CN106506701A - A kind of server load balancing method and load equalizer - Google Patents
A kind of server load balancing method and load equalizer Download PDFInfo
- Publication number
- CN106506701A CN106506701A CN201611235980.9A CN201611235980A CN106506701A CN 106506701 A CN106506701 A CN 106506701A CN 201611235980 A CN201611235980 A CN 201611235980A CN 106506701 A CN106506701 A CN 106506701A
- Authority
- CN
- China
- Prior art keywords
- server
- client
- weight
- load
- maximum
- 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
Classifications
-
- 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
- H04L67/101—Server selection for load balancing based on network conditions
-
- 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
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
- H04L67/1048—Departure or maintenance mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
- H04L69/161—Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
- H04L69/162—Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields involving adaptations of sockets based mechanisms
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer And Data Communications (AREA)
Abstract
A kind of server load balancing method and load equalizer is embodiments provided, load-balancing method includes:The first incoming message for receiving and being sent according to the first client, sets up first with the first client and is connected;Backup and the first client are set up first and are generated when being connected and transmit controlled state and sockets state;According to the first incoming message that the first client sends, the second incoming message is generated and sent to first server, set up the first client with first server second is connected;When first server load reaches predetermined threshold value, obtain the server of the weight maximum in server cluster in addition to first server, and according to transmission controlled state and sockets state, set up the maximum server of the first client and weight the 3rd is connected, and disconnects the first client and be connected with the second of first server.By the embodiment of the present invention, can realize according to server load, the connection that has set up is rescheduled according to weight, improve Consumer's Experience.
Description
Technical field
The present invention relates to net application technology field, more particularly to a kind of server load balancing method and load balancing
Device.
Background technology
With the popularization and ecommerce of the Internet, the development of E-Government, increasing application system needs face
To higher visit capacity and data volume.Meanwhile, to the dependence of on-line system also more and more higher, substantial amounts of crucial application needs for enterprise
System has enough online rates and high efficiency.These requirements cause single network server device meet these need
Will, it is therefore desirable to introduce the load balance of server, realize client while multiple stage is accessed while the server of work, it is to avoid clothes
The Single Point of Faliure of business device, improves the service processing ability of on-line system.
Load-balancing technique provides a kind of cheap, effective, transparent method on existing network infrastructure, extends net
The bandwidth of network equipment and server, the handling capacity that increases, Strengthens network data-handling capacity, the motility for improving network and available
Property.It has both sides implication:First, substantial amounts of concurrently access or data traffic are shared and being located on multiple servers equipment respectively
Reason, reduces the time of user's wait-for-response;Secondly, single heavy duty computing is shared and does parallel place on multiple servers equipment
Reason, after every server apparatus process terminates, result is collected, returns to user, and system processing power is greatly improved.
Existing load-balancing technique is according to server load condition, sets up new TCP in server and client
When (Transmission Control Protocol, transmission control protocol) connects, new TCP connections are loaded
Equilibrium assignment, but, when with client set up server load that TCP is connected larger when, existing load-balancing technique is not
Load balance scheduling can be carried out to the TCP connections having built up so that server process speed reduces, and affects customer experience.
Content of the invention
The purpose of the embodiment of the present invention is to provide a kind of server load balancing method and load equalizer, to realize root
According to server load condition, scheduling is redistributed according to weight to the TCP connections that has set up, improves Consumer's Experience.Particular technique
Scheme is as follows:
In a first aspect, embodiments providing a kind of server load balancing method, load equalizer is applied to, institute
The server load balancing method that states includes:
The first incoming message for receiving and being sent according to the first client, sets up first with the first client and is connected;
Backup generate when setting up the first connection with the first client corresponding with the first client transmit controlled state and
Sockets state;
According to the first incoming message that the first client sends, the second incoming message is generated and sent to first server,
The first client is set up with first server second is connected, so that first server is built with the first client by the second connection
Vertical communication;
When first server load reaches predetermined threshold value, the weight in acquisition server cluster in addition to first server is most
Big server, and according to transmission controlled state and sockets state, set up the service maximum with weight of the first client
3rd connection of device, and disconnect the first client and be connected with the second of first server, so that the server energy of weight maximum
Enough set up with the first client by the 3rd connection and communicated, wherein, weight is used for representing every server current available resource
Size.
Optionally, in server cluster is obtained in addition to first server the maximum server of weight, and according to transmission
Controlled state and sockets state, set up the 3rd of the maximum server of the first client and weight be connected before, this
The server load balancing method of bright embodiment also includes:
Obtain the early warning message that predetermined threshold value is reached by the load that first server sends;
According to early warning message, the load information for obtaining every server in server cluster in addition to first server is sent
Request message;
The load information of every server in the reception server cluster in addition to first server, calculates and removes first server
The weight of every outer server, and the server for selecting the weight in server cluster in addition to first server maximum, wherein,
The load information includes:CPU usage, memory usage, network bandwidth occupancy.
Optionally, the predetermined threshold value includes:It is that 85% or the network bandwidth are accounted for that CPU usage is 85%, memory usage
It is 85% with rate.
Optionally, the method for the server load balancing of the embodiment of the present invention also includes:
After the maximum server process of weight completes all packets of the first client transmission, the first client is disconnected
Hold the 3rd of the server maximum with weight to be connected, and delete the transmission controlled state and sockets state of backup.
On the other hand, a kind of load equalizer is embodiments provided, and the load equalizer includes:
First connection establishment module, for the first incoming message for receiving and sent according to the first client, with the first visitor
Set up the first connection in family end;
Backup module, generated when setting up the first connection for backup with the first client are corresponding with the first client
Transmission controlled state and sockets state;
Scheduler module, for the first incoming message sent according to the first client, generates and sends the second incoming message
To first server, that sets up the first client with first server second is connected, so that first server is by the second connection
Set up with the first client and communicate;
When first server load reaches predetermined threshold value, the weight in acquisition server cluster in addition to first server is most
Big server, and according to transmission controlled state and sockets state, set up the service maximum with weight of the first client
3rd connection of device, and disconnect the first client and be connected with the second of first server, so that the server energy of weight maximum
Enough set up with the first client by the 3rd connection and communicated, wherein, weight is used for representing every server current available resource
Size.
Optionally, the load equalizer also includes:
Early warning information receiver module, for obtaining the precaution alarm for being reached predetermined threshold value by the load that first server sends
Text;
Request message sending module, for according to early warning message, in transmission acquisition server cluster in addition to first server
Every server load information request message;
Selecting module is calculated, the load for every server in the reception server cluster in addition to first server is believed
Breath, calculates the weight of every server in addition to first server, and selects the power in server cluster in addition to first server
The maximum server of weight, wherein, the load information includes:CPU usage, memory usage, network bandwidth occupancy.
Optionally, the predetermined threshold value includes:It is that 85% or the network bandwidth are accounted for that CPU usage is 85%, memory usage
It is 85% with rate.
Optionally, the load equalizer also includes:
Removing module, for complete in the maximum server process of weight the transmission of the first client all packets it
Afterwards, disconnect the first client server maximum with weight the 3rd is connected, and deletes transmission controlled state and the network of backup
Socket state.
A kind of server load balancing method provided in an embodiment of the present invention and load equalizer, by setting up the first company
When connecing, transmission controlled state corresponding with the first client and net that backup is generated when setting up the first connection with the first client
Network socket state, when first server load reaches predetermined threshold value, according to transmission controlled state and sockets state,
The server for selecting the weight in server cluster in addition to first server maximum, sets up the 3rd connection, and disconnects the first client
End be connected with the second of first server so that the maximum server of the weight can by the described 3rd connect with described
First client sets up communication, realizes redistributing scheduling to the connection that has set up according to weight, improves Consumer's Experience.Certainly,
The arbitrary product or method for implementing the present invention must be not necessarily required to while reaching all the above advantage.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
The first embodiment flow chart of Fig. 1 for the server load balancing method of the embodiment of the present invention;
Second embodiment flow charts of the Fig. 2 for the server load balancing method of the embodiment of the present invention;
The first the example structure figure of Fig. 3 for the load equalizer of the embodiment of the present invention;
Second example structure figures of the Fig. 4 for the load equalizer of the embodiment of the present invention.
Specific embodiment
Accompanying drawing in below in conjunction with the embodiment of the present invention, to the embodiment of the present invention in technical scheme carry out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiment.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Referring to Fig. 1, Fig. 1 is the first embodiment flow chart of the server load balancing method of the embodiment of the present invention, such as
Shown in Fig. 1, the server load balancing method of the embodiment of the present invention may include steps of:
S101, the first incoming message for receiving and being sent according to the first client, sets up first with the first client and is connected;
Specifically, being set up the first process being connected with the first client is included:
The first step, obtains the connection request message that the first client sends;
Second step, processes connection request message, sends the reply message for authorizing connection to the first client;
3rd step, receives the connection confirmation message generated according to reply Message processing the company of foundation that the first client sends
Connect.
By above-mentioned three-way handshake mode so that the first client accurately can set up the first company with load equalizer
Connect, improve the correctness for setting up connection.Certainly, the embodiment of the present invention can also set up the first connection by other means, should
It is understood by, above-mentioned steps can not be used for limiting the present invention just to the clearer process for illustrating to set up the first connection
The process for setting up the first connection, therefore, obtain by other means first connection should also be as belonging to the embodiment of the present invention
Protection domain, should give protection.
S102, the transmission control corresponding with the first client that backup is generated when setting up the first connection with the first client
State and sockets state;
After being connected with the foundation of the first client, tcp state corresponding with the first client and socket states is backed up, its
In, the tcp state includes source IP address, port and purpose IP address, port.
S103, according to the first incoming message that the first client sends, generates and sends the second incoming message to the first clothes
Business device, set up the first client with first server second be connecteds, so that first server is objective by the second connection and first
Set up communication in family end;
Specifically, set up the second connection to comprise the steps:
The first step, generates the second incoming message according to the first incoming message that the first client sends and is sent to the first clothes
Business device;
Second step, receives and according to first server to the first outgoing message obtained after the process of the second incoming message, builds
Vertical first client is connected with the second of first server.
In this step, load equalizer selects the first server in server cluster to make according to the first incoming message
For destination server, IP address, the port of destination server is obtained;Purpose IP address in the first incoming message, port is changed,
The second incoming message is generated, and is sent to first server, second server obtains the second incoming message and the second input is reported
Text is processed, and generates the first outgoing message, and load equalizer sends to first server according to the first outgoing message and confirms report
Text simultaneously sets up the second connection, and wherein, first server is arbitrary server in server cluster.
It should be noted that when the method for the embodiment of the present invention is configured in load equalizer, in load equalizer
The IP address of every server, port in storage server cluster.
S104, when first server load reaches predetermined threshold value, in acquisition server cluster in addition to first server
The maximum server of weight, and according to transmission controlled state and sockets state, set up the first client maximum with weight
Server the 3rd connection, and disconnect the first client and be connected with the second of first server, so that the clothes of weight maximum
Business device can be set up with the first client by the 3rd connection and be communicated, and wherein, weight is used for representing that every server is currently available
The size of resource.
Wherein, the threshold value that the predetermined threshold value in this step is according to actual needs and pre-sets, can 81%~
Value is carried out between 90%.
In this step, the maximum server of a kind of preferred weight obtained in server cluster in addition to first server
Embodiment be:Obtain the weight of Servers-all in addition to first server in server cluster, and suitable by from big to small
Sequence is ranked up, and obtains weight sequencing table, the server for selecting weight maximum.
By sequence, weight sequencing table can be quickly obtained so that load equalizer can quickly select weight maximum
Server, improves the processing speed of load equalizer.
In addition to the implementation, the weight in server cluster in addition to first server can also be obtained in the following manner
Maximum server:
The weight of arbitrary server in server cluster in addition to first server is obtained, in traversal server cluster
The weight of other servers, and compared one by one, obtain the maximum server of weight.
It should be noted that both the above embodiment be the embodiment of the present invention preferred embodiment, can not use
In the embodiment of the present invention is limited, the service of weight maximum in server cluster except first server in addition to is obtained by other means
The embodiment of device also should belong to protection scope of the present invention, should give protection.
In the embodiment of the present invention, by when the first connection is set up, backup and the first client set up the first life when being connected
Into transmission controlled state and sockets state corresponding with the first client, reach in first server load default
During threshold value, according to transmission controlled state and sockets state, the weight in addition to first server in server cluster is selected
Maximum server, sets up the 3rd connection, and disconnects the first client and be connected with the second of first server, so that the power
The maximum server of weight can be set up with first client by the described 3rd connection and be communicated, and realize the connection to having set up
Scheduling is redistributed according to weight, Consumer's Experience is improved.
Referring to Fig. 2, Fig. 2 is second embodiment flow chart of the server load balancing method of the embodiment of the present invention,
The maximum server of step S104, the weight in server cluster is obtained in addition to first server, and according to transmission control shape
State and sockets state, set up the 3rd of the maximum server of the first client and weight be connected before, present invention enforcement
The server load balancing method of example also includes:
S201, obtains the early warning message for being reached predetermined threshold value by the load that first server sends;
Wherein, in server end, when first server load reaches predetermined threshold value, generate load and reach default threshold
The early warning message of value simultaneously sends message to load equalizer, and therefore, in load equalizer, the early warning message of acquisition is by first
Server sends.
S202, according to early warning message, sends bearing for every server in acquisition server cluster in addition to first server
The request message of information carrying breath;
In this step, according to early warning message, the acquisition request message of generation acquisition load information simultaneously will for load equalizer
Every server in addition to first server during request message is sent to server cluster is obtained, is removed with obtaining in server cluster
The load information of every server outside first server.
S203, the load information of every server in the reception server cluster in addition to first server are calculated and are removed first
The weight of every server outside server, and the service for selecting the weight in server cluster in addition to first server maximum
Device, wherein, the load information includes:CPU usage, memory usage, network bandwidth occupancy.
Wherein, in server end, after server receives acquisition request message, the load information of respective server is collected,
And be sent to load equalizer, therefore, load equalizer can receive in server cluster in addition to first server per platform
The load information that server sends, load equalizer are calculated according to the load information for receiving, are obtained except first server
The weight of every outer server, further according to the weight of every server, can obtain the maximum server of weight.
For the weight of the clearer explanation embodiment of the present invention, the embodiment of the present invention lists the side of two kinds of calculating weights
Method:
The first calculating weight computational methods be:Weight be equal to the inverse of CPU usage, memory usage reciprocal and
The reciprocal multiplication of network bandwidth occupancy is added the numerical value for obtaining.
Second calculating weight computational methods be:Weight deducts (CPU usage, memory usage and Netowrk tape equal to 3
Wide occupancy sum) numerical value that obtains.
It can be seen that, the weight of server is bigger, illustrates that currently processed data are fewer, and server performance is more superior.
It should be appreciated that the computational methods that both the above calculates weight are implemented just to the clearer explanation present invention
Example, is not intended to limit the computational methods that the present invention calculates weight, therefore, all should by the calculated weight of additive method
Belong to protection scope of the present invention.
It should be noted that when the present invention is implemented, for same server cluster, only should be counted by one kind simultaneously
Calculation method obtains the weight of every server in addition to first server, and can not be in same server cluster simultaneously by many
Plant computational methods and obtain above-mentioned weight.
Specifically, predetermined threshold value includes:It is 85% or network bandwidth occupancy that CPU usage is 85%, memory usage
For 85%.
By setting predetermined threshold value, server overload can be effectively prevented, improve Consumer's Experience.
It should be noted that due to the S101 in the first embodiment of other steps and server load balancing method~
S103 is same or like, therefore can combine to realize the present embodiment, and here is omitted.
After the maximum server process of weight completes all packets of the first client transmission, the embodiment of the present invention
The third feasible embodiment is additionally provided, including:
Disconnect the maximum server of the first client and weight the 3rd is connected, and delete backup transmission controlled state and
Sockets state.
By this step, can effectively reduce the resource occupation of load equalizer, improve the performance of load equalizer.
Corresponding to a kind of server load balancing method of above-mentioned offer, a kind of load balancing is embodiments provided
Device, referring to Fig. 3, the first the example structure figure of Fig. 3 for the load equalizer of the embodiment of the present invention, as shown in figure 3, the load
Equalizer includes:
First connection establishment module 301, for the first incoming message for receiving and sent according to the first client, with first
Client sets up the first connection;
Backup module 302, generated when setting up the first connection for backup with the first client are corresponding with the first client
Transmission controlled state and sockets state;
Scheduler module 303, for the first incoming message sent according to the first client, generates and sends the second input report
To first server, that sets up the first client with first server second is connected text, so that first server is by the second company
Connect to set up with the first client and communicate;
When first server load reaches predetermined threshold value, the weight in acquisition server cluster in addition to first server is most
Big server, and according to transmission controlled state and sockets state, set up the service maximum with weight of the first client
3rd connection of device, and disconnect the first client and be connected with the second of first server, so that the server energy of weight maximum
Enough set up with the first client by the 3rd connection and communicated, wherein, weight is used for representing every server current available resource
Size.
Referring to Fig. 4, Fig. 4 is second example structure figure of the load equalizer of the embodiment of the present invention, as shown in figure 4,
The load equalizer of the embodiment of the present invention also includes:
Early warning information receiver module 401, for obtaining the early warning for being reached predetermined threshold value by the load that first server sends
Message;
Request message sending module 402, remove first server for according to early warning message, sending to obtain in server cluster
The request message of the load information of every outer server;
Selecting module 403 is calculated, for the load of every server in the reception server cluster in addition to first server
Information, calculates the weight of every server in addition to first server, and selects in server cluster in addition to first server
The maximum server of weight, wherein, the load information includes:CPU usage, memory usage, network bandwidth occupancy.
Specifically, predetermined threshold value includes:It is 85% or network bandwidth occupancy that CPU usage is 85%, memory usage
For 85%.
It should be noted that the first embodiment of other modules in the present embodiment and the load equalizer shown in Fig. 3
Functions of modules same or like, therefore, it can combine to realize the present embodiment, here is omitted.
Specifically, the embodiment of the present invention additionally provides the load equalizer that the third can be realized, except including above two
Outside the module of embodiment, load equalizer provided in an embodiment of the present invention also includes:
Removing module, for complete in the maximum server process of weight the transmission of the first client all packets it
Afterwards, disconnect the first client server maximum with weight the 3rd is connected, and deletes transmission controlled state and the network of backup
Socket state.
It should be noted that the load equalizer of the embodiment of the present invention is the negative of the above-mentioned server load balancing method of application
Equalizer is carried, then all embodiments of above-mentioned server load balancing method are applied to the load equalizer, and can reach
Same or analogous beneficial effect.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation are made a distinction with another entity or operation, and are not necessarily required or implied these entities or deposit between operating
In any this actual relation or order.And, term " including ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that a series of process, method, article or equipment including key elements not only includes that those will
Element, but also other key elements including being not expressly set out, or also include for this process, method, article or equipment
Intrinsic key element.In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that
Also there is other identical element in process, method, article or equipment including the key element.
Each embodiment in this specification is described by the way of correlation, identical similar portion between each embodiment
Divide mutually referring to what each embodiment was stressed is the difference with other embodiment.Especially for system reality
For applying example, as which is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
Presently preferred embodiments of the present invention is the foregoing is only, protection scope of the present invention is not intended to limit.All
Any modification, equivalent substitution and improvements that is made within the spirit and principles in the present invention etc., are all contained in protection scope of the present invention
Interior.
Claims (8)
1. a kind of server load balancing method, it is characterised in that be applied to load equalizer, the server load balancing side
Method includes:
The first incoming message for receiving and being sent according to the first client, sets up first with first client and is connected;
The transmission control shape corresponding with first client that backup is generated when setting up the first connection with first client
State and sockets state;
According to the first incoming message that first client sends, the second incoming message is generated and sent to first server,
First client is set up with the first server second is connected, so that the first server connects by described second
Connect to set up with first client and communicate;
When first server load reaches predetermined threshold value, in the acquisition server cluster in addition to the first server
The maximum server of weight, and according to the transmission controlled state and the sockets state, set up first visitor
The 3rd of the maximum server of family end and the weight is connected, and disconnects the of first client and the first server
Two connections, so that the maximum server of the weight can be set up by the described 3rd connection and first client lead to
Letter, wherein, the weight is used for the size for representing every server current available resource.
2. server load balancing method according to claim 1, it is characterised in that obtain the server set described
The server of the weight maximum in group in addition to the first server, and according to the transmission controlled state and the network socket
Mouthful state, set up the 3rd of first client server maximum with the weight be connected before, described server is negative
Carrying equalization methods also includes:
Obtain the early warning message that predetermined threshold value is reached by the load that the first server sends;
According to the early warning message, the load for obtaining every server in server cluster in addition to the first server is sent
The request message of information;
Receive and the load information according to every server in the server cluster in addition to the first server, calculating is removed
The weight of every server outside the first server, and select in the server cluster in addition to the first server
The maximum server of weight, wherein, the load information includes:CPU usage, memory usage, network bandwidth occupancy.
3. server load balancing method according to claim 1 and 2, it is characterised in that the predetermined threshold value includes:
CPU usage is that 85%, memory usage is 85% or network bandwidth occupancy is 85%.
4. server load balancing method according to claim 1 and 2, it is characterised in that described server load is equal
The method of weighing apparatus also includes:
After the maximum server process of the weight completes all packets that first client sends, disconnect described
The 3rd of the maximum server of first client and the weight is connected, and deletes the transmission controlled state of backup and described
Sockets state.
5. a kind of load equalizer, it is characterised in that include:
First connection establishment module, for the first incoming message for receiving and sent according to the first client, with the described first visitor
Set up the first connection in family end;
Backup module, for backup and first client set up first be connected when generate and first client pair
The transmission controlled state that answers and sockets state;
Scheduler module, for the first incoming message sent according to first client, generates and sends the second incoming message
To first server, that sets up first client with the first server second is connected, so that the first server
Set up with first client by the described second connection and communicated;
When first server load reaches predetermined threshold value, in the acquisition server cluster in addition to the first server
The maximum server of weight, and according to the transmission controlled state and the sockets state, set up first visitor
The 3rd of the maximum server of family end and the weight is connected, and disconnects the of first client and the first server
Two connections, so that the maximum server of the weight can be set up by the described 3rd connection and first client lead to
Letter, wherein, the weight is used for the size for representing every server current available resource.
6. load equalizer according to claim 5, it is characterised in that the load equalizer also includes:
Early warning information receiver module, for obtaining the precaution alarm for being reached predetermined threshold value by the load that the first server sends
Text;
Request message sending module, remove the first service for according to the early warning message, sending to obtain in server cluster
The request message of the load information of every server outside device;
Selecting module is calculated, for receiving the load of every server in the server cluster in addition to the first server
Information, calculates the weight of every server in addition to the first server, and selects in the server cluster except described the
The server of the weight maximum outside one server, wherein, the load information includes:CPU usage, memory usage, network
Bandwidth usage.
7. the load equalizer according to claim 5 or 6, it is characterised in that the predetermined threshold value includes:CPU usage
For 85%, memory usage be 85% or network bandwidth occupancy is 85%.
8. the load equalizer according to claim 5 or 6, it is characterised in that the load equalizer also includes:
Removing module, for completing all packets that first client sends in the maximum server process of the weight
Afterwards, disconnect first client server maximum with the weight the 3rd is connected, and deletes the transmission of backup
Controlled state and the sockets state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611235980.9A CN106506701A (en) | 2016-12-28 | 2016-12-28 | A kind of server load balancing method and load equalizer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611235980.9A CN106506701A (en) | 2016-12-28 | 2016-12-28 | A kind of server load balancing method and load equalizer |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106506701A true CN106506701A (en) | 2017-03-15 |
Family
ID=58334652
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611235980.9A Pending CN106506701A (en) | 2016-12-28 | 2016-12-28 | A kind of server load balancing method and load equalizer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106506701A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107204932A (en) * | 2017-07-20 | 2017-09-26 | 湖南中云飞华信息技术有限公司 | Network flow control method and device based on network end node |
CN107302456A (en) * | 2017-06-22 | 2017-10-27 | 深圳市丰巨泰科电子有限公司 | A kind of method and device of data processing |
CN107547643A (en) * | 2017-08-29 | 2018-01-05 | 新华三技术有限公司 | A kind of load sharing method and device |
CN109922008A (en) * | 2019-03-21 | 2019-06-21 | 新华三信息安全技术有限公司 | A kind of file transmitting method and device |
CN109960565A (en) * | 2017-12-25 | 2019-07-02 | 航天信息股份有限公司 | Cloud platform, dispatching method of virtual machine and device based on cloud platform |
CN110198359A (en) * | 2019-07-08 | 2019-09-03 | 紫光云技术有限公司 | A kind of load-balancing method and device |
CN112615909A (en) * | 2020-12-10 | 2021-04-06 | 安徽鸿程光电有限公司 | Method for storing data in cascade storage server cluster and related equipment |
CN112866394A (en) * | 2021-01-26 | 2021-05-28 | 广州虎牙科技有限公司 | Load balancing method, device, system, computer equipment and storage medium |
CN114048020A (en) * | 2021-09-22 | 2022-02-15 | 北京中科金马科技股份有限公司 | Guest room management system based on big data |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101714949A (en) * | 2009-11-27 | 2010-05-26 | 中国工商银行股份有限公司 | Method, device and system for connecting and switching server |
US8244864B1 (en) * | 2001-03-20 | 2012-08-14 | Microsoft Corporation | Transparent migration of TCP based connections within a network load balancing system |
CN102932444A (en) * | 2012-10-29 | 2013-02-13 | 上海银商资讯有限公司 | Load balancing module in financial real-time trading system |
CN103036979A (en) * | 2012-12-12 | 2013-04-10 | 广州尚融网络科技有限公司 | Server loading balancing method and loading balancer |
CN103220354A (en) * | 2013-04-18 | 2013-07-24 | 广东宜通世纪科技股份有限公司 | Method for achieving load balancing of server cluster |
CN103618738A (en) * | 2013-12-09 | 2014-03-05 | 惠州华阳通用电子有限公司 | Intelligent load distribution system and method for achieving TCP long connection and communication |
CN105677451A (en) * | 2014-11-18 | 2016-06-15 | 北京风行在线技术有限公司 | Load balancing method and equipment used for multiple processes |
-
2016
- 2016-12-28 CN CN201611235980.9A patent/CN106506701A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8244864B1 (en) * | 2001-03-20 | 2012-08-14 | Microsoft Corporation | Transparent migration of TCP based connections within a network load balancing system |
CN101714949A (en) * | 2009-11-27 | 2010-05-26 | 中国工商银行股份有限公司 | Method, device and system for connecting and switching server |
CN102932444A (en) * | 2012-10-29 | 2013-02-13 | 上海银商资讯有限公司 | Load balancing module in financial real-time trading system |
CN103036979A (en) * | 2012-12-12 | 2013-04-10 | 广州尚融网络科技有限公司 | Server loading balancing method and loading balancer |
CN103220354A (en) * | 2013-04-18 | 2013-07-24 | 广东宜通世纪科技股份有限公司 | Method for achieving load balancing of server cluster |
CN103618738A (en) * | 2013-12-09 | 2014-03-05 | 惠州华阳通用电子有限公司 | Intelligent load distribution system and method for achieving TCP long connection and communication |
CN105677451A (en) * | 2014-11-18 | 2016-06-15 | 北京风行在线技术有限公司 | Load balancing method and equipment used for multiple processes |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107302456B (en) * | 2017-06-22 | 2020-10-27 | 常州市小先信息技术有限公司 | Data processing method and device |
CN107302456A (en) * | 2017-06-22 | 2017-10-27 | 深圳市丰巨泰科电子有限公司 | A kind of method and device of data processing |
CN107204932A (en) * | 2017-07-20 | 2017-09-26 | 湖南中云飞华信息技术有限公司 | Network flow control method and device based on network end node |
CN107547643A (en) * | 2017-08-29 | 2018-01-05 | 新华三技术有限公司 | A kind of load sharing method and device |
CN109960565B (en) * | 2017-12-25 | 2021-06-04 | 航天信息股份有限公司 | Cloud platform, and virtual machine scheduling method and device based on cloud platform |
CN109960565A (en) * | 2017-12-25 | 2019-07-02 | 航天信息股份有限公司 | Cloud platform, dispatching method of virtual machine and device based on cloud platform |
CN109922008A (en) * | 2019-03-21 | 2019-06-21 | 新华三信息安全技术有限公司 | A kind of file transmitting method and device |
CN109922008B (en) * | 2019-03-21 | 2022-06-21 | 新华三信息安全技术有限公司 | Message sending method and device |
CN110198359A (en) * | 2019-07-08 | 2019-09-03 | 紫光云技术有限公司 | A kind of load-balancing method and device |
CN112615909A (en) * | 2020-12-10 | 2021-04-06 | 安徽鸿程光电有限公司 | Method for storing data in cascade storage server cluster and related equipment |
CN112866394A (en) * | 2021-01-26 | 2021-05-28 | 广州虎牙科技有限公司 | Load balancing method, device, system, computer equipment and storage medium |
CN114048020A (en) * | 2021-09-22 | 2022-02-15 | 北京中科金马科技股份有限公司 | Guest room management system based on big data |
CN114048020B (en) * | 2021-09-22 | 2022-04-26 | 北京中科金马科技股份有限公司 | Guest room management system based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106506701A (en) | A kind of server load balancing method and load equalizer | |
CN113037869B (en) | Method and apparatus for back-sourcing of content distribution network system | |
CN110166570B (en) | Service session management method and device, and electronic device | |
CN102918813A (en) | Device and method for data load balancing | |
CN102347876B (en) | Multilink aggregation control device for cloud computing network | |
CN109831524B (en) | Load balancing processing method and device | |
CN107317879A (en) | The distribution method and system of a kind of user's request | |
CN103401947A (en) | Method and device for allocating tasks to multiple servers | |
CN103442030A (en) | Method and system for sending and processing service request messages and client-side device | |
CN102004673A (en) | Processing method and system of multi-core processor load balancing | |
CN104038525B (en) | The load-balancing method and device of server system | |
CN102724105B (en) | A kind of load-balancing method and device | |
CN108123995A (en) | The request scheduling and optimization method that space is perceived in distributed green cloud data center | |
CN106302230B (en) | A kind of data transmission method and device | |
CN104836747A (en) | Network outbound load balancing method and system | |
CN102932271A (en) | Method and device for realizing load balancing | |
CN106230992B (en) | A kind of load-balancing method and load balancing node | |
CN107579924A (en) | A kind of flow allots method and apparatus | |
CN102857547B (en) | The method and apparatus of distributed caching | |
CN108923817B (en) | Method for reducing interference between terminals in LoRa network | |
Kyung et al. | A load distribution scheme over multiple controllers for scalable SDN | |
CN107071020A (en) | Load balancing framework applied to cloud computing server | |
CN108111567A (en) | Realize the uniform method and system of server load | |
CN102387071A (en) | Network load balancing method, processor and system | |
CN107197043A (en) | A kind of cloud computing system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |