A scheduling method, apparatus, medium, and device

Abstract

This document relates to a scheduling method, apparatus, medium, and device applied to a scheduling device. The method includes: receiving a first access request from a client, including a content provider domain name and file identifier information; determining the target object corresponding to the first access request; querying the mapping relationship between the object and a service address to determine the access URL corresponding to the target object; and returning response information containing the access URL, so that the client sends a second access request to the corresponding service provider network based on the access URL, requesting the target object. This can schedule access requests for the same file to a specific edge device of a designated CDN service provider, increasing the access popularity of the target object within the CDN service provider network, thereby improving cache hit rate, reducing the number of origin pulls at edge nodes, reducing origin pull bandwidth costs, and improving response speed.

Description

Technical Field

[0001] This article relates to the Internet field, and in particular to a scheduling method, device, medium and equipment. Background Technology

[0002] In related technologies, domain name bandwidth allocation is mainly achieved through regional resolution, which distributes access bandwidth in different regions to different CDN service providers; or by allocating domain name access bandwidth to different CDN service providers according to a preset ratio.

[0003] The above domain bandwidth allocation method cannot differentiate access requests based on the requested file, nor can it allocate bandwidth for specific files to specific CDN service providers. This results in access requests for the same file being distributed across multiple CDN service providers. When file access activity is low, the file's access activity further decreases across each CDN service provider's network, leading to low cache hit rates. Furthermore, the accessed nodes need to fetch the target object from upstream. This results in increased bandwidth costs, increased file retrieval time, increased CDN upstream bandwidth consumption, and longer response latency, among other cost and quality of service issues. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this paper provides a scheduling method, apparatus, medium and equipment.

[0005] According to the first aspect of this paper, a scheduling method is provided, applied to a scheduling device, including:

[0006] Receive a first access request from a client, which includes the content provider's domain name and file identification information, and determine the target object corresponding to the first access request;

[0007] The mapping relationship between the query object and the service address is used to determine the access URL corresponding to the target object;

[0008] The system returns response information containing the access URL, enabling the client to send a second access request to the corresponding edge device based on the access URL, requesting the target object.

[0009] The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

[0010] Based on the foregoing solution, in an exemplary embodiment, the mapping relationship between the query object and the service address, and determining the access URL corresponding to the target object, includes:

[0011] Each object corresponds to a unique object key;

[0012] Each service domain name corresponds to a unique domain key;

[0013] Each object key is mapped to one of the domain keyes;

[0014] Calculate the target object KEY, and determine the access URL based on the mapping relationship.

[0015] Based on the foregoing solution, in an exemplary embodiment, the mapping relationship between the query object and the service address, and determining the access URL corresponding to the target object, includes:

[0016] Each object corresponds to a unique object key;

[0017] Each edge device corresponds to a unique device key;

[0018] Each object key is mapped to one of the device keys;

[0019] Calculate the target object KEY, and determine the access URL and target edge device IP based on the mapping relationship.

[0020] Based on the foregoing scheme, in an exemplary embodiment, the access URL corresponding to the target object includes the target service domain name mapped to the target object and the path of the target object.

[0021] Based on the foregoing scheme, in an exemplary embodiment, returning response information containing the access URL enables the client to send a second access request to the corresponding edge device based on the access URL, requesting the target object including:

[0022] The system returns a response containing the access URL to the client, enabling the client to request domain name resolution from the authoritative DNS of the service provider corresponding to the target service domain name and obtain the edge device IP, and then send the access URL to the edge device IP to request the target object.

[0023] Based on the foregoing scheme, in an exemplary embodiment, the response information further includes the target edge device IP, and the return of response information containing the access URL enables the client to send a second access request to the corresponding edge device according to the access URL, requesting the target object including:

[0024] The system returns a response containing the access URL and the target edge device IP to the client, so that the client sends the access URL to the target edge device IP to request the target object.

[0025] Based on the aforementioned scheme, in an exemplary embodiment, the mapping relationship is determined by the scheduling device according to the service domain name or edge device IP obtained in advance from different service providers.

[0026] Based on the aforementioned scheme, in an exemplary embodiment, the scheduling method further includes:

[0027] Receive feedback information from the client regarding abnormal service status of the edge device corresponding to the target service domain name or the target edge device, and adjust the mapping relationship.

[0028] According to another aspect of this paper, a scheduling method is provided for application on a client side, including:

[0029] Send a first access request including the content provider's domain name and file identification information;

[0030] Receive the response information returned by the scheduling device in response to the first access request;

[0031] When the response information contains an access URL, a domain name resolution request is sent to the authoritative DNS of the service provider corresponding to the target service domain name in the access URL to obtain the edge device IP corresponding to the target service domain name, the access URL is sent to the edge device IP, and the target object is obtained; when the response information contains the target edge device IP and the access URL, the access URL is sent to the target edge device IP, and the target object is obtained.

[0032] Based on the aforementioned scheme, in an exemplary embodiment, the scheduling method further includes:

[0033] When the edge device corresponding to the target service domain name or the target edge device service status is abnormal, the abnormal service status information is reported to the scheduling device so that the scheduling device can adjust the mapping relationship between the object and the service address.

[0034] According to another aspect of this paper, a scheduling method is provided for use in edge devices, comprising:

[0035] The client receives a second access request containing the service provider's service domain name, and the second access request includes an access URL;

[0036] Returns the target object corresponding to the access URL;

[0037] The access URL is determined by the scheduling device based on the target object corresponding to the client's first access request and the mapping relationship between the object and the service address.

[0038] The first access request includes the content provider's domain name and file identification information;

[0039] The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

[0040] According to another aspect of this document, a scheduling apparatus is provided, applied to a scheduling device, comprising:

[0041] The first request receiving module is used to receive a first access request from the client, including the content provider's domain name and file identification information, and to determine the target object corresponding to the first access request.

[0042] The query module is used to query the mapping relationship between objects and service addresses, and to determine the access URL corresponding to the target object;

[0043] The first response module is used to return response information containing the access URL, so that the client sends a second access request to the corresponding edge device according to the access URL to request the target object;

[0044] The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

[0045] Based on the foregoing solution, in an exemplary embodiment, the scheduling device further includes:

[0046] The mapping relationship adjustment module is used to receive feedback information from the client regarding the abnormal service status of the edge device corresponding to the target service domain name or the target edge device, and adjust the mapping relationship accordingly.

