CN118524102A - Dual-node BMC management device and method - Google Patents
Dual-node BMC management device and method Download PDFInfo
- Publication number
- CN118524102A CN118524102A CN202410444419.XA CN202410444419A CN118524102A CN 118524102 A CN118524102 A CN 118524102A CN 202410444419 A CN202410444419 A CN 202410444419A CN 118524102 A CN118524102 A CN 118524102A
- Authority
- CN
- China
- Prior art keywords
- bmc
- switching unit
- server node
- network card
- intelligent network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000009977 dual effect Effects 0.000 claims description 13
- 238000002955 isolation Methods 0.000 claims description 10
- 238000007726 management method Methods 0.000 abstract description 140
- 230000006870 function Effects 0.000 abstract description 20
- 230000008569 process Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000003068 static effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 108010028984 3-isopropylmalate dehydratase Proteins 0.000 description 2
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 229910052710 silicon Inorganic materials 0.000 description 2
- 239000010703 silicon Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a dual-node BMC management device and a dual-node BMC management method, wherein the device comprises: the system comprises a first server node, a second server node and an intelligent network card; the intelligent network card is used for receiving the BMC management message and executing management operation on the BMC of the first server node or the BMC of the second server node according to the BMC management message based on the system chip of the intelligent network card. According to the dual-node BMC management device and method provided by the embodiment of the invention, the intelligent network card is connected with the first server node and the second server node through the first switching unit. The second switching unit is arranged in the intelligent network card and used for expanding the functions of the intelligent network card, and can also realize the management operation of the BMC of the double server nodes under the condition of realizing network tasks, thereby furthest reducing the use of network resources, saving the network resources of the intelligent network card and improving the management efficiency of the intelligent network card management server nodes.
Description
Technical Field
The invention relates to the technical field of servers, in particular to a dual-node BMC management device and method.
Background
With the rise of cloud services, cloud space and cloud storage environments are built more and more widely. The general user operates in a management system provided by a manufacturer, and the manufacturer of the management system can conduct own customized design and limit of management and access rights. In such a server, the server is generally managed based on an intelligent network card, and a system is provided in the network card.
The existing scheme based on collocation and management of the intelligent network cards for single nodes, wherein each node is independently provided with an intelligent network card wastes a great deal of network equipment resources.
Disclosure of Invention
The invention provides a dual-node BMC management device and method, which are used for saving network resources of an intelligent network card and improving management efficiency of an intelligent network card management server node.
The invention provides a BMC management device of double nodes, comprising: the system comprises a first server node, a second server node and an intelligent network card;
The first end of a second switching unit in the intelligent network card is connected with an external network, the second end of the second switching unit is connected with a baseboard management controller BMC of the first server node and the BMC of the second server node respectively based on the first switching unit, the third end of the second switching unit is connected with a system chip in the intelligent network card, and the fourth end of the second switching unit is connected with the BMC in the intelligent network card;
the intelligent network card is used for receiving the BMC management message, and executing management operation on the BMC of the first server node or the BMC of the second server node according to the BMC management message based on a system chip of the intelligent network card.
According to the dual-node BMC management device provided by the invention, the second switching unit is internally provided with network isolation;
The network isolation is such that: the first end of the second exchange unit is communicated with the fourth end of the second exchange unit in the second exchange unit, the second end of the second exchange unit is communicated with the third end of the second exchange unit in the second exchange unit, and the second end of the second exchange unit is communicated with the fourth end of the second exchange unit in the second exchange unit;
The second switching unit is configured to receive, based on a third end of the second switching unit, a BMC management message sent by a system chip of the intelligent network card, and forward, based on a second end of the second switching unit, the BMC management message to a BMC of the first server node or a BMC of the second server node based on the first switching unit, so as to perform a management operation on the BMC of the first server node or the BMC of the second server node;
the second switching unit is further configured to:
Based on the first end of the second switching unit and the fourth end of the second switching unit, the BMC of the intelligent network card is communicated with the external network, and the intelligent network card and the external network can be accessed mutually.
According to the dual-node BMC management device provided by the invention, the first end of the first switching unit is connected with the second end of the second switching unit, the second end of the first switching unit is connected with the BMC of the first server node, and the third end of the first switching unit is connected with the BMC of the second server node;
and the first switching unit is used for receiving the management information of the intelligent network card and forwarding the management information to the BMC of the corresponding server node.
According to the dual-node BMC management device provided by the invention, the intelligent network card is further used for:
and the BMC of the intelligent network card is communicated with the external network based on the second switching unit, so that the intelligent network card and the external network can be mutually accessed.
According to the dual-node BMC management device provided by the invention, the first server node, the second server node and the intelligent network card are in the same network segment.
According to the dual-node BMC management device provided by the invention, the first end of the second switching unit is connected with the external network based on an RJ45 port, and the second end of the second switching unit is connected with the first end of the first switching unit based on the RJ45 port.
The invention also provides a BMC management method of the double nodes, which comprises the following steps:
Receiving a Baseboard Management Controller (BMC) management message sent by a third end of a second switching unit in an intelligent network card, wherein a first end of the second switching unit in the intelligent network card is connected with an external network, a second end of the second switching unit is respectively connected with a BMC of a first server node and a BMC of a second server node based on the first switching unit, and a fourth end of the second switching unit is connected with the BMC in the intelligent network card;
And determining a management operation instruction based on the BMC management message, and sending the management operation instruction to the BMC of the first server node or the BMC of the second server node based on the second exchange unit and the first exchange unit so as to execute management operation on the BMC of the first server node or the BMC of the second server node.
The BMC management method of the double nodes provided by the invention further comprises the following steps:
and setting the IP addresses of the first server node, the second server node and the intelligent network card so that the first server node, the second server node and the intelligent network card are in the same network segment.
According to the dual-node BMC management method provided by the invention, the first end of the second switching unit is connected with the external network based on an RJ45 port, and the second end of the second switching unit is connected with the first end of the first switching unit based on the RJ45 port.
The invention also provides an intelligent network card, which comprises the double-node BMC management device.
According to the dual-node BMC management device and method provided by the embodiment of the invention, the intelligent network card is connected with the BMC of the first server node and the BMC of the second server node through the first switching unit. The second switching unit is arranged in the intelligent network card and used for expanding the functions of the intelligent network card, and can also realize the management operation of the BMC of the double server nodes under the condition of realizing network tasks, thereby furthest reducing the use of network resources, saving the network resources of the intelligent network card and improving the management efficiency of the intelligent network card management server nodes.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are some embodiments of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a dual-node BMC management device according to the present invention;
FIG. 2 is a schematic flow chart of a dual-node BMC management method provided by the invention;
fig. 3 is a schematic device structure diagram of a dual-node BMC management method according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides a dual-node BMC management device, and FIG. 1 is a schematic structural diagram of the dual-node BMC management device. Referring to fig. 1, the dual-node BMC management apparatus provided by the present invention includes: a first server node 110, a second server node 120, and an intelligent network card 130.
The respective parts of the BMC management device of the dual node are described separately below.
The intelligent network card 130 includes a system on a chip SoC, a baseboard management controller, and a second switching unit.
The SoC system chip of the intelligent network card 130 is a silicon chip integrated with a processor, a memory, a network interface and other key components, and is used for processing more network traffic and more complex network tasks on the network card through hardware acceleration and optimized network functions. Because the system on chip SoC contains an operating system, the management operation of the BMC of the server node can be realized based on the system on chip SoC while the network task is realized based on the system on chip SoC.
In the case of implementing management operations of the BMC of the dual server node based on the system chip in the intelligent network card 130, it is necessary to redesign the device structure of the intelligent network card, and to: connection relationship between the first server node 110 and the second server node 120.
Specifically, a second switching unit is disposed in the intelligent network card 130, so as to implement expansion of functions of the intelligent network card 130, and under the condition that network tasks can be implemented, management operation of the BMC of the dual server node can also be implemented.
A first end of a second switching unit in the intelligent network card 130 is connected to an external network, and a fourth end of the second switching unit is connected to a BMC in the intelligent network card 130. The line can realize the mutual access of the external network and the intelligent network card, thereby realizing the network task.
The second end of the second switching unit is connected to the BMC of the first server node 110 and the BMC of the second server node 120 respectively based on the first switching unit, and the third end of the second switching unit is connected to the system chip in the intelligent network card 130. The connection between the system chip of the intelligent network card 130 and the BMC of the first server node 110 and the BMC of the second server node 120 is realized, and a foundation is provided for the subsequent management operation of the BMC of the dual nodes.
Specifically, based on the connection lines, the specific process of implementing management of the BMC of the first server node 110 and the BMC of the second server node 120 by the intelligent network card 130 is:
The intelligent network card 130 receives the BMC management message. The BMC management message is a message for managing the BMC of the first server node 110 or the BMC of the second server node 120.
Based on the system chip of the intelligent network card 130, according to the BMC management message, a management operation of the BMC of the first server node 110 or the BMC of the second server node 120 is performed.
It will be appreciated that based on management of the BMC of the first server node 110 or the BMC of the second server node 120, remote monitoring of the status of the device, performing operations, collecting logs, etc. may be implemented, thereby enabling comprehensive management of the device. The BMC management control function is rich, the functions of remote management, fault diagnosis, power management, firmware upgrading, safety management and the like can be provided, and a convenient and efficient device management and maintenance means can be provided.
Meanwhile, compared with the BMC of a server for managing single nodes by the intelligent network card, the BMC of the server for managing double nodes by the intelligent network card can improve the management efficiency of the intelligent network card management server nodes, and the scheme that each node independently designs one intelligent network card is avoided, so that a great deal of network equipment resources are wasted.
The more server nodes are managed by a single intelligent network card, the more difficult the network deployment of the whole system is, and the deployment scheme of more than two server nodes is extremely complex. Compared with the BMC of the server for managing multiple nodes based on the intelligent network card, the server BMC for managing the dual nodes based on the intelligent network card can reduce the difficulty of network deployment under the condition of guaranteeing the management of the dual node BMC.
According to the dual-node BMC management device provided by the embodiment of the invention, the intelligent network card is connected with the BMC of the first server node and the BMC of the second server node through the first switching unit. The second switching unit is arranged in the intelligent network card and used for expanding the functions of the intelligent network card, and can also realize the management operation of the BMC of the double server nodes under the condition of realizing network tasks, thereby furthest reducing the use of network resources, saving the network resources of the intelligent network card and improving the management efficiency of the intelligent network card management server nodes.
In one embodiment, the second switching unit is internally provided with network isolation; the network isolation is such that: the first end of the second exchange unit is communicated with the fourth end of the second exchange unit in the second exchange unit, the second end of the second exchange unit is communicated with the third end of the second exchange unit in the second exchange unit, and the second end of the second exchange unit is communicated with the fourth end of the second exchange unit in the second exchange unit; the second switching unit is configured to receive, based on a third end of the second switching unit, a BMC management message sent by a system chip of the intelligent network card, and forward, based on a second end of the second switching unit, the BMC management message to a BMC of the first server node or a BMC of the second server node based on the first switching unit, so as to perform a management operation on the BMC of the first server node or the BMC of the second server node; the second switching unit is further configured to: based on the first end of the second switching unit and the fourth end of the second switching unit, the BMC of the intelligent network card is communicated with the external network, and the intelligent network card and the external network can be accessed mutually.
Network isolation is provided inside the second switching unit. Specifically, by customizing the firmware version of the second switching unit, network isolation is achieved in a manner of setting a VLAN ID, so that the first end of the second switching unit is communicated with the fourth end of the second switching unit in the second switching unit, the second end of the second switching unit is communicated with the third end of the second switching unit in the second switching unit, and the second end of the second switching unit is communicated with the fourth end of the second switching unit in the second switching unit.
It will be appreciated that after the network isolation is set, two paths may be implemented based on the second switching unit, where the two paths are not communicated with each other. One path realizes network tasks; another task implements management operations for the BMC of the dual server node.
For network tasks, the specific implementation process may be: based on the first end of the second switching unit and the fourth end of the second switching unit, the BMC of the intelligent network card is communicated with the external network, and the intelligent network card and the external network can be mutually accessed.
For the management operation of the BMC of the double server node, the specific implementation process can be as follows: and receiving a BMC management message sent by a system chip of the intelligent network card based on a third end of a second switching unit, and forwarding the BMC management message to the BMC of the first server node or the BMC of the second server node based on the first switching unit based on a second end of the second switching unit so as to execute management operation on the BMC of the first server node or the BMC of the second server node.
In one embodiment, a first end of a first switching unit is connected to a second end of the second switching unit, the second end of the first switching unit is connected to the BMC of the first server node, and a third end of the first switching unit is connected to the BMC of the second server node; and the first switching unit is used for receiving the management information of the intelligent network card and forwarding the management information to the BMC of the corresponding server node.
Specifically, the first switching unit is provided with three ports. The first end of the first switching unit is connected with the second end of the second switching unit, the second end of the first switching unit is connected with the BMC of the first server node, and the third end of the first switching unit is connected with the BMC of the second server node so as to realize that the intelligent network card is connected with the BMC of the first server and the BMC of the second server based on the first switching unit.
And in the process of realizing management of the BMC of the first server and the BMC of the second server by the intelligent network card based on the first exchange unit. The intelligent network card issues management information to the first switching unit. And after receiving the management message issued by the intelligent network card, the first switching unit forwards the management message to the BMC of the corresponding server node.
In one embodiment, the intelligent network card is further configured to: and the BMC of the intelligent network card is communicated with the external network based on the second switching unit, so that the intelligent network card and the external network can be mutually accessed.
The second switching unit is typically another network interface on the intelligent network card for connecting to an external network. This interface may be connected to a Local Area Network (LAN), public internet or other network within the enterprise so that the intelligent network card may communicate with external networks.
The intelligent network card can establish a communication link with an external network through the management control function of the BMC. The BMC can control the network connection of the intelligent network card through the second switching unit so that the BMC can send and receive data packets and communicate with other devices in an external network.
The BMC of the intelligent network card is communicated with the external network based on the second switching unit, so that the intelligent network card and the external network can be accessed mutually, and the remote management and monitoring of the intelligent network card are realized through the management control function of the BMC, so that the flexibility, reliability and safety of the network are improved.
Optionally, the intelligent network card and the second switching unit are deployed in a cloud environment as a containerized network function. The deployment and expansion of the intelligent network card and the second switching unit are dynamically managed by a container orchestration tool (e.g., kubernetes) and communicated with an external network.
Specifically, the functions of the intelligent network card and the second switching unit may be containerized and packaged into a Docker mirror image. Ensuring that the required software, drivers, configuration files, etc. are contained within the container. The build process of defining the container is written Dockerfile and mirroring is built using the dock build command.
One Kubernetes cluster is deployed, optionally using a Kubernetes service provided by the public cloud (e.g., amazon EKS, google Kubernetes Engine, or Azure Kubernetes Service), or manually building the cluster using tools (e.g., kubeadm) in a private cloud or local environment.
The containerized intelligent network card and the second switching unit application are deployed into a Kubernetes cluster. The deployment can be performed through Deployment resource objects of Kubernetes, and the copy number of the container, the resource requirement, the network configuration and the like are defined. Deployment is performed using kubectl commands or Kubernetes API and the running state of the application is monitored.
The performance and operating status of the intelligent network card and the second switching unit are monitored using a monitoring and logging tool (e.g., prometheus, grafana, ELK, etc.) provided by Kubernetes.
The number of container copies is dynamically expanded by the automatic telescoping mechanism (Horizontal Pod Autoscaler) of Kubernetes, depending on load and demand.
Through the steps, the intelligent network card and the second exchange unit can be deployed in the Kubernetes cluster as a containerized network function, and dynamic management and communication with an external network are realized through a containerization tool.
In one embodiment, the first server node, the second server node, and the intelligent network card are in the same network segment.
And configuring the first server node, the second server node and the network of the intelligent network card to realize that the first server node, the second server node and the intelligent network card are in the same network segment.
Alternatively, the specific setting process may be:
step 1: starting a system kernel forwarding function in an operating system of the intelligent network card;
Step 2: acquiring the name of the intelligent network card, and carrying out network configuration to enable the intelligent network card to have the network IP of the DHCP on the one hand and have the static IP on the other hand: 192.168.1.1, mask: 255.255.255.0, gateway: 192.168.1.1. for network communication with the first server node or the second server node.
The specific configuration parameters are as follows:
auto enx2c16dba25ff3；
iface enx2c16dba25ff3 inet dhcp；
auto eno1.200；
iface eno1.200 inet static；
address 192.168.1.1/24；
gateway 192.168.1.1；
netmask 255.255.255.0。
Step 3: setting port forwarding rules: wherein 443/623/22 ports of the first server node are mapped to 8443/8623/8445 ports of the system chip of the intelligent network card, and 443/623/22 ports of the second server node are mapped to 8444/624/8446 ports of the system chip of the intelligent network card.
The specific configuration parameters are as follows:
iptables-t nat-IPREROUTING-p tcp-i enx2c16dba25ff3--dport8443-j DNAT--to 192.168.1.10:443；
iptables-t nat-IPREROUTING-p udp-i enx2c16dba25ff3--dport623-j DNAT--to 192.168.1.10:623；
iptables-t nat-IPREROUTING-p tcp-i enx2c16dba25ff3--dport8444-j DNAT--to 192.168.1.11:443；
iptables-t nat-IPREROUTING-p udp-i enx2c16dba25ff3--dport624-j DNAT--to 192.168.1.11:623；
iptables-t nat-IPREROUTING-p tcp-i enx2c16dba25ff3--dport8445-j DNAT--to 192.168.1.10:22；
iptables-t nat-IPREROUTING-p tcp-i enx2c16dba25ff3--dport8446-j DNAT--to 192.168.1.11:22。
After the configuration is completed, the data received by the system chip IP of the intelligent network card from the 8443 port is forwarded to the 443 port of the first server node, the BMC of the first server node processes the data, and the data packet is broadcasted from the 8443 port after the data processing is completed. The data received by the intelligent network card system chip IP from the 8444 port is forwarded to the 443 port of the second server node, the BMC of the second server node processes the data, and the data packet is broadcast from the 8444 port after the data processing is finished, so that the data transmission is completed.
