CN103220354A - Method for achieving load balancing of server cluster - Google Patents
Method for achieving load balancing of server cluster Download PDFInfo
- Publication number
- CN103220354A CN103220354A CN2013101348370A CN201310134837A CN103220354A CN 103220354 A CN103220354 A CN 103220354A CN 2013101348370 A CN2013101348370 A CN 2013101348370A CN 201310134837 A CN201310134837 A CN 201310134837A CN 103220354 A CN103220354 A CN 103220354A
- Authority
- CN
- China
- Prior art keywords
- server
- load
- balanced
- node
- address
- 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.)
- Pending
Links
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a method for achieving load balancing of a server cluster. The method for achieving the load balancing of the server cluster includes the following steps that the client broadcasts address resolution protocol request to the server cluster, a load balancing server identifies the address resolution protocol request, and the load balancing server feeds back an physical address to the client when the load balancing server is matched with the address resolution protocol request; the client transmits a service request to the load balancing server according to the physical address of the load balancing server; the load balancing server dispatches the service request to a node server to be processed, wherein the node server is connected with the load balancing server and load value of the node server is the smallest; and after the node server processes the service request, the node server transmits an obtained data package to the client. The method for achieving the load balancing of the server cluster achieves effects of rational utilization of resources and system performance optimization of the server cluster.
Description
Technical field
The present invention relates to technical field of the computer network, relate in particular to a kind of method that realizes the server cluster load balancing.
Background technology
Cluster, English name are Cluster.In the communication network technology field, cluster is meant server cluster, and it connects together multiple servers to provide with a kind of service, makes in client, and the multiple servers in the cluster can be worked as a machine.Each station server in the server cluster is also referred to as node server.
Server cluster can improve the stability of system and the data-handling capacity and the service ability of network center.For example, thus server cluster can utilize multiple servers to carry out parallel computation obtains very high computational speed; Also can utilize a plurality of computers to backup, thereby avoid Single Point of Faliure.In present server cluster system, each node server often is decided by the load balance ability of this server cluster to the service quality of client.
At present along with the raising of the traffic carrying capacity of each Core server of computer network, the quick growth of visit capacity and data traffic, the requirement of its disposal ability and calculating strength also correspondingly increases, make single server apparatus can't bear at all, therefore, the load-balancing technique relevant for server cluster arises at the historic moment.
Load balancing (being called load balancing again), English name is Load Balance, its effect is load or task balance to be shared on a plurality of operating units carry out.In server cluster, load balancing is based upon on the active computer network configuration, a kind of effective method expansion servers bandwidth is provided and has increased throughput, improves speed of response of server, strengthen the computer network data disposal ability, improve the flexibility and the availability of computer network.
At present, be the resource rational utilization of realization server cluster and the purpose of system function optimization, prior art provides the technical solution of multiple realization server cluster load balancing.
Wherein, at present based on the realization of domain name system a kind of load-balancing method.Domain name system (Domain Name System, be called for short DNS) be a kernel service of internet, it is with domain name and the network address (Internet Protocol, abbreviation IP) distributed data base of mutual mapping, make the user make things convenient for access internet, and needn't remember the IP string that directly read by machine.In existing load-balancing method based on domain name system, resolve by the random domain name in the DNS service and to realize load balancing, in dns server, can be the same domain name of a plurality of different address configuration.For same domain name, different client computer can obtain different addresses, therefore also just visited the Web(network on the different addresses) server, thereby reach the purpose of load balancing but this method in order to guarantee upgrading in time of DNS data, usually the refresh time with DNS is provided with lessly, this will cause a large amount of additional networks flows, and the DNS data after the renewal can not come into force; And this method can't be learnt the difference between each node server, can not be the node server overabsorption request of better performances, can not recognize the current state of each node server.
A kind of reverse proxy load-balancing method also is provided in the prior art, it uses acting server request can be transmitted to cluster internal web server, acting server will be asked to be transmitted to equably on one of inner many Web servers, thereby the shortcoming that reaches the purpose reverse proxy load balancing of load balancing is at service request each time, acting server just must be opened two connections, and (one externally connects, one internally connects), when service request quantity is very big, the load value of acting server sharply increases, and acting server becomes the bottleneck of server cluster load balancing.
In addition, address transition also Network Based in the prior art (Network Address Translation is called for short NAT) technology is changed home address and external address, can visit external network so that possess the server of home address; And when the server access address conversion gateway in the external network, address conversion gateway can be mapped to its external address on the home address of an internal server, thereby the purpose that reaches load balancing is shared owing to bandwidth based on the load-balancing technique of NAT, usually there is bandwidth constraints in the central loading equalizer, also becomes the bottleneck of whole server cluster load balancing.As at 100MB(MByte, Mbytes) under the Fast Ethernet condition, the fastest bandwidth that can reach 80MB of this method; Yet in actual applications, this method has only the available bandwidth of 40MB to 60MB usually.
Summary of the invention
Technical problem to be solved by this invention is, a kind of method that realizes the server cluster load balancing is provided, and solves the bottleneck problem that load equalizer brought, and utilizes the purpose with performance optimization to realize the server cluster reasonable resources.
For solving above technical problem, the invention provides a kind of method that realizes the server cluster load balancing, comprising:
S1, the request of user end to server cluster broadcast address analysis protocol, described server cluster comprises at least one load-balanced server, described load-balanced server is connected with at least one node server;
Load-balanced server in S2, the described server cluster is discerned described arp request, and when described load-balanced server and described arp request were complementary, described load-balanced server fed back to described client with the physical address of described load-balanced server;
S3, described client are sent to described load-balanced server according to the physical address of described load-balanced server with service request;
The node server that S4, described load-balanced server are dispatched the load value minimum that connects to described load-balanced server with described service request is handled;
After S5, described node server are handled described service request, obtain packet, and described packet is sent to described client.
But in a kind of implementation, described step S2 specifically comprises:
Load-balanced server in S21, the described server cluster is resolved described arp request, obtains the network address in the described address resolution protocol;
S22, described load-balanced server compare the network address of the network address in the described address resolution protocol and described load-balanced server;
S23, when the network address in the described address resolution protocol is identical with the network address of described load-balanced server, described load-balanced server feeds back to described client with the physical address of described load-balanced server.
Further, described load-balanced server is provided with at least one scheduler, and with described scheduler network interface one to one;
Then described load-balanced server is connected with at least one node server, is specially:
Described scheduler connects with the corresponding one by one data of setting up of described network interface; Each described network interface is set up data with at least one node server respectively and is connected by connecting a switch.
Further, after described step S5, described method also comprises:
S6: the operating state of each described node server that described load-balanced server regularly detects described load-balanced server respectively and connected, and with the handled service request of the node server that breaks down, scheduling is given in the node server of the load value minimum that described load-balanced server connected and is handled.
A kind of method that realizes the server cluster load balancing provided by the invention has realized the resource rational utilization and the system function optimization of server cluster.Particularly, the present invention is by horizontal increase load-balanced server or vertically increase scheduler in the load-balanced server, has expanded the bandwidth of server cluster effectively and has increased the resource throughput of server cluster; Load value according to each server in the server cluster, the service request of client dispatched to the node server of load value minimum handle, and when a large amount of concurrent data service requests when this server cluster sends, load-balanced server can be dispensed to many node servers with this concurrent data service request and handle, every node server parallel running has improved the data-handling capacity of server cluster; Each node server directly is sent to client with result respectively after service request is handled, and need not through load-balanced server, thus the bottleneck problem effectively in the settlement server cluster.
Description of drawings
Fig. 1 is the method flow diagram of first embodiment of a kind of method that realizes the server cluster load balancing provided by the invention;
Fig. 2 is the server cluster syndeton schematic diagram that first embodiment of the invention provides;
Fig. 3 is the flow chart of steps of a kind of preferred implementation of step S2 in the first embodiment of the invention;
Fig. 4 is the server cluster syndeton schematic diagram that second embodiment of the invention provides;
Fig. 5 is the flow chart of steps of a kind of implementation of step S4 in the second embodiment of the invention;
Fig. 6 is the flow chart of steps of another implementation of step S4 in the second embodiment of the invention;
Fig. 7 is the method flow diagram of the 3rd embodiment of a kind of method that realizes the server cluster load balancing provided by the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described.
Referring to Fig. 1, be the method flow diagram of first embodiment of a kind of method that realizes the server cluster load balancing provided by the invention.
In first embodiment, described a kind of method of server cluster load balancing that realizes may further comprise the steps:
Step S1: the request of user end to server cluster broadcast address analysis protocol, described server cluster comprises at least one load-balanced server, described load-balanced server is connected with at least one node server.
Referring to Fig. 2, be a server cluster syndeton schematic diagram that provides of the embodiment of the invention.
In the present embodiment, client 100 is connected with many load-balanced servers, as load-balanced server 110, load-balanced server 120 etc.Wherein, load-balanced server 110 is connected with many node servers, as node server 111, and node server 112, node server 113 node servers such as grade.
In the present embodiment, each load-balanced server and the node server that connected thereof constitute server cluster.During concrete enforcement, can be by laterally increasing the quantity of load-balanced server, to improve the data volume bearing capacity and the bandwidth of server cluster.
In the present embodiment, client 100 is to the request of server cluster broadcast address analysis protocol.Address resolution protocol is also referred to as ARP(Address Resolution Protocol) agreement is a kind of ICP/IP protocol of obtaining physical address; And TCP/IP is writing a Chinese character in simplified form of Transmission Control Protocol/Internet Protocol, and Chinese translation is " transmission control protocol/internet interconnection protocol ", has another name called network communication protocol, is the basic protocol in internet.
Step S2: the load-balanced server in the described server cluster is discerned described arp request, and when described load-balanced server and described arp request were complementary, described load-balanced server fed back to described client 100 with the physical address of described load-balanced server.
Physical address also is a MAC Address, is Media Access Control(medium access control) write a Chinese character in simplified form, MAC Address is that the transmission sign of really relying during data is sent the data computing machine and received the address of data computing machine in the identification local area network (LAN).
In the present embodiment, client 100 needed to obtain earlier the pairing target MAC (Media Access Control) address of this service request before sending service request.Therefore, during each load-balanced server broadcast arp request in server cluster of client 100, every load-balanced server in the cluster all receives this ARP request, just this ARP is asked to respond but have only with the load-balanced server of this ARP coupling, promptly have only with the load-balanced server of this ARP request coupling himself physical address is sent to client 100, so that client 100 obtains the destination address that service request will send.For example, after load-balanced server 110 receives described ARP request, the back is resolved in this ARP request find that itself and self mate, then load-balanced server 110 feeds back to client 100 with the MAC Address of himself.
Referring to Fig. 3, be the flow chart of steps of a kind of preferred implementation of the step S2 in the first embodiment of the invention.
As preferred implementation, in embodiments of the present invention, described step S2 specifically comprises:
Step S21: the load-balanced server in the described server cluster is resolved described arp request, obtains the network address in the described address resolution protocol.Particularly, the network address is also referred to as IP(Internet Protocol) address is to communicate the basic agreement that designs for computer network interconnects.The present IPV4(Internet Protocol version 4 that uses, internet protocol version 4) IP address size is 32, is divided into 4 sections, 8 every section, numeral decimally, every piece of digital scope is 0～255, separate with fullstop between section and the section, for example 159.226.1.1.
During concrete enforcement, client 100 is when the broadcast arp request, and this request carries the IP address of destination node server; In the server cluster each load-balanced server is resolved it when receiving this ARP request, the IP address that obtains among the ARP to be indicated.
Step S22: described load-balanced server compares the network address of the network address in the described address resolution protocol and described load-balanced server.The IP address is as the binary address sign of each computer in the computer network, and each station server in the server cluster also has corresponding IP address.When the request of client broadcast arp, the equally loaded server of each in the server cluster all asks resulting IP address to compare with parsing ARP its own IP address.
Step S23: when the network address in the described address resolution protocol was identical with the network address of described load-balanced server, described load-balanced server fed back to described client with the physical address of described load-balanced server.Particularly, after the comparison by execution in step S22, a certain equalization server in the server cluster detects IP address entrained in its own IP address and the ARP request when identical, and promptly this equalization server and ARP ask to be complementary, and send response to client.
In the present embodiment, the purpose of described step S2 is to obtain the needed physical address of client, so that in next procedure, client can be sent real data service request to the server that physical address indicated of its acquisition.
Step S3: described client is sent to described load-balanced server according to the physical address of described load-balanced server with service request.For example, if load-balanced server 110 is complementary with the ARP request that client is sent, and its MAC Address is " 00-23-5A-15-99-4E ", client 100 is set at " 00-23-5A-15-99-4E " target MAC (Media Access Control) address of this service request after the response of receiving load-balanced server 110.
In the present embodiment, client 100 stores the MAC Address of its acquisition.During concrete enforcement, when the destination address that sends to when the service request actual needs was identical with above-mentioned MAC Address, client 100 no longer needed just can know corresponding M AC address, the raising data processing efficiency by sending the ARP request.
Step S4: the node server that described load-balanced server is dispatched the load value minimum that connects to described load-balanced server with described service request is handled.During concrete enforcement, when load-balanced server carries out numerical quantization with the load information of each node server that it connected, the loading condition of each node server of disposable load value representation.Particularly, when client 100 each a certain load-balanced servers in server cluster sent service request, this load-balanced server all can be dispatched service request the node server of the load value minimum that connects to described load-balanced server and handle.
Step S5: after described node server is handled described service request, obtain packet, and described packet is sent to described client.This node server is as the execution destination of the service request that client sent, and after this service request is handled result directly sent to client.
With server cluster structure chart shown in Figure 2 is example.When the load value of node server 111 hour, equalization server 110 is dispatched the service request of client 100 to node server 111 and is handled; After 111 pairs of these service request of node server are handled, feed back to client 100 after directly one or more results (packet) of this service request being gathered, need not result to be fed back to client 100 through load-balanced server 110.Reduce load-balanced server to the restriction of whole server cluster with improved the bandwidth of load-balanced server, thereby improved the data-handling efficiency of whole server cluster.
Further, in the server cluster that the embodiment of the invention provided, each load-balanced server is provided with at least one scheduler, and with described scheduler network interface one to one.
Referring to Fig. 4, be the server cluster syndeton schematic diagram that second embodiment of the invention provides.
The present invention is based on server cluster johning knot composition shown in Figure 4, a kind of second embodiment that realizes the method for server cluster load balancing is provided.
In a second embodiment, the implementation procedure of step S1 ~ step S3 is consistent with related content described in the basic principle and first embodiment.
In the present embodiment, when specifically implementing, each load-balanced server is provided with at least one scheduler, and with described scheduler network interface one to one, then described load-balanced server is connected with at least one node server, is specially:
Described scheduler connects with the corresponding one by one data of setting up of described network interface; Each described network interface is set up data with at least one node server respectively and is connected by connecting a switch.
As shown in Figure 4, client 200 is connected with load-balanced server 300, and load-balanced server 300 is built-in with a plurality of schedulers such as scheduler 301, scheduler 302.During concrete enforcement, load-balanced server 300 provides scheduler by the mode of virtual machine.Wherein, the scheduler 301 in the load-balanced server 300 is connected with switch 401 by network interface; Switch 401 is connected with many node servers by network interface again, as node server 501, node server 502 etc.In like manner, the scheduler 302 in the load-balanced server 300 is connected with switch 402 by network interface; Switch 402 is connected respectively with many node servers such as node server 601, node servers 602 again.
Particularly, the quantity of the built-in scheduler device of load-balanced server 300 (quantity of virtual machine) is decided by the quantity of the network adapter (being network interface card) on the load-balanced server 300.In the present embodiment, can improve the bandwidth and the data-handling capacity of load-balanced server by the quantity that increases scheduler according to the practical application needs.
Further, in a second embodiment, described load-balanced server 300 also is provided with central processing unit 310.
In a kind of method that realizes the server cluster load balancing that second embodiment is provided, on the basis of first embodiment, further, described step S4 also comprises step S41 ~ step S44 when specific implementation.
Referring to Fig. 5, be the flow chart of steps of a kind of implementation of step S4 in the second embodiment of the invention.
Step S41: each described scheduler is regularly gathered the load value of the described node server that described network interface connected respectively by pairing network interface.During concrete enforcement, in the server cluster each load-balanced server, by central processing unit each built-in in load-balanced server scheduler is carried out Task Distribution, make each scheduler regularly collect and write down the load value of its each node server that connects, execution in step S42 then respectively.
Step S42: each described scheduler sends to described central processing unit 310 with the load value of described node server.
Therefore, the any load-balanced server that is complementary with the ARP of client request is when receiving the service request of client, all can in time know the node server of the load value minimum that it connected, thereby the service request that reduces mapping address or forwarding is brought extra propagation delay time.
Step S43: described central processing unit 310 gathers the load value of described node server and sorts, and obtains the physical address of the node server of load value minimum.Particularly, after central processing unit 310 obtains its load value by many node servers that respective switch connects, by gathering and sort to each load value, the location obtains the node server and the physical address thereof of load value minimum, carries out the node server of actual treatment to find the service request that client 200 is sent.After finding the target MAC (Media Access Control) address of the node server of carrying out actual treatment, execution in step S44.
Step S44: described central processing unit is according to the physical address of the node server of described load value minimum, described client's service request dispatched to the node server of described load value minimum handle.
During concrete enforcement, central processing unit 310 is a foundation with the physical address of the node server of load value minimum, and the node server that will be transmitted to its real-time load value minimum that connects by the service request (packet) that client 200 sends over is handled.Particularly, the node server of load value minimum directly sends to client 200 after one or more results of this service request are gathered.
For example, client 200 by the broadcast arp request after, known that load-balanced server 300 and current ARP request are complementary, and in many node servers that load-balanced server 300 is connected, the load value minimum of node server 502, then central processing unit 310 sends to switch 401 with the service request (packet) that client 200 is sent; Switch 401 is distributed to this service request in the node server 502 and is handled; Final result feeds back to client 200.
Need to prove, in inventive embodiments, when client when cluster server sends " the short connection " service request, when this service request disposed, it was connected the load-balanced server automatic disconnection with the node corresponding data in server; When client when cluster server sends " the long connection " service request, when this service request disposes, load-balanced server can't automatic disconnection its be connected with the node corresponding data in server, also be that the data link that control that load-balanced server need be accepted relevant signaling just can disconnect its foundation connects.
In computer networking technology, " the short connection " is meant when communicating pair has data interaction, just sets up a connection; After data are sent completely, then disconnect this and connect, the transmission of a business is only finished in promptly each connection.So-called " the long connection ", be meant in a connection to send a plurality of packets continuously; During connecting maintenance,, need both sides to send out the link detecting bag if there is not packet to send.
Wherein, the long load balancing that connects can well realize data distribution, and the processing flow of each node server is more or less the same, and the signalling analysis that its comparatively classical application scenario is a multiple access point is handled.Long connection characteristics is that in a single day it just connect not can automatic disconnection, and therefore, when the load value of a node server surpassed to certain value, the treatment effeciency of this node server can reduce greatly.
Therefore, in the present embodiment, further, need utilize scheduler, according to the load value of node server, dynamically each bar data link is carried out optimal selection, rationally to utilize the resource of each node server, avoid occurring the situation of the too high or too low load of some node servers, reach resource rational utilization maximization effect.
Referring to Fig. 6, be the flow chart of steps of another implementation of step S4 in the second embodiment of the invention.
Wherein, in this implementation, the implementation procedure of step S41 ~ step S44 and basic principle are consistent with method flow diagram shown in Figure 5.
In the present embodiment, described load-balanced server is set load threshold to the described node server that it connected.Present embodiment is by for each node server is provided with load threshold, with the situation of the too high or too low load of some node servers avoiding causing in the long connection procedure.
Particularly, then after described step S44, described method also comprises:
Step S45: described scheduler compares the load value and the described load threshold of the described node server that timing acquiring obtains.
Step S46: when the load value of described node server during greater than described load threshold, described scheduler disconnects described scheduler and is connected with the data of described node server.
Need to prove, when the scheduler in a certain load-balanced server in the server cluster disconnects it and is connected with the data of a certain node server, client can detect the off-state that this length connects, and will grow untreated service request in connecting again as new service request, dispatch to the node server of load value minimum by a certain load-balanced server in the server cluster and handle.
Referring to Fig. 7, be the method flow diagram of the 3rd embodiment of a kind of method that realizes the server cluster load balancing provided by the present invention.
Further, on the basis of the first embodiment of the invention or second embodiment, in the 3rd embodiment provided by the invention, after described step S5, described method also comprises:
Step S6: the operating state of each described node server that described load-balanced server regularly detects described load-balanced server respectively and connected, and with the handled service request of the node server that breaks down, scheduling is given in the node server of the load value minimum that described load-balanced server connected and is handled.
Present embodiment makes that by increasing step S6 load-balanced server all can provide related service constantly to client when any station server in the server cluster breaks down.
In sum, a kind of method that realizes the server cluster load balancing that the embodiment of the invention provided has realized the resource rational utilization and the system function optimization of server cluster.Particularly, the server cluster among the present invention has improved the bandwidth and the resource throughput of server cluster effectively by increasing load-balanced server; Load-balanced server is according to the load value of node server, dynamically each service conditions or data link connection are carried out optimal selection, rationally utilize the resource of each node server and the service request of reasonable distribution client, avoided a certain node server load too high or low excessively.Each node server directly is sent to client with result respectively after service request is handled, and need not delivery through load-balanced server, thereby has solved the bottleneck problem of the load-balanced server in the server cluster.
The above is a preferred implementation of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the principle of the invention; can also make some improvements and modifications, these improvements and modifications also are considered as protection scope of the present invention.
Claims (6)
1. a method that realizes the server cluster load balancing is characterized in that, comprising:
S1, the request of user end to server cluster broadcast address analysis protocol, described server cluster comprises at least one load-balanced server, described load-balanced server is connected with at least one node server;
Load-balanced server in S2, the described server cluster is discerned described arp request, and when described load-balanced server and described arp request were complementary, described load-balanced server fed back to described client with the physical address of described load-balanced server;
S3, described client are sent to described load-balanced server according to the physical address of described load-balanced server with service request;
The node server that S4, described load-balanced server are dispatched the load value minimum that connects to described load-balanced server with described service request is handled;
After S5, described node server are handled described service request, obtain packet, and described packet is sent to described client.
2. a kind of method that realizes the server cluster load balancing as claimed in claim 1 is characterized in that described step S2 specifically comprises:
Load-balanced server in S21, the described server cluster is resolved described arp request, obtains the network address in the described address resolution protocol;
S22, described load-balanced server compare the network address of the network address in the described address resolution protocol and described load-balanced server;
S23, when the network address in the described address resolution protocol is identical with the network address of described load-balanced server, described load-balanced server feeds back to described client with the physical address of described load-balanced server.
3. a kind of method that realizes the server cluster load balancing as claimed in claim 1 or 2 is characterized in that described load-balanced server is provided with at least one scheduler, and with described scheduler network interface one to one;
Then described load-balanced server is connected with at least one node server, is specially:
Described scheduler connects with the corresponding one by one data of setting up of described network interface; Each described network interface is set up data with at least one node server respectively and is connected by connecting a switch.
4. a kind of method that realizes the server cluster load balancing as claimed in claim 3 is characterized in that described load-balanced server also is provided with central processing unit, and then described step S4 specifically comprises:
S41, each described scheduler are regularly gathered the load value of the described node server that described network interface connected respectively by pairing network interface;
S42, each described scheduler send to described central processing unit with the load value of described node server;
S43, described central processing unit gather the load value of described node server and sort, and obtain the physical address of the node server of load value minimum;
S44, described central processing unit be according to the physical address of the node server of described load value minimum, described client's service request dispatched to the node server of described load value minimum handle.
5. a kind of method that realizes the server cluster load balancing as claimed in claim 4 is characterized in that, described load-balanced server is set load threshold to the described node server that it connected;
Then after described step S44, described method also comprises:
S45, described scheduler compare the load value and the described load threshold of the described node server that timing acquiring obtains;
S46, when the load value of described node server during greater than described load threshold, described scheduler disconnects described scheduler and is connected with the data of described node server.
6. a kind of method that realizes the server cluster load balancing as claimed in claim 1 or 2 is characterized in that, after described step S5, described method also comprises:
The operating state of each described node server that S6, described load-balanced server regularly detect described load-balanced server respectively and connected, and with the handled service request of the node server that breaks down, scheduling is given in the node server of the load value minimum that described load-balanced server connected and is handled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101348370A CN103220354A (en) | 2013-04-18 | 2013-04-18 | Method for achieving load balancing of server cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101348370A CN103220354A (en) | 2013-04-18 | 2013-04-18 | Method for achieving load balancing of server cluster |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103220354A true CN103220354A (en) | 2013-07-24 |
Family
ID=48817805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013101348370A Pending CN103220354A (en) | 2013-04-18 | 2013-04-18 | Method for achieving load balancing of server cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103220354A (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104079497A (en) * | 2014-07-21 | 2014-10-01 | 北京信诺瑞得软件系统有限公司 | High-availability loading balancing equipment and method under transparent network bridge mode |
| CN104683253A (en) * | 2013-11-27 | 2015-06-03 | 北京大唐高鸿数据网络技术有限公司 | Dynamic load balancing method for unified communication system |
| CN105376317A (en) * | 2015-11-19 | 2016-03-02 | 网宿科技股份有限公司 | Load balancing control method and load balancing control device |
| CN105450774A (en) * | 2015-12-28 | 2016-03-30 | 曙光信息产业(北京)有限公司 | Load balancing method and load balancing device for DNS |
| CN106034040A (en) * | 2015-03-13 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Scanning node control method, scanning node control device and scanning node control system |
| CN106254464A (en) * | 2016-08-07 | 2016-12-21 | 深圳市小马立行科技有限公司 | A kind of vehicle intelligent terminal and network communication method thereof |
| CN106326252A (en) * | 2015-06-24 | 2017-01-11 | 中兴通讯股份有限公司 | Data processing method and apparatus for database |
| CN106375395A (en) * | 2016-08-30 | 2017-02-01 | 厦门中学西渐信息科技有限公司 | Load balancing method and system for node servers |
| CN106506701A (en) * | 2016-12-28 | 2017-03-15 | 北京奇艺世纪科技有限公司 | A kind of server load balancing method and load equalizer |
| WO2017114017A1 (en) * | 2015-12-30 | 2017-07-06 | 华为技术有限公司 | Computer device, system and method for implementing load balancing |
| WO2017181890A1 (en) * | 2016-04-19 | 2017-10-26 | 中国银联股份有限公司 | Data processing system and method based on server cluster |
| CN107342929A (en) * | 2016-08-10 | 2017-11-10 | 杭州朗和科技有限公司 | A kind of sending method of new message notification, apparatus and system |
| CN107395379A (en) * | 2016-05-16 | 2017-11-24 | 北京京东尚科信息技术有限公司 | A kind of cluster cruising inspection system and method |
| CN107680374A (en) * | 2017-09-29 | 2018-02-09 | 南威软件股份有限公司 | A kind of intelligent acquisition scheduling system for crossing car data |
| CN107819825A (en) * | 2017-10-11 | 2018-03-20 | 深圳市买买提乐购金融服务有限公司 | A kind of service scheduling method, device and electronic equipment |
| CN108055338A (en) * | 2017-12-22 | 2018-05-18 | 创新科存储技术有限公司 | A kind of ISCSI accesses load-balancing method |
| CN108471387A (en) * | 2018-03-27 | 2018-08-31 | 中国农业银行股份有限公司 | A kind of daily record flow decentralized control method and system |
| CN108737527A (en) * | 2018-05-11 | 2018-11-02 | 重庆工商职业学院 | One kind being suitable for platform large-scale consumer access method and system |
| CN108848141A (en) * | 2018-05-31 | 2018-11-20 | 郑州云海信息技术有限公司 | A kind of response method of server data access and associated method and relevant apparatus |
| CN108881368A (en) * | 2018-04-22 | 2018-11-23 | 平安科技（深圳）有限公司 | High concurrent service request processing method, device, computer equipment and storage medium |
| CN109698796A (en) * | 2019-03-07 | 2019-04-30 | 江苏省人民医院 | A kind of high performance network SiteServer LBS and its implementation |
| CN110062032A (en) * | 2019-04-01 | 2019-07-26 | 北京航天发射技术研究所 | A kind of computer network clustered control platform application reconfiguration system |
| CN110099115A (en) * | 2019-04-30 | 2019-08-06 | 湖南麒麟信安科技有限公司 | A kind of load-balancing method and system of transparent scheduling forwarding |
| CN111078379A (en) * | 2019-12-06 | 2020-04-28 | 中至数据集团股份有限公司 | Task scheduling method, system, mobile terminal and storage medium |
| CN111343254A (en) * | 2020-02-17 | 2020-06-26 | 天津卓朗科技发展有限公司 | Client connection method and device and electronic equipment |
| CN111556125A (en) * | 2020-04-24 | 2020-08-18 | 北京奇艺世纪科技有限公司 | Access request distribution method, load balancing equipment and electronic equipment |
| CN111885105A (en) * | 2020-06-16 | 2020-11-03 | 广州三七互娱科技有限公司 | Task execution method, device, system, computer equipment and storage medium |
| CN113312151A (en) * | 2021-06-23 | 2021-08-27 | 哈尔滨工程大学 | Load balancing method of IPSecVPN cluster |
| CN113810304A (en) * | 2021-09-30 | 2021-12-17 | 深圳前海微众银行股份有限公司 | Load balancing method, device, equipment and computer storage medium |
| CN115225608A (en) * | 2022-07-22 | 2022-10-21 | 济南浪潮数据技术有限公司 | Load balancing method, device, equipment and medium for DNS domain name resolution |
| CN115225733A (en) * | 2022-02-22 | 2022-10-21 | 北京邮电大学 | Identification analysis method and device based on direct routing and dynamic quantitative analysis load |
| CN116112493A (en) * | 2023-02-09 | 2023-05-12 | 网易（杭州）网络有限公司 | Communication method, device, electronic equipment and storage medium |
| WO2023151264A1 (en) * | 2022-02-10 | 2023-08-17 | 华为云计算技术有限公司 | Load balancing method and apparatus, node, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101102288A (en) * | 2006-07-06 | 2008-01-09 | 阿里巴巴公司 | A method and system for realizing large-scale instant message |
| CN101242422A (en) * | 2007-02-06 | 2008-08-13 | 中国电信股份有限公司 | Content distribution network system and method applicable to multi-service fusion |
| CN101252591A (en) * | 2008-04-03 | 2008-08-27 | 中国科学技术大学 | Apparatus and method for realizing uplink and downlink data separation |
| CN102025630A (en) * | 2010-12-14 | 2011-04-20 | 成都市华为赛门铁克科技有限公司 | Load balancing method and load balancing system |
| CN102143046A (en) * | 2010-08-25 | 2011-08-03 | 华为技术有限公司 | Load balancing method, equipment and system |
| CN102752188A (en) * | 2011-04-21 | 2012-10-24 | 北京邮电大学 | Transmission control protocol connection migratory method and system |
-
2013
- 2013-04-18 CN CN2013101348370A patent/CN103220354A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101102288A (en) * | 2006-07-06 | 2008-01-09 | 阿里巴巴公司 | A method and system for realizing large-scale instant message |
| CN101242422A (en) * | 2007-02-06 | 2008-08-13 | 中国电信股份有限公司 | Content distribution network system and method applicable to multi-service fusion |
| CN101252591A (en) * | 2008-04-03 | 2008-08-27 | 中国科学技术大学 | Apparatus and method for realizing uplink and downlink data separation |
| CN102143046A (en) * | 2010-08-25 | 2011-08-03 | 华为技术有限公司 | Load balancing method, equipment and system |
| CN102025630A (en) * | 2010-12-14 | 2011-04-20 | 成都市华为赛门铁克科技有限公司 | Load balancing method and load balancing system |
| CN102752188A (en) * | 2011-04-21 | 2012-10-24 | 北京邮电大学 | Transmission control protocol connection migratory method and system |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104683253A (en) * | 2013-11-27 | 2015-06-03 | 北京大唐高鸿数据网络技术有限公司 | Dynamic load balancing method for unified communication system |
| CN104079497A (en) * | 2014-07-21 | 2014-10-01 | 北京信诺瑞得软件系统有限公司 | High-availability loading balancing equipment and method under transparent network bridge mode |
| CN104079497B (en) * | 2014-07-21 | 2017-03-22 | 北京信诺瑞得软件系统有限公司 | High-availability loading balancing equipment and method under transparent network bridge mode |
| CN106034040B (en) * | 2015-03-13 | 2019-07-02 | 阿里巴巴集团控股有限公司 | The control method of scan node, apparatus and system |
| CN106034040A (en) * | 2015-03-13 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Scanning node control method, scanning node control device and scanning node control system |
| CN106326252A (en) * | 2015-06-24 | 2017-01-11 | 中兴通讯股份有限公司 | Data processing method and apparatus for database |
| CN106326252B (en) * | 2015-06-24 | 2020-05-22 | 中兴通讯股份有限公司 | Data processing method and device for database |
| CN105376317A (en) * | 2015-11-19 | 2016-03-02 | 网宿科技股份有限公司 | Load balancing control method and load balancing control device |
| CN105450774A (en) * | 2015-12-28 | 2016-03-30 | 曙光信息产业(北京)有限公司 | Load balancing method and load balancing device for DNS |
| US10171567B2 (en) | 2015-12-30 | 2019-01-01 | Huawei Technologies Co., Ltd. | Load balancing computer device, system, and method |
| WO2017114017A1 (en) * | 2015-12-30 | 2017-07-06 | 华为技术有限公司 | Computer device, system and method for implementing load balancing |
| WO2017181890A1 (en) * | 2016-04-19 | 2017-10-26 | 中国银联股份有限公司 | Data processing system and method based on server cluster |
| CN107395379A (en) * | 2016-05-16 | 2017-11-24 | 北京京东尚科信息技术有限公司 | A kind of cluster cruising inspection system and method |
| CN106254464A (en) * | 2016-08-07 | 2016-12-21 | 深圳市小马立行科技有限公司 | A kind of vehicle intelligent terminal and network communication method thereof |
| CN107342929B (en) * | 2016-08-10 | 2020-07-03 | 杭州朗和科技有限公司 | Method, device and system for sending new message notification |
| CN107342929A (en) * | 2016-08-10 | 2017-11-10 | 杭州朗和科技有限公司 | A kind of sending method of new message notification, apparatus and system |
| CN106375395A (en) * | 2016-08-30 | 2017-02-01 | 厦门中学西渐信息科技有限公司 | Load balancing method and system for node servers |
| CN106375395B (en) * | 2016-08-30 | 2019-06-11 | 厦门中学西渐信息科技有限公司 | The load-balancing method and system of node server |
| CN106506701A (en) * | 2016-12-28 | 2017-03-15 | 北京奇艺世纪科技有限公司 | A kind of server load balancing method and load equalizer |
| CN107680374A (en) * | 2017-09-29 | 2018-02-09 | 南威软件股份有限公司 | A kind of intelligent acquisition scheduling system for crossing car data |
| CN107819825A (en) * | 2017-10-11 | 2018-03-20 | 深圳市买买提乐购金融服务有限公司 | A kind of service scheduling method, device and electronic equipment |
| CN108055338A (en) * | 2017-12-22 | 2018-05-18 | 创新科存储技术有限公司 | A kind of ISCSI accesses load-balancing method |
| CN108471387A (en) * | 2018-03-27 | 2018-08-31 | 中国农业银行股份有限公司 | A kind of daily record flow decentralized control method and system |
| CN108471387B (en) * | 2018-03-27 | 2022-10-21 | 中国农业银行股份有限公司 | Log flow decentralized control method and system |
| CN108881368A (en) * | 2018-04-22 | 2018-11-23 | 平安科技（深圳）有限公司 | High concurrent service request processing method, device, computer equipment and storage medium |
| WO2019205406A1 (en) * | 2018-04-22 | 2019-10-31 | 平安科技（深圳）有限公司 | Highly concurrent service request processing method and apparatus, and computer device and storage medium |
| CN108737527A (en) * | 2018-05-11 | 2018-11-02 | 重庆工商职业学院 | One kind being suitable for platform large-scale consumer access method and system |
| CN108737527B (en) * | 2018-05-11 | 2021-07-09 | 重庆工商职业学院 | Large-scale user access method and system suitable for platform |
| CN108848141A (en) * | 2018-05-31 | 2018-11-20 | 郑州云海信息技术有限公司 | A kind of response method of server data access and associated method and relevant apparatus |
| CN109698796A (en) * | 2019-03-07 | 2019-04-30 | 江苏省人民医院 | A kind of high performance network SiteServer LBS and its implementation |
| CN110062032A (en) * | 2019-04-01 | 2019-07-26 | 北京航天发射技术研究所 | A kind of computer network clustered control platform application reconfiguration system |
| CN110099115A (en) * | 2019-04-30 | 2019-08-06 | 湖南麒麟信安科技有限公司 | A kind of load-balancing method and system of transparent scheduling forwarding |
| CN111078379A (en) * | 2019-12-06 | 2020-04-28 | 中至数据集团股份有限公司 | Task scheduling method, system, mobile terminal and storage medium |
| CN111078379B (en) * | 2019-12-06 | 2024-01-09 | 中至数据集团股份有限公司 | Task scheduling method, system, mobile terminal and storage medium |
| CN111343254A (en) * | 2020-02-17 | 2020-06-26 | 天津卓朗科技发展有限公司 | Client connection method and device and electronic equipment |
| CN111343254B (en) * | 2020-02-17 | 2022-11-11 | 天津卓朗科技发展有限公司 | Client connection method and device and electronic equipment |
| CN111556125B (en) * | 2020-04-24 | 2022-05-17 | 北京奇艺世纪科技有限公司 | Access request distribution method, load balancing equipment and electronic equipment |
| CN111556125A (en) * | 2020-04-24 | 2020-08-18 | 北京奇艺世纪科技有限公司 | Access request distribution method, load balancing equipment and electronic equipment |
| CN111885105A (en) * | 2020-06-16 | 2020-11-03 | 广州三七互娱科技有限公司 | Task execution method, device, system, computer equipment and storage medium |
| CN113312151A (en) * | 2021-06-23 | 2021-08-27 | 哈尔滨工程大学 | Load balancing method of IPSecVPN cluster |
| CN113312151B (en) * | 2021-06-23 | 2024-07-05 | 哈尔滨工程大学 | Load balancing method of IPSecVPN cluster |
| CN113810304A (en) * | 2021-09-30 | 2021-12-17 | 深圳前海微众银行股份有限公司 | Load balancing method, device, equipment and computer storage medium |
| WO2023151264A1 (en) * | 2022-02-10 | 2023-08-17 | 华为云计算技术有限公司 | Load balancing method and apparatus, node, and storage medium |
| CN115225733A (en) * | 2022-02-22 | 2022-10-21 | 北京邮电大学 | Identification analysis method and device based on direct routing and dynamic quantitative analysis load |
| CN115225733B (en) * | 2022-02-22 | 2024-04-05 | 北京邮电大学 | Identification analysis method and device based on direct routing and dynamic quantization analysis load |
| CN115225608A (en) * | 2022-07-22 | 2022-10-21 | 济南浪潮数据技术有限公司 | Load balancing method, device, equipment and medium for DNS domain name resolution |
| CN116112493A (en) * | 2023-02-09 | 2023-05-12 | 网易（杭州）网络有限公司 | Communication method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103220354A (en) | Method for achieving load balancing of server cluster | |
| CN111345012B (en) | System and method for DNS resolution using link-level capacity of destination system | |
| US11522734B2 (en) | Method for controlling a remote service access path and relevant device | |
| EP3528440B1 (en) | Path selection method and system, network acceleration node, and network acceleration system | |
| JP4529974B2 (en) | Server load balancing system, server load balancing device, content management device, and server load balancing program | |
| CN102075445B (en) | Load balancing method and device | |
| CN101616079B (en) | NAT outlet link load balancing method and device of DNS request message | |
| CN111464592A (en) | Load balancing method, device, equipment and storage medium based on microservice | |
| CN109547517B (en) | Method and device for scheduling bandwidth resources | |
| US7292571B2 (en) | Load balancing with direct terminal response | |
| CN109040243B (en) | Message processing method and device | |
| CN102480469B (en) | Based on the method for the load dispatch of balancing energy and device in a kind of SIP service cluster | |
| US8130755B2 (en) | Load balancing with direct terminal response | |
| JPH11143804A (en) | Network load balancing for multicomputer server | |
| JP4041038B2 (en) | Higher layer processing method and system | |
| RU2010146258A (en) | METHOD, DEVICE AND SYSTEM FOR DISTRIBUTING MESSAGES | |
| CN101355521B (en) | Control method for equalizing load, communication apparatus and communication system | |
| Zhang et al. | Creating Linux virtual servers | |
| CN103368872A (en) | Data packet forwarding system and method | |
| CN102916898A (en) | Application keeping method and device of multilink egress | |
| CN109788062A (en) | Transmission system server load balancing method | |
| CN103414800A (en) | Allocation and selection method and system of distributed relay servers in NAT traversal | |
| CN111600929B (en) | Transmission line detection method, routing strategy generation method and proxy server | |
| CN105577546A (en) | Method for actively requesting access based on QoS | |
| CN116743836A (en) | Long connection communication link establishment method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130724 |