CN108259270A - A kind of data center's system for unified management design method - Google Patents
A kind of data center's system for unified management design method Download PDFInfo
- Publication number
- CN108259270A CN108259270A CN201810026547.7A CN201810026547A CN108259270A CN 108259270 A CN108259270 A CN 108259270A CN 201810026547 A CN201810026547 A CN 201810026547A CN 108259270 A CN108259270 A CN 108259270A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- data center
- unified management
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/04—Network management architectures or arrangements
- H04L41/042—Network management architectures or arrangements comprising distributed management centres cooperatively managing the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Mathematical Physics (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a kind of system for unified management design methods of data center, include the following steps:The server node of data center is divided into multiple monitoring host computers, server component, multithreading monitoring system is formed with system for unified management server;Extensible protocol interface for multithreading monitoring system configuration module;The data processing method of Data Convergence layer is provided with for multithreading monitoring system;The monitoring method blended between system for unified management master server and monitoring host computer in multithreading monitoring system, between monitoring host computer and server node using active training in rotation with passive poll.The design method of the present invention contributes to the unified management of data center, especially needs the scene monitored simultaneously being related to physical resource and virtual resource, realizes data center's unified efficient monitoring management to large-scale basis resource.
Description
Technical field
The present invention relates to data center's technical field, especially a kind of data center's system for unified management design method.
Background technology
Modular data center Module Data Center are abbreviated as MDC, are in the data of new generation based on cloud computing
Center portion affixes one's name to form, by the way that by data center module, the maximum coupling for reducing infrastructure to building environment improves number
According to the whole efficiency of operation at center.
Data center's infrastructure is the core of cloud computing framework, it is supplied to user to including CPU, memory, storage, net
The use of the computing resources such as network is effectively reduced the cost and complexity of IT O&Ms.Cloud computing framework is compared to traditional server
Aggregated structure, in addition to the management to physical resources such as Web server, application servers, it is also necessary to CPU, memory, storage, net
The unified management of the virtual resources such as network, virtual machine.
The management system of data center is the important component being configured inside data center, mainly including UPS, distribution
A variety of monitored object such as cabinet, air-conditioning, gate inhibition, sensor, abbreviation data center total management system, core equipment hardware are rotating ring
Monitoring host computer, software are data center's total management system platform software.
At present, data center's system for unified management is divided into centralization and two kinds of system patterns of layer-stepping from structure.It concentrates
Formula system is made of Tomcat-AdminPortal and monitoring agent two parts, and Tomcat-AdminPortal is located on specific server,
It is responsible for analyzing data, handling, storing simultaneously and data is shown, is responsible for carrying out dynamic configuration to monitoring agent;Monitoring
Agency is distributed on the node that each needs monitors, and is acquired the monitoring data of monitored resource and is sent to management system clothes
Business device, monitoring agent will receive the control instruction of Tomcat-AdminPortal transmission simultaneously;Monitoring agent is divided in layer-stepping system
Several groups of layer structure have in each group several monitoring nodes to handle this group of things, and each group is equivalent to one
Centralized data center system for unified management, part monitor the role that node serves as data center's system for unified management server,
Global monitoring node is responsible for monitoring each part monitoring node.
Since Tomcat-AdminPortal single-geophone receiver monitoring data is stored in centralized system, single-point easily occurs and loses
The problem of effect, and a large amount of monitoring data transmissions can lead to network congestion;Although layer-stepping system solves the problems, such as single point failure, but
The access for specifying node is needed successively to transmit data, access efficiency is caused to reduce, deployment is complex.
As Chinese patent (application publication number CN106707951A) discloses a kind of " intellectualized management system of data center
And management method " invention connect with more network comtrol servers using management backstage, realized by network comtrol server
It is connect with the information of each information acquisition module in data center cabinet, the network comtrol server can also pass through more dynamic rings
Border comprehensively monitoring host connection, data transmission is realized, and pass through IP by dynamic environment comprehensively monitoring host and data center's cabinet
Address accesses, and completes the one-stop monitoring of entire room system, saves bandwidth resources, and realize and all computer rooms of the project are moved
Power carries out monitoring management in 365*24 hours comprehensive Unified Sets with environmental system and makes abnormal alarm processing.Although the party
Method improves the performance of data center management system, but the data-handling efficiency for managing system is still limited.
