CN108055358A - A kind of load-balancing algorithm-intelligence weighting algorithm implementation method - Google Patents
A kind of load-balancing algorithm-intelligence weighting algorithm implementation method Download PDFInfo
- Publication number
- CN108055358A CN108055358A CN201810024579.3A CN201810024579A CN108055358A CN 108055358 A CN108055358 A CN 108055358A CN 201810024579 A CN201810024579 A CN 201810024579A CN 108055358 A CN108055358 A CN 108055358A
- Authority
- CN
- China
- Prior art keywords
- server
- load
- request
- maximum
- connection number
- 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
- H04L67/1012—Server selection for load balancing based on compliance of requirements or conditions with available server resources
-
- 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
- H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer And Data Communications (AREA)
Abstract
The present invention relates to server fields, more particularly to a kind of load-balancing algorithm intelligence weighting algorithm implementation method, the method most distinguishing feature is that the weights of each server and request connection quantity, maximum processing connection number are safeguarded on load equalizer, according to intelligent weighting algorithm formula, obtain the server of best performance, load balancing will ask the preferential server process for being distributed to best performance, the time overhead of poll was so both saved, the server for also allowing performance best plays the processing capacity of oneself to greatest extent.
Description
Technical field
The present invention relates to server field, more particularly to a kind of load-balancing algorithm-intelligence weighting algorithm implementation method.
Background technology
Load balancing is built upon on existing network infrastructure, it provides a kind of cheap effectively transparent method extension net
Network equipment and the bandwidth of server, the handling capacity that increases, Strengthens network data-handling capacity, the flexibility for improving network and availability
Equipment.The wherein algorithm of load-balanced server directly determines the processing capacity and performance of load balancing.It is now relatively more normal
Polling algorithm is the access one by one to existing server zone, although can so reach equiblibrium mass distribution user request,
The problem of having ignored server difference;Weighted polling is then to poll optimization of problems, he can accomplish according to server
The difference of configuration sets the quantity of each server process user request, this is really more reasonable, but there is also certain
The problem of, it is exactly the mode using poll, then load balancing remains inquiry successively and be not up to when distributing user is asked
Threshold service device is so still unable to reach the purpose optimized using server.
The content of the invention
Based on the above problem, the present invention proposes a kind of new load-balancing algorithm-intelligence weighting algorithm, and the method is most aobvious
Work feature is that the weights of each server and request connection quantity, maximum processing connection number are safeguarded on load equalizer, according to intelligence
Energy weighting algorithm formula, obtains the server of best performance, and load balancing will ask preferentially to be distributed to the server of best performance
Processing, had so both saved the time overhead of poll, the server for also allowing performance best plays the processing energy of oneself to greatest extent
Power.It is the significant increase calculated existing load balancing.
The present invention is achieved through the following technical solutions, and the present invention provides a kind of load-balancing algorithm-intelligence weighting and calculates
Method implementation method, specifically comprises the following steps:(1) load balancing intellectual analysis table is initialized;(2) intelligent weighted formula calculates most
Excellent server;(3) after server is fully loaded with request, processing status indicator change.
Preferably, server id, server weight value, request connection number, server maximum are included in intellectual analysis table can
Number is connected with processing, handles status indicator.
Preferably, the formula in step (2) is as follows:Server handling ability index=weighted value/(maximum can handle connection
Number-request connects number+1), the processing capacity that the process capability index of server is bigger to illustrate server is higher, load equalizer
The prioritizing selection server handling ability index maximum in distribution request.
Preferably, the particular content of step (3) is:The high server of server handling ability index in step (2), if
Connection number can be handled by having reached server maximum, and processing status indicator is arranged to 0, no longer receives the distribution of load balancing, when
Server releases connection, when can receiving connection again, then processing is identified and is arranged to 1.
Description of the drawings
Load-balancing algorithm-intelligence weighting algorithm flow chart that Fig. 1 one embodiment of the invention provides
Specific embodiment
Presently preferred embodiments of the present invention is described in detail below in conjunction with the accompanying drawings.Following embodiment is only used for clearer
Ground illustrates technical scheme, and is not intended to limit the protection scope of the present invention and limits the scope of the invention.
The present invention proposes a kind of new load-balancing algorithm-intelligence weighting algorithm.
Feature of the present invention is that the weights of each server, request connection number, maximum processing connection are safeguarded on load equalizer
The server that request distributes is calculated in number parameter information, the intelligent weighted formula proposed according to the present invention.Each server is asked
Connection number is asked to be recorded automatically in load equalizer distribution request and releasing request, maximum processing connection is several according to server
Weights and request consumption calculations ability integration are drawn.
Shown in a kind of new load-balancing algorithm-intelligence weighting algorithm implementation method process schematic (such as attached drawing 1).Specifically
Implementation process is as follows:
(1) load balancing intellectual analysis table is initialized.In the beginning of load equalizer work, it is necessary first to initialize this hair
Bright newly-increased intellectual analysis table can be located comprising server id, server weight value, request connection number, server maximum in table
Reason connection number, handles status indicator.
Server weight value:What is identified is the processing capacity of server, with existing load-balancing algorithm Weighted Round Robin
Computational methods it is the same, for each server, different weighted value is set.Value is bigger, and expression processing capacity is stronger.
Request connection number:It is external processing request to be worth, due to each request by load equalizer be responsible for distribution and
Release so the connection number in table is dynamic change, distributes how many requests to server, then corresponding server connects in the table
Connecing number will accordingly increase;Similarly, if releasing request, it is also desirable to corresponding to reduce.
Server maximum can handle connection number:According to the processing capacity of server and the value of request consumption calculations, estimate
Numerical value.
Handle status indicator:Whether identification server can continue to receive the mark of request.If 1 identification server shape
State is normal, if 0 identification server exception or full load condition, is not receiving load equalizer request distribution.
(2) intelligent weighted formula calculates optimal service device.Load balancing is in distribution request, it is necessary to obtain corresponding with service
The id of device, by intelligent weighted formula, the intellectual analysis table data being subject in step (1) calculate optimal service device.It can only
Formula is as follows:
Server handling ability index=weighted value/(maximum can handle connection number-request connection number+1)
The processing capacity that the process capability index of server is bigger to illustrate server is higher, and load equalizer is in distribution request
When can prioritizing selection server handling ability index it is maximum.
(3) after server is fully loaded with request, processing status indicator change.Server handling ability index is high in step (2)
Server, the maximum processing connection number of server may have been had reached.It needs this when to set processing status indicator
For 0, the distribution of load balancing is not being received.When server releases connection, can receive connection again, mark will handled
It is arranged to 1.
Term " computer system " includes realizing system according to the above embodiment or performs the hardware of method, software sum number
According to storage device.For example, computer system may include that central processing unit (CPU), input unit, output device and data are deposited
Storage.Preferably, computer system has to provide the monitor (for example, commercial processes design) that visual output is shown.Data
Storage may include RAM, disk drive or other computer-readable mediums.Computer system may include through the multiple of network connection
Computing device, and can communicate with one another by the network.
The method of embodiment of above can be set to computer program or carry the computer program product of computer program
Or computer-readable medium, the computer program perform the above method when being arranged to run on computers.
Term " computer-readable medium " including but not limited to can directly be read by computer or computer system or
Any non-provisional media or medium that person accesses.The medium may include (but not limited to) such as floppy disk, hard disc storage medium and
The magnetic storage medium of tape;The optical storage medium of such as CD or CD-ROM;The electric storage medium of such as memory, including
RAM, ROM and flash memory;And above mixing and combination, such as magnetic optical storage medium.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should all be included in the protection scope of the present invention.
Claims (4)
1. a kind of load-balancing algorithm-intelligence weighting algorithm implementation method, specifically comprises the following steps:(1) initialization load is equal
Weigh intellectual analysis table;(2) intelligent weighted formula calculates optimal service device;(3) after server is fully loaded with request, processing status indicator becomes
More.
2. according to the method described in claim 1, it is characterized in that:Server id, server weight are included in intellectual analysis table
Value, request connection number, server maximum can handle connection number, handle status indicator.
3. according to the method described in claim 1, it is characterized in that:Formula in step (2) is as follows:Server handling ability refers to
Number=weighted value/(maximum can handle connection number-request connection number+1), the process capability index of server is bigger to illustrate server
Processing capacity it is higher, load equalizer prioritizing selection server handling ability index in distribution request is maximum.
4. according to the method described in claim 1, it is characterized in that:The particular content of step (3) is:The service in step (2)
If connection number can be handled by having reached server maximum, processing status indicator is arranged to for the high server of device process capability index
0, no longer receive the distribution of load balancing, identified when server, which releases connection, can receive connection again, then by processing
It is arranged to 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810024579.3A CN108055358A (en) | 2018-01-11 | 2018-01-11 | A kind of load-balancing algorithm-intelligence weighting algorithm implementation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810024579.3A CN108055358A (en) | 2018-01-11 | 2018-01-11 | A kind of load-balancing algorithm-intelligence weighting algorithm implementation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108055358A true CN108055358A (en) | 2018-05-18 |
Family
ID=62127065
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810024579.3A Pending CN108055358A (en) | 2018-01-11 | 2018-01-11 | A kind of load-balancing algorithm-intelligence weighting algorithm implementation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108055358A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109600429A (en) * | 2018-11-28 | 2019-04-09 | 平安科技(深圳)有限公司 | Service shunting method, device, electronic equipment and storage medium |
CN113467955A (en) * | 2021-07-28 | 2021-10-01 | 国电南京自动化股份有限公司 | Intelligent distribution method and system for data acquisition link of distribution network master station |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6996615B1 (en) * | 2000-09-29 | 2006-02-07 | Cisco Technology, Inc. | Highly scalable least connections load balancing |
CN101605092A (en) * | 2009-07-10 | 2009-12-16 | 浪潮电子信息产业股份有限公司 | A kind of content-based SiteServer LBS |
CN103401947A (en) * | 2013-08-20 | 2013-11-20 | 曙光信息产业(北京)有限公司 | Method and device for allocating tasks to multiple servers |
CN105553872A (en) * | 2015-12-25 | 2016-05-04 | 浪潮(北京)电子信息产业有限公司 | Multipath data traffic load equalizing method |
CN106385459A (en) * | 2016-10-20 | 2017-02-08 | 杭州迪普科技有限公司 | Method and device for distributing connection request message |
-
2018
- 2018-01-11 CN CN201810024579.3A patent/CN108055358A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6996615B1 (en) * | 2000-09-29 | 2006-02-07 | Cisco Technology, Inc. | Highly scalable least connections load balancing |
CN101605092A (en) * | 2009-07-10 | 2009-12-16 | 浪潮电子信息产业股份有限公司 | A kind of content-based SiteServer LBS |
CN103401947A (en) * | 2013-08-20 | 2013-11-20 | 曙光信息产业(北京)有限公司 | Method and device for allocating tasks to multiple servers |
CN105553872A (en) * | 2015-12-25 | 2016-05-04 | 浪潮(北京)电子信息产业有限公司 | Multipath data traffic load equalizing method |
CN106385459A (en) * | 2016-10-20 | 2017-02-08 | 杭州迪普科技有限公司 | Method and device for distributing connection request message |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109600429A (en) * | 2018-11-28 | 2019-04-09 | 平安科技(深圳)有限公司 | Service shunting method, device, electronic equipment and storage medium |
CN113467955A (en) * | 2021-07-28 | 2021-10-01 | 国电南京自动化股份有限公司 | Intelligent distribution method and system for data acquisition link of distribution network master station |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2005008943A3 (en) | System and methods of cooperatively load-balancing clustered servers | |
JP4121132B2 (en) | Service processing allocation apparatus, control method, and program | |
CN106233276B (en) | The coordination admission control of network-accessible block storage device | |
CN105718479B (en) | Execution strategy generation method and device under cross-IDC big data processing architecture | |
US20150196841A1 (en) | Load balancing system and method for rendering service in cloud gaming environment | |
CN104901898B (en) | A kind of load-balancing method and device | |
US20200059402A1 (en) | Improving performance of multi-processor computer systems | |
CN110149395A (en) | One kind is based on dynamic load balancing method in the case of mass small documents high concurrent | |
CN108111586A (en) | The web cluster system and method that a kind of high concurrent is supported | |
WO2014035838A1 (en) | Client placement in a computer network system using dynamic weight assignments on resource utilization metrics | |
CN108551489A (en) | A kind of application server load balancing method, system, device and storage medium | |
CN110473354A (en) | A kind of cloud mobile phone optimal selection method, system, device and storage medium | |
CN108055358A (en) | A kind of load-balancing algorithm-intelligence weighting algorithm implementation method | |
CN106790381A (en) | Dynamic feedback of load equalization methods based on weighting Smallest connection | |
CN110233866A (en) | A kind of load-balancing method and load balancer | |
US8745232B2 (en) | System and method to dynamically allocate electronic mailboxes | |
CN105491085A (en) | Method and device for on-line requesting for queuing | |
CN107302580A (en) | Load balancing method and device, load balancer and storage medium | |
CN102497421B (en) | Web server cluster system round-robin scheduling load balancing method with good fairness | |
CN112363827A (en) | Multi-resource index Kubernetes scheduling method based on delay factors | |
CN104301944B (en) | Resource capability distribution method and equipment | |
CN102223395B (en) | Method and device for balancing dynamic load of middleware in radio frequency identification (RFID) network | |
CN110096352B (en) | Process management method, device and computer readable storage medium | |
CN116880968A (en) | Job scheduling method and scheduling system | |
CN109040283A (en) | A kind of modified load-balancing algorithm based on difference reaction type |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180518 |
|
RJ01 | Rejection of invention patent application after publication |