CN110708256A - CDN scheduling method, device, network device and storage medium - Google Patents

Abstract

Embodiments of the present invention relate to the field of content distribution networks, and disclose a CDN scheduling method. The CDN scheduling method includes: receiving a user request, and acquiring feature information of the user request, where the number of user requests is N, and N is a positive Integer; classify the feature information, and obtain the classification label requested by each user according to the classification result; obtain a preset scheduling policy according to the classification label requested by the user; The user request is scheduled to the corresponding CDN node. The embodiments of the present invention also provide a CDN device, a network device, and a storage medium. The CDN scheduling method, device, network device and storage medium provided by the embodiments of the present invention can ensure the timeliness of CDN scheduling and improve the efficiency of CDN scheduling.

Description

CDN scheduling method, device, network device and storage medium

technical field

The present invention relates to the field of content distribution networks, and in particular, to a CDN scheduling method, device, network equipment and storage medium.

Background technique

Content Delivery Network (CDN for short) is an intelligent virtual network built on the basis of existing networks, relying on edge servers deployed in various places, through the load balancing, content distribution, scheduling and other functional modules of the central platform, enabling users Get the desired content nearby, reduce network congestion, and improve user access response speed and hit rate.

However, the current CDN scheduling is based on the statistics of the back-end node information of the CDN before scheduling. Since the statistics of these nodes have a lag, the CDN scheduling also has a hysteresis, and the efficiency is low.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present invention is to provide a CDN scheduling method, apparatus, network device and storage medium, so that the CDN scheduling is timely and the efficiency is improved.

In order to solve the above-mentioned technical problem, an embodiment of the present invention provides a CDN scheduling method, which includes the following steps: receiving a user request, acquiring feature information requested by the user, the number of user requests being N, and N being a positive integer; classifying the feature information , and obtain the classification label of each user request according to the classification result; obtain the preset scheduling policy according to the classification label requested by the user; schedule the user request to the corresponding CDN node according to the preset scheduling policy.

Embodiments of the present invention also provide a CDN scheduling device, comprising: a feature information acquisition module, configured to receive a user request and acquire feature information requested by the user, where the number of user requests is N, where N is a positive integer; a classification label acquisition module, It is used to classify the feature information, and obtain the classification label requested by each user according to the classification result; the scheduling strategy obtaining module is used to obtain the preset scheduling strategy according to the classification label requested by the user; the node scheduling module is used to obtain the preset scheduling strategy according to the preset The scheduling policy schedules user requests to the corresponding CDN nodes.

Embodiments of the present invention also provide a network device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by at least one processor. A processor executes to enable at least one processor to execute the CDN scheduling method as described above.

Embodiments of the present invention further provide a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned CDN scheduling method is implemented.

Compared with the prior art, the embodiment of the present invention can obtain the classification label of each user request by acquiring the feature information related to the user request and then classifying the feature information; Set a scheduling policy, so that user requests are scheduled to the corresponding CDN nodes according to the preset scheduling policy, and the characteristic information of user requests is analyzed at the front end, and then active scheduling is performed according to the results of the front-end analysis, avoiding the need for back-end CDN node information. The hysteresis of scheduling ensures the timeliness of CDN scheduling and improves the efficiency of CDN scheduling.

In addition, obtaining the classification label requested by each user according to the classification result includes: using a preset classification label to identify the classification result, and obtaining the classification label requested by each user. The classification results are identified according to the preset classification labels, so that the classification labels requested by the user can be unified and standardized, and it is convenient for subsequent selection of the corresponding CDN scheduling policy according to the classification labels.

In addition, the feature information includes the requested resource; before obtaining the preset scheduling policy according to the classification label requested by the user, it also includes: obtaining the same number of concurrent users of the requested resource; obtaining the preset scheduling policy according to the classification label requested by the user, including: Obtain the preset scheduling policy according to the classification label requested by the user and the number of concurrent users. By obtaining the number of concurrent users with the same requested resources, and then obtaining the preset scheduling strategy according to the number of concurrent users and the classification label of user requests, the preset scheduling strategy can be more accurate, and in the case of high concurrency, it can also ensure that user requests are correct. The normal access of CDN nodes improves the stability of CDN node access.