The 443 port accessing the BMC can be in IPMI Command instruction communication with the port; the 623 port of the access BMC can log in the WEB UI thereof for management; and accessing 22 ports of the BMC, and entering a debugging serial port of the BMC for debugging. After the above configuration, the following operations are performed:
https:// SoC_os_ip 8443/# dashboard accesses the BMC WEB UI of the first server node;
ipmitool-H SoC_os_ip-U xxxx-P xxxx-I lanplus-P8623 sel get0x01 accesses BMC WEBUI of the first server node;
ssh-p 8445sysadmin@SoC_os_ip accesses a BMC debugging serial port of the first server node;
https:// soc_os_ip 8444/# dashboard access BMC WEBUI of the second server node;
ipmitool-H SoC_os_ip-U xxxx-P xxxx-I lanplus-P8624sel get0x01 accesses BMC WEBUI of the second server node;
ssh-p 8446sysadmin@SoC_os_ip accesses the BMC debug serial port of the second server node.
In one embodiment, the first end of the second switching unit is connected to the external network based on an RJ45 port, and the second end of the second switching unit is connected to the first end of the first switching unit based on an RJ45 port.
RJ45 ports are a common type of network connection port commonly used to connect Ethernet (Ethernet) devices. It is a standardized 8-pin connector commonly used to connect computers, routers, switches, network storage devices, etc. to achieve a Local Area Network (LAN) or Wide Area Network (WAN) connection.
The first end of the second switching unit is connected with the external network based on the RJ45 port, so that the management of the whole system can be realized by connecting only one external RJ45 network port with the external network.
The second end group of the second switching unit is connected with the first end of the first switching unit based on the RJ45 port, and the connection process of the second switching unit and the intelligent network card based on the RJ45 port can be realized.
Fig. 2 is a flow chart of a dual-node BMC management method provided by the invention. Referring to fig. 2, the dual-node BMC management method provided by the present invention includes:
Step 210, receiving a baseboard management controller BMC management message sent by a third end of a second switching unit in the intelligent network card, wherein a first end of the second switching unit in the intelligent network card is connected with an external network, a second end of the second switching unit is respectively connected with a BMC of a first server node and a BMC of a second server node based on the first switching unit, and a fourth end of the second switching unit is connected with the BMC in the intelligent network card;
Step 220, determining a management operation instruction based on the BMC management message, and sending the management operation instruction to the BMC of the first server node or the BMC of the second server node based on the second switching unit and the first switching unit, so as to execute a management operation on the BMC of the first server node or the BMC of the second server node.
The technical scheme of the invention is described in detail below by taking a system chip SoC in an intelligent network card as an example to execute the dual-node BMC management method provided by the invention.
The intelligent network card comprises a system chip SoC, a baseboard management controller and a second switching unit.
The SoC system chip of the intelligent network card is a silicon chip integrated with a processor, a memory, a network interface and other key components, and is used for processing more network traffic and more complex network tasks on the network card through hardware acceleration and optimized network functions. Because the system on chip SoC contains an operating system, the management operation of the BMC of the server node can be realized based on the system on chip SoC while the network task is realized based on the system on chip SoC.
Under the condition that the management operation of the BMC of the double server nodes is realized based on the system chip in the intelligent network card, the device structure of the intelligent network card needs to be redesigned, and the device structure is matched with the device structure: and the connection relation between the first server node and the second server node.
Specifically, a second switching unit is arranged in the intelligent network card, and is used for expanding the functions of the intelligent network card, and the management operation of the BMC of the double server nodes can be realized under the condition that network tasks can be realized.
The first end of a second switching unit in the intelligent network card is connected with an external network, and the fourth end of the second switching unit is connected with the BMC in the intelligent network card. The line can realize the mutual access of the external network and the intelligent network card, thereby realizing the network task.
The second end of the second switching unit is connected with the BMC of the first server node and the BMC of the second server node respectively based on the first switching unit, and the third end of the second switching unit is connected with the system chip in the intelligent network card. The line realizes the connection of the system chip of the intelligent network card, the BMC of the first server node and the BMC of the second server node, and provides a basis for the subsequent management operation of the BMC of the double nodes.
Specifically, based on the connection line, the intelligent network card realizes the specific process of managing the BMC of the first server node and the BMC of the second server node as follows:
The intelligent network card receives BMC management information. The BMC management message is a message for managing the BMC of the first server node or the BMC of the second server node.
And based on the system chip of the intelligent network card, based on the BMC management message, determining a management operation instruction, and based on a second exchange unit and the first exchange unit, sending the management operation instruction to the BMC of the first server node or the BMC of the second server node so as to execute management operation on the BMC of the first server node or the BMC of the second server node.
It can be appreciated that based on management of the BMC of the first server node or the BMC of the second server node, remote monitoring of the state of the device, performing operations, collecting logs, etc. may be implemented, thereby implementing overall management of the device. The BMC management control function is rich, the functions of remote management, fault diagnosis, power management, firmware upgrading, safety management and the like can be provided, and a convenient and efficient device management and maintenance means can be provided.
Meanwhile, compared with the BMC of a server for managing single nodes by the intelligent network card, the BMC of the server for managing double nodes by the intelligent network card can improve the management efficiency of the intelligent network card management server nodes, and the scheme that each node independently designs one intelligent network card is avoided, so that a great deal of network equipment resources are wasted.
The more server nodes are managed by a single intelligent network card, the more difficult the network deployment of the whole system is, and the deployment scheme of more than two server nodes is extremely complex. Compared with the BMC of the server for managing multiple nodes based on the intelligent network card, the server BMC for managing the dual nodes based on the intelligent network card can reduce the difficulty of network deployment under the condition of guaranteeing the management of the dual node BMC.
According to the dual-node BMC management method provided by the embodiment of the invention, the intelligent network card is connected with the BMC of the first server node and the BMC of the second server node through the first switching unit. The second switching unit is arranged in the intelligent network card and used for expanding the functions of the intelligent network card, and can also realize the management operation of the BMC of the double server nodes under the condition of realizing network tasks, thereby furthest reducing the use of network resources, saving the network resources of the intelligent network card and improving the management efficiency of the intelligent network card management server nodes.
In one embodiment, further comprising: and setting the IP addresses of the first server node, the second server node and the intelligent network card so that the first server node, the second server node and the intelligent network card are in the same network segment.
And configuring the first server node, the second server node and the network of the intelligent network card to realize that the first server node, the second server node and the intelligent network card are in the same network segment.
In one embodiment, the first end of the second switching unit is connected to the external network based on an RJ45 port, and the second end of the second switching unit is connected to the first end of the first switching unit based on an RJ45 port.
RJ45 ports are a common type of network connection port commonly used to connect Ethernet (Ethernet) devices. It is a standardized 8-pin connector commonly used to connect computers, routers, switches, network storage devices, etc. to achieve a Local Area Network (LAN) or Wide Area Network (WAN) connection.
The first end of the second switching unit is connected with the external network based on the RJ45 port, so that the management of the whole system can be realized by connecting only one external RJ45 network port with the external network.
The second end group of the second switching unit is connected with the first end of the first switching unit based on the RJ45 port, and the connection process of the second switching unit and the intelligent network card based on the RJ45 port can be realized.
The invention also provides a device structure schematic diagram of the dual-node BMC management method. As shown in fig. 3, the device includes a first server node, a second server node, a first switching unit, and an intelligent network card; the intelligent network card comprises a second switching unit, a system chip SoC and a BMC.
The first switching unit is an external switch, the first server node and the second server node are respectively connected with the second end and the third end of the first switching unit, and the first section of the first switching unit is connected with the second port of the second switching unit of the intelligent network card. The external network is connected to the first port of the second switching unit of the intelligent network card. The intelligent network card is internally provided with a second switching unit and 4 ports. The external form intelligent network card is provided with 2 RJ45 network cards and 2 optical network ports.
The BMC in the first server node may be implemented based on an AST2600 chip, and the second port of the first switching unit may be implemented based on an RTL8211PHY module, so as to connect the first switching unit to the BMC of the first server node. The BMC in the second server node may be implemented based on an AST2600 chip, and the third port of the first switching unit may be implemented based on an RTL8211PHY chip, to connect the first switching unit to the BMC of the second server node. And BMC in the intelligent network card can be realized based on an ASST2500 chip.
By customizing the firmware versions of the first switching unit and the second switching unit in the intelligent network card, setting vlan IDs for network isolation, an external management network can be realized, and network connection of the intelligent network card SOC/AST2500 (BMC) and AST2600 (BMC) in two nodes can be realized.
When the BMC of each node is started, whether the current node is a first server node or a second server node in the double nodes can be obtained through GPIO information, if the slave node is detected to be the first server node, the current network is set to be static IP through a program, and related parameters are set as follows: 192.168.1.10, mask: 255.255.255.0, gateway: 192.168.1.1. if the subordinate node is detected to be the second server node, setting the current second server node network to be static IP through a program, and setting the related parameters as follows: 192.168.1.11, mask: 255.255.255.0, gateway: 192.168.1.1.
And configuring the first server node, the second server node and the network of the intelligent network card to realize that the first server node, the second server node and the intelligent network card are in the same network segment.
The specific setting process can be as follows:
step 1: starting a system kernel forwarding function in an operating system of the intelligent network card;
Step 2: acquiring the name of the intelligent network card, and carrying out network configuration to enable the intelligent network card to have the network IP of the DHCP on the one hand and have the static IP on the other hand: 192.168.1.1, mask: 255.255.255.0, gateway: 192.168.1.1. for network communication with the first server node or the second server node.
The specific configuration parameters are as follows:
auto enx2c16dba25ff3；
iface enx2c16dba25ff3 inet dhcp；
auto eno1.200；
iface eno1.200 inet static；
address 192.168.1.1/24；
gateway 192.168.1.1；
netmask 255.255.255.0。
Step 3: setting port forwarding rules: wherein 443/623/22 ports of the first server node are mapped to 8443/8623/8445 ports of the system chip of the intelligent network card, and 443/623/22 ports of the second server node are mapped to 8444/624/8446 ports of the system chip of the intelligent network card.
The specific configuration parameters are as follows:
iptables-t nat-IPREROUTING-p tcp-i enx2c16dba25ff3--dport8443-j DNAT--to 192.168.1.10:443；
iptables-t nat-IPREROUTING-p udp-i enx2c16dba25ff3--dport623-j DNAT--to 192.168.1.10:623；
iptables-t nat-IPREROUTING-p tcp-i enx2c16dba25ff3--dport8444-j DNAT--to 192.168.1.11:443；
iptables-t nat-IPREROUTING-p udp-i enx2c16dba25ff3--dport624-j DNAT--to 192.168.1.11:623；
iptables-t nat-IPREROUTING-p tcp-i enx2c16dba25ff3--dport8445-j DNAT--to 192.168.1.10:22；
iptables-t nat-IPREROUTING-p tcp-i enx2c16dba25ff3--dport8446-j DNAT--to 192.168.1.11:22。
After the configuration is completed, the data received by the system chip IP of the intelligent network card from the 8443 port is forwarded to the 443 port of the first server node, the BMC of the first server node processes the data, and the data packet is broadcasted from the 8443 port after the data processing is completed. The data received by the intelligent network card system chip IP from the 8444 port is forwarded to the 443 port of the second server node, the BMC of the second server node processes the data, and the data packet is broadcast from the 8444 port after the data processing is finished, so that the data transmission is completed.
The 443 port accessing the BMC can be in IPMI Command instruction communication with the port; the 623 port of the access BMC can log in the WEB UI thereof for management; and accessing 22 ports of the BMC, and entering a debugging serial port of the BMC for debugging. After the above configuration, the following operations are performed:
https:// SoC_os_ip 8443/# dashboard accesses the BMC WEB UI of the first server node;
ipmitool-H SoC_os_ip-U xxxx-P xxxx-I lanplus-P8623 sel get0x01 accesses BMC WEBUI of the first server node;
ssh-p 8445sysadmin@SoC_os_ip accesses a BMC debugging serial port of the first server node;
https:// soc_os_ip 8444/# dashboard access BMC WEBUI of the second server node;
ipmitool-H SoC_os_ip-U xxxx-P xxxx-I lanplus-P8624sel get0x01 accesses BMC WEBUI of the second server node;
ssh-p 8446sysadmin@SoC_os_ip accesses the BMC debug serial port of the second server node.
The invention also provides an intelligent network card, which comprises the dual-node BMC management device.
According to the intelligent network card provided by the embodiment of the invention, the intelligent network card is connected with the BMC of the first server node and the BMC of the second server node through the first switching unit. The second switching unit is arranged in the intelligent network card and used for expanding the functions of the intelligent network card, and can also realize the management operation of the BMC of the double server nodes under the condition of realizing network tasks, thereby furthest reducing the use of network resources, saving the network resources of the intelligent network card and improving the management efficiency of the intelligent network card management server nodes.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A dual-node BMC management apparatus, the apparatus comprising: the system comprises a first server node, a second server node and an intelligent network card;
The first end of a second switching unit in the intelligent network card is connected with an external network, the second end of the second switching unit is connected with a baseboard management controller BMC of the first server node and the BMC of the second server node respectively based on the first switching unit, the third end of the second switching unit is connected with a system chip in the intelligent network card, and the fourth end of the second switching unit is connected with the BMC in the intelligent network card;
the intelligent network card is used for receiving the BMC management message, and executing management operation on the BMC of the first server node or the BMC of the second server node according to the BMC management message based on a system chip of the intelligent network card.
2. The dual-node BMC management device according to claim 1, wherein a network isolation is provided inside the second switching unit;
The network isolation is such that: the first end of the second exchange unit is communicated with the fourth end of the second exchange unit in the second exchange unit, the second end of the second exchange unit is communicated with the third end of the second exchange unit in the second exchange unit, and the second end of the second exchange unit is communicated with the fourth end of the second exchange unit in the second exchange unit;
The second switching unit is configured to receive, based on a third end of the second switching unit, a BMC management message sent by a system chip of the intelligent network card, and forward, based on a second end of the second switching unit, the BMC management message to a BMC of the first server node or a BMC of the second server node based on the first switching unit, so as to perform a management operation on the BMC of the first server node or the BMC of the second server node;
the second switching unit is further configured to:
Based on the first end of the second switching unit and the fourth end of the second switching unit, the BMC of the intelligent network card is communicated with the external network, and the intelligent network card and the external network can be accessed mutually.
3. The dual-node BMC management device according to claim 1, wherein a first end of the first switching unit is connected to a second end of the second switching unit, the second end of the first switching unit is connected to a BMC of the first server node, and a third end of the first switching unit is connected to a BMC of the second server node;
and the first switching unit is used for receiving the management information of the intelligent network card and forwarding the management information to the BMC of the corresponding server node.
4. The dual node BMC management device of claim 1, wherein the intelligent network card is further configured to:
and the BMC of the intelligent network card is communicated with the external network based on the second switching unit, so that the intelligent network card and the external network can be mutually accessed.
5. The dual-node BMC management device of claim 1, wherein the first server node, the second server node, and the intelligent network card are in a same network segment.
6. The dual node BMC management device of claim 1, wherein the first end of the second switching unit is connected to the external network based on an RJ45 port and the second end of the second switching unit is connected to the first end of the first switching unit based on an RJ45 port.
7. A method for BMC management of a dual node, the method comprising:
Receiving a Baseboard Management Controller (BMC) management message sent by a third end of a second switching unit in an intelligent network card, wherein a first end of the second switching unit in the intelligent network card is connected with an external network, a second end of the second switching unit is respectively connected with a BMC of a first server node and a BMC of a second server node based on the first switching unit, and a fourth end of the second switching unit is connected with the BMC in the intelligent network card;
And determining a management operation instruction based on the BMC management message, and sending the management operation instruction to the BMC of the first server node or the BMC of the second server node based on the second exchange unit and the first exchange unit so as to execute management operation on the BMC of the first server node or the BMC of the second server node.
8. The method of dual node BMC management according to claim 7, further comprising:
and setting the IP addresses of the first server node, the second server node and the intelligent network card so that the first server node, the second server node and the intelligent network card are in the same network segment.
9. The method of claim 7, wherein the first end of the second switching unit is connected to the external network based on an RJ45 port, and the second end of the second switching unit is connected to the first end of the first switching unit based on an RJ45 port.
10. An intelligent network card, characterized by comprising the dual-node BMC management device according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410444419.XA CN118524102A (en) | 2024-04-12 | 2024-04-12 | Dual-node BMC management device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410444419.XA CN118524102A (en) | 2024-04-12 | 2024-04-12 | Dual-node BMC management device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118524102A true CN118524102A (en) | 2024-08-20 |
Family
ID=92276392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410444419.XA Pending CN118524102A (en) | 2024-04-12 | 2024-04-12 | Dual-node BMC management device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118524102A (en) |
-
2024
- 2024-04-12 CN CN202410444419.XA patent/CN118524102A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107947961B (en) | SDN-based Kubernetes network management system and method | |
| US10715411B1 (en) | Altering networking switch priority responsive to compute node fitness | |
| WO2017162173A1 (en) | Method and device for establishing connection of cloud server cluster | |
| EP2449465B1 (en) | Network traffic processing pipeline for virtual machines in a network device | |
| WO2020024413A1 (en) | Method for controlling deployment of cloud computing platform, server, and storage medium | |
| CN105024855A (en) | Distributed cluster management system and method | |
| CN113572831B (en) | Communication method, computer equipment and medium between Kubernetes clusters | |
| JP5612468B2 (en) | Method and apparatus for communication of diagnostic data in a real-time communication network | |
| CN112042170B (en) | DHCP implementation on nodes for virtual machines | |
| RU2761186C1 (en) | Method and device for traffic exchange of the data processing center, device and data carrier | |
| CN112511326B (en) | Switching method, device, equipment and storage medium | |
| JP2010531602A5 (en) | ||
| CN112769602A (en) | System and method for unified configuration management of white box switch and network operating system | |
| CN110224917A (en) | Data transmission method, apparatus and system, server | |
| US10778467B2 (en) | Method for providing virtual CPE service by using single internet line and network function virtualization cloud | |
| EP3817293B1 (en) | Bulk discovery of devices behind a network address translation device | |
| CN114124803B (en) | Device management method and device, electronic device and storage medium | |
| CN118524102A (en) | Dual-node BMC management device and method | |
| JP5063726B2 (en) | Configuration control method for virtual node device | |
| CN114189485A (en) | Network port management method and system of switch and computer readable storage medium | |
| JP5870804B2 (en) | Communication control system, communication control method, and communication control program | |
| CN113438197B (en) | Multi-stage cascade communication system, method, computer device and medium for cross-network acquisition | |
| EP4149062A1 (en) | Deployment method and apparatus for virtualized network service | |
| JP5170000B2 (en) | Redundant pair detection method, communication device, redundant pair detection program, recording medium | |
| CN112671552A (en) | Automatic discovery method, system and equipment for intelligent network card of virtualization platform |
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 |