CN101207510B - System and method for processing invalidation situation of groups type computer equipment management control bus - Google Patents

System and method for processing invalidation situation of groups type computer equipment management control bus Download PDF

Info

Publication number
CN101207510B
CN101207510B CN2006101687312A CN200610168731A CN101207510B CN 101207510 B CN101207510 B CN 101207510B CN 2006101687312 A CN2006101687312 A CN 2006101687312A CN 200610168731 A CN200610168731 A CN 200610168731A CN 101207510 B CN101207510 B CN 101207510B
Authority
CN
China
Prior art keywords
management
bus
control bus
computer equipment
control
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.)
Expired - Fee Related
Application number
CN2006101687312A
Other languages
Chinese (zh)
Other versions
CN101207510A (en
Inventor
王宗斌
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.)
State Grid Shanghai Municipal Electric Power Co
Original Assignee
Inventec Corp
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 Inventec Corp filed Critical Inventec Corp
Priority to CN2006101687312A priority Critical patent/CN101207510B/en
Publication of CN101207510A publication Critical patent/CN101207510A/en
Application granted granted Critical
Publication of CN101207510B publication Critical patent/CN101207510B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The invention discloses a method as well as a system for processing the management-control bus failure condition of group type computer equipment, and for example, the invention is applicable to be integrated to a blade type server to provide the processing function for the management-control bus failure condition to the blade type server. The invention is characterized in that the cause ubiety can be automatically detected when the failure condition happens to the management-control bus of the blade type server, and the service module on which the cause is located is led to self-reset a belonged bus controller thereof; if the management-control bus cannot successfully return to the normal operation state, cresset type alarming information is sent out to enable a network system administrator to obtain the service module which is the cause of the management-control bus failure condition by only checking the cresset on each service module. The characteristic can enable the network system administrator to faster and more efficiently eliminate the cause of failure condition of the management-control bus.

