CN108777637A - A kind of data center's total management system and method for supporting server isomery - Google Patents
A kind of data center's total management system and method for supporting server isomery Download PDFInfo
- Publication number
- CN108777637A CN108777637A CN201810541454.8A CN201810541454A CN108777637A CN 108777637 A CN108777637 A CN 108777637A CN 201810541454 A CN201810541454 A CN 201810541454A CN 108777637 A CN108777637 A CN 108777637A
- Authority
- CN
- China
- Prior art keywords
- data center
- server
- management system
- total management
- isomery
- 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
- 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
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Computer And Data Communications (AREA)
Abstract
The present invention relates to a kind of data center's total management systems and method for supporting server isomery.Data center's total management system of the support server isomery of the present invention includes providing the heterogeneous nodes server end of cloud service, data center's total management system platform agent end of each data center and data center's total management system platform end in service front-end.It is an advantage of the invention that contributing to the unified management of data center, especially the scene monitored is needed simultaneously being related to physical resource and virtual resource, has more fine-grained hardware monitoring, the cloud server cluster of different scales can be suitble to monitor demand, with higher network adaptability and flexible autgmentability, there is reference significance for the server hardware management system for studying similar.
Description
Technical field
The present invention relates to technical field of data processing, relate in particular to a kind of support the data center of server isomery comprehensive
Management system is closed, a kind of data center's integrated management approach for supporting server isomery is further related to.
Background technology
With the rapid development of big data information industry, the development of data center also enters a new stage.In number
It measures in numerous information datas, since the source of data source is different, data type, data structure are also varied.Due to not
Data source with data structure will use different analysis logics, cause in the data source progress to multiple and different data structures
When data analysis, cannot these data sources directly be carried out with unified processing using general analysis logic.Management system is several
The important component configured according to central interior.Traditional management system mainly based on power & environment supervision, has a variety of data and connects
Mouthful, it can access UPS, power distribution cabinet, precision air conditioner, gate inhibition, Temperature Humidity Sensor, smoke detector, temperature detector, leak sensing
A variety of monitored object such as device, turning roof window and web camera.Currently, with the quick hair of cloud computing, big data and internet
Exhibition, information-based infrastructure have occurred right-about, and the demand of monitoring management is converted into whole from some individual system requirements
Body hardware and software platform, the unified platform, unified management system requirements.Every application server is no longer individual computing module, but
By the platforms such as cloud computing, big data will calculate, storage resource unite, across data center's range formed it is in large scale,
The resource pool of unified monitoring and management, it is therefore desirable to extensive, distributed, cross-region virtual resource can be monitored and physics provides
The unified monitoring system in source.The problem of being never concerned under the scene of number of servers scale is smaller, it is swollen in server farms
Swollen today is but exposed one after another.High-level problem is how both to have ensured high availability (SLA:Service-
LevelAgreement), and efficiency (efficiency of reaching the standard grade and remediation efficiency) can be improved, additionally it is possible to reduce TCO (hardware cost, personnel
Cost).The concept of unified monitoring is come into being at this time, but still is weak, short slab therein be exactly server hardware monitoring (including
Calculation server and storage server) it is not smart enough, today, intelligent server hardware monitoring had become IT operation personnel
(ITOperations changes from O&M to operation) pays close attention to one of object.Such as：It is relatively low (at present that hardware fault quotes rate
About 70%), hardware fault positioning is extensive, causes remediation efficiency low (time), and rehabilitation cost is high (time repairs)；It is also typical
Server batch problem, hardware difficult and complicated cases traffic affecting problem, Server Lifecycle the problem of how controlling, data
The relatively low problem etc. of the energy consumption cost problem of server, whole resource utilization in center.
Invention content
The present invention provides a kind of data center's total management system and method for supporting server isomery, to realize cloud service
Heterogeneous nodes server real-time dynamic monitoring in device cluster and warning function so that data center's total management system is uniformly received
Enter under designed server hardware management service frame, constructs an integrated management system of data center efficiently, stable
System.
In order to solve the above-mentioned technical problem, the invention discloses following technical schemes：
First aspect present invention provides a kind of data center's total management system for supporting server isomery, including provides
The heterogeneous nodes server end of cloud service, data center's total management system platform agent end of each data center and in service
Data center's total management system platform end of front end；The heterogeneous nodes server end responsible node server system performance letter
The acquisition of breath；Platform agent end installation is responsible for being acquired the load information of each node server and dynamic analysis, and
Timing is reported to data center's total management system platform end；Data center's total management system platform end and platform agent
End communication connection, data center's total management system platform end are responsible for receiving all platform agent ends load information in administering
Collection summarizes, calculates and analyzes.
