CN108243206A - A kind of server cluster area management method - Google Patents
A kind of server cluster area management method Download PDFInfo
- Publication number
- CN108243206A CN108243206A CN201611209390.9A CN201611209390A CN108243206A CN 108243206 A CN108243206 A CN 108243206A CN 201611209390 A CN201611209390 A CN 201611209390A CN 108243206 A CN108243206 A CN 108243206A
- Authority
- CN
- China
- Prior art keywords
- server
- cluster
- servers
- mentioned
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
-
- 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
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0659—Management of faults, events, alarms or notifications using network fault recovery by isolating or reconfiguring faulty entities
Abstract
The present invention provides a kind of server cluster area management method, physical address according to where server carries out cluster regions division, one standby server is set in each cluster regions, when the number of servers being abnormal in cluster regions is more, standby server is enabled as backup server, it avoids occupying more running servers as standby server, raising system overall operation efficiency, and performance and can physically reach the best demand of system.
Description
【Technical field】
The invention belongs to operation condition of server monitoring field more particularly to a kind of server cluster area management methods.
【Background technology】
Under normal circumstances, to the abnormal monitoring of server, it usually needs artificially carry out malfunction elimination, this artificial investigation side
Method waste of manpower resource, investigation accuracy are low, and cannot remotely be monitored and visualized management.
In the prior art, also there are some methods for carrying out remote monitoring to calculating operation condition of server in system,
But when finding server exception, the selection to backup server is typically random, and backup server is in performance and physics
The best demand of system is generally unable to reach on position.
Based on the above problem, now there is an urgent need for a kind of a kind of new server cluster area management method, according to server institute
Physical address carry out cluster regions division, in each cluster regions set a standby server, in cluster regions
When the number of servers being abnormal is more, standby server is enabled as backup server, avoids occupying more running
Server improves system overall operation efficiency as standby server, and performance and can physically reach system and most preferably need
It asks.
【Invention content】
In order to solve the above problem of the prior art, it is visual that the present invention proposes a kind of cloud system operation condition of server
Change management method.
The technical solution adopted by the present invention is as follows：
A kind of server cluster area management method, which is characterized in that the system comprises multiple calculation servers, clusters
Zone management server and multiple standby servers, wherein cluster regions management server connect above-mentioned multiple calculation servers and
Above-mentioned backup server, for managing the state of above-mentioned multiple calculation servers, this method comprises the following steps：
(1) cluster regions management server obtains the actual physical address of multiple calculation servers；
(2) cluster regions management server divides multiple calculation servers according to the above-mentioned actual physical address of acquisition
For the computer cluster in several regions, the physical distance between each computer in computer cluster in the region
In predetermined threshold range；
(3) standby server is set in above-mentioned each region, and the standby server may be provided at each region
A computer location vicinity in interior computer cluster.
Beneficial effects of the present invention include：Physical address according to where server carries out cluster regions division, each
One standby server in cluster regions is set, when the number of servers being abnormal in cluster regions is more, is enabled spare
Server avoids occupying more running servers as standby server, raising system is integrally transported as backup server
Line efficiency, and performance and can physically reach the best demand of system.
【Description of the drawings】
Attached drawing described herein is to be used to provide further understanding of the present invention, and forms the part of the application, but
It does not constitute improper limitations of the present invention, in the accompanying drawings：
Fig. 1 is the structure chart of present system；
Fig. 2 is the flow chart of server cluster area management method of the present invention.
【Specific embodiment】
Come that the present invention will be described in detail below in conjunction with attached drawing and specific embodiment, illustrative examples therein and say
It is bright to be only used for explaining the present invention, but not as a limitation of the invention.
It is the system that the present invention is applied referring to attached drawing 1, the system comprises multiple calculation servers, cluster regions to manage
Manage server and multiple standby servers, wherein cluster regions management server connects above-mentioned multiple calculation servers and above-mentioned standby
Part server, for managing the state of above-mentioned multiple calculation servers
In one embodiment, the system comprises multiple cloud computing servers, status visualization management server and
Multiple standby servers, wherein status visualization management server connect above-mentioned multiple cloud computing servers and above-mentioned backup services
Device, for managing the state of above-mentioned multiple cloud computing servers.
Referring to attached drawing 2, embodiment 1, a kind of server cluster area management method, this method comprises the following steps：
(1) cluster regions management server obtains the actual physical address of multiple calculation servers；
(2) cluster regions management server divides multiple calculation servers according to the above-mentioned actual physical address of acquisition
For the computer cluster in several regions, the physical distance between each computer in computer cluster in the region
In predetermined threshold range；
(3) standby server is set in above-mentioned each region, and the standby server may be provided at each region
A computer location vicinity in interior computer cluster.
Embodiment 2, this method comprises the following steps：
(1) status visualization management server classifies to multiple cloud computing servers.
In one embodiment, according to multiple cloud computing servers calculate, storage and communication aspects different performance
It is divided into calculation type server, storage-type server and communication type service device, setup algorithm threshold value stores threshold value and communication threshold,
Calculation type server subject to judging if the computing capability of calculation server is being calculated on threshold value, the computing capability of server
It can be weighed with the quantity of every server processing request per second；If the storage capacity of calculation server storage threshold value it
On then judge subject to storage-type server, the storage capacity of server can weigh with the hard disc storage capacity of every server
Amount；Communication type service device subject to judging if the communication capacity of calculation server is on communication threshold, the communication of server
Ability can send and receive quantity or the rate of information throughout of data packet with every server to weigh within the unit interval
Amount.
If server be only judged subject to one in calculation type, storage-type or communication type service device, by above-mentioned clothes
Business device is classified as corresponding calculation type, storage-type or communication type service device.
If server be judged subject in calculation type, storage-type or communication type service device at least two, i.e. server
Storage capacity, communication capacity or computing capability both be at least more than respective threshold, then which aspect of performance to be more than phase according to
The ratio highest of threshold value is answered, then is respective server by classification server.
Such as server storage ability, beyond storage threshold value 20%, computing capability is beyond calculating threshold value 30%, communication capacity
Beyond communication threshold 40%, i.e., the server be first judged subject to calculation type, storage-type and communication type service device, and due to logical
Letter ability exceeds 40% highest of ratio of communication threshold, and most the classification server is communication type service device at last.
(2) status visualization management server obtains the actual physical address of multiple cloud computing servers.
In one embodiment, the multiple cloud computing server determines it by the GPS module unit being arranged inside
Residing actual physical address, and send above-mentioned actual physical address to above-mentioned status visualization management server.
(3) status visualization management server is according to the above-mentioned actual physical address of acquisition, by multiple cloud computing servers
The computer cluster being divided into several regions, the physics between each computer in computer cluster in the region
Distance is in predetermined threshold range.
(4) standby server is set in above-mentioned each region.
In one embodiment, the standby server may be provided at one in the computer cluster in each region
Computer location vicinity.
(5) the display end generation server state management map of status visualization management server.
In one embodiment, label has multiple regions, each region on the server state management map
Each computer server and redundant computer in interior computer cluster are marked according to actual physical address accordingly
Figure position, the computer server icon representation of each calculation server same shape in the computer cluster, and use
Different computer server marks are distinguished, the redundant computer icon representation of the redundant computer same shape,
And it is distinguished with different redundant computer marks.
(6) status visualization management server monitors whether above-mentioned multiple cloud computing servers are abnormal in real time.
(7) status visualization management server is monitored if there is cloud computing server is abnormal, then in server shape
Abnormal marking, and selection and determining backup server are carried out to the above-mentioned cloud computing server being abnormal on state management map.
In one embodiment, abnormal marking can represent that different types of exception is different with an abnormal mark
Abnormal mark carries out difference expression, and the exception includes one in abnormal processing, communication abnormality and the abnormal three types of storage.
It is abnormal abnormal for processing if monitoring server to be abnormal in data calculating or processing procedure, if monitoring clothes
It is engaged in being abnormal in the data storage procedure of device, then it is abnormal abnormal for storage, if monitoring server is sending or is receiving letter
Exception is sent in breath or process data packet, then it is abnormal to be determined as communication abnormality.
Further,
(7-1) is abnormal when status visualization management server monitors a cloud computing server, then：
(7-1-1) carries out abnormal mark on server state management map to the above-mentioned cloud computing server being abnormal
Note；
(7-1-2) determines the type for the cloud computing server being abnormal, and the type is calculation type server, storage-type
One in server and communication type service device；
(7-1-3) determines the cluster regions where the cloud computing server being abnormal；
(7-1-4) one no exceptions of selection from multiple cloud computing servers in determining above-mentioned cluster regions
Server is as backup server, wherein selected backup server and the type phase for the cloud computing server being abnormal
Together；
(7-2) is abnormal when remote status visualized management server monitoring to m cloud computing server, and wherein m >=
2, then：
(7-2-1) carries out above-mentioned m cloud computing server being abnormal on server state management map abnormal
Label；
(7-2-2) determines the respective cluster regions where m cloud computing server being abnormal；
(7-2-3) is located at different cluster regions respectively in case of m abnormal cloud computing server, then from determining
The server of a no exceptions is selected in multiple cloud computing servers in above-mentioned respective cluster regions as backup services
Device, wherein the type of cloud computing server of the selected backup server with being abnormal is identical；
(7-2-4) is located at k cluster regions in case of m abnormal cloud computing server, wherein each cluster regions
In there is n or more cloud computing server to be abnormal, wherein 2≤n≤m, k >=1, then from each cluster in k cluster regions
N-1 cloud computing server of no exceptions is selected in multiple cloud computing servers in region respectively as backup server,
Wherein selected n-1 backup server is identical with the type of n-1 cloud computing server being abnormal, while swashs respectively
Standby server in k cluster regions living is as a backup server in cluster each in above-mentioned k cluster regions.
Assuming that there is 4 cloud computing servers to be abnormal, this 4 abnormal servers are located at 2 cluster regions, each cluster
There are 2 abnormal servers in region, there is 6 calculation servers and a standby server in each cluster regions, determines to occur different
The type of normal server selects the server of 1 no exceptions as a backup server in each cluster regions,
And the type of server is identical with a type in 2 servers being abnormal in the cluster regions, as the type phase
The backup server of the same server being abnormal, for another different types of server being abnormal, then selects
Standby server in the cluster regions is as its backup server.The number of servers being abnormal due to each cluster regions
It is higher (2/6) to account for cluster regions number of servers, therefore selects standby server as backup server rather than selection cluster
In runtime server as backup server, therefore avoid bigger being caused to influence the operation of whole region other servers, carry
High system overall operation efficiency.
(8) to selected backup server into line activating processing, to selected on server state management map
The backup server selected carries out backup server activation tagging.
By the above method, physical address of the present invention according to where server carries out cluster regions division, in each collection
Group sets a standby server in region, when the number of servers being abnormal in cluster regions is more, enables spare clothes
Device be engaged in as backup server, avoids occupying more running servers as standby server, improves system overall operation
Efficiency, and performance and can physically reach the best demand of system.
The above is only the better embodiment of the present invention, therefore all constructions according to described in present patent application range,
The equivalent change or modification that feature and principle are done, is included in the range of present patent application.
Claims (2)
1. a kind of server cluster area management method, which is characterized in that the system comprises multiple calculation servers, the areas of concentration
Field managing server and multiple standby servers, wherein cluster regions management server connect above-mentioned multiple calculation servers and upper
Backup server is stated, for managing the state of above-mentioned multiple calculation servers, this method comprises the following steps：
(1) cluster regions management server obtains the actual physical address of multiple calculation servers；
(2) cluster regions management server is according to the above-mentioned actual physical address of acquisition, if multiple calculation servers are divided into
Computer cluster in dry region, the physical distance between each computer in computer cluster in the region is pre-
Determine in threshold range；
(3) standby server is set in above-mentioned each region, and the standby server may be provided in each region
A computer location vicinity in computer cluster.
2. server cluster area management method according to claim 1, which is characterized in that the multiple calculation server
Actual physical address residing for it is determined, and above-mentioned actual physical address is sent to by the GPS module unit being arranged inside
Above-mentioned cluster regions management server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611209390.9A CN108243206B (en) | 2016-12-23 | 2016-12-23 | A kind of server cluster area management method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611209390.9A CN108243206B (en) | 2016-12-23 | 2016-12-23 | A kind of server cluster area management method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108243206A true CN108243206A (en) | 2018-07-03 |
| CN108243206B CN108243206B (en) | 2019-03-29 |
Family
ID=62704335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611209390.9A Active CN108243206B (en) | 2016-12-23 | 2016-12-23 | A kind of server cluster area management method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108243206B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101355476A (en) * | 2008-05-23 | 2009-01-28 | 林云帆 | System and method for storing, distributing and applying data files based on server cluster |
| CN102143215A (en) * | 2011-01-20 | 2011-08-03 | 中国人民解放军理工大学 | Network-based PB level cloud storage system and processing method thereof |
| CN102571772A (en) * | 2011-12-26 | 2012-07-11 | 华中科技大学 | Hot spot balancing method for metadata server |
| CN103685467A (en) * | 2013-11-15 | 2014-03-26 | 伏治军 | Interconnection and internetworking platform of Internet of things, and communication method thereof |
| CN104091375A (en) * | 2014-06-08 | 2014-10-08 | 山东天海科技股份有限公司 | A vehicle network monitoring system based on a Beidou positioning system |
| WO2014186225A1 (en) * | 2013-05-15 | 2014-11-20 | Citrix Systems, Inc. | Systems and methods for deploying a spotted virtual server in a cluster system |
| CN104601949A (en) * | 2014-12-29 | 2015-05-06 | 天维尔信息科技股份有限公司 | Delayering emergency command dispatching device, delayering emergency command dispatching system and delayering emergency command dispatching method |
| CN106131102A (en) * | 2016-06-01 | 2016-11-16 | 乐视控股（北京）有限公司 | A kind of method and device of distribution server |
-
2016
- 2016-12-23 CN CN201611209390.9A patent/CN108243206B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101355476A (en) * | 2008-05-23 | 2009-01-28 | 林云帆 | System and method for storing, distributing and applying data files based on server cluster |
| CN102143215A (en) * | 2011-01-20 | 2011-08-03 | 中国人民解放军理工大学 | Network-based PB level cloud storage system and processing method thereof |
| CN102571772A (en) * | 2011-12-26 | 2012-07-11 | 华中科技大学 | Hot spot balancing method for metadata server |
| WO2014186225A1 (en) * | 2013-05-15 | 2014-11-20 | Citrix Systems, Inc. | Systems and methods for deploying a spotted virtual server in a cluster system |
| CN103685467A (en) * | 2013-11-15 | 2014-03-26 | 伏治军 | Interconnection and internetworking platform of Internet of things, and communication method thereof |
| CN104091375A (en) * | 2014-06-08 | 2014-10-08 | 山东天海科技股份有限公司 | A vehicle network monitoring system based on a Beidou positioning system |
| CN104601949A (en) * | 2014-12-29 | 2015-05-06 | 天维尔信息科技股份有限公司 | Delayering emergency command dispatching device, delayering emergency command dispatching system and delayering emergency command dispatching method |
| CN106131102A (en) * | 2016-06-01 | 2016-11-16 | 乐视控股（北京）有限公司 | A kind of method and device of distribution server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108243206B (en) | 2019-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106789257B (en) | A kind of cloud system server state visual management method | |
| CN101111981B (en) | Mapping power system components | |
| CN103067297B (en) | A kind of dynamic load balancing method based on resource consumption prediction and device | |
| CN104011719B (en) | The method and system that message is tracked and checked | |
| CN102308559A (en) | Voting arbitration method and apparatus for cluster computer system | |
| US8443078B2 (en) | Method of determining equivalent subsets of agents to gather information for a fabric | |
| CN110784355B (en) | Fault identification method and device | |
| CN105872061B (en) | A kind of server set group managing means, apparatus and system | |
| CN106161092A (en) | A kind of network distributing failure emergency repair work order distributing method and device | |
| CN105243004A (en) | Failure resource detection method and apparatus | |
| CN111966289A (en) | Partition optimization method and system based on Kafka cluster | |
| CN106603299A (en) | Service health index generation method and service health index generation device | |
| CN103763126A (en) | System and method for monitoring database and database monitoring device | |
| CN110659180A (en) | Data center infrastructure management system based on cluster technology | |
| CN108241567B (en) | A kind of cloud system server state management map method | |
| CN110995785A (en) | Low-voltage distribution network cloud platform based on Internet of things | |
| CN113163353B (en) | Intelligent health service system of power supply vehicle and data transmission method thereof | |
| CN101997741B (en) | Network monitoring method and system for rail transit equipment state | |
| US8850321B2 (en) | Cross-domain business service management | |
| CN108932182A (en) | A kind of messaging bus performance test methods and system | |
| CN106021046A (en) | Hard disk performance comparison method, device and server | |
| CN109032320A (en) | Battery back unit test method and relevant device | |
| CN108243030A (en) | A kind of backup server selects management method | |
| CN111104283B (en) | Fault detection method, device, equipment and medium of distributed storage system | |
| CN104025628A (en) | Network system, node device group, sensor device group, and method for transmitting and receiving sensor data |
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 | ||
| CB02 | Change of applicant information |
Address after: 101399 No. 2 East Airport Road, Shunyi Airport Economic Core Area, Beijing (1st, 5th and 7th floors of Industrial Park 1A-4) Applicant after: Zhongke Star Map Co., Ltd. Address before: 101399 Building 1A-4, National Geographic Information Technology Industrial Park, Guomen Business District, Shunyi District, Beijing Applicant before: Space Star Technology (Beijing) Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information |
Inventor after: Chen Wei Inventor after: Wu Fangcai Inventor after: Lin Yin Inventor after: Liu Bin Inventor before: Wu Fangcai Inventor before: Lin Yin Inventor before: Liu Bin |
|
| CB03 | Change of inventor or designer information |