In addition, before obtaining the preset scheduling policy according to the classification label requested by the user, the method further includes: obtaining a preset user portrait, where the preset user portrait is obtained according to the historical user request and the classification label of the historical user request; according to the classification label requested by the user Obtaining the preset scheduling policy includes: taking the user request and the classification label of the user request as the pending user portrait; if the pending user portrait is the same as the preset user portrait, the preset scheduling policy is to schedule the user request to the preset access CDN node, The default access CDN node is the CDN node with the latest access or the highest access frequency requested by historical users. The user profiles corresponding to the user requests are compared. If the pending user profile is the same as the preset user profile, the user request is scheduled to the preset access CDN node, which can make CDN scheduling faster, reduce scheduling delay, and improve user access. experience.

In addition, the classification label includes at least one of the IP requested by the user, the province where the user belongs, the type of the client that issued the user request, the popularity of the requested resource, the content of the requested resource, and the type of the requested resource. The setting of the classification label can facilitate the scheduling server to obtain the preset scheduling policy according to the classification label.

In addition, the classification label includes the popularity of the requested resource, the province to which the user belongs, and the IP requested by the user; obtaining a preset scheduling policy according to the classification label requested by the user includes: if the popularity of the requested resource is greater than the first preset value, judging that the user Whether the load of the CDN node of the home province reaches the preset load; if the load of the CDN node is less than or equal to the preset load, the preset scheduling policy is to schedule the user request to the CDN node of the user's home province; if the load of the CDN node is greater than the preset load If the load is set, the preset scheduling policy is to schedule the user request to the idle CDN node in the province closest to the IP requested by the user in a round-robin manner. The preset scheduling policy is obtained by judging the heat of the requested resources, so that the user's access to hot or non-hot resources can be reasonably scheduled by the scheduling server to ensure that each user request can be satisfied; On the basis of , the load of CDN nodes can be further judged, and scheduling can be carried out in combination with the actual situation of CDN nodes, so that the load of CDN nodes is within a reasonable range and the stability of CDN node access is guaranteed.

In addition, the classification label includes the popularity of the requested resource and the IP requested by the user; the preset scheduling policy is obtained according to the classification label requested by the user and the number of concurrent users, including: if the popularity of the requested resource is greater than the second preset value, judging that the user Whether the number of concurrent users is greater than or equal to the preset number of concurrent users; if the number of concurrent users is greater than or equal to the preset number of concurrent users, the preset scheduling strategy is to schedule a preset proportion of user requests to the idle provincial CDN closest to the IP requested by the user node. Combining the number of concurrent users and classification labels to schedule user requests, proactively schedule a preset proportion of user requests to CDN nodes in other provinces, which can actively balance user requests and CDN nodes to ensure the stability of CDN access resources.

Description of drawings

One or more embodiments are exemplified by the pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments.

1 is a schematic flowchart of a CDN scheduling method provided by a first embodiment of the present invention;

FIG. 2 is another schematic flowchart of the CDN scheduling method provided by the first embodiment of the present invention;

3 is another schematic flowchart of the CDN scheduling method provided by the first embodiment of the present invention;

FIG. 4 is a schematic diagram of the principle example of the CDN scheduling method provided by the first embodiment of the present invention;

Fig. 5 is the module structure diagram of the CDN scheduling apparatus provided by the second embodiment of the present invention;

FIG. 6 is a schematic structural diagram of a network device provided by a third embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, each embodiment of the present invention will be described in detail below with reference to the accompanying drawings. However, those of ordinary skill in the art can appreciate that, in the various embodiments of the present invention, many technical details are set forth in order for the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can be realized.

The first embodiment of the present invention relates to a CDN scheduling method. By receiving a user request, the feature information requested by the user is obtained; the feature information is classified, and the classification label of each user request is obtained according to the classification result; The classification label obtains the preset scheduling policy; according to the preset scheduling policy, the user request is scheduled to the corresponding CDN node. By analyzing user requests at the front end, obtaining preset scheduling policies according to the analyzed classification labels, and then scheduling user requests to the corresponding CDN nodes according to the preset scheduling policies, front-end analysis and active scheduling are realized, and CDN scheduling is ensured. Timeliness improves the efficiency of CDN scheduling.

It should be noted that the execution body of the CDN scheduling method provided by this embodiment may be, but is not limited to, a CDN scheduling server. The following description will take the CDN scheduling server (hereinafter referred to as the scheduling server) as an example.

The specific flowchart of the CDN scheduling method provided by this embodiment is shown in FIG. 1 , which specifically includes the following steps:

S101: Receive a user request, and acquire feature information requested by the user, where the number of user requests is N, and N is a positive integer.

The user request refers to a request sent by the user through the client, such as requesting a web page, a video, or an audio. The feature information refers to the information related to the user request. When the scheduling server receives the user request, it can obtain information such as the IP, Uniform Resource Locator (Uniform Resource Locator, URL) and request time requested by the user. The scheduling server then obtains feature information according to the information, wherein the feature information may include but is not limited to the IP requested by the user, the province to which the user belongs, the type of client that issued the user request, the popularity of the requested resource, the content of the requested resource, and the like. For example, by analyzing the IP requested by the user, the province to which the user belongs can be obtained; by analyzing the request header information in the URL, the client type requested by the user can be obtained, and so on.

Since the scheduling server may receive user requests from multiple users at the same time, the number of user requests is N, where N is a positive integer.

S102: Classify the feature information, and obtain a classification label requested by each user according to the classification result.

Optionally, the scheduling server classifies according to feature information such as the IP requested by the user, the province to which the user belongs, the client type that sends the user request, the popularity of the requested resource, and the type of the requested resource, and then identifies the result of the classification with a label. , so that the classification label requested by each user can be obtained. For example, classify the province to which the user belongs, into "Beijing", "Shanghai" and "Guangzhou", etc.; for another example, classify the client type requested by the user into "mobile phone", "tablet" and "notebook" For another example, classify the popularity of the requested resources into "hot resources" and "non-hot resources", etc.

The classification label can be directly identified with the classification result, for example, identified with "Beijing", "Mobile Phone", "Hot Resource", or it can be identified with abbreviated letters or full spelling, etc. There is no specific limitation here.

Optionally, the classification label includes at least one of the IP requested by the user, the province where the user belongs, the type of the client that sent the user request, the popularity of the requested resource, the content of the requested resource, and the type of the requested resource. The requested resource refers to the resource pointed to by the URL.

In a specific example, the scheduling server uses a preset classification label to identify the classification result, so as to obtain the classification label requested by each user. Optionally, the preset classification label is stored in the database of the scheduling server, and the scheduling server judges the classification result, and if the classification result conforms to the preset classification label, the user request is identified with the preset classification label, Thereby, the classification label requested by each user is obtained.

It can be understood that the classification results are identified according to the preset classification labels, so that the classification labels requested by the user can be unified and standardized, and it is convenient for subsequent selection of the corresponding CDN scheduling policy according to the classification labels.

S103: Acquire a preset scheduling policy according to the classification label requested by the user.

The preset scheduling policy is stored in the database of the scheduling server. Optionally, a mapping table between classification labels and preset scheduling policies may be formed and stored in the database of the scheduling server, and the scheduling server may obtain the preset scheduling policies corresponding to the classification tags requested by the user according to the mapping table. The preset scheduling policy can be preset according to actual needs, and there is no specific limitation here.

For example, the classification labels of a user's request are "Beijing", "mobile phone" and "non-hot resources". Since the user requests are non-hot resources, the preset scheduling policy may be to directly schedule the user request to the CDN in Beijing node; since the client type requested by the user is a mobile phone, the preset scheduling policy may be to schedule the user request to a CDN node in Beijing that stores mobile phone resources.

Optionally, the scheduling server may combine traditional CDN scheduling methods, such as distance priority or round robin, when setting the preset scheduling policy. For example, in the above example, on the premise that the classification labels "Beijing", "mobile phone" and "non-hotspot resources" requested by the user are satisfied, the preset scheduling policy may be a scheduling method based on distance priority, scheduling the user request to the same location as the user The requested IP is the nearest CDN node in Beijing that stores mobile phone resources.

S104: Schedule the user request to the corresponding CDN node according to the preset scheduling policy.

Specifically, after obtaining the preset scheduling policy, the scheduling server schedules the user request to the corresponding CDN node according to the preset scheduling policy.

Compared with the prior art, the CDN scheduling method of this embodiment obtains the feature information related to the user request, and then classifies the feature information to obtain the classification label of each user request; according to the classification label requested by the user, it is possible to obtain According to the preset scheduling policy, the user request is scheduled to the corresponding CDN node, which realizes the analysis of information at the front end, and performs active scheduling according to the result of the front-end analysis, which ensures the timeliness of CDN scheduling. Improve the efficiency of CDN scheduling.

In a specific example, the characteristic information includes the requested resource. Please refer to FIG. 2 , which is another schematic flowchart of the CDN scheduling method provided in this embodiment, which specifically includes the following steps:

S201: Receive a user request, and acquire feature information requested by the user, where the number of user requests is N, and N is a positive integer.

S202: Classify the feature information, and obtain a classification label requested by each user according to the classification result.

S203: Acquire the concurrent number of users with the same requested resource.

S204: Acquire a preset scheduling policy according to the classification label requested by the user and the number of concurrent users.

S205: Schedule the user request to the corresponding CDN node according to the preset scheduling policy.

Wherein, S201, S202 and S205 are the same as the above-mentioned S101, S102 and S104, and will not be repeated here.

In S203, the scheduling server judges according to the URL requested by the user, and if the requested resources corresponding to the URLs are the same, the number of concurrent users is increased by 1, so as to count the concurrent number of users with the same requested resources.

In S204, when obtaining the preset scheduling policy according to the classification label requested by the user, the scheduling server selects the corresponding preset scheduling policy in combination with the factor of the number of concurrent users. Optionally, a judgment condition may be set according to the number of concurrent users, and when the number of concurrent users is less than a numerical value and the number of concurrent users is greater than or equal to the numerical value, different preset scheduling policies are selected. For example, when the number of concurrent users with the same requested resource is less than 500, the user request is scheduled to the CDN node corresponding to the classification label in a distance-first manner; The user request is dispatched to the CDN node corresponding to the classification label in the way of query.

By obtaining the number of concurrent users with the same requested resources, and then obtaining the preset scheduling strategy according to the number of concurrent users and the classification label of user requests, the preset scheduling strategy can be more accurate, and in the case of high concurrency, it can also ensure that user requests are correct. The normal access of CDN nodes improves the stability of CDN node access.

In a specific example, please refer to FIG. 3 , which is another schematic flowchart of the CDN scheduling method provided in this embodiment, which specifically includes the following steps:

S301: Receive a user request, and obtain feature information requested by the user, where the number of user requests is N, and N is a positive integer.

S302: Classify the feature information, and obtain a classification label requested by each user according to the classification result.

S303: Obtain a preset user portrait, where the preset user portrait is obtained according to historical user requests and classification labels of historical user requests.

S304: Use the user request and the classification label requested by the user as the pending user portrait.

S305: If the undetermined user profile is the same as the preset user profile, the preset scheduling policy is to schedule the user request to the preset access CDN node, and the preset access CDN node is the CDN node with the latest or highest access frequency of historical user requests.

S306: Schedule the user request to the corresponding CDN node according to the preset scheduling policy.

Among them, S301, S302 and S306 are the same as the above, and will not be repeated here.

In S303, optionally, the scheduling server may use each historical user request and a classification label corresponding to each historical user request as a preset user portrait. It can be understood that each historical user request and the corresponding category label are taken as a whole, and the preset user portrait can describe the behavior of the whole, and the same historical user request and category label are used as a preset user portrait. Optionally, the scheduling server can set preset user portraits according to the same historical user request and the number of times the classification label appears. Historical user requests and category tags that do not exceed this value are not set to default user portraits. The preset user portrait can be set according to actual needs, and there are no specific restrictions here.

In S304 and S305, specifically, the scheduling server takes the user request and the classification label corresponding to the user request as the pending user portrait, compares the pending user portrait with the preset user portrait, and if the pending user portrait is the same as the preset user portrait, then The user request corresponding to the pending user profile is dispatched to the preset access CDN node. The preset access CDN node refers to the CDN node with the latest access or the highest access frequency requested by historical users in the preset user profile. Optionally, if the to-be-determined user portrait is different from the preset user portrait, a preset scheduling policy is obtained according to the classification label requested by the user, and then the user request is scheduled to the corresponding CDN node according to the preset scheduling policy.

The user profiles corresponding to the user requests are compared. If the pending user profile is the same as the preset user profile, the user request is scheduled to the preset access CDN node, which can make CDN scheduling faster, reduce scheduling delay, and improve user access. experience.

In a specific example, the classification label includes the popularity of the requested resource, the province to which the user belongs, and the IP requested by the user. In S103, a preset scheduling policy is obtained according to the classification label requested by the user, which specifically includes: if the popularity of the requested resource is greater than The first preset value is to determine whether the load of the CDN node in the province to which the user belongs reaches the preset load; if the load of the CDN node is less than or equal to the preset load, the preset scheduling policy is to schedule the user request to the CDN of the user's home province. node; if the load of the CDN node is greater than the preset load, the preset scheduling policy is to use a round-robin method to schedule the user request to the idle provincial CDN node with the nearest IP requested by the user.

The popularity of the requested resource may be counted by the number of users accessing the requested resource, or may be counted by other methods. The first preset value can be set according to the actual situation, and no specific limitation is made here. Optionally, it can also be determined by whether the requested resource belongs to a hotspot resource, wherein whether the requested resource belongs to a hotspot resource can be provided by a corresponding portal website. The load of the CDN node can be measured by the CPU usage or memory usage of the CDN node. The preset load can be set according to actual needs, and there are no specific restrictions here.

Specifically, the scheduling server judges the heatness of the requested resource in the classification label, and if it is greater than the first preset value, further judges whether the load of the CDN node in the user's home province reaches the preset load. Optionally, if the popularity of the requested resource is less than or equal to the first preset value, the preset scheduling policy may be to directly schedule the user request to the CDN node of the user's home province. In further judgment, if the load of the CDN node in the province to which the user belongs is less than or equal to the preset load, the preset scheduling policy is to schedule the user request to the CDN node in the province to which the user belongs; optionally, the preset scheduling policy schedules the user request. To the CDN node of the user's home province closest to the user's IP. If the load of the CDN node of the user's home province is greater than the preset load, the preset scheduling strategy is to use a round-robin method to schedule the user request to the idle CDN node in the province that is closest to the IP requested by the user. Optionally, whether the CDN node is idle can be determined by whether the number of access users of the CDN node reaches a threshold.

The preset scheduling policy is obtained by judging the heat of the requested resources, so that the user's access to hot or non-hot resources can be reasonably scheduled by the scheduling server to ensure that each user request can be satisfied; On the basis of , the load of CDN nodes can be further judged, and scheduling can be carried out in combination with the actual situation of CDN nodes, so that the load of CDN nodes is within a reasonable range and the stability of CDN node access is guaranteed.

In a specific example, the classification label includes the popularity of the requested resource and the IP requested by the user; in S204, a preset scheduling policy is obtained according to the classification label requested by the user and the number of concurrent users, which may specifically include: if the requested resource is If the heat is greater than the second preset value, it is determined whether the number of concurrent users is greater than or equal to the preset number of concurrent users; if the number of concurrent users is greater than or equal to the preset number of concurrent users, the preset scheduling policy is to schedule a preset proportion of user requests To the idle out-of-province CDN node closest to the IP requested by the user.

The second preset value and the first preset value may be the same or different. The preset number of concurrent users can be set according to actual needs, and there is no specific limit here. The preset ratio can be set according to the proportion of the number of concurrent users exceeding the preset number of concurrent users, or it can be set according to other needs, which is not limited here.

Specifically, the scheduling server judges the popularity of the requested resource in the classification label, and if it is greater than the second preset value, further judges whether the concurrent number of users is greater than or equal to the preset concurrent number of users. Optionally, if the popularity of the requested resource is less than or equal to the second preset value, the preset scheduling policy may schedule the user request to the CDN node of the user's home province closest to the IP requested by the user. In further judgment, if the number of concurrent users is greater than or equal to the preset number of concurrent users, the preset scheduling strategy is to schedule a preset proportion of user requests to the idle CDN node in the province closest to the IP requested by the user; optionally, if If the number of concurrent users is less than the preset number of concurrent users, the preset scheduling policy is to schedule the user request to the CDN node in the province to which the user belongs, which is closest to the IP requested by the user. Optionally, when scheduling the user request to the CDN node of the user's home province closest to the IP requested by the user, a polling manner may be adopted.

Combining the number of concurrent users and classification labels to schedule user requests, proactively schedule a preset proportion of user requests to CDN nodes in other provinces, which can actively balance user requests and CDN nodes to ensure the stability of CDN access resources.

It should be noted that, in the above embodiment, the division can also be based on the home city requested by the user, not limited to the home province; and the preset scheduling strategy can be obtained by combining the above methods in other ways.

Please refer to FIG. 4 , which is a schematic diagram of the principle example of the CDN scheduling method provided in this embodiment. Specifically, the user sends a user request through the client to request access to the resource. The analyzer can be a module in the scheduling server, which is used to obtain the feature information requested by the user, and then classify the feature information to obtain the classification label; then summarize the classification labels requested by the user, and the scheduling server performs policy analysis on the aggregated information. , obtain the preset scheduling policy; then perform scheduling triggering to schedule the user request to the CDN node, when scheduling to the CDN node, it can be scheduled to the corresponding CDN node by distance priority or round-robin.

The step division of the above various methods is only for the purpose of describing clearly. During implementation, it can be combined into one step or some steps can be split and decomposed into multiple steps, as long as they contain the same logical relationship, they are all within the protection scope of this patent. ;Adding insignificant modifications to the algorithm or process or introducing insignificant designs, but not changing the core design of the algorithm and process are all within the scope of protection of this patent.

The second embodiment of the present invention relates to a CDN scheduling apparatus. As shown in FIG. 5 , it includes: a feature information obtaining module 401 , a classification label obtaining module 402 , a scheduling policy obtaining module 403 and a node scheduling module 404 .

A feature information acquisition module 401, configured to receive a user request and obtain the feature information requested by the user, where the number of user requests is N, and N is a positive integer;

The classification label obtaining module 402 is used to classify the feature information, and obtain the classification label requested by each user according to the classification result;

a scheduling policy obtaining module 403, configured to obtain a preset scheduling policy according to the classification label requested by the user;

The node scheduling module 404 is configured to schedule the user request to the corresponding CDN node according to the preset scheduling policy.

Further, the classification label obtaining module 402 is further configured to: use a preset classification label to identify the classification result, and obtain the classification label requested by each user.

Further, the feature information includes the requested resource, and before obtaining the preset scheduling strategy according to the user's classification label, it also includes: obtaining the same number of concurrent users of the requested resource; the scheduling strategy obtaining module 403 is further configured to: according to the classification requested by the user Get the preset scheduling policy for tags and user concurrency.

Further, before obtaining the preset scheduling strategy according to the classification label requested by the user, it also includes: obtaining a preset user portrait, the preset user portrait is obtained according to the historical user request and the classification label of the historical user request; the scheduling strategy obtaining module 403 It is also used to: take the user request and the classification label of the user request as the pending user portrait; if the pending user portrait is the same as the preset user portrait, the preset scheduling policy is to schedule the user request to the preset access CDN node, and the preset access CDN The node is the CDN node with the latest access or the highest access frequency for historical user requests.

Further, the classification label includes at least one of the IP requested by the user, the province where the user belongs, the type of the client that sent the user request, the popularity of the requested resource, the content of the requested resource, and the type of the requested resource.

Further, the classification label includes the heat of the requested resource, the province to which the user belongs, and the IP requested by the user; the scheduling policy obtaining module 403 is also used for:

If the heat of the requested resource is greater than the first preset value, determine whether the load of the CDN node of the user's home province reaches the preset load;

If the load of the CDN node is less than or equal to the preset load, the preset scheduling policy is to schedule the user request to the CDN node of the user's home province;

If the load of the CDN node is greater than the preset load, the preset scheduling strategy is to use a round-robin method to schedule the user request to the idle CDN node in the province closest to the IP requested by the user.

Further, the classification label includes the popularity of the requested resource and the IP requested by the user; the scheduling policy obtaining module 403 is also used for:

If the heat of the requested resource is greater than the second preset value, determine whether the concurrent number of users is greater than or equal to the preset number of concurrent users;

If the number of concurrent users is greater than or equal to the preset number of concurrent users, the preset scheduling policy is to schedule a preset proportion of user requests to idle CDN nodes in other provinces that are closest to the IP requested by the user.

It is not difficult to find that this embodiment is a device example corresponding to the first embodiment, and this embodiment can be implemented in cooperation with the first embodiment. The related technical details mentioned in the first embodiment are still valid in this embodiment, and are not repeated here in order to reduce repetition. Correspondingly, the related technical details mentioned in this embodiment can also be applied to the first embodiment.

It is worth mentioning that each module involved in this embodiment is a logical module. In practical applications, a logical unit may be a physical unit, a part of a physical unit, or multiple physical units. A composite implementation of the unit. In addition, in order to highlight the innovative part of the present invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other units in this embodiment.

The third embodiment of the present invention relates to a network device, as shown in FIG. 6 , comprising at least one processor 501; and a memory 502 communicatively connected with the at least one processor 501; wherein, the memory 502 stores data that can be processed by the at least one processor 501. The instruction executed by the processor 501 is executed by the at least one processor 501, so that the at least one processor 501 can execute the above-mentioned CDN scheduling method.

The memory 502 and the processor 501 are connected by a bus, and the bus may include any number of interconnected buses and bridges, and the bus connects one or more processors 501 and various circuits of the memory 502 together. The bus may also connect together various other circuits, such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides the interface between the bus and the transceiver. A transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing a means for communicating with various other devices over a transmission medium. The data processed by the processor 501 is transmitted on the wireless medium through the antenna, and further, the antenna also receives the data and transmits the data to the processor 501 .

Processor 501 is responsible for managing the bus and general processing, and may also provide various functions including timing, peripheral interface, voltage regulation, power management, and other control functions. The memory 502 may be used to store data used by the processor 501 when performing operations.

A fourth embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The above method embodiments are implemented when the computer program is executed by the processor.

That is, those skilled in the art can understand that all or part of the steps in the method of the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium and includes several instructions to make a device (which can be It is a single-chip microcomputer, a chip, etc.) or a processor (processor) that executes all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes.

Those skilled in the art can understand that the above-mentioned embodiments are specific examples for realizing the present invention, and in practical applications, various changes in form and details can be made without departing from the spirit and the spirit of the present invention. scope.

Claims (10)

1. a CDN scheduling method, is characterized in that, comprises: Receive a user request, and obtain the feature information requested by the user, where the number of user requests is N, and the N is a positive integer; classifying the feature information, and obtaining the classification label requested by each user according to the classification result; Acquire a preset scheduling policy according to the classification label requested by the user; The user request is scheduled to the corresponding CDN node according to the preset scheduling policy. 2 . The CDN scheduling method according to claim 1 , wherein the obtaining the classification label of each user request according to the classification result comprises: 2 . The classification result is identified by a preset classification label, and the classification label requested by each user is obtained. 3. The CDN scheduling method according to claim 1, wherein the characteristic information comprises a requested resource; Before obtaining the preset scheduling policy according to the classification label requested by the user, the method further includes: Obtain the number of concurrent users with the same requested resource; The obtaining the preset scheduling policy according to the classification label requested by the user includes: Acquire a preset scheduling policy according to the classification label requested by the user and the number of concurrent users. 4 . The CDN scheduling method according to claim 1 , wherein before the obtaining a preset scheduling policy according to the classification label requested by the user, the method further comprises: 4 . Obtaining a preset user portrait, the preset user portrait is obtained according to the historical user request and the classification label of the historical user request; The obtaining the preset scheduling policy according to the classification label requested by the user includes: Taking the user request and the classification label of the user request as the pending user portrait; If the pending user portrait is the same as the preset user portrait, the preset scheduling policy is to schedule the user request to a preset access CDN node, and the preset access CDN node is the latest update for the historical user request Access or visit the most frequently accessed CDN node. 5. The CDN scheduling method according to any one of claims 1-4, wherein the classification label includes the IP requested by the user, the province to which the user belongs, the type of the client that issued the user request, the requested At least one of the popularity of the resource, the content of the requested resource, and the type of the requested resource. 6 . The CDN scheduling method according to claim 5 , wherein the classification label includes the heat of the requested resource, the province to which the user belongs, and the IP requested by the user; 6 . The obtaining the preset scheduling policy according to the classification label requested by the user includes: If the heat of the requested resource is greater than the first preset value, determine whether the load of the CDN node in the province to which the user belongs has reached the preset load; If the load of the CDN node is less than or equal to the preset load, the preset scheduling policy is to schedule the user request to the CDN node of the user's home province; If the load of the CDN node is greater than the preset load, the preset scheduling policy is to use a round-robin manner to schedule the user request to an idle provincial CDN node closest to the IP requested by the user. 7 . The CDN scheduling method according to claim 5 , wherein the classification label includes the popularity of the requested resource and the IP requested by the user; 7 . The obtaining of the preset scheduling policy according to the classification label requested by the user and the concurrent number of the user includes: If the heat of the requested resource is greater than the second preset value, determine whether the concurrent number of users is greater than or equal to the preset number of concurrent users; If the concurrent number of users is greater than or equal to the preset concurrent number of users, the preset scheduling strategy is to schedule a preset proportion of the user requests to an idle CDN node in the province closest to the IP requested by the user. 8. A CDN scheduling device, comprising: a feature information acquisition module, configured to receive a user request, and obtain the feature information requested by the user, where the number of user requests is N, and the N is a positive integer; a classification label obtaining module, configured to classify the feature information, and obtain the classification label requested by each user according to the classification result; a scheduling policy obtaining module, configured to obtain a preset scheduling policy according to the classification label requested by the user; A node scheduling module, configured to schedule the user request to a corresponding CDN node according to the preset scheduling policy. 9. A network device, comprising: at least one processor; and, a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any one of claims 1 to 7 The CDN scheduling method described above. 10 . A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the CDN scheduling method according to any one of claims 1 to 7 is implemented. 11 .

Images