CN109522114A - Radar data high-speed communication processing module of virtualization framework - Google Patents
Radar data high-speed communication processing module of virtualization framework Download PDFInfo
- Publication number
- CN109522114A CN109522114A CN201811163154.7A CN201811163154A CN109522114A CN 109522114 A CN109522114 A CN 109522114A CN 201811163154 A CN201811163154 A CN 201811163154A CN 109522114 A CN109522114 A CN 109522114A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- virtual
- radar
- core
- subregion
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 58
- 238000004891 communication Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims description 18
- 238000009826 distribution Methods 0.000 claims description 17
- 238000005192 partition Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 12
- 238000004088 simulation Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 239000011800 void material Substances 0.000 claims description 2
- 230000035485 pulse pressure Effects 0.000 claims 1
- 230000010365 information processing Effects 0.000 abstract description 8
- 230000005540 biological transmission Effects 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 description 15
- 238000001514 detection method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention provides a radar data high-speed communication processing module of a virtualization framework, which comprises a virtual machine platform; in a virtual machine platform, a plurality of client operating systems are installed to simulate a distributed system, and communication transmission among clients is realized through a virtual network card, wherein the clients are virtual machines and adopt a network protocol stack multi-core parallelization computing framework. The invention meets the application requirement of integrated radar information processing system, improves the utilization rate of hardware resources, can fully utilize multi-core parallel computing resources and capacity, greatly improves the processing capacity and throughput performance of the gigabit Ethernet network protocol TCP and UDP, and improves the data processing capacity of the radar data communication module on the virtual platform by one level.
Description
Technical field
The present invention relates to the communications fields of radar data processing, and in particular, to virtualizes the radar data high speed of frame
Communications Processor Module.It is especially a kind of to be based on domestic multi-core processor and embedded OS, it is deployed on virtual machine platform
Be applied to radar data communication processing system.
Background technique
With the development of information technology, " networking " and " integration " becomes the grown form of information age, therefore to letter
The requirement of breath processing system also develops to the direction of synthesization, needs to solve modularization comprehensive open architecture, soft or hard
Part integrated design, Unified Network communication, high-performance calculation, information record and the key technologies such as analysis in real time.Embedded system
It is information-based important composition with software, there are the spies such as real-time, resource availability, hardware diversity, application field broadness
Point, with the development of multi-core technology, the continuous improvement of CPU/DSP process performance, it is therefore apparent that traditional application deployment mode will
Cause the serious waste of process resource and storage resource.
For this reason, it may be necessary to form novel embedded software architecture, core concept is: by embedded computer
The virtualization process of resource (processor, memory and external equipment) forms more embedded computers (subregion) in logic,
Each logical computer (subregion) is set to possess independent cpu resource, storage resource and equipment interface, mutually isolated, resource is mutually not
Interference, and the independent operating system of each partition running.In this way, different Embedded Applications can be deployed in corresponding subregion
In, so as to improve resource utilization and application execution efficiency, and equipment quantity is directly reduced, reduces system power dissipation and body
Product weight.
Virtualization technology integration, generalization, synthesization information-based overall background under, flourish, start to people
Illustrate its wide application prospect.Virtualized computing system can a variety of computing resources of dynamic organization, specific hardware is isolated
Close dependence between architecture and software systems realizes the scalable computing system framework of transparence, thus flexibly
Building meets the calculating environment of a variety of application demands, improves the service efficiency of computing resource, plays the polymerization efficiency of computing resource,
And personalized and generalization computing resource use environment is provided for user.Virtualized computing system can be more sufficiently and reasonably
Using computing resource, meet increasingly various calculating demand, enable people to use computing resource transparent, efficient, customizablely,
To really realize the theory of flexibly building, on-demand computing.
Information-based digital technology also promotes the development of radar system, gradually from tradition " centered on hardware technology, towards
The mode of special function " develops to the mode " centered on software technology, towards actual demand ".Include in its technological frame
Software implementation radar architectural framework can define broadband rf front end, Digital Receiver, software implementation radar system signal/information
Various contents such as processing system and software implementation radar monitoring.
It is designed in general, radar information processing system is used based on distributed component based architecture, distributed each inter-module
It is communicated by network implementations, as shown in Figure 1.Radar signal simulator independently of computing platform, for simulate installation radar when
Sequence generates and Wave beam forming.Radar Signal Processing software completes pulse compression, treatment process of the digital filtering to threshold point mark.It is aobvious
Software is controlled independently of simulation and computing platform, Radar Signal Processing is shown to terminal later.In radar communications system, each function
Component is separately operable in independent hardware platform, on the one hand makes radar system more and more huger, and different functions needs independence
Cabinet realize that multiple equipment forms entire distributed networking complication system.On the other hand, the function ratio of each cabinet
More single, there is no playing completely, the operation and maintenance cost of more equipment also increasingly increases the actual performance of hardware resource.
It, can be dispersion based on the real-time virtual framework technology of domestic multi-core processor in radar data communication scenes
Function to each hardware platform is integrated on integrated virtual platform, deployment high safety embedded software running virtualization system
System, and be in communication with each other by Microsoft Loopback Adapter.
The detection environment that radar information processing system faces gradually tends to complicate, and detection mode gradually tends to diversification,
Severe complicated electromagnetic environment and detection target exacerbate the growth of radar data amount and handle speed by network transmission to data
The demand of degree.Due to the complexity and diversity of network protocol, the processing of user mode network protocol is still single agreement mode stack,
With the model of single task role with interface card driving layer and user application layer interaction in operating system, to the place of network message data
Rationality can depend on the processing capacity of run CPU core, and after the CPU core full load run, network performance can not be into one
Step is promoted.In such a mode, for the radar data scene of flood tide, there are bottlenecks for the processing of network data performance, are unable to satisfy
Data throughput requirement.
Summary of the invention
For the defects in the prior art, the object of the present invention is to provide a kind of radar data high speed for virtualizing frame is logical
Believe processing module.
A kind of radar data high-speed communication processing module of the virtualization frame provided according to the present invention, including virtual machine are flat
Platform;
In virtual machine platform, multiple Client OSs are installed, carry out simulation distribution formula system, pass through Microsoft Loopback Adapter reality
Communications between existing client computer, wherein client computer is virtual machine.
Preferably, using network protocol stack multi-core parallel concurrent Computational frame.
Preferably, the virtual machine uses following deployment way:
Using multi-core processor, multi-core processor supports hardware virtual technology;Virtual process is controlled by instruction set, is provided
The hardware supported of intercepting and capturing and redirection to virtual machine instructions;By these instruction set, virtual machine is placed in by virtual machine manager
It is run under limited mode, when virtual machine accesses physical hardware resources, control is handed back to by the operation of hardware timeout virtual machine
Virtual machine manager processing;By virtual machine in a tethered mode to the access of resource, virtual machine pipe is redirected to by hardware completely
The specified virtual resource of device is managed, whole process does not suspend the operation of virtual machine and the participation of virtual machine manager.
Preferably, by virtual machine manager, multiple virtual machine partitions is generated, operates and is independent of each other between each subregion;Often
A virtual machine has the memory address space of oneself, and the memory headroom of subregion uses memory management unit MMU storage protection mechanism, will
It is isolated between virtual machine manager and virtual machine partitions and virtual machine partitions;And core resource required for subregion
Distribution and access implement management and safety verification by virtual machine manager;
To guarantee each subregion independent CPU time, virtual machine manager is abstracted into physics multi-core CPU multiple virtual
The number of vCPU, virtual vCPU are greater than the number of physical cpu, and each virtual machine partitions use one or more virtual vCPU;?
Time-domain, cutting processor timeslice, according to time-sharing multiplex principle, the vCPU of different virtual machine subregion is executed in different physics
The different time piece of CPU.
Preferably, by virtual machine manager, multiple virtual machine partitions is generated, operates and is independent of each other between each subregion;Often
A virtual machine has the memory address space of oneself, and the memory headroom of subregion uses memory management unit MMU storage protection mechanism, will
It is isolated between virtual machine manager and virtual machine partitions and virtual machine partitions;And core resource required for subregion
Distribution and access implement management and safety verification by virtual machine manager;
Preferably, two real-time embedded operating systems and a desktop non-real time operating system are disposed, as virtual machine
It operates on virtual machine platform;Wherein, two real-time virtual machines run embedded OS;Wherein, a virtual machine behaviour
Make system operation radar signal simulator, generate timing and waveform, another VME operating system receives what simulation was sent
Radar signal is filtered removal false-alarm point to original point mark, forms radar through extra pulse compression, filtering, Target dots processing process
Target congealing point mark;One non-real time operating system runs monitoring and control management software, and receives radar target by Microsoft Loopback Adapter and coagulate
Accumulation mark is shown in terminal.
Preferably, the scheduling strategy of priority is used inside two real time virtual machines, so that the high task of priority obtains
Real-time response;The radar congealing point mark exported after real-time processing, is buffered in one section of buffer area of Non real-time processing environment, radar
Display system obtains Targets Dots from buffer area, then is output to display terminal.
Preferably, between virtual machine by Microsoft Loopback Adapter, connected using TCP network protocol, send radar waveform signal to
Radar Signal Processing program, the display terminal through Radar Signal Processing program transmission congealing point mark to radar display system;
In the network protocol stack multi-core parallel concurrent Computational frame, network protocol stack is operated on multiple CPU simultaneously,
Realize parallel processing;Each virtual machine internal runs respective User space parallel network protocol stack;It is symmetrically more in Single NIC multicore
It handles in smp system, network interface card transmitting-receiving is interrupted to specify and is triggered in 0 core, justice is appraised and decided in 0 that message distribution is completed in response to network interruption
For network protocol stack schedule core, the query processing of message distribution and aided protocol is realized;Network layer IP's and transport layer TCP/UDP
Network protocol stack task instances operate on the vCPU of respective virtual machine internal, referred to as business core.
Preferably, message distributes work in trawl performance interrupt processing function, receives letter by NAPI (New API) message
Number calls, and message is joined message policy classifier buffer queue, by the strategy distribution of distributor, the report that will be received
Text is distributed in the work queue of different business core, by different business core protocol stack instances to receive message goes out
Team, parsing, processing and transmission.
Compared with prior art, the present invention have it is following the utility model has the advantages that
1, multi-core processor of the present invention virtualizes framework technology, can make full use of virtualization technology, being distributed to
Operating system and radar processing module on each hardware device are integrated into integrated virtual machine platform, and pass through Microsoft Loopback Adapter
It is in communication with each other, meets the application demand of radar information processing System all-in-one Integration, improve the use of hardware resource
Rate.
2, parallelization processing technique of the present invention, can make full use of multi-core parallel concurrent computing resource and ability, substantially mention
The processing capacity and throughput performance for rising ten thousand mbit ethernet network agreement TCP and UDP, by the radar data communication module on virtual platform
Data-handling capacity improve a rank.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is based on distributed radar information processing system.
Fig. 2 is the radar information processing system based on virtualization technology.
Fig. 3 is user mode network protocol stack concurrent technique frame diagram.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection scope.
The present invention relates to a kind of based on domestic multi-core processor hardware platform, in the embedded information system of military high safety
The communication module of radar data processing is carried out on real-time virtual machine platform.The communication module is installed multiple logical on virtual machine platform
It uses the embedded domestic operating system of operating system and sharp China as Client OS, carrys out simulation distribution formula system, pass through void
Quasi- network interface card technology realizes the communications between client computer, and radar number is improved using network protocol stack multi-core parallel concurrent technology
According to the network data processing performance and data throughout of ten thousand Broadcoms in communication.
Multi-core processor virtual platform frame of the present invention, is applied in radar data communication module, can be
The function of dispersing each cabinet is integrated on integrated virtual platform, is in communication with each other between virtual machine by Microsoft Loopback Adapter, such as
Shown in Fig. 2.In radar data Communications Processor Module, user mode network protocol parallelization Computational frame is introduced, according to embedded
The characteristics of system and multi-core processor devise network protocol parallel processing architecture, make full use of CPU multicore computing resource, have
Effect solves the problems, such as that 10,000,000,000 network message process performances are not high in current embedded system.
The deployment of virtual machine is illustrated below.
The virtualization framework technology selects the domestic multi-core processor of million cores, and processor is supported hardware virtual technology, optimized
Instruction set control virtual process, the intercepting and capturing to virtual machine instructions and the hardware supported of redirection are provided.By these instruction set,
Virtual machine is placed under a kind of limited mode and runs by virtual machine manager, when virtual machine accesses physical hardware resources, hardware meeting
Control is handed back to virtual machine manager processing by the operation for suspending virtual machine.In addition, virtual using the hardware of million die processors
Change enhancing mechanism and the virtual machine access to some resources in a tethered mode is redirected to Virtual Machine Manager by hardware completely
The specified virtual resource of device, whole process do not need the operation of pause virtual machine and the participation of virtual machine manager.
By virtual machine manager, multiple virtual machine partitions are generated, operates and is independent of each other between each subregion.In this programme
In, each virtual machine has the memory address space of oneself, and the memory headroom protection technique of subregion uses MMU storage protection mechanism,
It will be isolated between virtual machine manager and virtual machine partitions and virtual machine partitions.Meanwhile core required for subregion provides
The distribution and access in source implement management and safety verification by virtual machine manager.
To guarantee each subregion independent CPU time, virtual machine manager is abstracted into physics multi-core CPU multiple virtual
The number of vCPU, virtual vCPU can be greater than the number of physical cpu, and each virtual machine partitions can be used one or more virtual
vCPU.In time-domain, cutting processor timeslice, according to time-sharing multiplex principle, the vCPU of different virtual machine subregion can be executed
In the different time piece of different physical cpus.
Framework technology is virtualized based on above-mentioned multi-core processor, two real-time embedded operating systems is disposed and one general
Desktop non-real time operating system, operates on virtual platform as virtual machine.
Two real time virtual machines run domestic real time embedded system reworks.One VME operating system runs thunder
Up to signal simulator, timing and waveform are generated, a VME operating system receives the radar signal that simulation is sent, by arteries and veins
Punching press contracting, filtering, Target dots processing process are filtered the low-quality false-alarm point of removal to original point mark, it is solidifying to form radar target
Accumulation mark.
The domestic general magnificent desktop system of one non-real time operating system operation, runs monitoring and control management software, and pass through virtual net
Radar target congealing point mark is received in clamping, is shown in terminal.
For the real-time for guaranteeing real-time processing environment, 2 real time virtual machines inside use the scheduling strategy of priority, guarantee
The high task of priority can obtain real-time response.The radar congealing point mark exported after real-time processing, is buffered in Non real-time processing
One section of buffer area of environment, radar display system obtains Targets Dots from buffer area, then is output to display terminal.
The parallelization processing of network protocol stack is illustrated below.
On the virtual platform of radar information processing, by Microsoft Loopback Adapter between virtual machine, connected using TCP network protocol
It connects, sends radar waveform signal to radar processing routine, send congealing point mark to radar asorbing paint system through Radar Signal Processing program
System.In face of the radar signal data of flood tide, the user mode network protocol stack of multidiameter delay is devised.As shown in Figure 3.
Under single agreement mode stack, network protocol stack is operated on a CPU with single task model, network transmission
It can depend on cpu performance and cpu load.In the present solution, design user mode network protocol stack parallel processing, can be network
Protocol stack operates on multiple CPU simultaneously, realizes parallel processing, promotes network data transmission and process performance.
On the virtual platform of this programme, each virtual machine internal runs respective User space parallel network protocol stack.
In Single NIC multicore smp system, network interface card transmitting-receiving is interrupted to specify and is triggered in 0 core, therefore response to network is interrupted and completes message
0 core of distribution is defined as network protocol stack schedule core, realizes the query processing of message distribution and aided protocol.Other specific nets
Network layers (IP) and transport layer (TCP/UDP) network protocol stack task instances, operate on the vCPU of respective virtual machine internal, referred to as
Business core.
Message distributes work in trawl performance interrupt processing function, is called by NAPI (New API) message receiver function,
And message is joined message policy classifier buffer queue, by the strategy distribution of distributor, the message received is distributed
Into the work queue of different business core, by different business core protocol stack instances to receive message carry out out team, solution
Analysis, processing and transmission.
In conclusion the beneficial effects of the present invention are:
1) present invention has selected domestic million cores multi-core processor as hardware platform, and sharp China's real-time embedded operating system is made
For the real-time client system on virtual machine platform, general China's general desktop operating system is as the non real-time visitor on virtual machine platform
Family machine system substantially meets the demand of national autonomous software and hardware, has the ability of similar-type products outside surrogate.
2) multi-core processor virtual platform frame of the present invention can effectively solve radar system function and collect increasingly
At, and hardware device is dispersed in each cabinet, so that the problem that equipment redundancy utilization rate is inadequate.Pass through virtual platform, deployment
Multiple Client OSs run radar information processing system.
3) network protocol stack parallel processing technique of the present invention can efficiently solve under 10,000,000,000 network complex scenes, association
Stack Message processing performance bottleneck is discussed, by promoting the concurrent instances number of protocol stack, is sending and receiving two-way 10,000,000,000 network of promotion
Data throughput capabilities.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (9)
1. a kind of radar data high-speed communication processing module for virtualizing frame, which is characterized in that including virtual machine platform;
In virtual machine platform, multiple Client OSs are installed, carry out simulation distribution formula system, visitor is realized by Microsoft Loopback Adapter
Communications between the machine of family, wherein client computer is virtual machine.
2. the radar data high-speed communication processing module of virtualization frame according to claim 1, which is characterized in that use
Network protocol stack multi-core parallel concurrent Computational frame.
3. the radar data high-speed communication processing module of virtualization frame according to claim 1, which is characterized in that described
Virtual machine uses following deployment way:
Using multi-core processor, multi-core processor supports hardware virtual technology;Virtual process is controlled by instruction set, is provided to void
The intercepting and capturing of quasi- machine instruction and the hardware supported of redirection;By these instruction set, virtual machine is placed in limited by virtual machine manager
Mode under run, virtual machine access physical hardware resources when, control is handed back to virtually by the operation of hardware timeout virtual machine
Machine manager processes;By virtual machine in a tethered mode to the access of resource, virtual machine manager is redirected to by hardware completely
Specified virtual resource, whole process do not suspend the operation of virtual machine and the participation of virtual machine manager.
4. the radar data high-speed communication processing module of virtualization frame according to claim 3, which is characterized in that pass through
Virtual machine manager generates multiple virtual machine partitions, operates and be independent of each other between each subregion;Each virtual machine has the memory of oneself
The memory headroom of address space, subregion uses memory management unit MMU storage protection mechanism, by virtual machine manager and virtual machine
It is isolated between subregion and virtual machine partitions;And the distribution and access of core resource required for subregion, by virtual machine
Manager implements management and safety verification;
To guarantee each subregion independent CPU time, physics multi-core CPU is abstracted into multiple virtual vCPU by virtual machine manager,
The number of virtual vCPU is greater than the number of physical cpu, and each virtual machine partitions use one or more virtual vCPU;In the time
Domain, cutting processor timeslice, according to time-sharing multiplex principle, the vCPU of different virtual machine subregion is executed in different physical cpus
Different time piece.
5. the radar data high-speed communication processing module of virtualization frame according to claim 4, which is characterized in that pass through
Virtual machine manager generates multiple virtual machine partitions, operates and be independent of each other between each subregion;Each virtual machine has the memory of oneself
The memory headroom of address space, subregion uses memory management unit MMU storage protection mechanism, by virtual machine manager and virtual machine
It is isolated between subregion and virtual machine partitions;And the distribution and access of core resource required for subregion, by virtual machine
Manager implements management and safety verification.
6. the radar data high-speed communication processing module of virtualization frame according to claim 5, which is characterized in that deployment
Two real-time embedded operating systems and a desktop non-real time operating system, operate on virtual machine platform as virtual machine;
Wherein, two real-time virtual machines run embedded OS;Wherein, a VME operating system runs radar signal mould
Quasi- device generates timing and waveform, another VME operating system receives the radar signal that simulation is sent, through extra pulse pressure
Contracting, filtering, Target dots processing process are filtered removal false-alarm point to original point mark, form radar target congealing point mark;One non-
Real time operating system runs monitoring and control management software, and receives radar target congealing point mark by Microsoft Loopback Adapter, is shown in terminal
Show.
7. the radar data high-speed communication processing module of virtualization frame according to claim 6, which is characterized in that two
The scheduling strategy of priority is used inside real time virtual machine, so that the high task of priority obtains real-time response;It is handled in real time
The radar congealing point mark exported afterwards is buffered in one section of buffer area of Non real-time processing environment, and radar display system is from buffer area
Targets Dots are obtained, then are output to display terminal.
8. the radar data high-speed communication processing module of virtualization frame according to claim 2, which is characterized in that virtual
It by Microsoft Loopback Adapter between machine, is connected using TCP network protocol, sends radar waveform signal to Radar Signal Processing program, warp
Radar Signal Processing program sends congealing point mark to the display terminal of radar display system;
In the network protocol stack multi-core parallel concurrent Computational frame, network protocol stack is operated on multiple CPU simultaneously, is realized
Parallel processing;Each virtual machine internal runs respective User space parallel network protocol stack;In Single NIC multicore symmetric multi-processors
In smp system, network interface card transmitting-receiving is interrupted to specify and is triggered in 0 core, 0 core that response to network interrupts completion message distribution is defined as net
Network protocol stack schedule core realizes the query processing of message distribution and aided protocol;The network of network layer IP and transport layer TCP/UDP
Protocol stack task instances operate on the vCPU of respective virtual machine internal, referred to as business core.
9. the radar data high-speed communication processing module of virtualization frame according to claim 8, which is characterized in that message
Distribute work to be called in trawl performance interrupt processing function by NAPI (New API) message receiver function, and message is added
The message received is distributed to different business by the strategy distribution of distributor by message policy classifier buffer queue
In the work queue of core, by different business core protocol stack instances to receive message carries out out team, parsing, processing and biography
It is defeated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811163154.7A CN109522114A (en) | 2018-09-30 | 2018-09-30 | Radar data high-speed communication processing module of virtualization framework |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811163154.7A CN109522114A (en) | 2018-09-30 | 2018-09-30 | Radar data high-speed communication processing module of virtualization framework |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109522114A true CN109522114A (en) | 2019-03-26 |
Family
ID=65772460
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811163154.7A Pending CN109522114A (en) | 2018-09-30 | 2018-09-30 | Radar data high-speed communication processing module of virtualization framework |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109522114A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110798412A (en) * | 2019-10-18 | 2020-02-14 | 北京浪潮数据技术有限公司 | Multicast service processing method, device, cloud platform, equipment and readable storage medium |
CN111176616A (en) * | 2019-12-06 | 2020-05-19 | 中国人民解放军军事科学院国防科技创新研究院 | Satellite integrated electronic system architecture based on universal satellite application subsystem |
CN111541706A (en) * | 2020-04-30 | 2020-08-14 | 成都安恒信息技术有限公司 | Method for detecting system anti-DDoS performance |
CN111722191A (en) * | 2020-07-01 | 2020-09-29 | 成都汇蓉国科微系统技术有限公司 | Communication protocol design method of radar complex signal processor |
CN113220274A (en) * | 2021-05-25 | 2021-08-06 | 中国电子科技集团公司第二十九研究所 | System architecture based on radio frequency digital definable and design method thereof |
CN113296060A (en) * | 2021-07-28 | 2021-08-24 | 四川斯艾普电子科技有限公司 | MST radar final-stage transceiving system based on remote intelligent control |
CN117389691A (en) * | 2023-12-11 | 2024-01-12 | 利尔达科技集团股份有限公司 | Virtual machine based on embedded operating system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN85101171A (en) * | 1985-04-01 | 1987-02-11 | 株式会社日立制作所 | The I/O manner of execution of dummy machine system and computer system thereof |
CN103218266A (en) * | 2012-01-18 | 2013-07-24 | 国际商业机器公司 | Method, equipment and virtual machine system used during communication between virtual machine and external machine |
CN103621026A (en) * | 2013-04-01 | 2014-03-05 | 华为技术有限公司 | Virtual machine data exchange method, apparatus and system |
CN104102531A (en) * | 2014-08-06 | 2014-10-15 | 汉柏科技有限公司 | Multi-network fusion system and multi-network fusion method based on virtual machine |
CN106790162A (en) * | 2016-12-29 | 2017-05-31 | 中国科学院计算技术研究所 | Virtual network optimization method and system |
CN108037994A (en) * | 2017-11-15 | 2018-05-15 | 中国电子科技集团公司第三十二研究所 | Scheduling mechanism supporting multi-core parallel processing in heterogeneous environment |
CN108254727A (en) * | 2017-12-08 | 2018-07-06 | 西安电子科技大学 | A kind of radar plot condensing method based on Contour extraction |
CN108390810A (en) * | 2018-01-05 | 2018-08-10 | 郑州信大捷安信息技术股份有限公司 | One kind is based on the more android system network virtualization methods of single linux kernel |
-
2018
- 2018-09-30 CN CN201811163154.7A patent/CN109522114A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN85101171A (en) * | 1985-04-01 | 1987-02-11 | 株式会社日立制作所 | The I/O manner of execution of dummy machine system and computer system thereof |
CN103218266A (en) * | 2012-01-18 | 2013-07-24 | 国际商业机器公司 | Method, equipment and virtual machine system used during communication between virtual machine and external machine |
CN103621026A (en) * | 2013-04-01 | 2014-03-05 | 华为技术有限公司 | Virtual machine data exchange method, apparatus and system |
CN104102531A (en) * | 2014-08-06 | 2014-10-15 | 汉柏科技有限公司 | Multi-network fusion system and multi-network fusion method based on virtual machine |
CN106790162A (en) * | 2016-12-29 | 2017-05-31 | 中国科学院计算技术研究所 | Virtual network optimization method and system |
CN108037994A (en) * | 2017-11-15 | 2018-05-15 | 中国电子科技集团公司第三十二研究所 | Scheduling mechanism supporting multi-core parallel processing in heterogeneous environment |
CN108254727A (en) * | 2017-12-08 | 2018-07-06 | 西安电子科技大学 | A kind of radar plot condensing method based on Contour extraction |
CN108390810A (en) * | 2018-01-05 | 2018-08-10 | 郑州信大捷安信息技术股份有限公司 | One kind is based on the more android system network virtualization methods of single linux kernel |
Non-Patent Citations (2)
Title |
---|
任永杰 等: "《KVM虚拟化技术:实战与原理解析》", 31 October 2013, 机械工业出版社 * |
执假以为真: "《KVM虚拟化技术实战和原理解析》读书笔记(一)", 《HTTPS://BLOG.CSDN.NET/NIRENDAO/ARTICLE/DETAILS/52853103?LOCATIONNUM=2&FPS=1》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110798412A (en) * | 2019-10-18 | 2020-02-14 | 北京浪潮数据技术有限公司 | Multicast service processing method, device, cloud platform, equipment and readable storage medium |
CN111176616A (en) * | 2019-12-06 | 2020-05-19 | 中国人民解放军军事科学院国防科技创新研究院 | Satellite integrated electronic system architecture based on universal satellite application subsystem |
CN111541706A (en) * | 2020-04-30 | 2020-08-14 | 成都安恒信息技术有限公司 | Method for detecting system anti-DDoS performance |
CN111722191A (en) * | 2020-07-01 | 2020-09-29 | 成都汇蓉国科微系统技术有限公司 | Communication protocol design method of radar complex signal processor |
CN111722191B (en) * | 2020-07-01 | 2023-04-07 | 成都汇蓉国科微系统技术有限公司 | Communication protocol design method of radar complex signal processor |
CN113220274A (en) * | 2021-05-25 | 2021-08-06 | 中国电子科技集团公司第二十九研究所 | System architecture based on radio frequency digital definable and design method thereof |
CN113220274B (en) * | 2021-05-25 | 2023-07-18 | 中国电子科技集团公司第二十九研究所 | Definable system based on radio frequency numbers and design method thereof |
CN113296060A (en) * | 2021-07-28 | 2021-08-24 | 四川斯艾普电子科技有限公司 | MST radar final-stage transceiving system based on remote intelligent control |
CN117389691A (en) * | 2023-12-11 | 2024-01-12 | 利尔达科技集团股份有限公司 | Virtual machine based on embedded operating system |
CN117389691B (en) * | 2023-12-11 | 2024-03-22 | 利尔达科技集团股份有限公司 | Virtual machine based on embedded operating system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109522114A (en) | Radar data high-speed communication processing module of virtualization framework | |
Marty et al. | Snap: A microkernel approach to host networking | |
Mai et al. | Netagg: Using middleboxes for application-specific on-path aggregation in data centres | |
Shafer | I/O virtualization bottlenecks in cloud computing today | |
Liao et al. | Software techniques to improve virtualized I/O performance on multi-core systems | |
Xu et al. | Small is better: Avoiding latency traps in virtualized data centers | |
Guan et al. | CIVSched: A communication-aware inter-VM scheduling technique for decreased network latency between co-located VMs | |
Ram et al. | {Hyper-Switch}: A Scalable Software Virtual Switching Architecture | |
Shalev et al. | {IsoStack—Highly} Efficient Network Processing on Dedicated Cores | |
CN102609298A (en) | Network card virtualizing system and network card virtualizing method on basis of hardware array expansion | |
Garzarella et al. | Virtual device passthrough for high speed VM networking | |
Lai et al. | Sol: Fast distributed computation over slow networks | |
Li et al. | When I/O interrupt becomes system bottleneck: Efficiency and scalability enhancement for SR-IOV network virtualization | |
Maffione et al. | Flexible virtual machine networking using netmap passthrough | |
CN108965148A (en) | A kind of processor and message processing method | |
Zhou et al. | Fast coflow scheduling via traffic compression and stage pipelining in datacenter networks | |
Zhou et al. | Optimizations for high performance network virtualization | |
Noronha et al. | Performance evaluation of container based virtualization on embedded microprocessors | |
Nordal et al. | Paravirtualizing tcp | |
CN114691286A (en) | Server system, virtual machine creation method and device | |
CN116319240A (en) | Scale telemetry using interactive matrices for deterministic microservice performance | |
de Lacerda Ruivo et al. | Exploring infiniband hardware virtualization in opennebula towards efficient high-performance computing | |
Zeng et al. | XCollOpts: A novel improvement of network virtualizations in Xen for I/O-latency sensitive applications on multicores | |
Varma et al. | Analysis of a network io bottleneck in big data environments based on docker containers | |
Hu et al. | Research of scheduling strategy on OpenStack |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190326 |
|
RJ01 | Rejection of invention patent application after publication |