Description

Method for processing invalidation situation of groups type computer equipment management control bus and system
Technical field
The present invention relates to a kind of computerized information technology, particularly relevant for a kind of group-wise (clustering) computer equipment management and control bus disabled status processing method and system.
Background technology
Blade type server (blade server) is the webserver of a kind of group-wise (clustering type), its characteristics are to utilize same circuit cabinet (chassis) to integrate modular server unit (hereinafter referred to as " service module ") more than two or two, and these service modules promptly are used for providing servo function in group's mode, as long as that is network user be linked to these service modules wherein any one, can connect line and the servo function that uses this blade type server to be provided.In the practical application, each service module in the blade type server is promptly made the circuit board of a blade cutting edge of a knife or a sword shape, and therefore can allow the network management personnel be incorporated into the circuit cabinet in the mode of plugging together easily at any time increases user capacity.
On concrete the enforcement, the blade type server is provided with cabinet management and control device (chassismanagement unit) usually, in order to all service modules and the shared device thereof in the management and control blade type server; (Intelligent Platform Management Bus, IPMB) bus of type passes data mutually and reaches the management and control signal of being correlated with and cabinet management and control device exchanges the intelligent platform management interface specification Intelligent Platform Management Bus down that adopts IPMI (Intelligent Platform Management Interface) at present mostly with data between the service module.
Yet in the practical application, IPMB bus in the blade type server often might be for some reason and disabled status takes place, and makes between cabinet management and control device and each service module to exchange and make cabinet management and control device to carry out the management and control function to service module because of carrying out data.Because present blade type server is when IPMB bus generation disabled status, and which service module can't cause the service module of this situation to network system management personnel prompting be, therefore at present this way to solve the problem for by the network system management personnel with the mode of trial and error choose out some service modules or the blade type server of resetting whole.Yet this kind practice obviously wastes time and energy and is inefficent.
Summary of the invention
The shortcoming of prior art in view of the above, main purpose of the present invention is to be to provide a kind of method for processing invalidation situation of groups type computer equipment management control bus and system, it can be when the IPMB bus generation disabled status in the blade type server, automatically demonstrate the service module person why who causes this disabled status, to allow the network system management personnel can get rid of the cause that causes this disabled status fast and efficiently.
Method for processing invalidation situation of groups type computer equipment management control bus of the present invention comprises at least: (M1) during this management and control bus generation disabled status, correspondingly send cause and check enable information; (M2) responding this cause checks enable information and checks this management and control bus by which data processing unit in this group-wise computer equipment is caused; (M3) send bus control unit and reset and to require information, make reset bus control unit under it of this data processing unit that causes disabled status to this data processing unit that causes disabled status; (M4) check whether this management and control bus is returned to normal operating state; If not, then send the caution enable information; And (M5) respond this caution enable information and correspondingly send human appreciable information warning.
On the entity framework, invalidation situation of groups type computer equipment management control bus treatment system of the present invention comprises at least: (A) disabled status detecting module, it can be when this management and control bus generation disabled status, correspondingly detects this disabled status and sends cause and check enable information; (B) cause is checked module, it can be responded the cause that this disabled status detecting module sends and check enable information and check this management and control bus by which data processing unit in this group-wise computer equipment is caused, and the replacement of sending correspondence according to this requires enable information; (C) bus control unit is reset and is required module, it can be responded replacement that this cause checks that module is sent and require enable information and send bus control unit and reset and require information to cause the data processing unit of disabled status to this, makes reset bus control unit under it of this data processing unit that causes disabled status; (D) the answer situation is checked module, and it can cause that the data processing unit of disabled status resets after the bus control unit under it at this, checks whether this management and control bus is returned to normal operating state; If not, then send the caution enable information; If otherwise, then send caution elimination information; And (E) alarm module, it can be responded this answer situation and check the caution enable information that module is sent and correspondingly send human appreciable information warning; And can so when receiving this caution elimination information, eliminate this information warning.
The characteristics of method for processing invalidation situation of groups type computer equipment management control bus of the present invention and system are when IPMB bus generation disabled status, can detect the service module that causes IPMB bus disabled status automatically and be that, and make reset voluntarily bus control unit under it of this service module; Reply normal operating state if make the IPMB bus with failing, then send the information warning of cresset formula, make the network system management personnel and can learn which the service module that causes IPMB bus disabled status is, and this service module is carried out maintenance work as long as check the cresset on each service module.These characteristics can allow the network system management personnel reach the cause that eliminating efficiently causes IPMB bus disabled status more fast.
Description of drawings
Fig. 1 is for using schematic diagram, in order to show the application mode of invalidation situation of groups type computer equipment management control bus treatment system of the present invention;
Fig. 2 is a configuration diagram, in order to show the modularization basic framework of invalidation situation of groups type computer equipment management control bus treatment system of the present invention;
Fig. 3 is activity chart (activity diagram), in order to each processing action that shows that invalidation situation of groups type computer equipment management control bus treatment system of the present invention is performed.
The main element symbol description
10 group-wise computer equipments (blade type server)
21 service modules
22 service modules
23 service modules
24 service modules
30 cabinet management and control devices
40 bus interface (IPMB)
51 bus control units
52 light-emittingdiodes
100 invalidation situation of groups type computer equipment management control bus treatment systems of the present invention
110 disabled status detecting modules
120 causes are checked module
130 bus control units are reset and are required module
140 answer situations are checked module
150 alarm modules
201 IPMB bus failure event
The information warning of 202 cresset formulas
Embodiment
Below be conjunction with figs., disclose the embodiment of explanation method for processing invalidation situation of groups type computer equipment management control bus of the present invention and system in detail.
