CN115002117B - Content distribution network dynamic scheduling method, system, device and storage medium - Google Patents

Abstract

The present application discloses a content distribution network dynamic scheduling method, system, device and storage medium, the content distribution network dynamic scheduling method includes: obtaining trigger indicator items and custom scheduling rules configured according to business needs, generating several scheduling strategies based on the trigger indicator items and the custom scheduling rules, wherein the scheduling strategy includes scheduling business services, indicator trigger conditions and call-in node ranges, and if it is detected that the trigger indicator item corresponding to the target node meets the trigger condition, the scheduling strategy corresponding to the trigger condition is triggered and executed to schedule the scheduling business service of the target node to the call-in node in the call-in node range. The present application solves the technical problem that when business services change, it is necessary to use secondary development to schedule strategies to deal with new fault business scenarios, resulting in the inability to effectively accelerate user access requests, affecting the user experience.

Description

Content distribution network dynamic scheduling method, system, device and storage medium

Technical Field

The present application relates to the field of Internet technology, and in particular to a content distribution network dynamic scheduling method, system, device and storage medium.

Background technique

Currently, CDN (Content Delivery Network) provides acceleration services. Taking domain name access service as an example, the specific process is as follows: CDN plans CDN edge nodes according to geographical locations or network operators. When users access domain names, they can access domain names from edge nodes.

In the existing CDN cluster, each edge node is monitored by the corresponding monitoring equipment, and the operating status of the monitored edge node is reported to the scheduling system. When a certain edge node fails or the business volume of a service is too large, the service is scheduled to other available edge nodes nearby using a static fixed scheduling strategy. However, the static fixed scheduling strategy cannot adapt to changes in business services and has poor scalability. It requires secondary development to deal with new failure business scenarios, which results in the inability to effectively accelerate user access requests, affecting the user experience.

Summary of the invention

The main purpose of this application is to provide a content distribution network dynamic scheduling method, system, device and storage medium, aiming to solve the technical problem in the prior art that when business services change, secondary development is needed to schedule strategies to deal with new fault business scenarios, resulting in the inability to effectively accelerate user access requests, affecting the user experience.

To achieve the above-mentioned purpose, the present application provides a content distribution network dynamic scheduling method, the content distribution network dynamic scheduling method comprising:

Obtain trigger indicators and custom scheduling rules configured according to business needs;

Based on the trigger indicator item and the custom scheduling rule, a plurality of scheduling strategies are generated, wherein the scheduling strategy includes a scheduling business service, a trigger condition and a call-in node range;

If it is detected that the trigger indicator item corresponding to the target node meets the trigger condition, the scheduling policy corresponding to the trigger condition is triggered and executed to schedule the scheduling business service of the target node to the incoming node in the incoming node range.

The present application also provides a content distribution network dynamic scheduling system, wherein the content distribution network dynamic scheduling system is a virtual system, and the content distribution network dynamic scheduling system includes:

The acquisition module is used to obtain trigger indicator items and custom scheduling rules configured according to business needs;

A strategy generation module, used to generate a plurality of scheduling strategies based on the trigger indicator items and the custom scheduling rules, wherein the scheduling strategies include scheduling business services, indicator trigger conditions and call-in node ranges;

The policy execution module is used to trigger and execute the scheduling policy corresponding to the trigger condition if it is detected that the trigger indicator item corresponding to the target node meets the trigger condition, so as to schedule the scheduling business service of the target node to the incoming node in the incoming node range.

The present application also provides a content distribution network dynamic scheduling device, which is a physical device. The content distribution network dynamic scheduling device includes: a memory, a processor, and a content distribution network dynamic scheduling program stored on the memory. The content distribution network dynamic scheduling program is executed by the processor to implement the steps of the content distribution network dynamic scheduling method as described above.

The present application also provides a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores a content distribution network dynamic scheduling program, and the content distribution network dynamic scheduling program is executed by a processor to implement the steps of the content distribution network dynamic scheduling method as described above.

