CN113704165B - Super fusion server, data processing method and device - Google Patents
Super fusion server, data processing method and device Download PDFInfo
- Publication number
- CN113704165B CN113704165B CN202110801907.8A CN202110801907A CN113704165B CN 113704165 B CN113704165 B CN 113704165B CN 202110801907 A CN202110801907 A CN 202110801907A CN 113704165 B CN113704165 B CN 113704165B
- Authority
- CN
- China
- Prior art keywords
- circuit board
- circuit boards
- memory
- target
- interface
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
- G06F15/161—Computing infrastructure, e.g. computer clusters, blade chassis or hardware partitioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
- G06F15/163—Interprocessor communication
- G06F15/17—Interprocessor communication using an input/output type connection, e.g. channel, I/O port
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application discloses a super fusion server, a data processing method and a device, wherein the super fusion server comprises the following components: the first circuit boards are provided with a processor and a first memory, are respectively used for responding to input instructions representing service demands of different users and storing target data related to different users; and the second circuit board is provided with an I/O interface and is connected with the plurality of first circuit boards, and the second circuit board is used for transmitting the target data on the plurality of first circuit boards through the I/O interface. The super fusion server is provided with the first circuit board provided with the processor and the first memory, and the second circuit board is provided with the I/O interfaces and is connected with a plurality of the first circuit boards, so that data interaction is carried out between the first circuit board and the second circuit board through the I/O interfaces, the resource loss of the super fusion server is reduced, and the I/O performance of the super fusion server is improved.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a super fusion server, a data processing method and a data processing device.
Background
The super fusion server is a server architecture combining hardware and software, and the unified management of storage resources in a plurality of physical servers is realized by forming a logic storage pool by hard disks in the plurality of physical servers in a software definition method. When a virtual machine is operated on a physical server, 2 or 3 different copies can be generated by a virtual hard disk of the virtual machine, and when one physical server is down, the virtual machine can find out the virtual disk copies from other physical servers, so that the data of the virtual machine is not lost, and the uninterrupted operation of user services is ensured.
In the deployment architecture of the super fusion server in the prior art, most of local disks on a physical server are connected together through an ethernet switch, all the local disks form a logical storage pool in a software-defined manner, and the logical storage pool provides storage services for a virtual machine running on the physical server in the form of an iSCSI protocol (internet Small Computer System Interface) or other storage protocols. Under the architecture, on one hand, all local disks are connected through an external network, so that an I/O performance bottleneck exists, and on the other hand, the virtual machine has unavoidable CPU and memory loss relative to the physical machine.
Therefore, how to deploy a super-converged server architecture with low resource consumption and high I/O performance is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
Accordingly, the present application is directed to a super fusion server, a data processing method and a device, and a storage medium corresponding to the data processing method is provided, so that the resource consumption of the super fusion server can be reduced and the I/O performance of the super fusion server can be improved. The specific scheme is as follows:
a first aspect of the present application provides a super fusion server comprising:
the first circuit boards are provided with a processor and a first memory, are respectively used for responding to input instructions representing service demands of different users and storing target data related to different users;
and the second circuit board is provided with an I/O interface and is connected with the plurality of first circuit boards, and the second circuit board is used for transmitting the target data on the plurality of first circuit boards through the I/O interface.
Optionally, the processor on the first circuit board includes a plurality of central processors and/or network processors.
Optionally, the first memory on the first circuit board includes a plurality of nonvolatile memories and nonvolatile memories.
Optionally, the nonvolatile memory includes a first storage unit and a second storage unit;
the first storage unit is used for storing data on the first circuit board of the first storage unit, and the second storage unit is used for backing up data on other first circuit boards.
Optionally, the super fusion server further comprises a second memory, wherein:
the second memory is connected with the second circuit board through the I/O interface and is used for storing the hardware configuration information and/or the processor state information and/or the target data on the plurality of first circuit boards.
Optionally, the second memory is one or more solid state disks.
