CN105868077A - Method for obtaining monitoring information of complete cabinet server nodes - Google Patents

Method for obtaining monitoring information of complete cabinet server nodes Download PDF

Info

Publication number
CN105868077A
CN105868077A CN201610222967.3A CN201610222967A CN105868077A CN 105868077 A CN105868077 A CN 105868077A CN 201610222967 A CN201610222967 A CN 201610222967A CN 105868077 A CN105868077 A CN 105868077A
Authority
CN
China
Prior art keywords
node
cmd
bmc
information
cabinet server
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
Application number
CN201610222967.3A
Other languages
Chinese (zh)
Other versions
CN105868077B (en
Inventor
苏孝
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 CN201610222967.3A priority Critical patent/CN105868077B/en
Publication of CN105868077A publication Critical patent/CN105868077A/en
Application granted granted Critical
Publication of CN105868077B publication Critical patent/CN105868077B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/3058Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/34Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3466Performance evaluation by tracing or monitoring
    • G06F11/3476Data logging

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Computing Systems (AREA)
  • Computer And Data Communications (AREA)
  • Cooling Or The Like Of Electrical Apparatus (AREA)

Abstract

The invention discloses a method for obtaining monitoring information of complete cabinet server nodes. The concrete implementation process is that a hardware part is arranged; baseboard management controller (BMC) chips are arranged in each server node in a complete cabinet server composed of a plurality of server nodes, and a rack management controller (RMC) and a node middle plate are installed in the complete cabinet server; an OEM command module is added to a BMC; a concrete data format of BMC OEM CMD modules of the nodes is defined; that is, a CMD module format is adopted for an OEM command, and a plurality of CMD modules are supported to perform obtaining and sending simultaneously; the node middle plate sends OEM CMD module data to the BMC to obtain node information; and the RMC obtains node information between node middle plate, and performs monitors and heat dissipation control in real time. Compared with the prior art, the method for obtaining the monitoring information of the complete cabinet server nodes simplifies the communication process between the node BMC and the node middle plate, the node middle plate can obtain plenty of data in one time from the node BMC, particularly real-time change information, and the method has great benefit for improving system response time and is high in practicality.

Description

A kind of method obtaining whole machine cabinet server node monitoring information
Technical field
The present invention relates to field of computer technology, a kind of practical, method of acquisition whole machine cabinet server node monitoring information.
Background technology
Along with the development of computer technology, whole machine cabinet server is especially more and more extensive in large-scale data center application, and whole machine cabinet information is typically by RMC(Rack Management Controller) be managed collectively, Centralized Monitoring.In whole machine cabinet server system, each layer (usually 4U) server node is connected with plate in node by I2C, and in whole machine cabinet, in every node layer, plate is connected to upper strata Centralized Monitoring management system RMC by I2C.In node, plate sends commands to this layer of each node BMC and obtains nodal information, and RMC sends commands to plate in every node layer and indirectly obtains monitoring nodes information.In node, plate generally obtains the information such as this node layer sensor, network, FRU by the order of standard IPMI at present.But it is less that the order of standard IPMI there is problems of comprising quantity of information in data form, and plate needs the quantity of information obtained from node more in node, so in node, plate must send a lot of IPMI order to BMC to obtain nodal information, the interactive efficiency causing both is low, for the heat radiation strategy such as cpu temperature, internal memory temperature, intake air temperature need to use real-time change information, often because acquisition of information speed is slow, gathering data causes whole machine cabinet radiating effect poor not in time, and fan wall and node power consumption can not effectively reduce.Therefore, it is achieved a kind of method that can rapidly and efficiently obtain whole machine cabinet server node monitoring information, the problem that design needs solution badly with developer is become.
Summary of the invention
The technical assignment of the present invention is for above weak point, it is provided that a kind of practical, method of acquisition whole machine cabinet server node monitoring information.
A kind of method obtaining whole machine cabinet server node monitoring information, it implements process and is:
Hardware components is set, in the whole machine cabinet server being made up of some server nodes, the built-in BMC chip of each server node, whole machine cabinet server is installed plate in Centralized Monitoring administrative unit RMC and node;
OEM command module is increased in BMC;
The concrete data form of the BMC OEM CMD module of definition node, i.e. OEM order uses CMD block format, supports that multiple CMD module obtains simultaneously and sends;
In node, plate sends OEM CMD module data to BMC and obtains nodal information;
RMC obtains nodal information, monitoring in real time and heat radiation regulation and control from node between plate.
Described whole machine cabinet server is 4U server, and the server node of each layer is all connected with plate in node by I2C, and in whole machine cabinet server, in the node of every layer, plate is connected to upper strata Centralized Monitoring management system RMC by I2C.
The detailed process of definition node BMC OEM CMD module concrete data form is: this CMD module includes sensor CMD, network C MD, FRU CMD tri-part, in sensor CMD, define cpu temperature, node air inlet/outlet temperature, internal memory temperature, voltage, node power consumption, Node Switch machine state, the data form of health status;In network C MD, support that BMC share NIC and the special mouth network information obtain and arrange;In FRU CMD, support that Product Name, Product Serial, Chassis Extra field obtain simultaneously and arrange.
In described node, between plate and node BMC, communication uses the communication connection of IPMB communication interface.
Node carries out communication by CMD module between plate and node BMC, this CMD module support acquisition and setting command, in node, plate obtains information and arrange nodal information from node, and every CMD information includes three parts:
CMD Index, i.e. distinguishes different CMD;
CMD length, i.e. concrete data length;
CMD data, i.e. concrete data format definition, if the CMD data part of each CMD module comprises dry contact BMC monitoring management information.
A kind of method obtaining whole machine cabinet server node monitoring information of the present invention, has the advantage that
A kind of method obtaining whole machine cabinet server node monitoring information of the present invention, realize whole machine cabinet monitoring nodes information by plate in node based on OEM CMD modular manner in BMC to obtain in real time, simplify the communication process of plate in node BMC and node, greatly reduce RMC and obtain the time of nodal information, improve acquisition efficiency, in node, plate once can obtain mass data from node BMC, and especially real-time change information, substantially increases system response time;The real time information such as RMC can be according to CPU, internal memory, intake air temperature quickly adjust control rotation speed of the fan, not only increase radiating effect, also can reduce node power consumption further, practical, it is easy to promote.
Accompanying drawing explanation
Accompanying drawing 1 is the flowchart of the present invention.
Detailed description of the invention
The invention will be further described with specific embodiment below in conjunction with the accompanying drawings.
As shown in Figure 1, the present invention provides a kind of method obtaining whole machine cabinet server node monitoring information, by whole machine cabinet server centered monitoring management unit (RMC, Rack Management Controler) and node in plate, more quickly and efficiently information is obtained from node BMC based on the OEM command module increased in node BMC, such as server node on-off state, temperature information, the network information, FRU information, assets information, node power consumption etc..
It implements process:
Hardware components is set, in the whole machine cabinet server being made up of some server nodes, the built-in BMC chip of each server node, whole machine cabinet server is installed plate in Centralized Monitoring administrative unit RMC and node;
OEM command module is increased in BMC;
The concrete data form of the BMC OEM CMD module of definition node, i.e. OEM order uses CMD block format, supports that multiple CMD module obtains simultaneously and sends;
In node, plate sends OEM CMD module data to BMC and obtains nodal information;
RMC obtains nodal information, monitoring in real time and heat radiation regulation and control from node between plate.
Described whole machine cabinet server is 4U server, and the server node of each layer is all connected with plate in node by I2C, and in whole machine cabinet server, in the node of every layer, plate is connected to upper strata Centralized Monitoring management system RMC by I2C.
nullThe detailed process of definition node BMC OEM CMD module concrete data form is: this CMD module includes sensor CMD、Network C MD、FRU CMD tri-part,In sensor assembly sensor CMD,By cpu temperature、Node air inlet/outlet temperature、Internal memory temperature、Voltage、Node power consumption、Node Switch machine state、The data format definitions such as health status are good,In network C MD module, support that BMC share NIC and the special mouth network information obtain and arrange simultaneously,In FRU CMD module,I.e. field-replaceable unit field-replaceable unit module,Support Product Name、Product Serial、The fields such as Chassis Extra obtain simultaneously and arrange.
In described node, between plate and node BMC, communication uses the communication connection of IPMB communication interface.
Node carries out communication by CMD module between plate and node BMC, this CMD module support acquisition and setting command, in node, plate obtains information and arrange nodal information from node, and every CMD information includes three parts:
CMD Index, i.e. distinguishes different CMD;
CMD length, i.e. concrete data length;
CMD data, i.e. concrete data format definition, if the CMD data part of each CMD module comprises dry contact BMC monitoring management information.
The method rapidly and efficiently obtaining whole machine cabinet server node monitoring information that the present invention proposes, simplify the communication process of plate in node BMC and node, in node, plate once can obtain mass data, especially real-time change information from node BMC, and to improving, system response time is of great advantage.For whole machine cabinet heat radiation speed governing, owing to RMC can the most once get the information such as CPU, internal memory, intake air temperature by plate in node, just quickly rotation speed of the fan can be adjusted according to current heat dissipating state when node load changes, improve radiating effect, also can be substantially reduced fan wall and node power consumption simultaneously.
Above-mentioned detailed description of the invention is only the concrete case of the present invention; the scope of patent protection of the present invention includes but not limited to above-mentioned detailed description of the invention; any present invention of meeting a kind of obtains suitably change that it is done by the those of ordinary skill of claims of the method for whole machine cabinet server node monitoring information and any described technical field or replaces, and all should fall into the scope of patent protection of the present invention.

Claims (5)

1. the method obtaining whole machine cabinet server node monitoring information, it is characterised in that it implements process and is:
Hardware components is set, in the whole machine cabinet server being made up of some server nodes, the built-in BMC chip of each server node, whole machine cabinet server is installed plate in Centralized Monitoring administrative unit RMC and node;
OEM command module is increased in BMC;
The BMC OEM of definition node The concrete data form of CMD module, i.e. OEM order uses CMD block format, supports that multiple CMD module obtains simultaneously and sends;
In node, plate sends OEM CMD module data to BMC and obtains nodal information;
RMC obtains nodal information, monitoring in real time and heat radiation regulation and control from node between plate.
A kind of method obtaining whole machine cabinet server node monitoring information the most according to claim 1, it is characterized in that, described whole machine cabinet server is 4U server, the server node of each layer is all connected with plate in node by I2C, and in whole machine cabinet server, in the node of every layer, plate is connected to upper strata Centralized Monitoring management system RMC by I2C.
A kind of method obtaining whole machine cabinet server node monitoring information the most according to claim 1, it is characterized in that, the detailed process of definition node BMC OEM CMD module concrete data form is: this CMD module includes sensor CMD, network C MD, FRU CMD tri-part, in sensor CMD, define cpu temperature, node air inlet/outlet temperature, internal memory temperature, voltage, node power consumption, Node Switch machine state, the data form of health status;In network C MD, support BMC share NIC and the special mouth network information obtain and arrange;At FRU In CMD, support Product Name、Product Serial, Chassis Extra field obtains simultaneously and arranges.
A kind of method obtaining whole machine cabinet server node monitoring information the most according to claim 1, it is characterised in that in described node, between plate and node BMC, communication uses the communication connection of IPMB communication interface.
A kind of method obtaining whole machine cabinet server node monitoring information the most according to claim 4, it is characterized in that, node carries out communication by CMD module between plate and node BMC, this CMD module support acquisition and setting command, in node, plate obtains information and arrange nodal information from node, and every CMD information includes three parts:
CMD Index, i.e. distinguishes different CMD;
CMD length, i.e. concrete data length;
CMD data, i.e. concrete data format definition, if the CMD data part of each CMD module comprises dry contact BMC monitoring management information.
CN201610222967.3A 2016-04-12 2016-04-12 A method of obtaining whole machine cabinet server node monitoring information Active CN105868077B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610222967.3A CN105868077B (en) 2016-04-12 2016-04-12 A method of obtaining whole machine cabinet server node monitoring information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610222967.3A CN105868077B (en) 2016-04-12 2016-04-12 A method of obtaining whole machine cabinet server node monitoring information

Publications (2)

Publication Number Publication Date
CN105868077A true CN105868077A (en) 2016-08-17
CN105868077B CN105868077B (en) 2018-09-25

Family

ID=56637476

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610222967.3A Active CN105868077B (en) 2016-04-12 2016-04-12 A method of obtaining whole machine cabinet server node monitoring information

Country Status (1)

Country Link
CN (1) CN105868077B (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106326050A (en) * 2016-08-18 2017-01-11 浪潮电子信息产业股份有限公司 Automatic monitoring and managing method for complete machine cabinet server
CN106339294A (en) * 2016-08-29 2017-01-18 浪潮电子信息产业股份有限公司 Voltage monitoring system and method
CN106528308A (en) * 2016-11-25 2017-03-22 济南浪潮高新科技投资发展有限公司 Server sensor information collection method
CN106850814A (en) * 2017-02-15 2017-06-13 济南浪潮高新科技投资发展有限公司 It is a kind of to increase the method that custom command is supported to realize sensor information collection
CN107302465A (en) * 2017-08-18 2017-10-27 郑州云海信息技术有限公司 A kind of PCIe Switch servers complete machine management method
CN107623591A (en) * 2017-08-28 2018-01-23 北京云集智造科技有限公司 A kind of server universal monitor method and device
CN107979502A (en) * 2016-10-25 2018-05-01 郑州云海信息技术有限公司 The method and flow that plate compatibility different type node monitors in a kind of server
CN107977273A (en) * 2016-10-25 2018-05-01 郑州云海信息技术有限公司 The Memory Optimize Method of node information collection memory sharing in a kind of cabinet
CN109240891A (en) * 2018-09-26 2019-01-18 郑州云海信息技术有限公司 A kind of monitoring method and device of SR whole machine cabinet server
CN113204361A (en) * 2021-05-20 2021-08-03 山东英信计算机技术有限公司 Automatic configuration method and device for whole cabinet server
CN115150304A (en) * 2022-07-29 2022-10-04 苏州浪潮智能科技有限公司 Method, system, device and medium for monitoring IPv6 network of server node

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105224756A (en) * 2015-10-14 2016-01-06 浪潮电子信息产业股份有限公司 A kind of method for designing obtaining SmartRack whole machine cabinet air quantity
CN105389242A (en) * 2015-10-14 2016-03-09 浪潮电子信息产业股份有限公司 Method for acquiring overall cabinet server information in batch

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106326050A (en) * 2016-08-18 2017-01-11 浪潮电子信息产业股份有限公司 Automatic monitoring and managing method for complete machine cabinet server
CN106339294A (en) * 2016-08-29 2017-01-18 浪潮电子信息产业股份有限公司 Voltage monitoring system and method
CN107979502A (en) * 2016-10-25 2018-05-01 郑州云海信息技术有限公司 The method and flow that plate compatibility different type node monitors in a kind of server
CN107977273A (en) * 2016-10-25 2018-05-01 郑州云海信息技术有限公司 The Memory Optimize Method of node information collection memory sharing in a kind of cabinet
CN106528308B (en) * 2016-11-25 2019-07-02 山东浪潮人工智能研究院有限公司 A kind of server sensor information acquisition method
CN106528308A (en) * 2016-11-25 2017-03-22 济南浪潮高新科技投资发展有限公司 Server sensor information collection method
CN106850814A (en) * 2017-02-15 2017-06-13 济南浪潮高新科技投资发展有限公司 It is a kind of to increase the method that custom command is supported to realize sensor information collection
CN106850814B (en) * 2017-02-15 2020-02-14 浪潮集团有限公司 Method for realizing sensor information acquisition by adding custom command support
CN107302465A (en) * 2017-08-18 2017-10-27 郑州云海信息技术有限公司 A kind of PCIe Switch servers complete machine management method
CN107302465B (en) * 2017-08-18 2021-06-29 郑州云海信息技术有限公司 PCIe Switch server complete machine management method
CN107623591A (en) * 2017-08-28 2018-01-23 北京云集智造科技有限公司 A kind of server universal monitor method and device
CN109240891A (en) * 2018-09-26 2019-01-18 郑州云海信息技术有限公司 A kind of monitoring method and device of SR whole machine cabinet server
CN113204361A (en) * 2021-05-20 2021-08-03 山东英信计算机技术有限公司 Automatic configuration method and device for whole cabinet server
CN115150304A (en) * 2022-07-29 2022-10-04 苏州浪潮智能科技有限公司 Method, system, device and medium for monitoring IPv6 network of server node
CN115150304B (en) * 2022-07-29 2023-06-02 苏州浪潮智能科技有限公司 Monitoring method, system, device and medium for server node IPv6 network

Also Published As

Publication number Publication date
CN105868077B (en) 2018-09-25

Similar Documents

Publication Publication Date Title
CN105868077A (en) Method for obtaining monitoring information of complete cabinet server nodes
US10931550B2 (en) Out-of-band management techniques for networking fabrics
US10817398B2 (en) Data center management via out-of-band, low-pin count, external access to local motherboard monitoring and control
Kant Data center evolution: A tutorial on state of the art, issues, and challenges
CN104335535B (en) Use the method, apparatus and system of spanning tree and network switch element resource routing iinformation stream in a network
CN102129274B (en) Server, server subassembly and fan speed control method
CN103092138B (en) Control method of equipment cabinet system
CN103138972B (en) Server cabinet system
US20090031051A1 (en) Centralized server rack management using usb
CN105005363A (en) Server platform based on universal ARM architecture
TW200825762A (en) Apparatus and method for computer management
CN109150579A (en) Configure the method and system and its storage medium of multiple cases link
CN106598183A (en) Two-stage fan regulation and control system and method applicable to multi-node server
CN103200199A (en) Out of band (OOB) data collection system
CN106850286A (en) The baseboard management controller of baseboard management controller and NE management disk on veneer
CN102289402A (en) Monitoring and managing method based on physical multi-partition computer architecture
CN106933753A (en) The control method and device of intelligent interface card
US20140317267A1 (en) High-Density Server Management Controller
CN103926992A (en) Power management circuit, server and power management method thereof
CN105224756A (en) A kind of method for designing obtaining SmartRack whole machine cabinet air quantity
CN115708040A (en) Mainboard and computing equipment
CN104219061B (en) Request the method and device of power consumption state variation
CN203554493U (en) Server remote management interface system
CN204833071U (en) Server platform based on general type ARM framework
CN203812171U (en) CDN server under ARM architecture

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant