CN115442316B - Full stack type high-performance computing bare metal management service system and method - Google Patents
Full stack type high-performance computing bare metal management service system and method Download PDFInfo
- Publication number
- CN115442316B CN115442316B CN202211083900.8A CN202211083900A CN115442316B CN 115442316 B CN115442316 B CN 115442316B CN 202211083900 A CN202211083900 A CN 202211083900A CN 115442316 B CN115442316 B CN 115442316B
- Authority
- CN
- China
- Prior art keywords
- bare metal
- service system
- management service
- network
- metal management
- 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.)
- Active
Links
- 239000002184 metal Substances 0.000 title claims abstract description 148
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000004891 communication Methods 0.000 claims abstract description 26
- 238000002955 isolation Methods 0.000 claims abstract description 18
- 238000007726 management method Methods 0.000 claims description 116
- 230000006870 function Effects 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 27
- 108010028984 3-isopropylmalate dehydratase Proteins 0.000 claims description 26
- 238000005516 engineering process Methods 0.000 claims description 16
- 238000010276 construction Methods 0.000 claims description 15
- 238000013500 data storage Methods 0.000 claims description 8
- 238000011161 development Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000008878 coupling Effects 0.000 claims description 7
- 238000010168 coupling process Methods 0.000 claims description 7
- 238000005859 coupling reaction Methods 0.000 claims description 7
- 230000006835 compression Effects 0.000 claims description 6
- 238000007906 compression Methods 0.000 claims description 6
- 238000009434 installation Methods 0.000 claims description 4
- 101100217298 Mus musculus Aspm gene Proteins 0.000 claims description 3
- 239000000427 antigen Substances 0.000 claims description 3
- 102000036639 antigens Human genes 0.000 claims description 3
- 108091007433 antigens Proteins 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 230000018109 developmental process Effects 0.000 description 6
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/76—Admission control; Resource allocation using dynamic resource allocation, e.g. in-call renegotiation requested by the user or requested by the network in response to changing network conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/78—Architectures of resource allocation
- H04L47/783—Distributed allocation of resources, e.g. bandwidth brokers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/30—Public key, i.e. encryption algorithm being computationally infeasible to invert or user's encryption keys not requiring secrecy
- H04L9/3006—Public key, i.e. encryption algorithm being computationally infeasible to invert or user's encryption keys not requiring secrecy underlying computational problems or public-key parameters
- H04L9/302—Public key, i.e. encryption algorithm being computationally infeasible to invert or user's encryption keys not requiring secrecy underlying computational problems or public-key parameters involving the integer factorization problem, e.g. RSA or quadratic sieve [QS] schemes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3236—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using cryptographic hash functions
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a full stack type high-performance computing bare metal management service system, which comprises a user side, wherein the user side is electrically connected with the bare metal management service system through an input port, the bare metal management service system is in communication connection with a network service system, and the network service system is in communication connection with a cloud server; the method for calculating the bare metal management service system with full stack type high performance comprises the following steps: s1, connecting a bare metal management service system; s2, the bare metal management service system is in communication connection with the cloud server; s3, the bare metal management service system is deployed through a DHCP service and an FTP service; s4, a subnet is arranged on the bare metal management service system; s5, the cloud server processes the data; s6, safety isolation and firewall are used for protecting the system safety; the invention realizes fully automatic system deployment, application deployment and the like on bare metal, can deploy and complete the environment used by users in a short time, and simultaneously realizes quick and elastic expansion of resources.
Description
Technical Field
The invention belongs to the technical field of high-performance computing, and particularly relates to a full stack type high-performance computing bare metal management service system and method.
Background
Many modern project developments need to master various technologies to reduce communication costs, solve the problem of insufficient resources for hands and problem closed loop. The full stack has great value to the business, such as overall planning of the whole business, judgment and selection of a technical scheme, positioning and solving of problems, and the like, and has important influence on the full stack technology capability. In addition, for various talents matched with not very complete entrepreneur companies, the whole stack can solve various problems, has single-block and multi-face functions, saves cost, can promote the rapid development of business in early stage, but various high-performance calculation on the market still has various problems.
The resource management method and the resource management equipment of the bare metal server disclosed by the grant publication number CN112256393B realize that the bare metal server is added to a cloud platform resource pool; creating a virtual hard disk and a virtual network for the bare metal server in the cloud platform, and converting the virtual hard disk into an iSCSI target, so that the bare metal server can perform read-write access on the iSCSI target through a management network; sending a wake-up data packet to the bare metal server through a management network, so that the bare metal server responds to the wake-up data packet to start and mount an iSCSI target as a system disk or a data disk; responding to the starting of the bare metal server and entering an operating system, and sending virtual network configuration information to the bare metal server through a management network to enable the bare metal server to configure a network corresponding to the configuration information; the network interface corresponding to the configuration information is accessed to a network node of the cloud platform through a tunnel network; the management of the bare metal server in a software mode is realized, so that resources between the bare metal server and the virtual machine in the cloud platform are shared, but the problems that the existing system deployment, application deployment and the like on the bare metal can not be realized in a real-time data service scene are not solved. The environment for users to use can be deployed in a short time, and meanwhile, the quick elastic expansion and contraction of resources can be realized. Therefore, we propose a full stack type high-performance computing bare metal management service system and method.
Disclosure of Invention
The invention aims to provide a full stack type high-performance bare metal computing management service system and method, so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: the full stack type high-performance computing bare metal management service system comprises a user side, wherein the user side is electrically connected with the bare metal management service system through an input port, the bare metal management service system is in communication connection with a network service system, the network service system is in communication connection with a cloud server, the user side is used for realizing operation control input of a client, and the bare metal management service system comprises computing services with the performance of an elastic cloud server and a physical machine and is used for providing excellent computing performance and data security for a core database, a key application system, high-performance computing and big data service; the network service system is used for running a network operating system, storing and managing shared resources in the network, serving application programs of all workstations, supervising and controlling network activities, actually managing the network, distributing system resources, knowing and adjusting the running state of the system, closing/starting the resources, and the cloud server is simple, efficient, safe and reliable, and has elastically telescopic processing capacity, so that more stable and safe application can be quickly built, and the difficulty of developing operation and maintenance and the overall IT cost are reduced;
the bare metal management service system comprises an edge layer, a platform layer and an application layer, wherein the edge layer comprises data access, system access and edge calculation, the data access is used for realizing the transmission and access of data of the user side, the system access is used for realizing the access of the system, the edge calculation is used for realizing the preliminary calculation processing of the data, the platform layer comprises a development environment, an operation environment, big data and model construction, the development environment, the operation environment and the operation environment are used for realizing the environment construction of the bare metal management service system, the big data is used for realizing the inquiry and input of data information of the system, and the model construction is used for realizing the model construction of the bare metal management service system and finishing the calculation processing of the data; the application layer is used for realizing application construction of the bare metal management service system.
Preferably, the basic principle of the bare metal management service system is that the deployment server provides a DHCP service and an FTP service, instructs a plurality of bare metal devices to be started by the PXE network card and to distribute dynamic IP, and the bare metal devices download relevant software packages from the deployment server for system installation of the bare metal host.
Preferably, the bare metal management service system is connected through the input interface, where the input interface includes a BMC interface and an IPMI configuration for unique identification, that is, through an IPMI network, a management node remotely controls startup and shutdown, network startup, and disk startup of the bare metal management service system, supports batch deployment of all bare metal devices, requires the management node to connect to the IPMI network, remotely controls the bare metal devices through the IPMI, requires the bare metal management service system to be equipped with the BMC interface, configures an IPMI address, a port, a user name, and a password, and connects to the IPMI network.
Preferably, the bare metal management service system is electrically connected with a subnet, the subnet is provided with an internal and external network communication, the internal and external network communication is provided with a private IP and an EIP, the private IP is an IP address, the problem of the Internet is solved, and the interconnection and intercommunication of a large-scale heterogeneous network are realized; and the coupling relation between the top network application and the bottom network technology is divided, the EIP is an elastic public network IP address, and independent public network IP resources are provided, wherein the elastic public network IP support is dynamically bound and unbound with a bare metal server, a cloud server and a NAT gateway, and the service comprises public network IP addresses and public network outlet bandwidth.
Preferably, a cloud backup is electrically connected to the cloud server, the cloud backup is electrically connected to a cloud hard disk, the cloud hard disk realizes data storage, the cloud backup provides backup protection services for the cloud hard disk and the bare metal management service system, supports backup services based on snapshot technology, and supports data recovery of the server and the disk by using backup data, and the cloud server is electrically connected to an AI learning system for realizing continuous network learning and updating of the data processing system.
Preferably, the bare metal management service system and the subnet are provided with a security isolation, the security isolation comprises a firewall, and the security isolation and the firewall are used for realizing security protection of the bare metal management service system and the subnet, so that the security of the system is improved.
Preferably, the cloud server includes a virtualized resource area and a network area: the virtualized resource area provides resources required by a cloud host and a cloud database through a virtualization technology, and comprises a computing resource pool, a network resource pool and a storage resource pool; the network area is a variety of network interconnection devices required by the system.