Invention content
The present invention proposes a kind of data center's system for unified management design method, for solving existing management system effectiveness
The problem of relatively low.
The present invention is achieved by the following technical programs:
A kind of system for unified management design method of data center, includes the following steps:
The server node of data center is divided into multiple monitoring host computers, server component, is taken with system for unified management
Business device composition multithreading monitoring system;
Extensible protocol interface for multithreading monitoring system configuration module;
The data processing method of Data Convergence layer is provided with for multithreading monitoring system;
Between system for unified management master server and monitoring host computer in multithreading monitoring system, monitoring host computer and server
The monitoring method blended between node using active training in rotation with passive poll.
A kind of data center's system for unified management design method as described above, the multithreading monitoring system are distribution
Concurrent working mode, each monitoring host computer adjust data processing and Data Convergence according to the server node quantity flexibility that it is managed
The number of components of layer.
A kind of data center's system for unified management design method as described above, the protocol interface include intelligent platform pipe
Interface IPMI, Redfish agreement, network management snmp protocol, Modbus agreements, Web Service agreements are managed, protocol interface can
To be extended by custom protocol.
A kind of data center's system for unified management design method as described above, when the monitoring method includes normal condition
Active training in rotation and abnormality when passive poll;The server node being monitored during active training in rotation is within the setting period by shape
State reported to monitoring host computer, meanwhile, monitoring host computer interval multiple setting periods actively send to monitored server node asks,
Check whether monitored resource is survived, be can be used;When monitoring host computer is being set without information feedback in the period, to monitored server section
Point carry out follower inquiry, to confirm that monitored server node state and exception are alarmed.
A kind of data center's system for unified management design method as described above, the data processing method include Portal
Boundary layer, platform management layer, Data Convergence layer, managed object layer;The Portal boundary layers provide for providing data center
The figure and report form showing of source monitoring, log management and alert process function;The platform management layer is used for collected prison
Control data are counted, analyzed and are excavated, and accurately assessment and prediction are made to the state of data center, are Portal circle
Face layer shows offer data supporting;It is described to carry out data acquisition for monitoring system, and extensible protocol interface is configured, realization pair
The acquisition of monitoring data, and store into database;The managed object layer is the monitored hardware of data center and soft
Part resource, including various servers, storage, the network equipment, database and application service, UPS, power distribution cabinet, precision air conditioner, door
A variety of prisons such as taboo, Temperature Humidity Sensor, smoke detector, temperature detector, leakage sensor, turning roof window and web camera
Control object.
A kind of data center's system for unified management design method as described above, the Data Convergence layer include monitoring core
Engine, monitoring and scheduling process, alarm engine, data processing centre, active detection interrogator, passive type detection interrogator, mould
Extensible protocol interface, the data storage component of block adopt the data of the monitored hardware and software resource of data center
Collection and monitoring provide digitlization for data center's stable operation and support.
Compared with prior art, it is an advantage of the invention that:
1st, design method of the invention contributes to the unified management of data center, especially be related to physical resource with it is virtual
Resource needs the scene monitored simultaneously, realizes data center's unified efficient monitoring management to large-scale basis resource.
2nd, the present invention by set multi-thread range monitoring framework, it is modular can flexible extension protocol interface, active training in rotation with
The measures such as monitor mode and the management method of monitoring data convergence layer that passive poll blends, data acquisition modes it is various and
Data center is managed collectively, and builds data center's system for unified management efficiently, stable.Specifically, the present invention can be with
The function of realization includes:
(1) it can realize and resource management, state prison are carried out to the infrastructure of different vendor, different frameworks, different shape
Control and performance monitoring;Cover calculating, storage, network three categories resource;Abundant monitored item type is provided, is worked as including that can check
The utilization rate of preceding computer CPU, memory, hard disk etc. can check network flow, magnetic disc i/o, into number of passes etc.;It can be with number
It, can also monitoring device quantity extending transversely according to the Expansion at center.
(2) it realizes and asset management, condition monitoring and performance monitoring is carried out to the basic software resource of isomery;Support pair
Current process and information on services are checked in the monitoring of Linux/Unix and Windows operating system;Support to Tomcat,
The monitoring of the application servers such as IIS, Apache and the database servers such as SQL Server, MySQL, Oracle.
(3) the triggering alarm when system hardware, load occur abnormal is realized, reminds the timely maintenance issues equipment of user;
Long-term statistical analysis is carried out to the load of basic software and hardware resources, decision-making foundation is provided for scheduling of resource.By to monitoring number
According to analysis, data support is carried out to other Premium Features of resource management system for data center, the continuous of application is effectively ensured
Property and quick response.
It (4) can be to including UPS, power distribution cabinet, precision air conditioner, gate inhibition, Temperature Humidity Sensor, smoke detector, warming spy
It surveys a variety of monitored object such as device, leakage sensor, turning roof window and web camera and carries out effective monitoring and management.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described.
Fig. 1 is the flow diagram of the present invention;
Specific embodiment
Purpose, technical scheme and advantage to make the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical solution in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, instead of all the embodiments.
As shown in Figure 1, a kind of system for unified management design method of data center disclosed in the present embodiment, including walking as follows
Suddenly:
The server node of data center is divided into multiple monitoring host computers, server component, is taken with system for unified management
Business device composition multithreading monitoring system;
Extensible protocol interface for multithreading monitoring system configuration module;
The data processing method of Data Convergence layer is provided with for multithreading monitoring system;
Between system for unified management master server and monitoring host computer in multithreading monitoring system, monitoring host computer and server
The monitoring method blended between node using active training in rotation with passive poll.
Specifically, the disclosed management design method of the present embodiment, can be good at solving data center dynamic increasing
The problem of large number of equipment added and application, improves the data-handling efficiency of management system, and with the increase of monitoring scale, obtains
Monitoring data amount can also sharply increase, at this time the scheduling of single thread and poll influence whether monitoring data promptness, effectively
Property, and the monitoring property such as higher data sampling and processing that the present invention can be lived by monitoring host computer multi-threaded parallel working method
Energy.
Data center's system for unified management is configured with multi-thread range monitoring framework, according to its management in each monitoring host computer
Server node scale, intelligent increases data processing and the number of components of Data Convergence layer, and only serve each component
Certain amount of collection of server processing, which is not influence system performance according to single thread, being capable of acquisition process
Maximum service device number.By way of multi-threading parallel process, the utilization rate and throughput of system of monitoring host computer are improved, is improved
The real-time of gathered data.The multi-thread range monitoring frame of distributed parallel.In the environment of large-scale cloud calculating, distribution portion can be used
Administration function to monitoring host computer according to monitoring load be extended it is flexible, dynamic increase monitoring server node quantity, ensure
When data center expands, the performance of data acquisition process will not decline.
The present embodiment is the extensible protocol interface of multithreading monitoring system configuration module.Due in data center, prison
The resource type of control also can be continuously increased and develop with data center's scale development, technological progress, this is to protocol interface
Propose autgmentability requirement.
Use unified interface can be with the problem of resolution protocol Interface Expanding by the data to monitoring.It is flat in monitoring
A variety of different monitoring protocols, such as IPMI, SNMP, Modbus, Web Service agreement are had been realized in platform, is permitted simultaneously
Perhaps increase custom protocol to be extended unified interface.Server hardware monitoring protocol interface including IPMI protocol,
The server hardware monitoring protocol interfaces of Redfish agreements, the network equipment monitoring protocol interface of snmp protocol, snmp protocol
Operating-system resources information monitoring protocol interface, the application information monitoring protocol interface of heterogeneous database, Heterogeneous Web application
Server state information monitoring protocol interface.
Wherein, IPMI protocol is an open free Standard of Monitoring, and user can utilize IPMI monitoring to meet agreement and set
Standby physical state information, such as cpu temperature, voltage, fan operating state, power supply status.The advantages of IPMI is can be across
Different operating system, firmware and hardware platforms, can be with the monitoring of wisdom, control and the operation shape for actively sending a large amount of servers
State.IPMI both can be independently of self-contained operation outside operating system, also can be movable after os starting, with system management function
Reinforcement function can also be provided when using together.The core of IPMI is a special chip or controller BMC, can not have to rely on clothes
Processor, BIOS or the operating system of business device carry out work, have good independent performance.As long as there are BMC and IPMI firmwares
It is no proxy management pattern to be run as a separate payment, BMC is typically one only on server master board
Vertical board also has server master board directly to provide and the good autonomous characteristics of IPMI is supported IPMI to overcome based on operating system
The limitation of monitor mode, as long as powering on, IPMI can be carried out the operations such as switching on and shutting down and monitoring information acquisition.
Redfish agreements are a kind of new server admin standards, it expresses data using hypermedia RESTful interfaces,
Easy to use and realization;It can express relationship and the semanteme of service and component between modern system component towards model,
Easily extension.
Snmp protocol is made of the standard of one group of network management, includes application layer protocol, database model and one group
Resource object.SNMP supports Network Management System, to monitor the state for being connected to the equipment on network, for the exception of equipment
Situation is paid close attention to and is alarmed.
ModBus procotols are an industrial communication systems, suitable for data-center applications scene, by band intelligent terminal
Monitoring host computer be formed by connecting.Its system structure had both included hardware, has also included software.It can be applied to the various data of data center
Acquisition, monitoring.
Web service agreements are a platform independence, lower coupling, self-contained, answering based on programmable web
With program, open XML standards can be used to describe, issue, find, coordinate and be configured these application programs, divide for developing
The application program of the interoperability of cloth.
Web Service agreements can to operate in different application on different machines need not be by additional, special
Third party software or hardware, so that it may be exchanged with each other data or integrated.Between the application of foundation Web Service enforcement of regulations, nothing
By language, platform or internal agreement used in them what is, data can be exchanged with each other.Web Service also hold very much
Easily deployment, because they are based on some conventional industry standards and some existing technologies, such as standard generalized markup language
Under subset X ML, HTTP.Web Service reduce the cost of application interface, and the integrated of operation flow for data center carries
A general mechanism is supplied.
Multithreading monitoring system is used to obtain the agreement of monitoring data or needs to inherit third-party interface to other,
It can accomplish Seamless integration- under the modularization protocol interface of the compatibility multi-mode, without being made to existing monitoring framework
Big adjustment.Hardware resource can be not only monitored by Protocol extension schemas, also support to the resource of application level into
Row analog access formula monitors.It is applied for Web and obtains associated monitoring data in a manner that simulation submits http request to submit,
For database application associated monitoring data are obtained in a manner that simulant-client submits SQL request.
Between system for unified management master server and monitoring host computer in multithreading monitoring system, monitoring host computer and server
The monitoring method blended between node using active training in rotation with passive poll.Under normal circumstances, with being monitored machine high frequency by shape
State reported to monitoring equipment, meanwhile, monitoring equipment actively sends to monitored resource according to a longer gap periods and asks, and checks
Whether monitored resource is survived, be can be used.In addition, once monitoring equipment confiscates the information of monitored machine before the deadline, just
Request sent out to monitored machine and remove poll, confirm the state of monitored machine, can thus determine data center resource in time
Operating status, and alarm all kinds of exceptions.
Multithreading monitoring system can realize the monitoring resource to large-scale data center, and distributed deployment and isomery is supported to put down
Platform, provides abundant monitored item type and monitored object, and monitored item type includes CPU usage, cpu load rate, memory and uses
Rate, network flow, disk space utilization rate, magnetic disc i/o, into number of passes, database availability, application server availability etc., and
Support the dynamic expansion of monitoring protocol and monitored item.Support the monitoring to Linux/Unix servers and Windows servers.
Monitored object includes UPS, power distribution cabinet, precision air conditioner, gate inhibition, Temperature Humidity Sensor, smoke detector, temperature detector, leak
Sensor, turning roof window and web camera etc. are a variety of.
By the analysis to monitoring data, to data center resource management and running or operational system, such as load balancing, failure
Recovery etc. carries out data support, and the continuity of data-center applications and the quick response of failure is effectively ensured.According to certain section before
The monitoring of time carries out offer predicted value based on monitoring data, system is safeguarded in advance, prevents the generation of fortuitous event.
Further, the data processing method used in the present embodiment includes Portal boundary layers, platform management layer, data
Four layers of convergence layer, managed object layer.
Portal boundary layers mainly to data center management personnel provide data center resource monitoring intuitive figure and
Report form showing, log management and alert process function.
Platform management layer is mainly counted, analyzed and is excavated to collected monitoring data, to the shape of data center
State makes accurately assessment and prediction, and data supporting is provided for showing for Portal boundary layers.
