CN109769031A - A kind of dynamic self-adapting load-balancing method and system - Google Patents
A kind of dynamic self-adapting load-balancing method and system Download PDFInfo
- Publication number
- CN109769031A CN109769031A CN201910119364.4A CN201910119364A CN109769031A CN 109769031 A CN109769031 A CN 109769031A CN 201910119364 A CN201910119364 A CN 201910119364A CN 109769031 A CN109769031 A CN 109769031A
- Authority
- CN
- China
- Prior art keywords
- request
- server
- real
- time factor
- total
- 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
Landscapes
- Computer And Data Communications (AREA)
Abstract
The present invention relates to a kind of dynamic self-adapting load-balancing method and systems, belong to server scheduling technical field, its method is the following steps are included: analyze received web request, different by request content realize classification, to every a kind of request binding Dynamic Weights to quantify to request, the Dynamic Weights request the occupancy and request service time length to server resource for real-time representation;Collect and calculate the request total amount and real-time factor of wait-for-response in each server;Total request amount of Servers-all is calculated, and judges whether total request amount is more than preset request threshold value;Refuse to receive request if total request amount is more than request threshold value, otherwise receives request and forwarded according to the real-time factor of each server to request.Present invention reduces network loads, reduce the complexity that load calculates, improve the accuracy of load information and combine dynamical feedback and admission control mechanism, have low-response delay, high scalability and high-throughput performance.
Description
Technical field
The present invention relates to a kind of dynamic self-adapting load-balancing method and systems, belong to server scheduling technical field.
Background technique
Nowadays with the continuous extension that the Web such as e-commerce, Web bank, online game, shopping online are applied, so that clothes
Business website must cope with more dynamic requests, and server resource expense increases severely.Increasingly increase when single server can no longer cope with
It when the service request added, can be replaced with the better server generation of the more expensive performance of price, but from scalability, high availability
From the aspect of cost performance, Clustering is to solve the preferred option of this problem.Problem of load balancing is the core of group system
The heart, existing load balancing are broadly divided into static and dynamic, and static load balancing shows in the case of request amount is larger
It is bad;And dynamic load balancing is mostly the hidden dynamic dispatching of content, using the dynamic dispatching algorithm scheduler that content is hidden
Expense is smaller, and dispatching efficiency is high.But the Web server fluctuation of load is big, and the load information that previous moment is collected is in subsequent time
Perhaps it is no longer able to accurately reflect server load state, so that the dynamic dispatching based on server end load state information be made to calculate
Method failure.Furthermore the bottleneck problem of scheduler will seriously affect the throughput and scalability of whole system.On the other hand, it asks
Classification is asked to need artificial pre-processing, and this work is done again from the beginning again when service change, flexibility is poor.
Summary of the invention
The present invention provides a kind of dynamic self-adapting load-balancing method and system, settlement server load imbalance are asked
Topic.
Technical solution of the present invention first aspect is a kind of dynamic self-adapting load-balancing method, and the method includes following
Step:
Received web request is analyzed, different by request content realize classification, to every a kind of request binding dynamic
For weight to quantify to request, the Dynamic Weights request the occupancy and request service time to server resource for real-time representation
Length;
Collect and calculate the request total amount and real-time factor of wait-for-response in each server;
Total request amount of Servers-all is calculated, and judges whether total request amount is more than preset request threshold value;
Refuse to receive request if total request amount is more than request threshold value, otherwise receives request and according to the real-time of each server
Performance indicator forwarding request.
Further, the real-time factor include CPU usage, cpu busy percentage, disk available space, memory and
I/O utilization rate, network broadband occupation rate.
Further, by installing probe program in each server, to obtain the real-time factor of respective server.
Further, the probe program issues performance indicator acquisition instructions according to setpoint frequency, grabs and feeds back corresponding
Real-time factor.
Technical solution of the present invention second aspect be a kind of dynamic self-adapting SiteServer LBS, including scheduler and and its
The server cluster of connection, the scheduler include:
Weight classification binding module is divided for analyzing received web request by different realize of request content
Class, to every a kind of request binding Dynamic Weights to quantify to request, the Dynamic Weights request to provide server for real-time representation
The occupancy and request service time length in source;
Server state acquisition module, for collecting and calculating the request total amount and real-time of wait-for-response in each server
It can index;
Access forwarding module for calculating total request amount of Servers-all, and judges whether total request amount is more than default
Request threshold value;Refuse to receive request if total request amount is more than request threshold value, otherwise receives request and according to each server
Real-time factor forwarding request.
Further, the server state acquisition module includes:
Server request amount acquisition module, for collecting and acquiring the request total amount of wait-for-response in each server;
Real-time factor acquisition module, for acquiring the real-time factor of each server;The real-time factor
Including CPU usage, cpu busy percentage, disk available space, memory and I/O utilization rate, network broadband occupation rate.
Further, the real-time factor acquisition module includes:
Probe monitoring modular is installed on the real-time factor that respective server is obtained in each server;
Receiving module is installed on the real-time factor that server feedback is received in scheduler.
Further, the probe monitoring modular includes: timing trigger module, for making probe program according under setpoint frequency
The instruction of volatility index collection, grabs and feeds back corresponding real-time factor.
The technical solution of the present invention third aspect is a kind of computer installation, including memory, processor and being stored in is deposited
On reservoir and the computer program that can run on a processor, the processor realize such as above-mentioned first when executing described program
The method of aspect.
Technical solution of the present invention fourth aspect is a kind of computer readable storage medium, stores computer journey thereon
Sequence realizes the method such as above-mentioned first aspect when the computer program is executed by processor.
The invention has the benefit that dynamic self-adapting load-balancing method of the invention and system, pass through back-end services
Device is to requirement analysis, according to request content by requests classification;The calculating of server load is using hardware performance and request total amount phase
In conjunction with real-time factor, reduce network load, reduce load calculate complexity, improve the accurate of load information
Dynamical feedback and admission control mechanism are spent and combined, there is preferable low-response delay, high scalability and high-throughput
Performance.
Detailed description of the invention
Fig. 1 show basic flow chart according to the method for the present invention;
Fig. 2 show apparatus according to the invention schematic diagram.
Specific embodiment
It is carried out below with reference to technical effect of the embodiment and attached drawing to design of the invention, specific structure and generation clear
Chu, complete description, to be completely understood by the purpose of the present invention, scheme and effect.
It should be noted that unless otherwise specified, when a certain feature referred to as " fixation ", " connection " are in another feature,
It can directly fix, be connected to another feature, and can also fix, be connected to another feature indirectly.In addition, this
The descriptions such as the upper and lower, left and right used in open are only the mutual alignment pass relative to each component part of the disclosure in attached drawing
For system.The "an" of used singular, " described " and "the" are also intended to including most forms in the disclosure, are removed
Non- context clearly expresses other meaning.In addition, unless otherwise defined, all technical and scientific terms used herein
It is identical as the normally understood meaning of those skilled in the art.Term used in the description is intended merely to describe herein
Specific embodiment is not intended to be limiting of the invention.Term as used herein "and/or" includes one or more relevant
The arbitrary combination of listed item.Provided in this article any and all example or exemplary language (" such as ", " such as ")
Use be intended merely to that the embodiment of the present invention is better described, and unless the context requires otherwise, otherwise will not be to the scope of the present invention
Apply limitation.
With reference to Fig. 1, a kind of dynamic self-adapting load-balancing method be the described method comprises the following steps:
Received web request is analyzed, different by request content realize classification, to every a kind of request binding dynamic
For weight to quantify to request, the Dynamic Weights request the occupancy and request service time to server resource for real-time representation
Length;
Collect and calculate the request total amount and real-time factor of wait-for-response in each server;
Total request amount of Servers-all is calculated, and judges whether total request amount is more than preset request threshold value;
Refuse to receive request if total request amount is more than request threshold value, otherwise receives request and according to the real-time of each server
Performance indicator forwarding request.
Further, the real-time factor include CPU usage, cpu busy percentage, disk available space, memory and
I/O utilization rate, network broadband occupation rate.
Further, by installing probe program in each server, to obtain the real-time factor of respective server.
Further, the probe program issues performance indicator acquisition instructions according to setpoint frequency, grabs and feeds back corresponding
Real-time factor.
With reference to Fig. 2, a kind of dynamic self-adapting SiteServer LBS, including scheduler and server cluster connected to it,
The scheduler includes:
Weight classification binding module is divided for analyzing received web request by different realize of request content
Class, to every a kind of request binding Dynamic Weights to quantify to request, the Dynamic Weights request to provide server for real-time representation
The occupancy and request service time length in source;
Server state acquisition module, for collecting and calculating the request total amount and real-time of wait-for-response in each server
It can index;
Access forwarding module for calculating total request amount of Servers-all, and judges whether total request amount is more than default
Request threshold value;Refuse to receive request if total request amount is more than request threshold value, otherwise receives request and according to each server
Real-time factor forwarding request.
Further, the server state acquisition module includes:
Server request amount acquisition module, for collecting and acquiring the request total amount of wait-for-response in each server;
Real-time factor acquisition module, for acquiring the real-time factor of each server;The real-time factor
Including CPU usage, cpu busy percentage, disk available space, memory and I/O utilization rate, network broadband occupation rate.
Further, the real-time factor acquisition module includes:
Probe monitoring modular is installed on the real-time factor that respective server is obtained in each server;
Receiving module is installed on the real-time factor that server feedback is received in scheduler.
Further, the probe monitoring modular includes: timing trigger module, for making probe program according under setpoint frequency
The instruction of volatility index collection, grabs and feeds back corresponding real-time factor.
Specifically,
1) request of arrival is analyzed, is classified as m class, every a kind of corresponding weight by the difference of request content
Wi, and quantify to request with this, size indicate its to server resource occupy number and request service time length, value
It can isolated operation testing setup.
2) it collects and the wait-for-response in calculation server requests total amount and real-time factor information.If Nij indicates clothes
The quantity of jth class wait-for-response request in business device Si, SUMi indicate that the wait-for-response of server S i requests total amount, and n indicates to service
The quantity of device enables:
If Ni indicates the quantity of server S i wait-for-response request, Ri indicates the total amount of server S i wait-for-response request;
Ci indicates that the request of server S i wait-for-response accounts for the percentage of the total wait-for-response request of system, enables:
Ci=Ri/SUM
If Pi indicates server S i hardware performance weight, size can be according to server runtime server Performance measurement software
(such as Loadrunner) setting, CLi indicate server S i real-time factor, enable:
SUM and CLi are periodically submitted to the access forwarding module of scheduler respectively, and SUMi is notified into each service
Device.
3) according to the request total amount value SUM in current system, refuse request when it reaches scheduled request threshold value, otherwise
Receive to request and carries out load balance process;It requests threshold value that can be measured according to practical application and then be arranged again.
4) scheduler periodically collects real-time factor data CLi in each server, is used as each service accordingly
The connection weight of device.CLi is set as server hardware performance weight when system is initial, and CLi is that 0 expression server no longer receives to ask
It asks or has shut down, feeding back its value until next information is not 0;System is using the forwarding request of WRR algorithms selection server.
It should be appreciated that the embodiment of the present invention can be by computer hardware, the combination of hardware and software or by depositing
The computer instruction in non-transitory computer-readable memory is stored up to be effected or carried out.Standard volume can be used in the method
Journey technology-includes that the non-transitory computer-readable storage media configured with computer program is realized in computer program,
In configured in this way storage medium computer is operated in a manner of specific and is predefined --- according in a particular embodiment
The method and attached drawing of description.Each program can with the programming language of level process or object-oriented come realize with department of computer science
System communication.However, if desired, the program can be realized with compilation or machine language.Under any circumstance, which can be volume
The language translated or explained.In addition, the program can be run on the specific integrated circuit of programming for this purpose.
In addition, the operation of process described herein can be performed in any suitable order, unless herein in addition instruction or
Otherwise significantly with contradicted by context.Process described herein (or modification and/or combination thereof) can be held being configured with
It executes, and is can be used as jointly on the one or more processors under the control of one or more computer systems of row instruction
The code (for example, executable instruction, one or more computer program or one or more application) of execution, by hardware or its group
It closes to realize.The computer program includes the multiple instruction that can be performed by one or more processors.
Further, the method can be realized in being operably coupled to suitable any kind of computing platform, wrap
Include but be not limited to PC, mini-computer, main frame, work station, network or distributed computing environment, individual or integrated
Computer platform or communicated with charged particle tool or other imaging devices etc..Each aspect of the present invention can be to deposit
The machine readable code on non-transitory storage medium or equipment is stored up to realize no matter be moveable or be integrated to calculating
Platform, such as hard disk, optical reading and/or write-in storage medium, RAM, ROM, so that it can be read by programmable calculator, when
Storage medium or equipment can be used for configuration and operation computer to execute process described herein when being read by computer.This
Outside, machine readable code, or part thereof can be transmitted by wired or wireless network.When such media include combining microprocessor
Or other data processors realize steps described above instruction or program when, invention as described herein including these and other not
The non-transitory computer-readable storage media of same type.When dynamic self-adapting load-balancing method according to the present invention and
When technology programs, the invention also includes computers itself.
Computer program can be applied to input data to execute function as described herein, to convert input data with life
At storing to the output data of nonvolatile memory.Output information can also be applied to one or more output equipments as shown
Device.In the preferred embodiment of the invention, the data of conversion indicate physics and tangible object, including the object generated on display
Reason and the particular visual of physical objects are described.
The above, only presently preferred embodiments of the present invention, the invention is not limited to above embodiment, as long as
It reaches technical effect of the invention with identical means, all within the spirits and principles of the present invention, any modification for being made,
Equivalent replacement, improvement etc., should be included within the scope of the present invention.Its technical solution within the scope of the present invention
And/or embodiment can have a variety of different modifications and variations.
Claims (10)
1. a kind of dynamic self-adapting load-balancing method, which is characterized in that the described method comprises the following steps:
Received web request is analyzed, different by request content realize classification, to every a kind of request binding Dynamic Weights
To quantify request, the Dynamic Weights are requested long to the occupancy of server resource and request service time for real-time representation
It is short;
Collect and calculate the request total amount and real-time factor of wait-for-response in each server;
Total request amount of Servers-all is calculated, and judges whether total request amount is more than preset request threshold value;
Refuse to receive request if total request amount is more than request threshold value, otherwise receives request and according to the real-time performance of each server
Index forwarding request.
2. dynamic self-adapting load-balancing method according to claim 1, it is characterised in that: the real-time factor packet
Include CPU usage, cpu busy percentage, disk available space, memory and I/O utilization rate, network broadband occupation rate.
3. dynamic self-adapting load-balancing method according to claim 1, it is characterised in that: by each server
Probe program is installed, to obtain the real-time factor of respective server.
4. dynamic self-adapting load-balancing method according to claim 3, it is characterised in that: the probe program is according to setting
Determine frequency and issue performance indicator acquisition instructions, grab and feeds back corresponding real-time factor.
5. a kind of dynamic self-adapting SiteServer LBS, including scheduler and server cluster connected to it, which is characterized in that
The scheduler includes:
Weight classification binding module is classified for analyzing received web request by different realize of request content, right
To quantify to request, the Dynamic Weights account for server resource for real-time representation request every a kind of request binding Dynamic Weights
With rate and request service time length;
Server state acquisition module, request total amount and real-time performance for collecting and calculating wait-for-response in each server refer to
Mark;
Access forwarding module for calculating total request amount of Servers-all, and judges whether total request amount is more than preset ask
Seek threshold value;Refuse to receive request if total request amount is more than request threshold value, otherwise receives request and according to the real-time of each server
Performance indicator forwarding request.
6. dynamic self-adapting SiteServer LBS according to claim 5, which is characterized in that the server state acquisition
Module includes:
Server request amount acquisition module, for collecting and acquiring the request total amount of wait-for-response in each server;
Real-time factor acquisition module, for acquiring the real-time factor of each server;The real-time factor includes
CPU usage, cpu busy percentage, disk available space, memory and I/O utilization rate, network broadband occupation rate.
7. dynamic self-adapting SiteServer LBS according to claim 5, which is characterized in that the real-time factor is adopted
Collecting module includes:
Probe monitoring modular is installed on the real-time factor that respective server is obtained in each server;
Receiving module is installed on the real-time factor that server feedback is received in scheduler.
8. dynamic self-adapting SiteServer LBS according to claim 5, which is characterized in that the probe monitoring modular packet
It includes:
Timing trigger module, for making probe program issue performance indicator acquisition instructions according to setpoint frequency, grabbing and feeding back phase
The real-time factor answered.
9. a kind of computer installation, can run on a memory and on a processor including memory, processor and storage
Computer program, it is characterised in that: the processor realizes side according to any one of claims 1-4 when executing described program
Method.
10. a kind of computer readable storage medium, stores computer program thereon, it is characterised in that: the computer program
Method according to any of claims 1-4 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910119364.4A CN109769031A (en) | 2019-02-18 | 2019-02-18 | A kind of dynamic self-adapting load-balancing method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910119364.4A CN109769031A (en) | 2019-02-18 | 2019-02-18 | A kind of dynamic self-adapting load-balancing method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109769031A true CN109769031A (en) | 2019-05-17 |
Family
ID=66456852
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910119364.4A Pending CN109769031A (en) | 2019-02-18 | 2019-02-18 | A kind of dynamic self-adapting load-balancing method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109769031A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110417888A (en) * | 2019-07-30 | 2019-11-05 | 中国工商银行股份有限公司 | Flow control methods, volume control device and electronic equipment |
CN112988160A (en) * | 2021-03-15 | 2021-06-18 | 深圳市慧为智能科技股份有限公司 | Server compiling method, device, equipment and computer readable storage medium |
CN113765964A (en) * | 2020-08-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method and device for distributing services of distributed system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102244809A (en) * | 2011-06-22 | 2011-11-16 | 中兴通讯股份有限公司 | Method and device for processing service requests of set top box (Set Top Box) |
CN102420867A (en) * | 2011-12-01 | 2012-04-18 | 浪潮电子信息产业股份有限公司 | Cluster storage entry resolution method based on real-time load balancing mechanism |
CN103338228A (en) * | 2013-05-30 | 2013-10-02 | 江苏大学 | Cloud calculating load balancing scheduling algorithm based on double-weighted least-connection algorithm |
CN103713956A (en) * | 2014-01-06 | 2014-04-09 | 山东大学 | Method for intelligent weighing load balance in cloud computing virtualized management environment |
CN106572170A (en) * | 2016-10-28 | 2017-04-19 | 中国电子科技集团公司第五十四研究所 | Controller and dynamic load balancing method under SDN hierarchical multiple controllers |
CN106657379A (en) * | 2017-01-06 | 2017-05-10 | 重庆邮电大学 | Implementation method and system for NGINX server load balancing |
CN109032801A (en) * | 2018-07-26 | 2018-12-18 | 郑州云海信息技术有限公司 | A kind of request scheduling method, system and electronic equipment and storage medium |
-
2019
- 2019-02-18 CN CN201910119364.4A patent/CN109769031A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102244809A (en) * | 2011-06-22 | 2011-11-16 | 中兴通讯股份有限公司 | Method and device for processing service requests of set top box (Set Top Box) |
CN102420867A (en) * | 2011-12-01 | 2012-04-18 | 浪潮电子信息产业股份有限公司 | Cluster storage entry resolution method based on real-time load balancing mechanism |
CN103338228A (en) * | 2013-05-30 | 2013-10-02 | 江苏大学 | Cloud calculating load balancing scheduling algorithm based on double-weighted least-connection algorithm |
CN103713956A (en) * | 2014-01-06 | 2014-04-09 | 山东大学 | Method for intelligent weighing load balance in cloud computing virtualized management environment |
CN106572170A (en) * | 2016-10-28 | 2017-04-19 | 中国电子科技集团公司第五十四研究所 | Controller and dynamic load balancing method under SDN hierarchical multiple controllers |
CN106657379A (en) * | 2017-01-06 | 2017-05-10 | 重庆邮电大学 | Implementation method and system for NGINX server load balancing |
CN109032801A (en) * | 2018-07-26 | 2018-12-18 | 郑州云海信息技术有限公司 | A kind of request scheduling method, system and electronic equipment and storage medium |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110417888A (en) * | 2019-07-30 | 2019-11-05 | 中国工商银行股份有限公司 | Flow control methods, volume control device and electronic equipment |
CN113765964A (en) * | 2020-08-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method and device for distributing services of distributed system |
CN112988160A (en) * | 2021-03-15 | 2021-06-18 | 深圳市慧为智能科技股份有限公司 | Server compiling method, device, equipment and computer readable storage medium |
CN112988160B (en) * | 2021-03-15 | 2022-04-19 | 深圳市慧为智能科技股份有限公司 | Server compiling method, device, equipment and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108764863B (en) | Data transfer method, device, server and storage medium | |
CN112162865B (en) | Scheduling method and device of server and server | |
Huang et al. | Resource prediction based on double exponential smoothing in cloud computing | |
Salot | A survey of various scheduling algorithm in cloud computing environment | |
Bi et al. | Dynamic provisioning modeling for virtualized multi-tier applications in cloud data center | |
JP3959516B2 (en) | Network system, CPU resource provider, client device, processing service providing method, and program | |
US20160224392A1 (en) | Load balancing using improved component capacity estimation | |
CN109769031A (en) | A kind of dynamic self-adapting load-balancing method and system | |
CN106156115B (en) | A kind of resource regulating method and device | |
CN109144724A (en) | A kind of micro services resource scheduling system and method | |
CN103927229A (en) | Scheduling Mapreduce Jobs In A Cluster Of Dynamically Available Servers | |
CN109819047B (en) | Mobile edge computing resource allocation method based on incentive mechanism | |
CN103995735A (en) | Device and method for scheduling working flow | |
CN109543890A (en) | Power grid based on load estimation equilibrium takes control Optimization Scheduling, apparatus and system | |
CN109075988A (en) | Task schedule and resource delivery system and method | |
CN110264039A (en) | A kind of generation method and equipment of working report | |
CN109478973A (en) | For task schedule, the SDN controller of resource granting and service offer, system and method | |
CN102868573A (en) | Method and device for Web service load cloud test | |
Tuli et al. | GOSH: Task scheduling using deep surrogate models in fog computing environments | |
Wang et al. | Lube: Mitigating bottlenecks in wide area data analytics | |
Tang et al. | Data-aware resource scheduling for multicloud workflows: A fine-grained simulation approach | |
CN115269108A (en) | Data processing method, device and equipment | |
CN113051060A (en) | GPU dynamic scheduling method and device based on real-time load and electronic equipment | |
CN105260245B (en) | A kind of resource regulating method and device | |
CN106844175B (en) | A kind of cloud platform method for planning capacity based on machine learning |
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: 20190517 |
|
RJ01 | Rejection of invention patent application after publication |