CN114338808A - Data management method and device and server - Google Patents
Data management method and device and server Download PDFInfo
- Publication number
- CN114338808A CN114338808A CN202111552790.0A CN202111552790A CN114338808A CN 114338808 A CN114338808 A CN 114338808A CN 202111552790 A CN202111552790 A CN 202111552790A CN 114338808 A CN114338808 A CN 114338808A
- Authority
- CN
- China
- Prior art keywords
- access
- server
- network card
- intelligent network
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000013523 data management Methods 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 43
- 238000007726 management method Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 19
- 238000003860 storage Methods 0.000 claims description 12
- 239000000758 substrate Substances 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 230000005611 electricity Effects 0.000 description 6
- 239000007787 solid Substances 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000002035 prolonged effect Effects 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 101100045541 Homo sapiens TBCD gene Proteins 0.000 description 1
- 101150093640 SSD1 gene Proteins 0.000 description 1
- 101100111629 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) KAR2 gene Proteins 0.000 description 1
- 102100030290 Tubulin-specific chaperone D Human genes 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Landscapes
- Power Sources (AREA)
Abstract
The invention discloses a data management method, which is applied to a server, wherein an intelligent network card is arranged in the server, and the method comprises the following steps: acquiring an access request; judging whether the access request belongs to high-frequency access or not; and when the access request belongs to high-frequency access, processing the high-frequency access by adopting the intelligent network card. The invention separates the data by unloading some high-frequency accessed data to the intelligent network card, improves the expandability of the server, can increase the density of the server when a data center is deployed, meets the requirement of fast reading of the data, reduces the interrupt processing of the CPU to the data access, reduces the idle running of the CPU, improves the resource utilization rate of the CPU, can also effectively improve the response time of the data access, avoids the queue waiting for the interrupt processing of the CPU, and improves the user experience.
Description
Technical Field
The invention relates to the technical field of data management, in particular to a data management method, a data management device and a server.
Background
With the development of cloud computing and big data application, the design of a network architecture and a server is more and more complex, and the bandwidth requirement and the expandability of the server are higher and higher. Meanwhile, more and more enterprises start to be "on the cloud", and the requirements on data access delay and data security of the data center become problems to be solved urgently. In the current schematic diagram of data center virtualization, as shown in fig. 1 below, one server is connected once through virtualization and resource pool clouding technologies, so as to form storage in a resource pool and sharing of a computer network, and meet requirements of resource sharing and flexible scheduling. When an upper layer user needs a corresponding resource (such as 128 cores, 16G memory, 100M bandwidth, etc.), the corresponding resource is allocated to the user in a resource scheduling manner. Since after virtualization the user access process and the communication between different users becomes a difficult problem. Meanwhile, a large amount of valuable CPU resources are occupied in the virtualization process, the CPU idles due to rapid and continuous interruption, the utilization rate of the CPU is influenced, and the operation cost and the energy consumption are increased. The utilization of CPU resources and the quick response of accesses have become a current challenge.
In order to solve the above-mentioned related challenges caused by virtualization, a design scheme of an intelligent network card is currently promoted, so as to help a central processing unit CPU to solve related network tasks. As shown in fig. 2, the unloading architecture of the present invention has the following main schemes:
1. based on the implementation of an application specific integrated circuit ASIC. The corresponding chip is specially customized, certain specific functions are solidified, and the functions are fixed in the whole life cycle so as to meet the corresponding acceleration requirement. The advantages are mainly that once the method is successfully suitable for mass production, the power consumption is low; because the function solidification is realized through hardware, the performance is higher, and the method is suitable for relatively mature business. The disadvantage is that the function is fixed, so that the programmability and expansibility are poor, and the threshold and investment are large, so that the method is not suitable for exploring the initial service.
2. Based on the implementation of the system-on-chip SOC. A system on a chip SOC typically integrates components of a computer or other system, typically including a central processing unit CPU, memory, input/output I/O interfaces, and other related components. The intelligent network card realized through the method has a relatively low threshold, is suitable for popularization, can be finely adjusted along with the change of business in the later period, and has high expansibility. A disadvantage is that it generally presents a greater challenge to heat dissipation and power consumption control than other approaches. Moreover, since the method is mainly used for processing specific tasks, performance waste is caused, and cost performance is relatively low.
3. The FPGA-based FPGA implementation method is based on the FPGA. Based on the programmable characteristic of the FPGA, some specific acceleration unloading functions are realized by writing a program in software. By the method, different advantages and disadvantages of the SOC and the FPGA are relatively balanced, and expansibility, access threshold and investment are considered. But the proposal has higher requirements on FPGA engineers of the field programmable gate array and has small difficulty.
For the different schemes, the processing of some novel network functions such as network virtualization and Software Defined Networking (SDN) is mainly preferred, the calculation complexity is high, the service processing in the aspect of storage is not involved, the service processing of a Central Processing Unit (CPU) can be influenced by the quick reading of some same virtualized data, and the CPU performance of the central processing unit is reduced.
Disclosure of Invention
Therefore, the invention provides a data management method, a device and a server, aiming at solving the problems that the current quick reading of some same data can influence the service processing of a Central Processing Unit (CPU) and reduce the performance of the CPU.
In order to achieve the purpose, the invention adopts the following technical scheme:
the embodiment of the invention provides a data management method, which is applied to a server, wherein an intelligent network card is arranged in the server, and the method comprises the following steps: acquiring an access request; judging whether the access request belongs to high-frequency access or not; and when the access request belongs to high-frequency access, processing the high-frequency access by adopting the intelligent network card.
The method comprises the steps that an access request of a user is obtained through an intelligent network card of a server, the access request of the user is further judged, and whether the access request belongs to high-frequency access or not is judged; and when the access request belongs to high-frequency access, processing the high-frequency access by adopting an intelligent network card. The expandability of the server is improved, and the density of the server can be increased when the data center is deployed. The interrupt processing of the CPU to the data access is reduced, the idle running of the CPU is reduced, and the resource utilization rate of the CPU is improved. And high-frequency data are unloaded to the intelligent network card for management, so that the response time of data access can be effectively prolonged, the interruption processing of a CPU (central processing unit) is avoided waiting in a queue, and the user experience is improved.
Optionally, the determining whether the access request belongs to a high frequency access includes: obtaining an access rule of the access request; determining the type of the access request according to the access rule of the access request; and determining whether the access request belongs to high-frequency access or not according to a preset relation between the request type and the access type based on the type of the access request, wherein the access type comprises high-frequency access and low-frequency access.
The invention determines whether the access request belongs to high-frequency access according to the relation between the preset request type and the access type, thereby realizing more accurate classification of the access request.
Optionally, the determining whether the access request belongs to high-frequency access further includes: and establishing a relation between the request type and the access type according to a plurality of access requests acquired in the server power-on process.
Optionally, the establishing a relationship between the request type and the access type according to the multiple access requests acquired in the server power-on process includes: determining a type of each access request in the plurality of access requests respectively; classifying the multiple access requests according to the types, and counting the number of each type of access requests; sorting the types of the access requests in the multiple access requests according to the quantity of each type of access requests; and establishing the relation between the request type and the access type according to the sequence.
The invention completes the classification of the message by establishing the relation between the request type and the access type of the message, stores the high-frequency data and unloads the function of storing and reading part of the data from the CPU to the intelligent network card end.
Optionally, the power-on process of the server includes: when the auxiliary voltage output interface AUX power on the server mainboard is used for supplying power, a substrate management controller BMC and a complex programmable logic device CPLD on the mainboard are powered on; after the first complex programmable logic device CPLD is electrified, the intelligent network card is electrified; after the intelligent network card is electrified, sending a message of the electrification completion of the intelligent network card to the BMC; and starting the server after the mainboard receives the message of finishing the power-on.
The intelligent network card is electrified firstly, and the server is allowed to formally start to be electrified after the intelligent network card is electrified, so that the situation that the server works but the intelligent network card does not work and the cooperation is not smooth is avoided.
Optionally, before the processing the high-frequency access by using the intelligent network card, the method further includes: determining access data corresponding to the access request; when the intelligent network card has an access rule corresponding to the access data, processing the access data; and when the access rule corresponding to the access data does not exist in the intelligent network card, sending the access data to a server, and receiving the access rule corresponding to the access data.
According to the invention, some high-frequency accessed data are unloaded to the intelligent network card, and the data are partitioned, so that the data can be rapidly read, and the high-frequency data are unloaded to the intelligent network card for management, so that the response time of data access can be effectively prolonged, the CPU interrupt processing can be avoided waiting in a queue, and the user experience can be improved.
According to a second aspect, the present invention further discloses a data management device, which is applied to a server, wherein an intelligent network card is arranged in the server, and the data management device comprises: the acquisition module is used for acquiring the access request; the judging module is used for judging whether the access request belongs to high-frequency access; and the processing module is used for processing the high-frequency access by adopting the intelligent network card when the access request belongs to the high-frequency access.
According to a third aspect, an embodiment of the present invention further discloses a server, including: the intelligent network card comprises at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the steps of the data management method of the first aspect or any of the optional embodiments of the first aspect.
Optionally, the server further includes a main board, and the main board is disposed on a box of the server; the backboard is arranged on the mainboard and is in communication connection with the intelligent network card.
According to a fourth aspect, the embodiments of the present invention further disclose a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the data management method according to the first aspect or any of the optional embodiments of the first aspect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a diagram illustrating data center virtualization in accordance with the present invention;
FIG. 2 is a diagram illustrating a network offload manner in the prior art according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a data management method according to an embodiment of the invention;
fig. 4 is a schematic diagram of power-on control of an intelligent network card and a server system of the data management method in the embodiment of the present invention;
FIG. 5 is a schematic diagram of a data management access process of the data management method according to the embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a data management apparatus according to an embodiment of the present invention;
figure 7 is a schematic structural diagram of a server in an embodiment of the present invention,
fig. 8 is a schematic diagram of a data unloading and reading module based on an intelligent network card according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; the two elements may be directly connected or indirectly connected through an intermediate medium, or may be communicated with each other inside the two elements, or may be wirelessly connected or wired connected. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In describing the present invention, it is noted that the term "and/or" as used in this specification and the appended claims refers to and includes any and all combinations of one or more of the associated listed items.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other. The embodiment of the invention discloses a data management method, which is applied to a server, wherein an intelligent network card is arranged in the server, and as shown in figure 3, the method comprises the following steps:
For example, as an optional embodiment of the present invention, as shown in fig. 4, firstly, the intelligent network card and the server are assembled according to a topology design of the intelligent network card in advance, after the intelligent network card and the server are connected, the whole intelligent network card and the server system start to be powered on, at this time, the power is started to be output mainly through an auxiliary voltage output interface AUX on the server, and the power on of the baseboard management controller BMC and the complex programmable logic device CPLD of the server is completed. After a baseboard management controller BMC and a complex programmable logic device CPLD of the server are electrified, the intelligent network card starts to output Stanby electricity, the Stanby electricity refers to the dormancy electricity of the electric control system, at the moment, the power supply to the intelligent network card is completed, then the complex programmable logic device CPLD of the intelligent network card starts to work, and after the relevant Stanby electricity is electrified, the complex programmable logic device CPLD controls the other parts of the intelligent network card to complete electrification. After all the components of the intelligent network card are powered on, the SOC of the intelligent network card starts working, meanwhile, the intelligent network card sends the powered-on state information to the BMC of the intelligent network card through the SOC, the intelligent network card informs the server, and the BMC of the server starts to be powered on to allow starting. The intelligent network card is powered on, and the server formally starts to be powered on after the intelligent network card is powered on. Therefore, the situation that the intelligent network card and the server work cooperatively unsmoothly due to the fact that the server works and the intelligent network card does not work is avoided.
Before the intelligent network card processes the high-frequency access by adopting the intelligent network card, the server can determine access data corresponding to the access request, and then the access data is unloaded to the intelligent network card.
Specifically, the intelligent network card firstly determines the type of an access request, and then determines whether the access request belongs to high-frequency access or not according to the relationship between a preset request type and an access type based on the type of the access request, wherein the access type comprises high-frequency access and low-frequency access.
More specifically, the intelligent network card also establishes a relationship between the request type and the access type according to the multiple access requests acquired in the power-on process of the server, mainly by respectively determining the type of each access request in the multiple access requests, classifying the multiple access requests according to the types of the multiple access requests, counting the number of each type of access requests, sequencing the types of the access requests in the multiple access requests according to the number of each type of access requests, for example, from large to small, and finally establishing the relationship between the request type and the access type according to the sequencing.
For example, as an optional embodiment of the present invention, as shown in fig. 5, after a system composed of a server and an intelligent network card is powered on, the system starts to work, at this time, the intelligent network card stores all received data in a hard disk of the server, the server records all access rules of a requested message in the intelligent network card according to a type of a requested data message, so that the intelligent network card can conveniently determine the type of the data, and then determines whether the data is processed by the intelligent network card or is forwarded to the server for processing, and after the server records the access rules of the message in the intelligent network card, a network access request of a subsequent user is processed and forwarded by the intelligent network card. After receiving the access request, the intelligent network card judges the type of the access request according to the stored message access rule, when the intelligent network card has no access rule corresponding to the access request, the intelligent network card can directly send the access request to the server, the server processes the access request, at the moment, the server can send the access rule corresponding to the access request which cannot be directly processed by the intelligent network card to the intelligent network card, the access request can be directly processed by the intelligent network card when being accessed again, when the data received by the intelligent network card can be processed, the access data can be well recorded and classified according to the access frequency, and the access type and the access frequency of each data are recorded. The determination of the access frequency can be realized by a Bayesian algorithm. That is, first a sample set of data on the server is selected, and we divide the data into two parts according to the frequency of access. One part is accessed with high frequency, accounting for 20%, and the other part is accessed with lower frequency, accounting for 80%. And according to the access frequency sequence, determining the access frequency corresponding to the top 20% of the tail ends, and setting the access frequency as a threshold value for classified management. And then, transferring the data of the first 20 percent with high access frequency to a hard disk managed by the intelligent network card, and managing the data by the intelligent network card. In the process of classifying the data, the first 10% of the data may be directly processed by the intelligent network card, the remaining 90% of the data may be processed by the server, 10% of the hard disk of the corresponding server may be managed by the intelligent network card, and the remaining 90% of the data may be managed by the server. Or the intelligent network card can process the data with the frequency of the first bit or the first two bits. The classification processing process improves the expandability of the server, and the density of the server can be increased when the data center is deployed. The interrupt processing of the CPU to the data access is reduced, the idle running of the CPU is reduced, and the resource utilization rate of the CPU is improved.
And 303, when the access request belongs to high-frequency access, processing the high-frequency access by adopting the intelligent network card.
Illustratively, as an optional embodiment of the present invention, in a subsequent data request process, the intelligent network card adds a first identification action, that is, when the accessed data is the corresponding first 20% high-frequency data, the data is directly controlled by the intelligent network card to be read, and the data is partitioned, so that the data is quickly read. And high-frequency data are unloaded to the intelligent network card for management, so that the response time of data access can be effectively prolonged, the interruption processing of a CPU (central processing unit) is avoided waiting in a queue, and the user experience is improved.
The invention provides a new intelligent network card design and data management method, through the redesign of hardware lines and the combination of a software management mode, after the network unloading function of the intelligent network card is met, certain high-frequency access data can be effectively unloaded to the intelligent network card. In addition, a data management mode is provided for the cooperative work of the server and the intelligent network card from the data flow level. Meanwhile, a new data classification method is provided, and data are partitioned, so that the data can be rapidly read. The expandability of the server is improved, and the density of the server can be increased when the data center is deployed. The interrupt processing of the CPU to the data access is reduced, the idle running of the CPU is reduced, and the resource utilization rate of the CPU is improved. By unloading the high-frequency data to the intelligent network card for management, the response time of data access can be effectively prolonged, the CPU interrupt processing is avoided waiting in a queue, and the user experience is improved.
The present invention also provides a data management apparatus, as shown in fig. 6, the apparatus including:
an obtaining module 61, configured to obtain an access request, the details of which are described in reference to step 101;
a judging module 62, configured to judge whether the access request belongs to high-frequency access, where details refer to step 102;
and a processing module 63, configured to process the high-frequency access by using the intelligent network card when the access request belongs to the high-frequency access, where the detailed content refers to step 103.
Illustratively, as an optional implementation manner of the present invention, the determining module includes: the type determining module is used for determining the type of the access request; and the access request determining module is used for determining whether the access request belongs to high-frequency access or not according to the relationship between the preset request type and the access type based on the type of the access request, wherein the access type comprises high-frequency access and low-frequency access.
Illustratively, as an optional implementation manner of the present invention, the determining module further includes: and the relation establishing module is used for establishing the relation between the request type and the access type according to the multiple access requests acquired in the power-on process of the server.
Illustratively, as an optional implementation manner of the present invention, the relationship establishing module between the request type and the access type includes: a type determining module of each access request, configured to determine a type of each access request in the multiple access requests respectively; the classification and statistics module is used for classifying the access requests according to the types and counting the number of each type of access request; the sequencing module is used for sequencing the types of the access requests in the plurality of access requests according to the quantity of each type of access requests; and the relation establishing module is used for establishing the relation between the request type and the access type according to the sequence.
Illustratively, as an optional embodiment of the present invention, the data management apparatus further includes: the system comprises a mainboard, a substrate management controller and a complex programmable logic device power-on module, wherein the mainboard is provided with the substrate management controller and the complex programmable logic device power-on module, and the substrate management controller and the complex programmable logic device power-on module are used for powering on the substrate management controller and the complex programmable logic device when an auxiliary voltage output interface on the server mainboard supplies power; the intelligent network card electrifying module is used for electrifying the intelligent network card after the first complex programmable logic device is electrified; the message sending module is used for sending the message of completing the electrification of the intelligent network card to the substrate management controller after the electrification of the intelligent network card is completed; and the server starting module is used for starting the server after the mainboard receives the message of completing the power-on.
Illustratively, as an optional embodiment of the present invention, the data management apparatus further includes: a determining module, configured to determine access data corresponding to the access request; and the data unloading module is used for unloading the access data to the intelligent network card.
An embodiment of the present invention further provides a server, as shown in fig. 7, the server includes an intelligent network card, where the intelligent network card includes a processor 701 and a memory 702, where the processor 701 and the memory 702 may be connected by a bus or in another manner, and fig. 7 takes the connection by the bus as an example.
Specifically, the server further includes: the mainboard is arranged on the box body of the server; the backboard is arranged on the mainboard and is in communication connection with the intelligent network card. The intelligent network card and the backboard are powered by AUX electricity of the mainboard, and data transmission communication of the backboard is managed by the intelligent network card.
Illustratively, as an alternative embodiment of the present invention, the smart network card is provided on the motherboard as a daughter card component, and is powered by the Aux of the motherboard. The backboard is used as a daughter card of the whole server and is also arranged on the mainboard, the Aux of the mainboard supplies power, and the data management of the backboard is managed by the intelligent network card. The server is also provided with other backplanes for other functions except data management, and the power supply and management logic of the other backplanes is determined by the mainboard end. For example, as an optional implementation manner of the present invention, as shown in fig. 8, an intelligent network card of a server may mainly include a field programmable gate array FPGA, a system on a chip SOC, a double-data rate synchronous dynamic random access memory DDR, a baseboard management controller BMC, a complex programmable logic device CPLD, an optical module, a VR power supply module, and the like. The FPGA chip is provided with Flash, can store related FW files, and realizes forwarding of network access reports and judgment of data classification mainly in a programming mode. The SOC chip is responsible for transaction processing work of an intelligent network card of the server, completes analysis, forwarding and other work of a data packet by matching with the FPGA chip, and simultaneously completes processing of thermal data by matching with the backboard to read and store and the like. The BMC is mainly configured to perform an out-of-band management function on the entire card and perform some fault monitoring actions on the entire card. The complex programmable logic device CPLD mainly monitors and processes the power-on time sequence of the whole board card and some fault signals, and transmits the data back to the baseboard management controller BMC to complete related management actions in a matching way. The Flash mainly stores related FW files operated by the BMC, so that the BMC can normally operate. The DDR is used for supporting data operation, analysis and the like of the FPGA operation. The VR module serves as a power supply management unit of the whole network management card and converts and manages the power supply of the whole card. The solid state disk M.2 is mainly used for storing firmware relevant to the SOC and supporting the SOC to complete processing of relevant transactions. The intelligent network card receives network data through the optical module and transmits the network data to the field programmable gate array FPGA of the network card, the field programmable gate array FPGA is further connected with the system-on-chip SOC through PCIe, the system-on-chip SOC is further connected with the backboard through PCIe, and the backboard is connected with the solid state disk SSD0 and the solid state disk SSD1 of the server. The intelligent network card can store and manage data while meeting the network unloading requirement, and the function of the CPU is unloaded.
The back board is mainly used for meeting the data access and reading of the intelligent network card, and therefore PCIe signals are taken as high-speed signals of the back board and come from the intelligent network card. Meanwhile, in order to reduce the power supply pressure of the intelligent network card, the power supply of the backboard is supplied by AUX electricity of the main board, the management of the backboard is from the intelligent network card, the hard disk capacity managed by the backboard and the hard disk capacity of the server are mainly determined by the frequency ratio of the intelligent network card to the server for processing data, for example, when the frequency of the data processed by the intelligent network card is the first 20%, the hard disk capacity managed by the backboard and the hard disk capacity of the server are 1:4, and if the frequency of the data processed by the intelligent network card is the first 10%, the hard disk capacity managed by the backboard and the hard disk capacity of the server are 1: 9.
The processor 701 may be a Central Processing Unit (CPU). The processor 701 may also be other general purpose processors, Digital signal processors (DAPs), Application specific Integrated circuits (AAICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or any combination thereof.
The memory 702, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the key shielding method of the data management device in the embodiments of the present invention. The processor 701 executes various functional applications and data processing of the processor by executing non-transitory software programs, instructions and modules stored in the memory 702, that is, implements the data management method in the above-described method embodiment.
The memory 702 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 701, and the like. Further, the memory 702 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 702 may optionally include memory located remotely from processor 701, which may be connected to processor 701 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 702 and, when executed by the processor 701, perform the data management method of the embodiment shown in fig. 3-5.
The details of the electronic device may be understood with reference to the corresponding descriptions and effects in the embodiments shown in fig. 3-5, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Wherein, the storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a flash Memory (FlaAhMemory), a Hard disk (Hard DiAk Drive, abbreviated as HDD), or a solid state Drive (AAD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. A data management method is applied to a server, an intelligent network card is arranged in the server, and the data management method is characterized by comprising the following steps:
acquiring an access request;
judging whether the access request belongs to high-frequency access or not;
and when the access request belongs to high-frequency access, processing the high-frequency access by adopting the intelligent network card.
2. The method of claim 1, wherein the determining whether the access request belongs to a high frequency access comprises:
obtaining an access rule of the access request;
determining the type of the access request according to the access rule of the access request;
and determining whether the access request belongs to high-frequency access or not according to a preset relation between the request type and the access type based on the type of the access request, wherein the access type comprises high-frequency access and low-frequency access.
3. The method of claim 2, further comprising:
and establishing a relation between the request type and the access type according to a plurality of access requests acquired in the server power-on process.
4. The method according to claim 3, wherein the establishing the relationship between the request type and the access type according to the plurality of access requests acquired in the server power-on process comprises:
determining a type of each access request in the plurality of access requests respectively;
classifying the multiple access requests according to the types, and counting the number of each type of access requests;
sorting the types of the access requests in the multiple access requests according to the quantity of each type of access requests;
and establishing the relation between the request type and the access type according to the sequence.
5. The method of claim 1, wherein the power-up procedure of the server comprises:
when the auxiliary voltage output interface on the server mainboard supplies power, a substrate management controller and a complex programmable logic device on the mainboard are powered on;
after the first complex programmable logic device is powered on, the intelligent network card is powered on;
after the intelligent network card is electrified, sending a message of the electrification completion of the intelligent network card to the substrate management controller;
and starting the server after the mainboard receives the message of finishing the power-on.
6. The method of claim 1, further comprising, prior to said processing said high frequency access with said smart network card:
determining access data corresponding to the high frequency access;
when the intelligent network card has an access rule corresponding to the access data, processing the access data; and when the access rule corresponding to the access data does not exist in the intelligent network card, sending the access data to a server, and receiving the access rule corresponding to the access data.
7. The utility model provides a data management device, is applied to the server, be equipped with intelligent network card in the server which characterized in that includes:
the acquisition module is used for acquiring the access request;
the judging module is used for judging whether the access request belongs to high-frequency access;
and the processing module is used for processing the high-frequency access by adopting the intelligent network card when the access request belongs to the high-frequency access.
8. A server, comprising:
the intelligent network card comprises at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the steps of the data management method of any of claims 1 to 6.
9. The server of claim 8, further comprising:
the mainboard is arranged on the box body of the server;
the backboard is arranged on the mainboard and is in communication connection with the intelligent network card.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the data management method according to claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111552790.0A CN114338808A (en) | 2021-12-17 | 2021-12-17 | Data management method and device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111552790.0A CN114338808A (en) | 2021-12-17 | 2021-12-17 | Data management method and device and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114338808A true CN114338808A (en) | 2022-04-12 |
Family
ID=81051987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111552790.0A Pending CN114338808A (en) | 2021-12-17 | 2021-12-17 | Data management method and device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114338808A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117194172A (en) * | 2023-10-11 | 2023-12-08 | 珠海世宁达科技有限公司 | Network card power supply control method and related device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947795A (en) * | 2017-10-11 | 2019-06-28 | 阿里巴巴集团控股有限公司 | The acquisition methods and device of target data |
| CN110471939A (en) * | 2019-07-11 | 2019-11-19 | 平安普惠企业管理有限公司 | Data access method, device, computer equipment and storage medium |
| CN111756628A (en) * | 2020-05-14 | 2020-10-09 | 深圳震有科技股份有限公司 | Data packet forwarding processing method and system, intelligent network card and CPU |
| CN112181125A (en) * | 2020-08-28 | 2021-01-05 | 苏州浪潮智能科技有限公司 | Data processing method and device based on server and server |
-
2021
- 2021-12-17 CN CN202111552790.0A patent/CN114338808A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947795A (en) * | 2017-10-11 | 2019-06-28 | 阿里巴巴集团控股有限公司 | The acquisition methods and device of target data |
| CN110471939A (en) * | 2019-07-11 | 2019-11-19 | 平安普惠企业管理有限公司 | Data access method, device, computer equipment and storage medium |
| CN111756628A (en) * | 2020-05-14 | 2020-10-09 | 深圳震有科技股份有限公司 | Data packet forwarding processing method and system, intelligent network card and CPU |
| CN112181125A (en) * | 2020-08-28 | 2021-01-05 | 苏州浪潮智能科技有限公司 | Data processing method and device based on server and server |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117194172A (en) * | 2023-10-11 | 2023-12-08 | 珠海世宁达科技有限公司 | Network card power supply control method and related device |
| CN117194172B (en) * | 2023-10-11 | 2024-03-22 | 珠海世宁达科技有限公司 | Network card power supply control method and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10509456B2 (en) | Server rack power management | |
| US20150324232A1 (en) | Resource management method and apparatus for virtual machine system, and virtual machine system | |
| US20190041959A1 (en) | System, Apparatus And Method For Handshaking Protocol For Low Power State Transitions | |
| WO2019104947A1 (en) | System-on-chip, universal serial bus master device, system and awaking method | |
| CN105005363A (en) | Server platform based on universal ARM architecture | |
| EP3190478A1 (en) | Method, apparatus and system to transition system power state of a computer platform | |
| EP3035187B1 (en) | Hard disk and management method | |
| EP2656173A2 (en) | Dynamic and idle power reduction sequence using recombinant clock and power gating | |
| EP3367538A1 (en) | Smart power supply management for high standby power system | |
| CN108008917B (en) | Memory device and method of controlling link state thereof | |
| CN116541227B (en) | Fault diagnosis method and device, storage medium, electronic device and BMC chip | |
| CN104321716A (en) | Using device idle duration information to optimize energy efficiency | |
| TW202211035A (en) | System, device and method for resource allocation | |
| CN114338808A (en) | Data management method and device and server | |
| CN116868167A (en) | Operation control method and device of operating system, embedded system and chip | |
| CN106843890B (en) | Sensor network, node and operation method thereof based on intelligent decision | |
| CN115344358A (en) | Resource scheduling method, device and management node | |
| CN113325940A (en) | Power consumption control method, system, terminal and storage medium of intelligent device | |
| CN109002381A (en) | Process communication monitoring method, electronic device and computer readable storage medium | |
| CN112015342B (en) | IO scheduling system and scheduling method and corresponding electronic equipment | |
| CN114327023A (en) | Energy-saving method and system for Kubernetes cluster, computer medium and electronic equipment | |
| CN111143055A (en) | Virtual cloud host pre-allocation method and device, readable storage medium and electronic equipment | |
| US20140122799A1 (en) | Storage device and power saving method thereof | |
| CN113655963B (en) | Data storage system, method and computer equipment based on memory bridging | |
| US20240104028A1 (en) | Method for Operating a Multiplicity of Peripherals of a Vehicle, Computer-Readable Medium, System, and Vehicle |
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 |