Preferably, the unique identification and the password adopt RSA algorithm, ECC encryption method, MD5, IDEA or SHA1;
and one of the algorithms employed is a hash algorithm: the definition of the hash algorithm is as follows:
a hash function (output length l) consists of two algorithms (Gen, H) on PPT;
gen: a probabilistic algorithm takes a security parameter 1n as input and then outputs a secret key s, assuming that the security parameter 1n is implicit in s;
h: takes as input a key s and a 01 string x e 0,1, and then outputs Hs (x) e 0,1 l(n) Wherein n is a security parameter implicit in s;
i.e. H is defined as x.epsilon.0, 1 fixed at the input l ' (n) And l' (n)>l (n), then the hash function is called a fixed length hash function, and algorithm H is called a compression function;
security of the hash function:
anti-second primary image: given an s and a random x, it is computationally difficult for an adversary on a PPT to find that x' +.x satisfies H s (x')＝H s (x)；
Antigen image: given an s and a random y, it is computationally difficult to find a match H for an adversary on a PPT s (x) X value of =y.
Preferably, the hash function domain expansion adopts Merkle-Damgard conversion for expanding the compression function into a hash function capable of meeting the requirement and simultaneously maintaining the anti-collision characteristic of the former;
Merkle-Damgard conversion: let (Gen, h) be a hash function of fixed length with an input length of 2n and an output length of n, a hash function is constructed:
gen: unchanged;
h: for an input key s and a 01 string x e {0,1} * The length L of x is less than 2 n Then:
1. let B =ceil (L/n), where B is the number of packets, fill 0 at the end of x to make L a multiple of n, then divide x into packets x of length n of B 1 ，x 2 ，...，x B Then set x B +1: =l, where L is encoded into a 01 string of n bits;
2. let z be 0 :＝0 n (z 0 is also referred to as the initial vector),the initial vector is arbitrary and can be replaced with any other constant;
3. for i=1, 2,..b+1, z is calculated i :＝h s (z i -1||x i )；
4. Final output z B+1。
The method for calculating the bare metal management service system with full stack type high performance comprises the following steps:
s1, connection of a bare metal management service system: the user end is connected with the bare metal management service system through the input port, and the connection establishment of the whole system is realized;
s2, the bare metal management service system is in communication connection with the cloud server: the bare metal management service system is in communication connection with the no-server through the network service system, so that the bare metal management service system can be connected with a cloud platform to realize calculation processing of data;
s3, the bare metal management service system is deployed through a DHCP service and an FTP service: starting and distributing dynamic IP through XE network card, connecting BMC interface and IPMI network, and connecting through IPMI address, port, user name and password;
s4, a subnet is arranged on the bare metal management service system: a subnet is arranged on the bare metal management service system, private IP and EIP are established through the subnet, the problem of Internet is solved, and the interconnection and intercommunication of large-scale heterogeneous networks are realized; the coupling relation between the top network application and the bottom network technology is divided, independent public network IP resources are provided, and the elastic public network IP support is dynamically bound and unbound with the bare metal server, the cloud server and the NAT gateway;
s5, the cloud server effectively realizes data processing: the cloud server is provided with a cloud hard disk and a cloud backup, the cloud hard disk realizes data storage, the cloud backup provides backup protection service for the cloud hard disk and the bare metal management service system, and the cloud server is also provided with an AI learning system, so that the calculation processing capacity of the data is continuously learned and upgraded;
s6, safety isolation and a firewall are used for realizing safety protection on the system: the system is safely protected by setting the safety isolation and the firewall, so that data information is prevented from being mistakenly transmitted or the system is invaded and damaged.
Compared with the prior art, the invention has the beneficial effects that:
the invention realizes fully automatic system deployment, application deployment and the like on bare metal. The environment for users to use can be deployed and completed in a short time, meanwhile, the resources can be quickly and elastically stretched out and drawn back, the bare metal management service system is connected through an input interface, the communication connection with a cloud server is realized through a network service system, the communication connection between physics and cloud is realized, the bare metal management service system can realize full stack type calculation processing, the common operation of front ends, terminals, calculation and the like can be effectively realized, and a model is built in the bare metal management service system, so that the calculation processing on data information is realized;
full stack type high performance computing advantage:
immediately acquiring HPC resources; the method supports various charging modes such as machine time, month, season and year, and the cost of the client is saved;
the mass elasticity calculation and storage meet the valley peak of the service, and the calculation task is completed rapidly;
the latest Intel and AMD platform CPU and the latest V100/P100 GPU, FPGA and other various computing resources are adopted to easily cope with the latest application requirements;
industry solutions provide convenient SaaS application integration; and the corresponding operation flow is completed in a graphical interaction mode, so that a user can concentrate on application innovation.