The present application provides a content distribution network dynamic scheduling method, system, device and storage medium. The present application first obtains trigger indicator items and custom scheduling rules configured according to business needs, and then generates several scheduling strategies based on the trigger indicator items and the custom scheduling rules, wherein the scheduling strategy includes scheduling business services, trigger conditions and call-in node ranges. Further, if it is detected that the trigger indicator item corresponding to the target node meets the trigger condition, the scheduling strategy corresponding to the trigger condition is triggered and executed to schedule the scheduling business service of the target node to the call-in node in the call-in node range, so that the scheduling rules and trigger indicator items set by the user can be customized based on actual business needs, so as to automatically generate scheduling strategies. Even if the service of the business needs changes, the scheduling rules and trigger indicator items corresponding to the new business can be set online. That is, the corresponding scheduling rules are used for scheduling for different businesses, which can meet the needs of each business and have a wider range of applicable scenarios. Then, when the trigger indicator item of the target node meets the trigger condition, the scheduling strategy is automatically triggered, so that the scheduling business service of the target node is scheduled to the call-in node in the call-in node range.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

FIG1 is a schematic diagram of a flow chart of a first embodiment of a method for dynamic scheduling of a content distribution network of the present application;

FIG2 is a flow chart of a second embodiment of a method for dynamic scheduling of a content distribution network according to the present application;

FIG3 is a schematic diagram of scheduling in the content distribution network dynamic scheduling method of the present application;

FIG4 is a schematic diagram of a content distribution network dynamic scheduling device structure in a hardware operating environment involved in an embodiment of the present application;

FIG. 5 is a schematic diagram of the functional modules of the content distribution network dynamic scheduling system of the present application.

The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings.

Detailed ways

It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

The present application provides a content distribution network dynamic scheduling method. In the first embodiment of the content distribution network dynamic scheduling method of the present application, referring to FIG. 1 , the content distribution network dynamic scheduling method includes:

Step S10, obtaining trigger indicator items and custom scheduling rules configured according to business requirements;

In this embodiment, it should be noted that the trigger indicator item is indicator information customized by the user, and the indicator information includes system indicator information, business indicator information and network indicator information, wherein the system indicator information includes information such as CPU, memory and disk, the business indicator information includes information such as the number of visits and access success rate of the business domain name, and the network indicator information includes network performance information such as access delay, download efficiency and throughput.

It should be further explained that the custom scheduling rules include the indicator threshold (that is, triggering condition) corresponding to the trigger indicator item, duration, policy impact range and scheduling business service, wherein the policy impact range is the regional scope to which the scheduling rules are applied. For example, the policy impact range can be set to a large region (divided by adjacent provinces), a province, or a specific node in the region. For example, when the policy impact range is Shenzhen City, the trigger indicator items of each node in the preset scheduling system in Shenzhen City are detected in real time. Furthermore, the scheduling business service can be understood as each specific service with the same or different service types. For example, a business domain name corresponds to a domain name access service, and different services can refer to different domain name access services.

The step of obtaining trigger indicator items and custom scheduling rules configured according to business requirements includes:

Step S11, obtaining historical indicator information corresponding to each node in the preset scheduling system, wherein the historical indicator information includes system indicator information, business indicator information and network indicator information of different business services;

Step S12, performing statistical aggregation processing on the system indicator information, the business indicator information and the network indicator information to obtain each integrated indicator information, and storing each integrated indicator information in a preset time series database;

Step S13: According to the business needs, at least one indicator item is selected from each integrated indicator information in the time series database as the trigger indicator item, and a custom scheduling rule set according to the trigger indicator item is obtained.

In this embodiment, as a feasible implementation method, specifically, in order to preset the indicator information of each node in the scheduling system, at least one monitoring device for monitoring the indicator information is set for each node, wherein a node can be understood as an edge server with an independent IP address that provides network services to the outside in the CDN cluster, or a group of servers that share an IP address to provide services to the outside, and then collect historical indicator information monitored by the monitoring device, wherein the historical indicator information includes system indicator information, business indicator information and network indicator information of different business services, and then according to the preset indicator processing strategy, the system indicator information, the business indicator information and the network indicator information are statistically aggregated and processed respectively to obtain each integrated indicator information, and each integrated indicator information is stored in a preset time series database, so that the integrated indicator information can be quickly queried in the preset time series database, for example, the number of visits per hour, access traffic, access success rate and access delay of a specific business service on the statistical node, and the number of visits, access success rate and access delay corresponding to each day can also be statistically aggregated.

Furthermore, according to actual business needs, at least one indicator item is selected from each integrated indicator information of the time series database as the trigger indicator item, and a custom scheduling rule set according to the trigger indicator item is obtained, so as to configure corresponding trigger indicator items and corresponding scheduling rules according to different business needs. For example, three indicator items of memory, access traffic and access latency of a specific business service are selected as trigger indicator items, and then corresponding scheduling rules are set for the three indicator items respectively.

Step S20, generating a plurality of scheduling strategies based on the trigger indicator item and the custom scheduling rule, wherein the scheduling strategy includes scheduling business services, trigger conditions and a call-in node range;

In this embodiment, it should be noted that the node range to be transferred in is the regional range to which the scheduling business service is transferred in, and the scheduling strategy specifically includes trigger indicator items, numerical judgments (equal to, greater than, less than, etc.), condition judgments (and, or, not, etc.), duration of conditions (for example, the trigger conditions are met for N consecutive statistical periods), and indicator item statistical dimensions (nodes, domain names, communication lines, etc.).

As a feasible implementation method, specifically, for example, three indicator items, namely, memory in the system indicator information of a specific business service, access traffic in the business indicator information, and access delay in the network indicator information, are selected as trigger indicator items, and then corresponding scheduling rules are set for the three indicator items respectively. A scheduling strategy can be formed based on combining the three indicator items with their corresponding scheduling rules, or a scheduling strategy can be generated for each indicator item and its corresponding scheduling rule, or multiple or all business services in a node can be combined, thereby realizing scheduling according to corresponding scheduling rules for different businesses, so as to meet the needs of each business. At the same time, it can also be determined whether a scheduling service is needed based on multiple indicators, namely, network indicator information, system indicator information and business indicator information.

In addition, after determining the scheduling strategy, each scheduling strategy is parsed to obtain a corresponding conditional expression, and each conditional expression is stored in a preset rule database, and subsequently the corresponding conditional expression can be directly scanned and executed in the preset rule database.

Step S30: If it is detected that the trigger indicator item corresponding to the target node meets the trigger condition, the scheduling strategy corresponding to the trigger condition is triggered and executed to schedule the scheduling business service of the target node to the incoming node in the incoming node range.

In this embodiment, it should be noted that the target node is a node that is within the policy influence range in the custom scheduling rule and that meets the trigger conditions. Specifically, after the scheduling policy is generated, the trigger indicator items of each target node within the policy influence range are detected in real time. When the trigger indicator items for scheduling business services on the target node all meet the trigger conditions, the scheduling policy corresponding to the trigger conditions is triggered and executed. Furthermore, when it is detected that the trigger indicator items of multiple target nodes all meet the trigger conditions in each of the conditional expressions, each of the scheduling policies is sorted according to a preset priority sorting rule to obtain a priority sorting sequence, and each scheduling policy is executed in sequence according to the priority sorting sequence. For example, the scheduling policy priority for node failure is set to 1, the scheduling policy priority for business traffic excess is set to 2, and the scheduling policy priority for poor business service network quality is set to 3. The smaller the number, the higher the priority.

Furthermore, in the process of triggering and executing the scheduling strategy, the scheduling business service of the target node is scheduled to the call-in node in the call-in node range. In one feasible implementation mode, since there are multiple nodes in the call-in node range, the remaining carrying business capacity of each node can be calculated, and then according to the size of each remaining carrying business capacity, the node with the largest remaining carrying business capacity is selected as the call-in node, thereby scheduling the scheduling business service to the call-in node. It should be noted that the call-in node range may belong to the same regional range as the target node, or may not belong to the same regional range as the target node. For example, if the target node that meets the trigger condition belongs to Shenzhen City, the call-in node range may be set in Shenzhen City, thereby scheduling the scheduling business service of the target node that meets the trigger condition to other nodes in Shenzhen City. When the call-in node range is set in Guangzhou City, the scheduling business service of the target node that meets the trigger condition is scheduled to its node in Guangzhou City.

If it is detected that the trigger indicator item corresponding to the target node meets the trigger condition, the scheduling strategy corresponding to the trigger condition is triggered and executed, specifically including:

Step S31, collecting trigger indicator items of each target node within the influence range of the strategy;

Step S32, when it is detected that the trigger indicator items of the plurality of target nodes all satisfy the trigger conditions in the conditional expressions, sorting the scheduling strategies according to a preset priority sorting rule to obtain a priority sorting sequence;

Step S33, executing each scheduling strategy in sequence according to the priority sorting sequence.

In this embodiment, specifically, the information corresponding to the trigger indicator items of each target node within the influence range of the strategy is detected in real time by a monitoring device. When it is detected that the trigger indicator items of the target node meet the trigger conditions in the conditional expression, the scheduling strategy for the trigger condition pair is directly triggered to execute. When it is detected that the trigger indicator items of multiple target nodes meet the trigger conditions in the conditional expression, the corresponding scheduling strategies need to be prioritized, and then each scheduling strategy is executed in sequence according to the priority sorting sequence.

The embodiment of the present application adopts the above scheme, that is, obtains trigger indicator items and custom scheduling rules configured according to business needs, and then generates several scheduling strategies based on the trigger indicator items and the custom scheduling rules, wherein the scheduling strategy includes scheduling business services, trigger conditions and call-in node ranges. Furthermore, if it is detected that the trigger indicator item corresponding to the target node satisfies the trigger condition, the scheduling strategy corresponding to the trigger condition is triggered and executed to schedule the scheduling business service of the target node to the call-in node in the call-in node range, so that the scheduling strategy can be automatically generated based on the custom-set scheduling rules and the custom-set trigger indicator items. Even if the business service changes, new scheduling rules and trigger indicator items can be set online, and the applicable scenarios are relatively wide. When the trigger indicator item of the target node satisfies the trigger condition, the scheduling strategy is automatically triggered, so that the scheduling business service of the target node is scheduled to the call-in node in the call-in node range.

Further, referring to FIG. 2 , based on the first embodiment of the present application, in another embodiment of the present application, after the step of scheduling the scheduling service of the target node to the incoming node in the incoming node range, it also includes:

Step A10, calculating the historical access traffic peak value of the scheduling business service on the target node within a preselected time based on the historical indicator information of the target node;

In this embodiment, it should be noted that the historical indicator information is system indicator information, business indicator information and network indicator information detected by the monitoring equipment, and the preset time is set manually according to the actual situation. For example, the preset time is set to 7 days. Specifically, based on the historical indicator information of the target node, the traffic peak of the scheduling business service on the target node is determined every day within the preselected time, and further, the traffic peak with the highest peak value is selected as the historical access traffic peak of the scheduling business service on the target node.

Step A20, after executing the dynamic scheduling strategy, detecting the node real-time bandwidth of the incoming node, and determining the remaining bearer service capacity of the incoming node;

Step A30, determining the outgoing access traffic based on the historical access traffic peak value and the node real-time bandwidth;

Step A40, based on the remaining bearer service capacity, determining whether the incoming node can bear the outgoing access traffic of the scheduling service;

Step A50, if yes, then determine that the scheduling is successful;

Step A60, if yes, determine the joining scheduling node based on other joining nodes in the joining node range; schedule the scheduling business service of the target node to the joining scheduling node according to the preset traffic scheduling method, and return to the execution step: after executing the dynamic scheduling strategy, detect the node real-time bandwidth of the joining node, and determine the remaining carrying business capacity of the joining node.

In this embodiment, specifically, after the scheduling business service of the target node is scheduled to the call-in node in the call-in node range, the node real-time bandwidth of the scheduling business service on the call-in node is detected in real time, and the outgoing access traffic is determined based on the size between the historical access traffic peak and the node real-time bandwidth. Further, based on the remaining carrying business capacity and the preset remaining ratio, it is determined whether the call-in node can carry the outgoing access traffic of the scheduling business service. If so, it is determined that the scheduling is successful, and then the scheduling business service is scheduled to the call-in node. If not, based on other call-in nodes in the call-in node range, a joining scheduling node is selected, and the scheduling business service of the target node is scheduled to the newly added joining scheduling node and the scheduling node respectively according to the preset traffic scheduling method. For example, the outgoing access traffic of the scheduling business service is evenly distributed to the joining scheduling node and the scheduling node, or according to The preset allocation ratio evenly distributes the outgoing access traffic of the scheduling business service to the joining scheduling node and the scheduling node. The preset allocation ratio can be set according to the actual situation and is not specifically limited here. Then return to the execution step: after executing the dynamic scheduling strategy, detect the node real-time bandwidth of the calling-in node, and determine the remaining carrying service capacity of the calling-in node, so as to further judge whether the calling-in node and the joining scheduling node can carry the outgoing access traffic of the scheduling business service, until all the calling-in nodes in the calling-in node range are added or the calling-in access traffic carrying the scheduling business service is determined. For example, the historical access traffic peak is A, the node real-time bandwidth is B, and the remaining carrying service capacity of the calling-in node is recorded as C. The proportion to be reserved (the preset remaining proportion) is a (0<=a<=1). If max(A, B)<=C*(1-a), it means that the calling-in node and the joining scheduling node can carry the calling-out access traffic of the scheduling business service.

Wherein, after the step of dispatching the dispatching service of the target node to the joining dispatching node according to the preset traffic dispatching method and returning to the execution step: after executing the dynamic dispatching strategy, detecting the node real-time bandwidth of the incoming node, and determining the remaining bearer service capacity of the incoming node, it also includes;

Step b: If it is detected that the remaining bearer service capacity corresponding to all the incoming nodes in the incoming node range cannot bear the outgoing access traffic of the scheduling service, it is determined that the scheduling policy scheduling fails and a warning message is issued.

In this embodiment, specifically, the party detects that all incoming nodes cannot carry the outgoing access traffic of the scheduling business service, determines that the scheduling policy scheduling fails, and issues a warning message to remind the user to modify the scheduling policy.

Through the above scheme, the embodiment of the present application fully considers the carrying capacity of the incoming node when executing the scheduling strategy, avoiding the chain problem of response failure or slow response and the spread of faulty nodes when users access the service due to the faulty incoming node exceeding the carrying capacity of the incoming node.

Refer to Figure 3, which is a scheduling principle diagram for the content distribution network dynamic scheduling method of the present application, wherein 01 is the policy influence range, which includes three nodes A, B and C, 02 is the call-in node range, which includes four call-in nodes D, E, F and G, and the trigger index items of each node within the policy influence range are detected in real time. When it is detected that the trigger index item of the C node meets the trigger condition, the corresponding scheduling strategy is triggered and executed. The C node within the call-in node range can be randomly selected as the call-in node, and then the scheduling business service of the A node can be scheduled to the C node, or based on the remaining carrying capacity of each node within the call-in node range, the node with the highest remaining carrying capacity is selected as the call-in node. Node, assuming that the relationship between the remaining carrying capacity is: D>E>F>G. Further, during the scheduling process, determine whether the remaining carrying capacity of the current incoming node can carry the outgoing business traffic of the scheduled business service on node A. If it can, the scheduling is determined to be successful. If it cannot, continue to select E node from the incoming node range, and then schedule the scheduled business service on node A to nodes C and E, and return to the step of determining whether it can carry the outgoing business traffic of the scheduled business service on node A, until all nodes within the incoming node range are added. If all nodes within the incoming node range still cannot carry the outgoing business traffic of the scheduled business service on node A, the scheduling is determined to have failed, and an alarm message is issued.

Refer to Figure 4, which is a schematic diagram of the structure of a content distribution network dynamic scheduling device in a hardware operating environment involved in an embodiment of the present application.

As shown in FIG4 , the content distribution network dynamic scheduling device may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to realize the connection and communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

Optionally, the content distribution network dynamic scheduling device may also include a rectangular user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, etc. The rectangular user interface may include a display screen (Display), an input submodule such as a keyboard (Keyboard), and the optional rectangular user interface may also include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a WIFI interface).

Those skilled in the art will appreciate that the content distribution network dynamic scheduling device structure shown in FIG. 4 does not constitute a limitation on the content distribution network dynamic scheduling device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

As shown in FIG4 , the memory 1005 as a computer storage medium may include an operating system, a network communication module, and a content distribution network dynamic scheduling program. The operating system is a program that manages and controls the hardware and software resources of the content distribution network dynamic scheduling device, and supports the operation of the content distribution network dynamic scheduling program and other software and/or programs. The network communication module is used to realize the communication between the components inside the memory 1005, and to communicate with other hardware and software in the content distribution network dynamic scheduling system.

In the content distribution network dynamic scheduling device shown in FIG. 4 , the processor 1001 is used to execute the content distribution network dynamic scheduling program stored in the memory 1005 to implement the steps of any of the above-mentioned content distribution network dynamic scheduling methods.

The specific implementation of the content distribution network dynamic scheduling device of the present application is basically the same as the embodiments of the content distribution network dynamic scheduling method described above, and will not be repeated here.

In addition, please refer to FIG. 5 , which is a schematic diagram of the functional modules of the content distribution network dynamic scheduling system of the present application. The present application also provides a content distribution network dynamic scheduling system, and the content distribution network dynamic scheduling system includes:

The acquisition module is used to obtain trigger indicator items and custom scheduling rules configured according to business needs;

A strategy generation module, used to generate a plurality of scheduling strategies based on the trigger indicator items and the custom scheduling rules, wherein the scheduling strategies include scheduling business services, indicator trigger conditions and call-in node ranges;

The policy execution module is used to trigger and execute the scheduling policy corresponding to the trigger condition if it is detected that the trigger indicator item corresponding to the target node meets the trigger condition, so as to schedule the scheduling business service of the target node to the incoming node in the incoming node range.

Optionally, the acquisition module is further used for:

Obtaining historical indicator information corresponding to each node in the preset scheduling system, wherein the historical indicator information includes system indicator information, business indicator information and network indicator information of different business services;

Performing statistical aggregation processing on the system indicator information, the service indicator information and the network indicator information to obtain each integrated indicator information, and storing each integrated indicator information in a preset time series database;

According to the business requirements, at least one indicator item is selected from each integrated indicator information in the time series database as the trigger indicator item, and a custom scheduling rule set according to the trigger indicator item is obtained.

Optionally, the content distribution network dynamic scheduling system is further used for:

Based on the historical indicator information of the target node, calculate the historical access traffic peak value of the scheduling business service on the target node within a preselected time;

After executing the dynamic scheduling strategy, detecting the node real-time bandwidth of the incoming node, and determining the remaining bearer service capacity of the incoming node;

Determine the outgoing access traffic based on the historical access traffic peak value and the node real-time bandwidth;

Based on the remaining bearer service capacity, determining whether the incoming node can bear the outgoing access traffic of the scheduling service;

If so, it is determined that the scheduling is successful;

If not, determine the joining scheduling node based on other joining nodes in the joining node range; schedule the scheduling business service of the target node to the joining scheduling node according to the preset traffic scheduling method, and return to the execution step: after executing the dynamic scheduling strategy, detect the node real-time bandwidth of the joining node, and determine the remaining carrying business capacity of the joining node.

Optionally, the content distribution network dynamic scheduling system is further used for:

If it is detected that the remaining bearer service capacity corresponding to all the incoming nodes in the incoming node range cannot bear the outgoing access traffic of the scheduling service, it is determined that the scheduling policy scheduling fails and a warning message is issued.

Optionally, the content distribution network dynamic scheduling system is further used for:

Each of the scheduling strategies is parsed to obtain a corresponding conditional expression, and each of the conditional expressions is stored in a preset rule database.

Optionally, the policy execution module is further used to:

Collect trigger indicator items of each target node within the scope of influence of the strategy;

When it is detected that the trigger indicator items of several target nodes all satisfy the trigger conditions in the conditional expressions, sorting the scheduling strategies according to the preset priority sorting rules to obtain a priority sorting sequence;

Each scheduling strategy will be executed in turn according to the priority sorting sequence.

The specific implementation of the content distribution network dynamic scheduling system of the present application is basically the same as the various embodiments of the content distribution network dynamic scheduling method described above, and will not be repeated here.

An embodiment of the present application provides a storage medium, which is a computer-readable storage medium, and the computer-readable storage medium stores one or more programs, and the one or more programs can also be executed by one or more processors to implement the steps of the content distribution network dynamic scheduling method described in any one of the above items.

The specific implementation of the computer-readable storage medium of the present application is basically the same as the embodiments of the above-mentioned content distribution network dynamic scheduling method, and will not be repeated here.

The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims (9)

1. A method for dynamically scheduling a content distribution network, the method comprising:

acquiring a trigger index item configured according to service requirements and a custom scheduling rule;

generating a plurality of scheduling strategies based on the triggering index items and the self-defined scheduling rules, wherein the scheduling strategies comprise scheduling business services, triggering conditions and scheduling node ranges;

Triggering and executing a scheduling strategy corresponding to the triggering condition when the triggering index item corresponding to the target node is detected to meet the triggering condition, so as to schedule the scheduling service of the target node to a scheduling node in the range of the scheduling node;

the step of obtaining the trigger index item and the custom scheduling rule configured according to the service requirement comprises the following steps:

Acquiring historical index information corresponding to each node in a preset scheduling system, wherein the historical index information comprises system index information, business index information and network index information of different business services;

carrying out statistical aggregation processing on the system index information, the business index information and the network index information to obtain each piece of integrated index information, and storing each piece of integrated index information in a preset time sequence database;

And according to the service demand, at least one index item is selected from the integrated index information of the time sequence database as the trigger index item, and a self-defined scheduling rule set according to the trigger index item is obtained.

2. The method of dynamic scheduling of a content distribution network according to claim 1, further comprising, after the step of scheduling the scheduled traffic service of the target node into a scheduling node in the range of scheduling nodes:

calculating a historical access flow peak of the scheduling business service on the target node in a preselected time based on the historical index information of the target node;

after executing the dynamic scheduling strategy, detecting the node real-time bandwidth of the scheduling node, and determining the residual bearing service capacity of the scheduling node;

determining call-out access flow based on the magnitude between the historical access flow peak value and the node real-time bandwidth;

judging whether the calling-in node can bear calling-out access flow of the dispatching business service or not based on the residual bearing business capacity;

If yes, determining that the dispatching is successful;

If not, determining to add a scheduling node based on other scheduling nodes in the range of the scheduling node; scheduling the scheduling service of the target node to the joining scheduling node according to a preset traffic scheduling method, and returning to the execution step: after executing the dynamic scheduling policy, detecting the node real-time bandwidth of the scheduling node, and determining the residual bearing service capacity of the scheduling node.

3. The dynamic scheduling method of content delivery network according to claim 2, wherein, when the scheduling service of the target node is scheduled to the joining scheduling node according to a preset traffic scheduling method, the execution step is returned to: after the step of detecting the node real-time bandwidth of the scheduling node and determining the remaining bearer service capacity of the scheduling node after executing the dynamic scheduling policy, the method further comprises:

If the residual bearing service capacity corresponding to all the calling nodes in the calling node range is detected to be unable to bear the calling access flow of the dispatching service, determining that the dispatching strategy fails to dispatch, and sending out warning information.

4. The method for dynamic scheduling of a content distribution network according to claim 1, further comprising, after the step of generating a plurality of scheduling policies based on the trigger metrics and the custom scheduling rules:

Analyzing each scheduling strategy to obtain a corresponding conditional expression, and storing each conditional expression into a preset rule database.

5. The method for dynamic scheduling of a content distribution network according to claim 4, wherein the scheduling policy further comprises a policy scope of influence.

6. The method for dynamic scheduling of a content distribution network according to claim 5, wherein when it is detected that the trigger indicator item corresponding to the target node satisfies the trigger condition, the step of triggering and executing the scheduling policy corresponding to the trigger condition includes:

collecting trigger index items of all target nodes in the policy influence range;

When detecting that the trigger index items of a plurality of target nodes all meet the trigger conditions in the conditional expressions, sequencing the scheduling strategies according to a preset priority sequencing rule to obtain a priority sequencing sequence;

And executing each scheduling strategy in turn according to the priority ordering sequence.

7. A content distribution network dynamic scheduling system, the content distribution network dynamic scheduling system comprising:

the acquisition module is used for acquiring the trigger index item configured according to the service requirement and the custom scheduling rule;

The strategy generation module is used for generating a plurality of scheduling strategies based on the trigger index item and the custom scheduling rule, wherein the scheduling strategies comprise scheduling business service, index trigger conditions and a scheduling node range;

the strategy execution module is used for triggering and executing a scheduling strategy corresponding to the triggering condition when the triggering index item corresponding to the target node is detected to meet the triggering condition, so as to schedule the scheduling service of the target node to the scheduling node in the range of the scheduling node;

The acquisition module is further used for acquiring historical index information corresponding to each node in a preset scheduling system, wherein the historical index information comprises system index information, business index information and network index information of different business services;

carrying out statistical aggregation processing on the system index information, the business index information and the network index information to obtain each piece of integrated index information, and storing each piece of integrated index information in a preset time sequence database;

And according to the service demand, at least one index item is selected from the integrated index information of the time sequence database as the trigger index item, and a self-defined scheduling rule set according to the trigger index item is obtained.

8. A content distribution network dynamic scheduling apparatus, characterized in that the content distribution network dynamic scheduling apparatus comprises: memory, a processor and a content distribution network dynamic scheduler stored on the memory,

The content distribution network dynamic scheduling program performs the steps of implementing the content distribution network dynamic scheduling method according to any one of claims 1 to 6 by the processor.

9. A storage medium, which is a computer readable storage medium, wherein a content distribution network dynamic scheduler is stored on the computer readable storage medium, the content distribution network dynamic scheduler being executed by a processor to implement the steps of the content distribution network dynamic scheduling method according to any one of claims 1 to 6.