WO2022166609A1

WO2022166609A1 - Service scheduling method and apparatus, device, and storage medium

Info

Publication number: WO2022166609A1
Application number: PCT/CN2022/073053
Authority: WO
Inventors: 杨涛
Original assignee: 北京金山云网络技术有限公司
Priority date: 2021-02-02
Filing date: 2022-01-20
Publication date: 2022-08-11
Also published as: CN114844949B; CN114844949A

Abstract

The present disclosure relates to a service scheduling method and apparatus, a device, and a storage medium. The method comprises: after receiving a service request of a client, a first edge node in a CDN determining, at least according to the current bandwidth value thereof and a cost bandwidth value thereof, whether the service request needs to be re-scheduled; when re-scheduling is required, requesting, from a central service platform, the remaining bandwidth and the quality of service of at least one second edge node on the basis of an IP address and a service type that are carried in the service request; and re-scheduling the service request onto one or more second edge nodes according to the requested remaining bandwidth and quality of service of the at least one second edge node. By means of the method provided in embodiments of the present disclosure, refined control over a CDN cost can be realized, and the quality of service can be improved.

Description

Service scheduling method, device, equipment and storage medium

This disclosure claims the priority of the Chinese patent application with the application number 202110143761.2 filed on February 2, 2021 and the invention title is "service scheduling method, apparatus, device and storage medium", the entire contents of which are incorporated in this disclosure by reference.

technical field

The embodiments of the present disclosure relate to the field of CDN technologies, and in particular, to a service scheduling method, apparatus, device, and storage medium.

Background technique

In a Content Delivery Network (CDN), the central scheduling device can schedule edge nodes that are closer to users to provide services to users. However, different scheduling methods have different effects on the quality and cost of CDN services. Therefore, how to take into account the quality and/or cost of CDN services in the scheduling process is a technical problem to be solved by those skilled in the art.

SUMMARY OF THE INVENTION

(1) Technical problems to be solved

In order to solve the above technical problem or at least partially solve the above technical problem, the embodiments of the present disclosure provide a service scheduling method, apparatus, device, and storage medium.

(2) Technical solutions

A first aspect of the embodiments of the present disclosure provides a service scheduling method, which is applicable to a content delivery network (Content Delivery Network, CDN for short), wherein the CDN includes a method for periodically determining each edge node in the CDN The service quality and cost bandwidth value of the central service platform, the cost bandwidth value refers to the bandwidth value when the cost of the edge node is optimal, the method includes the first edge node in the CDN receiving the service request of the client, so The service request includes the service type and the IP address of the client; at least according to its current bandwidth value and cost bandwidth value, determine whether the service request needs to be rescheduled; if so, based on the IP address and the service type Request from the central service platform the bandwidth margin and service quality of at least one second edge node that belongs to the same area as the client and matches the service type, wherein the bandwidth margin refers to the The difference between the cost bandwidth value of the second edge node and the current bandwidth value of the second edge node; according to the bandwidth margin and service quality of the at least one second edge node, reschedule the service request to one or more on multiple second edge nodes.

A second aspect of the embodiments of the present disclosure provides a service scheduling apparatus, the service scheduling apparatus is set in a first edge node of a CDN, and the CDN includes a device for periodically determining the service quality of each edge node in the CDN and a central service platform for cost bandwidth value, the service scheduling device includes: a receiving module for receiving a service request from a client, the service request including the service type and the IP address of the client; a judging module for at least according to The current bandwidth value of the first edge node and the current cost bandwidth value of the first edge node are used to determine whether the service request needs to be rescheduled; the request module is used to determine whether the service request needs to be rescheduled. During scheduling, based on the IP address and the service type, request the central service platform for the bandwidth margin and service of at least one second edge node that belongs to the same area as the client and matches the service type. quality, wherein the bandwidth margin refers to the difference between the cost bandwidth value of the second edge node and the current bandwidth value of the second edge node; the execution module, according to the at least one second edge node the bandwidth margin and service quality, and reschedule the service request to one or more second edge nodes.

A third aspect of the embodiments of the present disclosure provides an edge node, including a memory and a processor, wherein the memory includes a computer program, and when the computer program is executed by the processor, the processor can execute The method described in the first aspect above.

A fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium, where a computer program is stored in the storage medium, and when the computer program is executed by a processor, the processor causes the processor to execute the above-mentioned first aspect. Methods.

(3) Beneficial effects

Compared with the related art, the above technical solutions provided by the embodiments of the present disclosure have the following advantages:

The embodiment of the present disclosure regularly determines the service quality and cost bandwidth value of each edge node in the CDN through the central service platform. When the first edge node in the CDN receives the service request from the client, the first edge node judges whether the service request needs to be rescheduled at least according to its current bandwidth value and cost bandwidth value, and when judging that rescheduling is necessary, Based on the IP address and service type carried in the service request, request from the central service platform at least one second edge node that belongs to the same area as the client and matches the service type requested by the client for the bandwidth margin and service quality of the second edge node. According to the requested bandwidth margin and service quality of the at least one second edge node, the service request is rescheduled to one or more of the second edge nodes. Different from the central 302 scheduling method and the Domain Name System (Domain Name System, DNS for short) scheduling method provided by the related art, the first edge node in the embodiment of the present disclosure does not acquiesce by itself after receiving the service request from the client. To process the service request, it will judge whether it needs to be rescheduled according to its current actual bandwidth and its own cost bandwidth. When it is judged that it needs to be rescheduled, it will request the central service platform for at least one second edge node. and service quality, and reschedules the service request to other edge nodes according to the requested margin and service quality of the at least one second edge node. This scheduling method not only meets the service scheduling requirements of the CDN, but also takes into account the cost and service quality of each edge node in the CDN, thereby realizing the refined control of the CDN cost and ensuring the service quality of the CDN.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

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

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the accompanying drawings required for describing the embodiments or related technologies will be briefly introduced below. Obviously, for those skilled in the art, On the premise of no creative labor, other drawings can also be obtained from these drawings.

1 is a flowchart of a service scheduling method provided by an embodiment of the present disclosure;

FIG. 2 is a network architecture diagram of a CDN provided by an embodiment of the present disclosure;

3 is a flowchart of another service scheduling method provided by an embodiment of the present disclosure;

4 is a flowchart of another service scheduling method provided by an embodiment of the present disclosure;

5 is a schematic structural diagram of a service scheduling apparatus provided by an embodiment of the present disclosure;

FIG. 6 is a schematic structural diagram of an edge node provided by an embodiment of the present disclosure.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than All examples. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

For the convenience of understanding, some professional terms involved in the embodiments of the present disclosure will be explained below first:

Edge node: An edge node refers to a business platform built on the edge side of the network close to users to provide users with resources such as storage, computing, and networks.

Cost bandwidth value, the cost bandwidth value of the edge node refers to the bandwidth value when the edge node obtains the optimal cost. The cost bandwidth value is related to the charging mode of the edge node. When the charging mode is determined, the cost bandwidth value of the edge node can be calculated based on the charging mode. For the calculation method of the cost bandwidth value, refer to the related art, which will not be repeated here.

Bandwidth margin, the bandwidth margin of the edge node refers to the difference between the cost bandwidth value of the edge node and the actual bandwidth value of the edge node.

In the related art, the service scheduling methods of CDN mainly include the following two:

1. DNS scheduling method

In the DNS scheduling mode, the client's service request is first sent to the local DNS system. According to the service request, the local DNS system requests the central scheduling device of the CDN for the address of the edge node for processing the service request, and feeds back the address of the edge node to the client. After the client receives the address of the edge node, it initiates a service request to the edge node, so that the edge node provides a business service for the client.

However, in the DNS scheduling method, there are often problems such as domain name hijacking, inaccurate or untimely scheduling, etc. These problems bring certain uncontrollability to the service quality and cost of CDN.

2. Central 302 scheduling method

In the central 302 scheduling mode, the client's service request is first sent to the local DNS system, and the local DNS system requests the address of the central scheduling device from the DNS system dedicated to the CDN service operator according to the service request, and then feeds back the address of the central scheduling device. to the client. After receiving the address of the central dispatching device, the client sends a service request to the central dispatching device according to the address. After receiving the client's service request, the central scheduling device allocates an edge node in the same area as the client according to the client's IP address to process the client's service request, and feeds back the address of the edge node to the client. The edge node re-initiates the service request.

In the central 302 scheduling method, the service scheduling lacks the perception of the cost and service quality of edge nodes, and there are problems that the cost cannot be controlled in a refined manner and the service quality cannot be guaranteed. In addition, after the central scheduling device schedules the client's business to an edge node, the edge node will generally provide services for the client by itself by default, and will not perform 302 scheduling again, so there is a problem of a single scheduling path.

In view of the above problems existing in the related art, the embodiments of the present disclosure provide a service scheduling solution applicable to CDN. This solution innovatively sets up a central service platform in the CDN. The central service platform can periodically determine the service quality and cost bandwidth value of each edge node in the CDN, and the edge nodes in the CDN need to reschedule service requests ( 302 scheduling), provide the edge node with the service quality data and bandwidth margin data of other edge nodes, so that the edge node can reschedule the service request to one or more other edge nodes according to the service quality and bandwidth margin of other edge nodes. on edge nodes.

Illustratively, FIG. 1 is a flowchart of a service scheduling method provided by an embodiment of the present disclosure. As shown in FIG. 1 , the method may include the following steps:

Step 101: A first edge node in the CDN receives a service request from a client, where the service request includes a service type and an IP address of the client.

Step 102: The first edge node determines whether the service request needs to be rescheduled according to at least its own current bandwidth value and cost bandwidth value, and if so, step 103 is performed.

Step 103: Based on the IP address and the service type in the service request, the first edge node requests the central service platform for the bandwidth margin of at least one second edge node that belongs to the same area as the client and matches the service type requested by the client. and business quality.

Step 104: The first edge node reschedules the service request of the client to one or more second edge nodes according to the bandwidth margin and service quality of the at least one second edge node obtained by the request.

The names of "first edge node" and "second edge node" in this embodiment are only for convenience of distinction and have no other meaning.

By way of example, FIG. 2 is a network architecture diagram of a CDN provided by an embodiment of the present disclosure. As shown in FIG. 2 , the CDN network architecture of FIG. 2 at least includes a client, a local DNS, a DNS dedicated to the CDN, and a central scheduling device. , a central service platform and N edge nodes, where N is an integer greater than 1. Among them, the charging methods of the N edge nodes may be the same or different, and the charging methods of each edge node are not fixed, but can be adjusted according to needs, such as using different charging methods in different time periods.

In the embodiment of the present disclosure, the central service platform determines data such as cost bandwidth value and service quality of each edge node according to a preset period, and feeds back the cost bandwidth value and service quality of the edge node to the edge node. There are various methods for the central server to determine the cost bandwidth value and service quality of each edge node:

For example, in one embodiment, an edge node may be configured to periodically update its own billing method, real-time bandwidth value, and quality parameters of multiple dimensions (for example, 4XX, 5XX, stall rate and other parameters) are reported to the central service platform. After receiving the data, the central service platform calculates the cost bandwidth value and service quality of the edge node based on the data. Wherein, the cost bandwidth value of the edge node may be calculated based on the charging mode of the edge node using a first preset algorithm corresponding to the charging mode. The service quality of the edge node can be calculated based on the quality parameter reported by the edge node using the second preset algorithm, wherein the first preset algorithm and the second preset algorithm can be set as required, and need not be limited to a certain one specific algorithm. For example, when the second preset algorithm is specifically a weighted summation algorithm, the central service platform may first perform weighting processing on the quality parameters of each dimension according to the weights corresponding to the quality parameters of each dimension, and then perform weighting on the weighted quality parameters. The summation process is performed, and the result of the summation process is used as the service quality of the edge node.

For another example, in another implementation of the embodiment of the present disclosure, the central server may also measure parameters such as 4XX, 5XX, and stall rate by periodically sending test data to edge nodes, and then calculate based on these parameters. Obtain the service quality of the edge node. Similarly, the billing method and real-time bandwidth value of the edge node can also be obtained from the edge node by periodically sending request messages, and then the cost bandwidth value of the edge node can be calculated based on the obtained billing method. Based on the obtained real-time bandwidth value and cost bandwidth value, the bandwidth margin of the edge node is calculated.

It should be noted that in order to reduce the computing pressure of edge nodes, the embodiments of the present disclosure exemplarily integrate the computing capabilities of cost bandwidth value and service quality on the central service platform, and in other embodiments, if the computing power of edge nodes is not considered pressure, the computing power can also be integrated on the edge node, that is, the edge node regularly calculates its own cost bandwidth value and service quality, and reports the calculated cost bandwidth value and service quality to the central service platform for storage. The method for the node to calculate the cost bandwidth value and the quality of service is similar to the above method, and will not be repeated here.

Referring to FIG. 2 , based on the bandwidth margin data and cost bandwidth value data periodically obtained by the above-mentioned central service platform, the service scheduling method of this embodiment can be described as follows:

The client first sends a service request to the local DNS, and the service request includes the client's IP address and the requested service type. The local DNS obtains the address of the central dispatching device from the DNS dedicated to the CDN, and feeds the address back to the client. The client sends a service request to the central dispatching device based on the address. The central dispatching device determines the IP address of the client and the requested service type. The address of the edge node 1 (ie, the first edge node) that supports the service type and is closest to the client is fed back to the client, and the client sends a service request to the edge node 1 according to the address of the edge node 1.

After receiving the service request from the client, the edge node 1 judges whether the service request needs to be rescheduled according to at least its own current bandwidth value and cost bandwidth value. Among them, there are various methods for judging whether rescheduling is required according to the current bandwidth value and cost bandwidth value. For example, in a feasible judgment method, edge node 1 can compare its current bandwidth value with its current cost bandwidth value. , if its current bandwidth value is greater than or equal to its current cost bandwidth value, that is, its current bandwidth value has exceeded the optimal cost bandwidth value, it is determined that the client's service request needs to be rescheduled. For another example, in another feasible judgment method, the difference between the current cost bandwidth value and the current actual bandwidth value of the user can be obtained to obtain the bandwidth margin, and then the calculated bandwidth margin can be compared with the preset value. If the calculated bandwidth margin is less than the first bandwidth threshold, it is determined that the service request of the client needs to be rescheduled, otherwise it is determined that rescheduling is not required. In this judgment method, by setting the first bandwidth threshold, it can be ensured that the edge node will not cause the bandwidth to exceed the cost bandwidth value due to processing the service request of the client, thereby realizing fine control of the cost. It should be noted that the above two judging methods are only exemplary descriptions, rather than unique limitations. In fact, the methods for judging whether rescheduling is required based on the bandwidth value and the cost bandwidth value can be set as required.

In some embodiments, if the client's service request needs to be rescheduled, the edge node 1 will carry the client's IP address and the service type requested by the client in the request message, and request the central service platform for other edge nodes in the CDN. Bandwidth margin and quality of service. Wherein, after receiving the request from the edge node 1, the central service platform can process at least one of the following processing methods:

In the first processing method, edge nodes that are in the same area as the client and match the service type requested by the client are selected from the CDN according to the client's IP address and the requested service type. Then, the bandwidth margin and service quality of at least one edge node (ie, at least one second edge node) among these edge nodes are fed back to edge node 1 . The edge node that matches the service type requested by the client, for example, can be understood as an edge node that can support the service type.

In the second processing method, the central service platform selects the edge nodes that are in the same area as the client and matches the service type requested by the client from all the edge nodes, and then compares the bandwidth margin and the bandwidth margin among these edge nodes. The bandwidth margin and service quality of at least one edge node (ie, at least one second edge node) whose service quality is greater than the preset value are fed back to edge node 1 . However, if there is no edge node in the CDN whose bandwidth margin and service quality are greater than the preset value, the processing is performed according to the first processing method.

In some embodiments, after requesting the bandwidth margin and service quality of the at least one second edge node from the central service platform, the edge node 1 can at least use one of the following methods to reschedule the service request of the client :

In a scheduling method, after requesting bandwidth headroom and service quality from at least one second edge node, edge node 1 first determines from these second edge nodes that the bandwidth headroom is greater than or equal to a second bandwidth threshold, and the service The edge nodes whose quality is greater than or equal to the quality threshold corresponding to the service type requested by the client, then request the addresses of these edge nodes from the central scheduling device, and feed back the addresses of these edge nodes to the client, so that the client can send these Edge nodes send service requests. However, if the requested second edge node does not have an edge node whose bandwidth margin is greater than or equal to the second bandwidth threshold and whose service quality is greater than or equal to the quality threshold corresponding to the service type requested by the client, the Perform weighted summation processing on the quality of service and bandwidth margin of the second edge node to obtain the weighted summation result corresponding to each second edge node, and then request the central scheduling device for the third edge whose weighted summation result is greater than the first preset threshold. address of the second edge node, and send the requested address to the client, so that the client re-initiates the service request according to these addresses.

In another scheduling method, after requesting the bandwidth margin and service quality of the at least one second edge node, the edge node 1 may first determine from the requested at least one second edge node that the bandwidth margin is greater than or equal to is equal to the second bandwidth threshold, and the second edge node whose service quality is greater than or equal to the quality threshold corresponding to the service type requested by the client is regarded as a candidate edge node; then the service quality and bandwidth margin of each candidate edge node are weighted to calculate and processing, and use the candidate edge node whose weighted summation result is greater than the second preset threshold as the target edge node, request the address of the target edge node from the central scheduling device, and feed back the address of the target edge node to the client, so that the client The service request of the terminal is rescheduled to the target edge node.

It should be noted that although only two scheduling methods are provided above, the scheduling methods in this embodiment are not limited to the above two, but can be set as required. In fact, any service rescheduling method that can be implemented based on the bandwidth margin and/or service quality of the edge node can be applied to the solutions of the embodiments of the present disclosure.

The embodiment of the present disclosure regularly determines the service quality and cost bandwidth value of each edge node in the CDN through the central service platform. When the first edge node in the CDN receives the service request from the client, the first edge node judges whether the service request needs to be rescheduled at least according to its current bandwidth value and cost bandwidth value, and when judging that rescheduling is necessary, Based on the IP address and service type carried in the service request, request from the central service platform at least one second edge node that belongs to the same area as the client and matches the service type requested by the client for the bandwidth margin and service quality of the second edge node. The service request is rescheduled to one or more of the second edge nodes according to the requested bandwidth margin and service quality of the at least one second edge node. Different from the central 302 scheduling method and the Domain Name System (Domain Name System, DNS for short) scheduling method provided by the related art, the first edge node in the embodiment of the present disclosure does not acquiesce by itself after receiving the service request from the client. To process the service request, it will judge whether it needs to be rescheduled according to its current actual bandwidth and its own cost bandwidth. When it is judged that it needs to be rescheduled, it will request the central service platform for at least one second edge node. and service quality, and reschedules the service request to other edge nodes according to the requested margin and service quality of the at least one second edge node. This scheduling method not only meets the service scheduling requirements of the CDN, but also takes into account the cost and service quality of each edge node in the CDN, thereby realizing the refined control of the CDN cost and ensuring the service quality of the CDN.

Illustratively, FIG. 3 is a flowchart of another service scheduling method provided by an embodiment of the present disclosure. As shown in FIG. 3 , the method includes:

Step 301, the first edge node in the CDN receives the service request of the client, and the service request includes the service type and the IP address of the client:

Step 302: The first edge node determines a bandwidth value after a preset time based on its own current bandwidth value and its own bandwidth change trend obtained in advance.

In this embodiment, the bandwidth change trend of the edge node can be obtained by the edge node itself. For example, the edge node in the CDN can be configured to collect its own real-time bandwidth value every preset time period, and then periodically A real-time bandwidth value is statistically processed to obtain the real-time bandwidth variation trend of edge nodes. After the first edge node receives the service request from the client, it predicts and obtains the bandwidth value after the preset time according to the newly obtained bandwidth change trend and its own current bandwidth value.

Step 303: The first edge node judges whether the bandwidth value after the preset time is greater than or equal to its current cost bandwidth value, and if so, executes step 304.

For example, assuming that the cost bandwidth of the first edge node is 10GB, and based on the pre-obtained bandwidth change trend, it is predicted that the bandwidth of the first edge node may reach 12GB after 1 second. Then, the first edge node will The client's service request is rescheduled.

Step 304: Based on the IP address and the service type in the service request, the first edge node requests the central service platform for the bandwidth margin of at least one second edge node that belongs to the same area as the client and matches the service type requested by the client. and business quality.

Step 305: The first edge node reschedules the service request of the client to one or more second edge nodes according to the bandwidth margin and service quality of the at least one second edge node obtained by the request.

This embodiment predicts the bandwidth value of the first edge node after a preset time according to the bandwidth change trend of the first edge node and the current bandwidth value of the first edge node, and determines whether rescheduling is required according to the prediction result, which can prevent The bandwidth value of the first edge node exceeds the cost bandwidth value, thereby realizing the refined control of the cost.

Exemplarily, FIG. 4 is a flowchart of another service scheduling method provided by an embodiment of the present disclosure. As shown in FIG. 4 , the method includes:

Step 401: A first edge node in the CDN receives a service request from a client, where the service request includes a service type and an IP address of the client.

Step 402: The first edge node judges whether the service request needs to be rescheduled according to its current bandwidth value, cost bandwidth value and service quality, wherein, if yes, step 403 is executed.

In this embodiment, according to its current bandwidth value, cost bandwidth value, and service quality, the first edge node can determine whether it is necessary to reschedule the service request of the client in various ways:

For example, in one embodiment, the first edge node may first calculate the current bandwidth margin according to its current cost bandwidth value and its own current bandwidth value, and then compare its current bandwidth margin with the preset No. A bandwidth threshold is compared, and its current service quality is compared with the quality threshold corresponding to the service type requested by the client. If its current bandwidth margin is less than the first bandwidth threshold, and its current service quality is less than the quality threshold, it is determined that the client's service request needs to be rescheduled, otherwise it is determined that rescheduling is not required.

For another example, in another implementation manner, after calculating the current bandwidth margin of the first edge node, the first edge node can also determine the current bandwidth margin for itself according to the weight corresponding to the preset bandwidth margin and the weight corresponding to the quality of service. The current bandwidth headroom and service quality are weighted, and then the weighted bandwidth headroom and the weighted service quality are summed. If the summation result is less than the preset threshold, it is judged that rescheduling needs to be performed. Judgment does not require rescheduling.

It should be understood by those skilled in the art that the above two implementations are only two exemplary implementations rather than all implementations of this embodiment. In fact, any service rescheduling performed based on the bandwidth margin and service quality of the edge node All methods can be applied to this embodiment.

Step 403: Based on the IP address and the service type in the service request, the first edge node requests the central service platform for the bandwidth margin of at least one second edge node that belongs to the same area as the client and matches the service type requested by the client. and business quality.

Step 404: The first edge node reschedules the service request of the client to one or more second edge nodes according to the bandwidth margin and service quality of the at least one second edge node obtained by the request.

In this embodiment, the first edge node judges whether it needs to reschedule the service request of the client according to its current bandwidth value, cost bandwidth value, and service quality, which can take into account both cost and service quality, and realizes fine control of cost. Guaranteed business quality.

It should be noted that, in the above embodiment, the method of the first edge node after judging that rescheduling is necessary can also be performed by the client, that is, the first edge node will feedback to the client after judging that rescheduling is necessary. A notification message. After receiving the notification message, the client obtains the bandwidth headroom and service quality of at least one second edge node from the central service platform, and then obtains the bandwidth headroom and service quality of the second edge node according to the obtained bandwidth headroom and service quality. , the service request is rescheduled to one or more second edge nodes, and the execution manner and intentional effect thereof are similar to those of the above-mentioned embodiment, and will not be repeated here.

FIG. 5 is a schematic structural diagram of a service scheduling apparatus provided by an embodiment of the present disclosure. The service scheduling apparatus can be exemplarily understood as the first edge node in the above-mentioned embodiment or a part of functional modules in the first edge node. As shown in FIG. 5, the service scheduling device 50 includes:

The receiving module 51 is configured to receive the service request of the client, and the service request includes the service type and the IP address of the client;

The judgment module 52 is configured to judge whether the service request needs to be rescheduled according to at least the current bandwidth value of the first edge node and the current cost bandwidth value of the first edge node;

The request module 53 is configured to, when judging that rescheduling is required, request the central service platform based on the IP address and the business type to request at least one of the same area as the client and matching the business type. Bandwidth headroom and service quality of the second edge node, wherein the bandwidth headroom refers to the difference between the cost bandwidth value of the second edge node and the current bandwidth value of the second edge node;

The execution module 54 is configured to reschedule the service request to one or more second edge nodes according to the bandwidth margin and service quality of the at least one second edge node.

In one embodiment, the judging module 52 includes:

a first judgment submodule, configured to judge the size between the current bandwidth value of the first edge node and the current cost bandwidth value of the first edge node;

The second judging submodule is configured to judge that the service request needs to be rescheduled when the current bandwidth value of the first edge node is greater than or equal to the current cost bandwidth value of the first edge node.

In one embodiment, the judging module 52 includes:

A first determining submodule, configured to determine the bandwidth value of the first edge node after a preset time based on the current bandwidth value of the first edge node and the pre-obtained bandwidth variation trend of the first edge node;

a third judging submodule, configured to judge the size between the bandwidth value of the first edge node after a preset time and the current cost bandwidth value of the first edge node;

The fourth judging submodule is configured to judge that rescheduling is required when the bandwidth value of the first edge node after the preset time is greater than or equal to the current cost bandwidth value of the first edge node.

In an embodiment, the judgment module 52 is further configured to: according to the current bandwidth value, cost bandwidth value and service quality of the first edge node, judge whether the service request needs to be rescheduled.