Data Convergence layer is the most important part of monitor supervision platform, assumes responsibility for the most important data acquisition function of monitor supervision platform,
It is also the key of platform property, the expansible protocol interface of this layer configuration multi-mode realizes the acquisition to monitoring data, and store
Into database.
Managed object layer is the various hardware and software resources of data center, is set including various servers, storage, network
Standby, database and application service, UPS, power distribution cabinet, precision air conditioner, gate inhibition, Temperature Humidity Sensor, smoke detector, temperature detection
A variety of monitored object such as device, leakage sensor, turning roof window and web camera etc..
Wherein, the Data Convergence layer function of configuration is the Core Feature of monitor supervision platform, carry accurately and timely collect and
Handle the task of various resource status data.
Data Convergence layer includes monitoring core engine, monitoring and scheduling process, alarm engine, data processing centre, active
Detect eight primary clusterings such as interrogator, passive type detection interrogator, modular extensible protocol interface, data storage, group
Cooperated between part, Each performs its own functions, it is final realize in data center server, storage, the network equipment, database and
Application service, UPS, power distribution cabinet, precision air conditioner, gate inhibition, Temperature Humidity Sensor, smoke detector, temperature detector, leak sensing
The data acquisition and monitoring of a variety of monitored object such as device, turning roof window and web camera etc. is that data center well stablizes
Operation provides digitlization and supports.Data processing centre is that the data of acquisition are carried out processing analysis, is the platform pipe of data center
Reason provides support.
The Functional Design of the main modular of monitoring data convergence layer is as follows:
(1) monitoring core engine:Monitoring management function is undertaken, is responsible for reading configuration file, distribution monitoring is configured to other
Component ensures processing consistency of the other assemblies to detection data, detects other engines whether in normal work, says the word
Drive scheduling process gathered data etc..And the administration portal in Web page is provided, administrator is allowed to match monitoring function
It puts, system is supported according to monitored object quantity and scheduling number of processes, the quantity of expanding monitoring configuration.
(2) monitoring and scheduling process:According to the configuration file of distribution, the state of active poll monitored object or reception poll
The monitoring data that device feedback is come up, judges monitoring data, when there is a certain index to exceed threshold value, generates certain event simultaneously
It is put into queue, while the data transfer of processing to data processing centre.
(3) engine is alerted:It is responsible for regularly inquiring the queue in scheduling process, is carried out for the event in queue specific
Processing, such as certain failures are carried out with automated diagnostic and processing or sends alarm email, short massage notice administrator.
(4) data processing centre:To the monitoring data that acquisition comes up, after scheduling process processing, it is persisted to number
According in library, as historical data, generation monitors the statistical informations such as tendency chart, historic state figure.
(5) interrogator is actively monitored:The extensible protocol interface of regular active access modules, obtains and is advised in configuration file
Fixed detection data, and data feedback is handled to monitoring and scheduling process.
(6) passive monitoring interrogator:It is driven by the timing of modular extensible protocol interface, passive reception agreement
Detection data specified in the configuration file that interface obtains, and data feedback is handled to monitoring and scheduling process.
(7) modular extensible protocol interface:The protocol interface realize IPMI protocol, snmp protocol, database and
Application service monitoring module etc. obtains monitoring data with the mode of various orders and analog access.And the protocol interface is supported
Modular it is integrated, allow customized agreement, third party's module or following certain agreement occurred it is seamless be integrated into this
In protocol interface.
(8) data store:Support the reading and write-in to multitype database.
The present invention realizes unified efficient monitoring management, the function of mainly realizing to the large-scale basis resource of data center
Including:
(1) it realizes and asset management, condition monitoring is carried out to the infrastructure of different vendor, different frameworks, different shape
And performance monitoring, including virtually or physically type;Cover physical computing resources and virtual computing resource, be locally stored, share and deposit
The storage modes such as storage, distributed storage, network three categories resource;Abundant monitored item type is provided, it is current including that can check
The utilization rate of computer CPU, memory, hard disk etc. can check network flow, magnetic disc i/o, into number of passes etc.;It can be with data
The Expansion at center, can also monitoring device quantity extending transversely.
(2) it realizes and asset management, condition monitoring and performance monitoring is carried out to the basic software resource of isomery;Support pair
Current process and information on services are checked in the monitoring of Linux/Unix and Windows operating system;Support to Tomcat,
The monitoring of the application servers such as IIS, Apache and the database servers such as SQL Server, MySQL, Oracle.
(3) the triggering alarm when system hardware, load occur abnormal is realized, reminds the timely maintenance issues equipment of user;
Long-term statistical analysis is carried out to the load of basic software and hardware resources, decision-making foundation is provided for scheduling of resource.By to monitoring number
According to analysis, data are carried out to other Premium Features (such as load balancing, fault recovery) of resource management system for data center
It supports, the continuity and quick response of application is effectively ensured.
(4) it realizes and is visited including UPS, power distribution cabinet, precision air conditioner, gate inhibition, Temperature Humidity Sensor, smoke detector, warming
Survey the management of a variety of monitored object such as device, leakage sensor, turning roof window and web camera.
The technology contents of the not detailed description of the present invention are known technology.
Claims (6)
1. the system for unified management design method of a kind of data center, which is characterized in that include the following steps:
The server node of data center is divided into multiple monitoring host computers, server component, with system for unified management server
Form multithreading monitoring system;
Extensible protocol interface for multithreading monitoring system configuration module;
The data processing method of Data Convergence layer is provided with for multithreading monitoring system;
Between system for unified management master server and monitoring host computer in multithreading monitoring system, monitoring host computer and server node
Between the monitoring method that is blended using active training in rotation and passive poll.
2. a kind of data center's system for unified management design method according to claim 1, which is characterized in that described multi-thread
Range monitoring system is distributed parallel working method, and each monitoring host computer is adjusted according to the server node quantity flexibility that it is managed
Data processing and the number of components of Data Convergence layer.
A kind of 3. data center's system for unified management design method according to claim 1, which is characterized in that the agreement
Interface includes Intelligent Platform Management Interface IPMI, Redfish agreement, network management snmp protocol, Modbus agreements, Web
Service agreements, protocol interface can be extended by custom protocol.
4. according to a kind of data center's system for unified management design method described in claim 1, which is characterized in that the monitoring side
Active training in rotation when method is including normal condition and passive poll during abnormality;The server node being monitored during active training in rotation
By state report to monitoring host computer within the setting period, meanwhile, monitoring host computer interval multiple setting periods are actively to monitored clothes
Business device node sends request, checks whether monitored resource is survived, be can be used;When monitoring host computer is anti-without information within the setting period
Feedback carries out passive poll to monitored server node, to confirm that monitored server node state and exception are alarmed.
5. according to a kind of data center's system for unified management design method described in claim 1, which is characterized in that at the data
Reason method includes Portal boundary layers, platform management layer, Data Convergence layer, managed object layer;The Portal boundary layers are used
In the figure and report form showing, the log management and alert process function that provide data center resource monitoring;The platform management layer
For collected monitoring data to be counted, analyzed and excavated, accurately assessment and pre- is made to the state of data center
It surveys, data supporting is provided for the showing for Portal boundary layers;It is described to carry out data acquisition for monitoring system, and be configured and can expand
Protocol interface is opened up, realizes the acquisition to monitoring data, and store into database;The managed object layer is data center
Monitored hardware and software resource, including various servers, storage, the network equipment, database and application service, UPS, distribution
Cabinet, precision air conditioner, gate inhibition, Temperature Humidity Sensor, smoke detector, temperature detector, leakage sensor, turning roof window and network
A variety of monitored object such as video camera.
6. according to a kind of data center's system for unified management design method described in claim 1, which is characterized in that the data are received
It holds back layer and includes monitoring core engine, monitoring and scheduling process, alarm engine, data processing centre, active detection interrogator, passive
Formula detection interrogator, modular extensible protocol interface, data storage component, monitored hardware to data center and soft
The data acquisition and monitoring of part resource provides digitlization for data center's stable operation and supports.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810026547.7A CN108259270A (en) | 2018-01-11 | 2018-01-11 | A kind of data center's system for unified management design method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810026547.7A CN108259270A (en) | 2018-01-11 | 2018-01-11 | A kind of data center's system for unified management design method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108259270A true CN108259270A (en) | 2018-07-06 |
Family
ID=62726147
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810026547.7A Pending CN108259270A (en) | 2018-01-11 | 2018-01-11 | A kind of data center's system for unified management design method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108259270A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108536555A (en) * | 2018-08-03 | 2018-09-14 | 中国人民解放军国防科技大学 | Data access method based on BCube (n, b) data center |
CN109828868A (en) * | 2019-01-04 | 2019-05-31 | 新华三技术有限公司成都分公司 | Date storage method, device, management equipment and dual-active data-storage system |
CN109933497A (en) * | 2019-03-12 | 2019-06-25 | 国网江西省电力有限公司赣州供电分公司 | A kind of data center's operation supervisory systems |
WO2020015061A1 (en) * | 2018-07-18 | 2020-01-23 | 平安科技(深圳)有限公司 | Monitoring alarm method, device and system for weblogic server, and computer storage medium |
CN110913662A (en) * | 2019-12-03 | 2020-03-24 | 中国工商银行股份有限公司 | Management method and device for data center, electronic equipment and medium |
CN111049881A (en) * | 2019-10-30 | 2020-04-21 | 烽火通信科技股份有限公司 | Cloud platform node resource monitoring method and system and computer readable medium |
CN111563018A (en) * | 2020-04-28 | 2020-08-21 | 北京航空航天大学 | Resource management and monitoring method of man-machine-object fusion cloud computing platform |
CN111817883A (en) * | 2020-06-23 | 2020-10-23 | 赛特斯信息科技股份有限公司 | Multi-data center resource intelligent scheduling control system |
CN112199197A (en) * | 2020-10-23 | 2021-01-08 | 网易(杭州)网络有限公司 | Server management method and system |
CN112882903A (en) * | 2020-12-23 | 2021-06-01 | 沈阳世纪高通科技有限公司 | Distributed monitoring method |
WO2021212748A1 (en) * | 2020-04-23 | 2021-10-28 | 苏州浪潮智能科技有限公司 | Polling method and system for server sensors, and related device |
CN114283520A (en) * | 2021-12-27 | 2022-04-05 | 苏州智康信息科技股份有限公司 | Self-service machine monitoring management method |
WO2022067915A1 (en) * | 2020-09-30 | 2022-04-07 | 苏州艾隆科技股份有限公司 | Operation and maintenance monitoring method, apparatus, and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7599293B1 (en) * | 2002-04-25 | 2009-10-06 | Lawrence Michael Bain | System and method for network traffic and I/O transaction monitoring of a high speed communications network |
CN101931592A (en) * | 2010-08-26 | 2010-12-29 | 北京科技大学 | WSN-based underground safety monitoring system gateway equipment |
CN103389715A (en) * | 2013-07-26 | 2013-11-13 | 浪潮电子信息产业股份有限公司 | High-performance distributed data center monitoring framework |
CN105305624A (en) * | 2015-10-28 | 2016-02-03 | 成都振中电气有限公司 | Intelligent power monitoring system |
CN105635279A (en) * | 2015-12-29 | 2016-06-01 | 长城信息产业股份有限公司 | Distributed monitor system and data acquisition method thereof |
-
2018
- 2018-01-11 CN CN201810026547.7A patent/CN108259270A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7599293B1 (en) * | 2002-04-25 | 2009-10-06 | Lawrence Michael Bain | System and method for network traffic and I/O transaction monitoring of a high speed communications network |
CN101931592A (en) * | 2010-08-26 | 2010-12-29 | 北京科技大学 | WSN-based underground safety monitoring system gateway equipment |
CN103389715A (en) * | 2013-07-26 | 2013-11-13 | 浪潮电子信息产业股份有限公司 | High-performance distributed data center monitoring framework |
CN105305624A (en) * | 2015-10-28 | 2016-02-03 | 成都振中电气有限公司 | Intelligent power monitoring system |
CN105635279A (en) * | 2015-12-29 | 2016-06-01 | 长城信息产业股份有限公司 | Distributed monitor system and data acquisition method thereof |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020015061A1 (en) * | 2018-07-18 | 2020-01-23 | 平安科技(深圳)有限公司 | Monitoring alarm method, device and system for weblogic server, and computer storage medium |
