CN106326050A - Automatic monitoring management method for whole cabinet server - Google Patents

Automatic monitoring management method for whole cabinet server Download PDF

Info

Publication number
CN106326050A
CN106326050A CN201610693486.0A CN201610693486A CN106326050A CN 106326050 A CN106326050 A CN 106326050A CN 201610693486 A CN201610693486 A CN 201610693486A CN 106326050 A CN106326050 A CN 106326050A
Authority
CN
China
Prior art keywords
information
rmc
continue
configuration
whole machine
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201610693486.0A
Other languages
Chinese (zh)
Inventor
张兆民
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inspur Electronic Information Industry Co Ltd
Original Assignee
Inspur Electronic Information Industry Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Inspur Electronic Information Industry Co Ltd filed Critical Inspur Electronic Information Industry Co Ltd
Priority to CN201610693486.0A priority Critical patent/CN106326050A/en
Publication of CN106326050A publication Critical patent/CN106326050A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/22Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
    • G06F11/2205Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested
    • G06F11/221Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested to test buses, lines or interfaces, e.g. stuck-at or open line faults
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/22Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
    • G06F11/2289Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing by configuration test

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Debugging And Monitoring (AREA)

Abstract

The invention discloses an automatic monitoring and management method for a whole cabinet server, which relates to the technical field of computers, and is characterized in that configuration information of a whole cabinet is completely acquired through an RMC (remote management center), the RMC generates a configuration file according to the configuration information, and corresponding parts in the whole cabinet are automatically monitored and managed according to the configuration file, wherein the method mainly comprises an RMC automatic detection power supply, an RMC automatic detection node middle plate, middle plate automatic detection fan information and middle plate automatic detection node information; and displaying the component information corresponding to the configuration according to the configuration of the cabinet. The invention avoids the probability of error without manual participation, realizes automatic management, reduces the complexity of maintenance, can be rapidly deployed in a short time in a large scale, reduces the operation and maintenance threshold, saves the working time and greatly improves the efficiency.

Description

A kind of server automated method for managing and monitoring of whole machine cabinet
Technical field
The present invention relates to field of computer technology, a kind of server automated monitoring management side of whole machine cabinet Method.
Background technology
The arriving of big data age, brings challenge to server industries, and whole machine cabinet server is applied more to come in practice The most extensive, the cluster server being made up of numerous whole machine cabinet is more and more universal.Integrated tens servers in each whole machine cabinet Node, is managed collectively by the RMC (Rack Management Controller) of responsible whole machine cabinet monitoring management, concentrates prison Control.The parts of the main monitoring management of RMC have server node, plate in node, PSU, fan control board, and fan etc., according to machine room Power supply capacity and the difference of the business form, often integrated in rack node, fan, the number of PSU etc. is not quite similar.
The method that whole machine cabinet server is monitored management legacy has two kinds, and one is right for different rack configurations RMC carries out secondary development, is allowed to adaptive different configuration, but owing to configuration is changeable and combines numerous, uses this customization Method often seems unable to do what one wishes, needs to expend substantial amounts of manpower and develops, safeguards, this method seldom can use;Second The method of kind, by operation maintenance personnel according to different rack configurations, writes configuration file, and RMC obtains rack according to configuration file Composition information, is managed, and this procedure is complicated, and link is too much, easily makes mistakes, although avoid secondary development, but Same needs manually participate in.
In view of the development of server industries, from traditional whole machine cabinet toward the conceptual change of computing pool, RMC is by the top managing tree End, becomes intermediate member, and the automated management of RMC becomes design and developer needs the problem of solution badly, and this is also intelligent The steps necessary of management development.
Summary of the invention
The present invention is directed to demand and the weak point of current technology development, it is provided that a kind of ARM platform one whole machine cabinet service The automatically-monitored management method of device.
A kind of server automated method for managing and monitoring of whole machine cabinet of the present invention, solves the skill that above-mentioned technical problem uses Art scheme is as follows: described a kind of server automated method for managing and monitoring of whole machine cabinet, is intactly obtained joining of whole machine cabinet by RMC Confidence ceases, and RMC generates configuration file according to configuration information, and according to portion corresponding in configuration file automatic monitoring management whole machine cabinet Part, mainly including automatically detecting power supply, RMC by RMC, automatically to detect plate in node, middle plate fan auto-detection information, middle plate automatic Detection nodal information;Component information according to rack configuration display this configuration corresponding.
Preferably, described RMC automatically detects power supply and mainly comprises the steps:
(1) RMC is according to the address RAP1 of IPMI protocol scanning bus RI2C1, it may be judged whether there is PSUA1;
(2) if equipment exists, then continue to read other information of PSUA1;
(3) jump to step (1) and continue to scan on the address RAP2 of RI2C1 ... RAP5, obtain PSUA2 ... the letter of PSUA5 Breath, jumps to step (4) after the end of scan;
(4) jump to step (1) and continue to scan on the address RAP1 of bus RI2C2 ... RAP5, obtain B road power information, knot Shu Jixu step (5);
(5) summary information, generates the profile information of power supply, terminates scanning.
Preferably, described RMC automatically detects plate in node and mainly comprises the steps:
(1) RMC is by the address RAM1 of IPMI protocol scanning bus RI2C3, it may be judged whether there is MB1;
(2) if equipment exists, then the fan of MB1 management, nodal information are read;
(3) jump to step (1) and continue to scan on RI2C4 ... RI2C12, obtain MB2 ... the information of MB10;
(4) scanned, the profile information of plate in generation, terminated scanning.
Preferably, described middle plate fan auto-detection information is primarily referred to as, and middle plate reads MI2C1 bus, collects fan letter Breath, when plate during RMC accesses, will send information to RMC.
Preferably, described middle plate automatically detects nodal information and mainly comprises the steps:
(1) in, plate is according to the address MAN1 of IPMI protocol scanning bus MI2C2, it may be judged whether there is node ND1;
(2) if equipment exists, then continue to read other information and the type of recognition node of node ND1;
(3) jump to step (1) and continue to scan on the address MAN2 of MI2C2 ... MAN8, obtain ND2 ... the information of ND8, sweep Step (4) is jumped to after retouching end;
(4) jump to step (1) and continue to scan on bus MI2C3 ... the address MAN1 of MI2C5 ... MAN8, obtain other U Nodal information, terminate continue step (5);
(5) summary information, when plate during RMC accesses, is sent to nodal information in RMC, terminates this intermittent scanning.
It is useful that the server automated method for managing and monitoring of a kind of whole machine cabinet of the present invention compared with prior art has Effect is: the present invention can scan the composition of whole machine cabinet automatically by RMC, is monitored managing to rack according to scanning result; When rack configuration changes, RMC can change monitoring information timely, it is not necessary to the artificial probability participating in avoiding makeing mistakes, real Existing automated management, decreases the complexity of maintenance, can short time rapid deployment on a large scale;RMC is by the configuration of whole machine cabinet Information is saved in file, and configuration file therein also can be modified by operation maintenance personnel, it is achieved self-defined to existing node Configuration, also provides artificial differential management interface while ensureing automated management;
The present invention is directed to the rack of different train or the demand that user is different, can be identified easily by RMC Configuration information, it is not necessary to develop RMC software for difference configuration or be manually entered configuration information, the whole automatization of whole process Carry out, it is also possible to the increase and decrease of automatic adaptation rack composition configuration, decrease RMC development amount and avoid again opening of product Send out, meanwhile, reduce O&M threshold, save the working time, drastically increase efficiency.
Figure of description
Accompanying drawing 1 is the flow chart of the described server automated method for managing and monitoring of a kind of whole machine cabinet.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, to this Bright described a kind of server automated method for managing and monitoring of whole machine cabinet further describes.
A kind of server automated method for managing and monitoring of whole machine cabinet of the present invention, at whole machine cabinet server RMC (Rack Management Controler, monitoring management unit) in, the configuration information of whole machine cabinet, RMC root is intactly obtained by RMC Generate configuration file according to configuration information, and according to corresponding component in configuration file automatic monitoring management whole machine cabinet, join according to rack Put the component information of display this configuration corresponding;For node number, power supply number and the position of different rack configurations, it is right to select The heat radiation speed governing curve answered.
The server automated method for managing and monitoring of whole machine cabinet that the present invention proposes, can identify whole machine cabinet server automatically The configuration combination that hardware is different, when configuration changes, RMC can update configuration information automatically, and record change daily record.And not Multiple RMC version, or manual amendment's configuration must be safeguarded, be substantially reduced exploitation and maintenance difficulties.
Embodiment:
Before the present embodiment described in whole machine cabinet server automated method for managing and monitoring is discussed in detail, the present embodiment is to whole In equipment cabinet server, relevant assembly illustrates, and mainly includes plate part in the I2C bus of RMC, power pack, node, and Fan and server node section.
The I2C bus of described RMC: I2C bus is numbered and is designated as RI2C1, RI2C2 ... RI2C12.
Described power pack: definition RI2C1, RI2C2 connect A road, B road power supply respectively, and wherein A road power supply comprises five electricity Source is designated as PSUA1 ... PSUA5, B road power supply comprises five power supplys and is designated as PSUB1 ... PSUB5;The power supply of two-way power supply PSU1 ... the address of PSU5 is RAP1, RAP2, RAP3, RAP4, RAP5.
Plate part in described node: definition RI2C3 ... RI2C12 connects plate MB1 in ten nodes respectively ... MB10; In node, the address of plate is RAM1.
Described fan and server node section: define each middle plate (MB) and comprise five road I2C bus: MI2C1 ... MI2C5;Each middle plate connects a fan control board (FB), then these ten middle plate MB1 by MI2C1 ... MB10 manages respectively FB1 ... FB10, each fan control board is unified connects three fans (FAN).Each middle plate is respectively by bus MI2C2 ... Can there is 1 to 8 server nodes (ND) or other equipment in the 4U, every U of MI2C5 management rack, the I2C address that can distribute For MAN1 ... MAN8.
Described in the present embodiment, a kind of server automated method for managing and monitoring of whole machine cabinet, automatically detects whole machine cabinet by RMC Node, middle plate, fan control board, fan, power supply number and the positional information in rack present in server, RMC according to Information result, generate configuration file, monitoring management automatic to corresponding parts, mainly include RMC automatically detect power supply, RMC detects plate in node automatically, middle plate fan auto-detection information, middle plate detect nodal information automatically;Aobvious according to rack configuration Show the component information of this configuration corresponding.
Described RMC detects power supply as shown in Figure 1 automatically, mainly comprises the steps:
(1) RMC is according to the address RAP1 of IPMI protocol scanning bus RI2C1, it may be judged whether there is PSUA1;
(2) if equipment exists, then continue to read other information of PSUA1;
(3) jump to step (1) and continue to scan on the address RAP2 of RI2C1 ... RAP5, obtain PSUA2 ... the letter of PSUA5 Breath, jumps to step (4) after the end of scan;
(4) jump to step (1) and continue to scan on the address RAP1 of bus RI2C2 ... RAP5, obtain B road power information, knot Shu Jixu step (5);
(5) summary information, generates the profile information of power supply, terminates scanning;Timing performs step (1).
Described RMC automatically detects plate in node and mainly comprises the steps:
(1) RMC is by the address RAM1 of IPMI protocol scanning bus RI2C3, it may be judged whether there is MB1;
(2) if equipment exists, then the fan of MB1 management, nodal information are read;
(3) jump to step (1) and continue to scan on RI2C4 ... RI2C12, obtain MB2 ... the information of MB10;
(4) scanned, the profile information of plate in generation, terminated scanning;Timing performs step (1).
Described middle plate fan auto-detection information is primarily referred to as, and middle plate reads MI2C1 bus, collects fan information, works as RMC In access during plate, will send information to RMC.
Described middle plate automatically detects nodal information and mainly comprises the steps:
(1) in, plate is according to the address MAN1 of IPMI protocol scanning bus MI2C2, it may be judged whether there is node ND1;
(2) if equipment exists, then continue to read other information and the type of recognition node of node ND1;
(3) jump to step (1) and continue to scan on the address MAN2 of MI2C2 ... MAN8, obtain ND2 ... the information of ND8, sweep Step (4) is jumped to after retouching end;
(4) jump to step (1) and continue to scan on bus MI2C3 ... the address MAN1 of MI2C5 ... MAN8, obtain other U Nodal information, terminate continue step (5);
(5) summary information, when plate during RMC accesses, is sent to nodal information in RMC, terminates this intermittent scanning;Regularly Perform step (1).
Additionally, the server automated method for managing and monitoring of whole machine cabinet described in the present embodiment, by above Four processes, RMC The configuration information getting whole machine cabinet that can be complete, it is possible to identify the configuration group that whole machine cabinet server hardware is different automatically Closing, when rack configuration changes, RMC can change configuration information the most timely, and record change daily record;Even if disposing Rack does after completing some increases and decreases, and RMC can also be the most newly configured, substantially increases automaticity, decreases fortune Row maintenance cost.The configuration information of whole machine cabinet is saved in file by RMC, and configuration file therein can be carried out by operation maintenance personnel Amendment, it is achieved custom-configure existing node, also provides artificial differentiation pipe while ensureing automated management Reason interface.Corresponding dissipating can be selected for node number, power supply number and the position of different rack configurations by the present invention Hot speed governing curve.
Above-mentioned detailed description of the invention is only the concrete case of the present invention, and the scope of patent protection of the present invention includes but not limited to Above-mentioned detailed description of the invention, any that meet claims of the present invention and any person of an ordinary skill in the technical field The suitably change being done it or replacement, all should fall into the scope of patent protection of the present invention.

Claims (5)

1. the server automated method for managing and monitoring of whole machine cabinet, it is characterised in that intactly obtained whole machine cabinet by RMC Configuration information, RMC generates configuration file according to configuration information, and according to portion corresponding in configuration file automatic monitoring management whole machine cabinet Part, mainly including automatically detecting power supply, RMC by RMC, automatically to detect plate in node, middle plate fan auto-detection information, middle plate automatic Detection nodal information;Component information according to rack configuration display this configuration corresponding.
A kind of server automated method for managing and monitoring of whole machine cabinet, it is characterised in that described RMC Automatically detection power supply mainly comprises the steps:
(1) RMC is according to the address RAP1 of IPMI protocol scanning bus RI2C1, it may be judged whether there is PSUA1;
(2) if equipment exists, then continue to read other information of PSUA1;
(3) jump to step (1) and continue to scan on the address RAP2 of RI2C1 ... RAP5, obtain PSUA2 ... the information of PSUA5, sweep Step (4) is jumped to after retouching end;
(4) jump to step (1) and continue to scan on the address RAP1 of bus RI2C2 ... RAP5, obtain B road power information, terminate to continue Continuous step (5);
(5) summary information, generates the profile information of power supply, terminates scanning.
A kind of server automated method for managing and monitoring of whole machine cabinet, it is characterised in that described RMC Automatically in detection node, plate mainly comprises the steps:
(1) RMC is by the address RAM1 of IPMI protocol scanning bus RI2C3, it may be judged whether there is MB1;
(2) if equipment exists, then the fan of MB1 management, nodal information are read;
(3) jump to step (1) and continue to scan on RI2C4 ... RI2C12, obtain MB2 ... the information of MB10;
(4) scanned, the profile information of plate in generation, terminated scanning.
A kind of server automated method for managing and monitoring of whole machine cabinet, it is characterised in that described middle plate Fan auto-detection information is primarily referred to as, and middle plate reads MI2C1 bus, collects fan information, when plate during RMC accesses, and will letter Breath is sent to RMC.
A kind of server automated method for managing and monitoring of whole machine cabinet, it is characterised in that described middle plate Automatically detection nodal information mainly comprises the steps:
(1) in, plate is according to the address MAN1 of IPMI protocol scanning bus MI2C2, it may be judged whether there is node ND1;
(2) if equipment exists, then continue to read other information and the type of recognition node of node ND1;
(3) jump to step (1) and continue to scan on the address MAN2 of MI2C2 ... MAN8, obtain ND2 ... the information of ND8, scanning knot Step (4) is jumped to after bundle;
(4) jump to step (1) and continue to scan on bus MI2C3 ... the address MAN1 of MI2C5 ... MAN8, obtain the joint of other U Dot information, terminates to continue step (5);
(5) summary information, when plate during RMC accesses, is sent to nodal information in RMC, terminates this intermittent scanning.
CN201610693486.0A 2016-08-18 2016-08-18 Automatic monitoring management method for whole cabinet server Pending CN106326050A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610693486.0A CN106326050A (en) 2016-08-18 2016-08-18 Automatic monitoring management method for whole cabinet server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610693486.0A CN106326050A (en) 2016-08-18 2016-08-18 Automatic monitoring management method for whole cabinet server

Publications (1)

Publication Number Publication Date
CN106326050A true CN106326050A (en) 2017-01-11

Family

ID=57743746

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610693486.0A Pending CN106326050A (en) 2016-08-18 2016-08-18 Automatic monitoring management method for whole cabinet server

Country Status (1)

Country Link
CN (1) CN106326050A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108255678A (en) * 2018-01-24 2018-07-06 郑州云海信息技术有限公司 Monitoring nodes method, apparatus and storage medium based on Rack whole machine cabinets
CN109189644A (en) * 2018-09-17 2019-01-11 郑州云海信息技术有限公司 Whole machine cabinet RMC, the method and system that whole machine cabinet increases number of nodes newly are automatically configured

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104809041A (en) * 2015-05-07 2015-07-29 浪潮电子信息产业股份有限公司 Batch test method for server power supply of whole cabinet
CN105119746A (en) * 2015-08-27 2015-12-02 浪潮电子信息产业股份有限公司 Intelligent monitoring method for SMARTRACK whole cabinet server configuration based on RMC management
CN105302690A (en) * 2015-10-14 2016-02-03 浪潮电子信息产业股份有限公司 Whole cabinet server monitoring and management method
US20160070627A1 (en) * 2014-09-08 2016-03-10 Quanta Computer Inc. Backup management control in a server system
CN105404570A (en) * 2015-12-11 2016-03-16 浪潮电子信息产业股份有限公司 Method for detecting information of whole cabinet through RMC
CN105868077A (en) * 2016-04-12 2016-08-17 浪潮电子信息产业股份有限公司 Method for acquiring monitoring information of server nodes of whole cabinet

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160070627A1 (en) * 2014-09-08 2016-03-10 Quanta Computer Inc. Backup management control in a server system
CN104809041A (en) * 2015-05-07 2015-07-29 浪潮电子信息产业股份有限公司 Batch test method for server power supply of whole cabinet
CN105119746A (en) * 2015-08-27 2015-12-02 浪潮电子信息产业股份有限公司 Intelligent monitoring method for SMARTRACK whole cabinet server configuration based on RMC management
CN105302690A (en) * 2015-10-14 2016-02-03 浪潮电子信息产业股份有限公司 Whole cabinet server monitoring and management method
CN105404570A (en) * 2015-12-11 2016-03-16 浪潮电子信息产业股份有限公司 Method for detecting information of whole cabinet through RMC
CN105868077A (en) * 2016-04-12 2016-08-17 浪潮电子信息产业股份有限公司 Method for acquiring monitoring information of server nodes of whole cabinet

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108255678A (en) * 2018-01-24 2018-07-06 郑州云海信息技术有限公司 Monitoring nodes method, apparatus and storage medium based on Rack whole machine cabinets
CN109189644A (en) * 2018-09-17 2019-01-11 郑州云海信息技术有限公司 Whole machine cabinet RMC, the method and system that whole machine cabinet increases number of nodes newly are automatically configured
CN109189644B (en) * 2018-09-17 2021-10-22 郑州云海信息技术有限公司 Whole cabinet RMC, and method and system for automatically configuring number of newly added nodes of whole cabinet

Similar Documents

Publication Publication Date Title
CN107368365A (en) Cloud platform automatic O&M method, system, equipment and storage medium
US11063901B2 (en) Manufacturing line computer system and network setup method of the same
CN102509178A (en) Distribution network device status evaluating system
CN103197640B (en) Production technology intelligence managing and control system and method
CN107395379A (en) A kind of cluster cruising inspection system and method
CN105024849A (en) Method for batch operation of high-density cabinet server on each node BMC
CN105653322B (en) The processing method of O&M server and server event
CN107577545A (en) A kind of failed disk detection and restorative procedure and device
CN106100913A (en) Error message alignment system and method
CN109101400A (en) A kind of monitoring system of cloud computation data center whole machine cabinet server
CN106934507A (en) A kind of new cruising inspection system and method for oil field petrochemical field
CN109753029A (en) The method and operator's system of identification and display operation person's access process object
JP2016115352A (en) System and method for monitoring production system
CN104731062B (en) A kind of Intelligence Network Management System and method for monitoring and dispatching for meter status
CN112036166A (en) Data labeling method and device, storage medium and computer equipment
JP2016115351A (en) Method and production system to configure control device for production system
CN115686280A (en) Deep learning model management system, method, computer device and storage medium
CN109189758A (en) O&M flow designing method, device and equipment, operation method, device and host
CN106326050A (en) Automatic monitoring management method for whole cabinet server
CN110532021A (en) The processing method and processing device of the configuration file of dcs
CN109299789A (en) Equipment point inspection method and device
CN106060125A (en) Distributed real-time data transmission method based on data tags
CN106022582A (en) Work order control system service automatic analyzing and processing method and system
CN107391617A (en) Model method is led based on monitoring system automatically
CN104766107A (en) System utilizing RFID electronic product code to collect data in BIM

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20170111