In one embodiment, the judging module 52 includes:

The second determination submodule is configured to determine the current bandwidth margin of the first edge node according to the current bandwidth value and cost bandwidth value of the first edge node;

The fifth judging sub-module is configured to judge whether the current bandwidth margin of the first edge node is less than the first bandwidth threshold, and whether the current service quality of the first edge node is less than the quality threshold corresponding to the service type, if so, judge that the need The service request is rescheduled.

In one embodiment, the execution module 54 includes:

The first execution sub-module is configured to reschedule the service request according to the bandwidth headroom and service quality of the at least one second edge node so that the bandwidth headroom is greater than or equal to the second bandwidth threshold, and the service quality is greater than or equal to the specified bandwidth. on the second edge node with the quality threshold corresponding to the service type.

In one embodiment, the execution module 54 further includes:

a first processing submodule, configured to not include a second edge node whose bandwidth margin is greater than or equal to the second bandwidth threshold and whose service quality is greater than or equal to the quality threshold in the at least one second edge node , respectively perform weighted summation processing on the service quality and bandwidth margin of each second edge node, and obtain the weighted summation result corresponding to each second edge node;

The second execution submodule is configured to reschedule the service request to the second edge node whose weighted sum result is higher than the first preset threshold.

In one embodiment, the execution module 54 includes:

a third determining submodule, configured to determine, from the at least one second edge node, a second edge node whose bandwidth margin is greater than or equal to a second bandwidth threshold, and whose service quality is greater than or equal to the quality threshold corresponding to the service type, as a candidate edge node;

The second processing submodule is set to carry out weighted summation processing to the quality of service of each candidate edge node and the bandwidth margin respectively, and the candidate edge node whose weighted summation result is greater than the second preset threshold is used as the target edge node;

The third execution submodule is configured to reschedule the service request to the target edge node.

The apparatus provided in this embodiment can execute the method in any of the foregoing embodiments in FIG. 1 to FIG. 4 , and the execution manner and beneficial effects thereof are similar, which will not be repeated here.

For example, FIG. 6 is a schematic structural diagram of an edge node provided by an embodiment of the present disclosure. As shown in FIG. 6 , the edge node 1600 includes a processor 1601 and a memory 1602 .

Processor 1601 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and/or instruction execution capabilities, and may control other components in edge node 1600 to perform desired functions.

Memory 1602 may be various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and/or cache memory, among others. Non-volatile memory may include, for example, read only memory (ROM), hard disk, flash memory, and the like. A computer program is stored in the memory 1602. When the computer program is executed by the processor 1601, the processor 1601 executes the method of any of the above-mentioned embodiments in FIG. 1 to FIG. 4 .

In one example, the edge node 1600 may further include a receiving device 1603 and a sending device 1604, these components being interconnected by a bus system and/or other form of connection mechanism (not shown).

The receiving means 1603 may receive data or information sent by a client in the CDN, a central service platform, a central scheduling device, and other devices. The sending means 1604 may send data or information to a client in the CDN, a central service platform, a central scheduling device, and other devices.

Of course, for the sake of simplicity, only some components of the edge node 1600 are shown in FIG. 6 , but not all of the components. In practice, the edge node 1600 may also include any other components.

An embodiment of the present disclosure further provides a computer-readable storage medium, where a computer program is stored in the storage medium, and when the computer program is executed by the processor, the processor can execute any one of the foregoing implementations in FIG. 1 to FIG. 4 . example method.

It should be noted that, in this document, relational terms such as "first" and "second" etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these There is no such actual relationship or sequence between entities or operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The above descriptions are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Industrial Applicability

The service scheduling method provided by the present disclosure not only satisfies the service scheduling requirements of CDN, but also takes into account the cost and service quality of each edge node in the CDN, thereby realizing the refined control of the CDN cost, ensuring the service quality of the CDN, and having high performance. Strong industrial applicability.

Claims

A service scheduling method, the method is applicable to a content distribution network CDN, the CDN includes a central service platform for periodically determining the service quality and cost bandwidth value of each edge node in the CDN, the cost bandwidth The value refers to the bandwidth value when the cost of the edge node is optimal, and the method includes:

The first edge node in the CDN receives a service request from a client, where the service request includes a service type and an IP address of the client;

Judging whether the service request needs to be rescheduled at least according to its own current bandwidth value and cost bandwidth value;

If yes, request from the central service platform based on the IP address and the service type the bandwidth margin and service of at least one second edge node that belongs to the same area as the client and matches the service type quality, wherein the bandwidth margin refers to the difference between the cost bandwidth value of the second edge node and the current bandwidth value of the second edge node;

The service request is rescheduled to one or more second edge nodes according to the bandwidth headroom and service quality of the at least one second edge node.
The method according to claim 1, wherein the judging whether the service request needs to be rescheduled according to at least its own current bandwidth value and cost bandwidth value comprises:

Determine the size between your current bandwidth value and your current cost bandwidth value;

If its current bandwidth value is greater than or equal to its current cost bandwidth value, it is determined that the service request needs to be rescheduled.
The method according to claim 1, wherein the judging whether the service request needs to be rescheduled according to at least its own current bandwidth value and cost bandwidth value comprises:

Determine the bandwidth value after the preset time based on its current bandwidth value and the pre-obtained own bandwidth change trend;

judging the size between the bandwidth value after the preset time and its current cost bandwidth value;

If the bandwidth value after the preset time is greater than or equal to its current cost bandwidth value, it is determined that rescheduling is required.
The method according to claim 1, wherein the judging whether the service request needs to be rescheduled according to at least its own current bandwidth value and cost bandwidth value, further comprising:

According to its current bandwidth value, cost bandwidth value and service quality, it is determined whether the service request needs to be rescheduled.
The method according to claim 4, wherein judging whether the service request needs to be rescheduled according to its current bandwidth value, cost bandwidth value and service quality, comprising:

Determine its current bandwidth margin according to its current bandwidth value and cost bandwidth value;

It is judged whether its current bandwidth margin is less than the first bandwidth threshold, and whether its current service quality is less than the quality threshold corresponding to the service type, and if so, it is judged that the service request needs to be rescheduled.
The method according to any one of claims 1-5, wherein the rescheduling of the service request to one or more second edge nodes according to bandwidth headroom and service quality of the at least one second edge node On edge nodes, including:

According to the bandwidth headroom and service quality of the at least one second edge node, the service request is rescheduled until the bandwidth headroom is greater than or equal to the second bandwidth threshold, and the service quality is greater than or equal to the quality threshold corresponding to the service type on the second edge node.
The method of claim 6, wherein the method further comprises:

If the at least one second edge node does not include a second edge node whose bandwidth margin is greater than or equal to the second bandwidth threshold, and whose service quality is greater than or equal to the quality threshold Perform weighted summation processing on the service quality and bandwidth margin of the edge node to obtain a weighted summation result corresponding to each second edge node;

The service request is rescheduled to a second edge node whose weighted summation result is higher than a first preset threshold.
The method according to any one of claims 1-5, wherein the rescheduling of the service request to one or more second edge nodes according to bandwidth headroom and service quality of the at least one second edge node On edge nodes, including:

Determine from the at least one second edge node a second edge node whose bandwidth margin is greater than or equal to the second bandwidth threshold and whose service quality is greater than or equal to the quality threshold corresponding to the service type as a candidate edge node;

Perform weighted summation processing on the quality of service and bandwidth margin of each candidate edge node respectively, and use the candidate edge node whose weighted summation result is greater than the second preset threshold as the target edge node;

The service request is rescheduled to the target edge node.
A service scheduling apparatus, the service scheduling apparatus is set in a first edge node of a CDN, the CDN includes a central service platform for regularly determining the service quality and cost bandwidth value of each edge node in the CDN, and the The service scheduling device includes:

A receiving module, configured to receive a service request of a client, where the service request includes a service type and the IP address of the client;

A judgment module, configured to judge whether the service request needs to be rescheduled according to at least the current bandwidth value of the first edge node and the current cost bandwidth value of the first edge node;

The requesting module is configured to request from the central service platform based on the IP address and the service type, when judging that rescheduling is required, at least one first request that belongs to the same area as the client and matches the service type. Bandwidth margin and service quality of the second edge node, wherein the bandwidth margin refers to the difference between the cost bandwidth value of the second edge node and the current bandwidth value of the second edge node;

The execution module is configured to reschedule the service request to one or more second edge nodes according to the bandwidth margin and service quality of the at least one second edge node.
An edge node, including:

A memory and a processor, wherein the memory includes a computer program, and when the computer program is executed by the processor, the processor performs the method of any one of claims 1-8.
A computer-readable storage medium having a computer program stored in the storage medium, when the computer program is executed by a processor, causes the processor to execute the method according to any one of claims 1-8.