WO2013075511A1 - Système de serveur en bâti - Google Patents

Système de serveur en bâti Download PDF

Info

Publication number
WO2013075511A1
WO2013075511A1 PCT/CN2012/078699 CN2012078699W WO2013075511A1 WO 2013075511 A1 WO2013075511 A1 WO 2013075511A1 CN 2012078699 W CN2012078699 W CN 2012078699W WO 2013075511 A1 WO2013075511 A1 WO 2013075511A1
Authority
WO
WIPO (PCT)
Prior art keywords
server
management
mmc
server node
rmc
Prior art date
Application number
PCT/CN2012/078699
Other languages
English (en)
Chinese (zh)
Inventor
周建军
武湛
黄剑敏
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2013075511A1 publication Critical patent/WO2013075511A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/04—Network management architectures or arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/34—Signalling channels for network management communication
    • H04L41/344—Out-of-band transfers

Definitions

  • the present invention relates to the field of communications, and in particular, to a machine rejection server system.
  • the machine is a server that provides unified power supply, fan cooling, and switching equipment. It can be installed with multiple server nodes. It can be configured with multiple server nodes. Due to the integration of multiple devices, there is a high density. Server node.
  • FIG 1 is a schematic diagram of an existing machine rejection server.
  • the whole machine refuses to support 1U server nodes.
  • the entire machine refuses to use unified power supply and heat dissipation processing.
  • Each node server supports hot swap function, and the server node has a single board management controller ( Baseboard Management Controller, BMC).
  • BMC Baseboard Management Controller
  • the IMM is connected to all fans using a network cable.
  • the machine is backed by a fan wall and consists of multiple fan modules.
  • Each fan has a fan control board that can communicate with the IMM management unit.
  • the fan control board and the IMM communicate with each other through the network to implement fan speed management, fan monitoring, and fan fault management.
  • the power module has a control board, which can communicate with the IMM management unit.
  • the power control board and the IMM communicate with each other through network communication to implement power switch management, power supply monitoring, and power failure management.
  • the IMM management unit is connected to all server nodes using the RS485 bus, via RS485 total
  • the line communication completes the power-on and power-off operations of the node, and can also implement the standard BMC out-of-band management function by communicating with the BMC of all server nodes through the network.
  • the management method of the prior art only supports the server node with the BMC and only supports a specific management mode, and the problem that the type of the supported server node is insufficient and the management mode is not flexible enough cannot satisfy the user's different types of server nodes and management methods. Demand.
  • the embodiment of the present invention provides a machine-rejected server system, which is used to solve the problem that the supported server node types of the prior art are insufficient and the management mode is not flexible enough to meet the requirements of different types of server nodes and management modes.
  • the embodiment of the present invention provides a machine rejection server system, where the machine rejection server system includes: a plurality of server nodes, a plurality of module management controllers MMC, a machine rejection management controller RMC, a power module, and a fan module;
  • Each of the MMCs is respectively connected to a server node of each of the plurality of server nodes to communicate with the server node, the set of server nodes including one or more of the plurality of server nodes; wherein, the MMC a plurality of interface units, wherein the MMC is configured to communicate with the server node by using a specific one or more interface units according to a communication interface type supported by the server node;
  • the RMC is connected to each of the MMC, the power module, and the fan module to implement communication with each of the MMC, the power module, and the fan module.
  • the MMC includes a plurality of interface units, and may use a specific one or more interface units to connect with the server node according to the interface type of the server node (if the node having the BMC adopts a communication interface, and the node without the BMC adopts another communication interface) Communicate to support different types of node servers.
  • the MMC communicates with multiple servers, and the RMC is connected to the power module, the fan module, and the multiple MMCs, so that the management switch can implement unified management of the machine rejection by connecting with the RMC.
  • the server node can be managed by the method of connecting to each server node, and the management of the power module and the fan module can be realized through the MMC or the RMC.
  • FIG. 1 is a schematic diagram of a conventional machine rejection server
  • FIG. 2 is a schematic diagram of a machine rejection server system according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram of power supply control in a machine rejection server system according to an embodiment of the present invention
  • FIG. 5 is a schematic diagram of another machine rejection server system according to an embodiment of the present invention
  • FIG. 6 is a schematic diagram of control of a server node in another machine rejection server system according to an embodiment of the present invention
  • 7 is a schematic diagram of another server rejection server system according to an embodiment of the present invention.
  • the machine rejection server system of the embodiment of the present invention can manage all server nodes (hereinafter also referred to as “servers” or “nodes”) of the machine and other devices, for example, the machine refuses to configure the organic rejection management controller (rack Management Controller (RCC), the whole machine refuses to include 10 chassis, each chassis can be configured with 8 half-width server nodes or 4 full-width server nodes, and a module management controller is configured in each chassis. ( Module Management Controller, MMC) to manage the server nodes in each chassis.
  • RRCC Rack Management Controller
  • MMC Module Management Controller
  • the MMC is configured to communicate with the server node, and has control and acquisition of temperature data and power consumption data of the server node; the RMC is configured to adjust a heat dissipation amount of the fan module according to the temperature data, and adjust power supply of the power module according to the power consumption data;
  • the node performs power-on or power-off processing according to the control signal forwarded by the MMC or directly received. Therefore, the RMC can implement unified management processing for all power module power supply and fan heat dissipation.
  • the RMC can implement temperature information, power consumption information, asset information, machine rejection resources, and server node management of the server node through the MMC.
  • the user can also use the BMC management module of the server node to implement independent out-of-band management of the server node through the switch.
  • the RMC receives power consumption information of all server nodes through the MMC; the RMC judges according to the power consumption control principle according to all power consumption information, and if the power consumption of the whole machine is greater than a preset value, the node power consumption control operation is performed, if less than the user pre- If the set value and the current power consumption are greater than the power consumption of the whole machine, the power module sleep operation is performed, otherwise the monitoring operation is continued.
  • each server node is an independent computing node.
  • each server node can have a single board management controller (BMC), which enables independent out-of-band management.
  • BMC board management controller
  • FIG. 2 is a schematic diagram of a machine rejection server system according to an embodiment of the present invention. As shown in the figure, the embodiment includes an RMC11, an MMC12, a server node 13, a power module 14, and a fan module 15.
  • the MMC 12 includes: a control unit, a logic control unit, and a storage unit.
  • the server system of the embodiment of the present invention further includes a backplane, each server node 13 is connected to the backplane, and is connected to the MMC through a Print Circuit Board (PCB) trace on the backplane.
  • PCB Print Circuit Board
  • the MMC12 can be connected to the backplane through a connector, and connected to the server node 13 or the RMC11 through the backplane PCB trace. Of course, it can also be connected to the server node 13 or the RMC11 through the front board.
  • Communication is carried out by means of PCB backplane.
  • the signal frequency of communication is high, the communication distance between two points cannot be too long, the distance is long, the signal capacity is disturbed, and the signal quality is poor.
  • cable communication is used, long-distance communication can be supported.
  • Ethernet communication is used,
  • the MMC 12 communicates with the server node 13 by means of peer-to-peer internal communication.
  • the peer-to-peer internal communication means that it is possible to communicate without knowing the address of the other party (unlike the IP communication method, it is necessary to know the address of both parties), which is advantageous in the machine rejection server.
  • the number of server nodes is relatively large, and the maximum support can reach 80 nodes.
  • the IP address of each node is dynamically generated.
  • the point-to-point internal communication between the MMC and the server node can solve the problem without knowing the IP address of the other party.
  • the node performs communication operations.
  • the RMC 11 includes: a control unit, a switching unit, a logic control unit, and a storage unit.
  • the RMC 11 is connected to each of the MMC 12, the power module 14 and the fan module 15 to implement communication with each of the MMC 12, the power module 14 and the fan module 15;
  • the management switch managed by the system can manage the power module 14 and the fan module 15 through the RMC 11 through the connection with the RMC 11, and manage each server node 13 through the RMC 11 and the MMC 12; and enable the machine rejection system to support management.
  • the switch manages the server node 13 by connecting with the server node 13, and manages the fan module 14 and the power module 15 through the server node 13, the MMC 11, and the RMC 15.
  • the machine rejects the server system and sends out a management network port.
  • the user can use the RMC11 to communicate with the server node through the switch 16 to implement the server management function.
  • the GPIO can be used to power on and off the server node, and the MMC12 can receive the temperature directly sent by the switch node.
  • Information, alarm information and asset information, RMC11 achieves the heat dissipation of the machine rejection system through the environmental temperature of the machine rejection.
  • the RMC11 can realize the power supply adjustment of the power module 14 rejected by the whole machine through the overall power consumption of each server node 13, and realize automatic deployment. Power design.
  • the power module 14 includes a control unit and a power conversion unit.
  • 3 is a schematic diagram of power module control in a server-rejected server system according to an embodiment of the present invention.
  • eight power modules PS are used as an example, and RMC11 and power module 14 use the same power module frame, RMC11 and power module 14 Make Connected to the backplane of the power module frame, the RMC11 is connected to the power module 14 through the I2C link to implement PMBUS protocol communication, and the RMC11 uses the PMBUS protocol to perform power module management functions on the eight power modules 14.
  • Each power module 14 is divided into an I2C address through the power module frame backplane (A0-A2 uses three address lines for unified addressing), and the RMC11 performs PMBUS protocol communication with each power module through the I2C address and reads the power module FRU. information. Therefore, all the power modules 14 can be managed by the PMBUS protocol RMC11, and the switching and power consumption management of the power module 14 can be realized.
  • Each power module 14 and the back panel of the power module frame also have PS_OK and power module in-position signals, and the RMC11 passes the power module.
  • the signal connection of the backplane of the frame enables the voltage output of all power modules 14, the power module in place, and the power module to be inserted and removed for identification management.
  • the RMC11 can implement fault location and fault management of the power module.
  • FIG. 4 is a schematic diagram of fan module control in a machine rejection server system according to an embodiment of the present invention.
  • heat dissipation is composed of 6-8 fan modules, and each fan module 15 is composed of two fan units 151 and a control circuit 150.
  • the control circuit 150 receives the control signal of the RMC 11 to generate a drive signal; the fan unit 151 adjusts the rotational speed according to the received drive signal to dissipate heat for the server node at the corresponding position.
  • the control circuit 150 has a fault light and an RJ45 interface.
  • One control circuit 150 can control two fans 151.
  • the control circuit 150 is connected to the RMC 11 through a network cable through an RJ45 interface. The connection between the fan module 15 and the RMC 11 has specific requirements.
  • the connection between the upper and lower fan modules 15 and the RMC 11 corresponds to the number 1-8 of the RMC11 fan management port.
  • the RMC controls the heat dissipation of the corresponding area of the fan module 15 by mapping the position of the specific port to the fan frame.
  • the layout of the fan module is that the fan module is behind the machine rejection server. From top to bottom, 6-8 fan modules are used to form the rear-rear fan wall.
  • Each fan module consists of two large fans.
  • the RMC uses a PWM signal to speed the fan of a fan module.
  • Each fan has its own fan speed signal for fan speed detection.
  • Each fan provides an independent in-position signal for fan in-position and plug-in detection management.
  • Each fan frame has a fan fault light.
  • the RMC When the RMC detects a fan fault, it is indicated by the RMC operating fan fault light. The fan is turned off until the fan fails.
  • the heat dissipation strategy of the machine is to adjust the temperature of the board to the temperature of the board.
  • the BMC of the server When the temperature of the server board of a node is too hot, the BMC of the server will report the temperature of the RMC board.
  • the RMC detects the current server node. Perform the speed adjustment operation on the corresponding fan frame in the area.
  • the switch chip can be integrated into the RMC11.
  • the 10 management network ports on the front panel correspond to the network ports on the MMC12 that the machine rejects.
  • Each MMC12 corresponds to one RMC11 management network port, corresponding from top to bottom.
  • Network port 1-10, RMC11 and MMC12 use network communication for device management control.
  • each chassis can be configured with 8 half-width server nodes without BMC management modules or 4 server nodes with full width without BMC management modules.
  • Each chassis is configured with an MMC12. All the server nodes 13 and MMC12 are inserted on the backplane of the chassis. The MMC12 and the server 13 use the serial port to communicate and use the GPIO port to manage the server.
  • the RMC11 integrates the LSW chip to perform port positioning operations. The location relationship of the MMC12 is used to determine the location of the chassis where the server node 13 is located.
  • FIG. 5 is a schematic diagram of another machine rejection server system according to an embodiment of the present invention. As shown in the figure, the embodiment includes an RMC 11, an MMC 12, a server node 13, a power module 14, a fan module 15, and a BMC 18.
  • the MMC 12 is configured to determine whether the server node 13 contains the BMC 18 according to the hardware signal generated after the server node 13 inserts the machine rejection. When the server node contains the BMC 18, the interface supported by the BMC 18 communicates with the server node 13.
  • the server node 13 carries the BMC 18, the machine refuses to send out a management network port, and the user can use the RMC 11 to communicate with the BMC 19 of the server node 13 to implement all out-of-band management of the server node 13.
  • the server node 13 is powered on and off, the alarm information is reported, and the asset information is reported.
  • the RMC11 communicates with the BMC18 through the MMC12.
  • the BMC18 collects the temperature information and power consumption information of the server node 13 and reports it to the RMC11.
  • the RMC can automatically implement the information through the RMC11.
  • the heat dissipation of the fan module is adjusted to achieve heat dissipation.
  • the RMC11 can realize power supply adjustment of the power module 14 rejected by the whole machine through the overall power consumption of each server node 13, thereby realizing automatic power consumption.
  • FIG. 6 is a schematic diagram of control of a server node in another server rejection server system according to an embodiment of the present invention.
  • the RMC11 integrates a switch chip, and 10 management network ports on the front panel respectively correspond to network ports on the MMC 12 that the machine rejects.
  • Each MMC12 corresponds to one RMC11 management network port, which corresponds to the network port 1-10 from top to bottom. Network management is used between RMC11 and MMC12 for device management.
  • each chassis can be configured with 8 half-width server nodes or 4 full-width server nodes.
  • Each chassis is configured with one MMC12, and all server nodes 13 and MMC12 in the chassis are inserted.
  • the MMC12 and the BMC18 use IPMB communication through the I2C connection.
  • Each chassis is divided into two upper and lower zones, and the secondary IPMB is used to form the active/standby relationship. A total of 4 IPMB connections.
  • the RMC11 communicates with the BMC 18 through the middle layer of the MMC12 to implement management of the server node 13.
  • the RMC11 integrates the LSW chip to perform port location operation, and determines the location of the chassis where the server node 13 is located through the positional relationship between the port and the MMC 12, and the RMC 11 and the MMC 12 use UDP.
  • the network communication protocol is used for data communication, and the internal communication protocol is encapsulated in the UDP message to perform the transmission and reception of the management data command.
  • the MMC can detect the presence of all the servers in the chassis through the in-position signal of the server node on the backplane of the chassis. Bit and plug and unplug actions, and report to RMC for unified server node management.
  • the present embodiment has a BMC, and the previous embodiment does not have a BMC.
  • the interface supported by the BMC board (such as IPMB) can be used for communication; When it is not supported, you can use a serial port to communicate.
  • FIG. 7 is a schematic diagram of another system for rejecting the server according to the embodiment of the present invention. As shown in the figure, the embodiment includes the RMC11, the MMC12, and the server node 13. , power module 14, fan module 15 and BMC18.
  • the difference between this embodiment and the previous embodiment is that the RMC that the machine rejects the use of the machine is in the same management plane as the BMC of each node, and the user can implement the control and management of the server node through the BMC of each node.
  • the control of the power module 14 and the fan module 15 is the same as in the previous embodiment.
  • the user can directly connect all the BMCs 18 of the server node 13 through the switch 16, and the BMC 18 receives the temperature data and power consumption data of the server node 13, and transmits the temperature data and the power consumption data through the I2C. Give MMC12 and forward it to RMC.
  • the fan module 15 and the power module 14 are still uniformly controlled by the RMC 11.
  • the BMC 18 sends the alarm information of the server node 13 and the fault information of the power module 15 or the fan module 14 to the external switch. 16. Notify the user to replace the power module 15 or the fan module 14.
  • the machine rejection server system has RMC, and the RMC provides an I2C interface for power supply management, provides control signals for fan module control, provides network interface and MMC for server node control, and each management interface and function are independent, There is coupling, and the unified management effect of rejecting resources of the whole machine can be realized through RMC.
  • MMC can provide IPMB, serial port, GPIO and PCIE interfaces to meet all external interfaces required by the management server.
  • BMC service server nodes can use IPMB connection.
  • No BMC server node can use serial port and GPIO interface to achieve through MMC.
  • the intermediate compatibility and interface adaptation between the RMC and the server node enable the RMC to manage multiple server nodes.
  • the management interface of the RMC is unified, and the machine refuses to support multiple server nodes.
  • the machine rejection server system of the embodiment of the present invention manages multiple server nodes through the MMC, and the MMC includes multiple interface units, which can be based on the interface type of the server node (if the node with the BMC adopts a certain communication interface, the node without the BMC adopts another A communication interface) uses a specific one or more interface units to communicate with server nodes to enable support for different types of node servers.
  • the MMC communicates with multiple servers, and the RMC is connected to the power module, the fan module, and the multiple MMCs, so that the management switch can implement unified management of the machine rejection by connecting with the RMC.
  • the steps of a method or algorithm described in connection with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both.
  • the software module can be placed in random access memory (RAM), memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or technical field. Any other form of storage medium known.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Cooling Or The Like Of Electrical Apparatus (AREA)
  • Power Sources (AREA)

Abstract

La présente invention concerne un système de serveur en bâti, comprenant : une pluralité de nœuds serveurs, une pluralité de contrôleurs de gestion de module (MMC), un contrôleur de gestion de bâti (RMC), un module d'alimentation et un module de ventilateur; chacun des MMC est connecté à chaque nœud serveur d'un groupe de nœuds serveurs de manière à réaliser une communication avec le nœud serveur, le groupe de nœuds serveurs comprenant un ou plusieurs nœuds serveurs de la pluralité de nœuds serveurs; le MMC comprenant une pluralité d'unités d'interface et fonctionnant pour réaliser une communication avec le nœud serveur à l'aide d'une ou plusieurs certaines unités d'interface en fonction du type d'interface de communication pris en charge par le nœud serveur. Le système de serveur en bâti selon les modes de réalisation de la présente invention permet au système global de prendre en charge davantage de types de nœuds serveurs et de moyens de gestion, et satisfait l'exigence d'un utilisateur concernant différents types de nœuds serveurs et moyens de gestion.
PCT/CN2012/078699 2011-11-23 2012-07-16 Système de serveur en bâti WO2013075511A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201110376524.7A CN102510344B (zh) 2011-11-23 2011-11-23 机柜服务器系统
CN201110376524.7 2011-11-23

Publications (1)

Publication Number Publication Date
WO2013075511A1 true WO2013075511A1 (fr) 2013-05-30

Family

ID=46222398

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2012/078699 WO2013075511A1 (fr) 2011-11-23 2012-07-16 Système de serveur en bâti

Country Status (2)

Country Link
CN (1) CN102510344B (fr)
WO (1) WO2013075511A1 (fr)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103983876A (zh) * 2014-05-27 2014-08-13 浪潮电子信息产业股份有限公司 一种节点中板在线检测的方法
CN105487964A (zh) * 2015-12-18 2016-04-13 山东海量信息技术研究院 一种高端容错服务器的风扇故障记录方法
CN109412847A (zh) * 2018-10-16 2019-03-01 郑州云海信息技术有限公司 一种面向sr整机柜自动化配置机柜套餐的方法和系统
CN111159093A (zh) * 2019-11-25 2020-05-15 华东计算技术研究所（中国电子科技集团公司第三十二研究所） 异构智能计算系统
CN112039923A (zh) * 2020-09-29 2020-12-04 福建中锐网络股份有限公司 一种实验室机架管理控制服务器

Families Citing this family (42)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102510344B (zh) * 2011-11-23 2014-11-05 华为技术有限公司 机柜服务器系统
CN103684829B (zh) * 2012-09-17 2016-09-07 英业达科技有限公司 网络服务系统及其管理方法
TWI473018B (zh) * 2012-10-23 2015-02-11 Inventec Corp 網路伺服器系統及其更新韌體的方法
CN110678027B (zh) * 2013-02-28 2021-09-07 甲骨文国际公司 架装式现场可更换单元的带外管理
CN103218030B (zh) * 2013-04-26 2016-02-10 北京百度网讯科技有限公司 基于多节点微服务器的电源管理系统及微服务器
CN104283709A (zh) * 2013-07-10 2015-01-14 英业达科技有限公司 服务器系统和其数据传送方法
CN103475514B (zh) * 2013-09-03 2016-12-07 华为技术有限公司 无bmc的节点、集群系统及bios修复和升级方法
US9232678B2 (en) * 2013-12-30 2016-01-05 Dell Products L.P. Modular, scalable, expandable, rack-based information handling system
TWI519100B (zh) * 2014-01-16 2016-01-21 廣達電腦股份有限公司 機櫃伺服器系統及其自動定址方法
CN104133793B (zh) * 2014-06-18 2018-03-09 长芯盛（武汉）科技有限公司 长距离PCIe延长系统及数据发送方法
CN104102291A (zh) * 2014-07-22 2014-10-15 浪潮(北京)电子信息产业有限公司 刀片服务器、刀片服务器的监控管理方法和系统
CN105739656A (zh) * 2014-12-08 2016-07-06 营邦企业股份有限公司 具有自动重置功能的机柜及其自动重置方法
CN105824332B (zh) * 2015-01-06 2021-01-26 中兴通讯股份有限公司 智能监控方法及系统
CN104503932B (zh) * 2015-01-07 2017-11-24 加弘科技咨询(上海)有限公司 多主板服务器主基板管理控制器仲裁方法及系统
CN106325761B (zh) * 2015-06-29 2020-04-28 中兴通讯股份有限公司 一种存储资源管理的系统及方法
CN106445001B (zh) * 2015-08-08 2019-07-23 昆达电脑科技(昆山)有限公司 运行状态信息共享的服务器系统
CN106557405B (zh) * 2015-09-28 2019-05-07 佛山市顺德区顺达电脑厂有限公司 服务器机柜监控方法
CN105302690A (zh) * 2015-10-14 2016-02-03 浪潮电子信息产业股份有限公司 一种整机柜服务器监控管理方法
CN105278646A (zh) * 2015-10-14 2016-01-27 浪潮电子信息产业股份有限公司 一种将fan table放在节点BMC上的整机柜风扇调速策略
US9936605B2 (en) * 2015-11-30 2018-04-03 Quanta Computer Inc. Controlling air flow in a server rack
CN105577430B (zh) * 2015-12-15 2018-07-24 山东海量信息技术研究院 一种高端容错服务器的节点管理方法
CN106980562A (zh) * 2016-01-18 2017-07-25 中兴通讯股份有限公司 一种硬盘监控方法及装置
CN111488048B (zh) * 2016-02-14 2023-05-16 华为技术有限公司 一种电源管理方法以及系统
US9967192B2 (en) * 2016-02-22 2018-05-08 Quanta Computer Inc. Offloading of management controller traffic
CN106227642B (zh) * 2016-08-04 2018-12-21 浪潮(北京)电子信息产业有限公司 一种Rack管理控制器及整机柜服务器
CN106250291A (zh) * 2016-08-04 2016-12-21 浪潮(北京)电子信息产业有限公司 一种整机柜服务器的管理装置及整机柜服务器
CN106598183A (zh) * 2016-12-26 2017-04-26 郑州云海信息技术有限公司 一种适用于多节点服务器的两级风扇调控系统及方法
CN106685725A (zh) * 2017-01-11 2017-05-17 郑州云海信息技术有限公司 一种集中管理控制板、方法及系统
CN106774725A (zh) * 2017-01-12 2017-05-31 郑州云海信息技术有限公司 一种机柜服务器
CN106817260A (zh) * 2017-01-19 2017-06-09 郑州云海信息技术有限公司 一种机柜管理系统及方法
CN106897245A (zh) * 2017-02-22 2017-06-27 郑州云海信息技术有限公司 一种机柜式计算器
CN106897195A (zh) * 2017-02-28 2017-06-27 郑州云海信息技术有限公司 一种服务器机柜的监测方法及相关装置
CN106992883B (zh) * 2017-03-27 2020-02-21 联想(北京)有限公司 数据控制方法和数据控制装置
CN107632911A (zh) * 2017-09-22 2018-01-26 郑州云海信息技术有限公司 一种机柜式服务器功耗测试方法及测试系统
CN109634898A (zh) * 2019-01-03 2019-04-16 浪潮商用机器有限公司 一种服务器节点的位置识别系统
TWI704464B (zh) * 2019-06-10 2020-09-11 神雲科技股份有限公司 資料備援系統
CN110402058B (zh) * 2019-07-26 2022-02-18 浪潮电子信息产业股份有限公司 一种服务器整机柜及其管理电源板
CN111315176B (zh) * 2020-02-29 2021-07-06 苏州浪潮智能科技有限公司 一种在机柜中定位节点的方法和装置
CN112000607A (zh) * 2020-09-11 2020-11-27 苏州浪潮智能科技有限公司 一种整机柜服务器节点非接触式id地址识别装置及方法
CN113778667B (zh) * 2021-08-17 2024-01-23 华东计算技术研究所（中国电子科技集团公司第三十二研究所） 服务器节点信息管理系统和方法、可读介质
CN114124159B (zh) * 2021-10-27 2023-05-23 苏州浪潮智能科技有限公司 一种整机柜服务器直流电力线定位通信系统与方法
CN115113706B (zh) * 2022-06-29 2023-08-25 浪潮(山东)计算机科技有限公司 一种具有自动识别前后出线机型的服务器及识别方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101059692A (zh) * 2007-04-30 2007-10-24 深圳日海通讯技术有限公司 综合监控系统集成
CN101145836A (zh) * 2006-09-12 2008-03-19 北京正有网络通信技术股份有限公司 一种多业务综合接入设备
CN101166100A (zh) * 2006-10-17 2008-04-23 国际商业机器公司 刀片服务器系统及其配置方法和交换机模块
CN201887782U (zh) * 2010-11-24 2011-06-29 浪潮电子信息产业股份有限公司 一种高密度的服务器节点中板
CN102510344A (zh) * 2011-11-23 2012-06-20 华为技术有限公司 机柜服务器系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101145836A (zh) * 2006-09-12 2008-03-19 北京正有网络通信技术股份有限公司 一种多业务综合接入设备
CN101166100A (zh) * 2006-10-17 2008-04-23 国际商业机器公司 刀片服务器系统及其配置方法和交换机模块
CN101059692A (zh) * 2007-04-30 2007-10-24 深圳日海通讯技术有限公司 综合监控系统集成
CN201887782U (zh) * 2010-11-24 2011-06-29 浪潮电子信息产业股份有限公司 一种高密度的服务器节点中板
CN102510344A (zh) * 2011-11-23 2012-06-20 华为技术有限公司 机柜服务器系统

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103983876A (zh) * 2014-05-27 2014-08-13 浪潮电子信息产业股份有限公司 一种节点中板在线检测的方法
CN105487964A (zh) * 2015-12-18 2016-04-13 山东海量信息技术研究院 一种高端容错服务器的风扇故障记录方法
CN109412847A (zh) * 2018-10-16 2019-03-01 郑州云海信息技术有限公司 一种面向sr整机柜自动化配置机柜套餐的方法和系统
CN109412847B (zh) * 2018-10-16 2021-11-05 郑州云海信息技术有限公司 一种面向sr整机柜自动化配置机柜套餐的方法和系统
CN111159093A (zh) * 2019-11-25 2020-05-15 华东计算技术研究所（中国电子科技集团公司第三十二研究所） 异构智能计算系统
CN111159093B (zh) * 2019-11-25 2023-12-08 华东计算技术研究所（中国电子科技集团公司第三十二研究所） 异构智能计算系统
CN112039923A (zh) * 2020-09-29 2020-12-04 福建中锐网络股份有限公司 一种实验室机架管理控制服务器
CN112039923B (zh) * 2020-09-29 2024-05-14 福建中锐网络股份有限公司 一种实验室机架管理控制服务器

Also Published As

Publication number Publication date
CN102510344A (zh) 2012-06-20
CN102510344B (zh) 2014-11-05

Similar Documents

Publication Publication Date Title
WO2013075511A1 (fr) Système de serveur en bâti
US10148746B2 (en) Multi-host network interface controller with host management
US7761622B2 (en) Centralized server rack management using USB
CN101150413B (zh) 一种atca刀片服务器多机框级联系统及方法
CN100450044C (zh) 一种智能平台管理接口系统中的后插板监控装置
EP1871040B1 (fr) Méthode et système de gestion reposant sur une interface intelligente de gestion de plate-forme
CN104281511B (zh) 智能平台管理接口系统、基板管理控制器及实现方法
WO2013120340A1 (fr) Procédé de configuration de port, dispositif et appareil de communication par trames pour module d'interface réseau
JP2004334864A (ja) フォームファクタ変換器および試験装置
US7688715B2 (en) Apparatus for providing shelf manager having duplicate ethernet port in ATCA system
CN102724093B (zh) 一种atca机框及其ipmb连接方法
CN103138945A (zh) 管理电源供应的服务器机架系统
US9384102B2 (en) Redundant, fault-tolerant management fabric for multipartition servers
CN111209241A (zh) 整机柜服务器的管理系统
WO2015035791A1 (fr) Disque dur et procédé de gestion
CN113645047B (zh) 一种基于智能网卡的带外管理系统和服务器
US20150156117A1 (en) High density server system
WO2014067264A1 (fr) Carte de commutation et serveur lame
US8031722B1 (en) Techniques for controlling a network switch of a data storage system
CN103605413A (zh) 机架式服务器系统的机柜、机架式服务器系统及其管理方法
CN202443354U (zh) 多节点无线缆模块化计算机
CN111628944A (zh) 交换机及交换机系统
KR100848316B1 (ko) Ａｔｃａ 시스템에서 ｉｐｍｉ 메시지를 이용한 보드의상태 정보 제공 방법 및 그 장치
CN103004157A (zh) 网络设备加入集群系统的接口注册方法和设备
CN102073365A (zh) 一种基于MicroTCA标准的媒体服务器

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 12852385

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 12852385

Country of ref document: EP

Kind code of ref document: A1