CN106774752A - A kind of Rack servers spare fans control method - Google Patents
A kind of Rack servers spare fans control method Download PDFInfo
- Publication number
- CN106774752A CN106774752A CN201710018028.1A CN201710018028A CN106774752A CN 106774752 A CN106774752 A CN 106774752A CN 201710018028 A CN201710018028 A CN 201710018028A CN 106774752 A CN106774752 A CN 106774752A
- Authority
- CN
- China
- Prior art keywords
- fan
- node
- rmc
- plate
- rack
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/16—Constructional details or arrangements
- G06F1/20—Cooling means
- G06F1/206—Cooling means comprising thermal management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2023—Failover techniques
- G06F11/2028—Failover techniques eliminating a faulty processor or activating a spare
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a kind of Rack servers spare fans control method, when exception occurs in RMC, when losing the adjusting function to whole machine cabinet fan, Rack servers will directly carry out fan control by plate in node.The inventive method can ensure that fan remains able to be operated according to the rotating speed needed for system when RMC modules occur abnormal, it is to avoid the situation of power wastage or component excess temperature occur, improve the stability of Rack racks operation.
Description
Technical field
The present invention relates to server radiating technical field, and in particular to a kind of Rack servers spare fans control method.
Background technology
Management mainboard（RMC）It is the administrative center of large server Smart Rack, is responsible for the management of system interior nodes, power supply
Management, fan management.Major design includes that node is based on the outband management of IPMB specifications, and AC/DC power supplys are based on PMBUS agreements
The function managements such as management, the rotation speed of the fan regulation based on I2C and air quantity compensation adjustment.Diode reason is employed in management design
Mode, RMC is managed for the first order, and plate is second level management in node.Management system is by RMC（Realize the monitoring of system, management,
Alarm）, plate in node（Realize out of band supervision, diode reason, alarm report, the fan monitoring of all nodes）, node fan（Collection
Into on each node, it is responsible for realtime monitoring, fault diagnosis, consumption detection of subsystem irrespective of size etc.）And I2C, IPMB, pipe
The compositions such as reason network.RMC passes through I2C and board communications in node, by plate in 10 nodes（Diode manages system）Monitoring,
The monitoring of control realization whole system, management.Fan and secondary power supply plate, confession of the plate by I2C/IPMB with each node in node
Electric pinboard, fan control board interconnection, realize to the monitor in real time outside the band of whole system, management function.Fan passes through multichannel
The monitored chip of I2C buses and each intra-node, part are connected, responsible node asset management, monitor in real time, fault diagnosis.
Scorpio standard Rack servers with to environmental requirement it is low, deployment is convenient, low cost and other advantages are accounted in the data center
According to increasing share.Rack servers are concentrated by the way of radiating using fan wall, are unified to manage by cabinet management module RMC
Reason.This mode can effectively improve radiating and the efficiency of management, it is ensured that the stable operation of rack.
The flow of this control method for fan is：BMC is calculated according to node key componentses temperature value and variable quantity and worked as
Forefan PWM value, and plate in corresponding node is delivered the data to by I2C；Plate collects corresponding whole in node
After the PWM value of node feeding back, data are passed into RMC by I2C；RMC is carried out to the PWM value of plate feedback in all nodes of rack
Compare, maximum of which PWM value is passed to plate in the node of whole machine cabinet by I2C；Plate will be received from RMC in node
PWM value passes to the control unit on correspondence fan backboard, and then rotation speed of the fan is adjusted.
A kind of fan failure solution based on RMC management of application number 201610425323 .4 disclosure of the invention, should
Fan failure solution step is as follows：1）Fan running status is monitored by RMC；2）When monitoring fan failure
When, by RMC, authenticate-acknowledge fan breaks down really again；3）Fan is actively completed by RMC and restarts action, and supervised again
Control fan running status；4）Step 1 is returned to after fan normal operation is monitored）；5）When monitoring that fan is still faulty,
RMC notifies that system informs user's fan failure and prompting is solved by way of hardware is restarted.One kind of the invention is based on
Compared to the prior art the fan failure solution of RMC management, can realize automatic decision fan failure, and can complete in time
The exclusion and reparation of fan failure, effectively meeting server need in time carry out fan failure judgement, the need for excluding and recovering
Ask.
Due to by the way of RMC unified managements, when RMC Module Fails, fan will no longer receive fan regulating strategy
Regulation and control, work according to the PWM value given tacit consent in fan backboard.In this case, two kinds of consequences are easily produced, one is rack with low
Load running, the air quantity that fan is provided causes the waste of power consumption more than the air quantity needed for radiating；Another situation is, once machine
Cabinet is run with high capacity, air quantity of fan deficiency, the risk of component excess temperature easily occurs.
The content of the invention
The technical problem to be solved in the present invention is：The present invention is directed to problem above, there is provided a kind of standby wind of Rack servers
Fan controlling method, it is ensured that in the case of RMC Module Fails, still can be controlled by fan regulating strategy, it is to avoid power consumption wave
Take or excess temperature risk.
The technical solution adopted in the present invention is：
A kind of Rack servers spare fans control method, when exception occurs in RMC, loses the adjusting function to whole machine cabinet fan
When, Rack servers will directly carry out fan control using spare fans control method by plate in node, it is ensured that system safety is high
Effect operation.
If RMC fails, in node plate detect with RMC communication disruptions, plate obtains corresponding node BMC and sends in node
PWM value, is contrasted to acquired PWM value, and maximum is sent into fan control board, and fan control board sends according to the value
Pwm signal gives fan module, completes speed regulation process, it is ensured that fan carries out speed governing according to the actual radiating requirements of system..
The fan regulation and controlling strategy that node BMC writes according to inside, according to needed for component temperature at that time and variable quantity are calculated
The fan PWM value wanted, and the value is passed into plate in corresponding node by I2C.
When RMC recovers fan control function, Rack racks recover acquiescence fan control mode, by BMC to whole machine cabinet wind
Fan is regulated and controled.
Beneficial effects of the present invention are：
The inventive method can ensure that fan remains able to be carried out according to the rotating speed needed for system when RMC modules occur abnormal
Work, it is to avoid the situation of power wastage or component excess temperature occur, improves the stability of Rack racks operation.
Brief description of the drawings
Fig. 1 is fan control schematic diagram of the present invention.
Specific embodiment
Below according to Figure of description, with reference to specific embodiment, the present invention is further described：
Embodiment 1：
A kind of Rack servers spare fans control method, when exception occurs in RMC, loses the adjusting function to whole machine cabinet fan,
Rack servers will directly carry out fan control, it is ensured that system is safe and efficient using spare fans control method by plate in node
Operation.
Embodiment 2
On the basis of embodiment 1, if the present embodiment RMC fails, plate is detected and RMC communication disruptions, plate in node in node
The PWM value that corresponding node BMC sends is obtained, acquired PWM value is contrasted, maximum is sent to fan control board,
Fan control board sends pwm signal and gives fan module according to the value, completes speed regulation process, it is ensured that fan is according to the actual radiating of system
Demand carries out speed governing.
Embodiment 3
On the basis of embodiment 2, the fan regulation and controlling strategy that the present embodiment node BMC writes according to inside, according to unit at that time
Device temperature and variable quantity calculate required fan PWM value, and the value is passed into plate in corresponding node by I2C.
Embodiment 4
On the basis of embodiment 3, the present embodiment recovers fan control function as RMC, and Rack racks recover acquiescence fan control
Mode, is regulated and controled by BMC to whole machine cabinet fan.
Embodiment 5
As shown in figure 1, by taking plate in 4 nodes of node of correspondence as an example, now RMC failures, the communication in node between plate and RMC
Disconnect；
The fan regulation and controlling strategy that node BMC writes according to inside, according to needed for component temperature at that time and variable quantity are calculated
The fan PWM value wanted, and the value is passed into plate in corresponding node by I2C；
Plate obtains the PWM value that 4 node BMC send in node, if RMC fails, during plate is detected and communicated with RMC in node
It is disconnected, then 4 groups of PWM values are contrasted, maximum is sent to fan control board, fan control board sends PWM letters according to the value
Number give fan, complete speed regulation process；
When RMC recovers fan control function, Rack racks recover acquiescence fan control mode.
Implementation method is merely to illustrate the present invention, and not limitation of the present invention, about the ordinary skill of technical field
Personnel, without departing from the spirit and scope of the present invention, can also make a variety of changes and modification, therefore all equivalent
Technical scheme fall within scope of the invention, scope of patent protection of the invention should be defined by the claims.
Claims (4)
1. a kind of Rack servers spare fans control method, it is characterised in that when RMC occurs abnormal, lose to whole machine cabinet wind
During the adjusting function of fan, Rack servers will directly carry out fan control by plate in node.
2. a kind of Rack servers spare fans control method according to claim 1, it is characterised in that plate is obtained in node
The PWM value that corresponding node BMC sends is taken, is contrasted by acquired PWM value, maximum is sent to fan control
Plate, fan control board sends pwm signal and gives fan module according to the value, completes speed regulation process.
3. a kind of Rack servers spare fans control method according to claim 2, it is characterised in that node BMC according to
According to the fan regulation and controlling strategy of internal write-in, required fan PWM value is calculated according to component temperature at that time and variable quantity,
And the value is passed into plate in corresponding node by I2C.
4. a kind of Rack servers spare fans control method according to claim 2, it is characterised in that when RMC recovers
During fan control function, Rack racks recover acquiescence fan control mode, and whole machine cabinet fan is regulated and controled by BMC.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710018028.1A CN106774752A (en) | 2017-01-11 | 2017-01-11 | A kind of Rack servers spare fans control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710018028.1A CN106774752A (en) | 2017-01-11 | 2017-01-11 | A kind of Rack servers spare fans control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106774752A true CN106774752A (en) | 2017-05-31 |
Family
ID=58949205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710018028.1A Pending CN106774752A (en) | 2017-01-11 | 2017-01-11 | A kind of Rack servers spare fans control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106774752A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239346A (en) * | 2017-06-09 | 2017-10-10 | 郑州云海信息技术有限公司 | A kind of whole machine cabinet computing resource tank node and computing resource pond framework |
| CN107420340A (en) * | 2017-09-29 | 2017-12-01 | 迈普通信技术股份有限公司 | Control method of cooling fan and system |
| CN107562387A (en) * | 2017-09-14 | 2018-01-09 | 郑州云海信息技术有限公司 | A kind of high density storage pool implementation method and its framework |
| CN107959543A (en) * | 2017-12-04 | 2018-04-24 | 郑州云海信息技术有限公司 | Based on RACK management board transmission signal jamproof systems and design method |
| CN108334418A (en) * | 2018-02-02 | 2018-07-27 | 郑州云海信息技术有限公司 | A kind of cabinet fan speed governing abnormality eliminating method, system, medium and equipment |
| CN108825543A (en) * | 2018-05-24 | 2018-11-16 | 郑州云海信息技术有限公司 | A kind of server fan regulation method and system |
| 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 |
| CN109753131A (en) * | 2019-01-11 | 2019-05-14 | 京东方科技集团股份有限公司 | Electronic equipment, heat dissipation debugging system and its adjustment method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035849A (en) * | 2014-06-19 | 2014-09-10 | 浪潮电子信息产业股份有限公司 | Method for preventing rack fan management failures |
-
2017
- 2017-01-11 CN CN201710018028.1A patent/CN106774752A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035849A (en) * | 2014-06-19 | 2014-09-10 | 浪潮电子信息产业股份有限公司 | Method for preventing rack fan management failures |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239346A (en) * | 2017-06-09 | 2017-10-10 | 郑州云海信息技术有限公司 | A kind of whole machine cabinet computing resource tank node and computing resource pond framework |
| CN107562387A (en) * | 2017-09-14 | 2018-01-09 | 郑州云海信息技术有限公司 | A kind of high density storage pool implementation method and its framework |
| CN107420340A (en) * | 2017-09-29 | 2017-12-01 | 迈普通信技术股份有限公司 | Control method of cooling fan and system |
| CN107959543A (en) * | 2017-12-04 | 2018-04-24 | 郑州云海信息技术有限公司 | Based on RACK management board transmission signal jamproof systems and design method |
| CN108334418A (en) * | 2018-02-02 | 2018-07-27 | 郑州云海信息技术有限公司 | A kind of cabinet fan speed governing abnormality eliminating method, system, medium and equipment |
| CN108825543A (en) * | 2018-05-24 | 2018-11-16 | 郑州云海信息技术有限公司 | A kind of server fan regulation method and system |
| 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 |
| CN109753131A (en) * | 2019-01-11 | 2019-05-14 | 京东方科技集团股份有限公司 | Electronic equipment, heat dissipation debugging system and its adjustment method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106774752A (en) | A kind of Rack servers spare fans control method | |
| CN102571441B (en) | Whole machine cabinet intelligent management, system and device | |
| US7146258B2 (en) | Direct current power pooling | |
| CN103139248B (en) | Machine frame system | |
| US20150115711A1 (en) | Multi-level data center consolidated power control | |
| CN104598329A (en) | Automatic BMC (baseboard management controller) fault solution method based on RMC (rack server management center) management | |
| US10375854B2 (en) | Liquid cooling system and control method thereof | |
| US11334136B1 (en) | Power loss siren | |
| CN105867196A (en) | Express delivery cabinet and power control board | |
| CN101563829A (en) | Data center uninterruptible power distribution architecture | |
| CN103135732B (en) | Server cabinet system | |
| CN105119746A (en) | RMC-management-based method for intelligently monitoring configuration of SMART RACK whole cabinet server | |
| WO2008119288A1 (en) | System, device, equipment and method for monitoring management | |
| CN106445055A (en) | Power supply protection mechanism of Rack server | |
| US7045914B2 (en) | System and method for automatically providing continuous power supply via standby uninterrupted power supplies | |
| CN106502355A (en) | A kind of Rack server power supplies inlet temperature acquisition methods | |
| CN109101400A (en) | A kind of monitoring system of cloud computation data center whole machine cabinet server | |
| CN105357313A (en) | Power consumption control method, system, and frame management controller | |
| TW201917524A (en) | Power supplying method for computer system | |
| CN105700657A (en) | Machine frame power management method and apparatus as well as machine frame system | |
| CN107026759A (en) | The firmware and its development approach of a kind of remote management BBU modules based on BMC | |
| CN111010840A (en) | Intelligent power cabinet and management method | |
| CN106095642A (en) | A kind of fan failure solution based on RMC management | |
| CN205750361U (en) | A kind of express delivery cabinet and power board | |
| CN103138975B (en) | Hosting method of multiple rack systems |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |