CN100349431C - Layered content distributing network and method thereof - Google Patents

Abstract

The present invention discloses a layered content distribution network, which is composed of a content issuance layer, a content distribution layer comprising at least a one-level distribution sublayer, and a margin service layer, wherein the content issuance layer comprises at least one ICP node. The content issuance layer is directly connected with the one-level distribution sublayer in the content distribution layer. Each level distribution sublayer of the content distribution layer is composed of at least one distribution node. The lowest level distribution sublayer in the content distribution layer is directly connected with the margin service layer. The margin service layer is composed of at least one margin service area. A content of the content issuance layer, needs to be issued, is step by step and downwards distributed to the margin service layer by the distribution node in the one-level distribution sub layer directly connected with the content issuance layer; meanwhile, the present invention also discloses a method of content layered distribution. The present invention is used for making the network assembly mode of CDN flexible. The scheduling mode of the traditional CDN is optimized, the service quality of the CDN is enhanced, the distributed service and the zone balance of service loads can be realized, and an access hit ratio can be enhanced.

Description

A layered content distribution network and method for layered content distribution

technical field

The present invention relates to content distribution network technology, in particular to a layered content distribution network and a method for layered content distribution.

Background technique

With the rapid growth of Internet users and the increasing demands of users for improving the quality of Internet services, the traditional mode of providing information services directly by Internet Content Provider (ICP, Internet Content Provider) is facing serious challenges. ICP application sites generally establish physical sites in one or a few places to provide information services to Internet users across the country and even around the world. Due to the structural characteristics of the Internet and the bottleneck of network bandwidth, people have long delays and low efficiency when accessing global sites.

Information distribution is an effective way to solve these problems, that is, by building a new layer of network on the basis of the existing Internet - Content Delivery Network (CDN, Content Delivery Network), which is specially used to efficiently deliver rich multimedia through the Internet. content. CDN greatly improves the response speed of the network by realizing the user's nearby access to the website and the intelligent distribution of network traffic, and technically solves the problems caused by the small network bandwidth, the large number of user visits, and the uneven distribution of network points. The problem that the access effect is affected. The technical principle of CDN is to push the content of the website from the backbone of the network to the "edge" of the network closest to the user in the existing Internet network, so as to reduce transmission delay, network jitter and other factors that affect the effect, thereby providing orderly And high-quality services enable users to obtain the required information at the fastest speed and from the place closest to the user. Since this technology has greatly alleviated the congestion of the Internet, the website has the ability to provide more content services such as video programs and song-on-demand services with huge data traffic. At the same time, the reliability of various services such as online transactions and online banking can also be guaranteed. be effectively guaranteed. In short, CDN can pre-publish the information of the ICP site to the edge device of the network, so that users can get a quick response on the nearest edge device when they visit the site, thereby improving the service quality for users and reducing the burden on the center. Node load.

The current CDN network structure is relatively simple, whether it is enterprise-wide, metropolitan-wide or nationwide, it adopts a single-level structure, and its network structure is shown in Figure 1. The main components of CDN are global load balancer, center server (CS), edge server (ES) and other equipment, and its network architecture can be divided into two parts: center and edge. The central part is generally composed of global load balancer, central server and other devices, and the edge part is generally composed of many edge servers, which serve as the edge device part that provides users with access information. The information of the ICP site is pre-published to each edge server through the central server, and each user's access request to the ICP site is dispatched by the global load balancer. From the CDN network structure shown in Figure 1, it can be seen that although the edge servers of the CDN are distributed at the edge of the network, the global load balancer as a scheduler is still concentrated in the center of the network.

In the above CDN network structure, the general user access scheduling process is shown in Figure 2, including the following steps:

In step 201, a user accesses a World Wide Web (WEB) website through a browser, and clicks on content in the website.

Step 202, the browser of the user terminal requests the local domain name server (DNS, Domain Name Server) to resolve the domain name of the website.

Step 203, the local DNS requests resolution from the authorized DNS of the website.

Step 204, the authoritative DNS of the website notifies the local DNS that the authoritative DNS of the subdomain name of the website domain name is the global load balancer, and returns the IP address of the global load balancer.

Step 205, the local DNS sends a resolution request to the global load balancer.

In step 206, the global load balancer selects an optimal ES based on a certain preset strategy, generally in a round-robin manner, and returns the IP address of the ES to the local DNS.

Step 207, the local DNS returns the IP address of the ES to the browser of the user terminal.

Step 208, the user accesses the above-mentioned ES according to the returned IP address, and sends a request to it.

Step 209, if the ES does not have the content required by the user, the ES obtains the content required by the user from the central server, and then executes step 210; otherwise, directly executes step 210.

Step 210, the ES provides the required content according to the user's request.

Although the CDN using the above scheme has improved the user's access quality to a certain extent, there are still some problems that make the CDN far from perfect in terms of service quality and network efficiency. For example: ① It is difficult to implement large-scale CDN Networking; ②Because of the unified and centralized scheduling method, no matter how wide the coverage area is, the global load balancer as the scheduler is centralized together, resulting in heavy load and slow response of the scheduler, and the concurrent load of the scheduler The ability requirements are also very high; ③The proximity of users cannot be detected according to the user's IP address, and the nearest scheduling can be accurately performed; ④In terms of content publishing management, only pull-down (PULL) is supported, push (PUSH) is not supported, and the active push capability is weak; ⑤When selecting an edge server, the content is not detected, resulting in a low access hit rate, and the busy or idle status of the network is not detected, so a network with low traffic cannot be selected to provide services, etc.

Currently, there is another solution using a Layer 4 (L4) switch. In this solution, the L4 switch has the function of the global load balancer in the above solution. The general user access scheduling process of this solution is shown in Figure 3, including the following steps:

In step 301, a user accesses a WEB website through a browser, and clicks on content in the website.

Step 302, the browser of the user terminal requests the local DNS to resolve the domain name of the website.

Step 303, the local DNS forwards the resolution request to the L4 switch.

In step 304, the L4 switch requests resolution from the authorized DNS of the website.

Step 305, the authorized DNS of the website resolves the IP addresses of multiple ESs according to the request, and returns these IP addresses to the L4 switch.

In step 306, the L4 switch selects the best ES among multiple ESs according to a certain preset strategy, such as round robin, and returns the IP address of the ES to the local DNS.

Step 307, the local DNS returns the IP address of the ES to the browser.

Step 308, the user accesses the ES according to the IP address returned by the local DNS, and sends a request to it.

Step 309, if the ES does not have the content required by the user, the ES obtains the content required by the user from the central server, and then executes step 310; otherwise, directly executes step 310.

Step 310, the ES provides the required content according to the user's request.

There are still some problems in the CDN using the above scheme, for example: all accesses are concentrated to the L4 switch, and its load is too heavy; for user requests, the L4 switch can only process the information of the fourth layer of the network protocol, but not the seventh layer information, that is, the content cannot be detected, etc.

From the above two solutions, it can be seen that with the increase of users, the currently widely used single-level CDN cannot adapt to a large-scale and high-density application environment, and cannot realize distributed services and regional balance of business load.

Contents of the invention

In view of this, the main purpose of the present invention is to provide a layered content distribution network and a method for layered content distribution, so that the networking mode of CDN is more flexible, the scheduling mode of traditional CDN is optimized, and the service quality of CDN is improved, and It can realize distributed services and regional balance of business load, and can improve the hit rate of access.

In order to achieve the above object, technical solution of the present invention is achieved in that way:

A layered content distribution network, the network is composed of a content distribution layer, a content distribution layer including at least one distribution sublayer, and an edge service layer; the content distribution layer includes at least one ICP node, and the content distribution layer is connected to the content The first-level distribution sub-layer in the distribution layer is directly connected; each distribution sub-layer of the content distribution layer is composed of at least one distribution node, and the lowest distribution sub-layer in the content distribution layer is directly connected to the edge service layer; The edge service layer is composed of at least one edge service area; the content to be published by the content release layer is distributed down to the edge service layer step by step through the distribution nodes in the first-level distribution sublayer directly connected to it; the edge service area It includes at least one central server (CS), one media manager (MM), one media request scheduler (MRB) and at least one edge server (ES).

Each ICP node includes at least one ICP operation terminal and at least one ICP.

Each distribution node includes at least one media manager (MM) and one central server (CS).

The MRBs in all edge service areas are distributed and deployed in the local center of each edge service area.

The ICP node in the content publishing layer is the upper node of the distribution node in the first-level distribution sub-layer directly connected to it, and the edge service area in the edge service layer is the lowest-level distribution sub-layer directly connected to it. The next-level node of the distribution node in the layer.

A method for layered distribution of a content distribution network, the method comprising the following steps:

a. The ICP node distributes the content to be published to at least one distribution node in the content distribution layer directly connected to it;

b. In the content distribution layer, the distribution node currently receiving the content distribution command judges whether it is a distribution node in the distribution sublayer of the lowest level, if yes, then execute step c; Read the content to be published in the upper-level node, store it on the CS in this node, and distribute the content to one or more lower-level distribution nodes directly connected to it, and return to step b;

c. The current distribution node receives the content to be published from the upper-level node directly connected to it according to the received content distribution command, stores it on the CS in the node, and distributes the content to one or one of the nodes directly connected to it above fringe service area;

d. The user's access to the ICP is scheduled by the MRB in the edge service area where the user is located, and the CS or ES in the edge service area where the user is located provides the service required by the user.

The scheduling includes at least analyzing the domain name of the ICP accessed by the user, detecting ESs in the edge service area, or selecting the best ES.

The detection of the ES includes at least detection of the proximity of the ES to the user, the presence or absence of content required by the user, or the status of the network being busy or idle.

The selection is to determine the best ES according to the proximity of the ES to the user, the presence or absence of content required by the user, or the busy or idle status of the network.

Compared with the prior art, the invention can form networks of various scales, including metropolitan area networks, provincial networks or national networks. It also supports level-by-level expansion, from the city area to the whole province, and even the whole country, making the CDN network more flexible. The invention optimizes the dispatching mode of the traditional CDN, adopts distributed dispatching, reduces the service range of the dispatcher, reduces the load, shortens the response time, and can further improve the service quality of the CDN network. Because the present invention adopts layered and hierarchical content distribution management, it is guaranteed that only one point of ICP access is required to realize the whole network release and whole network service, thereby realizing distributed service and regional balance of business load. At the same time, the present invention can perform scheduling based on the busy state of the edge server and user proximity, select a relatively idle edge server to provide services, and improve service quality; it can also schedule based on content to increase the hit rate of access.

Description of drawings

FIG. 1 is a schematic diagram of a network structure of a prior art solution;

FIG. 2 is a schematic diagram of a user access scheduling process in the prior art solution 1;

Fig. 3 is a schematic diagram of user access flow in the second prior art solution;

FIG. 4 is a schematic diagram of a network structure according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a content publishing process according to an embodiment of the present invention;

Fig. 6 is a schematic diagram of a user access scheduling process according to an embodiment of the present invention.

Detailed ways

In order to make the object, technical solution and advantages of the present invention more clearly, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

The main idea of the present invention is: use distributed scheduling and layered distribution to form a network, the scheduler is not concentrated in the center of the network, but distributed in the local center of each service area, responsible for access scheduling in this area; The content distribution management adopts a layered and hierarchical method to ensure that ICP can publish and serve the whole network with only one point of access.

The hierarchical CDN described in the present invention is composed of a content publishing layer, a content distribution layer including at least one distribution sub-layer, and an edge service layer. Taking a network structure in which the content distribution layer is composed of two distribution sub-layers as an example, the present invention The network structure is shown in Figure 4: the main components of CDN are ICP, ICP operation terminal, central server (CS), media manager (MM), media request scheduler (MRB), ES and other equipment. Among them, MM is responsible for processing signaling, and its main function is to accept the release command about content release issued by the ICP operation terminal, and issue a content distribution command to ES, next-level MM or CS at all levels according to the release command, and receive ES , Feedback information from MM at the next level or CS at all levels; CSs at all levels are responsible for the content storage, distribution and service provision of the center; MRBs in all edge service areas in the edge service layer are distributed and deployed locally in each edge service area The center is mainly responsible for access scheduling in the local area network to achieve load balancing. The solid line in FIG. 4 represents the process of publishing and distributing the content; the dotted line represents the publishing command of the content.

Various components in the above-mentioned CDN can be combined into: ICP nodes, distribution nodes, and edge service areas. Among them, each ICP node includes at least one ICP operation terminal, one or more ICPs; each distribution node includes at least one MM, one CS; each edge service area includes at least one CS, one MM, one MRB and one or more ES;

The content release layer is composed of one or more ICP nodes, the content distribution layer is composed of one or more distribution sublayers, each distribution sublayer is composed of at least one distribution node, and the edge service layer is composed of one or more edge service areas . The content distribution layer is directly connected to the content distribution layer, and the content distribution layer is directly connected to the edge service layer. The content to be distributed by the content distribution layer is distributed to the edge service layer through the content distribution layer.

According to the connection mode, each distribution sub-layer in the content distribution layer and the distribution nodes in each distribution sub-layer can be divided into different levels: the distribution node directly connected with the content distribution layer is regarded as the first-level distribution node, and all the first-level distribution nodes The collection of nodes is called the first-level distribution sublayer, and the ICP node in the content publishing layer is the upper-level node of the first-level distribution node directly connected to it; the distribution node directly connected to the first-level distribution node is called the second-level distribution node. The set of all secondary distribution nodes is called the secondary distribution sublayer, and the primary distribution node is the upper node of the secondary distribution node directly connected to it; and so on, the edge service area of the edge service layer is related to The lowest-level distribution nodes are directly connected, and the collection of all the lowest-level distribution nodes is called the lowest-level distribution sublayer, and the lowest-level distribution nodes are the upper-level nodes of the edge service area directly connected to it. There is at least one first-level distribution node in the content distribution layer.

The content to be published by the content publishing layer is first distributed to one or more first-level distribution nodes directly connected to it, and the above-mentioned first-level distribution node distributes the received content to be published to one or more first-level distribution nodes directly connected to the first-level distribution node. A plurality of secondary distribution nodes, and then the secondary distribution node distributes the received content to be published to one or more tertiary distribution nodes directly connected to the secondary distribution node; and so on, until the required The published content is distributed down to the edge service layer step by step, so as to realize the hierarchical distribution of content.

Based on the CDN network structure shown in Figure 4, the general content publishing process is shown in Figure 5, including the following steps:

In step 501, the ICP operation terminal of an ICP node in the content release layer sends a content release command to MMs in one or more first-level distribution nodes directly connected to it.

Step 502, the MM in the above-mentioned first-level distribution node sends a content publishing command to the CS in the distribution node where it is located according to the received content publishing command.

Step 503, the CS in the above-mentioned first-level distribution node reads the content to be released by the ICP from the ICP content storage device of the above-mentioned ICP node according to the received content release command, and stores it in the above-mentioned first-level distribution node. on CS.

Step 504, the CS in the above-mentioned first-level distribution node notifies the MM in the distribution node where it is located, that the content to be released by the above-mentioned ICP node has been stored on the CS in the above-mentioned first-level distribution node.

Step 505, the MM in the first-level distribution node sends a content distribution command to the MM in the second-level distribution node directly connected to the node.

Step 506, the MM in the above-mentioned secondary distribution node sends a content publishing command to the CS in the node where it is located according to the received content publishing command.

Step 507, the CS in the above-mentioned secondary distribution node reads the content to be published from the upper-level CS, that is, the CS in the above-mentioned primary distribution node according to the received content distribution command, and stores it in the secondary distribution node on the CS.

Step 508, the CS in the above-mentioned secondary distribution node notifies the MM in the node where it is located that the content to be released has been stored in the CS in the above-mentioned secondary distribution node.

Step 509, the MM in the above-mentioned secondary distribution node sends a content release command to the MM in the edge service area directly connected to the node.

Step 510, the MM in the fringe service area sends a content release command to the CS in the fringe service area where it is located according to the received content release command.

Step 511, according to the received content distribution command, the CS in the above-mentioned edge service area reads the content to be published from the upper-level CS, that is, the CS in the second-level distribution node directly connected to it, and stores it in the local CS, namely On the CS in the above edge service area.

Step 512, the CS in the above-mentioned edge service area notifies the MM in the node where it is located that the content to be released has been stored on the CS in the above-mentioned edge service area.

Step 513, the above-mentioned MM in the fringe service area sends a content distribution command to the ES in the fringe service area where it is located.

Step 514: According to the received content distribution command, the ES in the above-mentioned edge service area reads the content to be distributed from the CS in the edge service area where it is located, and stores it on the ES.

After the above-mentioned content release process, the content to be released by the ICP is pre-pushed to the edge of the network, that is, the ES in the edge network, through the above-mentioned layered CDN. The above-mentioned content publishing process is not only applicable to provincial CDNs, but also metropolitan-level CDNs and national-level CDNs.

In the CDN network structure described in the present invention, the general user access scheduling process is shown in Figure 6, including the following steps:

Step 601, the user visits the WEB page and clicks on the content of the website.

Step 602, the browser of the user terminal requests the local DNS to resolve the domain name of the website of the user.

Step 603, the local DNS requests resolution from the authorized DNS of the website.

In step 604, the authoritative DNS of the website notifies the local DNS that the authoritative DNS of the corresponding content of the website is the locally deployed MRB, and returns the IP address of the MRB.

Step 605, the local DNS returns the IP address of the MRB to the browser.

Step 606, the browser of the user terminal accesses the MRB.

Step 607, MRB detects all ESs in the area, selects the best ES according to proximity and content, and returns the IP address of the ES to the browser.

Step 608, the user accesses the ES and makes a request to the ES.

Step 609, if the ES does not have the content required by the user, the ES acquires the content required by the user from the local CS, and then executes step 610; otherwise, directly executes step 610.

Step 610, the ES provides the required content according to the user's request.

It can be seen from the above process that after the local user's access is resolved by DNS, the access is not only scheduled by the local MRB, but also provided by the local ES, which well reflects the idea of distributed business implementation.

Since the present invention adopts distributed scheduling and layered distribution for networking, compared with traditional CDNs, the present invention has the advantage of supporting hierarchical and hierarchical networking, and can form both small-scale CDNs and large-scale CDNs. CDN; the content distribution management of the present invention adopts a layered and hierarchical type, thereby ensuring that the ICP only needs one point of access, and can be published on the entire network and served on the entire network; due to the division of service areas in the present invention, each edge service area is locally distributed. Scheduling, thereby effectively reducing the load of the scheduler, and more effective detection of network conditions.

The above embodiments are described by taking a network structure in which the content distribution layer consists of two distribution sublayers as an example. The present invention is also applicable to a network structure in which the content distribution layer consists of one or more distribution sublayers.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (9)

1. A layered content distribution network, characterized in that: the network is composed of a content distribution layer, a content distribution layer including at least one distribution sublayer, and an edge service layer; the content distribution layer includes at least one ICP node, The content distribution layer is directly connected to the first-level distribution sub-layer in the content distribution layer; each distribution sub-layer of the content distribution layer is composed of at least one distribution node, and the lowest distribution sub-layer in the content distribution layer is connected to the edge The service layer is directly connected; the edge service layer is composed of at least one edge service area; the content to be published by the content publishing layer is distributed down to the edge service layer step by step through the distribution nodes in the first-level distribution sub-layer directly connected to it; The edge service area includes at least one central server CS, one media manager MM, one media request scheduler MRB and at least one edge server ES. 2. The content distribution network according to claim 1, wherein each ICP node includes at least one ICP operation terminal and at least one ICP. 3. The content distribution network according to claim 1, characterized in that each distribution node includes at least one media manager MM and one central server CS. 4. The content distribution network according to claim 1, characterized in that: MRBs in all edge service areas are deployed in a distributed manner at the local center of each edge service area. 5. The content distribution network according to claim 1, characterized in that: the ICP node in the content release layer is the upper-level node of the distribution node in the first-level distribution sub-layer directly connected to it, and the edge service The edge service area in the layer is the next-level node of the distribution node in the lowest-level distribution sub-layer directly connected to it. 6. A method for content distribution network hierarchical distribution, characterized in that the method comprises the following steps: a. The ICP node distributes the content to be published to at least one distribution node in the content distribution layer directly connected to it; b. In the content distribution layer, the distribution node currently receiving the content distribution command judges whether it is a distribution node in the distribution sublayer of the lowest level, if yes, then execute step c; Read the content to be published in the upper-level node, store it on the CS in this node, and distribute the content to one or more lower-level distribution nodes directly connected to it, and return to step b; c. The current distribution node receives the content to be published from the upper-level node directly connected to it according to the received content distribution command, stores it on the CS in the node, and distributes the content to one or one of the nodes directly connected to it above fringe service area; d. The user's access to the ICP is scheduled by the MRB in the edge service area where the user is located, and the CS or ES in the edge service area where the user is located provides the service required by the user. 7. The method according to claim 6, wherein the scheduling includes at least analyzing the domain name of the ICP visited by the user, detecting the ES in the edge service area, or selecting the best ES. 8. The method according to claim 7, wherein the detection of the ES includes at least detection of the proximity of the ES to the user, the availability of content required by the user, or the status of the network being busy or idle. 9. The method according to claim 7, wherein the selection is to determine the best ES according to the proximity of the ES to the user, the availability of content required by the user, or the busy or idle status of the network.

Images