CN108536555A (en) * | 2018-08-03 | 2018-09-14 | 中国人民解放军国防科技大学 | Data access method based on BCube (n, b) data center |
CN109828868A (en) * | 2019-01-04 | 2019-05-31 | 新华三技术有限公司成都分公司 | Date storage method, device, management equipment and dual-active data-storage system |
CN109933497A (en) * | 2019-03-12 | 2019-06-25 | 国网江西省电力有限公司赣州供电分公司 | A kind of data center's operation supervisory systems |
CN111049881A (en) * | 2019-10-30 | 2020-04-21 | 烽火通信科技股份有限公司 | Cloud platform node resource monitoring method and system and computer readable medium |
CN111049881B (en) * | 2019-10-30 | 2022-07-22 | 烽火通信科技股份有限公司 | Cloud platform node resource monitoring method and system and computer readable medium |
CN110913662A (en) * | 2019-12-03 | 2020-03-24 | 中国工商银行股份有限公司 | Management method and device for data center, electronic equipment and medium |
CN110913662B (en) * | 2019-12-03 | 2021-09-10 | 中国工商银行股份有限公司 | Management method and device for data center, electronic equipment and medium |
US11706050B2 (en) | 2020-04-23 | 2023-07-18 | Inspur Suzhou Intelligent Technology Co., Ltd. | Polling method and system for server sensors, and related apparatus |
WO2021212748A1 (en) * | 2020-04-23 | 2021-10-28 | 苏州浪潮智能科技有限公司 | Polling method and system for server sensors, and related device |
CN111563018A (en) * | 2020-04-28 | 2020-08-21 | 北京航空航天大学 | Resource management and monitoring method of man-machine-object fusion cloud computing platform |
CN111817883A (en) * | 2020-06-23 | 2020-10-23 | 赛特斯信息科技股份有限公司 | Multi-data center resource intelligent scheduling control system |
WO2022067915A1 (en) * | 2020-09-30 | 2022-04-07 | 苏州艾隆科技股份有限公司 | Operation and maintenance monitoring method, apparatus, and storage medium |
CN112199197A (en) * | 2020-10-23 | 2021-01-08 | 网易(杭州)网络有限公司 | Server management method and system |
CN112199197B (en) * | 2020-10-23 | 2023-07-18 | 网易(杭州)网络有限公司 | Server management method and system |
CN112882903A (en) * | 2020-12-23 | 2021-06-01 | 沈阳世纪高通科技有限公司 | Distributed monitoring method |
CN114283520A (en) * | 2021-12-27 | 2022-04-05 | 苏州智康信息科技股份有限公司 | Self-service machine monitoring management method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108259270A (en) | A kind of data center's system for unified management design method | |
US11005730B2 (en) | System, method, and apparatus for high throughput ingestion for streaming telemetry data for network performance management | |
Castelli et al. | Proactive management of software aging | |
CN104506393B (en) | A kind of system monitoring method based on cloud platform | |
US8892719B2 (en) | Method and apparatus for monitoring network servers | |
RU2636848C2 (en) | Method of estimating power consumption | |
CN108092813A (en) | Data center's total management system server hardware Governance framework and implementation method | |
Gill et al. | RADAR: Self‐configuring and self‐healing in resource management for enhancing quality of cloud services | |
CN103595131B (en) | On-line monitoring system of transformer device of transformer substation | |
US20060074946A1 (en) | Point of view distributed agent methodology for network management | |
CN106487574A (en) | Automatic operating safeguards monitoring system | |
CN104113585A (en) | Hardware Level Generated Interrupts Indicating Load Balancing Status For A Node In A Virtualized Computing Environment | |
CN103973815A (en) | Method for unified monitoring of storage environment across data centers | |
CN103905553A (en) | Cloud architecture of energy efficiency management system and operation method thereof | |
CN101095307A (en) | Network management appliance | |
CN112751726B (en) | Data processing method and device, electronic equipment and storage medium | |
CN102819478B (en) | A kind of data handling system monitoring and management method without agency | |
Litvinova et al. | A proactive fault tolerance framework for high-performance computing | |
CN114389937A (en) | Operation and maintenance monitoring and management system | |
CN107678915A (en) | A kind of power transmission and transforming equipment monitoring platform basic resource monitoring method | |
CN112615737B (en) | Method and system for automatically monitoring service system | |
CN106209444A (en) | A kind of IT assets synergic monitoring system based on unified view | |
Lu et al. | Iaso: an autonomous fault-tolerant management system for supercomputers | |
CN107704361A (en) | A kind of power transmission and transforming equipment monitoring platform basic resource monitoring system | |
CN103078764A (en) | Operational monitoring system and method based on virtual computing task |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180706 |
|
RJ01 | Rejection of invention patent application after publication |