[0047] According to another aspect of this document, a scheduling apparatus is provided for use on a client, comprising:

[0048] The sending module is used to send a first access request, including the content provider's domain name and file identification information;

[0049] The response receiving module is used to receive response information returned by the scheduling device in response to the first access request;

[0050] The acquisition module is configured to, when the response information contains an access URL, send a domain name resolution request to the authoritative DNS of the service provider corresponding to the target service domain name in the access URL, acquire the edge device IP corresponding to the target service domain name, send the access URL to the edge device IP, and acquire the target object; when the response information contains both the target edge device IP and the access URL, send the access URL to the target edge device IP and acquire the target object.

[0051] Based on the foregoing solution, in an exemplary embodiment, the scheduling device further includes:

[0052] The anomaly reporting module is used to report information about the abnormal service status to the scheduling device when the edge device corresponding to the target service domain name or the target edge device service status is abnormal, so that the scheduling device can adjust the mapping relationship between the object and the service address.

[0053] According to another aspect of this document, a scheduling device is provided for use in an edge device, comprising:

[0054] The second request receiving module is used to receive a second access request from the client containing the service domain name of the service provider, the second access request including the access URL;

[0055] The second response module is used to return the target object corresponding to the access URL;

[0056] The access URL is determined by the scheduling device based on the target object corresponding to the client's first access request and the mapping relationship between the object and the service address.

[0057] The first access request includes the content provider's domain name and file identification information;

[0058] The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

[0059] According to another aspect of this document, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed, implements the steps of a scheduling method.

[0060] According to another aspect of this document, a computer device is provided, including a processor, a memory, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of a scheduling method.

[0061] This paper describes a method where, upon receiving an access request from a client, the scheduling device queries a mapping relationship to determine the access URL, and returns response information containing the access URL to the client. This allows the client to send a second access request to the corresponding edge device based on the access URL, requesting the target object. This enables the scheduling of access requests for the same target object to a specific edge device of a designated CDN service provider, increasing the access frequency of the target object within the CDN service provider's network, improving cache hit rate, reducing origin pulls, decreasing origin pull bandwidth costs, improving response speed, and enhancing service quality. It should be understood that the above general description and the following detailed description are merely exemplary and explanatory and do not limit the scope of this paper. Attached Figure Description

[0062] The accompanying drawings, which form part of this document, are used to provide a further understanding of the document. The illustrative embodiments and descriptions herein are used to explain the document and do not constitute an undue limitation thereof. In the drawings:

[0063] Figure 1 This is a flowchart illustrating a scheduling method according to an exemplary embodiment.

[0064] Figure 2 This is a schematic diagram illustrating the establishment of a mapping relationship between object files and service domain names according to an exemplary embodiment.

[0065] Figure 3 This is a schematic diagram illustrating the mapping relationship between objects and service addresses according to an exemplary embodiment.

[0066] Figure 4 This is a flowchart illustrating a scheduling method applied to a client according to an exemplary embodiment.

[0067] Figure 5 This is a flowchart illustrating a scheduling method applied to an edge node according to an exemplary embodiment.

[0068] Figure 6 This is a block diagram illustrating a scheduling device according to an exemplary embodiment.

[0069] Figure 7 This is a block diagram illustrating a scheduling device according to an exemplary embodiment.

[0070] Figure 8 This is a block diagram illustrating a scheduling device according to an exemplary embodiment.

[0071] Figure 9 This is a block diagram illustrating a scheduling device according to an exemplary embodiment.

[0072] Figure 10 This is a block diagram illustrating a scheduling device according to an exemplary embodiment.

[0073] Figure 11 This is a block diagram illustrating a computer device according to an exemplary embodiment. Detailed Implementation

[0074] To make the objectives, technical solutions, and advantages of the embodiments described herein clearer, the technical solutions in the embodiments will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments described herein, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments described herein without creative effort are within the scope of protection of this document. It should be noted that, unless otherwise specified, the embodiments and features described herein can be arbitrarily combined with each other.

[0075] Content providers (which can be website users) choose a CDN service provider's network to accelerate their website content. They set an alias for their domain name in the DNS authoritative server; this alias is the CDN service provider's accelerated domain name. When the DNS authoritative server receives an access request from a client that includes the content provider's domain name, it resolves the content provider's domain name to the accelerated domain name, thus routing the client's traffic to the corresponding CDN service provider's network, where nodes in the CDN network provide acceleration services. As the website grows, content providers can choose multiple CDN service providers to jointly provide acceleration services for their website content.

[0076] In related technologies, bandwidth for accessing a domain can be allocated to different CDN service providers based on regional DNS resolution, or according to a preset ratio. When a user accesses online content through a client, sending a target URL to the internet system, the DNS domain name resolution system first resolves the content provider's domain name in the URL requested by the client. The resolution result is the designated entry domain name of a specific CDN service provider, i.e., the service domain name of the CDN service provider. Further resolution of the service domain name can route the client's request to the network system of the corresponding CDN service provider. When an online content provider uses the CDN networks of multiple CDN service providers for domain name acceleration, the bandwidth traffic for accessing a particular domain name is allocated to different CDN service providers based on different access regions, or according to a preset ratio, during DNS domain name resolution. For example, for access traffic to a particular domain name, the domain name of the request URL in region A is resolved to CDN service provider 1, and the domain name of the request URL in region B is resolved to CDN service provider 2. Alternatively, 80% of the access traffic is routed to CDN service provider 1, and 20% of the access traffic is routed to CDN service provider 2. When the bandwidth traffic for accessing a content provider's domain is distributed across the network nodes of multiple CDN service providers, it results in the request traffic for the same object file being distributed to the network nodes of multiple CDN service providers. Each of these network nodes needs to fetch the object file from the upper-layer server or the origin server and cache multiple copies of the cached file.

[0077] For object files with low access frequency, scheduling using traditional methods will further reduce the access frequency of the object file in each CDN service provider's network, leading to a decrease in cache hit rate. Furthermore, edge servers in the network nodes of multiple CDN service providers that are accessing the object file need to fetch it from upstream and cache it. This results in increased caching costs, increased time spent fetching object files, increased bandwidth consumption of the CDN network going upstream, and longer response latency, among other cost and quality of service issues.

[0078] This paper presents a scheduling method in which network content providers collaborate with multiple CDN service providers, and the networks of multiple CDN service providers provide acceleration services for the network content provided by the content provider, which can improve the speed at which clients obtain object files and improve service quality.

[0079] The scheduling device can be a domain name resolution server set up by the content provider to schedule network requests across the networks of multiple CDN service providers.

[0080] Figure 1 This is a flowchart illustrating a scheduling method according to an exemplary embodiment. (See reference) Figure 1 The scheduling method is applied to scheduling equipment and includes at least steps S11 to S13, which are described in detail below:

[0081] Step S11: Receive a first access request from the client, including the content provider's domain name and file identification information, and determine the target object corresponding to the first access request.

[0082] The client sends an access request in the form of a URL. The URL includes the content provider's domain name and the identifier of the file to be accessed. For example, the URL might be http: / / www.aaa.com / test.mp4, where www.aaa.com is the content provider's domain name and test.mp4 is the file identifier. First, the client's access request is sent to the DNS domain name resolution system. The DNS system resolves the content provider's domain name in the URL level by level, resolving the address of the scheduling device to the client. The client then sends the access request to the scheduling device based on the scheduling device's address. Upon receiving the user's request, the scheduling device can obtain the file identifier information of the target object in the URL, thereby determining the corresponding target object. For example, in the client's access request URL http: / / www.aaa.com / test.mp4, the scheduling device can determine that the target object to be accessed is test.mp4.

[0083] Step S12: Query the mapping relationship between the object and the service address to determine the access URL corresponding to the target object.

[0084] The mapping relationship can be pre-established by the content provider to identify which CDN service provider's service address corresponds to the target object. In other words, the user pre-determines which CDN service provider will provide acceleration services for the target object. It's worth noting that for low-traffic object files within a content provider's domain, if access requests for these object files are routed to different CDN service providers' networks, multiple edge servers in multiple CDN service providers' networks will fetch the object files from upper-layer servers or the origin server and cache them on various edge servers. Therefore, for low-traffic object files, it's desirable to have fewer edge servers providing services, thereby reducing the amount of caching. Content providers can predict the potential access popularity of object files within a domain based on past experience and forecast data. For object files predicted to have low access popularity, advance planning is conducted, determining which CDN service provider will provide acceleration services for each object file. A mapping relationship between each object file and its service address is established according to this plan. This mapping relationship can be stored in the scheduling device or a designated server for easy querying by the scheduling device.

[0085] The service address includes different service domains from different service providers, or all edge device IPs corresponding to the service domain, where the service domain is an alias of the content provider's domain to the service provider's domain. The service address can be either the service domain of the service provider or include the edge device IPs corresponding to the service domain.

[0086] An edge device can be the entry device of the edge node corresponding to the service domain name. In this application, the entry device of the edge node includes, but is not limited to, the load balancer, edge gateway, edge controller, edge router, or network set-top box of the edge node, etc., and is not limited thereto. Any other forms of edge devices, whether existing or emerging in the future, that are applicable to this application should be included within the scope of protection of this application. An edge device can also be a real edge server in an edge node.

[0087] For example, according to the content provider's plan, the file test1.mp4 on the domain www.ABC.com is accelerated by CDN service provider 1. CDN service provider 1's service domain is www.a.com. A mapping relationship can be established between test1.mp4 and the service domain www.a.com. When the scheduling device receives an access request http: / / www.ABC.com / test1.mp4, based on the mapping relationship, test1.mp4 corresponds to the service domain www.a.com, and the access URL is determined to be http: / / www.a.com / test1.mp4. The client resolves the server domain www.a.com, which can resolve to the address of the entry device of CDN service provider 1's edge node or the actual edge server address of CDN service provider 1. This allows the access request to be scheduled to the entry device of CDN service provider 1's edge node or the actual edge server address of CDN service provider 1. This not only increases the probability of subsequent users hitting the cached file and shortens the path to fetch the file upstream, reducing access waiting time, but also saves storage space.

[0088] For example, according to the content provider's plan, the file test2.mp4 is accelerated by CDN service provider 2, which specifies that a real edge server will provide this acceleration service. CDN service provider 2's service domain name is www.b.com, and the specified IP address of the edge server is 192.168.222.2. A mapping relationship is established between test2.mp4 and the service domain name: www.b.com and the IP address: 192.168.222.2. When the scheduling server receives an access request http: / / www.ABC.com / test2.mp4, based on the mapping relationship, test2.mp4 corresponds to the service domain name www.b.com and also to the IP address: 192.168.222.2. The scheduling device can then determine that the access URL is http: / / www.b.com / test1.mp4. The system sends the access URL (http: / / www.b.com / test1.mp4) and IP address (192.168.222.2) to the client in the response. This allows the client to request the object file from the designated edge server of CDN Service Provider 2, thus routing the access request to that edge server. This prevents the accessed file from being assigned to other CDN service providers or servers, which would reduce file popularity, thereby improving cache sharing, reducing CDN back-to-upstream bandwidth, and lowering service costs. It also reduces the redirection process for hot / cold file separation, improving service quality.

[0089] In one embodiment, establishing a mapping relationship between an object file and a service address ensures that the same object file is accelerated by a single edge device or the same edge device from the same CDN service provider, thereby guaranteeing the access frequency of the file and improving response speed. This avoids access requests for the same object file being routed to the CDN networks of multiple CDN service providers, which could further decrease access frequency and reduce cache hit rate. It also avoids the network bandwidth consumption caused by multiple edge servers in multiple edge nodes fetching file resources from upstream when acceleration services are provided by multiple CDN service providers.

[0090] In one embodiment, an object file is mapped to two or more service addresses, and access requests are scheduled to edge devices or designated edge servers within the network of a specified CDN service provider, rather than being randomly scheduled across the entire CDN service provider network. This increases the access frequency of the file to some extent and reduces network bandwidth consumption. Moreover, if an edge device of one CDN service provider fails, the service can be promptly switched to an edge device of another CDN service provider, ensuring service quality.

[0091] The mapping relationship between object files and service addresses needs to be determined based on the potential access frequency or actual access frequency of each object file.

[0092] Step S13: Return response information containing the access URL so that the client can send a second access request to the corresponding edge device based on the access URL, requesting the target object.

[0093] In a CDN network, the name of a cached file generally corresponds to the access URL. When a client requests a target file from the service provider's edge device, it needs to send the access URL to the edge device in order to hit the cached file.

[0094] The system returns a response containing the access URL to the client. Based on the access URL in the response, the client can send a domain name resolution request again. Since the domain name in the access URL is the service domain name of the CDN service provider, the access request will be resolved to the entry device of the corresponding CDN service provider's edge node or the corresponding edge server.

[0095] For example, when the scheduling device receives a client's first access request http: / / www.ABC.com / test1.mp4, it queries the mapping relationship and determines that the service domain name corresponding to the target object test1.mp4 is www.a.com. It can then generate a response containing the access URL http: / / www.a.com / test1.mp4 and send the response to the client. Upon receiving the response, the client resolves the service domain name www.a.com in the access URL http: / / www.a.com / test1.mp4. The service domain name www.a.com is resolved by the domain name resolution system to the IP address of the entry device or edge server of the edge node of CDN service provider 1. The client then sends a second access request http: / / www.a.com / test1.mp4 to the entry device or edge server of the edge node of CDN service provider 1, and ultimately, the edge server within the edge node provides acceleration services.

[0096] Upon receiving a second access request from a client, the ingress device at the edge node of a CDN service provider, assuming it is a load balancer, forwards the request to the backend edge server. If the edge server does not have a cached file of test1.mp4 locally, it retrieves the file from the upper-layer node, responds to the client, and caches it locally. When a client subsequently requests the same target object again, or when other clients request the same target object, the scheduling device again follows the above steps to schedule client requests, directing access requests for the same target object to the ingress device at the same CDN service provider's edge node. This improves cache hit rate, reduces the number of origin server requests, lowers network bandwidth consumption, and simultaneously improves response speed and service quality.

[0097] In this embodiment, the scheduling device schedules requests based on the target object in the first access request. Requests to access the same target object will be scheduled by the content provider's scheduling device to the edge server of a CDN service provider, which will then provide services. This increases the access popularity of the target object in the CDN network, improves the cache hit rate, reduces the number of times nodes return to the origin, reduces the origin bandwidth cost, improves the response speed, and enhances the service quality.

[0098] In one exemplary embodiment, the mapping relationship is determined by the scheduling device based on service domain names or edge device IPs obtained in advance from different service providers.

[0099] After selecting multiple CDN service providers to accelerate website content, content providers need to determine which object files within the website require scheduling before dispatching client access requests. They also need to pre-determine which service provider's edge devices will provide acceleration services for each object file, i.e., determine the service address of the object file. Therefore, they need to obtain service domain names, edge device IP addresses, etc., from different service providers. Due to their own considerations, some service providers may only provide their own service domain names, while others may provide both their own service domain names and specific node coverage schemes, such as different nodes configured in different regions, and the IP addresses of edge servers within each node. Content providers need to establish mapping relationships based on the information provided by different service providers to ensure service availability.

[0100] The mapping relationship can be a mapping between a target object and a service domain name, or a mapping between a target object and an edge device. After determining the mapping relationship between the object and the service address, the mapping relationship is stored in the scheduling device so that the scheduling device can quickly query and determine the access URL corresponding to the target object, thereby scheduling the client's first access request.

[0101] In an exemplary embodiment, querying the mapping relationship between the query object and the service address to determine the access URL corresponding to the target object includes:

[0102] Each object corresponds to a unique object key;

[0103] Each service domain name corresponds to a unique domain key;

[0104] Each object key is mapped to a domain key;

[0105] Calculate the target object key and determine the access URL based on the mapping relationship.

[0106] Because there is a mapping relationship between an object key and a domain key—a one-to-one mapping between objects and object keys, and a one-to-one mapping between service domains and domain keys—there is also a mapping relationship between objects and domains. When the scheduling system receives an access request and determines the target object based on the file identifier information in the request, it uses a preset algorithm to calculate the object key of the target object. By querying the mapping relationship between the object key and the domain key, it can quickly find the service domain corresponding to the object file.

[0107] The mapping relationship between an object key and a domain key is determined through function mapping. When it is necessary to adjust the mapping relationship, it can be done quickly and conveniently by modifying the function parameters.

[0108] Figure 2 This is a schematic diagram illustrating the establishment of a mapping relationship between object files and service domain names according to an exemplary embodiment. (See reference) Figure 2 This application describes a content provider website with n object files (URL1-URLn) that require scheduling using the method provided. The website collaborates with nine CDN service providers (C1-C9), who provide acceleration services. A unique object key is generated for each object file using an algorithm (F(m) in the diagram), resulting in a one-to-one correspondence between the n object keys (KEY1-KEYn) and the n object files. Each CDN service provider corresponds to a service domain (D1-D9 in the diagram). A domain key is generated for each service domain using an algorithm (G(m) in the diagram), resulting in a one-to-one correspondence between the nine domain keys (DOM1-DOM9) and the service domains. Finally, a mapping between object keys and domain keys is established using function mapping. For example, if the target object is http: / / www.aaa.com / test.mp4, the calculated object key (KEY3) is 10001. The remainder of 10001 divided by 9 is 2, thus mapping the target object test.mp4 to DOM2. Similarly, the same function is used to calculate the KYE of each object file, creating a mapping between each object file and a domain name. When a client sends a request for http: / / www.aaa.com / test.mp4, the scheduling device uses the same function to calculate the KYE of the requested URL, obtaining the KYE of the target object. By querying the mapping relationship, the domain name KEY corresponding to the target object test.mp4 is determined: DOM2. DOM2 corresponds to the service domain name D2 of the C2CDN service provider, generating the access URL http: / / D2 / test.mp4 and responding to the client. The client then initiates another domain name resolution request, the result of which is the IP address of the entry device or edge server of the C2 edge node of the CDN service provider. This method establishes a function mapping between object keys and domain names. Since the object keys and domain names occupy relatively few bytes, fast lookups are possible. Each object corresponds to a unique service domain name, allowing access requests for the same file to be scheduled to the entry device or edge server of the same CDN service provider's edge node. The edge server within the same CDN service provider's edge node provides accelerated services, thereby improving cache hit rate, reducing cache resource consumption, and increasing response speed.

[0109] In addition to the remainder method mentioned above, the mapping relationship between object keys and domain keys can also be established through functions such as direct addressing, digital analysis, mid-square, folding, MD5 (message digest algorithm), and SHA (hash algorithm). This article does not restrict the specific function form to be chosen.

[0110] After establishing the mapping relationship between object keys and domain keys, for each object file, there is one and only one CDN service provider's service domain name corresponding to it. This ensures that the scheduling device can determine the unique corresponding service domain name for access requests to the target object by querying the mapping relationship between object files and service domain names. In turn, access requests to the same object file are scheduled to the entry device or edge server of the edge node of the same CDN service provider, which improves the cache hit rate, reduces the number of caches, reduces the number of origin pulls, and reduces bandwidth consumption.

[0111] Based on the above embodiments, in an exemplary embodiment, the access URL corresponding to the target object includes the target service domain name mapped to the target object and the path of the target object.

[0112] An access URL can be generated based on the path of the target object and the corresponding target service domain name. For example, if a scheduling device receives a request for http: / / www.aaa.com / test.mp4, queries the mapping relationship, determines the target service domain name as D2, and generates an access URL of http: / / D2 / test.mp4 based on the target domain name D2 and the path of the target object / test.mp4. Of course, in practice, the access URL can also include access parameters, access tags, and other information. When scheduling, the scheduling device replaces the original domain name in the request with the target service domain name to quickly generate the access URL and schedule the access request to the edge device of the CDN service provider corresponding to the target service domain name.

[0113] In one exemplary embodiment, response information containing an access URL is returned, enabling the client to send a second access request to the corresponding edge device based on the access URL. The target object of the request includes:

[0114] The system returns a response containing the access URL to the client, enabling the client to request domain name resolution from the authoritative DNS of the service provider corresponding to the target service domain name and obtain the edge device IP. The system then sends the access URL to the edge device IP to request the target object. The edge device IP can be the virtual IP of the edge node's entry device or the real IP of the edge server.

[0115] After generating the access URL, the scheduling device returns a response containing the access URL to the client. Upon receiving the response, the client sends a domain name resolution request for the access URL. This request is sent to the authoritative server of the CDN service provider corresponding to the target service domain. The authoritative server resolves the URL to obtain the edge device IP. The edge device IP can be the IP of the edge node's ingress device (e.g., the virtual IP of a load balancer within the edge node). The authoritative server returns the resolved edge node ingress device IP to the client, allowing the client to send the access URL to that ingress device. The ingress device then forwards the URL to the edge server within the node, which then sends the target object to the client. Alternatively, the edge device IP can also be the IP of an edge server provided by the CDN service provider. The authoritative server returns the resolved edge server IP to the client, enabling the client to send the access URL to that edge server IP, which then returns the target object to the client.

[0116] For example, when a client requests http: / / www.aaa.com / test.mp4 from the scheduling device, the scheduling device determines the service domain name as D2 and the target object's path as / test.mp4 based on the mapping relationship between objects and service domain names; thus, it generates the access URL: http: / / D2 / test.mp4. Alternatively, it replaces the original domain name in the request URL with the service domain name D2 to generate the access URL. This access URL is then sent to the client as a response. The client then initiates a domain name resolution request, which is sent to the authoritative server of CDN service provider C2. This access URL is resolved to the load balancer at the edge node of CDN service provider C2, where acceleration services are provided.

[0117] In practical applications, the client requests the target file test.mp4 from the load balancer at the edge node of CDN service provider C2. The load balancer forwards the request to the backend edge server. Alternatively, the client requests test.mp4 from the edge server of CDN service provider C2. If the edge server does not cache test.mp4, it retrieves test.mp4 from the upper-layer server or the origin server and caches it locally. If the edge server already caches test.mp4, it directly responds to the client. Therefore, using the scheduling method provided in this paper, requests for the same file from different clients will be scheduled to the same edge node of the same CDN service provider. Compared to traditional technologies, this reduces the number of origin server requests, lowers bandwidth consumption, saves caching resources, and improves response speed.

[0118] In an exemplary embodiment, querying the mapping relationship between the query object and the service address to determine the access URL corresponding to the target object includes:

[0119] Each object corresponds to a unique object key;

[0120] Each edge device corresponds to a unique device key;

[0121] Each object key is mapped to a device key;

[0122] Calculate the target object KEY, and determine the access URL and target edge device IP based on the mapping relationship.

[0123] Figure 3 This is a schematic diagram illustrating the mapping relationship between objects and service addresses according to an exemplary embodiment. (Reference) Figure 3Taking a content provider website with n object files (URL1-URLn) requiring scheduling using the scheduling method provided in this application, and collaborating with nine CDN service providers (C1-C9) to provide acceleration services as an example: A unique object key is generated for each object file using the corresponding algorithm (F(m) in the diagram), thus corresponding one-to-one with each of the n object files (KEY1-KEYn). Each CDN service provider corresponds to a service domain name (D1-D9 in the diagram), and each service domain name corresponds one-to-one with an edge node. Each edge node includes multiple edge devices, and a one-to-one correspondence between edge devices and device keys is established using the corresponding algorithm (G(m) in the diagram). Finally, a mapping relationship between object keys and device keys is established through function mapping. For example, if the target object is http: / / www.aaa.com / test.mp4, the object key is calculated for the target object, and the function mapping determines that the target object test.mp4 is mapped to N1n. Similarly, the same function is used to calculate the key for each object file, and each object file is mapped to a device key. When the scheduling device receives a request from a client for http: / / www.aaa.com / test.mp4, it uses the same function to calculate the target object's key (KEY). By querying the mapping relationship, it determines the target edge device's key (KEY: N1n) corresponding to the target object test.mp4. N1n corresponds to the CDN service provider C1's service domain name D1. It can further determine the target edge device ND1n and ultimately its IP address. The scheduling device generates an access URL of http: / / D1 / test.mp4 and sends the access URL and the edge device's IP address as response information to the client. The edge device's IP address can be the virtual IP address of the edge node's entry device or the real IP address of the edge server.

[0124] Based on the mapping relationship, the scheduling device determines the target edge device corresponding to the target object and responds to the client with an access URL and the IP address of the target edge device, enabling the client to request the target object from the target edge device. Since the scheduling device provides the IP address of the edge device, the client does not need to resolve the service domain name in the access URL after receiving it, thus improving access speed. Furthermore, when the target edge device is an edge server, the client can send requests to the edge server, preventing multiple access requests for the same object file from being load-balanced across multiple edge servers, further reducing the amount of cached data, improving cache hit rate, and avoiding waste of cache resources.

[0125] In one exemplary embodiment, the response information further includes the target edge device IP address, and returns response information containing an access URL, so that the client sends a second access request to the corresponding edge device based on the access URL, requesting the target object including:

[0126] The system returns a response to the client containing the access URL and the IP address of the target edge device, enabling the client to send the access URL to the target edge device IP address and request the target object.

[0127] Because the scheduling device queries the mapping relationship, it can determine the access URL and the target edge device IP, and respond to the client with response information including the access URL and the target edge device IP. Upon receiving the response information, the client can send a second access request to the target edge device IP in the corresponding content provider network to obtain the target object. The client no longer resolves the service domain name in the access URL, but directly sends the second access request to the edge device, improving efficiency. When the edge device is an edge server, it can also schedule access requests for the same target file to a designated edge server within an edge node of the same CDN service provider, where the designated edge server provides acceleration services. Compared to load balancing devices that schedule access requests to edge nodes, this embodiment only stores cached files on a designated server within the edge node, further saving cache resources. Simultaneously, after receiving the response information, the client can directly request the target object from the target edge server without needing to resolve the domain name in the access URL, improving the speed of obtaining the target object.

[0128] The above describes a method that maps an object file address to a short string to ensure the uniqueness of the object file. Each object file is mapped to an object key using an irreversible function. Simultaneously, the domain key corresponding to the CDN service provider's accelerated domain or the device key corresponding to the edge device is calculated. By establishing a correspondence between the object file's key and the CDN provider's accelerated domain or edge device key, access to the same object file is assigned to the same CDN service provider or the same edge device. This increases the probability of subsequent users hitting the cached file, shortens the path to fetch the file upstream, and reduces access waiting time.

[0129] In one exemplary embodiment, the scheduling method further includes:

[0130] Receive feedback information from the client regarding the abnormal service status of the edge device corresponding to the target service domain name or the target edge device, and adjust the mapping relationship accordingly.

[0131] According to the aforementioned embodiments, after the scheduling device schedules the client's first access request based on the target service domain name, the client's second access request may be scheduled to the edge device of the target service domain name or directly to the target edge device. The client sends the second access request to the edge device of the target service domain name or the target edge device. If the edge device of the target service domain name or the target edge device experiences a service failure, the client needs to report feedback information about the abnormal service status of the edge device corresponding to the target service domain name or the target edge device to the scheduling device. The scheduling device promptly adjusts the mapping relationship between objects and service addresses, scheduling subsequent client access requests to the edge devices of other CDN service providers or directly to the target edge devices of other CDN service providers, thereby improving service quality.

[0132] In one exemplary embodiment, after receiving an access request from a client and determining the target object corresponding to the access request, the scheduling method further includes:

[0133] Determine the access frequency of the target object. When the access frequency is less than or equal to a preset threshold, return the source address corresponding to the target object to the client so that the client can directly request the target object from the source server.

[0134] In real-world applications, some files have very low access frequency. For example, private files shared among friends, accessed only a few times a month. If requests for such files are routed to a CDN network, where CDN nodes fetch the target object from the origin server and cache it, multiple copies might be cached on edge and upper-layer nodes within the CDN network. However, within the cache's validity period, the corresponding request might not be received again. When a user requests it again, the CDN nodes need to fetch it from the origin server again because the cache expiration date has passed. This not only fails to speed up the process but also wastes significant CDN network resources, doubling the cost. Therefore, when the scheduling device receives a client's request and identifies the target object, it first determines the access frequency of that target object. The access frequency is the number of times the target object is accessed within a unit of time. This could be the number of accesses within a day, a week, or a longer or shorter timeframe, depending on the specific network environment. If the access frequency of the target object is less than or equal to a preset threshold, the origin server address corresponding to the target object is returned to the client, and the client directly connects to the origin server to obtain the target object, instead of scheduling the client's request to any CDN service provider, thus avoiding unnecessary waste of CDN network resources.

[0135] Similarly, for a file, if future access popularity is unpredictable at the time of its release, a mapping relationship can be established between the file and a service domain name. Access requests for this file can then be routed to a CDN service provider's network, where edge nodes of that CDN service provider handle the service, reducing cache size and improving cache hit rate. However, once the file's access popularity reaches a preset level, rerouting access requests using the above method may overload the edge nodes, affecting response speed. In this case, the scheduling strategy can be switched to a strategy for popular files.

[0136] Figure 4 This is a flowchart illustrating a scheduling method applied to a client according to an exemplary embodiment. (Reference) Figure 4 The scheduling method is applied to the client and includes:

[0137] Step S41: Send a first access request including the content provider's domain name and file identification information;

[0138] Step S42: Receive the response information returned by the scheduling device in response to the first access request;

[0139] Step S43: When the response information contains an access URL, send a domain name resolution request to the authoritative DNS of the service provider corresponding to the target service domain name in the access URL, obtain the entry device IP or edge server IP of the edge node corresponding to the target service domain name, send the access URL to the entry device IP or edge server IP of the edge node, and obtain the target object; when the response information contains the target edge server IP and the access URL, send the access URL to the target edge server IP and obtain the target object.

[0140] The client sends an access request to the scheduling device, including the content provider's domain name and file identifier information, and receives a response from the scheduling device.

[0141] When the response includes an access URL but not the target edge server IP, the client needs to perform domain name resolution on the access URL. This involves sending a domain name resolution request to the authoritative DNS of the service provider corresponding to the target service domain in the access URL to obtain the edge device IP corresponding to the target service domain. The edge device IP can be the IP of the service provider's edge node's ingress device; the access URL is sent to the edge node's ingress device IP to obtain the target object. Alternatively, the edge device IP can be the service provider's edge server IP; the access URL is sent to the edge server IP to obtain the target object.

[0142] When the response information includes the access URL and the target edge server IP, the client no longer performs domain name resolution on the access URL, but directly sends the access URL to the target edge server IP and obtains the target object.

[0143] In one exemplary embodiment, the scheduling method further includes:

[0144] When the edge device corresponding to the target service domain name or the target edge device service status is abnormal, the information of the abnormal service status is reported to the scheduling device so that the scheduling device can adjust the mapping relationship between the object and the service address.

[0145] When a client requests a target object from the edge device corresponding to the target service domain name or the target edge device itself, if the service status of the edge device or the target edge device is abnormal, the client reports the abnormal service status information to the scheduling device. Upon receiving this abnormal service status information, the scheduling device can promptly adjust the mapping relationship between the object and the service address, scheduling subsequent client access requests to other CDN service providers or directly to the target edge device within another CDN service provider, thereby improving service quality and ensuring continuous service.

[0146] Figure 5 This is a flowchart illustrating a scheduling method applied to an edge node according to an exemplary embodiment.

[0147] refer to Figure 5 The scheduling method is applied to edge nodes, including:

[0148] Step S51: Receive a second access request from the client containing the service provider's service domain name, the second access request including the access URL;

[0149] Step S52: Return the target object corresponding to the accessed URL;

[0150] The access URL is determined by the scheduling device based on the target object corresponding to the client's first access request and the mapping relationship between the object and the service address.

[0151] The first access request includes the content provider's domain name and file identification information;

[0152] The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

[0153] The client sends a first access request to the scheduling device, including the content provider's domain name and file identifier information. The scheduling device then returns a response containing the access URL. Based on this response, the client sends a second access request to the edge device, which, after being scheduled by the scheduling device, includes the service provider's domain name and file identifier in the access URL. Specifically, if the edge device is a load balancer, the client requests the target object from the CDN service provider's load balancer, which forwards the request to the backend edge server. Alternatively, the client requests the target object from the CDN service provider's edge server. If the edge server already caches the object, it responds directly to the client. If the edge server does not cache `test.mp4`, it retrieves the target object from the upper-layer server or the origin server. After retrieving the target object from the origin server, it caches it, with the cache name corresponding to the access URL. When the edge node receives another request containing the access URL, it can quickly find the cached target object based on the URL and respond to the second access request with the cached target object, improving response speed.

[0154] Figure 6 This is a block diagram illustrating a scheduling device according to an exemplary embodiment. (Reference) Figure 6 The scheduling device is applied to the scheduling equipment and includes a first request receiving module 601, a query module 602, and a first response module 603.

[0155] The first request receiving module 601 is configured to receive a first access request from a client, including the content provider's domain name and file identification information, and to determine the target object corresponding to the first access request.

[0156] The query module 602 is configured to query the mapping relationship between objects and service addresses, and to determine the access URL corresponding to the target object.

[0157] The first response module 603 is configured to return response information containing the access URL, so that the client sends a second access request to the corresponding edge device based on the access URL, requesting the target object.

[0158] The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

[0159] Figure 7 This is a block diagram illustrating a scheduling device according to an exemplary embodiment. (Reference) Figure 7 The scheduling device also includes a mapping relationship adjustment module 701.

[0160] The mapping adjustment module 701 is configured to receive feedback information from the client regarding the abnormal service status of the edge device IP corresponding to the target service domain name or the target edge device IP, and adjust the mapping relationship accordingly.

[0161] Figure 8 This is a block diagram illustrating a scheduling device according to an exemplary embodiment. (Reference) Figure 8 The scheduling device is applied to the client and includes a sending module 801, a response receiving module 802, and an acquisition module 803.

[0162] The sending module 801 is configured to send a first access request that includes the content provider's domain name and file identification information.

[0163] The response receiving module 802 is configured to receive response information returned by the scheduling device in response to the first access request.

[0164] The acquisition module 803 is configured to, when the response information contains an access URL, send a domain name resolution request to the authoritative DNS of the service provider corresponding to the target service domain name in the access URL, obtain the edge device IP corresponding to the target service domain name, send the access URL to the edge device IP, and obtain the target object; when the response information contains the target edge server IP and the access URL, send the access URL to the target edge device IP and obtain the target object.

[0165] Figure 9 This is a block diagram illustrating a scheduling device according to an exemplary embodiment. (Reference) Figure 9 The scheduling device also includes an anomaly reporting module 901.

[0166] The anomaly reporting module 901 is configured to report information about the abnormal service status to the scheduling device when the edge device corresponding to the target service domain name or the service status of the target edge device is abnormal, so that the scheduling device can adjust the mapping relationship between the object and the service address.

[0167] Figure 10 This is a block diagram illustrating a scheduling device according to an exemplary embodiment. (Reference) Figure 10 The scheduling device applied to the edge device includes a second request receiving module 1001 and a second response module 1002.

[0168] The second request receiving module 1001 is configured to receive a second access request from a client containing a service provider's service domain name, the second access request including an access URL.

[0169] The second response module 1002 is configured to return the target object corresponding to the access URL.

[0170] The access URL is determined by the scheduling device based on the target object corresponding to the client's first access request and the mapping relationship between the object and the service address.

[0171] The first access request includes the content provider's domain name and file identification information;

[0172] The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

[0173] Figure 11 This is a block diagram illustrating a computer device 1100 for scheduling according to an exemplary embodiment. For example, the computer device 1100 may be provided as a server. (Refer to...) Figure 11 The computer device 1100 includes a processor 1101, the number of which can be set to one or more as needed. The computer device 1100 also includes a memory 1102 for storing instructions executable by the processor 1101, such as application programs. The number of memories can be set to one or more as needed. The stored application programs can be one or more. The processor 1101 is configured to execute instructions to perform the scheduling method described above.

[0174] Those skilled in the art will understand that the embodiments described herein can be provided as methods, apparatus (devices), or computer program products. Therefore, this document may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this document may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Computer storage media include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data), including but not limited to RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0175] This document is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments herein. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0176] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes

[0177] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0178] In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising…” does not exclude the presence of additional identical elements in the article or device that includes said element.

[0179] Although preferred embodiments have been described herein, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this document.

[0180] Obviously, those skilled in the art can make various modifications and variations to this document without departing from its spirit and scope. Thus, if such modifications and variations fall within the scope of the claims and their equivalents, the intent of this document also includes such modifications and variations.

Claims

1. A scheduling method applied to scheduling equipment, characterized in that, The scheduling device is used to schedule network requests across the networks of multiple CDN service providers, including: Receive a first access request from a client, which includes the content provider's domain name and file identification information, and determine the target object corresponding to the first access request; The mapping relationship between the query object and the service address is used to determine the access URL corresponding to the target object. The mapping relationship is for object files with low predicted access popularity. The content provider pre-plans which CDN service provider will provide acceleration services for each object file. The mapping relationship between each object file and the service address is established according to the plan. The system returns response information containing the access URL, enabling the client to send a second access request to the corresponding edge device based on the access URL, requesting the target object. The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

2. The scheduling method as described in claim 1, characterized in that, The mapping relationship between the query object and the service address, and the determination of the access URL corresponding to the target object, include: Each object corresponds to a unique object key; Each service domain name corresponds to a unique domain key; Each object key is mapped to one of the domain keyes; Calculate the target object KEY, and determine the access URL based on the mapping relationship.

3. The scheduling method as described in claim 1, characterized in that, The mapping relationship between the query object and the service address, and the determination of the access URL corresponding to the target object, include: Each object corresponds to a unique object key; Each edge device corresponds to a unique device key; Each object key is mapped to one of the device keys; Calculate the target object KEY, and determine the access URL and target edge device IP based on the mapping relationship.

4. The scheduling method as described in any one of claims 2 or 3, characterized in that, The access URL corresponding to the target object includes the target service domain name mapped to the target object and the path of the target object.

5. The scheduling method as described in claim 4, characterized in that, The response information, which includes the access URL, is returned so that the client can send a second access request to the corresponding edge device based on the access URL. The request to the target object includes: The system returns a response containing the access URL to the client, enabling the client to request domain name resolution from the authoritative DNS of the service provider corresponding to the target service domain name and obtain the edge device IP, and then send the access URL to the edge device IP to request the target object.

6. The scheduling method as described in claim 3, characterized in that, The response information also includes the IP address of the target edge device. The response information, which includes the access URL, enables the client to send a second access request to the corresponding edge device based on the access URL. The request to the target object includes: The system returns a response containing the access URL and the target edge device IP to the client, so that the client sends the access URL to the target edge device IP to request the target object.

7. The scheduling method as described in claim 1, characterized in that, The mapping relationship is determined by the scheduling device based on the service domain names or edge device IPs obtained in advance from different service providers.

8. The scheduling method as described in claim 5 or 6, characterized in that, Also includes: Receive feedback information from the client regarding abnormal service status of the edge device corresponding to the target service domain name or the target edge device, and adjust the mapping relationship.

9. A scheduling method applied to a client, characterized in that, include: Send a first access request including the content provider's domain name and file identification information; The system receives response information returned by the scheduling device in response to the first access request. The response information is obtained by the scheduling device from querying the mapping relationship between the target object and the service address based on the target object corresponding to the first access request, and determining the access URL corresponding to the target object. The mapping relationship is established by the content provider in advance for object files with low predicted access popularity, which CDN service provider will provide acceleration services for each object file, and the mapping relationship between each object file and the service address is established according to the plan. When the response information contains an access URL, a domain name resolution request is sent to the authoritative DNS of the service provider corresponding to the target service domain name in the access URL to obtain the edge device IP corresponding to the target service domain name, the access URL is sent to the edge device IP, and the target object is obtained; when the response information contains the target edge device IP and the access URL, the access URL is sent to the target edge device IP, and the target object is obtained.

10. The scheduling method as described in claim 9, characterized in that, Also includes: When the edge device corresponding to the target service domain name or the service status of the target edge device is abnormal, the abnormal service status information is reported to the scheduling device so that the scheduling device can adjust the mapping relationship between the object and the service address.

11. A scheduling method applied to edge devices, characterized in that, include: The client receives a second access request containing the service provider's service domain name, and the second access request includes an access URL; Returns the target object corresponding to the access URL; The access URL is determined by the scheduling device based on the target object corresponding to the first access request of the client, querying the mapping relationship between the object and the service address, and determining the access URL corresponding to the target object. The mapping relationship is for object files with predicted low access popularity. The content provider pre-plans which CND service provider will provide acceleration services for each object file, and establishes the mapping relationship between each object file and the service address according to the plan. The first access request includes the content provider's domain name and file identification information; The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

12. A scheduling device, applied to scheduling equipment, characterized in that, include: The first request receiving module is used to receive a first access request from the client, including the content provider's domain name and file identification information, and to determine the target object corresponding to the first access request. The query module is used to query the mapping relationship between objects and service addresses, and determine the access URL corresponding to the target object. The mapping relationship is for object files with predicted low access popularity. The content provider pre-plans which CDN service provider will provide acceleration services for each object file, and establishes the mapping relationship between each object file and the service address according to the plan. The first response module is used to return response information containing the access URL, so that the client sends a second access request to the corresponding edge device according to the access URL to request the target object; The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

13. The scheduling device as described in claim 12, characterized in that, Also includes: The mapping relationship adjustment module is used to receive feedback information from the client regarding the abnormal service status of the edge device corresponding to the target service domain name or the target edge device, and adjust the mapping relationship accordingly.

14. A scheduling device applied to a client, characterized in that, include: The sending module is used to send a first access request, including the content provider's domain name and file identification information; The response receiving module is used to receive response information returned by the scheduling device in response to the first access request. The response information is obtained by the scheduling device from querying the mapping relationship between the target object and the service address based on the target object corresponding to the first access request, and determining the access URL corresponding to the target object. The mapping relationship is established by the content provider in advance for object files with low predicted access popularity, which CDN service provider will provide acceleration services for each object file, and the mapping relationship between each object file and the service address is established according to the plan. The acquisition module is configured to, when the response information contains an access URL, send a domain name resolution request to the authoritative DNS of the service provider corresponding to the target service domain name in the access URL, acquire the edge device IP corresponding to the target service domain name, send the access URL to the edge device IP, and acquire the target object; when the response information contains both the target edge device IP and the access URL, send the access URL to the target edge device IP and acquire the target object.

15. The scheduling device as described in claim 14, characterized in that, Also includes: The anomaly reporting module is used to report information about the abnormal service status to the scheduling device when the edge device corresponding to the target service domain name or the target edge device service status is abnormal, so that the scheduling device can adjust the mapping relationship between the object and the service address.

16. A scheduling device applied to an edge device, characterized in that, include: The second request receiving module is used to receive a second access request from the client containing the service domain name of the service provider, the second access request including the access URL; The second response module is used to return the target object corresponding to the access URL; The access URL is determined by the scheduling device based on the target object corresponding to the first access request of the client, querying the mapping relationship between the object and the service address, and determining the access URL corresponding to the target object. The mapping relationship is for object files with predicted low access popularity. The content provider pre-plans which CDN service provider will provide acceleration services for each object file, and establishes the mapping relationship between each object file and the service address according to the plan. The first access request includes the content provider's domain name and file identification information; The service address includes different service domains of different service providers, or all edge device IPs corresponding to the service domain, wherein the service domain is an alias of the content provider's domain to the service provider's domain.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the steps of the scheduling method as described in any one of claims 1-11.

18. A computer device comprising a processor, a memory, and a computer program stored in the memory, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-11.

Images