CN105490859A - Node positioning method of high-end fault tolerance server - Google Patents

Node positioning method of high-end fault tolerance server Download PDF

Info

Publication number
CN105490859A
CN105490859A CN201510949028.4A CN201510949028A CN105490859A CN 105490859 A CN105490859 A CN 105490859A CN 201510949028 A CN201510949028 A CN 201510949028A CN 105490859 A CN105490859 A CN 105490859A
Authority
CN
China
Prior art keywords
node
smc
rmc
bmc
different
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
CN201510949028.4A
Other languages
Chinese (zh)
Other versions
CN105490859B (en
Inventor
黄家明
乔英良
李冠广
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.)
Shandong Mass Institute Of Information Technology
Original Assignee
Shandong Mass Institute Of Information Technology
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 Shandong Mass Institute Of Information Technology filed Critical Shandong Mass Institute Of Information Technology
Priority to CN201510949028.4A priority Critical patent/CN105490859B/en
Publication of CN105490859A publication Critical patent/CN105490859A/en
Application granted granted Critical
Publication of CN105490859B publication Critical patent/CN105490859B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • H04L41/044—Network management architectures or arrangements comprising hierarchical management structures
    • 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
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0677—Localisation of faults

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Hardware Redundancy (AREA)
  • Computer And Data Communications (AREA)

Abstract

The invention discloses a node positioning method of a high-end fault tolerance server. According to the invention, nodes are positioned through a mode of combining an I2C BUS with an I2C Switch through an RMC and a node BMC. First of all, the nodes are grouped, different node groups are connected with different RMC I2C BUSs; and secondly, the grouped nodes are connected with different channels of the I2C Switch, the RMC accesses the different nodes through switching the channels, and IDs of nodes are comprehensively calculated through the ID of an SMC and the ID of the nodes in the SMC. The method provided by the invention can avoid the problem that a standard IPMITool cannot access the node BMC due to modification of the address of a node BMC I2C, and at the same time, can expand the quantity of connection nodes of a whole cabinet.

Description

A kind of node positioning method of high-end fault-tolerant server
Technical field
The present invention relates to server monitoring administrative skill field, be specifically related to a kind of node positioning method of high-end fault-tolerant server, particularly relate to computing node location and node ID management, mainly for the feature of the centralized management of high-end fault-tolerant server node and differentiated control, the equipment such as computing node are various.
Background technology
Along with user is to the raising of the computation requirement of computer, user requires more and more higher to the calculated performance of single computer.High-end fault-tolerant server is a multipath server.Compared with traditional server, with in reliability, there is compared with traditional server very large advantage in calculated performance, and apply more and more extensive in the field to real-time, reliabilty and availability requirement harshness.High-end fault-tolerant server collects multiple computing node in rack.The monitoring management of high-end fault-tolerant server node adopts RMC, SMC and BMC three-level management framework, and RMC obtains the relevant information of node by SMC.SMC is interconnected by I2C and Node B MC.
Prior art from kinetic factor, substantially similar, comparative maturity, mainly adopt the address of the I2C of the GPIOpin pin definition BMC of RMC at present, main as follows: if after the default address of BMC makes an amendment, read the relevant information existing problems of node by standard I PMITool instrument, need user's Standard modification IPMITool instrument.
Summary of the invention
The technical problem to be solved in the present invention is: in order to solve the problem, the present invention proposes a kind of node positioning method of high-end fault-tolerant server, can avoid causing because of amendment Node B MCI2C address standard I PMITool can not the problem of access node BMC, the quantity of whole rack connected node can be expanded simultaneously.
The technical solution adopted in the present invention is:
A node positioning method for high-end fault-tolerant server, the location of the complete paired node of mode that described method is combined by I2CBUS and I2CSwitch by RMC and Node B MC, step is as follows:
First divide into groups to node, different node groups is connected to different RMCI2CBUS;
Secondly packet node is connected to the different passages of I2CSwitch, RMC accesses different node by switching channel, and specific implementation is as follows:
1) as RMC by network and SMC interconnected, RMC determines the position of SMC by the IP address of SMC;
2) as interconnected in adopted I2C to carry out between SMC and BMC, the node ID between SMC and BMC is located through I2CBus or I2CSwitch and positions;
3) ID of node carries out COMPREHENSIVE CALCULATING by the ID of SMC and the ID of node in SMC.
The realization of described method is by high-end fault-tolerant server rack RMC inside modules integrated network Switching Module, and interconnected by switch module between RMC and multistage SMC, RMC is by the ID of SMC address location SMC.
Between SMC and BMC, adopt I2C to carry out interconnected, the node ID location between SMC and BMC mainly contains two kinds of modes:
A. different nodes is connected to above the different I 2BBus of SMC, and SMC is by the ID of I2BBus location node;
B. many Node B MC are connected to above the 2CSwitch passage of same SMC module I 2BBus, and SMC is connected on BMC by I2CSwitch, and SMC is by the ID of the different channel location nodes of I2CSwitch.
If node number is more, use AB two kinds of method cross-references, improve the quantity of SMC connected node BMC.
Described RMC is as follows about the account form of node ID:
Suppose to need connection ID above calculating M SMC to be the node ID of N:
A. according to the quantity of connected node after each SMC obtained, SMC(i is supposed) quantity of connected node is Node(i);
B. be the node ID of N by connection ID above formulae discovery M SMC below:
Node（1）+Node（2）+…+Node（M-1）+N。
Beneficial effect of the present invention is:
The inventive method can avoid causing because of amendment Node B MCI2C address standard I PMITool can not the problem of access node BMC, can expand the quantity of whole rack connected node simultaneously.
Accompanying drawing explanation
Fig. 1 is RMC of the present invention and node connection diagram.
Embodiment
With reference to the accompanying drawings, in conjunction with embodiment, the present invention is further described:
Embodiment 1:
As shown in Figure 1, a kind of node positioning method of high-end fault-tolerant server, the location of the complete paired node of mode that described method is combined by I2CBUS and I2CSwitch by RMC and Node B MC, step is as follows:
First divide into groups to node, different node groups is connected to different RMCI2CBUS;
Secondly packet node is connected to the different passages of I2CSwitch, RMC accesses different node by switching channel, and specific implementation is as follows:
1) as RMC by network and SMC interconnected, RMC determines the position of SMC by the IP address of SMC;
2) as interconnected in adopted I2C to carry out between SMC and BMC, the node ID between SMC and BMC is located through I2CBus or I2CSwitch and positions;
3) ID of node carries out COMPREHENSIVE CALCULATING by the ID of SMC and the ID of node in SMC.
Embodiment 2:
On the basis of embodiment 1, the realization of method described in the present embodiment is by high-end fault-tolerant server rack RMC inside modules integrated network Switching Module, and interconnected by switch module between RMC and multistage SMC, RMC is by the ID of SMC address location SMC.
Embodiment 3:
On the basis of embodiment 1, it is interconnected that the present embodiment adopts I2C to carry out between SMC and BMC, and the node ID location between SMC and BMC mainly contains two kinds of modes:
A. different nodes is connected to above the different I 2BBus of SMC, and SMC is by the ID of I2BBus location node;
B. many Node B MC are connected to above the 2CSwitch passage of same SMC module I 2BBus, and SMC is connected on BMC by I2CSwitch, and SMC is by the ID of the different channel location nodes of I2CSwitch.
Embodiment 4:
On the basis of embodiment 3, if the present embodiment node number is more, use AB two kinds of method cross-references, improve the quantity of SMC connected node BMC.
Embodiment 5:
On the basis of 1-4 any embodiment, described in the present embodiment, RMC is as follows about the account form of node ID:
Suppose to need connection ID above calculating M SMC to be the node ID of N:
A. according to the quantity of connected node after each SMC obtained, SMC(i is supposed) quantity of connected node is Node(i);
B. be the node ID of N by connection ID above formulae discovery M SMC below:
Node（1）+Node（2）+…+Node（M-1）+N。
Above execution mode is only for illustration of the present invention; and be not limitation of the present invention; the those of ordinary skill of relevant technical field; without departing from the spirit and scope of the present invention; can also make a variety of changes and modification; therefore all equivalent technical schemes also belong to category of the present invention, and scope of patent protection of the present invention should be defined by the claims.

Claims (5)

1. a node positioning method for high-end fault-tolerant server, is characterized in that: the location of the complete paired node of mode that described method is combined by I2CBUS and I2CSwitch by RMC and Node B MC, and step is as follows:
First divide into groups to node, different node groups is connected to different RMCI2CBUS;
Secondly packet node is connected to the different passages of I2CSwitch, RMC accesses different node by switching channel, and specific implementation is as follows:
1) as RMC by network and SMC interconnected, RMC determines the position of SMC by the IP address of SMC;
2) as interconnected in adopted I2C to carry out between SMC and BMC, the node ID between SMC and BMC is located through I2CBus or I2CSwitch and positions;
3) ID of node carries out COMPREHENSIVE CALCULATING by the ID of SMC and the ID of node in SMC.
2. the node positioning method of a kind of high-end fault-tolerant server according to claim 1, it is characterized in that: the realization of described method is by high-end fault-tolerant server rack RMC inside modules integrated network Switching Module, interconnected by switch module between RMC and multistage SMC, RMC is by the ID of SMC address location SMC.
3. the node positioning method of a kind of high-end fault-tolerant server according to claim 1, is characterized in that: between SMC and BMC, adopt I2C to carry out interconnected, and the node ID location between SMC and BMC mainly contains two kinds of modes:
A. different nodes is connected to above the different I 2BBus of SMC, and SMC is by the ID of I2BBus location node;
B. many Node B MC are connected to above the 2CSwitch passage of same SMC module I 2BBus, and SMC is connected on BMC by I2CSwitch, and SMC is by the ID of the different channel location nodes of I2CSwitch.
4. the node positioning method of a kind of high-end fault-tolerant server according to claim 3, is characterized in that: if node number is more, uses AB two kinds of method cross-references, improves the quantity of SMC connected node BMC.
5., according to the node positioning method of the arbitrary described a kind of high-end fault-tolerant server of claim 1-4, it is characterized in that: described RMC is as follows about the account form of node ID:
Suppose to need connection ID above calculating M SMC to be the node ID of N:
A. according to the quantity of connected node after each SMC obtained, SMC(i is supposed) quantity of connected node is Node(i);
B. be the node ID of N by connection ID above formulae discovery M SMC below:
Node（1）+Node（2）+…+Node（M-1）+N。
CN201510949028.4A 2015-12-18 2015-12-18 A kind of node positioning method of high-end fault-tolerant server Active CN105490859B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510949028.4A CN105490859B (en) 2015-12-18 2015-12-18 A kind of node positioning method of high-end fault-tolerant server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510949028.4A CN105490859B (en) 2015-12-18 2015-12-18 A kind of node positioning method of high-end fault-tolerant server

Publications (2)

Publication Number Publication Date
CN105490859A true CN105490859A (en) 2016-04-13
CN105490859B CN105490859B (en) 2019-01-22

Family

ID=55677602

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510949028.4A Active CN105490859B (en) 2015-12-18 2015-12-18 A kind of node positioning method of high-end fault-tolerant server

Country Status (1)

Country Link
CN (1) CN105490859B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106484656A (en) * 2016-11-08 2017-03-08 郑州云海信息技术有限公司 A kind of management board collecting multinode management information
CN109117106A (en) * 2018-06-29 2019-01-01 深圳市同泰怡信息技术有限公司 A kind of method of the compatible node of server LCD display

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102571441A (en) * 2012-01-18 2012-07-11 百度在线网络技术（北京）有限公司 Method, system and device for intelligently managing whole machine cabinet
CN102594602A (en) * 2012-02-23 2012-07-18 浪潮电子信息产业股份有限公司 Location management design method of multi-node cloud computing server
CN103685386A (en) * 2012-09-12 2014-03-26 北京百度网讯科技有限公司 Method and equipment for determining positional information of calculation equipment in complete machine cabinet
US20140344431A1 (en) * 2013-05-16 2014-11-20 Aspeed Technology Inc. Baseboard management system architecture
CN104598329A (en) * 2015-02-12 2015-05-06 浪潮电子信息产业股份有限公司 Automatic BMC (baseboard management controller) fault solution method based on RMC (rack server management center) management
CN104777890A (en) * 2015-04-02 2015-07-15 浪潮电子信息产业股份有限公司 Power consumption management system of multipath server

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102571441A (en) * 2012-01-18 2012-07-11 百度在线网络技术（北京）有限公司 Method, system and device for intelligently managing whole machine cabinet
CN102594602A (en) * 2012-02-23 2012-07-18 浪潮电子信息产业股份有限公司 Location management design method of multi-node cloud computing server
CN103685386A (en) * 2012-09-12 2014-03-26 北京百度网讯科技有限公司 Method and equipment for determining positional information of calculation equipment in complete machine cabinet
US20140344431A1 (en) * 2013-05-16 2014-11-20 Aspeed Technology Inc. Baseboard management system architecture
CN104598329A (en) * 2015-02-12 2015-05-06 浪潮电子信息产业股份有限公司 Automatic BMC (baseboard management controller) fault solution method based on RMC (rack server management center) management
CN104777890A (en) * 2015-04-02 2015-07-15 浪潮电子信息产业股份有限公司 Power consumption management system of multipath server

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106484656A (en) * 2016-11-08 2017-03-08 郑州云海信息技术有限公司 A kind of management board collecting multinode management information
CN106484656B (en) * 2016-11-08 2019-10-18 郑州云海信息技术有限公司 A kind of management board of collectable multinode management information
CN109117106A (en) * 2018-06-29 2019-01-01 深圳市同泰怡信息技术有限公司 A kind of method of the compatible node of server LCD display

Also Published As

Publication number Publication date
CN105490859B (en) 2019-01-22

Similar Documents

Publication Publication Date Title
US11223577B2 (en) Switch network architecture
Fu et al. Orion: A hybrid hierarchical control plane of software-defined networking for large-scale networks
CN105577430A (en) Node management method of high-end fault-tolerant server
CN106155959A (en) Data transmission method and data transmission system
CN104486103A (en) Message transmission method and equipment
Guo et al. Exploring server redundancy in nonblocking multicast data center networks
CN104135514A (en) Integrated virtualized storing system
CN103023973A (en) Cluster server designing method based on CPCI (Compact Peripheral Component Interconnect) structure
CN105162623A (en) Cloud processing method and cloud server
CN105391651A (en) Virtual optical network multilayer resource convergence method and system
CN112463364A (en) Packet-based distributed storage SCSI target service management method and system
CN105490859A (en) Node positioning method of high-end fault tolerance server
EP3253030B1 (en) Method and device for reporting openflow switch capability
WO2016082442A1 (en) Storage system and exchange extension apparatus
CN203133718U (en) Blade server backboard
CN109428815A (en) A kind of method and device handling message
CN110036610B (en) Method and switch for route management in software defined network
CN104954439A (en) Cloud server, node interconnection method thereof and cloud server system
CN209545771U (en) A kind of double star Ethernet backboard for ATCA closed case
CN106506408A (en) A kind of implementation method of 96+6 interface switchboards
CN104052665A (en) Method and equipment for determining flow forwarding path
US9104562B2 (en) Enabling communication over cross-coupled links between independently managed compute and storage networks
Peng et al. A novel framework of distributed datacenter networks to support intelligent services: Architecture, operation, and solutions
CN106445001B (en) The shared server system of running state information
Xia et al. Stop rerouting! Enabling ShareBackup for failure recovery in data center networks

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