[0028] For example, based on container orchestration platforms such as Kubernetes, the platform's native monitoring components or dedicated monitoring tools can be used to obtain in real time core resource usage indicators such as CPU utilization, memory utilization, disk input / output, network input / output, network throughput, and disk utilization of each vCDN service container on the platform. At the same time, underlying resource status indicators such as the overall CPU / memory / disk utilization, remaining available resources, average resource load, and the total resource ratio of all containers running on the host machine to which each vCDN service container belongs can be collected simultaneously.

[0029] It is worth noting that this operation can effectively distinguish whether the abnormal operation of vCDN services is caused by problems with the container's own processes or insufficient host resources, thus improving the efficiency and accuracy of fault location for vCDN service resource anomalies. At the same time, it can provide real and effective data for intelligent resource scheduling and elastic scaling of container orchestration platforms.

[0030] Step S2: When the resource usage index meets the preset expansion trigger condition, determine whether the resource status of the host machine where the vCDN service container is located meets the preset resource sufficiency condition; if yes, perform resource expansion operation on the vCDN service container; if no, migrate the non-vCDN service load carried on the host machine to other nodes other than the current host machine, and then perform resource expansion operation on the vCDN service container.

[0031] In one optional embodiment, the preset expansion trigger condition is that at least one of the CPU utilization rate, memory utilization rate, and disk utilization rate exceeds the preset expansion trigger threshold.

[0032] In one alternative embodiment, the non-vCDN service load includes storage virtual machines below a preset threshold and containerized cloud management platform management components.

[0033] For example, when at least one of the CPU utilization, memory utilization, and disk utilization of a vCDN service container exceeds its respective monitoring threshold, thus meeting the expansion trigger condition, the system first determines whether the hardware resource status of the host machine where the vCDN service container is located meets the preset resource sufficiency conditions. If the host machine has sufficient resources, the system directly performs the corresponding resource expansion operation on the vCDN service container. If the host machine has insufficient resources, the system first migrates non-vCDN service loads such as containerized OpenStack core management components and low-usage storage virtual machines carried on the host machine to other nodes in the cluster other than the current host machine, and then completes the resource expansion operation on the vCDN service container.

[0034] This invention addresses scenarios where edge vCDN nodes have limited resources. It enables layered processing for expanding core vCDN services, prioritizing stable operation and low latency requirements for vCDN services while efficiently utilizing idle resources of the host machine and cluster through dynamic migration of non-core loads. This avoids wasting hardware resources and improves the overall resource utilization of edge nodes.

[0035] In an optional embodiment, the edge vCDN scenario resource scheduling method further includes step S3: When the resource usage metric meets the preset overload triggering condition, a portion of the service traffic of the vCDN service container is scheduled to other vCDN service containers.

[0036] In one optional embodiment, the preset overload triggering condition is that the network input / output of the vCDN service container exceeds a preset overload triggering threshold.

[0037] In one optional embodiment, redirecting a portion of the service traffic of the vCDN service container to other vCDN service containers includes: According to the pre-configured static scheduling policy, a portion of the service traffic of the vCDN service container is scheduled to other vCDN service containers; The static scheduling strategy is configured based on at least one dimension, including traffic load, disk status, number of connections, and geographical location.

[0038] Addressing the pain point of network I / O overload due to sudden traffic surges in vCDN scenarios, this invention can quickly alleviate the traffic pressure on a single vCDN service container without performing resource expansion, avoiding content distribution delays and increased access latency caused by network congestion, and ensuring the service continuity and low-latency experience of core vCDN distribution services. At the same time, based on a static scheduling strategy with multi-dimensional configuration, it can achieve accurate and reasonable traffic distribution, fully utilize the idle network resources of other vCDN service containers in the cluster, and improve the overall traffic processing capacity and resource utilization of the edge node cluster.

[0039] In an optional embodiment, the edge vCDN scenario resource scheduling method further includes step S4: Determine peak periods for CDN services based on historical business data; Before the start of the high-incidence period, proactively migrate the non-vCDN service load on at least one target host to other nodes besides the target host. After the peak period ends, if the resource usage metrics of the vCDN service containers on the target host return to a safe range, the migrated non-vCDN service load will be migrated back to the original target host.

[0040] For example, based on historical vCDN service data, it can be determined that the peak periods for CDN services are from 7 pm to 11 pm on weekdays and all day on holidays. Before these peak periods arrive, non-vCDN service loads such as containerized OpenStack core management components and low-usage storage virtual machines on the target host running vCDN service containers are proactively migrated to other idle nodes in the cluster other than the target host, reserving hardware resources for vCDN service containers in advance. After the peak period ends, if the CPU utilization, network I / O and other resource usage indicators of the vCDN service containers on the target host have been restored to the preset safe range, the previously migrated non-vCDN service loads are migrated back to the original target host. If the indicators still do not meet the standards, the migration is suspended.

[0041] This invention addresses scenarios with limited resources on edge vCDN nodes by employing predictive load migration based on historical data. This pre-emptively reserves sufficient resources for vCDN services during peak traffic periods, avoiding response delays caused by temporary scaling and migration operations during these periods. This ensures low latency and high stability for core vCDN services during peak traffic times. Furthermore, after the peak period ends, conditional migration is performed based on the vCDN service resource status, preventing the waste of target host resources and maximizing the overall resource utilization of the edge node cluster.

[0042] See Figure 3 , Figure 3 This is another flowchart of a resource scheduling method for edge vCDN scenarios provided by an embodiment of the present invention. For example... Figure 3 As shown, firstly, resource monitoring thresholds for vCDN containers and the host machine can be set, and static scheduling policies for GSLB (Global Server Load Balancing) can be configured. Then, continuously monitor resource metrics such as CPU utilization, memory utilization, and disk I / O of the vCDN containers, as well as the resource status of the host machine. When the CPU / memory metrics of the vCDN containers exceed the expansion trigger threshold, first determine if the host machine resources are sufficient. If sufficient, directly expand the vCDN container and temporarily divert traffic to high-availability nodes via GSLB to ensure uninterrupted service. If insufficient, first migrate non-vCDN business loads (such as containerized OpenStack components or low-usage storage virtual machines) on the host machine before performing expansion. Specifically, there are two scenarios for determining if the host machine resources are sufficient: one is whether the host machine's CPU metrics exceed the threshold; if not, directly perform expansion; if so, migrate the containerized OpenStack components on the host machine via Kubernetes before performing expansion. Secondly, it determines whether the host machine's memory and disk metrics exceed the threshold. If so, it migrates low-usage storage virtual machines on the host machine via Kubernetes before performing expansion. If not, when the network I / O of the vCDN container exceeds the overload trigger threshold, it directly schedules some traffic to other idle vCDN containers through the pre-configured GSLB static scheduling policy. After all expansion or traffic scheduling operations are completed, the traffic is switched back to the original vCDN container node, thereby achieving stable operation of core vCDN services and efficient utilization of edge node resources.

[0043] In summary, the edge vCDN scenario resource scheduling method provided by this invention collects low-level resource metrics such as CPU utilization, memory utilization, and disk I / O of vCDN service containers in real time, as well as the resource status of the host machine. When a scaling condition is triggered, it first determines whether the host machine resources are sufficient. If sufficient, it directly performs elastic scaling of the vCDN container; if insufficient, it migrates non-vCDN service loads on the host machine before completing the scaling. This avoids the service hit rate and availability degradation caused by simply relying on traffic transfer. Secondly, by monitoring and triggering thresholds for multi-dimensional low-level resource metrics of vCDN containers and the host machine, it can accurately perceive resource bottlenecks and quickly issue early warnings. Combined with the collaborative scheduling capabilities of the hybrid cloud architecture, it can ensure the stable operation of core vCDN services while avoiding interference with other public cloud services on the nodes, thereby improving the resource utilization of edge nodes.

[0044] See Figure 4 , Figure 4 This is a structural block diagram of an edge vCDN scenario resource scheduling system provided by an embodiment of the present invention. The edge vCDN scenario resource scheduling system is applied to a hybrid cloud environment system, which includes a container orchestration platform and a cloud management platform. The management components of the cloud management platform are containerized and scheduled by the container orchestration platform. The edge vCDN scenario resource scheduling system includes: The resource information collection module 21 is used to collect multiple resource usage indicators of the vCDN service containers running on the container orchestration platform and the resource status of the host machine where the vCDN service containers are located. The capacity scheduling module 22 is used to determine whether the resource status of the host machine where the vCDN service container is located meets the preset resource sufficiency condition when the resource usage index meets the preset expansion trigger condition; if yes, then perform a resource expansion operation on the vCDN service container; if no, then migrate the non-vCDN service load carried on the host machine to other nodes other than the current host machine, and then perform a resource expansion operation on the vCDN service container.

[0045] In one optional embodiment, the edge vCDN scenario resource scheduling system further includes an overload scheduling module, used for: When the resource usage metric meets the preset overload triggering condition, a portion of the service traffic of the vCDN service container is scheduled to other vCDN service containers.

[0046] In one optional embodiment, the edge vCDN scenario resource scheduling system further includes a service scheduling module, used for: Determine peak periods for CDN services based on historical business data; Before the start of the high-incidence period, proactively migrate the non-vCDN service load on at least one target host to other nodes besides the target host. After the peak period ends, if the resource usage metrics of the vCDN service containers on the target host return to a safe range, the migrated non-vCDN service load will be migrated back to the original target host.

[0047] It should be noted that the edge vCDN scene resource scheduling system provided in this embodiment of the invention is used to execute all the process steps of the edge vCDN scene resource scheduling method in the above embodiment. The working principle and beneficial effect of the two are one-to-one, so they will not be described again.

[0048] See Figure 5 , Figure 5 This is a structural block diagram of an edge vCDN scenario resource scheduling device provided in an embodiment of the present invention. The edge vCDN scenario resource scheduling device includes a processor 31, a memory 32, and a computer program stored in the memory 32 and executable on the processor 31. When the processor 31 executes the computer program, it implements the steps in the above-described embodiments of the edge vCDN scenario resource scheduling method, for example...

[0049] For example, the computer program can be divided into one or more modules / units, which are stored in the memory 32 and executed by the processor 31 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the edge vCDN scene resource scheduling device.

[0050] The edge vCDN scenario resource scheduling device may include, but is not limited to, a processor 31 and a memory 32. Those skilled in the art will understand that the schematic diagram is merely an example of an edge vCDN scenario resource scheduling device and does not constitute a limitation on the device. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, the edge vCDN scenario resource scheduling device may also include input / output devices, network access devices, buses, etc.

[0051] The processor 31 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 31 is the control center of the edge vCDN scene resource scheduling device, connecting various parts of the entire edge vCDN scene resource scheduling device through various interfaces and lines.

[0052] The memory 32 can be used to store the computer programs and / or modules. The processor 31 implements various functions of the edge vCDN scene resource scheduling device by running or executing the computer programs and / or modules stored in the memory 32 and calling the data stored in the memory 32. The memory 32 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 32 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0053] Wherein, if the modules / units integrated by the edge vCDN scene resource scheduling device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor 31, it can implement the steps of the above method embodiments. Wherein, the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0054] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A resource scheduling method for edge vCDN scenarios, characterized in that, This is applied to a hybrid cloud environment system, which includes a container orchestration platform and a cloud management platform, wherein the management components of the cloud management platform are containerized and scheduled by the container orchestration platform. The method includes: Collect multiple resource usage metrics of vCDN service containers running on the container orchestration platform and the resource status of the host machine where the vCDN service containers are located; When the resource usage index meets the preset expansion trigger condition, it is determined whether the resource status of the host machine where the vCDN service container is located meets the preset resource sufficiency condition; if yes, a resource expansion operation is performed on the vCDN service container; if no, the non-vCDN service load carried on the host machine is migrated to other nodes other than the current host machine, and then a resource expansion operation is performed on the vCDN service container.

2. The edge vCDN scenario resource scheduling method as described in claim 1, characterized in that, Also includes: When the resource usage metric meets the preset overload triggering condition, a portion of the service traffic of the vCDN service container is scheduled to other vCDN service containers.

3. The edge vCDN scenario resource scheduling method as described in claim 1, characterized in that, Also includes: Determine peak periods for CDN services based on historical business data; Before the start of the high-incidence period, proactively migrate the non-vCDN service load on at least one target host to other nodes besides the target host. After the peak period ends, if the resource usage metrics of the vCDN service containers on the target host return to a safe range, the migrated non-vCDN service load will be migrated back to the original target host.

4. The resource scheduling method for edge vCDN scenarios as described in claim 2, characterized in that, Dispatching a portion of the service traffic of the vCDN service container to other vCDN service containers includes: According to the pre-configured static scheduling policy, a portion of the service traffic of the vCDN service container is scheduled to other vCDN service containers; The static scheduling strategy is configured based on at least one dimension, including traffic load, disk status, number of connections, and geographical location.

5. The edge vCDN scenario resource scheduling method as described in any one of claims 1, characterized in that, The resource usage metrics include CPU utilization, memory utilization, disk utilization, and network input / output.

6. The resource scheduling method for edge vCDN scenarios as described in claim 5, characterized in that, The preset expansion trigger condition is that at least one of the CPU utilization rate, memory utilization rate, and disk utilization rate exceeds the preset expansion trigger threshold; the preset overload trigger condition is that the network input / output of the vCDN service container exceeds the preset overload trigger threshold.

7. The edge vCDN scenario resource scheduling method as described in any one of claims 1 to 6, characterized in that, The non-vCDN service load includes storage virtual machines below a preset threshold and containerized cloud management platform management components.

8. A resource scheduling system for edge vCDN scenarios, characterized in that, This is applied to a hybrid cloud environment system, which includes a container orchestration platform and a cloud management platform, wherein the management components of the cloud management platform are containerized and scheduled by the container orchestration platform. The edge vCDN scenario resource scheduling system includes: The resource information collection module is used to collect multiple resource usage indicators of the vCDN service containers running on the container orchestration platform and the resource status of the host machine where the vCDN service containers are located. The capacity scheduling module is used to determine whether the resource status of the host machine where the vCDN service container is located meets the preset resource sufficiency condition when the resource usage index meets the preset expansion trigger condition; if yes, then perform a resource expansion operation on the vCDN service container; if no, then migrate the non-vCDN service load carried on the host machine to other nodes other than the current host machine, and then perform a resource expansion operation on the vCDN service container.

9. A resource scheduling device for edge vCDN scenarios, characterized in that, include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the edge vCDN scenario resource scheduling method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the edge vCDN scenario resource scheduling method as described in any one of claims 1 to 7.

Images