CN112543150A - Dynamic load balancing method based on server control - Google Patents
Dynamic load balancing method based on server control Download PDFInfo
- Publication number
- CN112543150A CN112543150A CN202011178608.5A CN202011178608A CN112543150A CN 112543150 A CN112543150 A CN 112543150A CN 202011178608 A CN202011178608 A CN 202011178608A CN 112543150 A CN112543150 A CN 112543150A
- Authority
- CN
- China
- Prior art keywords
- service
- load balancing
- server
- client
- dynamic load
- 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
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/45—Network directories; Name-to-address mapping
- H04L61/4505—Network directories; Name-to-address mapping using standardised directories; using standardised directory access protocols
- H04L61/4511—Network directories; Name-to-address mapping using standardised directories; using standardised directory access protocols using domain name system [DNS]
-
- 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
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
-
- 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
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention provides a dynamic load balancing method based on server control, which comprises the following steps: the client declares the required service type, and applies for acquiring a connection address corresponding to the service from the load balancing server; after receiving the request of the client, the load balancing server executes weight calculation; the load balancing server performs weight calculation according to the service list sequence, performs sorting according to the weight value after the calculation is completed, and returns the sorted result to the client; after receiving the service list, the client selects the service with the largest weight value to execute connection; and when the client detects that the connected application service is interrupted and cannot provide the service, trying to reconnect the service with the second largest weight value according to the service list, wherein when all the services cannot be connected, the client acquires a latest service list from the load balancing server again.
Description
Technical Field
The invention relates to the field of computers, in particular to a dynamic load balancing method based on server side control.
Background
In computer services, a load balancing technology is a key step for guaranteeing high availability of a platform system architecture. The load of the system is to access a plurality of same service entrances through a unified entrance and provide certain strategic load. A common architecture is shown in fig. 1.
The user request is resolved by a DNS system of the Internet, and finally accesses to a public network IP address, and a service port of the user request is generally a load balancer. And the load balancer distributes the user request to different business services according to different strategies.
Common load balancing strategies include Round-Robin balancing (Round Robin), Weighted Round-Robin (Weighted Round Robin), Random balancing (Random), Weighted Random balancing (Weighted Random), Response speed balancing (Response Time), Least Connection balancing (Least Connection), and the like.
The load balancing strategy of the existing technical scheme cannot be well combined with the real service situation of the server. For example:
example 1 a service in a cluster is scheduled to perform high CPU consumption computing services, and it is desirable to reduce or stop requests from the load balancer. Since the application service is normal, the planned work and the port respond, and the service is completely normal but high in consumption. For such a scenario, the conventional load balancing cannot sense the situation, and still distributes the internet request to the high-pressure server according to the original strategy. The consequence is that the request assigned to this service is slow to respond if it is light, and fails if it is heavy. In extreme cases, this service may be caused to crash due to high pressure.
Example 2, some service scenarios expect that load-balanced access allocation can be performed more actively according to some rules. For example, the services after load balancing are deployed according to different machine rooms and different geographic locations. Business parties expect that users can access services nearby. For example, the service a is deployed in the shanghai IDC room, and the business side expects all shanghai local users to use the service of the shanghai IDC room to perform business operation, thereby ensuring better user experience. At this time, the load balancer needs to perform address analysis on the requested IP, screen out the IP addresses belonging to shanghai, and then allocate the IP addresses to the shanghai machine room to perform subsequent business processes.
It can be seen that in both cases, the conventional load balancer cannot respond. The traditional load balancer cannot sense the real condition of a server.
Disclosure of Invention
One of the objectives of the present invention is to provide a dynamic load balancing method based on server control, which can control the connection of different clients at the server, and is particularly suitable for a mobile phone client or a multi-computer-room environment microservice client.
Another objective of the present invention is to provide a dynamic load balancing method based on server control, which optimizes client connection according to a weight algorithm, and improves connection efficiency.