Fig. 1 promptly shows the application mode of invalidation situation of groups type computer equipment management control bus treatment system of the present invention (as the part that square comprised of label 100 indications).As shown in the figure, be incorporated into the computer equipment of group-wise in invalidation situation of groups type computer equipment management control bus treatment system 100 practical applications of the present invention, it for example is blade type server (blade server) 10, and this blade type server 10 have group individually independently data processing unit (in this application example, for example be 4 service modules 21,22,23,24; But there is no particular restriction for its number) and cabinet management and control device (Chassis Management Unit) 30, and wherein between this cabinet management and control device 30 and each service module 21,22,23,24 by the management and control bus interface, for example be the bus 40 of IPMB (IntelligentPlatform Management Bus) type, pass data and relevant management and control signal mutually; That is cabinet management and control device 30 can come each service module 21,22,23,24 is carried out every management and control function by IPMB bus 40.
As shown in Figure 2, the modular basic framework of invalidation situation of groups type computer equipment management control bus treatment system 100 of the present invention comprises at least: (A) the disabled status detecting module 110; (B) cause is checked module 120; (C) bus control unit is reset and is required module 130; (D) the answer situation is checked module 140; And (E) alarm module 150.The individual attribute and the function of these modules below promptly are described at first respectively.
Whether disabled status detecting module 110 disabled status (that is whether IPMB bus failure event 201 takes place) takes place in the time of can detecting these IPMB bus 40 practical operations; If then correspondingly send cause and check that enable information is to cause inspection module 120.On concrete the enforcement, this disabled status detecting module 110 for example is with two general I/O (General Purpose Input/Output that are connected to IPMB bus 40, GPIO) be connected to central processor or microcontroller (Microcontroller Unit among cabinet management and control device 30 embedded, MCU) (the Complex Programmable Logic Device of the CPLD in the chip, CPLD) device, make this GPIO pin disabled status take place and can't receive specific signal the time, send relevant signal to this central processing unit or MCU/CPLD device and make it send cause to check enable information in IPMB bus 40.
Cause checks that module 120 can respond the above-mentioned cause that disabled status detecting module 110 sent and check enable information and check the disabled status of this IPMB bus 40 by which service module in the blade type server 10 (21,22,23 or 24) is caused, and sends corresponding replacement according to this and require enable information to bus control unit replacement to require module 130.On concrete the enforcement, this cause checks that module 120 for example is to adopt bus to close the mode of separating in proper order to find out the service module that causes the bus disabled status and be which (21,22,23 or 24); That is adopt one group of controllable contactor (not shown) to be arranged between the bus control unit and its bus of these service modules 21,22,23,24, and close contactor between each service module bus control unit and the bus one by one by another transmission path, which is to separate out the service module that causes IPMB bus disabled status.Below hypothesis IPMB bus disabled status is caused by service module 21.
Bus control unit is reset and to be required module 130 can send bus control unit to reset and require information to this service module 21 that causes IPMB bus disabled status, makes reset bus control unit 51 under it of this service module 21.
Answer situation inspection module 140 can check whether this IPMB bus 40 is returned to normal operating state after the bus control unit 51 under the service module 21 that causes IPMB bus disabled status is reset it; If not, then send the caution enable information and give alarm module 150; If otherwise, then send caution elimination information and give alarm module 150.
Alarm module 150 can be responded above-mentioned answer situation and check the caution enable information that module 140 is sent and correspondingly send human appreciable information warning, for example is the information warning 202 of cresset formula; And can so when receiving this caution elimination information, eliminate the information warning 202 of this cresset formula.On concrete the enforcement, this alarm module 150 is for example for adopting an existing light-emittingdiode 52 on each service module 21,22,23,24 to show this information warning in the cresset mode; That is the network system management personnel can learn which the service module that causes IPMB bus disabled status is as long as check the illuminating state of the light-emittingdiode 52 on each service module 21,22,23,24.
Integrated operation mode when below promptly utilizing application example that invalidation situation of groups type computer equipment management control bus treatment system 100 practical applications of the present invention are described.
In the actual mechanical process of blade type server 10, if disabled status takes place and (IPMB bus failure event 201 takes place promptly in IPMB bus 40 for some reason, then it will cause disabled status detecting module 110 correspondingly to send cause and check that enable information starts cause audit program (the processing action P10 shown in Fig. 3), make cause check that the correspondingly responsible execution of module 120 processing action P20 shown in Figure 3 checks that the disabled status of this IPMB bus 40 is which service module (21 in the blade type server 10,22,23, or 24) cause, and send corresponding replacement according to this and require enable information to reset to require module 130 to bus control unit.Suppose that IPMB bus disabled status is caused by service module 21, then bus control unit is reset and to be required module 130 promptly correspondingly to carry out processing action P30 shown in Figure 3 to send bus control unit and reset and require information to this service module 21 that causes IPMB bus disabled status, makes this service module 21 carry out reset voluntarily bus control unit 51 under it of processing action P31 shown in Figure 3.
Then check that by the answer situation module 140 responsible execution processing action P40 shown in Figure 3 checks whether this IPMB bus 40 is returned to normal operating state; If not, then send the caution enable information and give alarm module 150, make alarm module 150 correspondingly carry out processing shown in Figure 3 action P51 and send cresset and light the light-emittingdiode 52 that controls signal on the service module 21, make service module 21 carry out that processing action P61 shown in Figure 3 lights this light-emittingdiode 52 and the information warning 202 that produces the cresset formula.If otherwise, then send caution elimination information and give alarm module 150, making alarm module 150 correspondingly carry out processing shown in Figure 3 action P52 sends cresset and extinguishes the light-emittingdiode 52 that controls signal on the service module 21, make service module 21 carry out processing action P62 shown in Figure 3 and extinguish this light-emittingdiode 52, represent IPMB bus 40 to reply normal operating state therefrom.
Generally speaking, the invention provides a kind of method for processing invalidation situation of groups type computer equipment management control bus and system, it can for example be applied to be incorporated into the blade type server, in order to this blade type server is provided management and control bus disabled status processing capacity; And its characteristics are when IPMB bus generation disabled status, can detect the service module that causes IPMB bus disabled status automatically which is, and make reset voluntarily bus control unit under it of this service module; Reply normal operating state if make the IPMB bus with failing, then send the information warning of cresset formula, make the network system management personnel and can learn the service module person why who causes IPMB bus disabled status, and this service module is carried out maintenance work as long as check cresset on each service module.These characteristics can allow the network system management personnel reach the cause that eliminating efficiently causes IPMB bus disabled status more fast.Therefore the present invention has better progressive and practicality than background technology.
The above is preferred embodiment of the present invention only, is not in order to limit the scope of essence technology contents of the present invention.Essence technology contents of the present invention is broadly to be defined in the described claim.If any technology entity that other people are finished or method and following claim are defined as identical or are a kind of change of equivalence, all will be regarded as being covered by among the claim of the present invention.

Claims (9)

1. method for processing invalidation situation of groups type computer equipment management control bus, it is applied to the group-wise computer equipment, and described group-wise computer equipment has data processing unit and at least one cabinet management and control device of group, and wherein said cabinet management and control device comes each data processing unit is carried out the management and control function by the management and control bus;
Described method for processing invalidation situation of groups type computer equipment management control bus comprises at least:
During described management and control bus generation disabled status, correspondingly send cause and check enable information;
Responding described cause checks enable information and checks the disabled status of described management and control bus by which data processing unit in the described group-wise computer equipment is caused;
Send bus control unit and reset and to require information, make reset bus control unit under it of the described data processing unit that causes disabled status to the described data processing unit that causes disabled status;
Check whether described management and control bus is returned to normal operating state; If not, then send the caution enable information; And
Respond described caution enable information and correspondingly send the information warning of cresset formula.
2. method for processing invalidation situation of groups type computer equipment management control bus according to claim 1, wherein said group-wise computer equipment is the blade type server system.
3. method for processing invalidation situation of groups type computer equipment management control bus according to claim 1, the management and control bus that wherein said management and control bus is the Intelligent Platform Management Bus type.
4. invalidation situation of groups type computer equipment management control bus treatment system, it is incorporated into the group-wise computer equipment, and described group-wise computer equipment has data processing unit and at least one cabinet management and control device of group, and wherein said cabinet management and control device comes each data processing unit is carried out the management and control function by the management and control bus;
Described invalidation situation of groups type computer equipment management control bus treatment system comprises at least:
The disabled status detecting module, it correspondingly detects described disabled status and sends cause and check enable information when described management and control bus generation disabled status;
Cause is checked module, it is responded the described cause that described disabled status detecting module sends and checks enable information and check the disabled status of described management and control bus by which data processing unit in the described group-wise computer equipment is caused, and the replacement of sending correspondence according to this requires enable information;
Bus control unit is reset and is required module, it is responded described replacement that described cause checks that module is sent and requires enable information and send bus control unit and reset and require information to the data processing unit that causes disabled status, makes reset bus control unit under it of the described data processing unit that causes disabled status;
The answer situation is checked module, after its bus control unit under the described data processing unit that causes disabled status is reset it, checks whether described management and control bus is returned to normal operating state; If not, then send the caution enable information; If then send caution elimination information; And
Alarm module, it responds that described answer situation is checked the described caution enable information that module is sent and the information warning that correspondingly sends the cresset formula; And and then receiving described caution when eliminating information, eliminate described information warning.
5. invalidation situation of groups type computer equipment management control bus treatment system according to claim 4, wherein said group-wise computer equipment is the blade type server system.
6. invalidation situation of groups type computer equipment management control bus treatment system according to claim 4, the management and control bus that wherein said management and control bus is the Intelligent Platform Management Bus type.
7. invalidation situation of groups type computer equipment management control bus treatment system according to claim 4, wherein said disabled status detecting module is detected the management and control bus by general I/O whether disabled status is taken place, when making this general I/O pin can't receive specific signal in Intelligent Platform Management Bus generation disabled status, send relevant signal to central processing unit, microcontroller or CPLD device, check enable information so that it sends described cause.
8. invalidation situation of groups type computer equipment management control bus treatment system according to claim 4, wherein said alarm module is used as the information warning of described cresset formula by the cresset that light-emittingdiode sent.
9. invalidation situation of groups type computer equipment management control bus treatment system according to claim 4, wherein said cause check that module adopts bus to close the mode of separating in proper order and finds out the described data processing unit that causes disabled status.
CN2006101687312A 2006-12-19 2006-12-19 System and method for processing invalidation situation of groups type computer equipment management control bus Expired - Fee Related CN101207510B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2006101687312A CN101207510B (en) 2006-12-19 2006-12-19 System and method for processing invalidation situation of groups type computer equipment management control bus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2006101687312A CN101207510B (en) 2006-12-19 2006-12-19 System and method for processing invalidation situation of groups type computer equipment management control bus

Publications (2)

Publication Number Publication Date
CN101207510A CN101207510A (en) 2008-06-25
CN101207510B true CN101207510B (en) 2011-12-07

Family

ID=39567414

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2006101687312A Expired - Fee Related CN101207510B (en) 2006-12-19 2006-12-19 System and method for processing invalidation situation of groups type computer equipment management control bus

Country Status (1)

Country Link
CN (1) CN101207510B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102708031B (en) * 2012-05-15 2016-08-31 浪潮电子信息产业股份有限公司 A kind of method of quick location failure memory

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1707434A (en) * 2004-06-09 2005-12-14 威芯科技股份有限公司 Intelligent platform management interface system and executing method thereof
CN1787512A (en) * 2005-11-30 2006-06-14 成都同和资讯有限责任公司 Communication interface controller
CN1808990A (en) * 2005-01-18 2006-07-26 英业达股份有限公司 Network connectivity backup system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1707434A (en) * 2004-06-09 2005-12-14 威芯科技股份有限公司 Intelligent platform management interface system and executing method thereof
CN1808990A (en) * 2005-01-18 2006-07-26 英业达股份有限公司 Network connectivity backup system
CN1787512A (en) * 2005-11-30 2006-06-14 成都同和资讯有限责任公司 Communication interface controller

Also Published As

Publication number Publication date
CN101207510A (en) 2008-06-25

Similar Documents

Publication Publication Date Title
TWI238933B (en) Computer system with dedicated system management buses
CN102402395A (en) Quorum disk-based non-interrupted operation method for high availability system
CN101964543B (en) HVDC thyristor valve base electronic equipment system
CN1803510A (en) Computer interlock system
CN101488101A (en) CPCI redundancy stand-by system
CN102026042A (en) Keep-alive and self-healing method and device for advanced telecom computing architecture control surface
CN102147640A (en) Server with a plurality of main boards
CN101207510B (en) System and method for processing invalidation situation of groups type computer equipment management control bus
CN1277227C (en) Backup managment control arbitration system
CN101453337A (en) Micro telecommunication and computer general hardware platform architecture system and electric power control method
CN106527409B (en) A kind of master control cabinet
CN101778091B (en) Expandable security server alternate system
CN105739656A (en) Cabinet with automatic reset function and automatic reset method thereof
CN103995759A (en) High-availability computer system failure handling method and device based on core internal-external synergy
CN110114805B (en) Fire protection control unit
CN102006190A (en) High-availability cluster backup system and backup method thereof
CN103513596A (en) MVB management function implementation system based on ARM
CN205427464U (en) But redundant redundant control system of automatic recovery
US20040153695A1 (en) System and method for interconnecting nodes of a redundant computer system
CN100481016C (en) Computer platform management unit operation mode intercede processing method and system
CN212064044U (en) Real-time fault-tolerant Ethernet switch module
CN102095952B (en) Self-monitoring system of valve-based electronic device of converter valve
KR100388965B1 (en) Apparatus for cross duplication of each processor board in exchange
CN104503858A (en) System configuration method based on LRM position identification
CN107741740B (en) Multi-board system fault reporting method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
C53 Correction of patent for invention or patent application
COR Change of bibliographic data

Free format text: CORRECT: INVENTOR; FROM: WANG ZONGBIN TO: ZHANG JIN KANG XIAOYAN PAN HONGGUANG YU YINBO REN WENLONGZHANG YANJUN WANG ZONGBIN

Free format text: CORRECT: ADDRESS; FROM: TAIWAN, CHINA TO: 200002 HUANGPU, SHANGHAI

ASS Succession or assignment of patent right

Owner name: STATE GRID SHANGHAI ELECTRIC POWER COMPANY

Free format text: FORMER OWNER: YINGYEDA CO., LTD., TAIWAN

Effective date: 20140917

C41 Transfer of patent application or patent right or utility model
TR01 Transfer of patent right

Effective date of registration: 20140917

Address after: 200002 Nanjing East Road, Shanghai, No. 181, No.

Patentee after: State Grid Shanghai Municipal Electric Power Company

Address before: Taipei City, Taiwan, China

Patentee before: Inventec Corporation

CB03 Change of inventor or designer information

Inventor after: Zhang Jin

Inventor after: Kang Xiaoyan

Inventor after: Pan Hongguang

Inventor after: Yu Yinbo

Inventor after: Ren Wenlong

Inventor after: Zhang Yanjun

Inventor after: Wang Zongbin

Inventor before: Wang Zongbin

CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20111207

Termination date: 20141219

EXPY Termination of patent right or utility model