Further, the heterogeneous nodes server end installs MonitorClient programs, responsible node server system
The acquisition of performance information.Specially：Pass through Performance Logsand Alerts (the performance inventory days of call operation system
Will and alarm) service, be periodically to cpu busy percentage, memory usage, the disk utilization rate etc. of current heterogeneous nodes server
Performance of uniting and the information of load carry out dynamic acquisition, and are periodically reported to data center's total management system platform.
Further, MonitorServer programs are installed at platform agent end, are responsible for the load information to each node server
It is acquired and dynamic analysis, periodically each supervised entities actively inquire after, the network for obtaining each isomery node server is rung
Between seasonable；It is collected simultaneously the real-time CPU profits that each isomery node server is obtained by locally-installed MonitorClient programs
With the system performances such as rate, memory usage, disk utilization rate and load information；To the load of each isomery node server into action
State comprehensive analysis forms dynamic property library and dynamic alarm library, and timing is reported to data center's total management system platform end.
The present invention uses Simple Network Management Protocol SNMP for basic communication mode, and the algorithm that data collection framework is carried out with Java is retouched
It states, IPMI protocol and Modbus agreements is carried out the encapsulation of MIB formats, define the method for compatible new acquisition protocols and can be changed
Acquisition strategies, define protocol encapsulation template pattern, the configuration mode of configuration database storage module used between defining,
Upper layer module can reinform system refresh configuration to achieve the purpose that update configuration by the configuration of change database.It uses
Standardized interface mode runs main program, defines IMPI agreements and Modbus agreements correspond to MIB nodes, systematic unity is difference
Monitoring information distribute MIB nodes.The interface reunification between heterogeneous server and management platform can be solved by MIB,
Long-range device object to be monitored identifies in MIB.
Further, data center's total management system platform end installation procedure includes cloud platform real-time monitoring module and cloud
Dispatching management module, cloud platform real-time monitoring module be responsible for dynamic receive Ji Ge data centers total management system platform it is real-time on
The performance library of report and alarm library, visualize the performance and load state for presenting administer all heterogeneous nodes servers in real time, right
The high heterogeneous nodes server of integrated load Distribution Indexes carries out early warning and shows；Cloud dispatching management module is periodically calculated and is sorted
The integrated load index at platform agent end, when new cloud service asks to reach, Analysis Service type will be asked by request type
It is forwarded to the minimum platform agent end of weighted comprehensive loading index in dynamic load table, meanwhile, to the void in cloud cluster server
Quasi- machine carries out dynamic migration, to the manual troubleshooting in failure platform agent end.
Further, data center's total management system platform end uses double-machine standby technology, introduces Backup Data
Center total management system platform end, to ensure the high availability and robustness of scheduling.Under normal circumstances, comprehensive by primary data center
It closes management system platform end and service is externally provided, once primary data center total management system platform end is broken down, backup number
Corresponding work will be taken over immediately according to center total management system platform end, to ensure being normally carried out for cloud service.
Further, the integrated secure management end includes all kinds of host systems of high in the clouds and incoming end, provides end and arrives
The safe practice supportability at end, and abundant Restful API are provided, it can be carried out with data center's total management system deep
The integrated and linkage of degree, realizes the automation of cloud data center safety management, reduces O&M cost.
The invention also discloses a kind of data center's integrated management approach for supporting server isomery, include the following steps：
Acquire heterogeneous nodes server system performance information；
Collection system performance information is analyzed dynamic performance index information and is reported and summarizes to data center's total management system
Platform end；
Load information data is calculated and analyzed, data center's total management system platform agent end is sent a command to.
Further, the specific method of acquisition heterogeneous nodes server system performance information is：With the relevant data of network
It is acquired using snmp protocol, is acquired using IPMI protocol with the relevant data of hardware parameter, some UPS and precision are empty
Call the acquisition of Modus agreements.
Further, the implementation process at platform agent end is as follows：
(1) according to the application scenarios of data center, the core of data collection framework is exactly to carrying out data by monitoring equipment
Acquisition, includes the static datas such as server name, model, memory, hard disk size here, also includes the net of server node
Mouth rate, network interface input flow rate, network interface output flow, network interface controlled state, system CPU load, temperature, voltage, fan etc. are dynamic
State information.Wherein with the relevant data of network (such as network interface rate, network interface input flow rate, network interface output flow, network interface controlled state
Deng) be acquired using snmp protocol, use IPMI protocol with the relevant data of hardware parameter (such as temperature, voltage, fan)
It is acquired, some UPS and precision air conditioner are acquired with Modus agreements, including power supply parameter, load factor or wind pushing temperature etc..
(2) system is by snmp protocol, IPMI protocol and Modbus protocol encapsulations to acquisition module, according to acquisition node
The calling related service of channel selectivity carries out operation, and systematic unity is that different monitoring informations distributes MIB nodes, remotely waits supervising
Measurement equipment object is exactly to be identified in MIB；The data information of the main storage system of database, is divided into database allocation list and data
Library information table.Allocation list is used to store the configuration information of system, mainly include each equipment acquisition node configuration information and
The configuration information etc. of acquisition strategies engine, and information table is mainly used to store the collection result of monitored device.Due to node
Acquisition channel has SNMP, IPMI and Modbus agreement etc., therefore wanted when realizing can be according to node for bottom data acquisition
Channel species selectivity must call corresponding acquisition method.
(3) platform agent end carries out periodic polling, the inquiry and control of device node response management platform to device node
Order, and by result loopback, this completes the unified monitoring processing to heterogeneous server.
Specifically, the workflow at platform agent end includes following steps：
1. nodal information is read in platform agent end from the database allocation list at platform end first, the first of nodal analysis method is completed
Beginningization；
2. protocol encapsulation module assembles agreement according to node channel Different Dynamic, working node can encapsulate corresponding agreement letter
Breath；
3. input parameter：It is dynamic to assemble agreement and return it into according to the channel type of node；
4. output parameter：Model node object, channel object；
5. return value：The protocol object of the node；
6. system will use SNMP4J tools to carry out core process encapsulation and integrate, this method initializes snmp protocol node,
And it returns the result；
7. determining transport protocol and instantiating Snmp objects；
8. monitoring snmp message, construction sends target, and driving acquisition is completed；
9. the data that acquisition is completed are reported to platform end；
10. repeating 1.~9. step, circle collection process is completed.
In the present invention, heterogeneous nodes server is the server for really providing specific service to the user.Node server pair
It is transparent for user, according to the service that user requires, there may be multiple heterogeneous nodes servers to participate in specific cloud service,
Distributed storage or parallel computation including data etc..Heterogeneous nodes server is normally at some data center or some cloud clothes
Business device cluster.Platform agent end is responsible for controlling the real-time performance and integrated status for administering each isomery node server, to data
The server cluster at center is monitored in real time, to extra-heavy server carry out early warning, fault management with restore etc. work, together
When, the data acquired in real time are periodically sent to data center's total management system platform end.Under cloud server cluster environment,
To adapt to, to high requests such as the high-performance of server, high availability and flexible autgmentabilities, need to introduce data center's integrated pipe
System platform end is managed, to serve as the allocator of service role and the manager of cloud.Introduce data center's total management system platform
Behind end, cloud server cluster externally has unique IP, i.e. data center's total management system platform end IP, also referred to as cloud
Location.Data center's total management system platform end is the command centre of entire cloud.After user submits cloud service to ask, data center
It can analyze according to built-in scheduling strategy and determine the heterogeneous nodes server that service is really provided at total management system platform end
And service diverting search is carried out, user is not required to know that whom the specific server for providing service is.Integrated safety management is towards support
Cloud data center physics, fictitious host computer system, virtualization software, PC service terminals, the autonomous Intelligent Service of server isomery are whole
The host software Software for Design in the fields such as end is the mode of management that Host Security is reinforced, and is to constitute cloud security system of the present invention
Core provides comprehensive security capabilities guarantee for cloud security.The integrated secure management of the present invention implements unified safety prison
Control and visualized management, by base map monitoring mode can complete perception sorts of systems safe condition, quickly position the whole network it is high-risk
Resource and security incident, improve the ability of safe emergency response, and have abundant Security Trend analysis, safe TOP analyses, reality
When the analysis such as Safety actuality and alarm ability.Integrated secure management of the present invention supports classification decentralized management, can pass through
Resource group, policy template, the combination of backup and reduction function, provide the convenient management such as the maintenance of batch strategy and update.
Compared with prior art, the beneficial effects of the invention are as follows：The present invention contributes to the unified management of data center, especially
It is to have more fine-grained hardware monitoring in the scene for being related to physical resource and virtual resource and needing to monitor simultaneously, it is of the invention
Three-in-one framework, can be suitble to different scales cloud server cluster monitor demand, have higher network adaptability with
Flexible autgmentability has reference significance for the server hardware management system for studying similar.
Description of the drawings
Fig. 1 is the connection relationship diagram of data center's total management system of the support server isomery of the present invention；
Fig. 2 is the overall workflow figure of the present invention；
Fig. 3 is the work flow diagram at platform agent end of the present invention；
Wherein, 1- heterogeneous nodes server end；2- data centers total management system platform agent end；3- data centers are comprehensive
Close management system platform end；
31- cloud platform real-time monitoring modules；32- cloud dispatching management modules.
Specific implementation mode
In order to make those skilled in the art more fully understand the technical solution in the present invention, below in conjunction with attached drawing to this
The technical solution of invention is clearly and completely described, it is clear that described embodiment is only that a present invention part is implemented
Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creativeness
The every other embodiment obtained under the premise of labour, should all belong to the scope of protection of the invention.
First, understanding to embodiment for convenience, below to involved in embodiment initialism and Key Term give
Explanation and illustration：API refers to application programming interfaces.
Embodiment 1
As shown in Figure 1, data center's total management system of the support server isomery of the present invention is by offer cloud service
Heterogeneous nodes server end, data center's total management system platform agent end of each data center, the number in service front-end
It is formed according to center total management system platform end and integrated safety management.The present invention is set using Client/Server frameworks
Meter, each specific design of layering are as follows：
Heterogeneous nodes server end installs MonitorClient programs, and responsible node server system performance information is adopted
Collection.Specially：It is taken by the Performance Logs and Alerts (performance inventory daily record and alarm) of call operation system
Business, it is periodical to system performances such as cpu busy percentage, memory usage, the disk utilization rates of current heterogeneous nodes server and negative
The information of load carries out dynamic acquisition, and is periodically reported to data center's total management system platform.The platform agent end installation
MonitorServer programs are responsible for being acquired the load information of each node server and dynamic analysis, periodically to each supervision
Object actively inquire after, and obtains the network response time of each isomery node server；It is collected simultaneously each isomery node server
Real-time cpu busy percentage, memory usage, disk utilization rate for being obtained by locally-installed MonitorClient programs etc. are
Performance of uniting and load information；Integrated dynamic analysis is carried out to the load of each isomery node server, dynamic property library is formed and moves
State alerts library, and timing is reported to data center's total management system platform end.The present invention uses Simple Network Management Protocol
SNMP is basic communication mode, and the algorithm description of data collection framework is carried out with Java, IPMI protocol and Modbus agreements into
The encapsulation of row MIB formats defines the method for compatible new acquisition protocols and variable acquisition strategies, defines protocol encapsulation mould
Block pattern has used the configuration mode of configuration database storage module, upper layer module can be by changing database between defining
Configuration, reinform system refresh configuration come achieve the purpose that update configuration.Main program is run using standardized interface mode,
It defines IMPI agreements and Modbus agreements corresponds to MIB nodes, systematic unity is that different monitoring informations distributes MIB nodes.Pass through
MIB can solve the interface reunification between heterogeneous server and management platform, and long-range device object to be monitored is got the bid in MIB
Know.Data center's total management system platform end installation procedure includes cloud platform real-time monitoring module and cloud management and running mould
Block, cloud platform real-time monitoring module are responsible for the performance library that dynamic receives Ji Ge data centers total management system platform real-time report
And alarm library, the performance and load state for presenting administer all heterogeneous nodes servers in real time are visualized, integrated load is referred to
Mark distributes high heterogeneous nodes server progress early warning and shows；Cloud dispatching management module periodically calculates and platform agent end of sorting
Integrated load index, when new cloud service asks to reach, Analysis Service type forwards requests to dynamic by request type
The minimum platform agent end of weighted comprehensive loading index in table is loaded, meanwhile, to the virtual machine in cloud cluster server into action
State migrates, to the manual troubleshooting in failure platform agent end.The integrated secure management end includes each of high in the clouds and incoming end
Class host system provides end-by-end security technique support capability, and provides abundant Restful API, can in data
Heart total management system carries out the integrated of depth and linkage, realizes the automation of cloud data center safety management, reduce O&M at
This.
In the present embodiment, data center's total management system platform end uses double-machine standby technology, introduces backup number
According to center total management system platform end, to ensure the high availability and robustness of scheduling.Under normal circumstances, by primary data center
Total management system platform end externally provides service, once primary data center total management system platform end is broken down, backup
Data center's total management system platform end will take over corresponding work immediately, to ensure being normally carried out for cloud service.
Embodiment 2
A kind of data center's integrated management approach for supporting server isomery, includes the following steps：
Acquire heterogeneous nodes server system performance information；
Collection system performance information is analyzed dynamic performance index information and is reported and summarizes to data center's total management system
Platform end；
Load information data is calculated and analyzed, data center's total management system platform agent end is sent a command to.
Specifically, data center's integrated management approach of the support server isomery of the present embodiment, includes the following steps：
The performance real time information of heterogeneous nodes server end periodically acquisition server itself is (including cpu busy percentage, interior
Deposit the system performance informations such as utilization rate, disk utilization rate), periodically performance real time information is reported and gives data center's integrated management
System, response are asked by the cloud service that data center's total management system platform end forwards；
Data center's total management system platform agent end periodic harvest is administered each isomery node server and is periodically reported
The integrated performance index information of announcement is periodically actively inquired after the network response time of each isomery node server, and visualization is real
The performance state of the administered heterogeneous nodes servers of Shi Chengxian, divides the performance indicator of heterogeneous nodes collection of server in real time
Analysis, the heterogeneous nodes server high to integrated load Distribution Indexes carry out early warning, and failure is carried out to failure heterogeneous nodes server
Processing and recovery etc. periodically form joint behavior summary sheet, and are reported to data center's total management system platform end；
Periodically all platform agent ends load information in administering is received at data center's total management system platform end
Collection summarizes, and periodically calculates and the integrated load index at platform agent end of sorting, when new cloud service request reaches, Analysis Service class
Type, according to nearby and just low principle from the minimum platform agent end of nearest data center and load, look for respectively with currently
Service type is identical and loads relatively small platform agent end, forwards requests to weighted comprehensive load in dynamic load table and refers to
Mark minimum platform agent end；
System permission separation and strong access control are completed in integrated safety management end, to system core catalogue, file, into
The strong access control of the carry out such as journey, service, executable program changes in real-time perception system, and is implemented according to the level of trust of program
Control, it is ensured that and legal executable program energy normal operation；Compliance is detected and is repaired, and is differentiated to host system identity, is accessed
Control, security audit, using the security functions such as utilizing to implement compliance detection, reduce host system compliance risk；Master is provided
Machine firewall functionality can be directed to the point-to-point access control of host implementation.
In the present embodiment, the implementation process at platform agent end is as follows：
(1) according to the application scenarios of data center, the core of data collection framework is exactly to carrying out data by monitoring equipment
Acquisition, includes the static datas such as server name, model, memory, hard disk size here, also includes the net of server node
Mouth rate, network interface input flow rate, network interface output flow, network interface controlled state, system CPU load, temperature, voltage, fan etc. are dynamic
State information.Wherein with the relevant data of network (such as network interface rate, network interface input flow rate, network interface output flow, network interface controlled state
Deng) be acquired using snmp protocol, use IPMI protocol with the relevant data of hardware parameter (such as temperature, voltage, fan)
It is acquired, some UPS and precision air conditioner are acquired with Modus agreements, including power supply parameter, load factor or wind pushing temperature etc..
(2) system is by snmp protocol, IPMI protocol and Modbus protocol encapsulations to acquisition module, according to acquisition node
The calling related service of channel selectivity carries out operation, and systematic unity is that different monitoring informations distributes MIB nodes, remotely waits supervising
Measurement equipment object is exactly to be identified in MIB；The data information of the main storage system of database, is divided into database allocation list and data
Library information table.Allocation list is used to store the configuration information of system, mainly include each equipment acquisition node configuration information and
The configuration information etc. of acquisition strategies engine, and information table is mainly used to store the collection result of monitored device.Due to node
Acquisition channel has SNMP, IPMI and Modbus agreement etc., therefore wanted when realizing can be according to node for bottom data acquisition
Channel species selectivity must call corresponding acquisition method.
(3) platform agent end carries out periodic polling, the inquiry and control of device node response management platform to device node
Order, and by result loopback, this completes the unified monitoring processing to heterogeneous server.
Specifically, the workflow at the present embodiment platform agent end includes following steps：
1. nodal information is read in platform agent end from the database allocation list at platform end first, the first of nodal analysis method is completed
Beginningization；
2. protocol encapsulation module assembles agreement according to node channel Different Dynamic, working node can encapsulate corresponding agreement letter
Breath；
3. input parameter：It is dynamic to assemble agreement and return it into according to the channel type of node；
4. output parameter：Model node object, channel object；
5. return value：The protocol object of the node；
6. system will use SNMP4J tools to carry out core process encapsulation and integrate, this method initializes snmp protocol node,
And it returns the result；
7. determining transport protocol and instantiating Snmp objects；
8. monitoring snmp message, construction sends target, and driving acquisition is completed；
9. the data that acquisition is completed are reported to platform end
10. repeating 1.~9. step, circle collection process is completed.
In the present invention, heterogeneous nodes server is the server for really providing specific service to the user.Node server pair
It is transparent for user, according to the service that user requires, there may be multiple heterogeneous nodes servers to participate in specific cloud service,
Distributed storage or parallel computation including data etc..Heterogeneous nodes server is normally at some data center or some cloud clothes
Business device cluster.Platform agent end is responsible for controlling the real-time performance and integrated status for administering each isomery node server, to data
The server cluster at center is monitored in real time, to extra-heavy server carry out early warning, fault management with restore etc. work, together
When, the data acquired in real time are periodically sent to data center's total management system platform end.Under cloud server cluster environment,
To adapt to, to high requests such as the high-performance of server, high availability and flexible autgmentabilities, need to introduce data center's integrated pipe
System platform end is managed, to serve as the allocator of service role and the manager of cloud.Introduce data center's total management system platform
Behind end, cloud server cluster externally has unique IP, i.e. data center's total management system platform end IP, also referred to as cloud
Location.Data center's total management system platform end is the command centre of entire cloud.After user submits cloud service to ask, data center
It can analyze according to built-in scheduling strategy and determine the heterogeneous nodes server that service is really provided at total management system platform end
And service diverting search is carried out, user is not required to know that whom the specific server for providing service is.Integrated safety management is towards support
Cloud data center physics, fictitious host computer system, virtualization software, PC service terminals, the autonomous Intelligent Service of server isomery are whole
The host software Software for Design in the fields such as end is the mode of management that Host Security is reinforced, and is to constitute cloud security system of the present invention
Core provides comprehensive security capabilities guarantee for cloud security.The integrated secure management of the present invention implements unified safety prison
Control and visualized management, by base map monitoring mode can complete perception sorts of systems safe condition, quickly position the whole network it is high-risk
Resource and security incident, improve the ability of safe emergency response, and have abundant Security Trend analysis, safe TOP analyses, reality
When the analysis such as Safety actuality and alarm ability.Integrated secure management of the present invention supports classification decentralized management, can pass through
Resource group, policy template, the combination of backup and reduction function, provide the convenient management such as the maintenance of batch strategy and update.
The above is only the specific implementation mode of the present invention, is made skilled artisans appreciate that or realizing this hair
It is bright.Various modifications to these embodiments will be apparent to one skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (8)
1. a kind of data center's total management system for supporting server isomery, which is characterized in that including providing the different of cloud service
Structure node server end, data center's total management system platform agent end of each data center and the data in service front-end
Center total management system platform end；
The acquisition of the heterogeneous nodes server end responsible node server system performance information；
Platform agent end installation is responsible for being acquired the load information of each node server and dynamic analysis, and in timing
Offer data center's total management system platform end；
Data center's total management system platform end is communicated to connect with platform agent end, and data center's total management system is flat
End, which is responsible for being collected all platform agent ends load information in administering, to be summarized, calculate and analyzes.
2. the data center's total management system according to claim 1 for supporting server isomery, which is characterized in that described
Heterogeneous nodes server end installs MonitorClient programs.
3. the data center's total management system according to claim 2 for supporting server isomery, which is characterized in that described
Heterogeneous nodes server end is serviced by the Performance Logs and Alerts of call operation system, periodically to working as
The system performance of preceding heterogeneous nodes server and the information of load carry out dynamic acquisition.
4. the data center's total management system according to claim 1 for supporting server isomery, which is characterized in that platform
Agent side is acquired to the load information of each node server by installation MonitorServer programs and dynamic analysis, fixed
Phase to each supervised entities actively inquire after, and obtains the network response time of each isomery node server；Collect each heterogeneous nodes
The real-time system performance and load information that server passes through locally-installed MonitorClient programs acquisition；To each isomery section
The load of point server carries out integrated dynamic analysis, forms dynamic property library and dynamic alarm library, and timing is reported in data
Heart total management system platform end.
5. the data center's total management system according to claim 1 for supporting server isomery, which is characterized in that data
Center total management system platform end installation procedure includes cloud platform real-time monitoring module and cloud dispatching management module.
6. the data center's total management system according to claim 1 for supporting server isomery, which is characterized in that described
Data center's total management system platform end uses double-machine standby technology.
7. a kind of data center's integrated management approach for supporting server isomery, which is characterized in that include the following steps：
Acquire heterogeneous nodes server system performance information；
Collection system performance information is analyzed dynamic performance index information and is reported and summarizes to data center's total management system platform
End；
Load information data is calculated and analyzed, data center's total management system platform agent end is sent a command to.
8. the data center's integrated management approach according to claim 7 for supporting server isomery, which is characterized in that acquisition
The specific method of heterogeneous nodes server system performance information is：It is acquired using snmp protocol with the relevant data of network,
It is acquired using IPMI protocol with the relevant data of hardware parameter, some UPS and precision air conditioner are acquired with Modus agreements.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810541454.8A CN108777637A (en) | 2018-05-30 | 2018-05-30 | A kind of data center's total management system and method for supporting server isomery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810541454.8A CN108777637A (en) | 2018-05-30 | 2018-05-30 | A kind of data center's total management system and method for supporting server isomery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108777637A true CN108777637A (en) | 2018-11-09 |
Family
ID=64028037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810541454.8A Pending CN108777637A (en) | 2018-05-30 | 2018-05-30 | A kind of data center's total management system and method for supporting server isomery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108777637A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110096366A (en) * | 2019-05-10 | 2019-08-06 | 苏州浪潮智能科技有限公司 | A kind of configuration method, device and the server of isomery memory system |
| CN110391954A (en) * | 2019-07-19 | 2019-10-29 | 苏州浪潮智能科技有限公司 | A kind of SNMP automatic alarm testing method, system, terminal and storage medium |
| CN110597681A (en) * | 2019-04-26 | 2019-12-20 | 贵州广思信息网络有限公司 | Server hardware monitoring system |
| CN111459415A (en) * | 2020-04-15 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Cross-cloud data migration method, device, equipment and storage medium |
| 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 |
| CN111884853A (en) * | 2020-07-29 | 2020-11-03 | 浪潮云信息技术股份公司 | Cloud environment automatic resource management method and system |
| CN116828045A (en) * | 2023-05-15 | 2023-09-29 | 嵩山实验室 | Management system and management method of heterogeneous computing server |
| US20230379300A1 (en) * | 2022-05-19 | 2023-11-23 | Cisco Technology, Inc. | Authorization and audit control in a multi-protocol iot domain |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103281366A (en) * | 2013-05-21 | 2013-09-04 | 山东地纬计算机软件有限公司 | Embedded agency monitoring device and method supporting real-time operating state acquiring |
| CN105024851A (en) * | 2015-06-25 | 2015-11-04 | 四川理工学院 | Cloud computing-based monitoring management system |
| US20160080402A1 (en) * | 2014-09-12 | 2016-03-17 | Level 3 Communications, Llc | Dynamic configuration of settings in response to ddos attack |
| CN106254172A (en) * | 2016-07-14 | 2016-12-21 | 东软集团股份有限公司 | Heterogeneous applications collecting method and device |
| CN106961367A (en) * | 2017-05-19 | 2017-07-18 | 济南浪潮高新科技投资发展有限公司 | Cloud resource monitoring and method based on openstack |
-
2018
- 2018-05-30 CN CN201810541454.8A patent/CN108777637A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103281366A (en) * | 2013-05-21 | 2013-09-04 | 山东地纬计算机软件有限公司 | Embedded agency monitoring device and method supporting real-time operating state acquiring |
| US20160080402A1 (en) * | 2014-09-12 | 2016-03-17 | Level 3 Communications, Llc | Dynamic configuration of settings in response to ddos attack |
| CN105024851A (en) * | 2015-06-25 | 2015-11-04 | 四川理工学院 | Cloud computing-based monitoring management system |
| CN106254172A (en) * | 2016-07-14 | 2016-12-21 | 东软集团股份有限公司 | Heterogeneous applications collecting method and device |
| CN106961367A (en) * | 2017-05-19 | 2017-07-18 | 济南浪潮高新科技投资发展有限公司 | Cloud resource monitoring and method based on openstack |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110597681A (en) * | 2019-04-26 | 2019-12-20 | 贵州广思信息网络有限公司 | Server hardware monitoring system |
| CN110096366A (en) * | 2019-05-10 | 2019-08-06 | 苏州浪潮智能科技有限公司 | A kind of configuration method, device and the server of isomery memory system |
| CN110391954A (en) * | 2019-07-19 | 2019-10-29 | 苏州浪潮智能科技有限公司 | A kind of SNMP automatic alarm testing method, system, terminal and storage medium |
| CN111459415A (en) * | 2020-04-15 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Cross-cloud data migration method, device, equipment and storage medium |
| 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 |
| CN111884853A (en) * | 2020-07-29 | 2020-11-03 | 浪潮云信息技术股份公司 | Cloud environment automatic resource management method and system |
| US20230379300A1 (en) * | 2022-05-19 | 2023-11-23 | Cisco Technology, Inc. | Authorization and audit control in a multi-protocol iot domain |
| US12041033B2 (en) * | 2022-05-19 | 2024-07-16 | Cisco Technology, Inc. | Authorization and audit control in a multi-protocol IoT domain |
| CN116828045A (en) * | 2023-05-15 | 2023-09-29 | 嵩山实验室 | Management system and management method of heterogeneous computing server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108777637A (en) | A kind of data center's total management system and method for supporting server isomery | |
| CN102882969B (en) | A kind of safety production cloud service platform of industrial and mining enterprises | |
| CN102932419B (en) | A kind of data-storage system for the safety production cloud service platform towards industrial and mining enterprises | |
| CN105843182B (en) | A kind of power scheduling accident prediction system and method based on OMS | |
| CN102917032B (en) | A kind of safety production cloud service platform of industrial and mining enterprises | |
| CN112102111A (en) | Intelligent processing system for power plant data | |
| CN109934402A (en) | A kind of wind power plant centralized control center concentrate wind power prediction system and its design method | |
| CN102880802B (en) | A kind of assay method for the major hazard source towards industrial and mining establishment's safety production cloud service platform system | |
| CN108092813A (en) | Data center's total management system server hardware Governance framework and implementation method | |
| CN107786616A (en) | Main frame intelligent monitor system based on high in the clouds | |
| CN102929827B (en) | A kind of wireless sensor data for ore deposit enterprise safety in production cloud platform gathers cluster | |
| CN102903011A (en) | Mass data processing system used for safety production cloud service platform facing industrial and mining enterprises | |
| CN102903010A (en) | Support vector machine-based abnormal judgment method for safety production cloud service platform orientating industrial and mining enterprises | |
| CN102930372A (en) | Data analysis method for association rule of cloud service platform system orienting to safe production of industrial and mining enterprises | |
| CN102917031A (en) | Data computing system of safety production cloud service platform for industrial and mining enterprises | |
| CN107968482A (en) | A kind of generation of electricity by new energy station management platform | |
| CN107910956A (en) | A kind of integrated power network schedule automation operation comprehensive supervision method of main plant stand | |
| CN114169579B (en) | Nuclear Power Industry Internet Comprehensive Intelligent Platform System | |
| CN112883001A (en) | Data processing method, device and medium based on marketing and distribution through data visualization platform | |
| CN107657389A (en) | A kind of demand Side Management platform | |
| CN114757797B (en) | Power grid resource service central platform architecture method based on data model drive | |
| CN102903009B (en) | Malfunction diagnosis method based on generalized rule reasoning and used for safety production cloud service platform facing industrial and mining enterprises | |
| CN113516331A (en) | Building data processing method and device | |
| CN104579784B (en) | Power industry Control System NetWork management method based on multidimensional virtual link | |
| CN114138501B (en) | Processing method and device for edge intelligent service for field safety 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181109 |
|
| RJ01 | Rejection of invention patent application after publication |