Cloud resource scheduling system, method and device

Abstract

The embodiments of this specification provide a cloud resource scheduling system, method and device, wherein the cloud resource scheduling method includes: pre-dividing the traffic of the traffic scheduling unit into several traffic slices; in response to monitoring the target event, selecting the traffic slice to be scheduled according to the target event; selecting and binding the target cloud resource for the traffic slice to be scheduled based on a preset resource scheduling algorithm; and generating resource scheduling information for the traffic slice to be scheduled based on the target cloud resource bound to the traffic slice to be scheduled.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of cloud computing technology, and in particular to a cloud resource scheduling method. Background Art

[0002] Edge cloud, built on edge infrastructure between the central cloud and endpoints, leverages cloud computing capabilities from the center to the edge, enabling collaborative cloud-edge management to address service needs that cannot be met under centralized cloud computing. The edge nature of edge cloud dictates that cloud resource scheduling systems must meet high throughput, real-time feedback, and rapid exception mitigation requirements.

[0003] However, traditional edge cloud resource scheduling generally adopts a rule-based heuristic greedy algorithm to plan resource scheduling information from the global perspective of the traffic scheduling unit. The planning process is slow and the resource scheduling information fluctuates greatly, resulting in low scheduling efficiency and poor flexibility. Summary of the Invention

[0004] In view of this, embodiments of this specification provide a cloud resource scheduling method. One or more embodiments of this specification also relate to a cloud resource scheduling system, a cloud resource scheduling apparatus, a computing device, a computer-readable storage medium, and a computer program to address technical deficiencies in the prior art.

[0005] According to the first aspect of the embodiments of this specification, a cloud resource scheduling system is provided, including: a resource scheduling node, configured to pre-divide the traffic of a traffic scheduling unit into several traffic slices, monitor target events, and in response to monitoring target events, select a traffic slice to be scheduled according to the target event, select and bind a target cloud resource for the traffic slice to be scheduled based on a preset resource scheduling algorithm, and generate resource scheduling information for the traffic slice to be scheduled based on the target cloud resource bound to the traffic slice to be scheduled; an edge node, configured to schedule based on the resource scheduling information, receive the traffic of the corresponding traffic slice and provide services.

[0006] According to the second aspect of the embodiments of this specification, a cloud resource scheduling method is provided, including: pre-dividing the traffic of a traffic scheduling unit into several traffic slices; in response to monitoring the target event, selecting the traffic slice to be scheduled according to the target event; selecting and binding the target cloud resource for the traffic slice to be scheduled based on a preset resource scheduling algorithm; and generating resource scheduling information for the traffic slice to be scheduled based on the target cloud resource bound to the traffic slice to be scheduled.

[0007] According to the third aspect of the embodiments of this specification, a cloud resource scheduling device is provided, including: a slicing module, configured to pre-divide the traffic of a traffic scheduling unit into several traffic slices; a control module, configured to select a traffic slice to be scheduled according to the target event in response to monitoring the target event; a scheduling calculation module, configured to select and bind a target cloud resource for the traffic slice to be scheduled based on a preset resource scheduling algorithm; and a policy generation module, configured to generate resource scheduling information for the traffic slice to be scheduled based on the target cloud resource bound to the traffic slice to be scheduled.

[0008] According to the fourth aspect of the embodiments of this specification, a computing device is provided, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the cloud resource scheduling method described in any embodiment of this specification.

[0009] According to a fifth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the cloud resource scheduling method described in any embodiment of this specification are implemented.

[0010] According to a sixth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned cloud resource scheduling method.

[0011] An embodiment of the present specification implements a cloud resource scheduling method. Since the method divides the traffic of the traffic scheduling unit into several traffic slices in advance, in response to monitoring the target event, the traffic slice to be scheduled is selected according to the target event, and the target cloud resource is selected and bound for the traffic slice to be scheduled based on a preset resource scheduling algorithm. Resource scheduling information is generated for the traffic to be scheduled based on the target cloud resource bound to the traffic slice to be scheduled, so that the method can further subdivide the traffic slice based on the traffic scheduling unit. The minimum unit for scheduling cloud resources in the edge cloud access scenario is the traffic slice. When the target event is monitored, the traffic slice is selected based on the event-driven method to adjust the local resource scheduling information. The policy changes are small, the scheduling response is fast, the planning delay is low, and the effect of real-time feedback can be achieved. The scheduling efficiency is higher and the system scheduling flexibility is better. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a block diagram of a cloud resource scheduling system provided by one embodiment of this specification;

[0013] Figure 2This is a schematic diagram of a live broadcast application scenario of a cloud resource scheduling system provided by an embodiment of this specification;

[0014] Figure 3 This is a flow chart of a cloud resource scheduling method provided by one embodiment of this specification;

[0015] Figure 4 This is a schematic diagram of the system architecture of a cloud resource scheduling method provided by an embodiment of this specification;

[0016] Figure 5 This is a block diagram of a cloud resource scheduling device provided by one embodiment of this specification;

[0017] Figure 6 This is a structural block diagram of a computing device provided by one embodiment of this specification. DETAILED DESCRIPTION

[0018] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0019] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0020] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0021] First, the terms involved in one or more embodiments of this specification are explained.

[0022] Traffic Scheduling Unit: In a content distribution network, a geographic area is divided into multiple traffic scheduling units, also known as scheduling groups. A traffic scheduling unit represents a unit of traffic within that area and can also be understood as an aggregated unit of traffic in edge cloud access scenarios. A traffic scheduling unit is represented by a collection of computer location identifiers, which can be domain names or IP addresses. Traffic scheduling units are typically divided based on a combination of factors, including user, service type (such as live / on-demand), and quality requirements, and are considered a single traffic unit.

[0023] Traffic slicing: For content delivery networks, traffic of a traffic scheduling unit within a certain area is further subdivided based on one or more factors such as bandwidth and service type, thereby logically virtualizing the slices.

[0024] Content Delivery Network (CDN) is an intelligent virtual network built on the existing network. Through the load balancing, content distribution, scheduling and other functional modules of the central platform, users can rely on edge nodes deployed in various places to obtain the required content nearby, reducing network congestion and improving access response speed and hit rate.

[0025] In content distribution networks, traffic scheduling in traditional access scenarios uses a rule-based heuristic greedy algorithm for global policy planning. Since this global greedy algorithm allocates traffic, the planning process is slow, the policy changes greatly, and the minimum scheduling unit is a traffic scheduling unit in a region, resulting in low system scheduling efficiency and poor flexibility.

[0026] In view of this, in this specification, a cloud resource scheduling system and a cloud resource scheduling method are provided. This specification also involves a cloud resource scheduling device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0027] See also Figure 1 , Figure 1 A block diagram of a cloud resource scheduling system provided according to one embodiment of this specification is shown, specifically including:

[0028] The resource scheduling node 102 is configured to pre-divide the traffic of the traffic scheduling unit into several traffic slices, monitor the target event, and in response to monitoring the target event, select the traffic slice to be scheduled according to the target event, select and bind the target cloud resource for the traffic slice to be scheduled based on the preset resource scheduling algorithm, and generate resource scheduling information for the traffic slice to be scheduled based on the target cloud resource.

[0029] The resource scheduling node is a node for traffic scheduling cloud resources. The cloud resources include, for example, edge node storage, network bandwidth, computing power, and other nodes. The arrangement of the resource scheduling node is not limited. For example, it can be arranged at the center of the edge cloud of the content distribution network. The center may include but is not limited to providing resource scheduling nodes, source stations, and other capabilities. The source station is a website server that provides relevant data for services and is the source of accelerated distribution data. The source station can be used to process and respond to user requests. When the edge node does not cache the content requested by the user, the node will return to the source station to obtain resource data and return it to the user.

[0030] The resource scheduling information is information indicating that the target cloud resource is used for the traffic slice. For example, the resource scheduling information may include information such as the region, traffic scheduling unit, traffic slice, and edge node.

[0031] The edge node 104 is configured to receive the corresponding traffic slice and provide services based on the scheduling of the resource scheduling information.

[0032] An edge node is a node in the access network located near the edge of the user's network in the edge cloud. Multiple edge nodes can exist, providing storage, computing, networking, and other resources. In practical applications, an edge node can represent one or multiple computer rooms. To ensure service availability across regions and computer rooms, some application scenarios group edge cloud computer rooms. Each group can include one or more computer rooms. In these application scenarios, an edge node can correspond to a group. In a content distribution network, after various user terminals collect massive amounts of data, small-scale, localized data requiring real-time processing is processed locally on the edge cloud, while complex, large-scale, global tasks are aggregated and analyzed in depth by the central cloud. The central and edge clouds implement unified management and intelligent scheduling, thereby optimizing the allocation of computing power. Therefore, moving some critical tasks to the edge of the access network can reduce bandwidth and latency losses caused by network transmission and multi-stage forwarding. For example, edge nodes can cache resources from the source server to quickly and locally respond to user requests in different regions.

[0033] Alternatively, as Figure 1 As shown, in the cloud resource scheduling system, other networks can also be set up according to the application scenario. For example, a layer of nodes can be arranged between the center and the access network to cache content. Specifically, if the edge node does not cache the content requested by the user, it can return to the upper node such as Figure 1 The cache node shown is used to request the content.

[0034] The cloud resource scheduling system provided by the embodiments of this specification enables the resource scheduling node to further subdivide the traffic slice based on the traffic scheduling unit. The smallest unit for scheduling cloud resources in the edge cloud access scenario is the traffic slice. When the target event is monitored, the traffic slice is selected based on the event drive to adjust the local resource scheduling information. The policy changes are small, the scheduling response is fast, the planning delay is low, and the effect of real-time feedback can be achieved. The scheduling efficiency is higher and the system scheduling flexibility is better.

[0035] See also Figure 2 , Figure 2 A schematic diagram of a live broadcast application scenario of a cloud resource scheduling system provided according to an embodiment of this specification is shown. Figure 2 As shown:

[0036] In a live streaming application scenario, user 1 of live streaming application A (such as a live streamer or conference initiator) uses stream pusher A1 to push the live stream upstream. User 2 of live streaming application A (such as a live stream audience or conference participant) uses stream puller A2 to subscribe to and play the live stream. Stream pusher A1 accesses a nearby edge node of the content distribution network (CDN) and transmits the live stream to the central cloud, which is responsible for computing and processing the live stream data. Stream puller A2 accesses a nearby edge node of the CDN, pulls the live stream, and then plays it.

[0037] As can be seen from the above process, in a content delivery network, traffic from live streaming application A within a certain traffic scheduling unit in a certain area will be connected to one or more edge nodes nearby for computing and processing related to the live streaming service. Therefore, cloud resource scheduling nodes are required in the content delivery network to schedule edge nodes.

[0038] Assume that the traffic volume of live streaming application A in traffic scheduling unit Y in region X is 56G. The resource scheduling node divides the traffic into 10G bandwidth slices, further subdividing the 56G traffic into five 10G and one 6G traffic slices 1-6. Initially, edge nodes are selected and bound to these traffic slices based on their matching with edge nodes, including their regional and live streaming service configurations. For example, traffic slices 1-3 are bound to edge node 1, and traffic slices 4-6 are bound to edge node 2. Based on the region Y where the traffic slices reside, traffic scheduling unit X and the bound edge nodes generate resource scheduling information for each traffic slice. For example, the resource scheduling information for traffic slice 1 indicates that edge node 1 will provide live streaming services for traffic in traffic slice 1 in traffic scheduling unit Y in region X. The resource scheduling node monitors for target events such as node uptime / downtime, whether the cloud resources bound to a traffic slice exceed the corresponding service's preset region, or whether the cloud resources bound to a traffic slice cannot meet service requirements. If so, the traffic slice associated with the target event is identified as the traffic slice to be scheduled. Assuming edge node 1 goes offline, traffic slices 1-3 are selected as the traffic slices to be scheduled. The resource scheduling node reselects and binds edge nodes for traffic slices 1-3 based on the matching of the edge node's configuration information, such as the region and live broadcast service. Assuming edge node 4 is reselected and bound, resource scheduling information is generated to instruct edge node 4 to provide live broadcast service for traffic slices 1-3 in traffic scheduling unit Y in region X.

[0039] It should be noted that the cloud resource scheduling system provided in the embodiments of this specification can be applied to various application scenarios based on cloud computing, including but not limited to live video broadcasting, online video conferencing, website / application acceleration, etc.

[0040] See also Figure 3 , Figure 3 A flow chart of a cloud resource scheduling method according to an embodiment of this specification is shown. Figure 3 As shown, the specific steps include the following steps.

[0041] Step 302: Divide the traffic of the traffic scheduling unit into several traffic slices in advance.

[0042] For example, the traffic scheduling unit may be a set of domain names.

[0043] The specific method for dividing traffic slices is not limited, and traffic can be divided based on any one or more factors, such as bandwidth and service type. For example, the bandwidth of a single slice can be set, and the resource scheduling node slices the traffic of the traffic scheduling unit according to the bandwidth of the single slice. For another example, the service type of a single slice can be set, and the resource scheduling node slices the traffic of the traffic scheduling unit according to the service type of the single slice.

[0044] Step 304: In response to monitoring the target event, a traffic slice to be scheduled is selected according to the target event.

[0045] Among them, the target events that need to be monitored can be set according to the events that affect the scheduling of cloud resources in the actual application scenario. The target events that need to be monitored can be written into the configuration and modified as needed. For example, in one or more embodiments of this specification, the target events include:

[0046] Nodes in the cloud computing network come online or offline;

[0047] and / or,

[0048] Whether the cloud resources bound to the traffic slice exceed the corresponding preset area;

[0049] and / or,

[0050] Whether the cloud resources bound to the traffic slice cannot meet the service requirements.

[0051] In the above embodiment, cloud resources are rescheduled based on the perception of target events, and only local policy adjustments are performed, resulting in fast scheduling response and low planning latency.

[0052] The implementation method for selecting the traffic slice to be scheduled based on the target event is not limited. For example, when a traffic slice is bound to a cloud resource, the binding relationship can be recorded. Then, when a target event is detected, the cloud resource affected by the target event is first determined, and then the traffic slice bound to the cloud resource is found as the traffic slice to be scheduled. Specifically, based on the target event detected that a certain traffic slice does not use the cloud resources in the provincial area, the traffic slice is determined as the traffic slice to be scheduled.

[0053] Step 306: Select and bind target cloud resources for the traffic slice to be scheduled based on a preset resource scheduling algorithm.

[0054] The specific implementation of the resource scheduling algorithm is not limited and can be set according to the scheduling needs of cloud resources in actual application scenarios. For example, the preset resource scheduling algorithm selects and binds target cloud resources for the traffic slice to be scheduled, including:

[0055] Calculate the matching degree between the traffic slice to be scheduled and the cloud resource by using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resource;

[0056] Based on the matching degree, target cloud resources are selected and bound.

[0057] For example, the degree of configuration information matching can specifically include, but is not limited to, the affinity between the traffic slice and the target cloud resource's regional configuration, as well as the matching degree of the service label configuration. Selecting target cloud resources based on the degree of configuration information matching allows resource scheduling nodes or users to flexibly configure configuration information based on scenario needs, making it easier to bind cloud resources to appropriate service types and improving scheduling efficiency.

[0058] Among them, the configuration information of the traffic slice can be set by the background manager of the resource scheduling node according to the resource scheduling needs, or can be flexibly set by the user. Therefore, the method also includes: receiving and saving the configuration information set by the user for the traffic slice. For example, the configuration information of the traffic slice may include: the preset area, preset service type and / or cloud resource preference information of the traffic slice to be scheduled. Configuration information based on the preset area, preset service type and / or cloud resource preference information of the service makes it easier to bind cloud resources to suitable services, thereby improving scheduling efficiency.

[0059] Step 308: Generate resource scheduling information for the traffic slice to be scheduled based on the target cloud resources.

[0060] The resource scheduling information is information indicating that the target cloud resource is used for the traffic slice. In practical application scenarios, the resource scheduling node can perform scheduling based on the resource scheduling information in any manner. For example, the resource scheduling node can store the resource scheduling information in a database. Upon receiving an access request for traffic corresponding to a traffic slice, the resource scheduling node can distribute the traffic to the corresponding edge node based on the resource scheduling information for the traffic slice recorded in the database.

[0061] Through the cloud resource scheduling method provided in the embodiments of this specification, the resource scheduling node can further subdivide the traffic slice based on the traffic scheduling unit. The smallest unit for scheduling cloud resources in the edge cloud access scenario is the traffic slice. When the target event is monitored, the traffic slice is selected based on the event drive to adjust the local resource scheduling information. The policy changes are small, the scheduling response is fast, the planning delay is low, and the effect of real-time feedback can be achieved. The scheduling efficiency is higher and the system scheduling flexibility is better.

[0062] In one or more embodiments of this specification, in order to separate event control and resource scheduling capabilities and decouple components, the method further includes:

[0063] Receive plug-in and plug-out instructions from the event control algorithm;

[0064] Based on the plug-in instruction, an event control algorithm is set for selecting a traffic slice to be scheduled according to a target event.

[0065] The event control algorithm is the selection logic for selecting traffic slices to be scheduled based on any one or more target events. The selection logic can be configured based on the application scenario. For example, when an edge node in a cloud computing network comes online, because the edge node's location and the types of services it can handle are more suitable for certain traffic slices, traffic slices that are closer to the edge node's location and the types of services it can handle are selected and rescheduled to improve edge node utilization. For another example, when an edge node in a cloud computing network goes offline, to ensure the smooth operation of the affected services, the traffic slices bound to the edge node are selected and rescheduled to minimize the impact of the node's offline on the services. For another example, as edge nodes are used, their performance may degrade, making them unable to meet the traffic usage of the bound traffic slices. Alternatively, as the service scale increases, or the traffic volume associated with a particular traffic slice increases, in these cases, whether the cloud resources bound to the traffic slice are unable to meet service requirements, the relevant traffic slices are selected and rescheduled.

[0066] In one or more other embodiments of this specification, in order to separate event control and resource scheduling capabilities and decouple components, the method further includes:

[0067] Receive plug-in and pull-out instructions from the resource scheduling algorithm;

[0068] Based on the plug-in and pull-out instructions, a resource scheduling algorithm for selecting target cloud resources is set.

[0069] Among them, the resource scheduling algorithm is the logic used to select the target cloud resources for the traffic slice to be scheduled. The selection logic can be set specifically according to the needs of the application scenario. For example, in some application scenarios, the focus is on selecting cloud resources based on regional affinity, then a resource scheduling algorithm can be inserted as needed, including but not limited to selecting target cloud resources based on the affinity of the regional configuration of the traffic slice and the cloud resource. For another example, in other application scenarios, the focus is on selecting target cloud resources based on the matching degree of the service type, then another resource scheduling algorithm can be inserted as needed, including but not limited to selecting target cloud resources based on the matching degree of the traffic slice and the service label configuration of the cloud resource.

[0070] The plug-in and unplug-out instructions may include instructions for inserting an algorithm, such as taking effect or installing an algorithm, or instructions for removing an algorithm, such as disabling or uninstalling an algorithm.

[0071] In the above embodiment, by decoupling service control and scheduling, it is convenient to plug and unplug the event control algorithm on demand in actual application scenarios, which makes the application flexible and the scalability better.

[0072] In one or more embodiments of this specification, a priority queue can be set up, and before the preset resource scheduling algorithm is used to select and bind the target cloud resources for the traffic slice to be scheduled, the traffic slice to be scheduled is placed in the priority queue according to the priority of the target event; according to the priority order of the traffic slices in the priority queue, the traffic slice to be scheduled is taken out from the priority queue, and the step of selecting and binding the target cloud resources for the traffic slice to be scheduled based on the preset resource scheduling algorithm is entered. Priority queue means assigning an identifier to the element to be placed in the priority queue to mark its priority, so that after the element is placed in the priority queue, the element with the highest priority can be taken out when the element is taken out. Elements with the same priority can be processed in first-in-first-out order or according to any priority.

[0073] In order to reduce the amount of calculation of the matching degree and improve the scheduling efficiency, in one or more embodiments of this specification, before using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resources to calculate the matching degree between the traffic slice to be scheduled and the cloud resources, it also includes: from the total set of cloud resources, filtering out the cloud resources that are allowed to be used by the traffic scheduling unit where the traffic slice to be scheduled is located, to obtain a preliminary screening resource set; based on the resource capabilities required by the traffic slice to be scheduled, filtering out the cloud resources that meet the resource capabilities from the preliminary screening resource set, to obtain a resource set to be evaluated. Accordingly, the use of the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resources to be scheduled to calculate the matching degree between the traffic slice to be scheduled and the cloud resources includes: using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resources to be evaluated in the resource set to be evaluated to calculate the matching degree between the traffic slice to be scheduled and the cloud resources to be evaluated.

[0074] In the above embodiment, for example, cloud resources that are allowed to be used by the traffic scheduling unit where the traffic slice to be scheduled is located can be preliminarily screened out based on factors such as region and preset service type of the service, and then cloud resources that meet the resource capabilities required by the traffic slice to be scheduled are screened out from the preliminarily screened resource set based on the resource capabilities, thereby narrowing the scope of cloud resources that need to be matched and reducing the amount of matching calculation, thereby achieving the purpose of improving scheduling efficiency.

[0075] In actual application scenarios, based on resource management requirements in some special scenarios or factors such as network security, it is also necessary to check whether the resource scheduling information is compliant. Specifically, before binding the target cloud resources, the method further includes:

[0076] Based on preset policy compliance checking rules, checking whether the resource scheduling information generated based on the target cloud resource is compliant;

[0077] If it is compliant, proceed to the step of binding the target cloud resources.

[0078] In addition, if compliance is met, resource scheduling information is allowed to be actually generated based on the bound target cloud resources, and the generated resource scheduling information is saved to the database.

[0079] The policy compliance check rules can be configured based on application scenario resource management requirements or network security. For example, the preset policy compliance check rules may include the correspondence between certain types of services and edge nodes that are not allowed to be bound, the correspondence between certain services and restricted regions, and so on. This ensures that the resources bound to the traffic slices meet the needs of the application scenario, meet the requirements of edge node and service adaptation, and meet service security requirements.

[0080] As can be seen from the above embodiments, according to the methods provided in the embodiments of this specification, cloud resources of any dimension can be scheduled based on traffic slices divided into the smallest unit granularity. Cloud resources can be locally scheduled in real time when unexpected events such as abnormalities occur, providing excellent system flexibility. Furthermore, because the scheduling granularity is based on traffic slices divided by traffic scheduling units, virtualized logical slices mapped based on the traffic of the traffic scheduling units can be used to schedule access network resources to meet the needs of a wide range of edge scenarios, enabling edge resource utilization to develop in a computationally oriented and dynamic direction.

[0081] The following combined Figure 4 , the system architecture diagram of the cloud resource scheduling method combined with the above multiple embodiments is described in detail. Figure 4 As shown, a resource scheduling node that applies the cloud resource scheduling method provided in the embodiments of this specification may include the following components:

[0082] The sensor is used to monitor target events and, upon detecting a target event, notify the event controller to select the traffic slice to be scheduled. The controller registration unit can be used to establish or cancel the interaction channel between the controller and the sensor based on the controller's plug-in and unplug instructions.

[0083] The controller is used to select the traffic slices to be scheduled according to the target events monitored by the sensor, and send the relevant information of the traffic slices to be scheduled to the scheduler through the service interface of the scheduler, so that the scheduler can schedule cloud resources for these traffic slices to be scheduled.

[0084] Creating and deleting a controller can be understood as plugging and unplugging an event control algorithm. To create a new controller, a controller creation instruction can be sent to the controller registration module. To delete a controller, a controller deregistration instruction can be sent to the controller registration module.

[0085] The scheduler includes:

[0086] A service interface unit, used to establish an interaction channel with the controller;

[0087] The traffic scheduling unit registration unit is used to identify the traffic slices sent by the controller and the priorities of their corresponding target events based on the relevant registration information of the traffic scheduling unit, and put the traffic slices to be scheduled into the priority queue according to the priority.

[0088] Priority queue, used to dequeue traffic slices according to their priority order.

[0089] The resource scheduling algorithm unit includes:

[0090] The pre-screening unit is used to screen out the cloud resources that are allowed to be used by the traffic scheduling unit where the traffic slice to be scheduled is located from the total set of cloud resources, and obtain a preliminary screening resource set.

[0091] The screening unit is used to screen out cloud resources that meet the resource capabilities required by the traffic slice to be scheduled from the initial screening resource set, and obtain the resource set to be evaluated.

[0092] The scoring unit is used to calculate the matching degree between the traffic slice to be scheduled and the cloud resource to be evaluated by using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resource to be evaluated in the resource set to be evaluated.

[0093] The resource locking unit is configured to select a target cloud resource from the set of resources to be evaluated based on the matching degree.

[0094] The policy compliance checking unit is used to check whether the resource scheduling information generated based on the target cloud resource is compliant based on preset policy compliance checking rules. If it is not compliant, the resource locking module can be triggered to reselect the target cloud resource.

[0095] The resource binding unit is used to bind the traffic slice to be scheduled with the selected target cloud resource if the policy compliance check module determines that it is compliant.

[0096] In addition, the scheduler may further include:

[0097] The data cache unit is used to cache relevant data involved in the resource scheduling algorithm calculation and resource scheduling information. For example, the relevant data may include the configuration of the traffic scheduling unit, the user's configuration of bandwidth and traffic slices, etc.

[0098] The scheduling policy update component is used to update the newly generated resource scheduling information into the database and perform addition, deletion, and modification on the resource scheduling information as needed.

[0099] It should be noted that the aforementioned sensors, controllers, schedulers, and related units and components may be implemented as software, hardware, or a combination thereof in actual applications, and this specification does not limit this. Rescheduling based on configured anomaly perception only involves local policy adjustments, resulting in fast scheduling response and low planning latency.

[0100] Service control and scheduling algorithms are decoupled, converting service demands into sensor anomaly monitoring, affinity / label configuration, and scoring selection during resource selection.

[0101] The smallest unit of scheduling is a slice. The system scheduling is highly flexible and minimizes policy changes during rescheduling.

[0102] Corresponding to the above method embodiment, this specification also provides a cloud resource scheduling device embodiment, Figure 5 FIG1 shows a schematic diagram of the structure of a cloud resource scheduling device provided by an embodiment of this specification. Figure 5 As shown, the device includes:

[0103] The slicing module 502 is configured to pre-divide the traffic of the traffic scheduling unit into a number of traffic slices, where the traffic scheduling unit is a collection of domain names.

[0104] The control module 504 is configured to select a traffic slice to be scheduled according to the target event in response to monitoring the target event.

[0105] The scheduling calculation module 506 is configured to select and bind target cloud resources for the traffic slice to be scheduled based on a preset resource scheduling algorithm.

[0106] The policy generation module 508 is configured to generate resource scheduling information for the traffic slice to be scheduled based on the target cloud resources.

[0107] In one or more embodiments of this specification, the device further includes:

[0108] The algorithm setting module can be configured to receive an insertion and removal instruction of the event control algorithm, and based on the insertion and removal instruction, set an event control algorithm for selecting the traffic slice to be scheduled according to the target event.

[0109] In one or more other embodiments of the present specification, the algorithm setting module may also be configured to receive a plug-in instruction of a resource scheduling algorithm, and set a resource scheduling algorithm for selecting target cloud resources based on the plug-in instruction.

[0110] In one or more embodiments of this specification, the device further includes:

[0111] The queue processing module is configured to place the traffic slices to be scheduled into a priority queue according to the priority of the target event, and to take out the traffic slices to be scheduled from the priority queue according to the priority order of the traffic slices in the priority queue, thereby triggering the scheduling calculation module to execute the steps of selecting and binding target cloud resources for the traffic slices to be scheduled based on a preset resource scheduling algorithm.

[0112] In one or more embodiments of this specification, the scheduling calculation module includes:

[0113] A matching degree calculation submodule is configured to calculate the matching degree between the traffic slice to be scheduled and the cloud resource by using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resource;

[0114] The resource selection submodule is configured to select and bind target cloud resources based on the matching degree.

[0115] In one or more embodiments of this specification, the device further includes:

[0116] a first resource screening module configured to screen out, from the total set of cloud resources, cloud resources that are allowed to be used by the traffic scheduling unit where the traffic slice to be scheduled is located, to obtain a pre-screened resource set;

[0117] The second resource screening module is configured to screen out cloud resources that meet the resource capabilities required by the traffic slice to be scheduled from the primary screening resource set, and obtain the resource set to be evaluated.

[0118] Accordingly, the scheduling calculation module can be configured to calculate the matching degree between the traffic slice to be scheduled and the cloud resource to be evaluated by using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resource to be evaluated in the resource set to be evaluated.

[0119] In one or more embodiments of this specification, the device further includes:

[0120] The configuration module is configured to receive and save the configuration information set by the user for the traffic slice.

[0121] In one or more embodiments of this specification, the device further includes:

[0122] The compliance checking module is configured to check whether the resource scheduling information generated based on the target cloud resources is compliant based on preset policy compliance checking rules, and if compliant, enter the step of binding the target cloud resources.

[0123] The above is a schematic scheme of a cloud resource scheduling device of this embodiment. It should be noted that the technical scheme of the cloud resource scheduling device and the technical scheme of the cloud resource scheduling method described above are based on the same concept. For details not described in detail in the technical scheme of the cloud resource scheduling device, please refer to the description of the technical scheme of the cloud resource scheduling method described above.

[0124] Figure 6 6 shows a block diagram of a computing device 600 according to one embodiment of the present disclosure. Components of the computing device 600 include, but are not limited to, a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and a database 650 is used to store data.

[0125] The computing device 600 also includes an access device 640 that enables the computing device 600 to communicate via one or more networks 660. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)), whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0126] In one embodiment of the present specification, the above components of the computing device 600 and Figure 6 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 6 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0127] Computing device 600 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 600 can also be a mobile or stationary server.

[0128] The processor 620 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-mentioned cloud resource scheduling method.

[0129] The above is a schematic diagram of a computing device according to this embodiment. It should be noted that the technical solution of the computing device and the technical solution of the aforementioned cloud resource scheduling method are based on the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the aforementioned cloud resource scheduling method.

[0130] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned cloud resource scheduling method.

[0131] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of this storage medium and the technical scheme of the cloud resource scheduling method described above are based on the same concept. For details not described in detail in the technical scheme of the storage medium, please refer to the description of the technical scheme of the cloud resource scheduling method described above.

[0132] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned cloud resource scheduling method.

[0133] The above is an illustrative solution of a computer program of this embodiment. It should be noted that the technical solution of this computer program and the technical solution of the above-mentioned cloud resource scheduling method are based on the same concept. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the above-mentioned cloud resource scheduling method.

[0134] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0135] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may 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.

[0136] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0137] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0138] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A cloud resource scheduling system, comprising: A resource scheduling node is configured to pre-divide the traffic of the traffic scheduling unit into several traffic slices, monitor target events, select a traffic slice to be scheduled according to the target event in response to monitoring the target event, select and bind a target cloud resource for the traffic slice to be scheduled based on a preset resource scheduling algorithm, and generate resource scheduling information for the traffic slice to be scheduled based on the target cloud resource bound to the traffic slice to be scheduled, wherein the selecting and binding of the target cloud resource for the traffic slice to be scheduled based on the preset resource scheduling algorithm includes: using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resource to calculate the matching degree between the traffic slice to be scheduled and the cloud resource; based on the matching degree, selecting and binding the target cloud resource; The edge node is configured to receive traffic corresponding to the traffic slice and provide services based on the scheduling of the resource scheduling information.

2. A cloud resource scheduling method, comprising: Divide the traffic of the traffic scheduling unit into several traffic slices in advance; In response to detecting a target event, selecting a traffic slice to be scheduled according to the target event; Selecting and binding a target cloud resource for the traffic slice to be scheduled based on a preset resource scheduling algorithm, wherein the selecting and binding a target cloud resource for the traffic slice to be scheduled based on the preset resource scheduling algorithm includes: calculating a matching degree between the traffic slice to be scheduled and the cloud resource using configuration information of the traffic slice to be scheduled and configuration information of the cloud resource; and selecting and binding a target cloud resource based on the matching degree; Generate resource scheduling information for the traffic slice to be scheduled based on the target cloud resources bound to the traffic slice to be scheduled.

3. The method according to claim 2, further comprising: Receive plug-in and plug-out instructions from the event control algorithm; Based on the plug-in instruction, an event control algorithm is set for selecting a traffic slice to be scheduled according to a target event.

4. The method according to claim 2, further comprising: Receive plug-in and pull-out instructions from the resource scheduling algorithm; Based on the plug-in and pull-out instructions, a resource scheduling algorithm for selecting target cloud resources is set.

5. The method according to any one of claims 2 to 4, wherein the target event comprises: Nodes in the cloud computing network come online or offline; and / or, Whether the cloud resources bound to the traffic slice exceed the preset area; and / or, Whether the cloud resources bound to the traffic slice cannot meet the service requirements.

6. The method according to claim 2, before selecting and binding a target cloud resource for the traffic slice to be scheduled based on a preset resource scheduling algorithm, further comprising: Put the traffic slice to be scheduled into a priority queue according to the priority of the target event; According to the priority order of the traffic slices in the priority queue, the traffic slices to be scheduled are taken out from the priority queue, and the step of selecting and binding target cloud resources for the traffic slices to be scheduled based on the preset resource scheduling algorithm is entered.

7. The method according to claim 2, before calculating the matching degree between the traffic slice to be scheduled and the cloud resource using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resource, further comprising: Filtering, from the total set of cloud resources, cloud resources that are allowed to be used by the traffic scheduling unit where the traffic slice to be scheduled is located, to obtain a pre-screened resource set; According to the resource capacity required by the traffic slice to be scheduled, cloud resources that meet the resource capacity are screened from the pre-screened resource set to obtain a resource set to be evaluated; The calculating the matching degree between the traffic slice to be scheduled and the cloud resource by using the configuration information of the traffic slice to be scheduled and the cloud resource includes: The matching degree between the traffic slice to be scheduled and the cloud resource to be evaluated is calculated by using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resource to be evaluated in the resource set to be evaluated.

8. The method according to claim 2, further comprising: Receive and save the configuration information set by the user for the traffic slice.

9. The method according to claim 2, wherein the configuration information of the traffic slice comprises: The preset area, preset service type and / or cloud resource preference information of the traffic slice to be scheduled.

10. The method according to claim 2, before binding the target cloud resource, further comprising: Based on preset policy compliance checking rules, checking whether the resource scheduling information generated based on the target cloud resource is compliant; If it is compliant, proceed to the step of binding the target cloud resources.

11. A cloud resource scheduling device, comprising: a slicing module configured to pre-divide the traffic of the traffic scheduling unit into a plurality of traffic slices; a control module configured to, in response to detecting a target event, select a traffic slice to be scheduled according to the target event; A scheduling calculation module is configured to select and bind target cloud resources for the traffic slice to be scheduled based on a preset resource scheduling algorithm; The scheduling calculation module includes: A matching degree calculation submodule is configured to calculate the matching degree between the traffic slice to be scheduled and the cloud resource by using the configuration information of the traffic slice to be scheduled and the configuration information of the cloud resource; a resource selection submodule, configured to select and bind target cloud resources based on the matching degree; The policy generation module is configured to generate resource scheduling information for the traffic slice to be scheduled based on the target cloud resources bound to the traffic slice to be scheduled.

12. A computing device comprising: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the cloud resource scheduling method described in any one of claims 2 to 10 are implemented.

13. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the cloud resource scheduling method according to any one of claims 2 to 10.

14. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the cloud resource scheduling method according to any one of claims 2 to 10.

Images