Drawings
FIG. 1 is a schematic diagram of a system architecture of the present invention;
FIG. 2 is a flow chart of the steps of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but 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.
Referring to fig. 1, the present invention provides a technical solution: the full stack type high-performance computing bare metal management service system comprises a user side, wherein the user side is electrically connected with the bare metal management service system through an input port, the bare metal management service system is in communication connection with a network service system, the network service system is in communication connection with a cloud server, the user side is used for realizing operation control input of a client, and the bare metal management service system comprises computing services with the performance of an elastic cloud server and a physical machine and is used for providing excellent computing performance and data security for a core database, a key application system, high-performance computing and big data service; the network service system is used for running a network operating system, storing and managing shared resources in the network, serving application programs of all workstations, supervising and controlling network activities, actually managing the network, distributing system resources, knowing and adjusting the running state of the system, closing/starting the resources, and the cloud server is simple, efficient, safe and reliable, and has elastically telescopic processing capacity, so that more stable and safe application can be quickly built, and the difficulty of developing operation and maintenance and the overall IT cost are reduced;
the bare metal management service system comprises an edge layer, a platform layer and an application layer, wherein the edge layer comprises data access, system access and edge calculation, the data access is used for realizing the transmission and access of data of the user side, the system access is used for realizing the access of the system, the edge calculation is used for realizing the preliminary calculation processing of the data, the platform layer comprises a development environment, an operation environment, big data and model construction, the development environment, the operation environment and the operation environment are used for realizing the environment construction of the bare metal management service system, the big data is used for realizing the inquiry and input of data information of the system, and the model construction is used for realizing the model construction of the bare metal management service system and finishing the calculation processing of the data; the application layer is used for realizing application construction of the bare metal management service system.
In order to implement deployment of a server for a bare metal management service system and implement installation of the system, in this embodiment, preferably, the bare metal management service system has a basic principle that the deployment server provides DHCP service and FTP service, instructs a plurality of bare metal devices to be started by a PXE network card and to distribute dynamic IP, and downloads related software packages from the deployment server for system installation of a bare metal host.
In order to realize the interface connection of the bare metal management service system, in this embodiment, preferably, the bare metal management service system is connected through the input interface, where the input interface includes a BMC interface and an IPMI configuration to perform unique identification, that is, through an IPMI network, a management node remotely controls the on/off, network start, and disk start of the bare metal management service system, supports batch deployment of all bare metal devices, requires the management node to connect to the IPMI network, remotely controls the bare metal devices through the IPMI, requires the bare metal management service system to be equipped with the BMC interface, configures an IPMI address, a port, a user name, and a password, and connects to the IPMI network.
In order to realize connection between the public network and the private network, in this embodiment, preferably, the bare metal management service system is electrically connected with a subnet, the subnet is provided with an intranet communication, the intranet communication is provided with a private IP and an EIP, the private IP is an IP address, the problem of the internet is solved, and interconnection and intercommunication of large-scale heterogeneous networks are realized; and the coupling relation between the top network application and the bottom network technology is divided, the EIP is an elastic public network IP address, and independent public network IP resources are provided, wherein the elastic public network IP support is dynamically bound and unbound with a bare metal server, a cloud server and a NAT gateway, and the service comprises public network IP addresses and public network outlet bandwidth.
In order to achieve data storage and backup, in this embodiment, preferably, a cloud backup is electrically connected to the cloud server, a cloud hard disk is electrically connected to the cloud backup, the cloud hard disk achieves data storage, the cloud backup provides backup protection services for the cloud hard disk and the bare metal management service system, supports backup services based on snapshot technology, and supports data recovery of the server and the disk by using backup data, and the cloud server is electrically connected to an AI learning system for achieving continuous network learning and updating of the data processing system.
In order to realize the safety protection of the system, in this embodiment, preferably, the bare metal management service system and the subnet are provided with a safety isolation, the safety isolation includes a firewall, and the safety isolation and the firewall are used for realizing the safety protection of the bare metal management service system and the subnet, so as to improve the security of the system.
In order to implement allocation processing for resources in the cloud server, in this embodiment, preferably, the cloud server includes a virtualized resource area and a network area: the virtualized resource area provides resources required by a cloud host and a cloud database through a virtualization technology, and comprises a computing resource pool, a network resource pool and a storage resource pool; the network area is a variety of network interconnection devices required by the system.
In order to implement encryption processing, in this embodiment, it is preferable that the unique identification and the password use RSA algorithm, ECC encryption, MD5, IDEA or SHA1;
and one of the algorithms employed is a hash algorithm: the definition of the hash algorithm is as follows:
a hash function (output length l) consists of two algorithms (Gen, H) on PPT;
gen: a probabilistic algorithm takes a security parameter 1n as input and then outputs a secret key s, assuming that the security parameter 1n is implicit in s;
h: takes as input a key s and a 01 string x e 0,1, and then outputs Hs (x) e 0,1 l(n) Wherein n is a security parameter implicit in s;
i.e. H isDefinition fixed at input as x ε {0,1} l ' (n) And l' (n)>l (n), then the hash function is called a fixed length hash function, and algorithm H is called a compression function;
security of the hash function:
anti-second primary image: given an s and a random x, it is computationally difficult for an adversary on a PPT to find that x' +.x satisfies H s (x')＝H s (x)；
Antigen image: given an s and a random y, it is computationally difficult to find a match H for an adversary on a PPT s (x) X value of =y.
In order to implement the conversion processing on the hash function, in this embodiment, preferably, the hash function domain expansion uses Merkle-Damgard conversion, which is used to expand the compression function into a hash function capable of meeting the requirement, and at the same time, maintain the anti-collision characteristic of the former;
Merkle-Damgard conversion: let (Gen, h) be a hash function of fixed length with an input length of 2n and an output length of n, a hash function is constructed:
gen: unchanged;
h: for an input key s and a 01 string x e {0,1} * The length L of x is less than 2 n Then:
1. let B =ceil (L/n), where B is the number of packets, fill 0 at the end of x to make L a multiple of n, then divide x into packets x of length n of B 1 ，x 2 ，...，x B Then set x B +1: =l, where L is encoded into a 01 string of n bits;
2. let z be 0 :＝0 n (z 0 is also referred to as an initial vector), which is arbitrary and can be replaced with any other constant;
3. for i=1, 2,..b+1, z is calculated i :＝h s (z i -1||x i )；
4. Final output z B+1。
Referring to fig. 2, the method for calculating the bare metal management service system with full stack type high performance includes the following steps:
s1, connection of a bare metal management service system: the user end is connected with the bare metal management service system through the input port, and the connection establishment of the whole system is realized;
s2, the bare metal management service system is in communication connection with the cloud server: the bare metal management service system is in communication connection with the no-server through the network service system, so that the bare metal management service system can be connected with a cloud platform to realize calculation processing of data;
s3, the bare metal management service system is deployed through a DHCP service and an FTP service: starting and distributing dynamic IP through XE network card, connecting BMC interface and IPMI network, and connecting through IPMI address, port, user name and password;
s4, a subnet is arranged on the bare metal management service system: a subnet is arranged on the bare metal management service system, private IP and EIP are established through the subnet, the problem of Internet is solved, and the interconnection and intercommunication of large-scale heterogeneous networks are realized; the coupling relation between the top network application and the bottom network technology is divided, independent public network IP resources are provided, and the elastic public network IP support is dynamically bound and unbound with the bare metal server, the cloud server and the NAT gateway;
s5, the cloud server effectively realizes data processing: the cloud server is provided with a cloud hard disk and a cloud backup, the cloud hard disk realizes data storage, the cloud backup provides backup protection service for the cloud hard disk and the bare metal management service system, and the cloud server is also provided with an AI learning system, so that the calculation processing capacity of the data is continuously learned and upgraded;
s6, safety isolation and a firewall are used for realizing safety protection on the system: the system is safely protected by setting the safety isolation and the firewall, so that data information is prevented from being mistakenly transmitted or the system is invaded and damaged.