Optionally, the I/O interface connected between the first circuit board and the second circuit board and between the second circuit board and the second memory is a PCIE interface.
A second aspect of the present application provides a data processing method, applied to the aforementioned super fusion server, including:
acquiring input instructions representing service demands of different users, and determining different first target circuit boards from first circuit boards in idle states;
responding to the input instructions of different users by using processors and first memories on different first target circuit boards respectively, and storing target data related to the users;
and transmitting the target data on the first target circuit board to other first circuit boards for storage through an I/O interface on the second circuit board.
Optionally, the data processing method further includes:
transmitting the hardware configuration information and/or the processor state information and/or the target data on the first target circuit board to a second memory through the second circuit board for storage; the second memory is connected with the second circuit board through the I/O interface.
A third aspect of the present application provides a data processing apparatus applied to the aforementioned super fusion server, comprising:
the determining module is used for acquiring input instructions representing service demands of different users and determining different first target circuit boards from first circuit boards in idle states;
the response module is used for responding to the input instructions of different users by utilizing the processors and the first memories on different first target circuit boards respectively and storing target data related to the users;
and the transmission module is used for transmitting the target data on the first target circuit board to other first circuit boards for storage through the I/O interface on the second circuit board.
A fourth aspect of the present application provides a computer readable storage medium having stored therein computer executable instructions which, when loaded and executed by a processor, implement the foregoing data processing method.
The application discloses a super fusion server, which comprises a plurality of first circuit boards provided with a processor and a first memory, wherein the first circuit boards are respectively used for responding to input instructions representing business demands of different users and storing target data related to different users; and the second circuit board is provided with an I/O interface and is connected with the plurality of first circuit boards, and the second circuit board is used for transmitting the target data on the plurality of first circuit boards through the I/O interface. Therefore, the super fusion server integrates the first circuit board provided with the processor and the first memory and the second circuit board provided with the I/O interfaces and connected with the plurality of first circuit boards, so that data interaction is carried out between the first circuit board and the second circuit board through the I/O interfaces, the resource loss of the super fusion server is reduced, and the I/O performance of the super fusion server is improved.
In the application, the data processing method applied to the super fusion server firstly obtains input instructions representing the business demands of different users, and determines different first target circuit boards from first circuit boards in idle states; then respectively responding to the input instructions of different users by utilizing different processors and first memories on the first target circuit boards, and storing target data related to the users; and simultaneously transmitting the target data on the first target circuit board to other first circuit boards for storage through the I/O interface on the second circuit board. Therefore, the application obtains the input instructions representing the business demands of different users, determines different first target circuit boards from the first circuit boards in the idle state, responds to the corresponding input instructions by utilizing the first target circuit boards, stores target data related to the users, transmits the target data to other first circuit boards for storage through the I/O interface on the second circuit board, and improves the data processing efficiency on the basis of low resource consumption and high I/O performance.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a diagram of a super fusion server architecture provided by the present application;
FIG. 2 is a diagram of a prior art super-converged server architecture provided by the present application;
FIG. 3 is a schematic diagram of a first circuit board according to the present application;
FIG. 4 is a schematic diagram of a super-converged server architecture in accordance with the present application;
FIG. 5 is a flow chart of a data processing method according to the present application;
fig. 6 is a schematic structural diagram of a data processing apparatus according to the present application.
Detailed Description
The following description of the embodiments of the present application 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 application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the deployment architecture of the super fusion server in the prior art, most of local disks on a physical server are connected together through an ethernet switch, all the local disks form a logical storage pool in a software-defined manner, and the logical storage pool provides storage services for a virtual machine running on the physical server in the form of an iSCSI protocol (internet Small Computer System Interface) or other storage protocols. Under the architecture, on one hand, all local disks are connected through an external network, so that an I/O performance bottleneck exists, and on the other hand, the virtual machine has unavoidable CPU and memory loss relative to the physical machine. In view of the technical defects, the application provides a super-fusion server, which integrates a first circuit board provided with a processor and a first memory and a second circuit board provided with an I/O interface and connected with a plurality of the first circuit boards, so that data interaction is carried out between the first circuit board and the second circuit board through the I/O interface, the resource loss of the super-fusion server is reduced, and the I/O performance of the super-fusion server is improved.
Fig. 1 is a schematic diagram of a super-fusion server according to an embodiment of the present application. Referring to fig. 1, the super fusion server includes:
a plurality of first circuit boards 01 provided with a processor 011 and a first memory 012, and used for responding to input instructions representing service demands of different users and storing target data related to different users;
and a second circuit board 02 which is provided with an I/O interface and is connected with the plurality of first circuit boards, and is used for transmitting the target data on the plurality of first circuit boards through the I/O interface.
In this embodiment, the super fusion server integrates a plurality of first circuit boards 01 with processors 011 and first memories 012, and a second circuit board 02 with I/O interfaces and connected to the plurality of first circuit boards, and the first circuit boards 01 and the second circuit boards 02 perform data interaction through the I/O interfaces without using an external network. FIG. 2 is a diagram of a conventional super-converged service architecture, in which local disks on 3 physical servers in FIG. 2 are connected together through an Ethernet switch, and all the local disks form a logical storage pool in a software-defined manner; the logical storage pool provides storage services in the form of iSCSI protocol or other storage protocols to virtual machines running on physical servers. In contrast, the super-fusion server in fig. 1 replaces the virtual machine in the original super-fusion architecture, and the conventional super-fusion architecture is based on a physical server cluster, in this embodiment, all the first circuit boards 01 are placed on the same physical server, and the first circuit boards 01 are allocated to users as the minimum units for use, so that the resource consumption of the super-fusion server is reduced and the I/O performance of the super-fusion server is improved.
In this embodiment, the design of the first circuit board 01 is shown in fig. 3, and the first circuit board may also be called a computing pad. In one aspect, the processor 011 on the first circuit board 01 includes a plurality of Central Processing Units (CPUs) and/or network processors, and the number of the Central Processing Units (CPUs) and the number of the Network Processors (NPUs) can be set according to specific traffic. Of course, other types of processors may be installed in addition to the CPU and NPU, which is not limited in this embodiment. On the other hand, the first memory 011 on the first circuit board 01 includes a plurality of nonvolatile memories and nonvolatile memories. The data of the conventional super fusion architecture is stored on a solid state Disk (SSD, solid State Drives) and/or a Hard Disk Drive (HDD), and the data of this embodiment is mainly stored on a nonvolatile memory. Specifically, a gold finger is located under the computing board and can be inserted into the second circuit board 02 (also referred to as an I/O board). And a plurality of CPUs are arranged in the computing board, and if the user has an artificial intelligence computing requirement, NPU or other artificial intelligence computing chips can be optionally arranged. Volatile memory and nonvolatile memory can be inserted into the computing board, wherein the volatile memory is used as data to a cache region of the CPU and/or the NPU; the nonvolatile memory is used as data storage. In the memory product design of many manufacturers, such as Intel option product, a system administrator can configure whether the memory is volatile or nonvolatile through a software form, that is, all memory banks inserted into the computing board belong to the same model, but the available capacities of two memory modes can be adjusted according to different application scenarios. It can be understood that the computing board is the smallest computing unit that can be allocated to the user, and the CPU and memory resources in the computing board are all used to run the user's service except for a small portion of the service of the software defined storage system.
In this embodiment, the nonvolatile memory includes a first storage unit and a second storage unit; the first storage unit is used for storing data on the first circuit board of the first storage unit, and the second storage unit is used for backing up data on other first circuit boards. The non-volatile memory is divided into a plurality of storage areas and is stored as storage copies in different computing boards, so that the reliability of data is improved. Because data can be transmitted between nonvolatile memories on different computing boards at high speed, the embodiment forms a storage resource pool with extremely high performance and logic uniformity by a software definition method through the nonvolatile memories on all the computing boards. The total capacity of the storage resource pool is larger than the storage capacity which can be provided by the single computing board, when the storage space of the single computing board is insufficient, the storage resource pool can read and write the storage space on other computing boards through the I/O interface, and obvious I/O performance fluctuation can not be generated. In addition, by setting the copy number of the storage resource pool, the data on the computing boards can be synchronously read and written into the nonvolatile memory of another one or more computing boards, so that when one computing board is damaged, the key data of the computing boards can be obtained in the copy on the other computing boards.
Further, the super fusion server in this embodiment further includes a second memory 03, where the second memory 03 is connected to the second circuit board 02 through the I/O interface, and is configured to store hardware configuration information and/or the processor state information and/or the target data on the plurality of first circuit boards 01. The second memory 03 may be one or more Solid State Disks (SSD), as shown in fig. 4. One or more blocks are used as high-capacity persistent storage of the super fusion server and are also connected with the I/O board through an I/O interface. In this embodiment, the user uses the computing board as a virtual machine, and when the user issues a similar "close virtual machine" command, the CPU state in the computing board, and persistent data related to the user, are transferred to the SSD for storage, and then the computing board is placed in an "idle" state. Other users may apply for the idle computing pad to be used as a virtual machine.
On the basis, on the one hand, a user can snapshot the computing board, and when the user initiates a snapshot request, the hardware configuration information of the computing board, the CPU state in the computing board, the memory data related to the user (stored in the volatile memory) and the hard disk data related to the user (stored in the nonvolatile memory) are packaged into one file and stored in an SSD hard disk connected with the I/O board. On the other hand, the user can make a template based on the computing board, and when the user initiates a template making request, the hardware configuration information of the computing board and the hard disk data (stored in the nonvolatile memory) related to the user are packaged into a file and stored in the SSD hard disk connected with the I/O board.
In this embodiment, the I/O interface between the first circuit board 01 and the second circuit board 02, and between the second circuit board 02 and the second memory 03 is a PCIE interface. The traditional super-fusion architecture performs data transmission through an external network (such as an ethernet switch and a TCP/IP protocol), and in this embodiment, high-speed transmission is performed based on a PCIE (PCI-Express, peripheral Component Interconnect Express) protocol, that is, all the computing boards are inserted into the I/O boards, and high-speed interconnection between the computing boards is realized through a high-speed channel based on the PCIE protocol. The PCIE protocol is a high-speed serial computer expansion bus standard. In addition, the SSD hard disks are also accessed to the I/O board based on PCIE protocol. Of course, the PCIE interface may also be replaced by a Serial SATA interface, where the SATA interface (Serial ATA, serial Advanced Technology Attachment) is a computer bus, and is responsible for data transmission between a motherboard and a mass storage device (such as a hard disk and an optical disk drive), and is mainly used in a personal computer. The present embodiment is not limited as long as the interface can achieve the technical effects of the embodiment of the present application.
In summary, the embodiment of the application designs a super-fusion server architecture with higher performance through the high-speed interconnected computing card topology, and the super-fusion server architecture comprises a plurality of computing boards, an I/O board, a plurality of SSD hard disks, and a software design thereof. The computing board is provided with a plurality of processor chips (CPU, NPU and the like) and a plurality of memory strips, the memory strips can be configured into volatile memory or nonvolatile memory in a hardware configuration or software setting mode according to actual application scenes, the nonvolatile memory is constructed into a unified logic memory pool through a software definition technology, and the copy number can be set for data in the logic memory pool. The data of the CPU state, the memory state and the like in the computing board can be saved into an SSD disk connected with the I/O board. In addition, the snapshot and modules of the computing pad may also be saved to the SSD disk to which the I/O pad is connected.
It can be seen that the super fusion server in the embodiment of the present application includes a plurality of first circuit boards provided with a processor and a first memory, which are respectively configured to respond to input instructions representing service demands of different users, and store target data related to different users; and the second circuit board is provided with an I/O interface and is connected with the plurality of first circuit boards, and the second circuit board is used for transmitting the target data on the plurality of first circuit boards through the I/O interface. Therefore, the super fusion server integrates the first circuit board provided with the processor and the first memory and the second circuit board provided with the I/O interfaces and connected with the plurality of first circuit boards, so that data interaction is carried out between the first circuit board and the second circuit board through the I/O interfaces, the resource loss of the super fusion server is reduced, and the I/O performance of the super fusion server is improved.
Fig. 5 is a flowchart of a data processing method according to an embodiment of the present application. Referring to fig. 5, the data processing method is applied to the aforementioned super fusion server, and includes:
s11: and acquiring input instructions representing service requirements of different users, and determining different first target circuit boards from the first circuit boards in the idle state.
In this embodiment, input instructions representing service demands of different users are first obtained, and different first target circuit boards are determined from first circuit boards in idle states. The input instruction characterizes the business requirement of the user, namely the task that the user wants the super fusion server to execute. The super fusion server is provided with a plurality of first circuit boards, different first circuit boards are different in state at the same time, and can execute new tasks when the first circuit boards are in an idle state, so that after the input instructions representing the business demands of different users are acquired, the first circuit boards in the idle state need to be further determined, and the first circuit boards responding to the input instructions, namely the first target circuit boards, are determined.
S12: and responding to the input instructions of different users by utilizing the processor and the first memory on different first target circuit boards respectively, and storing target data related to the users.
S13: and transmitting the target data on the first target circuit board to other first circuit boards for storage through an I/O interface on the second circuit board.
In this embodiment, after the first target circuit board corresponding to the input instruction is determined, the processor and the first memory on the different first target circuit boards are used to respond to the input instruction of the different users, and target data related to the users is stored. And simultaneously, transmitting the target data on the first target circuit board to other first circuit boards for storage through the I/O interface on the second circuit board. In this embodiment, when a user issues a command similar to "close a virtual machine", the CPU state in the first circuit board and persistent data related to the user are transferred to the SSD for storage, and then the first circuit board may be set to an "idle" state, so as to release computing resources, so that other users may apply for the idle first circuit board as a virtual machine.
Furthermore, in this embodiment, the hardware configuration information and/or the processor state information and/or the target data on the first target circuit board may be transferred to a second memory through the second circuit board for storage; the second memory is connected with the second circuit board through the I/O interface. Compared with the traditional super fusion architecture, the super fusion server is newly added with an SSD hard disk for storing the data of the virtual machine/the computing card after power-off, the SSD hard disk can store the snapshot and the template of the computing board, and the SSD hard disk is used for storing the data in a lasting mode.
In addition, the data transmission in the above steps may be implemented through PCIE interfaces, that is, I/O interfaces connected between the first circuit board 01 and the second circuit board 02 and between the second circuit board 02 and the second memory 03 are PCIE interfaces. And data transmission is not required to be performed through an external network (such as an Ethernet switch and a TCP/IP protocol), high-speed transmission is performed based on the PCIE protocol, and the data transmission efficiency and performance are improved.
Steps S11, S12 and S13 in this embodiment are all implemented based on the above-mentioned super fusion server architecture, on the one hand, the SSD medium is replaced by the memory medium, the TCP/IP protocol is replaced by the PCIE protocol, and the I/O performance is improved. On the other hand, the CPU and memory resources in the computing board are almost distributed to one user for use except the necessary software definition storage system service, so that the resource loss of the virtual machine and the resource preemption problem among different virtual machines do not exist, and the computing performance is improved. The data processing method in the embodiment of the application obviously improves the data processing performance in a mode of combining hardware and software of the super fusion server.
It can be seen that, in the data processing method applied to the super fusion server in the embodiment of the present application, input instructions representing service requirements of different users are obtained first, and different first target circuit boards are determined from first circuit boards in an idle state; then respectively responding to the input instructions of different users by utilizing different processors and first memories on the first target circuit boards, and storing target data related to the users; and simultaneously transmitting the target data on the first target circuit board to other first circuit boards for storage through the I/O interface on the second circuit board. Therefore, the application obtains the input instructions representing the business demands of different users, determines different first target circuit boards from the first circuit boards in the idle state, responds to the corresponding input instructions by utilizing the first target circuit boards, stores target data related to the users, transmits the target data to other first circuit boards for storage through the I/O interface on the second circuit board, and improves the data processing efficiency on the basis of low resource consumption and high I/O performance.
Referring to fig. 6, the embodiment of the application also correspondingly discloses a data processing device, which is applied to the super fusion server and comprises:
the determining module 11 is configured to obtain input instructions representing service requirements of different users, and determine different first target circuit boards from the first circuit boards in an idle state;
a response module 12, configured to respond to the input instructions of different users by using a processor and a first memory on different first target circuit boards, and store target data related to the users;
and the transmission module 13 is used for transmitting the target data on the first target circuit board to other first circuit boards for storage through an I/O interface on the second circuit board.
Therefore, the embodiment of the application firstly obtains the input instruction representing the business requirements of different users, and determines different first target circuit boards from the first circuit boards in the idle state; then respectively responding to the input instructions of different users by utilizing different processors and first memories on the first target circuit boards, and storing target data related to the users; and simultaneously transmitting the target data on the first target circuit board to other first circuit boards for storage through the I/O interface on the second circuit board. Therefore, the application obtains the input instructions representing the business demands of different users, determines different first target circuit boards from the first circuit boards in the idle state, responds to the corresponding input instructions by utilizing the first target circuit boards, stores target data related to the users, transmits the target data to other first circuit boards for storage through the I/O interface on the second circuit board, and improves the data processing efficiency on the basis of low resource consumption and high I/O performance.
In some embodiments, the data processing apparatus further comprises:
the storage module is used for transmitting the hardware configuration information and/or the processor state information and/or the target data on the first target circuit board to a second memory through the second circuit board for storage; the second memory is connected with the second circuit board through the I/O interface.
Further, the embodiment of the application also discloses a storage medium, wherein the storage medium stores a computer program, and the computer program realizes the steps of the data processing method disclosed in any one of the previous embodiments when being loaded and executed by a processor.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above describes the super fusion server, the data processing method, the device and the storage medium provided by the application in detail, and specific examples are applied to the description of the principle and the implementation of the application, and the description of the above examples is only used for helping to understand the method and the core idea of the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (7)
1. A super fusion server, comprising:
the first circuit boards are provided with a processor and a first memory, are respectively used for responding to input instructions representing service demands of different users and storing target data related to different users;
a second circuit board which is provided with an I/O interface and is connected with a plurality of the first circuit boards, and is used for transmitting the target data on a plurality of the first circuit boards through the I/O interface;
a second memory, wherein: the second memory is connected with the second circuit board through the I/O interface and is used for storing hardware configuration information and/or processor state information and/or the target data on the plurality of first circuit boards; the second memory is one or more solid state disks; the I/O interfaces connected between the first circuit board and the second circuit board and between the second circuit board and the second memory are PCIE interfaces.
2. The super fusion server of claim 1, wherein the processor on the first circuit board comprises a plurality of central processors and/or network processors.
3. The superfusion server of claim 1, wherein the first memory on the first circuit board comprises a plurality of non-volatile memories and non-volatile memories.
4. The super fusion server of claim 3, wherein said non-volatile memory comprises a first storage unit and a second storage unit;
the first storage unit is used for storing data on the first circuit board of the first storage unit, and the second storage unit is used for backing up data on other first circuit boards.
5. A data processing method, characterized by being applied to the super fusion server according to any one of claims 1 to 4, comprising:
acquiring input instructions representing service demands of different users, and determining different first target circuit boards from first circuit boards in idle states;
responding to the input instructions of different users by using processors and first memories on different first target circuit boards respectively, and storing target data related to the users;
and transmitting the target data on the first target circuit board to other first circuit boards for storage through an I/O interface on the second circuit board.
6. The data processing method according to claim 5, further comprising:
transmitting the hardware configuration information and/or the processor state information and/or the target data on the first target circuit board to a second memory through the second circuit board for storage; the second memory is connected with the second circuit board through the I/O interface.
7. A data processing apparatus, applied to the super fusion server of any one of claims 1 to 4, comprising:
the determining module is used for acquiring input instructions representing service demands of different users and determining different first target circuit boards from first circuit boards in idle states;
the response module is used for responding to the input instructions of different users by utilizing the processors and the first memories on different first target circuit boards respectively and storing target data related to the users;
and the transmission module is used for transmitting the target data on the first target circuit board to other first circuit boards for storage through the I/O interface on the second circuit board.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110801907.8A CN113704165B (en) | 2021-07-15 | 2021-07-15 | Super fusion server, data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110801907.8A CN113704165B (en) | 2021-07-15 | 2021-07-15 | Super fusion server, data processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113704165A CN113704165A (en) | 2021-11-26 |
| CN113704165B true CN113704165B (en) | 2023-09-12 |
Family
ID=78648919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110801907.8A Active CN113704165B (en) | 2021-07-15 | 2021-07-15 | Super fusion server, data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113704165B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018157836A1 (en) * | 2017-03-02 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Resource management method for programmable hardware, programmable hardware device, and storage medium |
| CN111427833A (en) * | 2020-05-26 | 2020-07-17 | 林沧 | Server cluster |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11714763B2 (en) * | 2019-10-16 | 2023-08-01 | Intel Corporation | Configuration interface to offload capabilities to a network interface |
-
2021
- 2021-07-15 CN CN202110801907.8A patent/CN113704165B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018157836A1 (en) * | 2017-03-02 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Resource management method for programmable hardware, programmable hardware device, and storage medium |
| CN108536526A (en) * | 2017-03-02 | 2018-09-14 | 腾讯科技（深圳）有限公司 | A kind of method for managing resource and device based on programmable hardware |
| CN111427833A (en) * | 2020-05-26 | 2020-07-17 | 林沧 | Server cluster |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113704165A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111488241B (en) | Method and system for realizing agent-free backup and recovery operation in container arrangement platform | |
| US9317320B2 (en) | Hypervisor-based server duplication system and method and storage medium storing server duplication computer program | |
| US9413683B2 (en) | Managing resources in a distributed system using dynamic clusters | |
| US9811276B1 (en) | Archiving memory in memory centric architecture | |
| JP5680961B2 (en) | Integrated provision of physical and virtual images | |
| US9547605B2 (en) | Method for data backup, device and system | |
| CN111722786A (en) | Storage system based on NVMe equipment | |
| CN106777394B (en) | Cluster file system | |
| CN110457261B (en) | Data access method, device and server | |
| CN110704161B (en) | Virtual machine creation method and device and computer equipment | |
| CA3129984A1 (en) | Method and system for accessing distributed block storage system in user mode | |
| US9755986B1 (en) | Techniques for tightly-integrating an enterprise storage array into a distributed virtualized computing environment | |
| US20140082275A1 (en) | Server, host and method for reading base image through storage area network | |
| JP2012123556A (en) | Virtual server system and control method thereof | |
| CN112486858A (en) | Data prefetching method and device | |
| EP3959611A1 (en) | Intra-device notational data movement system | |
| US8621260B1 (en) | Site-level sub-cluster dependencies | |
| CN112596669A (en) | Data processing method and device based on distributed storage | |
| CN112202855A (en) | Communication device for storing bare metal server and elastic block, intelligent network card and system | |
| CN113377278A (en) | Solid state disk, garbage recycling and controlling method, equipment, system and storage medium | |
| CN113704165B (en) | Super fusion server, data processing method and device | |
| CN115687193A (en) | Memory module, system including the same, and method of operating memory module | |
| CN108139980B (en) | Method for merging memory pages and memory merging function | |
| CN109947704B (en) | Lock type switching method and device and cluster file system | |
| Meyer et al. | Impact of single parameter changes on Ceph cloud storage performance |
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 |