CN114500340A - Intelligent scheduling distributed path calculation method and system - Google Patents
Intelligent scheduling distributed path calculation method and system Download PDFInfo
- Publication number
- CN114500340A CN114500340A CN202111590170.6A CN202111590170A CN114500340A CN 114500340 A CN114500340 A CN 114500340A CN 202111590170 A CN202111590170 A CN 202111590170A CN 114500340 A CN114500340 A CN 114500340A
- Authority
- CN
- China
- Prior art keywords
- central path
- server
- detection data
- detection
- path computation
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/12—Network monitoring probes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Hardware Redundancy (AREA)
Abstract
The invention discloses a method and a system for calculating an intelligent scheduling distributed path, wherein the method comprises the following steps: the detection server initiates a detection data request; the intelligent dispatching platform acquires heartbeat detection results of the central path calculation server clusters of all regions from the monitoring platform, and dispatches the detection data request to a target central path calculation server cluster if the heartbeat detection results of the target central path calculation server cluster of the region where the detection server is located are normal; and the switch in the target central path computation server cluster dispatches the detection data request to a central path computation server according to a load balancing mode so as to store the detection data through the central path computation server and synchronize the detection data to central path computation server clusters of other regions. The technical scheme provided by the application can improve the processing efficiency of the detection request.
Description
Technical Field
The invention relates to the technical field of internet, in particular to an intelligent scheduling distributed path calculation method and system.
Background
A conventional CDN (Content Delivery Network) dynamically loads an intelligent routing system to dynamically request a user, and mainly initiates a periodic probe request through a probe server, probes availability and Network performance of a transit node and a source station of the CDN, and selects an optimal back-source link according to a probe result. However, after the detection result is obtained, in order to reduce the computation pressure of the detection server, the detection and routing function modules are usually separated and completed in different servers or server clusters, a special server (generally a highly distributed machine based on a border gateway protocol) is used as a central path computation server for routing, the detection server reports detection data to the central path computation server, and the central path computation server computes a return-to-source path according to the reported detection data, and selects an optimal return-to-source link from the return-to-source path.
In order to realize high availability of central path computation, some existing central path computation server architectures are server clusters which are only deployed in a certain area, and the mode can cause the problem of large delay and even failure in reporting detection data. In addition, once the machine room in the area is powered off or in cut-over, the optimal return path cannot be calculated. Some of the systems are deployed in different regions, but a main-standby framework is adopted, which can solve the problem of power failure of a machine room in a certain region, but can not schedule the detection data requests reported by the detection servers in different regions nearby, and the standby central path computation server is idle in most cases, so that resources are wasted, the main-standby central path computation server cluster can not share the requests of the detection data reported by the detection servers in different regions evenly, and the cluster is not convenient to expand and change subsequently.
Disclosure of Invention
In view of this, embodiments of the present invention provide an intelligent scheduling distributed path calculation method and system, which can improve the processing efficiency of a probe request.
One aspect of the present invention provides a method for calculating an intelligent scheduling distributed path, including: a detection server initiates a detection data request, wherein the detection data request comprises detection data detected by the detection server; the intelligent dispatching platform acquires heartbeat detection results of the central path calculation server clusters of all regions from the monitoring platform, and dispatches the detection data request to a target central path calculation server cluster if the heartbeat detection results of the target central path calculation server cluster of the region where the detection server is located are normal; and the switch in the target central path computation server cluster dispatches the detection data request to a central path computation server according to a load balancing mode so as to store the detection data through the central path computation server and synchronize the detection data to central path computation server clusters of other regions.
In one embodiment, each central path computation server cluster is assigned a respective virtual IP address for external access, and a central path computation system formed by the respective central path computation server clusters is provided with a service domain name, wherein the service domain name can be resolved into the virtual IP addresses of the central path computation server clusters.
In one embodiment, the method further comprises: and if the heartbeat detection result of the target central path calculation server cluster in the area where the detection server is located is abnormal, dispatching the detection data request to other normally-served central path calculation server clusters.
In one embodiment, the dispatching the probe data request to one central path computation server by the switch in the target central path computation server cluster according to a load balancing manner includes: the switch sends a packet to detect the connectivity with each central path computation server at the back end, and if a certain path fails, other paths replace the central path computation servers to complete forwarding processing so as to realize route redundancy backup; and monitoring whether the service of the central path computing server is normal or not at regular time through a script, and if the service is abnormal, setting the route from the switch to the central path computing server to be unreachable, wherein when the switch carries out the detection data request scheduling, the switch does not schedule the detection data request to the central path computing server with unreachable route.
In one embodiment, the method further comprises: and a central path computation application program deployed on the central path computation server stores the detection data into a local database, and the inside of the central path computation server cluster realizes master-slave synchronization and backup of the detection data among different central path computation servers through the database.
In one embodiment, the central path computation server synchronizes the probe data to a cluster of central path computation servers of other regions in the following manner: and the central path computing server receiving the detection data initiates a request for reporting the detection data to the virtual IP addresses of the central path computing server clusters of other regions, so that the central path computing server clusters of all the regions acquire the same detection data, and the synchronization of cross-cluster detection data is realized.
The invention also provides an intelligent dispatching distributed path computing system, which comprises a detection server, an intelligent dispatching platform, a monitoring platform and a central path computing server cluster, wherein: the detection server is used for initiating a detection data request, and the detection data request comprises detection data detected by the detection server; the intelligent dispatching platform is used for acquiring heartbeat detection results of the central path calculation server clusters of all regions from the monitoring platform, and dispatching the detection data request to the target central path calculation server cluster if the heartbeat detection results of the target central path calculation server cluster of the region where the detection server is located are normal; the target central path computation server cluster is used for dispatching the detection data request to a central path computation server through a switch according to a load balancing mode, storing the detection data through the central path computation server, and synchronizing the detection data to central path computation server clusters of other regions.
In one embodiment, each central path computation server cluster is assigned a respective virtual IP address for external access, and a central path computation system formed by the respective central path computation server clusters is provided with a service domain name, wherein the service domain name can be resolved into the virtual IP addresses of the central path computation server clusters.
In one embodiment, the switch is further specifically configured to: sending a packet to detect the connectivity with each central path computing server at the back end, and if a certain path fails, replacing the path with other paths to complete forwarding processing so as to realize route redundancy backup; monitoring whether the service of the central path computation server is normal or not at regular time through a script, if the service is abnormal, setting the route to the central path computation server to be unreachable, wherein when the detection data request is dispatched, the detection data request is not dispatched to the central path computation server with the unreachable route.
In one embodiment, the central path computation server receiving the probe data is further configured to: and initiating a request for reporting the detection data to the virtual IP addresses of the central path computation server clusters in other areas, so that the central path computation server clusters in all areas acquire the same detection data, and the synchronization of cross-cluster detection data is realized.
The technical scheme provided by the application at least has the following technical effects:
1) the method can meet the requirement that the requests of the detection servers in different areas for reporting the detection data can be preferentially scheduled to the central path computing server clusters in the same area nearby, and the detection data requests reported by the detection servers are scheduled to the central path computing server clusters in other areas only when the central path computing server clusters in the same area are unavailable, so that the success rate of reporting the detection data can be improved, and the request delay of reporting the detection data is reduced;
2) the method and the system realize the multi-activity of the central path computing service in different places, namely, the central path computing server clusters in all regions provide the service at the same time, the reported detection data requests of the detection servers in different regions can be shared, and the path computing pressure of a single central path computing server cluster is reduced. In addition, the cluster architecture of the distributed central path computation server with multiple activities at different places facilitates subsequent capacity expansion and server updating, and is convenient to manage and maintain;
3) the ECMP (Equal Cost Multi-path) technology of the switch is adopted to realize load balancing scheduling in the central path computing server cluster, and compared with the traditional LVS + keepalive load balancing technology, the method saves server resources for deploying LVS and keepalive software.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are illustrative and not to be construed as limiting the invention in any way, and in which:
FIG. 1 is a schematic diagram illustrating the steps of a method for intelligently scheduling distributed path computation according to an embodiment of the present invention;
FIG. 2 is a flow diagram illustrating a method for intelligently scheduling distributed path computations in accordance with an embodiment of the present invention;
FIG. 3 is a block diagram of a system for intelligently scheduling distributed path computations in accordance with an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Referring to fig. 1, the method for calculating an intelligent scheduling distributed path provided by the present application may include the following steps.
S1: the detection server initiates a detection data request, wherein the detection data request comprises detection data detected by the detection server.
S2: and the intelligent dispatching platform acquires heartbeat detection results of the central path calculation server clusters of all regions from the monitoring platform, and dispatches the detection data request to the target central path calculation server cluster if the heartbeat detection results of the target central path calculation server cluster of the region where the detection server is located are normal.
S3: and the switch in the target central path computation server cluster dispatches the detection data request to a central path computation server according to a load balancing mode so as to store the detection data through the central path computation server and synchronize the detection data to central path computation server clusters of other regions.
Referring to fig. 2, each central path computation server cluster is assigned a Virtual IP address (VIP) for external access, and a central path computation system formed by the central path computation server clusters has a service domain name, wherein the service domain name can be resolved into the VIP addresses of the central path computation server clusters. Specifically, after receiving a probe data request from a probe Server, a Domain Name Server (DNS) may resolve the probe data request to a central path computation Server cluster under a central path computation system.
In one embodiment, a probe server in the area a initiates a probe data request to a central path computing system, and the request is preferentially scheduled to a central path computing server cluster located in the same area a as the probe server by a DNS intelligent scheduling platform, thereby implementing the near scheduling of the probe data request.
The monitoring platform acquires and detects A, B heartbeat detection results of VIPs of central path computing server clusters of multiple regions at regular time, the DNS intelligent scheduling platform acquires the heartbeat detection results of the central path computing server clusters of each region, and once the heartbeat detection of the VIPs of the central path computing server clusters scheduled nearby fails, the DNS intelligent scheduling platform switches to other central path computing server clusters which are normally served.
That is, in this embodiment, if the heartbeat detection result of the target central path computation server cluster in the area where the probe server is located is abnormal, the probe data request is dispatched to other normally served central path computation server clusters.
In one embodiment, after a probe data request reaches a switch of an area a machine room, a packet is sent by using an Open Shortest Path First (OSPF) load balancing technology (ECMP, equal cost multi-Path routing) of the switch to probe connectivity with a back-end real central Path computing server, and if a Path fails, other paths are substituted to complete forwarding processing, so that a routing redundancy backup function is realized. The method comprises the steps of monitoring whether the service of a central path computing server is normal or not at regular time through a script (including whether heartbeat detection is sent to a central path computing application program or not, whether a Redis application program port is monitored or not and the like), and if the service is abnormal, modifying the route from a switch to the central path computing server through routing software Quagga to be unreachable, so that a request cannot be dispatched to the central path computing server with abnormal service when the load of the switch is balanced and dispatched.
That is, the switch sends a packet to detect connectivity with each central path computation server at the back end, and if a certain path fails, other paths are used to complete forwarding processing instead, so as to implement route redundancy backup. And monitoring whether the service of the central path computing server is normal or not at regular time through a script, and if the service is abnormal, setting the route from the switch to the central path computing server to be unreachable, wherein when the switch carries out the detection data request scheduling, the switch does not schedule the detection data request to the central path computing server with unreachable route.
In one embodiment, a central path computation application deployed on each central path computation server in a central path computation server cluster is responsible for receiving detection data reported by a detection server, storing the detection data in a local Redis application (database), and implementing master-slave synchronization and backup of the detection data between different central path computation servers through the Redis application in the cluster.
In this way, the central path computation application deployed on the central path computation server stores the detection data in a local database, and the inside of the central path computation server cluster realizes master-slave synchronization and backup of the detection data between different central path computation servers through the database.
In one embodiment, after the detection data reported by the detection server is dispatched to a certain central path computing server in the central path computing server cluster in the same region through intelligent dispatching and switch load balancing, the detection server actively initiates a detection data request to the central path computing server clusters VIP in other regions, so that the central path computing server clusters in all regions can obtain the same detection data, and cross-cluster detection data synchronization is realized.
That is to say, the central path computation server receiving the probe data initiates a probe data reporting request to the virtual IP addresses of the central path computation server clusters in other regions, so that the central path computation server clusters in each region all acquire the same probe data, thereby achieving synchronization of cross-cluster probe data.
In a specific application example, the technical solution of the present application may be executed according to the following steps:
1) the method comprises the steps that a detection server periodically initiates detection requests for CDN transit nodes and source stations to obtain detection data;
2) reporting the detection data to a central path computing system in an http request mode;
3) the DNS intelligent scheduling platform combines heartbeat detection results of the VIP of the central path calculation server clusters of all the regions acquired from the monitoring platform according to the region where the IP of the detection server sending the detection data request is located, and if the heartbeat detection of the VIP of the central path calculation server clusters in the same region as the detection server is normal, nearby scheduling of reporting the detection data request is achieved by modifying the resolution of the service domain name of the central path calculation system; otherwise, dispatching the request to a central path computation server cluster of other regions;
4) after a detection data request reported by a detection server reaches a machine room of a central path computation server cluster, monitoring the service condition of the central path computation server at regular time by combining a script through an OSPF + ECMP load balancing technology of a machine room switch, realizing load balancing scheduling in the central path computation server cluster, and eliminating the central path computation server with abnormal service in time without participating in load balancing scheduling of the switch;
5) after a central path calculation application program deployed on each central path calculation server in the cluster finally receives detection data reported by the detection server, the detection data is stored in the Redis of the cluster, and the master-slave synchronization and backup of the detection data between different central path calculation servers are realized in the cluster through the Redis application program; meanwhile, the detection data received by the user are sent to the VIP of the central path computing server clusters of other regions in an http request mode, so that the central path computing server clusters of all the regions can acquire the same detection data, and synchronization of cross-cluster detection data is achieved.
Referring to fig. 3, the present application further provides an intelligent scheduling distributed path computing system, which includes a detection server, an intelligent scheduling platform, a monitoring platform, and a central path computing server cluster, where:
the detection server is used for initiating a detection data request, and the detection data request comprises detection data detected by the detection server;
the intelligent dispatching platform is used for acquiring heartbeat detection results of the central path calculation server clusters of all regions from the monitoring platform, and dispatching the detection data request to the target central path calculation server cluster if the heartbeat detection results of the target central path calculation server cluster of the region where the detection server is located are normal;
the target central path computation server cluster is used for dispatching the detection data request to a central path computation server through a switch according to a load balancing mode, storing the detection data through the central path computation server, and synchronizing the detection data to central path computation server clusters of other regions.
In one embodiment, each central path computation server cluster is assigned a respective virtual IP address for external access, and a central path computation system formed by the respective central path computation server clusters is provided with a service domain name, wherein the service domain name can be resolved into the virtual IP addresses of the central path computation server clusters.
In one embodiment, the switch is further specifically configured to:
sending a packet to detect the connectivity with each central path computing server at the back end, and if a certain path fails, replacing the path with other paths to complete forwarding processing so as to realize route redundancy backup;
and monitoring whether the service of the central path computing server is normal or not at regular time through a script, and if the service is abnormal, setting the route to the central path computing server to be unreachable, wherein when the detection data request is dispatched, the detection data request is not dispatched to the central path computing server with unreachable route.
In one embodiment, the central path computation server receiving the probe data is further configured to: and initiating a request for reporting the detection data to the virtual IP addresses of the central path computing server clusters of other areas, so that the central path computing server clusters of all areas acquire the same detection data, and the synchronization of cross-cluster detection data is realized.
The technical scheme provided by the application at least has the following technical effects:
1) the method can meet the requirement that the requests of the detection servers in different areas for reporting the detection data can be preferentially scheduled to the central path computing server clusters in the same area nearby, and the detection data requests reported by the detection servers are scheduled to the central path computing server clusters in other areas only when the central path computing server clusters in the same area are unavailable, so that the success rate of reporting the detection data can be improved, and the request delay of reporting the detection data is reduced;
2) the method and the system realize the multi-activity of the central path computing service in different places, namely, the central path computing server clusters in all regions provide the service at the same time, the reported detection data requests of the detection servers in different regions can be shared, and the path computing pressure of a single central path computing server cluster is reduced. In addition, the cluster architecture of the distributed central path computation server with multiple different places and activities facilitates subsequent capacity expansion and server updating, and facilitates management and maintenance;
3) the ECMP (Equal Cost Multi-path) technology of the switch is adopted to realize load balancing scheduling in the central path computing server cluster, and compared with the traditional LVS + keepalive load balancing technology, the method saves server resources for deploying LVS and keepalive software.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. An intelligent scheduling distributed path computation method, the method comprising:
a detection server initiates a detection data request, wherein the detection data request comprises detection data detected by the detection server;
the intelligent dispatching platform acquires heartbeat detection results of the central path calculation server clusters of all regions from the monitoring platform, and dispatches the detection data request to a target central path calculation server cluster if the heartbeat detection results of the target central path calculation server cluster of the region where the detection server is located are normal;
and the switch in the target central path computation server cluster dispatches the detection data request to a central path computation server according to a load balancing mode so as to store the detection data through the central path computation server and synchronize the detection data to central path computation server clusters of other regions.
2. The method of claim 1, wherein each of the central path computation server clusters is assigned a respective virtual IP address for external access, and wherein a central path computation system formed by each of the central path computation server clusters is provided with a service domain name, wherein the service domain name is resolvable to the virtual IP address of the central path computation server cluster.
3. The method of claim 1, further comprising:
and if the heartbeat detection result of the target central path calculation server cluster in the area where the detection server is located is abnormal, dispatching the detection data request to other normally-served central path calculation server clusters.
4. The method of claim 1, wherein the dispatching of the probe data request to one central path computation server by the switch in the target central path computation server cluster in a load balancing manner comprises:
the switch sends a packet to detect the connectivity with each central path computing server at the back end, if a certain path fails, other paths replace the central path computing servers to complete forwarding processing so as to realize route redundancy backup;
and monitoring whether the service of the central path computing server is normal or not at regular time through a script, and if the service is abnormal, setting the route from the switch to the central path computing server to be unreachable, wherein when the switch carries out the detection data request scheduling, the switch does not schedule the detection data request to the central path computing server with unreachable route.
5. The method of claim 1, further comprising:
and a central path computation application program deployed on the central path computation server stores the detection data into a local database, and the inside of the central path computation server cluster realizes master-slave synchronization and backup of the detection data among different central path computation servers through the database.
6. The method of claim 1, wherein the central path computation server synchronizes the probe data to a cluster of central path computation servers of other regions in the following manner:
and the central path computing server receiving the detection data initiates a request for reporting the detection data to the virtual IP addresses of the central path computing server clusters of other regions, so that the central path computing server clusters of all the regions acquire the same detection data, and the synchronization of cross-cluster detection data is realized.
7. An intelligent scheduling distributed path computation system, the system comprising a probe server, an intelligent scheduling platform, a monitoring platform and a central path computation server cluster, wherein:
the detection server is used for initiating a detection data request, and the detection data request comprises detection data detected by the detection server;
the intelligent dispatching platform is used for acquiring heartbeat detection results of the central path calculation server clusters of all regions from the monitoring platform, and dispatching the detection data request to the target central path calculation server cluster if the heartbeat detection results of the target central path calculation server cluster of the region where the detection server is located are normal;
the target central path computation server cluster is used for dispatching the detection data request to a central path computation server through a switch according to a load balancing mode, storing the detection data through the central path computation server, and synchronizing the detection data to central path computation server clusters of other regions.
8. The system of claim 7, wherein each of the central path computation server clusters is assigned a respective virtual IP address for external access, and wherein a central path computation system formed by each of the central path computation server clusters is provided with a service domain name, wherein the service domain name is resolvable to the virtual IP address of the central path computation server cluster.
9. The system of claim 7, wherein the switch is further specifically configured to:
sending a packet to detect the connectivity with each central path computing server at the back end, and if a certain path fails, replacing the path with other paths to complete forwarding processing so as to realize route redundancy backup;
and monitoring whether the service of the central path computing server is normal or not at regular time through a script, and if the service is abnormal, setting the route to the central path computing server to be unreachable, wherein when the detection data request is dispatched, the detection data request is not dispatched to the central path computing server with unreachable route.
10. The system of claim 7, wherein the central path computation server that receives the probe data is further configured to: and initiating a request for reporting the detection data to the virtual IP addresses of the central path computing server clusters of other areas, so that the central path computing server clusters of all areas acquire the same detection data, and the synchronization of cross-cluster detection data is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111590170.6A CN114500340B (en) | 2021-12-23 | 2021-12-23 | Intelligent scheduling distributed path calculation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111590170.6A CN114500340B (en) | 2021-12-23 | 2021-12-23 | Intelligent scheduling distributed path calculation method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114500340A true CN114500340A (en) | 2022-05-13 |
CN114500340B CN114500340B (en) | 2023-08-04 |
Family
ID=81494490
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111590170.6A Active CN114500340B (en) | 2021-12-23 | 2021-12-23 | Intelligent scheduling distributed path calculation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114500340B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115865932A (en) * | 2023-02-27 | 2023-03-28 | 天翼云科技有限公司 | Traffic scheduling method and device, electronic equipment and storage medium |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050172161A1 (en) * | 2004-01-20 | 2005-08-04 | International Business Machines Corporation | Managing failover of J2EE compliant middleware in a high availability system |
CN103731482A (en) * | 2013-12-24 | 2014-04-16 | 浪潮电子信息产业股份有限公司 | Cluster load balancing system and achieving method thereof |
US20140108339A1 (en) * | 2011-09-23 | 2014-04-17 | Hybrid Logic Ltd | System for live-migration and automated recovery of applications in a distributed system |
CN103780591A (en) * | 2012-10-25 | 2014-05-07 | 北京航天长峰科技工业集团有限公司 | Public security cloud computing center construction method |
CN105357142A (en) * | 2015-12-02 | 2016-02-24 | 浙江工商大学 | Method for designing network load balancer system based on ForCES |
CN105812255A (en) * | 2016-05-06 | 2016-07-27 | 网宿科技股份有限公司 | Source return line selection method and device |
US9454444B1 (en) * | 2009-03-19 | 2016-09-27 | Veritas Technologies Llc | Using location tracking of cluster nodes to avoid single points of failure |
CN107846445A (en) * | 2017-09-20 | 2018-03-27 | 南京邮电大学 | A kind of server load balancing method based on SDN |
CN107864228A (en) * | 2017-12-22 | 2018-03-30 | 网宿科技股份有限公司 | Connection method for building up and system in a kind of content distributing network |
CN108055321A (en) * | 2017-12-11 | 2018-05-18 | 中国电子科技集团公司第二十八研究所 | Highly reliable cluster construction method based on production domesticization platform |
CN108429682A (en) * | 2018-02-26 | 2018-08-21 | 湖南科技学院 | A kind of optimization method and system of network transmission link |
CN110034925A (en) * | 2019-01-07 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Across computer room trust computing cluster formation and communication means and device |
US20210089415A1 (en) * | 2019-09-25 | 2021-03-25 | Sap Se | High availability for a relational database management system as a service in a cloud platform |
US20210243250A1 (en) * | 2020-02-04 | 2021-08-05 | Nutanix, Inc. | Efficient virtual ip address management for service clusters |
CN113300955A (en) * | 2020-12-16 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Method, system and equipment for determining paths between nodes in content distribution network |
CN113703950A (en) * | 2021-09-10 | 2021-11-26 | 国泰君安证券股份有限公司 | System, method and device for realizing server cluster flow scheduling processing, processor and computer readable storage medium thereof |
US11188393B1 (en) * | 2021-03-02 | 2021-11-30 | NortonLifeLock Inc. | Systems and methods for performing load balancing and distributed high-availability |
-
2021
- 2021-12-23 CN CN202111590170.6A patent/CN114500340B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050172161A1 (en) * | 2004-01-20 | 2005-08-04 | International Business Machines Corporation | Managing failover of J2EE compliant middleware in a high availability system |
US9454444B1 (en) * | 2009-03-19 | 2016-09-27 | Veritas Technologies Llc | Using location tracking of cluster nodes to avoid single points of failure |
US20140108339A1 (en) * | 2011-09-23 | 2014-04-17 | Hybrid Logic Ltd | System for live-migration and automated recovery of applications in a distributed system |
CN103780591A (en) * | 2012-10-25 | 2014-05-07 | 北京航天长峰科技工业集团有限公司 | Public security cloud computing center construction method |
CN103731482A (en) * | 2013-12-24 | 2014-04-16 | 浪潮电子信息产业股份有限公司 | Cluster load balancing system and achieving method thereof |
CN105357142A (en) * | 2015-12-02 | 2016-02-24 | 浙江工商大学 | Method for designing network load balancer system based on ForCES |
CN105812255A (en) * | 2016-05-06 | 2016-07-27 | 网宿科技股份有限公司 | Source return line selection method and device |
CN107846445A (en) * | 2017-09-20 | 2018-03-27 | 南京邮电大学 | A kind of server load balancing method based on SDN |
CN108055321A (en) * | 2017-12-11 | 2018-05-18 | 中国电子科技集团公司第二十八研究所 | Highly reliable cluster construction method based on production domesticization platform |
CN107864228A (en) * | 2017-12-22 | 2018-03-30 | 网宿科技股份有限公司 | Connection method for building up and system in a kind of content distributing network |
CN108429682A (en) * | 2018-02-26 | 2018-08-21 | 湖南科技学院 | A kind of optimization method and system of network transmission link |
CN110034925A (en) * | 2019-01-07 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Across computer room trust computing cluster formation and communication means and device |
US20210089415A1 (en) * | 2019-09-25 | 2021-03-25 | Sap Se | High availability for a relational database management system as a service in a cloud platform |
US20210243250A1 (en) * | 2020-02-04 | 2021-08-05 | Nutanix, Inc. | Efficient virtual ip address management for service clusters |
CN113300955A (en) * | 2020-12-16 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Method, system and equipment for determining paths between nodes in content distribution network |
US11188393B1 (en) * | 2021-03-02 | 2021-11-30 | NortonLifeLock Inc. | Systems and methods for performing load balancing and distributed high-availability |
CN113703950A (en) * | 2021-09-10 | 2021-11-26 | 国泰君安证券股份有限公司 | System, method and device for realizing server cluster flow scheduling processing, processor and computer readable storage medium thereof |
Non-Patent Citations (5)
Title |
---|
JUNAID QADIR等: "Exploiting the Power of Multiplicity: A Holistic Survey of Network-Layer Multipath", 《IEEE COMMUNICATIONS SURVEYS & TUTORIALS ( VOLUME: 17, ISSUE: 4, FOURTHQUARTER 2015)》 * |
屈钢 等: "Linux集群技术研究", 《计算机应用研究》 * |
张淼: "CDN系统中基于层次策略的负载均衡算法的研究与性能仿真", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
马双良 等: "基于LVS和计算任务的实时集群负载均衡方法", 《计算机工程与设计》 * |
高爱莲;刘增磊;刘中艳;: "高可用集群系统的研究", 信息系统工程, no. 10 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115865932A (en) * | 2023-02-27 | 2023-03-28 | 天翼云科技有限公司 | Traffic scheduling method and device, electronic equipment and storage medium |
CN115865932B (en) * | 2023-02-27 | 2023-06-23 | 天翼云科技有限公司 | Traffic scheduling method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN114500340B (en) | 2023-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112087333B (en) | Micro-service registry cluster and information processing method thereof | |
CN107454155B (en) | Fault processing method, device and system based on load balancing cluster | |
CN107465721B (en) | Global load balancing method and system based on double-active architecture and scheduling server | |
US11416359B2 (en) | Hot standby method, apparatus, and system | |
WO2017162184A1 (en) | Method of controlling service traffic between data centers, device, and system | |
CN103475566A (en) | Real-time message exchange platform and distributed cluster establishment method | |
CN112671882A (en) | Same-city double-activity system and method based on micro-service | |
US20220131935A1 (en) | Service Unit Switching Method, System, and Device | |
US20180069782A1 (en) | Network address translation in networks using multiple nat devices | |
CN111615066A (en) | Distributed micro-service registration and calling method based on broadcast | |
CN110391940B (en) | Service address response method, device, system, equipment and storage medium | |
CN113268351A (en) | Load balancing method and device for gateway service | |
CN114500340B (en) | Intelligent scheduling distributed path calculation method and system | |
EP1762069A1 (en) | Method of selecting one server out of a server set | |
US10652305B2 (en) | High availability voice over internet protocol telephony | |
CN113326100A (en) | Cluster management method, device and equipment and computer storage medium | |
CN100423514C (en) | Data synchronization method in distributed equipment according to address resolution protocol | |
US9015518B1 (en) | Method for hierarchical cluster voting in a cluster spreading more than one site | |
CN114268581B (en) | Method for realizing high availability and load sharing of network equipment | |
US8438261B2 (en) | Failover scheme with service-based segregation | |
CN110971872B (en) | Video image information acquisition method based on distributed cluster | |
CN112261095A (en) | Load distribution implementation system and method based on two-stage agent | |
US11637893B2 (en) | Load distribution across superclusters | |
CN117478488B (en) | Cloud management platform switching system, method, equipment and medium | |
CN117041329B (en) | Micro-service configuration system based on heterogeneous bus structure and control method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |