CN109800120A - A kind of monitoring system of the server zone of long-distance educational system - Google Patents
A kind of monitoring system of the server zone of long-distance educational system Download PDFInfo
- Publication number
- CN109800120A CN109800120A CN201711142005.8A CN201711142005A CN109800120A CN 109800120 A CN109800120 A CN 109800120A CN 201711142005 A CN201711142005 A CN 201711142005A CN 109800120 A CN109800120 A CN 109800120A
- Authority
- CN
- China
- Prior art keywords
- server
- monitoring
- processing
- processing server
- network
- 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 229
- 238000012545 processing Methods 0.000 claims abstract description 324
- 230000002159 abnormal effect Effects 0.000 claims abstract description 10
- 230000006854 communication Effects 0.000 claims description 63
- 238000004891 communication Methods 0.000 claims description 62
- 239000003795 chemical substances by application Substances 0.000 claims description 30
- 238000000034 method Methods 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 19
- 230000005540 biological transmission Effects 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 230000000737 periodic effect Effects 0.000 claims description 4
- 238000007726 management method Methods 0.000 description 44
- 238000005516 engineering process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000001816 cooling Methods 0.000 description 3
- 230000007812 deficiency Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 108010028984 3-isopropylmalate dehydratase Proteins 0.000 description 1
- 206010048669 Terminal state Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
-
- 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
- H04L69/40—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection
Abstract
The present invention relates to a kind of monitoring systems of the server zone of long-distance educational system, including multiple processing servers, the multiple processing server includes Baseboard Management Controller, the monitoring system includes monitoring terminal, which includes the server state real-time monitoring unit that can be connected to the network with the processing server in server zone;The server state real-time monitoring unit of the monitoring terminal is regularly connected to the network with processing server, and requires the Baseboard Management Controller of the processing server to return the current state information of the processing server when discovery and the network connection of processing server are abnormal.System energy initiative baseboard management controller of the invention provides the current state information of its own processing server, allow the manager of the server zone after the server zone is abnormal, in time and the situation of server zone can be well understood, and corresponding measure or disposition can be carried out immediately, and then promote the efficiency of management of server zone.
Description
Technical field
The present invention relates to Internet education technical fields, more particularly to a kind of long-distance education system based on Internet technology
System, relates in particular to a kind of monitoring system of the server zone of long-distance educational system.
Background technique
With the development of science and technology, there is numerous long-distance education products, long-distance education is students and teacher, student
Between educational institution, the forms of education for mainly taking media mode to carry out systematic teaching and write to each other are by course
Send the education of one or more students outside campus to.Modern distance education then refers to through audio, video (live streaming or record
Picture) and Internet technology including real-time and is non real-time course transmission is arrived school outer education.Currently, long-distance education
Among flourishing, it is the important means for solving educational resource, the problems such as educational opportunities are unbalanced, not only enriches religion
Mode also reduces the limitation to teaching place, therefore obtains liking for many students and teacher.
Current remote educational system carries out framework typically with the mode of single machine centralization, in general, using single machine
Centralization long-distance educational system be usually provided with including impart knowledge to students end, one or more study ends, and by network with it is described
The server at teaching end and the communication of one or more of study ends, wherein the server can store teaching resource, processing comes
From the various requests at teaching end or study end, according to from the end or the request distribution and the reception teaching resource that learn end etc. of imparting knowledge to students.
The example of long-distance educational system as single machine centralization, in Chinese invention patent prospectus
A kind of Distance Education Service system Internet-based is disclosed in CN107195212, wherein the Distance Education Service system allusion quotation
Use to type the working principle of single server set Chinese style processing.Specifically comprising Administrator Client, user client
End, cloud server, the Administrator Client includes administrator's login module, instructional video release module, instructional video
Categorization module, administrator's login module are used for registration and administrator's meeting for the administrator's person's of being managed member account
The login of member's account, the instructional video release module are used to issue instructional video, the instructional video hair for administrator
Cloth module is also used to for the instructional video that administrator issues being sent to instructional video categorization module, the instructional video classification mould
Block classifies to instructional video, and sorted instructional video is sent to cloud server, the user client packet
Include user log-in block, video display module, the user log-in block be used to carry out for user the registration of member account with
And the login of member account, the video display module are used to receive the sorted instructional video of cloud server transmission simultaneously
It shows to click for user and check.
Further, it is also disclosed in Chinese invention patent prospectus CN104464412A a kind of using this single machine
The long-distance educational system and its implementation of centralization, wherein the long-distance educational system includes: education terminal, client and service
Device;It educates terminal and client carries out information exchange, server exchanges information by Internet with client.
Continuous with long-distance education is flourished, the teaching end and the number for learning end that various long-distance educational systems are covered
Gauge mould constantly expands, Distance instruction content constantly increases, video file and audio file accounting in curricula
Constantly increasing, these factors all inevitably lead to the data interaction amount based on the Internet transmission, and exponentially rank increases,
It finds in actual use in this case, conventional single machine centralized processing method is in real time data processing and computational efficiency
Aspect has seemed that some are unable to do what one wishes, and the real-time and responsiveness for showing as whole system are unable to get guarantee, thus band
Carry out bad user experience, thereby reduces the business public praise using the operator of the long-distance educational system, and in technology
On constrain the potential market share of operator, this is the actual challenges that there is an urgent need to technically be overcome.
In response to this, common solution is usually the single centralized processing clothes in upgrading remote educational system
Business device, by promoting the performance of centralized processing server come speed up processing.In batches of task requests to the processing time
In the case where of less demanding, this mode can improve the treatment effeciency of system;But if it is very high to processing time requirement, or place
In the very big situation of the data volume of reason, processing requirement has been unable to reach only by processing server performance is promoted.In other words
It says, there is no the places of limited processing capacity and magnanimity that processing server is fundamentally solved in technological layer for this solution
Manage the contradiction of imbalance of supply and demand existing between task requests.
It is by existing single service that another, which can fundamentally solve the above technical problem, promising scheme,
Device replaces with the server zone that can carry out parallel computation, i.e., increases the number of servers of carry out task processing first, then lead to
The artificial mode set or system automatically configures is crossed, batches of task requests to be treated are distributed according to certain rules
Parallel computation processing is carried out to multiple servers.This scheme fundamentally solves problems of the prior art, that is, works as
By when promoting separate unit processing server performance and being unable to satisfy processing and need, more task processing servers can be equipped with to share
The task requests to be processed of separate unit processing server, in processing capacity and meet service application demand on the processing time.
Although this technical solution using server zone have the advantages that it is apparent, also correspondingly there will be with
The lower technical problem for restricting its large-scale application, the i.e. monitoring reliability of server zone.At existing single server set Chinese style
In the long-distance educational system of reason, the complexity of whole system is very low, it is only necessary to which being monitored to individual server can realize
Monitoring to whole system reliability.As the mode for the operating state for monitoring processing server known to one kind, by locating
It manages and configures a Baseboard Management Controller in server, which, which can monitor the integrality of processing server and be recorded in, is
It is read out in system event log (System Event Log, will simply be referred to as SEL below) file for monitoring personnel's timing, Huo Zhechuan
The SEL file is given to check when needing to terminal installation for server managers.As an example, it is disclosed in Chinese invention patent
A kind of long-distance educational system of single server set Chinese style processing is disclosed in specification CN105184498A, including log pipe
Manage module: the log management module records all operations of user, and administrative staff can be inquired all by log management module
Log information;The log information includes: the operation note of user, server monitoring log and server alarm log,
Whereby, the working condition of server in educational system is monitored by the way of the monitoring log for reading processing server.Meanwhile
It is disclosed in Chinese invention patent prospectus CN105868077A and a kind of obtains whole machine cabinet server node monitoring information
Method, wherein the method for the acquisition whole machine cabinet server node monitoring information compared with prior art, simplifies node BMC and section
The communication process of plate in point, plate can once obtain mass data, especially real-time change information from node BMC in node, right
Raising system response time is of great advantage, practical.Further, in Chinese invention patent prospectus CN106844162A
In disclose a kind of storage server cabinet management system and method based on BMC, wherein by the monitoring of Chassis Monitoring module,
According to the status information of monitored device, judges whether status information is abnormal, and exception information is reported to memory module, deposit
Storage module further judges, and order management module issues corresponding action command, realizes the management to monitored device, protects
Cabinet normal operation is demonstrate,proved, the stability of storage server is improved;And it reads the operating status on BMC by IPMI protocol to believe
Breath, compared to based on SES agreement carry out shelf management method, convenient for management, process is simple, reduce management cost and exploitation at
This;Also the process of chassis management module and memory module is linked by IPC, severely subnormal once occurs in stored module judgement
Situation just interrupts the iostream of data, has achieved the purpose that protect data, has improved the reliability of storage server.
In order to reduce the workload of monitoring personnel's reading system event log, by Alibaba Group Holdings Limited
A kind of SOT state of termination based reminding method is disclosed in the Chinese invention patent prospectus CN104464412A of submission and correlation is set
Standby and system knows the state of terminal by sending prompting message to management end on other occasions, and there is no need to special
Industry knowledge you can learn that first terminal state, relative to traditional side for knowing the SOT state of termination by way of checking SEL
It for formula, more easily realizes, this mode can reduce the workload of monitoring personnel to a certain extent.
However, the mode described above for individual server monitoring can not be suitable for having multiple processing servers
Server zone server zone monitoring, this is because externally providing net common for the server zone for including many servers
Network needs the working condition to each server to be monitored when servicing.By taking the server zone comprising 100 servers as an example, such as
Fruit continues to continue to use the monitoring mode for single server, i.e., a monitoring device is arranged to record to each processing server
The mode of log monitors its abnormality.It is apparent that no matter on the hardware cost of the monitoring device required for server zone, also
It is in the workload faced required for monitoring personnel, is all unacceptable.It is obvious that monitoring personnel is difficult to short
The part of record server exception is found in time from the log file contents of magnanimity, and then can not understand in time and exclude event
Hinder the unusual condition of server.In other words, the exactly this upper existing deficiency of server zone monitoring, technically constrains
Large-scale application server zone carries out data processing in long-distance educational system.
It is current remote in consideration of it, how to provide a kind of monitoring system of server zone suitable for long-distance educational system
It is anxious to be resolved that server zone technical application is handled task requests by the research staff of educational system into long-distance educational system
Problem.
Applicant it is hereby stated that, what is stated in above section is only the technology contents that are known of applicant.Above content is only
Provide only the prior art for being related to the relevant background information of the disclosure but not necessarily constituting the application.
Summary of the invention
In order to overcome the deficiencies in the prior art, the present invention provides a kind of server zones of long-distance educational system
Monitoring system, the server zone include multiple processing servers, and the multiple processing server includes Baseboard Management Controller,
Wherein: the monitoring system includes monitoring terminal, which includes that can carry out with the processing server in server zone
The server state real-time monitoring unit of network connection;The server state real-time monitoring unit of the monitoring terminal regularly with
Processing server is connected to the network, and requires the processing server when discovery and the network of processing server are abnormal
Baseboard Management Controller returns the current state information of the processing server.
As a result, by the present invention in that monitoring terminal is regularly connected to the network actively and with the server zone, to survey
It tries the server zone and the situation of network service is externally provided, and the place of network service cannot be provided in discovery server zone presence
When managing server, mentioned by the baseboard management controller of each processing server in the monitoring terminal initiative server zone
For the current state information of its own processing server, allow the manager of the server zone after the server zone is abnormal,
In time and the situation of server zone can be well understood, and corresponding measure or disposition can be carried out immediately, and then promote service
The efficiency of management of device group.
Preferably, wherein multiple processing servers in the server zone have the same of common externally offer network service
Network address, and the Baseboard Management Controller has different network address to each other, the server state real-time monitoring unit
It is according to the Unified Network address of processing server and processing server network connection to test the network service, and according to the master
The network address of board management controller is connected to the network to require Baseboard Management Controller return to work as with the Baseboard Management Controller
Preceding status information.
As a result, server zone according to the present invention by single network address externally provide stable network service and via
Unified port accept the interview request after burden is allocated in server zone again.Meanwhile by with multiple and different networks
The Baseboard Management Controller of address may insure that monitoring terminal can receive the current state letter of each processing server respectively
Breath.
Preferably, the server state real-time monitoring unit include: with Baseboard Management Controller be connected to the network to
A few network input port, Baseboard Management Controller of the network input port to receive at least one processing server
Reported information;And the network input/output port being connected to the network with server zone.
Preferably, the quantity of the network input port is identical as the quantity of the processing server in server zone, each
Network input port is communicated to connect with the Baseboard Management Controller of a processing server respectively.
Monitoring terminal according to the present invention can concurrently receive the mainboard pipe from each processing server simultaneously as a result,
Manage the information report of controller.
Preferably, which further includes at least one monitor agent server, which is configured
Receive the status information of multiple proxy servers connected to it at multiple proxy servers and being configured to are connected to, and will receive
To the status informations of multiple proxy servers be transferred to monitoring terminal, wherein the quantity of the network input port and monitoring generation
The quantity for managing server is identical, and each network input port is communicatively coupled with a monitor agent server respectively.
The quantity for monitoring the network input port in terminal in this scenario as a result, only needs to be set as to take with monitor agent
The quantity of business device is consistent, thus greatly reduces the hardware requirement and cost of monitor terminal.At the same time, due to reducing
The number of servers being directly communicatively coupled with monitoring terminal, if the return so as to avoid processing server simultaneous transmission is believed
The problem of processing of monitor terminal caused by breath is too many is not in time or the processor of monitoring terminal overloads, so that even if reducing monitoring
The processing speed of terminal also can satisfy the normal monitoring of server zone.
Preferably, the monitor agent server include the information input unit successively communicated to connect, data buffer storage pond,
Information output unit and the control unit communicated to connect respectively with information input unit, data buffer storage pond, information output unit,
Wherein the information input unit receives the status information from processing server connected to it and is transferred to the status information
Data buffer storage pond, described control unit are used to carry out priority to the status information of multiple processing servers in data cache pool
Sequence, and the status information after sequence is transferred to monitoring terminal in an orderly manner via information output unit.
Thereby, it is possible to be ranked up the status information of multiple processing servers to handle and preferentially send to be most likely to occur event
The status information of the processing server of barrier can further increase monitoring eventually compared with multiple processing servers are returned simultaneously
Hold the identification and response speed to the processing server to break down.
Preferably, which includes queue and local data base, which is configurable for multiple places that sort
The status information of server is managed, which is configured in status information and is not yet transferred to before monitoring terminal temporarily
When store the status information, wherein described control unit is according to the average time between failures and server of multiple proxy servers
Reliability index in queue status information carry out priority ranking.
Preferably, which further includes being made of multiple processing servers in server zone with common output
The monitoring server group of port, the common output end mouth are configured as the status information of output failed server, wherein described
The quantity of network input port is identical as the quantity of monitoring server group, and each network input port is supervised with a server respectively
The common output end mouth of survey group is communicatively coupled.
Each processing server in server zone is divided into multiple monitoring groups with common output end mouth as a result,
To reduce the quantity and processing requirement of the network input port for monitoring terminal.
Preferably, it all has in each processing server that same monitoring server is concentrated and is communicated with Baseboard Management Controller
The wireless communication unit of connection, each Baseboard Management Controller all have setting unit, monitoring unit and status information output section, this sets
Portion is set for family and communication in the title of the processing server subordinate server monitoring group and the communication of the processing server to be arranged
The player whose turn comes next, the wireless communication unit includes emission part and receiving portion, wherein the emission part of each processing server and receiving portion quilt
It is configured to communicate with family and communication player whose turn comes next's communication, to form complete closed-loop communication chain in the monitoring group.
Each processing server in server zone spatially this advantageous item of compact Layout is taken full advantage of as a result,
Part, by the way that closed data link is formed using the short distance wireless communication technology between each processing server, into
And multiple processing servers are combined into the monitoring server group with common output end mouth and are monitored.
Preferably, whether the status information that the monitoring unit is configurable for determination processing server exceeds state threshold
Value issues to wireless communication unit when exceeding state threshold and stops transmitting and receive the instruction of information to make the closed loop
Communication chain disconnects, and the common output end mouth issues instruction to the processing server in closed-loop communication chain cut-off point, so that its
Affiliated status information output section sends the status information of the mainboard controller belonging to it to the common output end mouth and via altogether
Monitoring terminal is transmitted to output port.
Preferably, wherein the server zone further includes being connect with multiple processing servers by transmission control protocol data
Allocation unit, wherein the allocation unit for establish allocation matrix with dynamically manage the management in idle time on each processing server into
Number of passes;The whether pending task requests of allocation unit periodic monitor, if so, then, in inspection allocation matrix respectively handling
The management in idle time process number of server, waiting task, then is distributed to idle processing by idle processing server if it exists
Server.
As a result, by being equipped with allocation unit and multiple processing servers, by allocation unit automatically by batches of task point
The each processing server of dispensing reaches processing capacity and handles temporal requirement.Therefore server zone can made full use of
In processing server, accomplish there are a large amount of access requests it is timely, quickly handle batches of task
Detailed description of the invention
Additional technical characteristic of the invention and beneficial effect, will with reference to the following drawings shown in embodiment and it is clear
Present to Chu, in which:
Fig. 1 is the general frame figure of long-distance educational system according to the present invention;
Fig. 2 is the architecture diagram of the first embodiment of monitoring system according to the present invention;
Fig. 3 is the work flow diagram of the monitoring system in Fig. 2;
Fig. 4 is the architecture diagram of the second embodiment of monitoring system according to the present invention;
Fig. 5 is the architecture diagram of the server of the 3rd embodiment of monitoring system according to the present invention;And
Fig. 6 is the architecture diagram of the 3rd embodiment of monitoring system according to the present invention.
Reference signs list
1 processing server group, 101 allocation unit 11 (a) processing server 12 (a) processing server 13 (a) processing clothes
Business 3 network port of device 14 (a) processing server 15 processing server, 2 user terminal, 4 Baseboard Management Controller 41EWS interface
42 monitoring unit, 43 setting unit, 44 status information output section 5 monitors 51 server state real-time monitoring unit 5a network of terminal
61 proxy server of input/output end port 5b network input port, 62 proxy server 61a information input unit 61b number
According to 71 common output end mouth of cache pool 61c information output unit 61d 7 processing server group of control unit, 8 wireless telecommunications list
82 receiving portion of first 81 emission part
Specific embodiment
Below in conjunction with attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that institute
The embodiment of description is only a part of the embodiment of the present invention, instead of all the embodiments.Usually described in attached drawing here
It can arrange and design with a variety of different configurations with the component of the embodiment of the present invention shown.Therefore, below in attached drawing
The detailed description of the embodiment of the present invention of middle offer is not intended to limit the range of claimed invention, but only table
Show selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not making creative work
Under the premise of every other embodiment obtained, shall fall within the protection scope of the present invention.
As shown in Fig. 1, it is disclosed that the general frame schematic diagram of long-distance educational system according to the present invention, wherein
In attached drawing 1, the function and mutual technology correlation of each functional module are indicated with the figure of component.As shown in Fig. 1,
In the long-distance educational system include: processing server group 1, wherein processing server group 1 include multiple processing server 11-
14,11a-14a etc. can make in the present invention according to task requests amount to be processed how much come the quantity of setting processing server
Not limit an example of the present invention, processing server group 1 has 40 processing servers in the present invention, for simplicity
For the sake of, part processing server is schematically shown only in fig. 1.
In the present invention, in order to enable multiple processing servers in server zone 1 externally to provide network service jointly
(such as, but not limited to provide a teaching website operated for the user in user terminal 2), in processing server group 1
The network port of multiple processing servers network address having the same (IP), multiple processing server 11-14 etc. can be total to
Together for providing network service to user terminal 2 to realize the load balancing of inter-process server.In use, any to use
Family end 2 can connect or access the network port of server zone 1 according to the consolidated network address, to receive to come from the processing
The computational service of server.When there are access request, by allocation unit by certain Hash (HASH) algorithm, access is asked
Seek the processing server being converted into server zone 1 with management in idle time process according to certain allocation rule.
In the present invention, specifically, user terminal 2 can be teaching end or study end, and the user terminal 2 is by long-distance education system
The employee of the operator of system such as teacher and/or consumer such as student's operation with by cable network or wireless network or
The mode of bluetooth is interacted with the server zone 1, and then realizes the teaching, training work of long-distance education.Due to the server zone
Multiple processing server 11-14 in 1 have consolidated network address, therefore request can be with for the batches of processing from user terminal 2
The direction arrow A as shown access server zone 1 via consolidated network address and be then distributed to multiple processing server 11-14 into
Row is handled and is undertaken, multiple processing servers so as to efficiently handle batches of task requests, in subsequent server zone 1
Respective handling is carried out to the task requests distributed and the operation that will be responsive to user's request in a manner of the direction shown by arrow B is returned
It is transmitted to user terminal 2, it is thus achieved that interacting between server zone 1 and user terminal 2 and being finally completed the religion of long-distance educational system
Learn work.
It is used to distribute the example of the access request from user terminal 2 as the server zone 1 in the present invention, it can be in the clothes
It is provided with allocation unit 101 in business device group 1, wherein each processing server 11-14 etc. can be via transmission control protocol (TCP)
The allocation unit is sent data to inform that the allocation unit 101 itself can currently undertake the general assignment number of execution, to divide
Access task requests are distributed with unit.It can establish an allocation matrix in allocation unit, record each processing server
Current task number situation manages the task distribution of each processing server by the allocation matrix.Specifically, matrix master
The management in idle time process number on each processing server 11-14 is recorded, with reference to use when for distributing task.
After allocation unit receives processing task requests in batch, each task will be asked according to the rule of first in first out (FIFO)
It asks to be ranked up and waits to form task request queue and distribute to each processing server and handled.Allocation unit timing
It checks task request queue, the pending task requests such as checks whether.If there is pending task requests in queue,
Allocation unit checks allocation matrix, checks the situation of the management in idle time process number of current each processing server.If there is processing takes
The be engaged in management in idle time process number of device is greater than 0, then means that task requests distribution can be carried out to the processing server, and then can be with
Task requests distribution is for example carried out via HASH algorithm by allocation unit;If current each processing server is in busy shape
State, then waiting has processing server to be in idle condition.
Then, allocation unit successively takes out task to be processed in task queue, will be to be processed by sending TCP data
Task requests are distributed to idle processing server and are handled, and correspondingly adjust each processing server in allocation matrix
Management in idle time process number.When distribution server, which checks multiple processing servers, idle treatment progress, the present invention understands root
Disperse to distribute according to the number of the management in idle time process number on each processing server, to make full use of each processing server
Resource.For example, it is assumed that currently there is 6 access task requests, the management in idle time process number of processing server 11 is 5, processing service
The management in idle time process number of device 12 is 4, and the management in idle time process number of processing server 13 is 3;So allocation unit can be by 3
Processing task requests distribute to processing server 11, and 2 processing task requests are distributed to processing server 12, finally again will
1 processing task requests distributes to processing server 13.This allocation plan is the processing server more than management in idle time process number
More task is distributed, the few processing server of management in idle time process number just distributes less task or do not distribute task, in this way
The performance for being conducive to give full play to all processing servers reaches and undertakes external tasks balancedly to handle task in time
Purpose.
Certainly, those skilled in the art are it is contemplated that allocation unit can also be according to task requests to be allocated
The size of management in idle time process number determines in quantity and each processing server, such as each processing server may distribute to obtain phase
Same task requests.Alternatively, alternatively, batch tasks are first distributed to a processing server, until the clothes
The management in idle time process number of device be engaged in when being 0, then remaining task is distributed into other idle processing servers.
Further, the server zone 1 according to the present invention for long-distance educational system is schematically illustrated in Fig. 2
Monitoring system.For each processing server 11-14 in server zone 1 etc., each processing server includes master
Board management controller (Baseboard management controller, hereinafter referred to as BMC) 4.It is with processing server 11
Example, BMC 4 therein is the microcontroller in a mainboard for being embedded in processing server 11, mainly monitors processing server
11 state such as the state of temperature, electric source modes, cooling fan speed, operation system state or other hardware driving equipment
Information, and send alerting in due course and be transferred to the monitoring terminal 5 in monitoring system.It is and each in server zone 1 of the invention
The network port 3 of a processing server has consolidated network address different, and the BMC4 of each processing server is respectively provided with each other
Different network address, and the BMC can be provided with embedded web page server based on the network address of its own
(Embedded Web Server, hereinafter referred to as EWS) interface 41, so that 5 network linking of monitoring terminal in the present invention be allowed to arrive
The network address of the BMC4 of each processing server and login EWS interface 41, and by EWS interface 41 receive come from each processing
Hardware and application state in the status information of server, such as processing server 11, and monitor the processing server 11.
Configured with a server state real-time monitoring unit, (hereinafter referred to as monitoring is single in monitoring terminal 5 of the invention
Member) 51, wherein the monitoring unit 51 includes: multiple network input port 5b being connected to the network with BMC4, the network inputs
The reported information of BMC of the port 5b to receive a processing server, therefore the quantity and service of network input port 5b
The number of units of processing server in device group 1 is identical, and for example communicates to connect correspondingly with the EWS interface 41 of BMC;And one
A network input/output port 5a being connected to the network with server zone, wherein the monitoring unit 51 can be via the network
Input/output port 5a is uniformly online with the progress of the network port of each processing server, to test each processing service
Whether device 11-14 normally can provide network service to external such as user terminal 2, if each processing server can be with
51 proper network of the monitoring unit connection of terminal 5 is monitored, then (such as the 1 second) monitoring unit 51 can be with after a predetermined time
Each server interruption is online, and then, which can wait a predetermined time segment (such as 1 hour), subsequently should
Monitoring unit 51 can again attempt to carry out with each processing server online to test whether it still is able to normally provide net
Network service, to realize the monitoring to server zone 1.
When one or more processing servers in the server zone 1 break down, then monitoring unit 51 can monitor
There are cannot normally provide the processing server of network service in server zone 1, monitoring unit 51 can be according to each place at this time
The network address and BMC4 for managing the BMC4 of server are connected to the network, and issue to BMC4 and it is required to return its current state information
Instruction, such as return order is assigned to BMC4 by the EWS interface 41 that BMC4 is provided, it is desirable that BMC4 return processing server is worked as
Preceding status information.Therefore, when the current shape of the BMC that monitoring unit 51 the receives each processing server processing server returned
After state information, will record the current state information of each processing server, and real-time display monitoring terminal 5 display with
It shows outside to the monitoring personnel such as server administrators of server zone, so that network administrator be enable to be serviced according to each processing
The status information record of device judges the processing server to break down and then repairs operation to it.
It is shown in Figure 3 according to fig. 2 in monitoring system operating method, wherein the monitoring system can be supervised periodically
The functioning condition for surveying server zone 1, and when server zone 1 is abnormal, allow server zone 1 monitoring personnel or manager's energy
Obtain the system status information of server zone 1 immediately to be disposed in real time.Specifically, as shown in the step 101 of Fig. 3, this
Monitoring terminal 5 in invention can be regularly connected to the network with server zone 1, that is, monitor 51 meeting of monitoring unit of terminal 5
According to the unified network address of server zone 1, regularly with each of its network input/output port 5a and server zone 1
A processing server is connected to the network (for example, periodically for 1 hour), and whether the network service provided with testing service device group 1
Normally.
As illustrated by step 102 of figure 3, if network service provided by each processing server in server zone 1 does not have
It is abnormal, then network connection can be interrupted with each processing server in server zone 1 by monitoring terminal 5, and such as the step of Fig. 3
Shown in rapid 103, monitoring terminal 5 can remain waiting within the period until end cycle, executes step 101, again with it again
Network input/output port 5a and each processing server of server zone 1 are connected to the network, to reach periodic monitor service
The purpose of the functioning condition of device group 1.
In contrast, if in a step 102, when monitoring unit 51 discovery can not with some in server zone 1 or
When the multiple processing servers of person are normally connected to the network, this indicates there are the processing clothes to break down in the server zone 1
Business device, then, in the step 104 of Fig. 3, the monitoring unit 51 of monitoring terminal 5 can be via multiple and Baseboard Management Controller
The BMC of network input port 5b and each processing server that EWS interface 41 is connected to the network are connected to the network, and assign requirement
BMC4 returns the instruction of its current state information, it is desirable that BMC4 returns the current state information of the processing server of its own.Cause
This, after monitoring the current state information for the processing server that terminal 5 receives BMC passback, monitoring unit 51 will record processing clothes
The fault state and current state information of business device, and real-time display is on the display of monitoring terminal 5.Therefore, server zone 1
Monitoring personnel can understand the status information of each processing server in server zone 1 by monitoring 5 real-time visual of terminal,
Disposition immediately is carried out to the processing server to break down, or analyzes the original that the processing server to break down is abnormal
Cause.
In conclusion above-described embodiment actively and regularly carries out network company with server zone 1 by monitoring terminal 5
It connects, with the overall operation situation of testing service device group 1, and is finding connecting to outer network for the processing server in server zone 1
When sending and receiving life unusual condition, initiatively requires the BMC4 of each processing server to provide by the monitoring unit 51 of monitoring terminal 5 and be somebody's turn to do
The current state information of processing server allows the monitoring personnel of server after server zone 1 is abnormal, so that it may in time and
The situation of each processing server in current server zone 1 is well understood, and corresponding measure or place can be carried out immediately
It sets, and then promotes the monitoring efficiency of server zone 1.It can be seen that the present invention can be very low hardware cost and human cost be
It can be achieved to carry out malfunction monitoring to huge server zone 1, this is to be appointed server farm applications into long-distance educational system
Obstacle has technically been cleared away in business request processing.
It will hereinafter describe to be made on the basis of the above embodiments in a manner of preferred embodiment further
It improves.The purpose of preferred embodiment below is to further decrease the hardware cost of monitoring system, i.e., in reduction monitoring terminal 5
In the network input port 5b being connected to the network with the EWS interface 41 of the BMC4 of processing server quantity while, also
The monitoring to server zone 1 is not interfered with.
Second embodiment according to the present invention is shown in FIG. 4.Compared with above-described embodiment, according to the present invention second
The monitoring system of the server zone 1 of embodiment includes multiple monitor agent server 61-62, and 2 are for example shown as in Fig. 4
(but being not limited to 2 as known to those skilled in the art), wherein make a monitor agent server 61 or 62 simultaneously service
Multiple processing servers in device group 1, thus using the monitor agent server as multiple processing servers in server zone 1
With the coffret between single monitoring terminal 5, the quantity for monitoring the network input port 5b in terminal 5 whereby only needs to be arranged
Be it is consistent with the quantity of monitor agent server, thus greatly reduce the hardware requirement and cost of monitor terminal.With this
Simultaneously as the number of servers being directly communicatively coupled with monitoring terminal is reduced, if so as to avoid processing server
The problem of processing of monitor terminal caused by the reported information of simultaneous transmission is too many is not in time or the processor of monitoring terminal overloads,
So that also can satisfy the normal monitoring of server zone 1 even if reducing the processing speed of monitoring terminal.It should be pointed out that removing
Except monitor agent server, the component in second embodiment has and first embodiment basically same structure.Therefore, with
Component in first embodiment gives herein with the component of essentially identical function to be identically numbered.
As shown in figure 4, the monitoring system of second embodiment according to the present invention is specifically included that with multiple processing servers
1,2 monitor agent server 61 and 62 of server zone and monitor terminal 5 of 11-14,11a-14a etc..As shown, multiple
Processing server 11-14 is connected respectively to monitor agent server 61, while multiple proxy server 11a-14a are then separately connected
To monitor agent server 62, it is thus achieved that the port EWS 41 of the BMC4 of Monitor Daemon Server and multiple proxy servers
Information transmission.Monitor agent server 61 and monitor agent server 62 are then connected respectively to monitoring terminal 5, so as to incite somebody to action
The status information from processing server received is transferred to monitoring terminal 5.
In the present embodiment, the quantity of monitor agent server will be less than the processing clothes in the server zone 1 for needing to monitor
The quantity of business device 11-14 and 11a-14a, and each monitor agent server all can be multiple proxy servers offer prisons
It surveys.In this way, can be greatly decreased monitoring terminal 5 networking input interface quantity and monitoring terminal processing capacity require and
The monitoring function of monitoring system is not influenced.Such as shown in Fig. 4, which schematically illustrates 8 proxy servers
11-14 and 11a-14a, 8 proxy servers are serviced by two monitor agent server 61-62 respectively.Whereby, the prison
It surveys 5 need of terminal and has two network input ports, and no longer need to have 8 network input ports, therefore can effectively drop
Hardware cost is closed in its low load.
Monitor agent server 61 and 62 starting after, first to monitoring terminal 5 issue signal with to monitoring terminal 5 net
Network input port 5b is registered.On the other hand, multiple proxy servers in monitored server zone 1 is needed to be also required to elder generation
It is registered to the monitoring terminal 5, and after the completion of registration, then receives the distribution of the monitoring terminal 5.Whereby, these are handled
Server can be learnt must transmit itself status information to the monitoring terminal by which monitor agent server.This
In embodiment, the processing server is mainly by the status information of itself, such as temperature, electric source modes, cooling fan speed, behaviour
Make system mode or the state of other hardware driving equipment etc. and send assigned monitor agent server 61 or 62 to, and again
It carries out sequentially inputting the monitoring terminal 5 again after caching and priority sequence by the monitor agent server and carries out outer aobvious and analysis
Reason.
The monitor agent server 61 includes information input unit 61a, data buffer storage pond 61b, information output unit 61c
And control unit 61d, wherein information input unit 61a, data buffer storage pond 61b and information output unit 61c successively communication link
It connects, and control unit 61d is also correspondingly communicatively connected to information input unit 61a, data buffer storage pond 61b and information output is single
First 61c.After monitor agent server 61 is received from the status information that the processing server for being appended to its own issues, meeting
Data buffer storage pond is first transmitted to be cached and send the notice for receiving input information to control unit.
Wherein the data buffer storage pond mainly includes queue and local data base, and the queue is to input to be processed of sorting
Status information, and the local data base then to the status information be not yet successfully delivered to monitoring terminal 5 before, temporarily
Store the status information.Control unit, will be according to scheduled rule to team after receiving the notice from information input unit
The status information of multiple proxy servers in column be ranked up with by the status information of multiple proxy servers according to certain
It is input to monitoring terminal regularly.
For multiple proxy servers in server zone 1, break down or the probability of abnormality simultaneously
Substantially it is not present.In actual use, the proxy server in server zone 1 is due to each proxy server itself
Service life or loading condition can break down with staggering the time or exception.It is desirable that, being with the probability size to break down
According to the sequence for carrying out status information transmission priority, i.e., the state that prioritised transmission is most likely to occur the processing server of failure is believed
Breath, and the status information for the processing server that is less likely or can not break down substantially is transmitted later or the latest.By
It is taken in the processing that the status information of multiple processing servers can be ranked up to processing and preferentially transmission is most likely to occur failure
The status information of business device can further increase monitoring terminal to generation event compared with multiple processing servers are returned simultaneously
The identification and response speed of the processing server of barrier.
For this purpose, ordering rule as one preferred, is to record multiple processing services by control unit in this application
The probability that the average time between failures of device and the reliability index of processing server carry out assessment processing server fail is big
It is small, to realize the transmission priority sequence of status information.Specifically, there is each proxy server by control unit record
(reliability index is based on processing for average time between failures (abbreviation MTBF) and the reliability index of each processing server
The operational capability and memory space of server are set by manager).For MTBF and reliability index distribute respectively a weight because
Son, wherein the summation of weight factor is 1.As an example, the weight of reliability index is 0.4 for example, the weight of MTBF is 0.6.
Control unit calculates separately the average time between failures of each proxy server according to the time that server zone 1 has been run
With the difference between runing time, and difference is multiplied with the weight of MTBF and adds the numerical value of reliability index
Obtain the current failure risk factors of each proxy server.For exemplary purposes, if the MTBF of processing server 11 is
1000 hours, and the MTBF of processing server 12 be 800 hours, when server zone 1 worked 700 it is small when at the time of,
In processing server failure has occurred, then in the case where the two reliability is almost the same, control unit will determine to service
The probability that device 12 breaks down is greater than the probability that server 11 breaks down, then requiring each processing to service in monitoring terminal 5
When the BMC4 of device returns oneself state information, the control unit in monitor agent server 61 will be located at the processing service in queue
The priority of the status information of device 12 comes before the status information of processing server 11.Similarly, if processing server 11
It is very nearly the same with the MTBF of processing server 12, and the operational capability of processor employed in processing server 12 and storage are empty
Between be all larger than processing server 11 (this means that data are overflowed and operational capability deficiency a possibility that leading to delay machine is small), then
Control unit when monitoring the BMC return oneself state information of each processing server of demanding terminal, in monitor agent server
The priority of the status information for the processing server 12 being located in queue can be come before the status information of processing server 11.
It, can be temporary after status information of the control unit to each processing server being located in queue is ranked up
When the state information storage of priority ranking will be completed in the local data base in the data pool, to ensure that status information exists
It will not lose before sending out.So design, can effectively promote the safety of monitoring system, and ensure data
Integrality.Then, control unit is issued when the network input port 5b for detecting monitoring terminal 5 can receive status information
Allow to store the network input port that status information in the local database is sent to monitoring terminal via information output unit
The instruction of 5b, thus the transmission of completion status information.
The operating process of second embodiment will be described in detail below.
Monitor Daemon Server and processing server are carried out by registration and processing server according to above description first
Share out the work, make each processing server know self by which Monitor Daemon Server to monitoring 5 posting status of terminal
Information.Next, monitoring terminal 5 can be periodically connected to the network with server zone 1, the net provided with testing service device group 1
Whether network service is normal.If the service of network provided by each processing server in server zone 1 there is no exception,
Network connection can be interrupted with each processing server in server zone 1 by monitoring terminal 5, and after waiting for a period of time, monitoring is eventually
End 5 is connected to the network with each processing server of server zone 1 again, to reach the running of periodic monitor server zone 1
The purpose of situation.
When the discovery of monitoring terminal 5 can not carry out normal net with some in server zone 1 or multiple processing servers
When network connects, monitoring terminal 5 may require that BMC4 returns the current state information of the processing server of its own.When multiple processing take
When the BMC of business device returns oneself state information, which is transferred to the letter for the monitor agent server that it is attached first
Cease input unit, and after information input unit receives status information unloading enter the medium unit to be controlled of queue of data pool into
Row major power sequence.Control unit, will be according to scheduled rule to queue after receiving the notice from information input unit
In the status informations of multiple proxy servers be ranked up, the status information of the ranked multiple proxy servers finished is then
It is temporarily stored in local data base.It can receive status information in the network input port that control unit detects monitoring terminal
When, allow to store the network inputs that status information in the local database is sent to monitoring terminal via information output unit
The instruction of port, thus the transmission of completion status information.
From the foregoing, it will be observed that the second embodiment is by being arranged at least one Monitor Daemon Server compared with first embodiment
As the coffret between multiple processing servers and monitoring terminal, the network inputs of monitoring terminal so can be effectively controlled
The requirement of the quantity of port and the processing capacity to monitoring terminal.At the same time, it is communicated due to reducing with monitoring terminal
The number of servers of connection, if at monitor terminal caused by reported information so as to avoid processing server simultaneous transmission is too many
The problem of reason is not in time or the processor of monitoring terminal overloads, so that also can even if reducing the processing speed of monitoring terminal
Meet the normal monitoring of server zone.
Third embodiment according to the present invention is shown in figures 5-6.3rd embodiment is on the basis of the above embodiments
It further reduced the hardware requirement to monitor terminal 5.The 3rd embodiment takes full advantage of each processing in server zone
Server spatially this advantage of compact Layout, by utilizing wireless near field communication between each processing server
Technology forms closed data link, and then multiple processing servers are combined into one with common output end mouth
Monitoring server group is monitored.Whereby, each processing server in server zone 1 is divided into multiple with common output
The monitoring group of port, to reduce the quantity and processing requirement of the network input port of monitoring terminal.
The processing server in the server zone of third embodiment according to the present invention is shown in FIG. 5.In third reality
It applies in example, includes BMC4 and wireless communication unit 8 for communicating therewith letter in processing server.The wireless communication unit
8 can be NFC (Near Field Communication the short distance wireless communication technology) or other Near Field Communication moulds
Block.The wireless communication unit 8 includes emission part 81 and receiving unit 82.And in BMC4 then include setting unit, monitoring unit and state
Information output part.As an example, the components such as setting unit in BMC can be as performed by the central processing unit in BMC.
As shown in fig. 6, in the present embodiment, as an example, the processing server 11 in server zone 1, processing are serviced
This 5 processing servers of device 12, processing server 13, processing server 14, processing server 15, which constitute one, to be had jointly
The monitoring server group 7 of output port 71.Those skilled in the art understand that, the processing service in each monitoring server group
The number of device is not limited to 5, also can according to need and is set as more or less than 5.Thus, it is possible to by entire server
Group 1 is divided into multiple monitoring server groups.
In the present embodiment, the setting unit in the BMC of each processing server is for being arranged clothes belonging to the processing server
Family and the communication player whose turn comes next in the title for device monitoring group of being engaged in and the communication of the processing server.As a server shown in Fig. 6 is supervised
In survey group, by processing server 11 as the first processing server in monitoring group, the name that the monitoring group where it is arranged is
Group 1, family is processing server 15 in communication, and the communication player whose turn comes next is then processing server 12;Choosing processing server 12 is the
Two processing servers, the name that the monitoring group where it is arranged is Group 1, and family is processing server 11 in communication, under communication
Family is processing server 13;Selection processing server 13 is third processing server, and the name that the monitoring group where it is arranged is
Group 1, family is processing server 12 in communication, and the communication player whose turn comes next is processing server 14;Choosing processing server 14 is the 4th
Processing server, the name that the monitoring group where it is arranged is Group 1, and family is processing server 13 in communication, communicates the player whose turn comes next
For processing server 15;Selection processing server 15 is the 5th processing server, and the name that the monitoring group where it is arranged is
Group 1, family is processing server 14 in communication, and the communication player whose turn comes next is processing server 11;Pass through each processing server 11-15
BMC in setting unit above-mentioned setting, this five processing servers can be integrated into the same monitoring group Group 1 and shape
At a complete closed-loop communication chain as shown in FIG. 6.In the present embodiment, processing server 11, processing server 12, processing
Pass through the respective mutually communication of wireless communication unit 8 between server 13, processing server 14 and processing server 15.
When the discovery of monitoring terminal 5 can not carry out normal network with some in server zone or multiple processing servers
When connection, monitoring terminal may require that BMC4 returns the current state information of the processing server of its own.In this embodiment, respectively
The BMC of a processing server starts to carry out self-test.Specifically, the monitoring unit in the BMC4 of each processing server can will supervise
The state such as temperature, electric source modes, cooling fan speed, operation system state or other hardware driving equipment that measures and pre-
If the state threshold in the normal operating condition compare.Wherein whether monitoring unit has surpassed according to above state value
The state threshold for having gone out normal operating condition issues operational order to correspondingly wireless communication unit 8.
Meanwhile in wireless communication unit, each emission part 81 belongs in the same monitoring group for sending information to
Communication on family and communication the player whose turn comes next.Correspondingly, each receiving unit 82 is used to receive the information for communicating upper family and communicating the player whose turn comes next.It should
Emission part 81 is also used to receive after communicating upper family or communicating the information of the player whose turn comes next in receiving unit 82, to the upper family of communication or communication
The player whose turn comes next issues response message.
In use, when the monitoring unit discovery in each of same monitoring server group processing server
The state information value of the processing server of its own without departing from the state threshold of normal operating condition when, respectively to respective
Wireless communication unit 8 issues normal externally transmitting information and receives the instruction of information.In this case, in monitoring server group
Complete closed-loop communication chain be it is smooth, this indicates that processing server all in the monitoring server group is in normal work
Make state.
Further, when the monitoring unit of one or more processing servers in the same monitoring server group finds it
When the state information value of the processing server of itself has exceeded the state threshold of normal operating condition, respectively to the wireless of itself
Communication unit issues the instruction for stopping external transmitting information and receiving information.In this case, monitoring server group is complete
Closed-loop communication chain be at such as the first processing server 11 and second processing server 12 disconnect, this indicates the server
There are the processing servers of failure in monitoring group.Further, since each processing server all has in its corresponding communication
Family and communication the player whose turn comes next, can be easily positioned in the monitoring server group according to the cut-off point of closed-loop communication chain break down or
The processing server of person's exception.
Further, in the case where the processing server to break down has been determined according to the cut-off point of closed-loop communication chain,
The common output end mouth 71 of monitoring server group issues instruction to the monitoring unit of the processing server of identified failure.The failure
Processing server monitoring unit after receiving the instruction from common output end mouth 71, indicate belonging to it status information output
Portion sends the status information of the BMC belonging to it to common output end mouth.Common output end mouth is in the processing service for receiving failure
After the status information of the BMC of device, then the network input port 5b by monitoring terminal is input in monitoring terminal, to realize
Monitoring to the monitoring server group.
It can be seen that 3rd embodiment on BMC only by adding one compared with the first and second embodiments above-mentioned
Simple close communication unit, which can be realized, divide and quickly identifies every to multiple processing servers in server zone 1
Failed server in a monitoring server group.Specifically, due to the quantity of the network input port 5b of 3rd embodiment with
The number of monitoring server group is identical (part even 1/tens that the number of monitoring group is processing server number),
Compared with first embodiment, this can greatly reduce the quantity of the network input port 5b of monitoring terminal 5, this is effectively controlled in turn
The quantity of the network input port of system monitoring terminal and the requirement to the processing capacity of monitoring terminal eventually reduce monitoring system
Hardware cost, while not interfering with the monitoring to server zone 1 also.
Meanwhile compared with second embodiment, then Monitor Daemon Server in a second embodiment is eliminated, and then reduce
The hardware cost of monitoring system, while not interfering with the monitoring to server zone 1 also.
The technical scheme of the present invention has been explained in detail above with reference to the attached drawings, although preferred implementation of the invention has been described
Example, once a person skilled in the art knows basic creative concepts, then other change can be made to these embodiments
More and modify.So it includes preferred embodiment and all changes for falling into the scope of the invention that the following claims are intended to be interpreted as
More and modify.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of monitoring system of the server zone of long-distance educational system, including multiple processing servers, the multiple processing clothes
Business device includes Baseboard Management Controller, it is characterised in that: wherein the server zone further includes logical with multiple processing servers
The allocation unit of transmission control protocol data connection is crossed, wherein the allocation unit is managed everywhere for establishing allocation matrix with dynamic
Manage the management in idle time process number on server;The whether pending task requests of allocation unit periodic monitor, if so, then
Check the management in idle time process number of each processing server in allocation matrix, if it exists idle processing server, then it will be to be processed
Task distributes to idle processing server;
The monitoring system includes monitoring terminal, which includes that can carry out net with the processing server in server zone
The server state real-time monitoring unit of network connection;The server state real-time monitoring unit of the monitoring terminal regularly with place
Reason server is connected to the network, and requires each processing server when discovery and the network connection of processing server are abnormal
Baseboard Management Controller return the current state information of the processing server.
2. monitoring system according to claim 1, wherein
Wherein multiple processing servers in the server zone have the consolidated network address of common externally offer network service, and
The Baseboard Management Controller has different network address to each other, which taken according to processing
The Unified Network address of business device and processing server are connected to the network to test the network service, and according to the Baseboard Management Controller
Network address and the Baseboard Management Controller be connected to the network with require the Baseboard Management Controller return current state information.
3. monitoring system according to claim 1 or 2, wherein
The server state real-time monitoring unit includes: that at least one network for being connected to the network with Baseboard Management Controller is defeated
Inbound port, the reported information of Baseboard Management Controller of the network input port to receive at least one processing server;With
And the network input/output port being connected to the network with server zone.
4. monitoring system according to claim 2 or 3, wherein
The quantity of the network input port is identical as the quantity of the processing server in server zone, each network input port
It is communicated to connect respectively with the Baseboard Management Controller of a processing server.
5. monitoring system according to claim 2 or 3, wherein
The monitoring system further includes at least one monitor agent server, which is configured to connect to multiple
Proxy server and the multiple agencies that is configured to receive the status information of multiple proxy servers connected to it, and will receive
The status information of server is transferred to monitoring terminal, wherein the number of the quantity of the network input port and monitor agent server
Measure identical, each network input port is communicatively coupled with a monitor agent server respectively.
6. monitoring system described in claim 5, wherein
The monitor agent server includes the information input unit successively communicated to connect, data buffer storage pond, information output list
Member and respectively with information input unit, data buffer storage pond, information output unit communication connection control unit, the wherein information
Input unit receives the status information from processing server connected to it and the status information is transferred to data buffer storage pond,
Described control unit is used to carry out the status informations of multiple processing servers in data cache pool priority ranking, and via
Status information after sequence is transferred to monitoring terminal by information output unit in an orderly manner.
7. monitoring system according to claim 6, wherein
The data buffer storage pond includes queue and local data base, which is configurable for sorting the shapes of multiple processing servers
State information, the local data base are configured in front of status information is not yet transferred to monitoring terminal and temporarily store the state
Information, wherein described control unit is according to the average time between failures of multiple proxy servers and the reliability index of server
Priority ranking is carried out to the status information in queue.
8. monitoring system according to claim 2 or 3, wherein
The monitoring system further includes the service with common output end mouth being made of multiple processing servers in server zone
Device monitoring group, the common output end mouth is configured as the status information of output failed server, wherein the network input
Mouthful quantity it is identical as the quantity of monitoring server group, each network input port is common with monitoring server group respectively
Output port is communicatively coupled.
9. monitoring system according to claim 8, wherein
It is all had in each processing server that same monitoring server is concentrated wireless with Baseboard Management Controller communication connection
Communication unit, each Baseboard Management Controller all have setting unit, monitoring unit and status information output section, and the setting unit is for setting
Set family and the communication player whose turn comes next, the nothing in the title of the processing server subordinate server monitoring group and the communication of the processing server
Line communication unit includes emission part and receiving portion, wherein the emission part of each processing server and receiving portion is configured for and it
Family and communication player whose turn comes next's communication in communication, to form complete closed-loop communication chain in the monitoring group.
10. monitoring system as claimed in claim 9, wherein
Whether the status information that the monitoring unit is configurable for determination processing server exceeds state threshold, is exceeding state
When threshold value, is issued to wireless communication unit and stop transmitting and receive the instruction of information to make the closed-loop communication chain disconnection, institute
It states common output end mouth and issues instruction to the processing server in closed-loop communication chain cut-off point, so that the status information belonging to it
Output section sends the status information of the mainboard controller belonging to it to the common output end mouth and via common output end port transmission
To monitoring terminal.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711142005.8A CN109800120B (en) | 2017-11-17 | 2017-11-17 | Monitoring system of server group of remote education system |
PCT/CN2017/114405 WO2019095448A1 (en) | 2017-11-17 | 2017-12-04 | Monitoring system for remote education system server farm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711142005.8A CN109800120B (en) | 2017-11-17 | 2017-11-17 | Monitoring system of server group of remote education system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109800120A true CN109800120A (en) | 2019-05-24 |
CN109800120B CN109800120B (en) | 2020-12-08 |
Family
ID=66538357
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711142005.8A Active CN109800120B (en) | 2017-11-17 | 2017-11-17 | Monitoring system of server group of remote education system |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109800120B (en) |
WO (1) | WO2019095448A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112035259A (en) * | 2020-09-01 | 2020-12-04 | 中国银行股份有限公司 | Data processing system, method and server group |
CN112035231A (en) * | 2020-09-01 | 2020-12-04 | 中国银行股份有限公司 | Data processing system, method and server group |
CN117354075A (en) * | 2023-12-05 | 2024-01-05 | 广州炫视智能科技有限公司 | Multi-user interaction method and interaction system |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112512027A (en) * | 2020-12-25 | 2021-03-16 | 浪潮电子信息产业股份有限公司 | Server, communication method, system and computer readable storage medium |
CN116205766B (en) * | 2023-04-28 | 2023-07-21 | 北京华医网科技股份有限公司 | Big data analysis method and system applied to medical relay teaching |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102404160A (en) * | 2010-09-13 | 2012-04-04 | 中国移动通信集团福建有限公司 | Method and system for realizing intelligent monitoring |
CN103227838A (en) * | 2013-05-10 | 2013-07-31 | 中国工商银行股份有限公司 | Multi-load equalization processing device and method |
US20140068033A1 (en) * | 2012-09-05 | 2014-03-06 | John Berger | Systems, methods, and articles of manufacture to manage alarm configurations of servers |
CN105184498A (en) * | 2015-09-18 | 2015-12-23 | 成都虹昇光电科技有限公司 | Educational equipment management platform |
CN106021070A (en) * | 2016-04-29 | 2016-10-12 | 乐视控股(北京)有限公司 | Method and device for server cluster monitoring |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101004743B (en) * | 2006-01-21 | 2010-05-26 | 鸿富锦精密工业(深圳)有限公司 | Distribution type file conversion system and method |
WO2012076492A1 (en) * | 2010-12-07 | 2012-06-14 | Basf Se | Melamine resin foams comprising nanoporous fillers |
CN102523234B (en) * | 2011-12-29 | 2015-12-02 | 山东中创软件工程股份有限公司 | A kind of application server cluster implementation method and system |
-
2017
- 2017-11-17 CN CN201711142005.8A patent/CN109800120B/en active Active
- 2017-12-04 WO PCT/CN2017/114405 patent/WO2019095448A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102404160A (en) * | 2010-09-13 | 2012-04-04 | 中国移动通信集团福建有限公司 | Method and system for realizing intelligent monitoring |
US20140068033A1 (en) * | 2012-09-05 | 2014-03-06 | John Berger | Systems, methods, and articles of manufacture to manage alarm configurations of servers |
CN103227838A (en) * | 2013-05-10 | 2013-07-31 | 中国工商银行股份有限公司 | Multi-load equalization processing device and method |
CN105184498A (en) * | 2015-09-18 | 2015-12-23 | 成都虹昇光电科技有限公司 | Educational equipment management platform |
CN106021070A (en) * | 2016-04-29 | 2016-10-12 | 乐视控股(北京)有限公司 | Method and device for server cluster monitoring |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112035259A (en) * | 2020-09-01 | 2020-12-04 | 中国银行股份有限公司 | Data processing system, method and server group |
CN112035231A (en) * | 2020-09-01 | 2020-12-04 | 中国银行股份有限公司 | Data processing system, method and server group |
CN117354075A (en) * | 2023-12-05 | 2024-01-05 | 广州炫视智能科技有限公司 | Multi-user interaction method and interaction system |
CN117354075B (en) * | 2023-12-05 | 2024-03-15 | 广州炫视智能科技有限公司 | Multi-user interaction method and interaction system |
Also Published As
Publication number | Publication date |
---|---|
WO2019095448A1 (en) | 2019-05-23 |
CN109800120B (en) | 2020-12-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109800120A (en) | A kind of monitoring system of the server zone of long-distance educational system | |
US11533234B2 (en) | Autonomous distributed workload and infrastructure scheduling | |
US7822841B2 (en) | Method and system for hosting multiple, customized computing clusters | |
US8891403B2 (en) | Inter-cluster communications technique for event and health status communications | |
CN100367217C (en) | Method, system for supporting a large number of intermittently used application clusters | |
US8634328B2 (en) | Endpoint-to-endpoint communications status monitoring | |
CN109784508A (en) | A kind of power grid panorama monitoring operation management method and system based on cloud platform | |
CN107534570A (en) | Virtualize network function monitoring | |
CN104168326B (en) | A kind of method and system of server equally loaded | |
Mishra et al. | Software defined IoT systems: Properties, state of the art, and future research | |
CN102916839A (en) | Automatic monitoring system for agricultural work in sugarhouse | |
CN109513206A (en) | The network architecture of online game and data forwarding method for online game | |
CN102891756A (en) | Active power management architecture and active power management method | |
WO2017222763A2 (en) | Autonomous distributed workload and infrastructure scheduling | |
CN106993043A (en) | Data communication system and method based on agency | |
US10554497B2 (en) | Method for the exchange of data between nodes of a server cluster, and server cluster implementing said method | |
CN105912439A (en) | Method, device and system for computer monitoring | |
CN109840186A (en) | A kind of data center is health management system arranged and method | |
CN109800133A (en) | A kind of method, one-stop monitoring alarm platform and the system of unified monitoring alarm | |
CN107306289A (en) | A kind of load-balancing method and equipment based on cloud computing | |
CN109412940A (en) | Router administration method and router management system | |
CN103929335A (en) | Monitoring system of managing cloud host and monitoring method thereof | |
CN109005050A (en) | A kind of IDC information management system | |
Yang et al. | Joint optimization of mapreduce scheduling and network policy in hierarchical data centers | |
CN110198246A (en) | A kind of method and system of traffic monitoring |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201012 Address after: 512000 101, building 31, Huangshaping Innovation Park, phase I, guanshaocheng, Wujiang District, Shaoguan City, Guangdong Province Applicant after: YINGSHUO (Shaoguan) Information Industry Group Co., Ltd Address before: 518100 Guangdong city of Shenzhen province Baoan District Xin'an three industrial zone 1 road Cantor Fitzgerald building two floor, Room 202 Applicant before: SHENZHEN EAGLESOUL TECHNOLOGY Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |