A distributed content scheduling method, scheduling system and central server

Abstract

The present invention discloses a distributed content scheduling method, scheduling system and central server, wherein the method comprises: a first cache server in a first network access node receives a resource acquisition request initiated by a client, if the first cache server does not have the resource corresponding to the resource acquisition request, the first cache server initiates a resource query request to a first central server in the first network access node; if the first central server does not have the cache content corresponding to the resource query request, the second central server to which the cache content belongs is determined, and the cache content is obtained from the second central server; the first central server feeds back the cache content to the first cache server. The technical solution provided by the present application can improve the overall stability of the system.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a distributed content scheduling method, a scheduling system and a central server. Background Art

[0002] In the current CDN (Content Delivery Network), content scheduling can be performed through the cooperation of the central server and the cache server. Specifically, the mapping relationship between the file URL (Uniform Resource Locator) and the corresponding cache server can be cached in the central server, and the actual content of the file can be cached in the cache server. In this way, the central server can query the corresponding cache server according to the file URL requested by the user, and then provide the actual file to the user through the cache server.

[0003] In the current CDN, the mapping relationship between file URLs and cache servers is usually cached in a single central server cluster, which requires the central server to have strong performance. In addition, this single cluster caching method also poses a major risk to system stability. Summary of the invention

[0004] The purpose of the present application is to provide a distributed content scheduling method, a scheduling system and a central server, which can improve the overall stability of the system.

[0005] To achieve the above-mentioned purpose, the present application provides a distributed content scheduling method on the one hand, the method comprising: a first cache server in a first network access node receives a resource acquisition request initiated by a client, if the first cache server does not have the resource corresponding to the resource acquisition request, the first cache server initiates a resource query request to a first central server in the first network access node for the resource acquisition request; if the first central server does not have the cache content corresponding to the resource query request, determines a second central server to which the cache content belongs, and obtains the cache content from the second central server; the first central server feeds back the cache content to the first cache server, so that after the first cache server obtains the corresponding resource from the second cache server pointed to by the cache content, the first cache server provides the obtained resource to the client.

[0006] To achieve the above-mentioned purpose, the present application also provides a distributed content scheduling system on the other hand, the system includes multiple network access nodes, the network access nodes include a central server and at least one cache server, wherein: the first cache server in the first network access node receives a resource acquisition request initiated by a client, if the first cache server does not have the resource corresponding to the resource acquisition request, the first cache server initiates a resource query request to the first central server in the first network access node for the resource acquisition request; if the first central server does not have the cache content corresponding to the resource query request, determine the second central server to which the cache content belongs, and obtain the cache content from the second central server; the first central server feeds back the cache content to the first cache server, so that after the first cache server obtains the corresponding resource from the second cache server pointed to by the cache content, the first cache server provides the obtained resource to the client.

[0007] To achieve the above objectives, the present application further provides a central server on the other hand, the transfer device includes a memory and a processor, the memory is used to store a computer program, and when the computer program is executed by the processor, the functions performed by the central server in the above method are implemented.

[0008] From the above, it can be seen that in the technical solution provided by one or more embodiments of the present application, the request response time between machines in the same network access node is relatively short, and this time can be ignored compared to the request response time between different machines across the network access node. In the original technical solution, there are two requests across the network access node (the communication process between the cache server and the central server, and the communication process between different cache servers). The technical solution of the present application also has two requests across the network access node (the communication process between the first central server and the second central server, and the communication process between the first cache server and the second cache server). Therefore, after adopting the technical solution of the present application, the overall service quality will not deteriorate.

[0009] The current content scheduling system needs to store the cache content of URLs of the entire network in a few central servers, which places extremely high performance requirements on the central servers. After changing to the distributed content scheduling system proposed in this application, the cache content is evenly distributed to the central servers of each access node in the entire network, thereby greatly reducing the performance requirements on the central servers while ensuring that the service quality does not deteriorate, thereby improving the overall stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 is a schematic diagram of the architecture of a distributed content scheduling system in an embodiment of the present invention;

[0012] Figure 2 is a schematic diagram of a consistent hashing algorithm in an embodiment of the present invention;

[0013] Figure 3 is a schematic diagram of an abnormality in a central server in an embodiment of the present invention;

[0014] Figure 4 is a schematic diagram of a newly added central server in an embodiment of the present invention;

[0015] Figure 5 is a schematic diagram of a virtual node in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in combination with the specific implementation methods of this application and the corresponding drawings. Obviously, the described implementation methods are only part of the implementation methods of this application, not all of the implementation methods. Based on the implementation methods in this application, all other implementation methods obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] The technical solution provided in this application can be applied to Figure 1 In the system architecture shown. In the system architecture, multiple network access nodes (Point Of Presence, POP) may be included, and each POP may include a central server (or a central server cluster) and at least one cache server. Among them, the cache server can be used to store various resources, and the central server can cache the mapping relationship between the URL of the resource and the corresponding cache server. For example, in the central server, the mapping relationship between the URL of the file and the IP address of the cache server storing the file can be cached.

[0018] In order to avoid centrally storing the above mapping relationships in one or several central servers, the central servers in different POPs can be distributed on the hash ring through the consistent hashing algorithm. Figure 2, the hash ring can pre-set the value space of the hash value, which can be, for example, 0 to 2 32 -1, that is to say, each hash value on the hash ring can be represented by a 32-bit unsigned integer value. Then, when distributing the central servers on the hash ring, the identifier of the central server can be identified first. The identifier can be a numerical value, string, or other information that can uniquely identify the central server. For example, the identifier can be the name of the central server, or the MAC address of the central server, or the IP address of the central server, etc. Through the hash operation, the hash value corresponding to the identifier can be calculated. For example, the hash value of the identifier can be calculated through a conventional hash function. Then, the position of the calculated hash value in the above-mentioned hash ring can be used as the distribution position of the central server in the hash ring. For example, in Figure 2 In the example, the four central servers can be distributed at different locations on the hash ring after hash operation.

[0019] In this application, the mapping relationship of various resources in the CDN can also be evenly cached in different central servers through the consistent hashing algorithm. Figure 2 , the mapping relationship between the resource URL and the cache server can be used as the cache content in the CDN. For the current cache content, the cache identifier of the current cache content can be identified, and the cache identifier can be, for example, the resource URL. Then, the cache identifier can be used as a string, and the hash value of the cache identifier can be calculated through a hash algorithm, so that the target location corresponding to the current cache content can be determined on the hash ring based on the hash value of the cache identifier. It should be noted that the hash algorithm used to calculate the hash value of the cache identifier and the hash value of the identifier of the computing center server can be the same hash algorithm.

[0020] In this embodiment, after the target location of the current cached content is determined on the hash ring, the search can be started from the target location and along the specified direction on the hash ring, and the first central server found is used as the central server storing the current cached content. The above-mentioned specified direction can be the clockwise direction of the hash ring. Figure 2 As shown in FIG. 1 , when the current cache content object1 is searched clockwise along the hash ring, the first central server encountered is the central server of POP1, so the cache content object1 can be cached in the central server of POP1. Other cache contents can also determine their corresponding central servers in the same way.

[0021] Through the processing of the above consistent hashing algorithm, the cached contents in the CDN can be relatively evenly distributed in different central servers. In this way, when the subsequent central servers provide services to users, they can avoid the aggregation of too much traffic at the same central server, greatly improving the overall stability of the system.

[0022] In actual applications, a central server may fail to provide services due to an abnormality. When distributing cache content in the above manner, it can be ensured that the impact of this situation is minimal. For details, please refer to Figure 3 , assuming that there were originally four central servers in working order, and the central server in POP2 stopped working due to an abnormality, at this time, part of the cached content in the CDN needs to be redistributed in order to continue to provide services to users. Figure 3 As shown in the figure, assuming that the central server in POP2 stops working, then in the entire CDN system, only the cached content object2 needs to change its storage location (converted from the central server in POP2 to the central server in POP3), and other cached contents do not need to be changed. It can be seen that when the central server stops working abnormally, the cached content can be allocated in the above manner, which can minimize the redistribution of cached content, thereby ensuring that CDN can continue to provide stable services in a very short time.

[0023] In addition, as the volume of CDN business increases, additional POPs may be added, which will introduce new central servers. Figure 4 When a new POP5 central server is introduced, the distribution location of the new central server can be determined on the hash ring in the above manner. Figure 4 As shown, the new central server is located between the central servers of POP3 and POP4. At this time, only the cached content object4 needs to change its storage location (from the central server in POP4 to the central server in POP5), and other cached contents do not need to be changed. It can be seen that when a new central server is added to the CDN, the cached content is allocated in the above manner, and the cached content can be redistributed as little as possible, thereby ensuring that the CDN can continue to provide stable services in a very short time.

[0024] In one embodiment, if the number of central servers in the CDN system is small, most of the cached content may be stored in one or several central servers. To avoid this situation, a virtual node method can be used to distribute the cached content.

[0025] Specifically, see Figure 5For the central server in the POP, one or more virtual central servers of the central server can be generated. When generating a virtual central server, a virtual identifier can be set for the virtual central server, and the virtual identifier can be used to uniquely identify the virtual central server. In actual applications, the virtual identifier can be generated based on the identifier of the central server. For example, the identifier of the central server is named nodeA, then the virtual identifiers of the virtual central servers generated based on the central server can be nodeA#1, nodeA#2, nodeA#3, etc.

[0026] After generating the virtual central servers of the central server and setting respective virtual identifiers for the virtual central servers, the distribution locations of the virtual central servers can be determined on the hash ring in the above manner based on the virtual identifiers. Figure 5 In the example, there are only two real central servers, nodeA and nodeB, and based on these two real central servers, there can be multiple different virtual central servers, and these virtual central servers can also be distributed on the hash ring. In this way, both the central server and the virtual central server can participate in the distribution of cache content in the above manner. However, if the cache content is allocated to a virtual central server, then the cache content is actually stored in the real central server corresponding to the virtual central server. By distributing multiple virtual central servers on the hash ring, the cache content can be distributed as evenly as possible in the real central server.

[0027] Based on the above-mentioned central server and cache content distribution method, this application provides a distributed content scheduling system, please refer to Figure 1 The system may include multiple network access nodes, including a central server and at least one cache server, wherein the central server and the cache server in the system may perform content scheduling in the following manner.

[0028] S1: A first cache server in a first network access node receives a resource acquisition request initiated by a client. If the first cache server does not have a resource corresponding to the resource acquisition request, the first cache server initiates a resource query request to a first central server in the first network access node in response to the resource acquisition request.

[0029] In this embodiment, the resources that the client needs to obtain may be network resources such as files, videos, audios, articles, and images. When the client needs to obtain resources, it may initiate a resource acquisition request containing the URL of the resource. In practical applications, the URL in the resource acquisition request may first be processed by a domain name resolution server. The domain name resolution server may identify the domain name contained in the URL, query the IP address corresponding to the domain name, and feed back the queried IP address to the client. The IP address may generally be the IP address of the first cache server in the first network access node.

[0030] After receiving the domain name resolution result fed back by the domain name resolution server, the client can initiate a resource acquisition request to the first cache server. The first cache server can identify the URL in the resource acquisition request, and then query locally whether the resource corresponding to the URL is stored. If the corresponding resource is available, the first cache server can directly provide the queried resource to the client. If the corresponding resource is not available, the first cache server can initiate a resource query request to the first central server in the first network access node where it is located. Specifically, the resource query request can carry the URL in the resource acquisition request initiated by the client.

[0031] S2: If the first central server does not have the cache content corresponding to the resource query request, determine the second central server to which the cache content belongs, and obtain the cache content from the second central server.

[0032] In this embodiment, after receiving the resource query request, the first central server can identify the URL contained therein, and then query locally whether there is cache content corresponding to the URL. If the first central server has the corresponding cache content, the first central server can provide the queried cache content to the first cache server. The cache content can represent the mapping relationship between the above-mentioned URL and the corresponding cache server. For example, the cache content can include the IP address of the cache server that stores the corresponding resource. In this way, the first cache server can initiate a resource acquisition request to the cache server pointed to by the IP address by identifying the IP address in the cache content. Subsequently, the cache server pointed to by the IP address can provide the corresponding resource to the first cache server, and the first cache server can thus feed back the resource to the client.

[0033] However, since the cached content is distributed to the central servers of each access node according to the consistent hashing algorithm, the first central server may not have the cached content corresponding to the URL. If the first central server does not have the cached content corresponding to the URL, the first central server needs to search for the central server in the CDN that has cached the cached content corresponding to the URL according to the URL.

[0034] Specifically, the first central server can calculate the hash value of the URL according to the consistent hashing algorithm. The position of the hash value on the hash ring can be used as the target position of the URL on the hash ring. Then, starting from the target position, the search can be conducted along the specified direction on the hash ring, and the first central server found can be used as the central server that caches the cache content corresponding to the URL. For example, the central server found here is the second central server in the second network access node.

[0035] S3: The first central server feeds back the cache content to the first cache server, so that the first cache server obtains corresponding resources from the second cache server pointed to by the cache content, and then provides the obtained resources to the client.

[0036] After searching for the second central server, the first central server can initiate a resource query request to the second central server, and the above-mentioned URL can be carried in the request. The second central server can identify the URL of the request, so that the cache content corresponding to the URL can be fed back to the first central server. Then, the first central server can provide the received cache content to the first cache server. In this way, the first cache server can know the second cache server that stores the resources corresponding to the URL. Subsequently, the first cache server can obtain the corresponding resources based on the IP address of the second cache server in the cache content, and provide the obtained resources to the client.

[0037] In actual applications, the request response time between machines in the same network access node is relatively short, which can be ignored compared to the request response time between different machines across the network access node. In the original technical solution, there are two requests across the network access node (the communication process between the cache server and the central server, and the communication process between different cache servers). The technical solution of this application also has two requests across the network access node (the communication process between the first central server and the second central server, and the communication process between the first cache server and the second cache server). Therefore, after adopting the technical solution of this application, the overall service quality will not deteriorate.

[0038] The current content scheduling system needs to store the cached content of URLs in a few central servers, which places extremely high requirements on the performance of the central servers. After changing to the distributed content scheduling system proposed in this application, the cached content is evenly distributed to the central servers of each POP in the entire network, thereby greatly reducing the performance requirements on the central servers while ensuring that the service quality does not deteriorate, thereby improving the overall stability of the system.

[0039] The present application also provides a distributed content scheduling method, the method comprising:

[0040] The first cache server in the first network access node receives a resource acquisition request initiated by a client. If the first cache server does not have a resource corresponding to the resource acquisition request, the first cache server initiates a resource query request to a first central server in the first network access node in response to the resource acquisition request.

[0041] If the first central server does not have the cache content corresponding to the resource query request, determine the second central server to which the cache content belongs, and obtain the cache content from the second central server;

[0042] The first central server feeds back the cache content to the first cache server, so that the first cache server obtains corresponding resources from the second cache server pointed to by the cache content, and then provides the obtained resources to the client.

[0043] The present application also provides a central server, wherein the transfer device includes a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the functions performed by the central server in the above system are implemented.

[0044] In the present application, the memory may include a physical device for storing information, which is usually a device that digitizes the information and then stores it in a medium using electrical, magnetic or optical methods. The memory may also include: a device that stores information using electrical energy, such as RAM or ROM; a device that stores information using magnetic energy, such as a hard disk, a floppy disk, a magnetic tape, a magnetic core memory, a magnetic bubble memory or a USB flash drive; a device that stores information using optical means, such as a CD or a DVD. Of course, there are other types of memory, such as quantum memory or graphene memory, etc.

[0045] In the present application, the processor may be implemented in any suitable manner. For example, the processor may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc.

[0046] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the implementation of the system and the central server, the introduction of the implementation of the aforementioned method can be referred to for comparative explanation.

[0047] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0051] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0052] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0053] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0054] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0055] The above is only the implementation mode of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A distributed content scheduling method, characterized in that: The method comprises: The first cache server in the first network access node receives a resource acquisition request initiated by a client. If the first cache server does not have a resource corresponding to the resource acquisition request, the first cache server initiates a resource query request to a first central server in the first network access node in response to the resource acquisition request. If the first central server does not have the cache content corresponding to the resource query request, the first central server determines the second central server that has cached the cache content corresponding to the URL according to the URL of the resource, and obtains the cache content from the second central server, wherein the cache content is used to characterize the mapping relationship between the URL and the cache server that stores the corresponding resource, and the cache content is stored in each of the central servers in the following manner: identifying a cache identifier of the current cache content, and calculating a hash value of the cache identifier, so as to determine a target position corresponding to the current cache content on a hash ring based on the hash value of the cache identifier; starting from the target position, searching along a specified direction on the hash ring, and using the first central server found as the central server that stores the current cache content; The first central server feeds back the cache content to the first cache server, so that the first cache server obtains corresponding resources from the second cache server pointed to by the cache content, and then provides the obtained resources to the client.

2. The method according to claim 1, characterized in that The central servers are distributed in the hash ring in the following manner: Identify the identifier of the central server and calculate a hash value corresponding to the identifier; The position of the hash value in the hash ring is used as the distribution position of the central server in the hash ring.

3. The method according to claim 1 or 2, characterized in that: The central server has one or more virtual central servers, and the virtual central servers are distributed on the hash ring according to virtual identifiers; for the current cache content to be allocated, the target position corresponding to the current cache content is determined on the hash ring, and starting from the target position, a search is conducted along a specified direction on the hash ring to determine the first central server or the first virtual central server found; wherein the first central server found serves as the central server for storing the current cache content, or the central server to which the first virtual central server found belongs serves as the central server for storing the current cache content.

4. The method according to claim 1, characterized in that: The method further comprises: If the first central server has cache content corresponding to the resource query request, the first central server provides the cache content to the first cache server; The first cache server obtains corresponding resources from the cache server pointed to by the cache content, and provides the obtained resources to the client.

5. The method according to claim 1, characterized in that The second central server determining the ownership of the cached content includes: The first central server identifies a cache identifier of the cache content and calculates a hash value of the cache identifier to determine a target location corresponding to the cache content on a hash ring based on the hash value of the cache identifier; Starting from the target location, search along the specified direction on the hash ring, and use the first central server found as the second central server for storing the cached content.

6. The method according to claim 1 or 5, characterized in that: The first cache server obtains the corresponding resource from the second cache server pointed to by the cache content, including: The first cache server identifies the IP address of the second cache server from the cache content, and based on the identified IP address, initiates a resource acquisition request to the second cache server to acquire corresponding resources from the second cache server.

7. A distributed content scheduling system, characterized in that: The system includes a plurality of network access nodes, wherein the network access nodes include a central server and at least one cache server, wherein: The first cache server in the first network access node receives a resource acquisition request initiated by a client. If the first cache server does not have a resource corresponding to the resource acquisition request, the first cache server initiates a resource query request to a first central server in the first network access node in response to the resource acquisition request. If the first central server does not have the cache content corresponding to the resource query request, the first central server determines the second central server that has cached the cache content corresponding to the URL according to the URL of the resource, and obtains the cache content from the second central server, wherein the cache content is used to characterize the mapping relationship between the URL and the cache server that stores the corresponding resource, and the cache content is stored in each of the central servers in the following manner: identifying a cache identifier of the current cache content, and calculating a hash value of the cache identifier, so as to determine a target position corresponding to the current cache content on a hash ring based on the hash value of the cache identifier; starting from the target position, searching along a specified direction on the hash ring, and using the first central server found as the central server that stores the current cache content; The first central server feeds back the cache content to the first cache server, so that the first cache server obtains corresponding resources from the second cache server pointed to by the cache content, and then provides the obtained resources to the client.

8. A central server, characterized in that: The central server comprises a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the function performed by the central server in the method according to any one of claims 1 to 6 is realized.

Images