CN103441952B - Based on multinuclear or the processing method of network data packets of many-core flush bonding processor - Google Patents
Based on multinuclear or the processing method of network data packets of many-core flush bonding processor Download PDFInfo
- Publication number
- CN103441952B CN103441952B CN201310365607.5A CN201310365607A CN103441952B CN 103441952 B CN103441952 B CN 103441952B CN 201310365607 A CN201310365607 A CN 201310365607A CN 103441952 B CN103441952 B CN 103441952B
- Authority
- CN
- China
- Prior art keywords
- core
- data
- packet
- multinuclear
- many
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a kind of based on multinuclear or the processing method of network data packets of many-core flush bonding processor, including: 1) core in multinuclear or many-core flush bonding processor is divided into data receiver core and data process core, described data receiver verification shared drive region carries out Buffer allocation, and data process core and are distributed policy registration to described data receiver core, determine that each data process core packet to be dealt with feature;2) data receiver core is according to the data packet header information received from the network hardware, is deposited to corresponding relief area by packet;3) data receiver core processes, according to data, the distribution policy that core is registered, process core to described data and send message, described data process core and process according to described message, the packet read in relief area, and send process state information to described data receiver core.
Description
Technical field
The present invention relates to multinuclear or many-core flush bonding processor and network service process field, particularly relate to
A kind of based on multinuclear or the processing method of network data packets of many-core flush bonding processor.
Background technology
Traditional single core processor tupe is single task serial process, in order to only improve processing speed
Dominant frequency can be increased, and the raising of dominant frequency is conditional, and add power consumption.At multinuclear or many-core
Reason device solves these problems well, and multinuclear or many-core processor use parallel processing mode, many
Business parallel processing, can improve processing speed in the case of low dominant frequency, and reduce power consumption.And with
The increase day by day of bandwidth, web database technology explosive growth.The rise of Internet of Things heat exacerbates especially
The demand of process quick to network data, the numerous data in network are desirable that the strongest real-time simultaneously
Property, flowed fluctuation during in order to ensure the smooth transport of data and reduce data transmission, software system is such as
What effectively utilize its framework advantage carry out network packet quickly receive and distribution becomes research already
Focus.
The patent of invention of Application No. CN201010289667.X discloses a kind of based on multicore architecture
Message forwarding method and system, this invention is by obtaining the packet in the Internet, and at packet is
During tunnel links packet, it is decapsulated, obtain IP packet, use hash algorithm to IP
The five-tuple of packet carries out hash algorithm, further according to counted cryptographic Hash and Hash table size thereof, with
And the quantity of CPU, by cryptographic Hash labelling to above-mentioned IP packet, retransmit to described CPU
In.
Although foregoing invention patent is a kind of file transmitting method about multicore architecture, but the most only
The forwarding of a kind of message, the data receiver being not directed in multinuclear or many-core embedded system and point
Send out, the strategy of more not mentioned data distribution, and for multinuclear or many-core flush bonding processor, for it
The research receiving management and point-score processing method of network packet is significant.
Summary of the invention
The invention provides connecing of network packet in a kind of multinuclear or many-core embedded processor system
Closed tube reason and the distribution policy method of packet, it is possible to quickly effectively realize network packet accurately
Reception and distribution.
A kind of based on multinuclear or the processing method of network data packets of many-core flush bonding processor, including following
Step:
1) core in multinuclear or many-core flush bonding processor is divided into data receiver core and data process
Core, described data receiver verification shared drive region carries out Buffer allocation, and data process core to
Described data receiver core is distributed policy registration, determines that each data process core number to be dealt with
According to bag feature;
2) data receiver core is according to the data packet header information received from the network hardware, is deposited by packet
Put to corresponding relief area;
3) data receiver core processes, according to data, the distribution policy that core is registered, at described data
Reason core sends message, and described data process core according to described message, the data in reading relief area
Bag processes, and sends process state information to described data receiver core.
Described multinuclear or many-core flush bonding processor are isomorphism or heterogeneous processor, the quantity of described core
At least 8, wherein, the quantity of described data receiver core is one or more.
Data receiver core is responsible for network data in shared drive region and is received the allocation manager of relief area, number
The judgement of core is processed according to the purpose data of the management and pending packet that process core registration distribution policy,
Data receiver core is also responsible for configuration and the data interaction of network hardware equipment, including configuration network interface card hardware
Mode of operation and obtain its state parameter etc., data interaction refers to the reception of network data;At data
Reason core is distributed the registration of strategy according to practical application request to data receiver core, and extraction is left in
Packet in relief area processes.
The number of data receiver core and data process the number of core and all can join according to reality application
Put.Such as, choosing 8 cores and carry out simple image binaryzation process, data receiver core has only received
Whole piece image, then be distributed, therefore choose a data receiver core and just can complete
State operation;When image is processed, remaining 7 cores can be chosen and carry out as data process core
Binary conversion treatment.Meanwhile, data receiver core can according to processor structure, network hardware equipment position,
The composite factors such as core position are set, and it is distance network hardware interface position that general data receives core
Nearest process core, the number of data process core and position selection gist application demand and data receiver core
Depending on, data process core completely can be by user's sets itself.
In step 1) in, the size of described relief area be 256 bytes, 512 bytes, 1024 bytes,
1536 bytes, 2048 bytes, 4096 bytes or 10240 bytes, the quantity of described relief area is multiple,
Described data process nuclear energy and check the physical address of each relief area.
In multiple relief areas, the quantity of the relief area of every kind of size configures according to packet feature,
The physical address of the most all relief areas can be processed verification by data and see, say, that these bufferings
District is all shared for all process cores, and each relief area is except depositing the appointment size of reception
Packet content outside, further comprises and which data this packet is sent to processes the information of core,
The data i.e. processed this packet process the information of core.The specifying information of each relief area such as table
Shown in 1:
Data buffering structure in table 1 data receiver core
In Table 1, in its structure of different size of relief area, buffer data varies in size, relief area
The size processing core mark vary in size according to the process core of used flush bonding processor and different,
The time being sent to data process core message refers to when data receiver core judges that this record data send
When which data to process core to, at the timestamp that this data buffering afterbody adds.
Described step 2) in, described packet feature includes that type of data packet, hardware head are believed
Breath type and port information, packet feature determines the data process core processing its network data.
In step 1) in, each data process core can only register a distribution policy, same distribution plan
Slightly can be processed core by multiple data to register simultaneously.
Data receiver core is used for the management to distribution policy and distribution, can dynamically configure at each data
The distribution policy of reason core, depending on distribution policy number altogether processes check figure according to data, each core is only
A distribution policy can be registered.Data process core and are responsible for by certain strategy foundation or application demand
It is distributed policy registration to data receiver core, specifies in registration process and be sent on this registration core
Packet feature.
Described distribution policy includes data pack protocol strategy, packet MAC Address strategy, IP address
Strategy and packet port policy.
In the present invention, data process core and are sent to the distribution policy information such as table 2 below institute of data receiver core
No:
Table 2 data process core make a determined effort policy content
Data process core is distributed in the information of policy registration to data receiver core in table 2, each
The determination of distribution policy is processed core by data and determines, can be comprehensive distribution policy, it is also possible to be single
The configuration of individual distribution policy.Share and indicate that representing that these data process core receives meets its distribution policy
After packet, if having other data to process core also register identical strategy, if be ready and other numbers
Share according to processing core.
When each data process core is distributed policy registration, data receiver core judges that these data process core
Whether the distribution policy of request is that other data process the registered distribution policies of core, if registered and
Needing to share with other cores, the shared flag bit that each data process core is updated.
After data receiver core receives the distribution policy that data process core, right inside data receiver core
Each distribution policy can carry out storage management, and in storage management, each data process the distribution plan of core
Outside slightly divided by the content in upper table 2, also include following two contents:
1): the distribution policy the tool whether distribution policy that these data process core is registered is registered with other core
There is identical flag bit.It is distributed policy registration to data receiver core when any one data processes core
Time, data receiver core can process the registered distribution policy of core to data and judge, at more new data
This flag bit of reason core.
2): the number of data packets that this network data processing core had received.This obtains in real time
It is dynamic that each data process core received data, can be used to carry out subsequent network analysis.
When data receiver verification network data is distributed judging, the packet being first depending on receiving is special
Levying, the registration distribution policy utilizing each data to process core judges, traversal finds and meets this data
The data of bag feature process core.What if data processed core registration is can sharing policy, then directly by table
The process core mark correspondence position position of the relief area in this buffer structure described in 1, updates corresponding sending out
Give the time that data process core message, then send a message to data and process core.Described disappears
Breath includes packet address in the buffer and buffer size.
Process after core when data receiver core determines the data of current data packet, use corresponding multinuclear or
The message sending strategy of many-core flush bonding processor processes core to each data and carries out message transmission, message
Include the buffer address of pending data, the content such as buffer size.It is disposed when data process core
After buffering, need the core mark that processes of relief area is neutralized the bit clearing that this process verification is answered.
If the distribution policy that multiple data process core is registered is identical, data receiver core is according to each data
Process processing data packets state and number of data packets in core, pending packet is carried out weight distribution
Calculate, process core to multiple data packet delivery according to weight and process simultaneously.
It is, for example possible to use analytic hierarchy process (AHP) carries out decision-making, processed the number of core by comprehensive analytical data
According to diversities such as bag processing speed, the number of pending packet, and the sizes of pending packet
Can relevant parameter, construct multilevel iudge matrix two-by-two, by with method, minimum angle-off set or feature to
The different pieces of information of asking for such as mensuration processes the weight of core, by comparing weighted value, it is judged that pending packet
The data being sent to are processed core.
If data process core registration be non-sharing policy and also multiple data process core have registered with
During a kind of distribution policy, need simultaneously according to data process the last packet that core sends time
Between, the number of data packets that has been received by of the process state of packet and this core comprehensively judge,
Carry out purpose data and process the selection of core, core can be processed with multiple data and process simultaneously.
The beneficial effects of the present invention is:
(1) present invention propose network data cache management and the autgmentability of network data tactical management
Very strong, go for current most of multinuclear or many-core flush bonding processor, major part can be met
Network packet detecting application demand.
(2) in the present invention, the process of network data processing verification data achieves zero-copy, is conducive to
The lifting of processing speed.And the same network packet of verification can be processed with multiple data and carry out parallel
Collaborative process.
Accompanying drawing explanation
Fig. 1 is the entire block diagram of the present invention;
Fig. 2 is registration and the flow chart of data processing figure that in the present invention, data process core;
Fig. 3 is the flow chart of data processing figure of data receiver core in the present invention;
Fig. 4 is the Snort intruding detection system block diagram of parallelization in the present invention;
Fig. 5 is the basic flow sheet using the present invention to carry out Snort intrusion detection realization.
Detailed description of the invention
Below by detailed description of the invention, the present invention will be described in detail.
The present invention is that a kind of network packet based on multinuclear or many-core flush bonding processor receives management
With distribution processing method.Fig. 1 show the entire block diagram of the present invention, is divided into the network hardware, data to connect
Receive core, data process core and four, shared drive region module.In figure: 1 represents data receiver caryogamy
Put network hardware equipment;2 represent data receiver cores carry out network data receive deposit buffering distribution and
Management;3 represent that data process core and carry out policy registration to data receiver core;4 represent data receiver core
Receiving after the data packet header information of hardware device, from internal memory, finding suitably buffering
District, transfers the destination of entire data using its address as network hardware equipment;5 represent the network hardware
Equipment sends message to show that data receiver completes to data receiver core;6 represent data receiver cores according to
Distribution policy configuration information processes core to corresponding data and sends message, comprises data buffer zone in message
Address, show currently have complete data to be received and etc. pending;7 represent that data process core and read
Data in corresponding address relief area specifically process.
In the present invention, multinuclear or many-core flush bonding processor use Tile64 polycaryon processor.This processor
It is integrated with 64 tile on a single chip, 192BOPs can be provided (per second with the power consumption of the highest 23W
1000000000 operations) disposal ability, be mainly directed towards network processes, multimedia, information security, wireless
The built-in fields such as communication.Tile64 is a novel polycaryon processor, solves high disposal simultaneously
The problem of performance, flexible programmable and power supply power consumption, and for network application demand growth with
Feasible bridge has been erected between the performance that existing processor can bring.
In the present invention, the main process of data manipulation is as follows: data receiver core is first to the network hardware
Equipment Transfer Parameters, configuration network bindings equipment, it is primarily referred to as the configuration of network interface card hardware effort pattern;
After hardware device configuration, in data receiver exclusive verification shared drive region, network data receives and deposits
Put relief area specifically to distribute, according to actual application demand, be assigned as different size of many
Plant relief area, and it is managed;Subsequently, data process core according to certain strategy according to or
Application demand is distributed policy registration to data receiver core, can specify in the process and be sent to this
Packet feature on registration core, including type of data packet, hardware header information type, port and
Other information etc.;After policy registration, data receiver core according to receiving the information of data packet header,
From internal memory, find suitably buffering, its address is carried out partial data transmission as network hardware equipment
Destination;After network hardware equipment completes data transmission, send message to data receiver core and show
Data receiver is complete;After data receiver core receives the completion message of network hardware equipment, according to respectively
Individual data process the distribution policy configuration information of core and (wrap in message to corresponding data process core transmission message
Buffer address containing receiving pending data), show currently to have event;Final data process core according to
The message of data receiver core, the data read in corresponding address relief area specifically process.
In the present invention, it is divided into data receiver core according to function and data process core.Wherein at data
The concrete flow chart of data processing of reason core is as shown in Figure 2.Data process core and connect with data firstly the need of setting up
Receiving the communication of core, data process core and could send message, registration point to data receiver core on this basis
Sending out strategy, after distribution policy succeeds in registration, data process core and enter waiting state, until data connect
Receipts core is sent to message and shows currently to have event, i.e. has pending data buffering, at network data
The message that reason core sends according to data receiver core, obtains data buffering and processes, after being disposed,
Sending message to data receiver core again and show that data are disposed, above-mentioned is that the most complete data process
The data handling procedure of core.
And the handling process of data receiver core is as shown in Figure 3.Data receiver core upon actuation, first needs
Want configuration network bindings module, including the configuration to network interface card hardware effort pattern, then should according to reality
By demand buffering is assigned as 256 bytes, 512 bytes, 1024 bytes, 1536 bytes, 2048
Byte, 4096 bytes and 10240 bytes.Then data receiver core enters the state waited for the arrival of news.As
Fruit receives the registration message processing core from data, i.e. according to message request, and dividing of location registration process core
Send out strategy, registered content is updated simultaneously.Connect to data when any one data processes core
When receipts core is distributed policy registration, data receiver core all can process core registered distribution plan to data
Slightly judge, update each flag bit processing core.If received from network hardware equipment
About the information of data packet header, after it is analyzed, carry out strategy judgement, from relief area
Choose suitably buffering, carry out DMA configuration to network hardware equipment simultaneously.If receive from
The message being transmitted about packet of network hardware equipment, first updates relief area and distribution policy
Entry, then processes core to data and sends message, show currently there is pending packet.
Management and distribution is received in above-mentioned network packet based on multinuclear or many-core flush bonding processor
On the basis of processing method, it is possible to achieve the Snort intrusion detection of parallelization, its system block diagram such as figure
Shown in 4.Snort program is operated on multiple process core, for number only by simply replicating
Need program is carried out following two special handling according to the restriction of dependence:
1, eliminating global data to rely on, each data process and are held as a process by Snort on core
OK, the data privacy feature of each process can solve global data Dependence Problem.Simultaneously by Snort
Processing core as independent process and data and carry out map bindings, this is to obtain parallel capture storehouse
The precondition of Libpcap data distribution.
2, eliminate file resource to rely on, meeting log hereof in Snort program operation process,
When multiple data process verification identical file operates, easily bring serialization problem.According to data
Process core and there is uniquely identified feature, journal file is bound with the mark that data process core,
The most each Snort can have respective journal file, thus solves asking of file resource dependence
Topic.
Intrusion detection process prescription based on Snort system architecture is as follows: first, is carrying out network
The network packet produced during invasion is excavated, and finds out the rule with the network packet attacking character
Then feature;Then, the raw network data bag meeting these rules is examined in intruding detection system
Survey the knowledge base of engine;Finally, in real time express network data are carried out rule match, just once mating
Really being considered as network intrusions to produce, notice output module processes accordingly at once.According to each portion
Divide execution number of times system to be run and be divided into two stages.First stage is the initialization of system, accurate
The standby rear first stage that work performs to terminate, and sends out unless there are phenomenons such as the injection of new regulation or exceptions
Raw, otherwise the first stage will not perform again.In this stage, it is initial that system mainly completes global data
Change, rule file parsing, plug-in registration, the structure generation of rule tree, Network Data Capturing initialize
Deng work.Second stage is that system detects in real time, performs along with the arrival of new data circulates.At this
In the stage, complete the reception of network packet, data parsing, pretreatment system main loop, enter
Invade the work such as behavioral value and warning output.The basic procedure that system is run is as shown in Figure 5.
Snort system, after the first stage completes, enters second stage circular wait and processes packet.
System finishing condition mainly has two: one to be that user specifies detection bag quantity, and resolved detection can be along with
The reception circulation of new network data performs, until having detected the packet specified number;Two is that user does not has
Having appointment detection data bulk, resolved detection module acquiescence is processed by individual data bag, until being
Stop after the generation of system End Event.After having detected a packet, all signal event can be entered every time
Row checks, the renewal judgement etc. performing new regulation operates, in order to timely respond to demand.
Through above-mentioned realization, can by Snort parallel running on multinuclear or many-core embedded platform,
It is not only able to promote the performance of detecting system, and makes system have the strongest extensibility.
Claims (7)
1., based on multinuclear or a processing method of network data packets for many-core flush bonding processor, it is special
Levy and be, including:
1) core in multinuclear or many-core flush bonding processor is divided into data receiver core and data process
Core, described data receiver verification shared drive region carries out Buffer allocation, and data process core to
Described data receiver core is distributed policy registration, determines that each data process core number to be dealt with
According to bag feature;
Each data process core can only register a distribution policy, and same distribution policy can be the most multiple
Data process core registration;Described distribution policy includes data pack protocol strategy, packet MAC ground
Location strategy, IP the address Policy and packet port policy;
When each data process core is distributed policy registration, data receiver core judges that these data process core
Whether the distribution policy of request is that other data process the registered distribution policies of core, if registered and
Needing to process core with other data to share, the shared flag bit that each data process core is carried out more
Newly;
2) data receiver core is according to the data packet header information received from the network hardware, is deposited by packet
Put to corresponding relief area;
3) data receiver core processes, according to data, the distribution policy that core is registered, at described data
Reason core sends message, and described data process core according to described message, the data in reading relief area
Bag processes, and sends process state information to described data receiver core.
2. as claimed in claim 1 based on multinuclear or the network packet of many-core flush bonding processor
Processing method, it is characterised in that described multinuclear or many-core flush bonding processor are at isomorphism or isomery
Reason device, the quantity of described core is at least 8, wherein, the quantity of described data receiver core be 1 or
Multiple.
3. as claimed in claim 2 based on multinuclear or the network packet of many-core flush bonding processor
Processing method, it is characterised in that in step 1) in, the size of described relief area be 256 bytes,
512 bytes, 1024 bytes, 1536 bytes, 2048 bytes, 4096 bytes or 10240 bytes.
4. as claimed in claim 3 based on multinuclear or the network packet of many-core flush bonding processor
Processing method, it is characterised in that the quantity of described relief area is multiple, in step 3) in, described
Data process nuclear energy and check the physical address of each relief area.
5. as claimed in claim 1 based on multinuclear or the network packet of many-core flush bonding processor
Processing method, it is characterised in that described step 2) in, described packet feature includes data
Packet type, hardware header information type and port information.
6. as claimed in claim 1 based on multinuclear or the network packet of many-core flush bonding processor
Processing method, it is characterised in that described message includes packet address in the buffer and buffering
Size.
7. as claimed in claim 6 based on multinuclear or the network packet of many-core flush bonding processor
Processing method, it is characterised in that if multiple data process the distribution policy registered of core identical time,
Described step 3) in, data receiver core processes processing data packets state sum in core according to each data
According to bag number, pending packet is carried out weight distribution and calculates, according to weight by packet delivery
Process core to multiple data to process simultaneously.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310365607.5A CN103441952B (en) | 2013-08-20 | 2013-08-20 | Based on multinuclear or the processing method of network data packets of many-core flush bonding processor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310365607.5A CN103441952B (en) | 2013-08-20 | 2013-08-20 | Based on multinuclear or the processing method of network data packets of many-core flush bonding processor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103441952A CN103441952A (en) | 2013-12-11 |
CN103441952B true CN103441952B (en) | 2016-10-05 |
Family
ID=49695618
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310365607.5A Active CN103441952B (en) | 2013-08-20 | 2013-08-20 | Based on multinuclear or the processing method of network data packets of many-core flush bonding processor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103441952B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105589829A (en) * | 2014-09-15 | 2016-05-18 | 华为技术有限公司 | Data processing method based on multi-core processor chip, device and system |
CN104639460A (en) * | 2015-02-03 | 2015-05-20 | 重庆邮电大学 | High-speed network data packet parallel receiving method based on many-core processor |
CN105991755B (en) * | 2015-05-21 | 2019-03-15 | 杭州迪普科技股份有限公司 | Service message distribution method and device |
CN113138711B (en) * | 2020-01-20 | 2023-11-17 | 北京希姆计算科技有限公司 | Storage management device and chip |
CN112650705B (en) * | 2020-12-31 | 2024-08-20 | 清华大学 | Route control method and artificial intelligent processor |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101562544A (en) * | 2008-04-17 | 2009-10-21 | 浩通科技(深圳)有限公司 | Data packet generator and data packet generating method |
CN102301664A (en) * | 2011-07-20 | 2011-12-28 | 华为技术有限公司 | Method and device for dispatching streams of multicore processor |
CN103166842A (en) * | 2011-12-13 | 2013-06-19 | 百度在线网络技术(北京)有限公司 | Message generation method based on multi-core platform and generation device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110153982A1 (en) * | 2009-12-21 | 2011-06-23 | Bbn Technologies Corp. | Systems and methods for collecting data from multiple core processors |
-
2013
- 2013-08-20 CN CN201310365607.5A patent/CN103441952B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101562544A (en) * | 2008-04-17 | 2009-10-21 | 浩通科技(深圳)有限公司 | Data packet generator and data packet generating method |
CN102301664A (en) * | 2011-07-20 | 2011-12-28 | 华为技术有限公司 | Method and device for dispatching streams of multicore processor |
CN103166842A (en) * | 2011-12-13 | 2013-06-19 | 百度在线网络技术(北京)有限公司 | Message generation method based on multi-core platform and generation device |
Also Published As
Publication number | Publication date |
---|---|
CN103441952A (en) | 2013-12-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102659439B1 (en) | Naming and Blockchain Recording for the Internet of Things | |
CN103441952B (en) | Based on multinuclear or the processing method of network data packets of many-core flush bonding processor | |
CN102739473B (en) | Network detecting method using intelligent network card | |
CN100425025C (en) | Security system and method using server security solution and network security solution | |
CN101610264B (en) | Firewall system, safety service platform and firewall system management method | |
CN102904729B (en) | The intelligent acceleration network card of more applications is supported according to agreement, port shunt | |
CN103875214A (en) | Intelligent phy with security detection for ethernet networks | |
SA515360321B1 (en) | Based discovery engine configurations for neighborhood aware wi-fi networks | |
CN101964749A (en) | Message retransmission method and system based on multi-core architecture | |
CN105917632A (en) | A method for scalable distributed network traffic analytics in telco | |
CN106453474A (en) | Network transfer of large files in unstable network environments | |
CN105282169A (en) | DDoS attack warning method and system based on SDN controller threshold | |
CN101997700A (en) | Internet protocol version 6 (IPv6) monitoring equipment based on deep packet inspection and deep flow inspection | |
CN102833336A (en) | Data sub-packet processing method in separate distributed information acquisition and concurrent processing system | |
CN104821924A (en) | Network data packet processing method and apparatus, and network processing device | |
CN103988478A (en) | Intelligent connectors integrating magnetic modular jacks and intelligent physical layer devices | |
CN102664815A (en) | Load sharing method, device and system for message traffic | |
KR101679573B1 (en) | Method and apparatus for service traffic security using dimm channel distribution multicore processing system | |
CN111865996A (en) | Data detection method and device and electronic equipment | |
CN109729059A (en) | Data processing method, device and computer | |
CN102457543A (en) | Wireless hydrology monitoring system based on ZigBee and GPRS (General Packet Radio Service) | |
CN109981596A (en) | A kind of host external connection detection method and device | |
Wang et al. | Internet of things | |
CN101635639B (en) | Network connection tracing method and system thereof | |
Dong et al. | [Retracted] Design of IoT Gateway for Crop Growth Environmental Monitoring Based on Edge‐Computing Technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210114 Address after: 311200 room b1-3-034, No. 198, Qidi Road, economic and Technological Development Zone, Xiaoshan District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou purevision Technology Co.,Ltd. Address before: 710071 Xi'an Electronic and Science University, 2 Taibai South Road, Shaanxi, Xi'an Patentee before: XIDIAN University |
|
TR01 | Transfer of patent right |