The working principle and the using flow of the invention are as follows:
first step, connection of a bare metal management service system: the user end is connected with the bare metal management service system through the input port, and the connection establishment of the whole system is realized;
the second step, the bare metal management service system is connected with the cloud server in a communication way: the bare metal management service system is in communication connection with the no-server through the network service system, so that the bare metal management service system can be connected with a cloud platform to realize calculation processing of data;
thirdly, the bare metal management service system is deployed through a DHCP service and an FTP service: starting and distributing dynamic IP through XE network card, connecting BMC interface and IPMI network, and connecting through IPMI address, port, user name and password;
fourthly, the bare metal management service system is provided with a subnet: a subnet is arranged on the bare metal management service system, private IP and EIP are established through the subnet, the problem of Internet is solved, and the interconnection and intercommunication of large-scale heterogeneous networks are realized; the coupling relation between the top network application and the bottom network technology is divided, independent public network IP resources are provided, and the elastic public network IP support is dynamically bound and unbound with the bare metal server, the cloud server and the NAT gateway;
fifthly, the cloud server effectively realizes data processing: the cloud server is provided with a cloud hard disk and a cloud backup, the cloud hard disk realizes data storage, the cloud backup provides backup protection service for the cloud hard disk and the bare metal management service system, and the cloud server is also provided with an AI learning system, so that the calculation processing capacity of the data is continuously learned and upgraded;
sixth, the security isolation and firewall are used to realize security protection for the system: the system is safely protected by setting the safety isolation and the firewall, so that data information is prevented from being mistakenly transmitted or the system is invaded and damaged.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The full stack type high-performance bare metal computing management service system comprises a user end and is characterized in that: the user side is electrically connected with the bare metal management service system through an input port, the bare metal management service system is in communication connection with the network service system, the network service system is in communication connection with the cloud server, the user side is used for realizing operation control input of a client, and the bare metal management service system comprises a computing service with the performance of an elastic cloud server and a physical machine and is used for providing excellent computing performance and data security for a core database, a key application system, high-performance computing and big data service; the network service system is used for running a network operating system, storing and managing shared resources in the network, serving application programs of all workstations, supervising and controlling network activities, actually managing the network, distributing system resources, knowing and adjusting the running state of the system, closing/starting the resources, and the cloud server is simple, efficient, safe and reliable, and has elastically telescopic processing capacity, so that more stable and safe application can be quickly built, and the difficulty of developing operation and maintenance and the overall IT cost are reduced;
the bare metal management service system comprises an edge layer, a platform layer and an application layer, wherein the edge layer comprises data access, system access and edge calculation, the data access is used for realizing the transmission and access of data of the user side, the system access is used for realizing the access of the system, the edge calculation is used for realizing the preliminary calculation processing of the data, the platform layer comprises a development environment, an operation environment, big data and model construction, the development environment, the operation environment and the operation environment are used for realizing the environment construction of the bare metal management service system, the big data is used for realizing the inquiry and input of data information of the system, and the model construction is used for realizing the model construction of the bare metal management service system and finishing the calculation processing of the data; the application layer is used for realizing application construction of the bare metal management service system.
2. The full stack high performance computing bare metal management service system according to claim 1, wherein: the basic principle of the bare metal management service system is that a deployment server provides DHCP service and FTP service, a plurality of bare metal devices are instructed to be started by a PXE network card and distribute dynamic IP, and the bare metal devices download relevant software packages from the deployment server for system installation of a bare metal host.
3. The full stack high performance computing bare metal management service system according to claim 1, wherein: the bare metal management service system is connected through the input interface, the input interface comprises a BMC interface and IPMI configuration for unique identification, namely, through an IPMI network, a management node remotely controls the startup and shutdown, network startup and disk startup of the bare metal management service system, supports batch deployment of all bare metal devices, requires the management node to be connected to the IPMI network, remotely controls the bare metal devices through the IPMI, requires the bare metal management service system to be provided with the BMC interface, configures IPMI addresses, ports, user names and passwords, and is connected to the IPMI network.
4. The full stack high performance computing bare metal management service system according to claim 1, wherein: the bare metal management service system is electrically connected with a subnet, the subnet is provided with an internal and external network communication, the internal and external network communication is provided with a private IP and an EIP, the private IP is an IP address, the problem of the Internet is solved, and the interconnection and the intercommunication of a large-scale heterogeneous network are realized; and the coupling relation between the top network application and the bottom network technology is divided, the EIP is an elastic public network IP address, and independent public network IP resources are provided, wherein the elastic public network IP support is dynamically bound and unbound with a bare metal server, a cloud server and a NAT gateway, and the service comprises public network IP addresses and public network outlet bandwidth.
5. The full stack high performance computing bare metal management service system according to claim 1, wherein: the cloud server is electrically connected with a cloud backup, the cloud backup is electrically connected with a cloud hard disk, the cloud hard disk realizes data storage, the cloud backup provides backup protection service for the cloud hard disk and the bare metal management service system, supports backup service based on snapshot technology and supports data recovery of the server and a disk by using backup data, the cloud server is electrically connected with an AI learning system, and the AI learning system is used for realizing continuous network learning and updating of a data processing system.
6. The full stack high performance computing bare metal management service system according to claim 4, wherein: the bare metal management service system and the subnet are provided with safety isolation, the safety isolation comprises a firewall, and the safety isolation and the firewall are used for realizing safety protection of the bare metal management service system and the subnet, so that the security of the system is improved.
7. The full stack high performance computing bare metal management service system according to claim 1, wherein: the cloud server comprises a virtualized resource area and a network area: the virtualized resource area provides resources required by a cloud host and a cloud database through a virtualization technology, and comprises a computing resource pool, a network resource pool and a storage resource pool; the network area is a variety of network interconnection devices required by the system.
8. The full stack high performance computing bare metal management service system according to claim 3, wherein: the unique identification and the password adopt RSA algorithm, ECC encryption method, MD5, IDEA or SHA1;
and one of the algorithms employed is a hash algorithm: the definition of the hash algorithm is as follows:
a hash function (output length l) consists of two algorithms (Gen, H) on PPT;
gen: a probabilistic algorithm takes a security parameter 1n as input and then outputs a secret key s, assuming that the security parameter 1n is implicit in s;
h: takes as input a key s and a 01 string x e 0,1, and then outputs Hs (x) e 0,1 l(n) Wherein n is a security parameter implicit in s;
i.e. H is defined as x.epsilon.0, 1 fixed at the input l ' (n) And l' (n)>l (n), then the hash function is called a fixed length hash function, and algorithm H is called a compression function;
security of the hash function:
anti-second primary image: given an s and a random x, it is computationally difficult for an adversary on a PPT to find that x' +.x satisfies H s (x')＝H s (x)；
Antigen image: given an s and a random y, it is computationally difficult to find a match H for an adversary on a PPT s (x) X value of =y.
9. The full stack high performance computing bare metal management service system according to claim 8, wherein: the Hash function definition domain expansion adopts Merkle-Damgard conversion, which is used for expanding a compression function into a Hash function capable of meeting the requirement and simultaneously maintaining the anti-collision characteristic of the former;
Merkle-Damgard conversion: let (Gen, h) be a hash function of fixed length with an input length of 2n and an output length of n, a hash function is constructed:
gen: unchanged;
h: for an input key s and a 01 string x e {0,1} * The length L of x is less than 2 n Then:
1. let B =ceil (L/n), where B is the number of packets, fill 0 at the end of x to make L a multiple of n, then divide x into packets x of length n of B 1 ，x 2 ，...，x B Then set x B +1: =l, where L is encoded into a 01 string of n bits;
2. let z be 0 :＝0 n (z0Also referred to as an initial vector), the initial vector is arbitrary and can be replaced with any other constant;
3. for i=1, 2,..b+1, z is calculated i :＝h s (z i -1||x i )；
4. Final output z B+1。
10. The method for the full stack type high-performance calculation bare metal management service system is characterized by comprising the following steps of: the method comprises the following steps:
s1, connection of a bare metal management service system: the user end is connected with the bare metal management service system through the input port, and the connection establishment of the whole system is realized;
s2, the bare metal management service system is in communication connection with the cloud server: the bare metal management service system is in communication connection with the no-server through the network service system, so that the bare metal management service system can be connected with a cloud platform to realize calculation processing of data;
s3, the bare metal management service system is deployed through a DHCP service and an FTP service: starting and distributing dynamic IP through XE network card, connecting BMC interface and IPMI network, and connecting through IPMI address, port, user name and password;
s4, a subnet is arranged on the bare metal management service system: a subnet is arranged on the bare metal management service system, private IP and EIP are established through the subnet, the problem of Internet is solved, and the interconnection and intercommunication of large-scale heterogeneous networks are realized; the coupling relation between the top network application and the bottom network technology is divided, independent public network IP resources are provided, and the elastic public network IP support is dynamically bound and unbound with the bare metal server, the cloud server and the NAT gateway;
s5, the cloud server effectively realizes data processing: the cloud server is provided with a cloud hard disk and a cloud backup, the cloud hard disk realizes data storage, the cloud backup provides backup protection service for the cloud hard disk and the bare metal management service system, and the cloud server is also provided with an AI learning system, so that the calculation processing capacity of the data is continuously learned and upgraded;
s6, safety isolation and a firewall are used for realizing safety protection on the system: the system is safely protected by setting the safety isolation and the firewall, so that data information is prevented from being mistakenly transmitted or the system is invaded and damaged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211083900.8A CN115442316B (en) | 2022-09-06 | 2022-09-06 | Full stack type high-performance computing bare metal management service system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211083900.8A CN115442316B (en) | 2022-09-06 | 2022-09-06 | Full stack type high-performance computing bare metal management service system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115442316A CN115442316A (en) | 2022-12-06 |
| CN115442316B true CN115442316B (en) | 2024-02-23 |
Family
ID=84247169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211083900.8A Active CN115442316B (en) | 2022-09-06 | 2022-09-06 | Full stack type high-performance computing bare metal management service system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115442316B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016101638A1 (en) * | 2014-12-23 | 2016-06-30 | 国家电网公司 | Operation management method for electric power system cloud simulation platform |
| CN110532065A (en) * | 2019-09-02 | 2019-12-03 | 广州市品高软件股份有限公司 | A kind of dispositions method and device of bare metal server |
| CN111782283A (en) * | 2020-06-28 | 2020-10-16 | 北京思特奇信息技术股份有限公司 | Automatic management method, device and medium for bare metal server |
| CN112256393A (en) * | 2020-10-22 | 2021-01-22 | 上海云轴信息科技有限公司 | Resource management method and equipment for bare metal server |
| CN113918174A (en) * | 2021-10-27 | 2022-01-11 | 华云数据控股集团有限公司 | Bare metal server deployment method, deployment controller and server cluster |
| CN114024799A (en) * | 2022-01-06 | 2022-02-08 | 杭州优云科技有限公司 | Method and device for interconnecting bare metal server and virtualization network |
| CN114610447A (en) * | 2022-03-14 | 2022-06-10 | 浪潮云信息技术股份公司 | Bare metal server implementation method and system based on intelligent network card |
-
2022
- 2022-09-06 CN CN202211083900.8A patent/CN115442316B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016101638A1 (en) * | 2014-12-23 | 2016-06-30 | 国家电网公司 | Operation management method for electric power system cloud simulation platform |
| CN110532065A (en) * | 2019-09-02 | 2019-12-03 | 广州市品高软件股份有限公司 | A kind of dispositions method and device of bare metal server |
| CN111782283A (en) * | 2020-06-28 | 2020-10-16 | 北京思特奇信息技术股份有限公司 | Automatic management method, device and medium for bare metal server |
| CN112256393A (en) * | 2020-10-22 | 2021-01-22 | 上海云轴信息科技有限公司 | Resource management method and equipment for bare metal server |
| CN113918174A (en) * | 2021-10-27 | 2022-01-11 | 华云数据控股集团有限公司 | Bare metal server deployment method, deployment controller and server cluster |
| CN114024799A (en) * | 2022-01-06 | 2022-02-08 | 杭州优云科技有限公司 | Method and device for interconnecting bare metal server and virtualization network |
| CN114610447A (en) * | 2022-03-14 | 2022-06-10 | 浪潮云信息技术股份公司 | Bare metal server implementation method and system based on intelligent network card |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115442316A (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10069630B2 (en) | Synchronizing credential hashes between directory services | |
| JP6498230B2 (en) | Flexible HDD / SSD storage support system and method | |
| US11469964B2 (en) | Extension resource groups of provider network services | |
| JP3948957B2 (en) | Extensible computing system | |
| US7761573B2 (en) | Seamless live migration of virtual machines across optical networks | |
| CN101986651B (en) | Remote storage method, remote storage system and client | |
| CN107819891B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| WO2020024413A1 (en) | Method for controlling deployment of cloud computing platform, server, and storage medium | |
| CN106686051B (en) | Cloud computing network topology system and method based on BIM design | |
| Zhang et al. | A survey of computational offloading in mobile cloud computing | |
| CN106899477A (en) | The construction method and device of physical machine in cloud computing platform | |
| CN105704042A (en) | Message processing method, BNG and BNG cluster system | |
| Azougaghe et al. | Many-to-one matching game towards secure virtual machines migration in cloud computing | |
| JP5220675B2 (en) | Thin client master rewrite system, thin client master rewrite method, and thin client | |
| CN115442316B (en) | Full stack type high-performance computing bare metal management service system and method | |
| CN112887330A (en) | Structure and method for realizing network ACL isolation floating IP | |
| CN109379444B (en) | Method and system for providing private cloud service based on automatic adaptation | |
| CN101170544A (en) | A communication method in high-availability cluster system based on single practical IP address | |
| Hari et al. | The swiss army smartphone: Cloud-based delivery of usb services | |
| JP7212158B2 (en) | Provider network service extension | |
| Gardasu et al. | A fog computing solution for advanced security, storage techniques for platform infrastructure | |
| JP5250573B2 (en) | Thin client master rewrite system and thin client master rewrite method | |
| Li et al. | DVMP: Incremental traffic-aware VM placement on heterogeneous servers in data centers | |
| JP4246472B2 (en) | Data processing method and program | |
| CN117978552A (en) | Business process safety protection system and method for generalized deterministic network |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |