CN109819050A - SiteServer LBS and method between multiserver - Google Patents

SiteServer LBS and method between multiserver Download PDF

Info

Publication number
CN109819050A
CN109819050A CN201910171986.1A CN201910171986A CN109819050A CN 109819050 A CN109819050 A CN 109819050A CN 201910171986 A CN201910171986 A CN 201910171986A CN 109819050 A CN109819050 A CN 109819050A
Authority
CN
China
Prior art keywords
load
classification
task
server
task requests
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
Application number
CN201910171986.1A
Other languages
Chinese (zh)
Inventor
杜小芳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Huaan Putt Network Technology Co Ltd
Original Assignee
Beijing Huaan Putt Network Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Huaan Putt Network Technology Co Ltd filed Critical Beijing Huaan Putt Network Technology Co Ltd
Priority to CN201910171986.1A priority Critical patent/CN109819050A/en
Publication of CN109819050A publication Critical patent/CN109819050A/en
Pending legal-status Critical Current

Links

Landscapes

  • Data Exchanges In Wide-Area Networks (AREA)
  • Computer And Data Communications (AREA)

Abstract

The invention discloses the SiteServer LBSs and method between multiserver, are related to server load balancing field.The present invention includes: Classification Management processor, several load allocation processing devices and several processing servers;The Classification Management server is connect with several load allocation processing devices respectively;The load allocation processing device is connect with several processing servers respectively;It include classification of task module in the Classification Management processor;The load allocation processing device further includes monitoring distribution module.Task requests are sorted out according to different type by Classification Management processor and are assigned to the load allocation processing device of corresponding types by the present invention, the classification processing for realizing different types of task requests, load imbalance, processing facilitate the quick processing of task requests, improve the treatment effeciency of task requests when multiprocessor being avoided to handle task requests.

Description

SiteServer LBS and method between multiserver
Technical field
The invention belongs to server load balancing field, more particularly between multiserver SiteServer LBS and Method.
Background technique
In order to solve the imbalance problem of network service processing, network communication technology is from one-node network server One-to-many framework migrates to the multi-to-multi framework of clustering, multiserver, extends network throughput and bandwidth, to realize Inexpensively, efficiently, reliable network service capabilities.
Multiserver framework in the application can there are the following problems: under the network architecture of multiserver, due to server Connection is different, and different server will receive different task requests, this server resulted in is in high load, even super negative Carrying row, and some servers are in low-load or idle state, network equipment resource is not effectively utilized.
The present invention provides a kind of computer network load-balancing method, is dedicated to the task of the multiserver processing network equipment The problem that load when request is uneven, treatment effeciency is lower.
Summary of the invention
The purpose of the present invention is to provide the SiteServer LBSs and method between multiserver, pass through Classification Management processor Task requests are sorted out to according to different type and are assigned to the load allocation processing device of corresponding types, load allocation processing device is successively Task requests in task requests pond are assigned to alignment processing server according to load capacity from high to low, realize different type Task requests classification processing and same type of task requests using corresponding types processing server handle, improve The treatment effeciencies of task requests, load when solving existing multiserver processing task requests is uneven, treatment effeciency compared with Low problem.
In order to solve the above technical problems, the present invention is achieved by the following technical solutions:
SiteServer LBS of the present invention between multiserver, comprising: Classification Management processor, several load allocation processings Device and several processing servers;
The Classification Management server is connect with several load allocation processing devices respectively;The load allocation processing device difference It is connect with several processing servers;
It include classification of task module in the Classification Management processor;What the classification of task module was used to receive appoints Uniquely tagged and type mark is arranged according to classification of type and for task requests in business;The classification of task module is also by task requests Uniquely tagged and type mark storage in task information table;The classification of task module is real-time by the task requests of same type It is transmitted to the load allocation processing device of corresponding types;
The task that setting task requests pond is used to store the transmitting of Classification Management server in the load allocation processing device is asked It asks;The load allocation processing device further includes monitoring distribution module;The monitoring distribution module receives processing server transmitting Server load information is simultaneously stored into load information table;
The processing server timing transmits load information to corresponding load allocation processing device;The load information includes Request task waiting number and cpu busy percentage;The load information that the monitoring distribution module compares each processing server will appoint Task requests in business request pond distribute to processing server one by one.
Preferably, the task requests allocation rule in the task requests pond is according to the advanced sequence first handled.
Preferably, when the load allocation processing device is connect with Classification Management processor, the load allocation processing device to Classification Management processor transmitting management registration information is registered;The management registration information includes with loading classification processor IP Location and load classification processor type mark;The type mark pair of load the classification processor type mark and task requests It answers;The classification of task module distributes task requests to corresponding load classification processor, is in the mission bit stream table Task requests addition load classification processor IP address.
Preferably, when the processing server is connected to the load allocation processing device, the processing server is to load Allocation processing device sends distribution registration information;The distribution registration information includes processing server IP address as processing server Unique identification;The monitoring distribution module storage processing server IP is into load information table.
Preferably, the monitoring distribution module calculates the load capacity of each processing server according to server load information;Institute It states monitoring distribution module and is sorted according to load capacity to the processing server IP in load information table;The processing server timing passes After passing server load information, the load distribution module all recalculates the load capacity of alignment processing server and takes to processing Business device IP rearrangement;
The computation rule of the load capacity is as follows:
Load capacity=task waiting number * waits weight+cpu busy percentage * CPU weight.
Load-balancing method between multiserver specifically includes following process:
Step 1: classifying for request task and establishes company of the Classification Management server respectively with several load allocation processing devices It connects;
Step 2: confirmation various types of processors number simultaneously establishes the load allocation processing device company with several processing servers respectively It connects;
Step 3: the classification of task module is task requests classification setting uniquely tagged and type mark and storage is taken office It is engaged in information table;
Step 4: task requests are assigned to the load allocation processing device of corresponding types by the classification of task module;
Step 5: the monitoring distribution module divides the task requests in process pool according to the load capacity of each processing server It is fitted on processing server.
The invention has the following advantages:
1, task requests are sorted out according to different type by Classification Management processor and are assigned to corresponding types by the present invention Load allocation processing device, realize the classification processing of different types of task requests, avoid multiprocessor handle task requests When load imbalance, processing facilitate the quick processing of task requests, improve the treatment effeciency of task requests.
2, the present invention is handled by same type of task requests using the processing server of corresponding types, while being loaded and being divided Task requests in task requests pond are distributed to module according to the size of the load capacity of processing server each processing clothes one by one Business device avoids the occurrence of the case where processing server overload loads appearance, improves the treatment effeciency of task requests.
Certainly, it implements any of the products of the present invention and does not necessarily require achieving all the advantages described above at the same time.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will be described below to embodiment required Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached Figure.
SiteServer LBS structural schematic diagram of the Fig. 1 between multiserver of the invention;
The flow chart of load-balancing method of the Fig. 2 between multiserver of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts all other Embodiment shall fall within the protection scope of the present invention.
Specific embodiment one:
Refering to Figure 1, SiteServer LBS of the present invention between multiserver, comprising: if Classification Management processor, Dry load allocation processing device and several processing servers;
Classification Management server is connect with several load allocation processing devices respectively;Load allocation processing device respectively with several places Manage server connection;
It include classification of task module in Classification Management processor;Classification of task module is used for received task according to class Type classifies and is task requests setting uniquely tagged and type mark;Classification of task module also by the uniquely tagged of task requests and In type mark storage to task information table;Classification of task module is by the task requests real-time transmission of same type to corresponding types Load allocation processing device;
Setting task requests pond is used to store the task requests of Classification Management server transmitting in load allocation processing device;It is negative Carrying allocation processing device further includes monitoring distribution module;Monitor the server load information that distribution module receives processing server transmitting And it stores into load information table;
Processing server timing transmits load information to corresponding load allocation processing device;Load information includes request task Waiting number and cpu busy percentage;The load information that monitoring distribution module compares each processing server will be in task requests pond Task requests distribute to processing server one by one.
Wherein, the task requests allocation rule in task requests pond is according to the advanced sequence first handled.
Wherein, load allocation processing device is with Classification Management processor when connecting, and loads allocation processing device at Classification Management Reason device transmitting management registration information is registered;Managing registration information includes load classification processor IP address and load classification Processor type label;It is corresponding with the type mark of task requests to load classification processor type mark;Classification of task module will Task requests are distributed to corresponding load classification processor, are task requests addition load classification processor in task information table IP address.
Wherein, when processing server is connected to load allocation processing device, processing server is sent to load allocation processing device Distribute registration information;Distributing registration information includes processing server IP address as processing server unique identification;Monitoring point With module storage processing server IP into load information table.
Wherein, monitoring distribution module calculates the load capacity of each processing server according to server load information;Monitoring distribution Module sorts to the processing server IP in load information table according to load capacity;Processing server timing delivery server load letter After breath, load distribution module all recalculates the load capacity of alignment processing server and resequences to processing server IP;
The computation rule of load capacity is as follows:
Load capacity=task waiting number * waits weight+cpu busy percentage * CPU weight.
Load-balancing method between multiserver specifically includes following process:
Step 1: classifying for request task and establishes company of the Classification Management server respectively with several load allocation processing devices It connects;
Step 2: confirmation various types of processors number simultaneously establishes the load allocation processing device company with several processing servers respectively It connects;
Step 3: classification of task module is task requests classification setting uniquely tagged and type mark and stores to task letter It ceases in table;
Step 4: task requests are assigned to the load allocation processing device of corresponding types by classification of task module;
Step 5: the task requests in process pool are assigned to by monitoring distribution module according to the load capacity of each processing server Processing server.
It is worth noting that, included each unit is only drawn according to function logic in the above system embodiment Point, but be not limited to the above division, as long as corresponding functions can be realized;In addition, each functional unit is specific Title is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
In addition, those of ordinary skill in the art will appreciate that realizing all or part of the steps in the various embodiments described above method It is that relevant hardware can be instructed to complete by program, corresponding program can store to be situated between in a computer-readable storage In matter.
Present invention disclosed above preferred embodiment is only intended to help to illustrate the present invention.There is no detailed for preferred embodiment All details are described, are not limited the invention to the specific embodiments described.Obviously, according to the content of this specification, It can make many modifications and variations.These embodiments are chosen and specifically described to this specification, is in order to better explain the present invention Principle and practical application, so that skilled artisan be enable to better understand and utilize the present invention.The present invention is only It is limited by claims and its full scope and equivalent.

Claims (6)

1. the SiteServer LBS between multiserver characterized by comprising at Classification Management processor, several load distribution Manage device and several processing servers;
The Classification Management server is connect with several load allocation processing devices respectively;If the load allocation processing device respectively with The connection of dry-cure server;
It include classification of task module in the Classification Management processor;The classification of task module is for pressing received task According to classification of type and for task requests, uniquely tagged and type mark are set;The classification of task module also by task requests only In one label and type mark storage to task information table;The classification of task module is by the task requests real-time transmission of same type To the load allocation processing device of corresponding types;
Setting task requests pond is used to store the task requests of Classification Management server transmitting in the load allocation processing device;Institute Stating load allocation processing device further includes monitoring distribution module;The monitoring distribution module receives the server of processing server transmitting Load information is simultaneously stored into load information table;
The processing server timing transmits load information to corresponding load allocation processing device;The load information includes request Task waiting number and cpu busy percentage;The load information that the monitoring distribution module compares each processing server asks task The task requests in pond are asked to distribute to processing server one by one.
2. the SiteServer LBS between multiserver according to claim 1, which is characterized in that in the task requests pond Task requests allocation rule according to the advanced sequence first handled.
3. the SiteServer LBS between multiserver according to claim 1, which is characterized in that the load allocation processing When device is connect with Classification Management processor, the load allocation processing device to Classification Management processor transmit management registration information into Row registration;The management registration information includes load classification processor IP address and load classification processor type mark;Institute It is corresponding with the type mark of task requests to state load classification processor type mark;The classification of task module divides task requests It is that task requests are added with loading classification processor IP in the mission bit stream table after being assigned to corresponding load classification processor Location.
4. the SiteServer LBS between multiserver according to claim 1, which is characterized in that the processing server to When the load allocation processing device connects, the processing server sends distribution registration information to load allocation processing device;It is described Distributing registration information includes processing server IP address as processing server unique identification;The monitoring distribution module storage Processing server IP is into load information table.
5. the SiteServer LBS between multiserver according to claim 1, which is characterized in that the monitoring distribution module The load capacity of each processing server is calculated according to server load information;The monitoring distribution module believes load according to load capacity Cease the processing server IP sequence in table;After the processing server timing delivery server load information, the load distribution Module all recalculates the load capacity of alignment processing server and resequences to processing server IP;
The computation rule of the load capacity is as follows:
Load capacity=task waiting number * waits weight+cpu busy percentage * CPU weight.
6. the load-balancing method between multiserver as described in claim 1-5 is any one, which is characterized in that specifically include as Lower process:
Step 1: classifying for request task and establishes connection of the Classification Management server respectively with several load allocation processing devices;
Step 2: confirmation various types of processors number simultaneously establishes the load allocation processing device connection with several processing servers respectively;
Step 3: the classification of task module is task requests classification setting uniquely tagged and type mark and stores to task letter It ceases in table;
Step 4: task requests are assigned to the load allocation processing device of corresponding types by the classification of task module;
Step 5: the task requests in process pool are assigned to by the monitoring distribution module according to the load capacity of each processing server Processing server.
CN201910171986.1A 2019-03-07 2019-03-07 SiteServer LBS and method between multiserver Pending CN109819050A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910171986.1A CN109819050A (en) 2019-03-07 2019-03-07 SiteServer LBS and method between multiserver

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910171986.1A CN109819050A (en) 2019-03-07 2019-03-07 SiteServer LBS and method between multiserver

Publications (1)

Publication Number Publication Date
CN109819050A true CN109819050A (en) 2019-05-28

Family

ID=66608476

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910171986.1A Pending CN109819050A (en) 2019-03-07 2019-03-07 SiteServer LBS and method between multiserver

Country Status (1)

Country Link
CN (1) CN109819050A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117176592A (en) * 2023-09-04 2023-12-05 广州佳新智能科技有限公司 Multi-bank link artificial intelligent gateway processing method, system, medium and equipment

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7600229B1 (en) * 2003-09-30 2009-10-06 Emc Corporation Methods and apparatus for load balancing processing of management information
CN102932271A (en) * 2012-11-27 2013-02-13 无锡城市云计算中心有限公司 Method and device for realizing load balancing
CN104065745A (en) * 2014-07-07 2014-09-24 电子科技大学 Cloud computing dynamic resource scheduling system and method
CN104657221A (en) * 2015-03-12 2015-05-27 广东石油化工学院 Multi-queue peak-alternation scheduling model and multi-queue peak-alteration scheduling method based on task classification in cloud computing
CN105141541A (en) * 2015-09-23 2015-12-09 浪潮(北京)电子信息产业有限公司 Task-based dynamic load balancing scheduling method and device
CN106161552A (en) * 2015-04-16 2016-11-23 国家电网公司 Load-balancing method and system under a kind of mass data environment
CN106657379A (en) * 2017-01-06 2017-05-10 重庆邮电大学 Implementation method and system for NGINX server load balancing

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7600229B1 (en) * 2003-09-30 2009-10-06 Emc Corporation Methods and apparatus for load balancing processing of management information
CN102932271A (en) * 2012-11-27 2013-02-13 无锡城市云计算中心有限公司 Method and device for realizing load balancing
CN104065745A (en) * 2014-07-07 2014-09-24 电子科技大学 Cloud computing dynamic resource scheduling system and method
CN104657221A (en) * 2015-03-12 2015-05-27 广东石油化工学院 Multi-queue peak-alternation scheduling model and multi-queue peak-alteration scheduling method based on task classification in cloud computing
CN106161552A (en) * 2015-04-16 2016-11-23 国家电网公司 Load-balancing method and system under a kind of mass data environment
CN105141541A (en) * 2015-09-23 2015-12-09 浪潮(北京)电子信息产业有限公司 Task-based dynamic load balancing scheduling method and device
CN106657379A (en) * 2017-01-06 2017-05-10 重庆邮电大学 Implementation method and system for NGINX server load balancing

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
马原龙: "《Nginx负载均衡技术研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117176592A (en) * 2023-09-04 2023-12-05 广州佳新智能科技有限公司 Multi-bank link artificial intelligent gateway processing method, system, medium and equipment
CN117176592B (en) * 2023-09-04 2024-03-01 广州佳新智能科技有限公司 Multi-bank link artificial intelligent gateway processing method, system, medium and equipment

Similar Documents

Publication Publication Date Title
CN103237045B (en) Parallel processing system and parallel processing method for large-scale real-time traffic data
CN103067293B (en) Method and system for multiplex and connection management of a load balancer
CN107025139A (en) A kind of high-performance calculation Scheduling Framework based on cloud computing
CN101977236B (en) Large-file multipoint distribution system
CN101951411A (en) Cloud scheduling system and method and multistage cloud scheduling system
JP2005539298A (en) Method and system for remotely and dynamically configuring a server
CN108337275A (en) Task distribution method, device and equipment for Distributor
CN102137128A (en) Method and device for balancing load of cluster service
CN104426800A (en) System and method for managing message queues in a peer-to-peer communication network
CN102724132B (en) Method and device for improving transmission control protocol (TCP) connection multiplexing processing efficiency
CN109558446A (en) Job request method, apparatus, electronic equipment and storage medium
CN109800120B (en) Monitoring system of server group of remote education system
CN102571568A (en) Method and device for processing task
CN113014611A (en) Load balancing method and related equipment
CN105100277A (en) Software inspection method, device and system
CN107197039B (en) A kind of PAAS platform service packet distribution method and system based on CDN
CN109491895A (en) Server stress test method and device
CN109819050A (en) SiteServer LBS and method between multiserver
CN108471435A (en) A kind of distributed background service system and method based on Self-help vending machine
CN104731660B (en) data distributing method, device and system
CN106570011B (en) Distributed crawler URL seed distribution method, scheduling node and capturing node
CN107071020A (en) Load balancing framework applied to cloud computing server
CN105872082A (en) Fine-grained resource response system based on load balancing algorithm of container cluster
CN108512761A (en) File transmission dispatching method, management platform, request platform and storage medium
CN103747439B (en) Wireless controller equipment, wireless authentication processing method, system, networking

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20190528