Another objective of the present invention is to provide a dynamic load balancing method based on server control, which has high scalability, and can adjust the weight algorithm design according to the actual requirements, so as to achieve different effects.
Another objective of the present invention is to provide a dynamic load balancing method based on server control, which can perform online adjustment of weight parameters of an algorithm by developing corresponding web services, and implement control of offloading of client connections without restarting services.
Another objective of the present invention is to provide a dynamic load balancing method based on server control, where the server is provided with status data and load data of the client, and is capable of monitoring a service status and providing an alarm service.
The invention also aims to provide a dynamic load balancing method based on server side control, which can record the request record and the return result record of the client side at the server side in the aspect of data statistics, perform data summary statistics and analyze the connection tendency of the client side.
In order to achieve at least one of the above objects, the present invention provides a dynamic load balancing method based on server side control, including the following steps:
the client declares the required service type, and applies for acquiring a connection address corresponding to the service from the load balancing server;
after receiving the request of the client, the load balancing server executes weight calculation;
the load balancing server performs weight calculation according to the service list sequence, performs sorting according to the weight value after the calculation is completed, and returns the sorted result to the client;
after receiving the service list, the client selects the service with the largest weight value to execute connection;
and
when the client detects that the connected application service is interrupted and cannot provide the service, the client tries to reconnect to the service with the second largest weight value according to the service list, wherein when all the services cannot be connected, the client acquires a latest service list from the load balancing server again.
In some embodiments, the dynamic load balancing method based on server side control further includes the steps of: the parameters of the plan transmitted by the client are the IP address of the client, the service type of the client, the service data of the address of the user, the service data of the area of the user and the service data of the organizational structure.
In some embodiments, the dynamic load balancing method based on server side control further includes the steps of: and performing the calculation of the weight value according to the service state, the service load rate, the network flow and the intervention factors of whether the IP address of the client and the application service are near.
In some embodiments, the dynamic load balancing method based on server side control further includes the steps of: the weight value for each service is calculated according to the following formula: the weight value of each service is service state x { (1-service load rate) × service pressure + (network traffic upper limit-current network traffic) × network traffic + intervention factor of whether the IP address is close × client IP and whether the server is close + server intervention weight }.
In some embodiments, the dynamic load balancing method based on server side control further includes the steps of: and the client performs additional weight calculation on the returned service list, initiates a connection test on the returned IP address, acquires response time, weights the response time, adds the response time to a weight value returned by the server, and selects the service with the largest weight value to perform connection.
In some embodiments, the service list in which the server-side controlling dynamic load balancing service manager is a service list of a single host node.
In some embodiments, the service list in which the server controls the dynamic load balancing service manager is a service list that is externally accessible to the client through all the rooms to which the public network DNS service is connected.
In some embodiments, the dynamic load balancing method based on server side control includes the following steps:
the client side adopts public network DNS service domain name resolution service, a first request for acquiring a service address of a user is transferred to one of the machine rooms, the request passes through a firewall of the machine room and is loaded to the server side control dynamic load balancing server by the load balancing server, and the server side control dynamic load balancing server performs weight calculation according to client side parameters and then returns an external access service list corresponding to the application of the service;
the client side obtains the sorted service list returned from the server side and then connects the external access address of the corresponding machine room service;
the method comprises the steps that an Agent service node is arranged, Agent collection is carried out on all services in a machine room, data summarization is carried out on collected application state data, and the data summarization is periodically pushed to one server side control dynamic load balancing server;
and
and performing consistency synchronization on all server side control dynamic load balancing servers, setting the server side control dynamic load balancing servers to be in a non-centralized design, and performing data synchronization by adopting a non-centralized Gossip protocol through the server side control dynamic load balancing servers.
In some embodiments, wherein the Gossip protocol execution process comprises the steps of:
the seed node periodically disseminates the message;
an infected node randomly selects a plurality of adjacent nodes to disseminate the message;
the node only receives the message and does not feed back the result;
each time of message dissemination, selecting nodes which have not been sent to perform dissemination;
and
the node that received the message is no longer broadcasting to the sending node.
In some embodiments, the period in which the seed node disseminates the message is 1 second, with a maximum of 6 nodes disseminated at a time.
Drawings
Fig. 1 is a general architecture diagram of a conventional load balancing technique.
Fig. 2 is a flowchart illustrating a dynamic load balancing method based on server side control according to a preferred embodiment of the present invention.
Fig. 3 is an architecture diagram of the dynamic load balancing method based on server side control according to another embodiment of the present invention.
Detailed Description
The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as defined in the following description, may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
It will be understood by those skilled in the art that in the present disclosure, the terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in an orientation or positional relationship indicated in the drawings for ease of description and simplicity of description, and do not indicate or imply that the referenced devices or components must be constructed and operated in a particular orientation and thus are not to be considered limiting.
It is understood that the terms "a" and "an" should be interpreted as meaning that a number of one element or element is one in one embodiment, while a number of other elements is one in another embodiment, and the terms "a" and "an" should not be interpreted as limiting the number.
The invention provides a dynamic load balancing method based on server control, and a system applying the dynamic load balancing method based on server control can overcome the defects of perceptibility and individuation of the traditional load balancing algorithm. The method can control the connection of different clients at the server, and is particularly suitable for mobile phone clients or multi-computer-room environment micro-service clients. According to the weight algorithm, the client connection is optimized, and the connection efficiency is improved. The system applying the dynamic load balancing method based on the server control has high expansibility, and the weight algorithm design can be adjusted according to actual requirements to achieve different effects. The weight parameters of the algorithm can be adjusted online by developing corresponding web services, and the shunting of client connection can be controlled under the condition of not restarting the services. Meanwhile, the server side has the state data and the load data of the client side, so that certain service state monitoring can be carried out, and the alarm service is provided. In the aspect of data statistics, the request record and the return result record of the client can be recorded at the server, data summarization statistics is carried out, and the connection tendency of the client is analyzed.
Fig. 2 is a flowchart of the dynamic load balancing method based on server control according to the preferred embodiment of the present invention, which can solve the problem that the conventional load balancer cannot sense the real status of the server, and customize a system that combines real service requirements.
Specifically, as shown in fig. 2, the dynamic load balancing method based on server side control includes the following steps:
step 1: a client acquires a request address from a load balancing server;
step 2: sorting after receiving the service list;
and step 3: initiating a connection request; when the connection with the application service 01 fails, automatically connecting the application service 02;
and 4, step 4: and the application server 01 or the application server 02 feeds the application state back to the server side to control the dynamic load balancing service.
In the implementation of the dynamic load balancing method based on the server control, the server control dynamic load balancing service is used as an observer of a traffic bypass instead of directly loading the request of the user traffic, and indicates the optimal connection service address of the client, and then the client performs direct connection on the application service.
Specifically, in this preferred embodiment, the dynamic load balancing method based on server side control includes the following steps:
a, the client declares the required service type and applies for the optimal connection address corresponding to the service from the load balancing server.
At this time, the client may be introduced with planning parameters, such as an IP address of the client, a service type to which the client belongs, various service data, such as a user ID, a region to which the client belongs, an organization structure, and the like.
And B: and after receiving the client request, the load balancing server performs weight calculation for one time.
And B, returning an ordered service list with weight values according to parameters transmitted by the client in the step A, such as user ID, IP address where the client is located, applied service type and the like, and according to the actual service state of the corresponding application service, such as pressure and network flow condition.
Preferably, in a specific embodiment, the typical dimension of the weight calculation is service state, service load rate, network traffic, whether the client IP address and the application service are nearby (same network segment or same region), and a service intervention weight.
In the preferred embodiment, when the intervention weight of the server is calculated, the weight is set to W, the service state is set to T, the value range is [0,1], the service load rate is P, the value range is (0,1), the upper limit of the network traffic is S, the current network traffic is S1, whether the client IP and the server are nearby is N, the value range is [0.25,1], and the intervention weight of the server is O. The calculation formula for each service is:
W＝T×((1-P)×K+(S-S1)×V+U×N+O)
the K, the V and the U are intervention factors for judging whether the service pressure, the network flow and the IP address are close or not respectively, and can be configured according to the effect which is required to be achieved actually.
And C: and the load balancing server sequentially calculates the weight according to the service list. And after the calculation is finished, sorting according to the weight value. And returning the sorted result to the client.
Step D: after receiving the service list, the client selects the service with the highest priority (i.e. the highest weight value) for connection.
It is worth mentioning that, at this time, the client can perform additional weight calculation on the returned service list, for example, initiate PING (Packet Internet Groper) connection test on the returned IP, and obtain the response time. And weighting the response time, and adding the weighted value to the weight value returned by the server. And selecting the service with the largest weight value for connection.
Step E: when the client detects that the application services which are connected are interrupted and cannot provide the services, the client can attempt to reconnect to suboptimal services according to the service list. And when all the services are not connectable, newly acquiring an up-to-date service list from the load balancing server. Said step E can be repeated.
Fig. 2 shows a single-node principle scheme of the dynamic load balancing method based on server-side control according to the present invention. In another embodiment of the dynamic load balancing method based on server side control according to the present invention, in order to ensure that all services are highly available in an actual multi-computer-room environment, the system shown in fig. 3 is used. The biggest difference between this scheme and the scheme of fig. 2 is that the service list of the server-side controlled dynamic load balancing service management is not the service list of a single host node, but the service list of all the servers accessible to the outside.
Specifically, as shown in fig. 3, the client connection uses a public network DNS service domain name resolution service, and transfers a first request of a user to obtain an a service address to a certain machine room. The request passes through a firewall of a computer room, and is loaded to a server side control dynamic load balancing service by the traditional load balancing service. And the server side controls the dynamic load balancing service to perform weight calculation according to the client side parameters, and then returns to the external access service list of the application A. It is worth mentioning that, at this time, the returned address is not the IP address of a single service in the room, but the external access address of the application service of the whole room a. With N rooms, N addresses are returned.
And the client directly connects an external access address of a certain computer room A service after receiving the service list returned by the server.
Because different machine rooms carry out clustered deployment on the A service and provide the service externally also with a cluster access address, when the A service state is collected, the A service state cannot be directly inquired about the state of a certain application service node, but an Agent service node needs to carry out Agent collection on all the A service in the machine room and carry out data summarization on the collected application state data. And periodically pushed to a certain server side to control the dynamic load balancing service.
The server side controls the dynamic load balancing service to store a service list of the application service and corresponding state data. Because the Agent service is only pushed to a certain service end to control the dynamic load balancing service, the service list data and the state data of each service are inconsistent at the moment. It is necessary to perform consistent synchronization for all server side control dynamic load balancing services. The server side controls the dynamic load balancing service to carry out non-centralized design, and the condition that the dynamic load balancing service does not have single-point faults is guaranteed. The server side controls the dynamic load balancing service to adopt a centerless Gossip protocol to carry out data synchronization. And the server controls the state of the dynamic load balancing service data to be weakly consistent.
It is worth mentioning that the dynamic load balancing method based on server control of the present invention uses a centerless Gossip protocol for data synchronization. Among them, Gossip Protocol (Gossip Protocol) is also called Epidemic Protocol (Epidemic Protocol). The method is originally used for node synchronization data in a distributed database, and then widely used for database replication, information diffusion, cluster membership confirmation, fault detection and the like. In this embodiment of the present invention, the Gossip protocol execution process is:
the seed node periodically disseminates the message, wherein, in one embodiment, the period is defined as 1 second;
the infected node randomly selects N neighboring nodes to disseminate the message, where, in one embodiment, fan-out is set to 6, disseminating to a maximum of 6 nodes at a time;
the node only receives the message and does not feed back the result;
each time of message dissemination, selecting nodes which are not sent for dissemination;
the node that receives the message no longer disseminates to the sending node: a- > B, then B is not sent to A when B is disseminated.
Information propagation and flooding of the Goosip protocol typically needs to be initiated by the seed node. The whole propagation process may take a certain time, and since it cannot be guaranteed that all nodes receive messages at a certain time, it is a final consistency protocol since theoretically all nodes will eventually receive messages.
The Gossip protocol is a multi-master protocol, and all writes may be initiated by different nodes and synchronized to other copies. The network nodes formed in Gossip are all peer nodes and are unstructured networks.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are given by way of example only and are not limiting of the invention. The objects of the invention have been fully and effectively accomplished. The functional and structural principles of the present invention have been shown and described in the examples, and any variations or modifications of the embodiments of the present invention may be made without departing from the principles.
Claims (10)
1. A dynamic load balancing method based on server side control is characterized by comprising the following steps:
the client declares the required service type, and applies for acquiring a connection address corresponding to the service from the load balancing server;
after receiving the request of the client, the load balancing server executes weight calculation;
the load balancing server performs weight calculation according to the service list sequence, performs sorting according to the weight value after the calculation is completed, and returns the sorted result to the client;
after receiving the service list, the client selects the service with the largest weight value to execute connection;
and
when the client detects that the connected application service is interrupted and cannot provide the service, the client tries to reconnect to the service with the second largest weight value according to the service list, wherein when all the services cannot be connected, the client acquires a latest service list from the load balancing server again.
2. The dynamic load balancing method based on server-side control as claimed in claim 1, wherein the dynamic load balancing method based on server-side control further comprises the steps of: the parameters of the plan transmitted by the client are the IP address of the client, the service type of the client, the service data of the address of the user, the service data of the area of the user and the service data of the organizational structure.
3. The dynamic load balancing method based on server side control as claimed in claim 2, wherein the dynamic load balancing method based on server side control further comprises the steps of: and performing the calculation of the weight value according to the service state, the service load rate, the network flow and the intervention factors of whether the IP address of the client and the application service are near.
4. The dynamic load balancing method based on server side control as claimed in claim 2, wherein the dynamic load balancing method based on server side control further comprises the steps of: the weight value for each service is calculated according to the following formula: the weight value of each service is service state x { (1-service load rate) × service pressure + (network traffic upper limit-current network traffic) × network traffic + intervention factor of whether the IP address is close × client IP and whether the server is close + server intervention weight }.
5. The dynamic load balancing method based on server side control as claimed in claim 2, wherein the dynamic load balancing method based on server side control further comprises the steps of: and the client performs additional weight calculation on the returned service list, initiates a connection test on the returned IP address, acquires response time, weights the response time, adds the response time to a weight value returned by the server, and selects the service with the largest weight value to perform connection.
6. The method for dynamic load balancing based on server side control as claimed in any one of claims 1 to 5, wherein the service list of the server side control dynamic load balancing service manager is a service list of a single host node.
7. The dynamic load balancing method based on server side control as claimed in any one of claims 1 to 5, wherein the service list of the server side control dynamic load balancing service manager is a service list that is externally accessible to all the machine rooms to which the client is connected through the public network DNS service.
8. The dynamic load balancing method based on server-side control as claimed in claim 7, wherein the dynamic load balancing method based on server-side control includes the steps of:
the client side adopts public network DNS service domain name resolution service, a first request for acquiring a service address of a user is transferred to one of the machine rooms, the request passes through a firewall of the machine room and is loaded to the server side control dynamic load balancing server by the load balancing server, and the server side control dynamic load balancing server performs weight calculation according to client side parameters and then returns an external access service list corresponding to the application of the service;
the client side obtains the sorted service list returned from the server side and then connects the external access address of the corresponding machine room service;
the method comprises the steps that an Agent service node is arranged, Agent collection is carried out on all services in a machine room, data summarization is carried out on collected application state data, and the data summarization is periodically pushed to one server side control dynamic load balancing server;
and
and performing consistency synchronization on all server side control dynamic load balancing servers, setting the server side control dynamic load balancing servers to be in a non-centralized design, and performing data synchronization by adopting a non-centralized Gossip protocol through the server side control dynamic load balancing servers.
9. The dynamic load balancing method based on server side control as claimed in claim 8, wherein the Gossip protocol execution procedure includes the steps of:
the seed node periodically disseminates the message;
an infected node randomly selects a plurality of adjacent nodes to disseminate the message;
the node only receives the message and does not feed back the result;
each time of message dissemination, selecting nodes which have not been sent to perform dissemination;
and
the node that received the message is no longer broadcasting to the sending node.
10. The method for dynamic load balancing based on server side control according to claim 9, wherein the seed node spreads the message with a period of 1 second, wherein a maximum of 6 nodes are spread at a time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011178608.5A CN112543150B (en) | 2020-10-29 | 2020-10-29 | Dynamic load balancing method based on server control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011178608.5A CN112543150B (en) | 2020-10-29 | 2020-10-29 | Dynamic load balancing method based on server control |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112543150A true CN112543150A (en) | 2021-03-23 |
| CN112543150B CN112543150B (en) | 2022-11-04 |
Family
ID=75013613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011178608.5A Active CN112543150B (en) | 2020-10-29 | 2020-10-29 | Dynamic load balancing method based on server control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112543150B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114900524A (en) * | 2022-05-11 | 2022-08-12 | 福建科融世纪信息科技有限公司 | Load balancing and node delay reducing method for MQTT service |
| CN116800473A (en) * | 2023-05-10 | 2023-09-22 | 广州市玄武无线科技股份有限公司 | Method, device, storage medium and system for communication between client and cloud service |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1207668A2 (en) * | 2000-11-16 | 2002-05-22 | Microsoft Corporation | System and method for performing client-centric load balancing of multiple globally-dispersed servers |
| CN101207550A (en) * | 2007-03-16 | 2008-06-25 | 中国科学技术大学 | Load balancing system and method for multi business to implement load balancing |
| CN101534244A (en) * | 2009-02-09 | 2009-09-16 | 华为技术有限公司 | Method, device and system for load distribution |
| CN102457440A (en) * | 2012-01-13 | 2012-05-16 | 华为软件技术有限公司 | Method for realizing load balancing, DNS server, and Client |
| CN103442030A (en) * | 2013-07-31 | 2013-12-11 | 北京京东尚科信息技术有限公司 | Method and system for sending and processing service request messages and client-side device |
| CN105050139A (en) * | 2015-07-27 | 2015-11-11 | 中国科学院信息工程研究所 | Global load balancing-based service gateway selecting method and system |
| CN107241418A (en) * | 2017-06-13 | 2017-10-10 | 腾讯科技（深圳）有限公司 | A kind of load-balancing method, device, equipment and computer-readable recording medium |
| CN107579924A (en) * | 2017-09-29 | 2018-01-12 | 阿里巴巴集团控股有限公司 | A kind of flow allots method and apparatus |
| CN108199909A (en) * | 2018-03-30 | 2018-06-22 | 浙江网新恒天软件有限公司 | A kind of High Availabitity SiteServer LBS based on consistency Hash |
-
2020
- 2020-10-29 CN CN202011178608.5A patent/CN112543150B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1207668A2 (en) * | 2000-11-16 | 2002-05-22 | Microsoft Corporation | System and method for performing client-centric load balancing of multiple globally-dispersed servers |
| CN101207550A (en) * | 2007-03-16 | 2008-06-25 | 中国科学技术大学 | Load balancing system and method for multi business to implement load balancing |
| CN101534244A (en) * | 2009-02-09 | 2009-09-16 | 华为技术有限公司 | Method, device and system for load distribution |
| CN102457440A (en) * | 2012-01-13 | 2012-05-16 | 华为软件技术有限公司 | Method for realizing load balancing, DNS server, and Client |
| CN103442030A (en) * | 2013-07-31 | 2013-12-11 | 北京京东尚科信息技术有限公司 | Method and system for sending and processing service request messages and client-side device |
| CN105050139A (en) * | 2015-07-27 | 2015-11-11 | 中国科学院信息工程研究所 | Global load balancing-based service gateway selecting method and system |
| CN107241418A (en) * | 2017-06-13 | 2017-10-10 | 腾讯科技（深圳）有限公司 | A kind of load-balancing method, device, equipment and computer-readable recording medium |
| CN107579924A (en) * | 2017-09-29 | 2018-01-12 | 阿里巴巴集团控股有限公司 | A kind of flow allots method and apparatus |
| CN108199909A (en) * | 2018-03-30 | 2018-06-22 | 浙江网新恒天软件有限公司 | A kind of High Availabitity SiteServer LBS based on consistency Hash |
Non-Patent Citations (2)
| Title |
|---|
| MAURO FRANCESCHELLI: "Load Balancing over heterogeneous networks with gossip-based algorithms", 《2009 AMERICAN CONTROL CONFERENCE》 * |
| 李亚非: "高并发web服务器集群负载均衡器的设计与实现", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114900524A (en) * | 2022-05-11 | 2022-08-12 | 福建科融世纪信息科技有限公司 | Load balancing and node delay reducing method for MQTT service |
| CN116800473A (en) * | 2023-05-10 | 2023-09-22 | 广州市玄武无线科技股份有限公司 | Method, device, storage medium and system for communication between client and cloud service |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112543150B (en) | 2022-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11611592B1 (en) | Multiple-master DNS system | |
| CN109274707B (en) | Load scheduling method and device | |
| CN103581276B (en) | Cluster management device, system, service customer end and correlation method | |
| CN111615066B (en) | Distributed micro-service registration and calling method based on broadcast | |
| CN108712464A (en) | A kind of implementation method towards cluster micro services High Availabitity | |
| US7548945B2 (en) | System, network device, method, and computer program product for active load balancing using clustered nodes as authoritative domain name servers | |
| US6675199B1 (en) | Identification of active server cluster controller | |
| CN107547661B (en) | Container load balancing implementation method | |
| US20080183991A1 (en) | System and Method for Protecting Against Failure Through Geo-Redundancy in a SIP Server | |
| US7373394B1 (en) | Method and apparatus for multicast cloud with integrated multicast and unicast channel routing in a content distribution network | |
| CN107947960A (en) | The method for pushing and system of configuration information, the method for reseptance and system of configuration information | |
| US20130007253A1 (en) | Method, system and corresponding device for load balancing | |
| US20070088703A1 (en) | Peer-to-peer auction based data distribution | |
| WO2015101260A1 (en) | Method and system for processing instant communication service | |
| US20120166391A1 (en) | Method and System for Data Synchronization in Content Delivery Network | |
| CN112543150B (en) | Dynamic load balancing method based on server control | |
| US6763372B1 (en) | Load balancing of chat servers based on gradients | |
| WO2006040327A1 (en) | Method, system and program product for automated topology formation in dynamic distributed environments | |
| CN110086886B (en) | Dynamic session holding method and device | |
| US6675217B1 (en) | Recovery of cluster consistency following failover | |
| WO2021120633A1 (en) | Load balancing method and related device | |
| CN114036236A (en) | Multi-gateway cluster system | |
| CN113326100A (en) | Cluster management method, device and equipment and computer storage medium | |
| CN111193778B (en) | Method and device for balancing WEB service load | |
| WO2012000455A1 (en) | Client terminal and load balancing method |
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 |