WO2014146541A1 - Système de convergence de cdn et de réseau, procédé de sélection de module de planification et support de stockage informatique - Google Patents

Système de convergence de cdn et de réseau, procédé de sélection de module de planification et support de stockage informatique Download PDF

Info

Publication number
WO2014146541A1
WO2014146541A1 PCT/CN2014/072941 CN2014072941W WO2014146541A1 WO 2014146541 A1 WO2014146541 A1 WO 2014146541A1 CN 2014072941 W CN2014072941 W CN 2014072941W WO 2014146541 A1 WO2014146541 A1 WO 2014146541A1
Authority
WO
WIPO (PCT)
Prior art keywords
scheduling module
cdn
module
main
primary
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2014/072941
Other languages
English (en)
Chinese (zh)
Inventor
黄孙亮
陈建业
吴萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZTE Corp
Original Assignee
ZTE Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ZTE Corp filed Critical ZTE Corp
Publication of WO2014146541A1 publication Critical patent/WO2014146541A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications

Definitions

  • the present invention relates to the field of communication network technologies, and in particular, to a Content Delivery Network (CDN) and network convergence system, a scheduling module selection method, and a computer storage medium.
  • CDN Content Delivery Network
  • Background technique
  • embodiments of the present invention provide a CDN and network convergence system, a scheduling module selection method, and a computer storage medium, which are designed to improve the stability of a CDN and a network convergence system, thereby improving user usage.
  • the embodiment of the present invention provides a scheduling module selection method, which is applied to a CDN and network convergence system, where the CDN and network convergence system includes multiple CDNs.
  • the service device, the CDN service device includes a scheduling module, and the method includes:
  • the primary scheduling module and the standby primary scheduling module are selected;
  • the primary scheduling module is configured to uniformly schedule access requests of the client access application
  • the standby primary scheduling module is configured to, when the primary scheduling module fails, take over the access scheduling request by the primary scheduling module to the client access application.
  • the selecting the primary scheduling module and the standby primary scheduling module, among the multiple scheduling modules included in the plurality of the CDN service devices includes:
  • the Internet Protocol (IP, Internet Protocol) address of the CDN service device and the internal address of the CDN service device select the primary scheduling module and the standby primary scheduling module.
  • the method further includes:
  • the survival detection mechanism is established between the primary scheduling module and the standby primary scheduling module, and detecting whether the primary scheduling module and/or the standby primary scheduling module are generated according to the survival detection mechanism Faults include: Determining, in the preset fault period, whether the number of the survival detection packets received by the primary scheduling module and/or the standby primary scheduling module is zero, when the primary scheduling module determines the received survival When the number of the detected packets is zero, it is determined that the standby primary scheduling module is faulty; when the standby primary scheduling module determines that the number of received survival detection packets is zero, it is determined that the primary scheduling module is faulty; The result is processed accordingly;
  • the survival detection packet is sent to the other party by the primary scheduling module and/or the standby primary scheduling module according to a preset detection packet interval.
  • the performing the corresponding processing according to the fault result comprises:
  • a new primary primary scheduling module is triggered to be reselected.
  • the embodiment of the invention further provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is used to execute the scheduling module selection method according to the embodiment of the invention.
  • the embodiment of the present invention further provides a CDN and a network convergence system, where the CDN and network convergence system includes a plurality of CDN service devices, and the CDN service device includes a scheduling module.
  • the system further includes:
  • the selected module is configured to adopt a multicast mode, and among the multiple scheduling modules included in the plurality of CDN service devices, the active scheduling module is selected, and the primary scheduling module is configured to access the application for the client. Accessing the request for unified scheduling; selecting an alternate primary scheduling module, the standby primary scheduling module configured to take over the access scheduling request of the primary scheduling module to the client access application when the primary scheduling module fails .
  • the selected module is configured to pass a configuration preference level of a plurality of scheduling modules included in the plurality of CDN service devices, a device slot number of the CDN service device, and the CDN.
  • the primary scheduling module and the secondary primary scheduling module are selected by a MAC address of the service device, an IP address of the CDN service device, and an internal address of the CDN service device.
  • the system further includes a mechanism establishment and fault detection module, configured to establish a survival detection mechanism between the primary scheduling module and the standby primary scheduling module, and detect the primary usage according to the survival detection mechanism. Whether the scheduling module and/or the standby primary scheduling module has failed.
  • a mechanism establishment and fault detection module configured to establish a survival detection mechanism between the primary scheduling module and the standby primary scheduling module, and detect the primary usage according to the survival detection mechanism. Whether the scheduling module and/or the standby primary scheduling module has failed.
  • the mechanism establishment and fault detection module comprises:
  • the determining sub-module is configured to determine, during a preset fault period, whether the number of the survival detection packets received by the primary scheduling module and/or the standby primary scheduling module is zero, when the primary scheduling module determines to receive When the number of the survival detection packets is zero, it is determined that the standby primary scheduling module is faulty, and when the standby primary scheduling module determines that the number of the received survival detection packets is zero, it is determined that the primary scheduling module is faulty;
  • the survival detection message is sent by the primary scheduling module and/or the standby primary scheduling module to the other party according to the preset detection packet interval;
  • the processing submodule is configured to perform corresponding processing according to the fault result when it is determined that the primary scheduling module and/or the standby primary scheduling module are faulty.
  • the processing submodule is configured to trigger the standby main scheduling module to be upgraded as a main scheduling module when determining that the main scheduling module is faulty; and triggering reselection when determining that the standby main scheduling module is faulty New alternate master scheduling module.
  • the technical solution provided by the embodiment of the present invention selects a primary scheduling for uniformly scheduling an access request of a client accessing application among multiple scheduling modules included in multiple CDN service devices by using a multicast manner.
  • the module, and an alternate primary scheduling module for selecting a unified scheduling of the access request of the client access application by the primary scheduling module when the primary scheduling module fails.
  • the service scheduling modules of multiple CDN service devices are uniformly coordinated by the selected active scheduling module, thereby improving the stability of the CDN and the network convergence system, thereby ensuring service quality and improving the user experience.
  • FIG. 1 is a schematic flowchart of a method 1 for selecting a scheduling module according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a method 2 for selecting a scheduling module according to an embodiment of the present invention
  • FIG. 3 is a schematic flowchart of detecting whether a primary scheduling module and/or an alternate primary scheduling module fails according to the survival detecting mechanism according to the method 2 of selecting a scheduling module according to an embodiment of the present invention
  • FIG. 4 is a schematic flowchart of performing corresponding processing according to a fault result in a method 2 of selecting a scheduling module according to an embodiment of the present invention
  • FIG. 5 is a schematic structural diagram of a CDN and a network convergence system according to an embodiment of the present invention
  • FIG. 6 is a schematic structural diagram of a CDN and a network convergence system according to an embodiment of the present invention
  • FIG. 7 is a CDN and network fusion according to an embodiment of the present invention
  • the invention provides a method for selecting a primary and backup scheduling module in a CDN and network convergence system, and combines a CDN function and a network function into a CDN and a network convergence system, and multiple CDN service devices in the CDN and network convergence system.
  • the main scheduling module for uniformly scheduling the access request of the client access application is selected, and the standby main scheduling module that takes over the unified scheduling of the access request of the client access application when the main scheduling module fails
  • the main scheduling module is used to implement the scheduling of the user's access request, so as to ensure the reliability of the CDN and the network convergence system.
  • Step 101 In the multicast mode, among the multiple scheduling modules included in the multiple CDN service devices, the primary scheduling module is selected, and the primary scheduling module is configured to perform unified scheduling on the access request of the client access application. .
  • Step 102 Select an alternate primary scheduling module, where the standby primary scheduling module is configured to take over the access scheduling request of the primary scheduling module to the client access application when the primary scheduling module fails.
  • the CDN function and the network function are integrated into a CDN and network convergence system, and the content distribution node of the CDN and the network device are merged as an important component of the network device.
  • the CDN and network convergence system can provide content distribution services for users' applications while providing network services to users; and maintain corresponding user content usage state machines through CDN and CDN components of network convergence systems, through state machines and network components.
  • the linkage between the network and the content can be achieved for a specific user, for a specific time period.
  • the external application service link, load balancing scheduling, service processing, and content distribution are all handled by the CDN service device, and each CDN service device initially has the same relationship; The point of view requires a unified external service address to be uniformly scheduled. Therefore, at the same time, the external application link service and the scheduling service can be provided only by the scheduling module of one primary CDN service device, and the user's access is scheduled to the service unit of the different CDN service device.
  • the multicast mode is used to select among a plurality of scheduling modules included in the plurality of CDN service devices, that is, an active scheduling module is selected,
  • the client accesses the application's access request for unified scheduling.
  • the external scheduling address is uniformly issued by the main scheduling module, and an application link is established with the client to perform overall scheduling and load balancing, thereby scheduling the user's access request to the corresponding CDN service device.
  • the business service module In the business service module.
  • an alternate primary scheduling module needs to be selected, so that when the primary scheduling module fails, the standby primary scheduling is adopted.
  • the module directly takes over the main scheduling module, and performs unified scheduling on the access request of the client access application, without waiting for the new main scheduling module to be re-selected to take over the service.
  • the other scheduling modules that are not selected as the primary scheduling module and the standby primary scheduling module serve as the standby scheduling module.
  • the selection of the primary scheduling module and the standby primary scheduling module may be through a configuration preference level of multiple scheduling modules included in multiple CDN service devices, a device slot number of the CDN service device, and a CDN service device.
  • the MAC address, the IP address of the CDN service device, and the internal address of the CDN service device are selected.
  • the multicasting may be performed by specifying a specific reserved multicast group address in the CDN and the network convergence system as the selected dedicated multicast group of the primary scheduling module and the standby primary scheduling module.
  • an internal interface is deployed between the plurality of CDN service devices and the main control and switching device, and between the network service device and the main control and switching device, for the CDN service.
  • the primary scheduling module and the standby primary scheduling module communicate with the service service module through the internal protocol interface, and schedule the user's access request to the corresponding service service module, so that the service service module processes the access request of the user, and distributes The corresponding content to the client.
  • the technical solution provided by the embodiment of the present invention uses a multicast mode to select a primary scheduling for uniformly scheduling an access request of a client access application among multiple scheduling modules included in multiple CDN service devices. Module, and one for when the primary scheduling module fails, An alternate primary scheduling module that takes over the unified scheduling of the access request of the client access application by the primary scheduling module.
  • the service scheduling modules of multiple CDN service devices are uniformly coordinated by the selected active scheduling module, thereby improving the stability of the CDN and the network convergence system, so that the service quality can be guaranteed.
  • the embodiment of the invention further provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is used to execute the scheduling module selection method according to the embodiment of the invention.
  • FIG. 2 is a schematic flowchart diagram of a method 2 for selecting a scheduling module according to an embodiment of the present invention. Based on the embodiment shown in FIG. 1, after the step 102 is performed, the scheduling module selection method of the embodiment of the present invention further includes:
  • Step 103 Establish a survival detection mechanism between the primary scheduling module and the standby primary scheduling module, and detect, according to the survival detection mechanism, whether the primary scheduling module and/or the standby primary scheduling module are faulty. .
  • the active scheduling module for performing unified scheduling of the access request of the client access application, and as the standby standby primary scheduling module, it is also necessary to establish a survival detection mechanism, that is, in the primary scheduling module. Establishing a survival detection mechanism with the standby primary scheduling module to perform mutual detection, and determining whether the other party is faulty according to the detection result. When it is detected that the primary scheduling module and/or the standby primary scheduling module are faulty, the corresponding mechanism is triggered and corresponding processing is performed.
  • the survival scheduling mechanism is used to mutually interact between the primary scheduling module and the standby primary scheduling module. Detecting and judging whether the other party has a fault, so as to perform corresponding processing in the event of a fault, thereby further ensuring the stability of the CDN and the network convergence system.
  • the embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores a computer program, and the computer program is used to execute the scheduling module according to the embodiment of the present invention. Block selection method.
  • FIG. 3 is a schematic flowchart of detecting whether a failure of an active scheduling module and/or an alternate primary scheduling module according to the survival detecting mechanism according to the method for selecting a scheduling module according to an embodiment of the present invention; Based on the embodiment shown in FIG. 2, step 103 in FIG. 2 includes:
  • Step 1031 Determine, in a preset fault period, whether the number of the survival detection packets received by the primary scheduling module and/or the standby primary scheduling module is zero, when determining that the primary scheduling module receives When the number of the survival detection packets is zero, step 1032 is performed; when it is determined that the number of the survival detection packets received by the standby primary scheduling module is zero, step 1033 is performed; when the primary scheduling module and/or If the number of the survival detection packets received by the standby primary scheduling module is not zero, step 1034 is performed.
  • Step 1032 Determine that the standby primary scheduling module is faulty, perform corresponding processing according to the fault result, and continue to step 1034.
  • Step 1033 Determine that the primary scheduling module is faulty, perform corresponding processing according to the fault result, and continue to step 1034.
  • Step 1034 End the current operation flow.
  • the detection mechanism is: the primary scheduling module and the standby primary scheduling module send a survival detection packet to the other party according to the preset detection packet interval, Indicates that your current status is normal.
  • the preset fault period it is determined whether the number of the survival detection messages sent by the other party received by the primary scheduling module and the standby primary scheduling module is zero, and if so, determining that the other party has a fault, when determining the primary scheduling module and When one of the standby main scheduling modules fails, the corresponding processing is further performed according to the fault result.
  • the preset fault period is a time maximum value of the received survival detection packet set according to the actual situation, and the value can detect the interval of the packet twice or three times. After the preset fault period, if the number of the survival detection packets received by the primary scheduling module or the standby primary scheduling module is zero, it indicates that the standby primary scheduling mode is within this time range.
  • the embodiment of the invention further provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is used to execute the scheduling module selection method according to the embodiment of the invention.
  • FIG. 4 is a schematic flowchart of performing corresponding processing according to a fault result in a method 2 for selecting a scheduling module according to an embodiment of the present invention. As shown in FIG. 4, the method includes:
  • Step 201 Determine, in a preset fault period, whether the number of the survival detection packets received by the primary scheduling module and/or the standby primary scheduling module is zero; when determining that the primary scheduling module receives When the number of the surviving detection packets is zero, step 202 to step 203 are performed; when the standby main scheduling module determines that the number of the received survival detecting packets is zero, step 204 to step 205 are performed; When the number of the survival detection packets received by the active scheduling module and/or the standby primary scheduling module is not zero, step 206 is executed to end the current operation flow.
  • step 202 to step 203 when the standby primary scheduling module receives the number of the activity detection packets sent by the active scheduling module is zero, it determines that the primary scheduling module is faulty, and triggers the standby primary scheduling module to upgrade to the primary scheduling module.
  • step 204 to step 205 when the primary scheduling module receives the number of the activity detection packets sent by the standby primary scheduling module is zero, it determines that the standby primary scheduling module is faulty, and triggers the reselection of the new standby primary scheduling module.
  • the survival detection mechanism detects whether the primary scheduling module and the standby primary scheduling module are faulty, if the number of the survival detection packets sent by the primary scheduling module received by the standby primary scheduling module is zero, the primary scheduling module may be determined. If the fault occurs, the fast switching is performed, that is, the standby primary scheduling module is upgraded to the primary scheduling module, and the failed primary scheduling module is replaced, and the access request of the client access application is continuously scheduled.
  • the standby primary scheduling module detects that the primary scheduling module is faulty through the detection mechanism, triggers the self-upgrading as the primary scheduling module, and simultaneously triggers the update of the internal forwarding table of the device, so that the user's application link request Then, the service access module of the switched main scheduling module is forwarded, and an application link is established with the active scheduling module, and the user's access is scheduled and load balanced by the switched primary scheduling module.
  • the primary scheduling module may determine that the standby primary scheduling module is faulty, and at this time, trigger a new selection mechanism, that is,
  • the new standby main scheduling module is reselected for scheduling the access to the user when the primary scheduling module fails. Load balancing work.
  • the primary scheduling module and the standby primary scheduling module After the primary scheduling module and the standby primary scheduling module are selected, whether the number of the survival detection packets received by the primary scheduling module and the standby primary scheduling module is zero or not is determined in the preset fault period. Fault, and after determining that the primary scheduling module or the standby primary scheduling module has failed, perform corresponding processing. In the case of faults, it can quickly replace and switch, avoiding the need to re-select a new active scheduling module and then switching services, improving the speed of service switching, and ensuring the stability of the CDN and network convergence system.
  • the embodiment of the invention further provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is used to execute the scheduling module selection method according to the embodiment of the invention.
  • FIG. 5 is a schematic structural diagram 1 of a CDN and a network convergence system according to an embodiment of the present invention.
  • the CDN and network convergence system provided in this embodiment includes a plurality of CDN service devices 50, and the CDN service device 50 includes a scheduling module 51.
  • the system further includes a selection module 52 configured to adopt In the multicast mode, among the plurality of scheduling modules 51 included in the plurality of CDN service devices 50, the main scheduling module is selected, and the main scheduling module is configured to perform unified scheduling on the access request of the client access application;
  • An alternate primary scheduling module configured to replace access by the primary scheduling module to a client access application when the primary scheduling module fails Request for unified scheduling.
  • the CDN function and the network function are integrated into a CDN and network convergence system, and the content distribution node of the CDN and the network device are merged as an important component of the network device.
  • the CDN and network convergence system can provide content distribution services for users' applications while providing network services to users; and maintain corresponding user content usage state machines through CDN and CDN components of network convergence systems, through state machines and network components.
  • the linkage between the network and the content can be achieved for a specific user, for a specific time period.
  • the externally provided application service links, load balancing scheduling, service processing, and content distribution are all handled by the CDN service device 50, and each CDN service device initially has an equal relationship. From a holistic perspective, the system needs to adopt a unified external service address to perform unified scheduling. Therefore, at the same time, the external application link service and the scheduling service can be provided only by the scheduling module 51 of the primary CDN service device 50, and the user's access is dispatched to the service service modules of the different CDN service devices.
  • the selected module 52 selects among the plurality of scheduling modules 51 included in the plurality of CDN service devices 50 by means of multicast, that is, An active scheduling module is selected to uniformly schedule access requests of the client access application.
  • An active scheduling module is selected to uniformly schedule access requests of the client access application.
  • the user After receiving the access request of the user accessing the application, the user establishes an application link with the client through the unified external service address, performs overall scheduling and load balancing, and then schedules the user's access request to the service service module of the corresponding CDN service device. .
  • the selected module 52 After the primary scheduling module is selected, in order to prevent the switching speed from being affected when the primary scheduling module fails, the selected module 52 also needs to select the standby primary scheduling module, so that when the primary scheduling module fails
  • the standby main scheduling module directly takes over the main scheduling module, and performs unified scheduling on the access request of the client access application, and does not need to wait for the new main scheduling module to be re-selected to take over the service. Others are not selected as the primary scheduling module and the alternate primary scheduling module.
  • the scheduling module of the block acts as an alternate scheduling module.
  • the selection of the primary scheduling module and the standby primary scheduling module by the selection module 52 may be through the configuration preference of the plurality of scheduling modules 51 included in the plurality of CDN service devices 50, and the CDN service device 50.
  • the device slot number, the MAC address of the CDN service device 50, the IP address of the CDN service device 50, and the internal address of the CDN service device 50 are selected.
  • the specific implementation can be performed by multicasting, that is, specifying a specific reserved multicast group address within the CDN and the network convergence system as the selected dedicated multicast group of the primary scheduling module and the standby primary scheduling module.
  • an internal interface is deployed between the plurality of CDN service devices 50 and the main control and switching devices, and between the network service device and the main control and switching device, for the CDN.
  • the information exchange between the service device 50 or the network service device and the main control and switching device for management information, monitoring information, and service deployment; and the corresponding internal protocol interface is deployed between the CDN service device and the network service device.
  • User status, service management and monitoring, traffic forwarding channels, etc.; internal protocol interfaces are also deployed between multiple CDN service devices for service management, collaboration and monitoring, service access and interaction.
  • the primary scheduling module and the standby primary scheduling module communicate with the service service module through the internal protocol interface, and schedule the user's access request to the corresponding service service module, so that the service service module processes the access request of the user, and distributes The corresponding content to the client.
  • the main scheduling module for uniformly scheduling the access request of the client access application is selected, and the selection is performed.
  • An alternate primary scheduling module that is used to relay the access request of the active access scheduling module to the client access application when the primary scheduling module fails.
  • the service scheduling modules of multiple CDN service devices are unified and coordinated through the selected active scheduling module, which improves the stability of the CDN and the network convergence system, so that the service quality can be guaranteed.
  • the CDN and the network convergence system described in this embodiment may be used in practical applications.
  • the CDN server implements the CDN service device 50 and its sub-module scheduling module 51 and the selected module 52 in the CDN and the network convergence system, and in actual applications, the central processing unit (CPU) in the CDN and network convergence system can be used.
  • CPU central processing unit
  • CPU Central Processing Unit
  • DSP Digital Signal Processor
  • programmable gate array J 'J FPGA, Field-Programmable Gate Array
  • FIG. 6 is a schematic structural diagram 2 of a CDN and network convergence system according to an embodiment of the present invention.
  • the system further includes a mechanism establishment and fault detection module 53 configured to establish a survival detection mechanism between the primary scheduling module and the standby primary scheduling module, and detect the primary according to the survival detection mechanism. Whether there is a failure with the scheduling module and/or the standby primary scheduling module.
  • the mechanism for establishing and detecting the fault detection module 53 is also required to establish a survival detection mechanism, that is, A survival detection mechanism is established between the primary scheduling module and the standby primary scheduling module to perform mutual detection, and determine whether the other party is faulty according to the detection result.
  • a survival detection mechanism is established between the primary scheduling module and the standby primary scheduling module to perform mutual detection, and determine whether the other party is faulty according to the detection result.
  • the primary scheduling module and the secondary primary scheduling module are mutually detected by the survival detection mechanism to determine whether the other party has a fault, so that the fault occurs.
  • Corresponding processing further ensures the stability of the CDN and network convergence system.
  • FIG. 7 is a schematic structural diagram of a mechanism for establishing a mechanism and a fault detection module in a CDN and network convergence system according to an embodiment of the present invention; as shown in FIG. 7, in the embodiment, the mechanism establishment and fault detection module 53 includes :
  • the determining sub-module 531 is configured to determine, in a preset fault period, whether the number of the survival detection packets received by the primary scheduling module and/or the standby primary scheduling module is zero;
  • the processing submodule 532 is configured to perform corresponding processing according to the fault result when it is determined that the primary scheduling module and/or the standby primary scheduling module are faulty.
  • the detection mechanism is: the primary scheduling module and the standby primary scheduling module send a survival detection packet to the other party according to the preset detection packet interval, Indicates that your current status is normal.
  • the determining sub-module 53 1 determines whether the number of the survival detection messages sent by the other party received by the primary scheduling module and/or the standby primary scheduling module is zero, and if so, determines the primary usage.
  • the scheduling module and/or the standby primary scheduling module fails; when it is determined that one of the primary scheduling module and the standby primary scheduling module fails, the processing sub-module 532 further performs corresponding processing according to the failure result.
  • the preset fault period is a time maximum value of the received survival detection packet set according to the actual situation, and the value can detect the interval of the packet twice or three times. After the preset fault period, if the number of the survival detection packets received by the primary scheduling module and/or the standby primary scheduling module is zero, it indicates that the primary scheduling module and/or The running state of the standby main scheduling module is abnormal, so that the party that has failed can be further determined.
  • the processing sub-module 532 is configured to: when determining that the primary scheduling module is faulty, triggering the standby primary scheduling module to be upgraded to be the primary scheduling module; when determining that the standby primary scheduling module is faulty, triggering re-selection A new alternate primary scheduling module.
  • the survival detection mechanism detects whether the primary scheduling module and the standby primary scheduling module are faulty, if the number of the survival detection packets sent by the primary scheduling module received by the standby primary scheduling module is zero, it is determined that the primary scheduling module appears. Failure, at this time, by processing sub-module 532 The fast switching, that is, triggering the standby main scheduling module to be upgraded as the main scheduling module, succeeding the failed main scheduling module, and continuing to uniformly schedule the access request of the client access application.
  • the standby primary scheduling module detects that the primary scheduling module is faulty through the detection mechanism, triggering the self-upgrading as the primary scheduling module, and triggering the update of the internal forwarding table of the device, so that the user's application link
  • the request is forwarded to the service access unit of the switched primary scheduling module, and an application link is established with the primary scheduling module, and the user's access is scheduled and load balanced by the switched primary scheduling module.
  • the primary scheduling module may determine that the standby primary scheduling module is faulty. At this time, the processing sub-module 532 triggers a new selection mechanism, that is, on the CDN. And a plurality of scheduling modules included in the plurality of CDN service devices of the network convergence system, re-selecting a new standby primary scheduling module for scheduling and loading access to the user when the primary scheduling module fails Balanced work.
  • the primary scheduling module and the standby primary scheduling module After the primary scheduling module and the standby primary scheduling module are selected, whether the number of the survival detection packets received by the primary scheduling module and the standby primary scheduling module is zero or not is determined in the preset fault period. Fault, and after determining that the primary scheduling module or the standby primary scheduling module has failed, perform corresponding processing. In the case of faults, it can quickly replace and switch, avoiding the need to re-select a new active scheduling module and then switching services, improving the speed of service switching, and ensuring the stability of the CDN and network convergence system.
  • the mechanism establishment and fault detection module 53 and the sub-module thereof in the embodiment: the judgment sub-module 531 and the processing sub-module 532 can be used by the CPU or the DSP in the CDN and the network fusion system in practical applications. , or FPGA implementation.
  • a plurality of scheduling modules included in the plurality of CDN service devices are selected by the multicast scheduling method, and an active scheduling module for uniformly scheduling the access request of the client access application is selected, and selected.
  • An alternate main scheduling module for relaying the access request of the active access scheduling module to the client access application when the primary scheduling module fails.
  • the service scheduling module of multiple CDN service devices is unified and coordinated through the selected active scheduling module, which improves the stability of the CDN and the network convergence system, thereby ensuring the quality of the service and improving the user experience.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

L'invention concerne un système de convergence de CDN (réseau de distribution de contenu) et de réseau, un procédé de sélection de module de planification et un support de stockage informatique. Le procédé de sélection de module de planification est appliqué au système de convergence de CDN et de réseau. Le système de convergence de CDN et de réseau comprend une pluralité de dispositifs de service CDN. Les dispositifs de service CDN comprennent des modules de planification. Le procédé comprend : la sélection d'un module de planification principal et d'un module de planification maître de réserve parmi la pluralité de modules de planification contenus dans la pluralité de dispositifs de service CDN dans un mode de multidiffusion, le module de planification principal étant conçu pour exécuter une planification unifiée sur une demande d'accès appliquée par un client pour l'accès et le module de planification maître de réserve étant conçu pour remplacer rapidement le module de planification principal pour exécuter une planification unifiée sur la demande d'accès appliquée par le client pour un accès lorsque le module de planification principal est défaillant.
PCT/CN2014/072941 2013-03-21 2014-03-05 Système de convergence de cdn et de réseau, procédé de sélection de module de planification et support de stockage informatique Ceased WO2014146541A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201310092340.7 2013-03-21
CN201310092340.7A CN103200033B (zh) 2013-03-21 2013-03-21 Cdn与网络融合系统及其主、备用调度单元的选举方法

Publications (1)

Publication Number Publication Date
WO2014146541A1 true WO2014146541A1 (fr) 2014-09-25

Family

ID=48722399

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/072941 Ceased WO2014146541A1 (fr) 2013-03-21 2014-03-05 Système de convergence de cdn et de réseau, procédé de sélection de module de planification et support de stockage informatique

Country Status (2)

Country Link
CN (1) CN103200033B (fr)
WO (1) WO2014146541A1 (fr)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103200033B (zh) * 2013-03-21 2016-09-07 中兴通讯股份有限公司 Cdn与网络融合系统及其主、备用调度单元的选举方法
CN103647710A (zh) * 2013-11-01 2014-03-19 华为技术有限公司 一种路径配置方法及装置
CN105872614A (zh) * 2016-04-12 2016-08-17 乐视控股（北京）有限公司 直播流切换方法和装置
CN107360025B (zh) * 2017-07-07 2020-11-10 郑州云海信息技术有限公司 一种分布式存储系统集群监控方法及设备
CN107809480A (zh) * 2017-10-25 2018-03-16 上海瀚银信息技术有限公司 一种交易整流系统
CN110138808B (zh) * 2019-06-27 2021-04-13 苏宁消费金融有限公司 基于cdn的反劫持下载方法和系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101119318A (zh) * 2007-09-04 2008-02-06 中兴通讯股份有限公司 流媒体节点控制器的切换处理方法
CN101547334A (zh) * 2009-04-30 2009-09-30 杭州华三通信技术有限公司 保证主用mcu具有备用mcu的方法及视频会议系统
CN101640688A (zh) * 2009-08-20 2010-02-03 中兴通讯股份有限公司 基于cdn的节点主备用控制器切换方法及cdn网络
CN103117876A (zh) * 2013-01-24 2013-05-22 中兴通讯股份有限公司 用户状态信息的同步方法及装置
CN103200033A (zh) * 2013-03-21 2013-07-10 中兴通讯股份有限公司 Cdn与网络融合系统及其主、备用调度单元的选举方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101119318A (zh) * 2007-09-04 2008-02-06 中兴通讯股份有限公司 流媒体节点控制器的切换处理方法
CN101547334A (zh) * 2009-04-30 2009-09-30 杭州华三通信技术有限公司 保证主用mcu具有备用mcu的方法及视频会议系统
CN101640688A (zh) * 2009-08-20 2010-02-03 中兴通讯股份有限公司 基于cdn的节点主备用控制器切换方法及cdn网络
CN103117876A (zh) * 2013-01-24 2013-05-22 中兴通讯股份有限公司 用户状态信息的同步方法及装置
CN103200033A (zh) * 2013-03-21 2013-07-10 中兴通讯股份有限公司 Cdn与网络融合系统及其主、备用调度单元的选举方法

Also Published As

Publication number Publication date
CN103200033B (zh) 2016-09-07
CN103200033A (zh) 2013-07-10

Similar Documents

Publication Publication Date Title
US10999125B1 (en) Inter-application communication via signal-routes
CN108965123B (zh) 一种链路切换方法和网络通信系统
JP5913635B2 (ja) 冗長ネットワーク接続
EP2680510B1 (fr) Protection de réacheminement rapide déclenchée par un plan de service
US9380111B2 (en) Feature peer network with scalable state information
US8570857B2 (en) Resilient IP ring protocol and architecture
US8665711B2 (en) Fast restoration for provider edge node and access link failures
EP2878105B1 (fr) Système et procédé utilisant la suppression d'accueil rsvp pour le redémarrage progressif de voisins compétents
CN104168193B (zh) 一种虚拟路由器冗余协议故障检测的方法及路由设备
US9001671B2 (en) Feature peer network representations and scalable feature peer network management
US10148554B2 (en) System and methods for load placement in data centers
AU2009292017B2 (en) Reducing CC message transmission in a provider network
KR102050910B1 (ko) 연결 실패 시에 홈 네트워크에 대한 재라우팅을 인에이블시키는 방법 및 시스템
WO2012068996A1 (fr) Procédé et dispositif de détection d'état de liaisons
KR20120120472A (ko) Ｍｐｌｓ 링 토폴로지들에서의 최적화된 고속 리-라우트
CN101860492A (zh) 快速切换的方法、装置和系统
US8711681B2 (en) Switch redundancy in systems with dual-star backplanes
WO2014146541A1 (fr) Système de convergence de cdn et de réseau, procédé de sélection de module de planification et support de stockage informatique
WO2012106915A1 (fr) Procédé de notification d'incidents, appareil de détection, appareil de réacheminement, système, et structure de données
CN102447639B (zh) 一种策略路由方法及装置
US7940694B2 (en) Intelligent filtering of redundant data streams within computer networks
WO2014048128A1 (fr) Procédé de protection de service point à multipoint pour réseau en anneau et nœud d'anneau supérieur sur réseau en anneau
KR20200072941A (ko) 실시간 오류 감지를 통한 vrrp 기반의 네트워크 장애 대응 방법 및 장치
CN102461110B (zh) 用于对通过双环因特网协议(ip)网络的呼叫会话进行负荷平衡的方法和系统
CN101170450A (zh) 虚拟专用网络故障处理方法及网络提供商边界路由设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14770072

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14770072

Country of ref document: EP

Kind code of ref document: A1