CN107147635A - The protocol analysis processing method and system for significantly improving the up file data of magnanimity based on multithreading - Google Patents
The protocol analysis processing method and system for significantly improving the up file data of magnanimity based on multithreading Download PDFInfo
- Publication number
- CN107147635A CN107147635A CN201710299966.3A CN201710299966A CN107147635A CN 107147635 A CN107147635 A CN 107147635A CN 201710299966 A CN201710299966 A CN 201710299966A CN 107147635 A CN107147635 A CN 107147635A
- Authority
- CN
- China
- Prior art keywords
- file
- packet
- sub
- thread
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/22—Parsing or analysis of headers
-
- 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
- G06F9/461—Saving or restoring of program or task context
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of protocol analysis processing method and system for significantly improving the up file data of magnanimity based on multithreading, its method comprises the following steps：S1：The up file of user behavior data is obtained from server；S2：Host process generates multiple subprocess, and each subprocess generates multiple father's threads；S3：Each father's thread is decompressed and decryption processing operation to single up file respectively；S4：Each father's thread generates multiple sub-line journeys, and dissection process is carried out to the packet in up file by sub-line journey.Advantage is：The extraction of protocol data fields is significantly improved, shortens the processing time of up file, efficiency is improved.
Description
Technical field
Computer realm of the present invention, more particularly to a kind of association for significantly improving the up file data of magnanimity based on multithreading
Discuss analyzing and processing method and system.
Background technology
At present, the processing procedure of the up file of report is wrapped to the http user behavior datas by K2 routers includes solution
Pressure, three processes of decryption and parsing, wherein the preservation form of up file is as shown in figure 1, legacy data processing framework such as Fig. 2
It is shown, these three processes use single node multithreading, each thread be responsible for a up file processing mode be
Circular order processing, and have up to ten million packets in each up file, the processing mode of each packet is identical, whenever
One thread is completed after the decompression decryption oprerations of a up file, in the up file to each packet (PACKET)
Processing use sequential processes, analyzing efficiency is extremely low.
In order to solve the above-mentioned technical problem, people have carried out long-term exploration, and such as Chinese patent discloses a kind of network
Packet load equilibrium and pre-parsed method [application number：CN201510535316.5], build on a many-core server, have
Body includes 1 exchange chip and 2 multinuclear programmable, intelligent bag engines, abbreviation MPIPE；Each MPIPE corresponds to 1 respectively to be had
The TILERACPU of 36 cores；Characterized in that, specifically including following steps：Step 1: configuration exchanges core under many-core server
Piece；The physical port of exchange chip is divided into two groups, and each group corresponds to 1 MPIPE respectively, from the corresponding things of each MPIPE
Optional composition logic port in port is managed, the binding of logic port is carried out by trunk orders；Step 2: the number of input
According to bag after the external interface XGBE of exchange chip enters, 2 MPIPE are averagely assigned to；Packet is patrolled by exchange chip
Collect behind port, if the purpose IP of packet is identical with source IP, by packet delivery to same physical port, and then be forwarded to
The corresponding MPIPE of physical port；Step 3: each MPIPE forwards a packet to data on corresponding TILERACPU, line number of going forward side by side
According to bag pre-parsed；Step 4: calling pthread_create built-in functions to create 36 processing data packets on each TILERACPU
Thread；Step 5: binding a TILERACPU cores respectively for each processing data packets thread；Step 6: by the pre- solution of packet
Analysis result is distributed to corresponding processing data packets thread；Configure the hash algorithm of logic port, for identical purpose IP and
The packet of source IP, calculates the id values of packet, is judged according to id values, the packet of identical id values is transferred into the same of binding
Individual processing data packets thread；Step 7: 36 processing threads are respectively by calling built-in function gxio_mpipe_iqueue_try_
Peek received data packets and pre-parsed result is obtained, preserve source IP and purpose IP.
For another example, the balanced shunt method [application number of a kind of multithread analyzing：CN201610761812.7], specific method
For N number of thread, from thread 0- (N-1), to be followed successively by each thread and distributing a sequence of threads train value ThreadIndexID；Institute
It is the integer more than 1 to state N；The each thread of thread is used for the packet that analysis of allocated is obtained；An array space is created, should
Array space includes N number of array, corresponds N number of thread；That array corresponding to each thread is worked as depositing the thread
The pending data amount check such as preceding；When delivering a packet to a thread, used in that array corresponding to the thread
In deposit the pending data amount check values such as the thread is current from plus；When the complete packet of Thread Analysis, it is used in array
The pending data amount check values such as the thread is current are deposited from subtracting；Packet capture thread collects packet, according to tcp/ip
The specification of agreement, obtains the quaternary group information of each packet, and then obtains the cryptographic Hash of each packet；Use obtained Kazakhstan
Uncommon value obtains packet thread sequential value ThreadIndex of each packet on thread with analysis number of threads modulus；Institute
State packet thread sequential value ThreadIndex and indicate the actual thread that the packet should be assigned to, the actual thread
Sequence of threads train value ThreadIndexID is equal to packet thread sequential value ThreadIndex；Defining one is used for uniform divided flows
Hash table, using the quaternary group information of packet as Hash table key values, for inquiring about, by the actual distribution of the packet
Sequence of threads train value ThreadIndexID writes as the value values of Hash table；
The specific method step of allocation of packets is：Whether S1, the quaternary group information of inquiry current data packet are in Hash table
In, if it is, its corresponding value value in Hash table is found, actually should corresponding thread so as to find the packet
Sequential value ThreadIndexID, is distributed directly to the thread etc. pending by the packet；If it is not, then into next step；S2
The packet thread sequential value ThreadIndex of current data packet is inquired about, is read from array space pending corresponding to it
Packet number be a most threads, if not being then distributed directly to thread；If it is, into next step；
S2, check that the packet is first packet of session, if it is not, then by the allocation of packets to thread；If
It is then by the allocation of packets to the minimum thread of the pending data amount check such as current, and the four-tuple of the packet to be believed
Breath is recorded in Hash table as key values, the sequence of threads train value ThreadIndexID of actual distribution as value values.
Although above-mentioned two technical scheme improves the efficiency of parsing to a certain extent, disclosed in the first string
It is that the pre-parsed result of packet is distributed to corresponding processing data packets thread, its technical scheme is still to net using single thread
Network packet is parsed；Although second scheme solve the problem of allocation of packets is uneven, but analyzing efficiency increases
Insufficient amplitude it is big, still have much room for improvement.
The content of the invention
Regarding the issue above, the present invention provides it is a kind of can improve dissection process speed based on multithreading
Significantly improve the protocol analysis processing method of the up file data of magnanimity；
It is another object of the present invention to composed a piece of writing in view of the above-mentioned problems, providing a kind of significantly improving based on multithreading in magnanimity
The protocol analysis processing system of number of packages evidence.
To reach above-mentioned purpose, present invention employs following technical proposal：
The protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading of the present invention, including with
Lower method：
S1：The up file of user behavior data is obtained from server；
S2：Host process generates multiple subprocess, and each subprocess generates multiple father's threads；
S3：Each father's thread is decompressed and decryption processing operation to single up file respectively；
S4：Each father's thread generates multiple sub-line journeys, and dissection process is carried out to the packet in up file by sub-line journey.
By above-mentioned technical proposal, up file is passed through and decompresses the packet delivery with decryption processing to son in father's thread
Thread carries out dissection process, significantly improves protocol analysis speed.
In the above-mentioned protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading, in step
In rapid S4, the method that sub-line journey is parsed to the packet in up file includes：
S4-1：After the decryption of father's thread one up file of completion and decompression operations, one is obtained from the up file
Individual packet；
S4-2：Whether be sky packet, if packet is non vacuum data bag if judging the packet obtained in S4-1 steps,
Allocation of packets is then given to the sub-line journey for being currently at idle condition；
S4-3：Dissection process is carried out to packet by the sub-line journey of received data packet.
It is described in the above-mentioned protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading
Server in the up file of user behavior data be the up file data that reports of router.
In the above-mentioned protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading, when one
Individual sub-line journey carries out being in busy condition when dissection process to a packet, new packet is not received, and work as
One sub-line journey is completed to returning to idle condition after the dissection process of a packet, waits new packet to be received.
It is described in the above-mentioned protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading
Sub-line journey the protocol data fields extraction process to corresponding data bag is included to the dissection process of packet.
In the above-mentioned protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading, in step
In rapid S2, described host process generates at least five subprocess, and each subprocess generates at least 50 father's threads.
In the above-mentioned protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading, in step
In rapid S4, each described father's thread generates at least 50 sub-line journeys.
In the above-mentioned protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading, in step
In rapid S2, described host process generates the subprocess of corresponding number, each subprocess according to the quantity and/or size of up file
Father's thread of corresponding number is generated according to the quantity and/or size of corresponding up file.
In the above-mentioned protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading, in step
In rapid S4, each described father's thread generates the sub-line journey of corresponding number according to the quantity and/or size of corresponding data bag.
A kind of protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading based on multi-thread
The protocol analysis processing system for significantly improving the up file data of magnanimity of journey.
Protocol analysis processing method and system phase of the invention that significantly improve the up file data of magnanimity based on multithreading
There is advantages below compared with prior art：The extraction of protocol data fields is significantly improved, shortens the processing time of up file, carries
High efficiency.
Brief description of the drawings
Fig. 1 is the preservation form of up file；
Fig. 2 is prior art data processing architecture figure；
Fig. 3 is data processing architecture figure of the present invention；
Fig. 4 is the workflow diagram that a pair of up files of the embodiment of the present invention are handled；
Fig. 5 is flow chart of the sub-line journey of the embodiment of the present invention one to resolve packet process.
Embodiment
The present embodiment can be applied to wrap the http user behavior datas by router the processing of the up file of report
Process, the main protocol analysis speed that up file data bag is improved by the way of multi-threading parallel process, is solved existing
Technology uses the low problem of analyzing efficiency caused by sequential processes to up file
The following is the preferred embodiments of the present invention and with reference to accompanying drawing, technical scheme is further described,
But the present invention is not limited to these embodiments.
Embodiment one
As shown in Figure 3 and Figure 4, the protocol analysis of the invention that significantly improve the up file data of magnanimity based on multithreading
Processing method, including following methods：
S1：The up file of user behavior data is obtained from server；
Specifically, the up file of user behavior data is the up file data that router is reported in server.
S2：After the up file of user behavior data is obtained, start host process, many height are generated by host process and entered
Journey, and each subprocess generates multiple father's threads；
S3：Each father's thread is decompressed and decryption processing operation to single up file respectively；
S4：Each father's thread generates multiple sub-line journeys, and dissection process is carried out to the packet in up file by sub-line journey.
And in order to meet decompression, decryption and parsing the need for, it is ensured that the efficiency of foregoing three processes, host process generation
At least five subprocess, each subprocess generates at least 50 father's threads, and each father's thread generates at least 50 sons
Thread.
And in the present embodiment, every time after up file is obtained, when processing up file, fixed of generation
Several subprocess, and fixed number father's thread and the sub-line journey of fixed number, such as, every time in the processing to up file
During, generate five subprocess, five father's threads, and 50 sub-line journeys.
Below to being specifically described in the case where generating five subprocess, five father's threads and 50 sub-line journeys：
Wherein host process is used to receive up file, then gives five subprocess by up file distributing, and subprocess again will
All up file distributings oneself received are decompressed to 50 each following father's threads, father's thread to up file
And decryption processing, generally each up file generates thousands of packets after the decompression and decryption processing of father's thread,
The processing mode of each packet is identical in the prior art, whenever the decompression that a thread completes a up file decrypts behaviour
After work, to using sequential processes to the processing of each packet (PACKET) in the up file, analyzing efficiency is extremely low,
And each father's thread of the present embodiment is after by up file decompression and decryption processing, and by the thousands of of each up file
Individual packet is distributed to 50 sub-line journeys below each, thousands of packets is carried out by 50 sub-line journeys parallel
Processing.
Further, each sub-line journey includes carrying the protocol data fields of corresponding data bag to the dissection process of packet
Take processing.
The present embodiment is by the way of multi-threading parallel process, and the multiple of the protocol analysis speed of raising is equal to parallel processing
Thread Count, and the collection stored number of up file has risen to TB ranks at present, so as to shorten the processing of up file
The effect that time is brought is significant.
Further, as shown in figure 5, in step s 4, the side that sub-line journey is parsed to the packet in up file
Method includes：
S4-1：After the decryption of father's thread one up file of completion and decompression operations, one is obtained from the up file
Individual packet；
Condition monitoring is carried out to sub-line journey, when a sub-line journey carries out dissection process to packet at
In busy condition, new packet is not received, so packet delivery will not be given to this class sub-line journey, and when a sub-line journey
Complete to returning to idle condition after the dissection process of a packet, new packet to be received is waited, from up file acquisition
Packet be distributed to this class be in idle condition sub-line journey, to greatest extent reduce packet queuing time,
As long as available free sub-line journey is present, it becomes possible to receive the parsing task carried out to packet.
S4-2：Whether be sky packet, if packet is non vacuum data bag if judging the packet obtained in S4-1 steps,
Then show that the packet without dissection process, then gives allocation of packets the sub-line journey for being currently at idle condition；
S4-3：Dissection process is carried out to packet by the sub-line journey of received data packet.
The sub-line journey of corresponding received data packet carries out including the dissection process of protocol data fields extraction to the packet,
Now, the sub-line journey externally shows as the task distribution of busy condition, no longer received data packet；
After the completion of to current resolve packet, the sub-line journey be return to idle condition with etc. new packet to be received
Parsing task；
And show the packet when packet not empty packet to pass through dissection process or need not be parsed
Processing, then directly terminate the dissection process process to the packet,
The present embodiment passes through up file to be carried out in father's thread decompression and the packet delivery of decryption processing to sub-line journey
Dissection process, the defect of sequential processes can only be carried out to packet by changing prior art, reached and significantly improved protocol analysis speed
Effect.
Embodiment two
The present embodiment is similar with embodiment one, and difference is, the present embodiment in step s 2, fix by host process generation
The subprocess of number, each subprocess generates father's thread of fixed number.
And in step s 4, each father's thread generates the son of corresponding number according to the quantity and/or size of corresponding data bag
Thread.
The each host process consistent with embodiment one that the present embodiment is used generates the subprocess of fixed number, enters per height
Journey generates father's thread of fixed number again, still, and the sub-line journey number of each father's thread generation of the present embodiment is not fixed, this reality
Apply in example, in order to reach saving space while processing speed is improved, and sub-line journey quantity try one's best be adapted to it is current up
The quantity of the packet of file generated, father's thread generation sub-line journey number be it is variable, below five subprocess of generation, five
It is specifically described in the case of father's thread：
Wherein host process is used to receive up file as embodiment one, while up file distributing is entered to five sons
Journey, all up file distributings that subprocess again receives oneself are to 50 each following father's threads, and father's thread is to upper
Style of writing part is decompressed and decryption processing, and generally each up file generates thousands of after the decompression and decryption processing of father's thread
Up to ten thousand packets, the processing mode of each packet is identical in the prior art, whenever a thread completes a upper style of writing
After the decompression decryption oprerations of part, to being used in the up file to the processing of each packet (PACKET) at order
Reason, analyzing efficiency is extremely low, and each father's thread of the present embodiment obtains several after by up file decompression and decryption processing
Packet, is estimated by load equalizer to the quantity and size of packet, is then existed according to the quantity and size of packet
The sub-line journey of suitable number is generated under corresponding father's thread, for example, when father's thread completes the decryption to a up file
With 500 equal-sized packets have been obtained after decompression processing, then 50 sub-line journeys can be generated, by father's thread by 500
Packet delivery gives 50 sub-line journeys below, now, if each sub-line journey processing is smooth, each sub-line journey meeting
10 packets are handled, now, belong to most perfect condition, until terminating parsing at the last moment, all sub-line journeys are in
Working condition, some resources are not wasted, certainly, and the packet of each up file generated may be many more than 500, each
The size of packet may also can be different, when packet has a variety of size species, then according to packet number
When simultaneously according to the size of packet generate sub-line journey number, such as during being parsed to packet, most start
With 50 sub-line journeys, when terminating soon to resolve packet, there are multiple sub-line journeys to be in idle condition and do not had
Unnecessary packet needs parsing, then automatic release sub-line journey；For another example, when the number of the packet of a up file is few enough
When, then only generate the sub-line journey as packet number；And when a up file has the number of many different sizes
When according to bag, it is also desirable to by the specification of packet in the limit of consideration of generation sub-line journey number, such as refer on one
The specification summation generation sub-line journey of style of writing all packets of part；When the packet number of a up file has substantial amounts of data
When bag, most sub-line journeys can be generated in allowed limits to meet needs.
Certain sub-line journey generation number can also change with the change of some other situation, for example, the up file
Processing speed requirement, system context etc..
The present embodiment can flexibly change the number of sub-line journey according to the size and number of packet, can either improve parsing
Speed, can at utmost save space and further improve resolution speed again.
Embodiment three
The present embodiment is similar with embodiment two, and difference is, the present embodiment in step s 2, fix by host process generation
The subprocess of number；
And each subprocess generates father's thread of corresponding number according to the quantity and/or size of corresponding up file；
And, each described father's thread generates the sub-line of corresponding number according to the quantity and/or size of corresponding data bag
Journey.
The each host process consistent with embodiment one that the present embodiment is used generates the subprocess of fixed number, still, this
The number of each subprocess generation father's thread of embodiment is not fixed, and the sub-line journey number of each father's thread generation is not also fixed,
In the present embodiment, in order to reach saving space while processing speed is improved, and father's thread quantity try one's best be adapted to it is current
The quantity of up file, and the quantity of sub-line journey are tried one's best the quantity of the packet for being adapted to current up file generated, subprocess
Generation father's number of threads is variable, and father's thread generation sub-line journey number is also variable.
The present embodiment can not only flexibly change the number of sub-line journey according to the size and number of packet, and being capable of root
Change the number of father's thread according to the quantity and flexible in size of up file, resolution speed can either be improved, again can be at utmost
Save space and further improve resolution speed.
Example IV
The present embodiment is similar with embodiment three, and difference is, the host process of the present embodiment generates the number of subprocess
It is also variable, is equally that the size and number of based on context part is changed, generates the root of subprocess number herein certainly
, can also be according to other environment according to the size and number for being not limited to up file.
Embodiment five
Present embodiment discloses a kind of protocol analysis for significantly improving the up file data of magnanimity processing based on multithreading
The protocol analysis processing system for significantly improving the up file data of magnanimity based on multithreading of method.
Specific embodiment described herein is only to spirit explanation for example of the invention.Technology neck belonging to of the invention
The technical staff in domain can be made various modifications or supplement to described specific embodiment or be replaced using similar mode
Generation, but without departing from the spiritual of the present invention or surmount scope defined in appended claims.
Although more having used the terms such as host process, subprocess, father's thread, sub-line journey herein, it is not precluded from using
The possibility of other terms.It is used for the purpose of more easily describing and explaining the essence of the present invention using these terms；Them
Any additional limitation is construed to all to disagree with spirit of the present invention.
Claims (10)
1. a kind of protocol analysis processing method for significantly improving the up file data of magnanimity based on multithreading, it is characterised in that
Comprise the following steps：
S1：The up file of user behavior data is obtained from server；
S2：Host process generates multiple subprocess, and each subprocess generates multiple father's threads；
S3：Each father's thread is decompressed and decryption processing operation to single up file respectively；
S4：Each father's thread generates multiple sub-line journeys, and dissection process is carried out to the packet in up file by sub-line journey.
2. the protocol analysis processing side according to claim 1 that significantly improve the up file data of magnanimity based on multithreading
Method, it is characterised in that in step s 4, the method that sub-line journey is parsed to the packet in up file includes：
S4-1：After the decryption of father's thread one up file of completion and decompression operations, a number is obtained from the up file
According to bag；
S4-2：Whether be sky packet, if packet is non vacuum data bag if judging the packet obtained in S4-1 steps, will
Allocation of packets gives the sub-line journey for being currently at idle condition；
S4-3：Dissection process is carried out to packet by the sub-line journey of received data packet.
3. at the protocol analysis according to claim 1 or 2 that significantly improve the up file data of magnanimity based on multithreading
Reason method, it is characterised in that the up file of user behavior data is the up file that router is reported in described server
Data.
4. the protocol analysis processing side according to claim 2 that significantly improve the up file data of magnanimity based on multithreading
Method, it is characterised in that be in busy condition when a sub-line journey carries out dissection process to a packet, do not connect
New packet is received, and when returning to idle condition after the dissection process that a sub-line journey is completed to a packet, waits waiting
Receive new packet.
5. the protocol analysis processing side according to claim 2 that significantly improve the up file data of magnanimity based on multithreading
Method, it is characterised in that described sub-line journey includes carrying the protocol data fields of corresponding data bag to the dissection process of packet
Take processing.
6. the protocol analysis processing side according to claim 2 that significantly improve the up file data of magnanimity based on multithreading
Method, it is characterised in that in step s 2, described host process generates at least five subprocess, each subprocess generation at least five
Ten father's threads.
7. the protocol analysis processing side according to claim 6 that significantly improve the up file data of magnanimity based on multithreading
Method, it is characterised in that in step s 4, each described father's thread generates at least 50 sub-line journeys.
8. at the protocol analysis according to claim 1 or 2 that significantly improve the up file data of magnanimity based on multithreading
Reason method, it is characterised in that in step s 2, described host process generates corresponding according to the quantity and/or size of up file
The subprocess of number, each subprocess generates father's thread of corresponding number according to the quantity and/or size of corresponding up file.
9. the protocol analysis processing side according to claim 8 that significantly improve the up file data of magnanimity based on multithreading
Method, it is characterised in that in step s 4, each described father's thread generates phase according to the quantity and/or size of corresponding data bag
Answer the sub-line journey of number.
10. it is a kind of based on significantly improving the up file data of magnanimity based on multithreading described in claim 1-9 any one
Protocol analysis processing method the protocol analysis processing system for significantly improving the up file data of magnanimity based on multithreading.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710299966.3A CN107147635A (en) | 2017-04-28 | 2017-04-28 | The protocol analysis processing method and system for significantly improving the up file data of magnanimity based on multithreading |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710299966.3A CN107147635A (en) | 2017-04-28 | 2017-04-28 | The protocol analysis processing method and system for significantly improving the up file data of magnanimity based on multithreading |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107147635A true CN107147635A (en) | 2017-09-08 |
Family
ID=59774478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710299966.3A Pending CN107147635A (en) | 2017-04-28 | 2017-04-28 | The protocol analysis processing method and system for significantly improving the up file data of magnanimity based on multithreading |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107147635A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108196956A (en) * | 2017-12-28 | 2018-06-22 | 郑州云海信息技术有限公司 | A kind of NAS service nodes realize the method and system of NAS services |
| CN109783255A (en) * | 2019-01-07 | 2019-05-21 | 中国银行股份有限公司 | Data parse diostribution device and high concurrent data processing method |
| CN110322391A (en) * | 2019-07-08 | 2019-10-11 | 上海天诚比集科技有限公司 | Visual alarm affair analytical method based on multithreading |
| CN112905324A (en) * | 2021-02-10 | 2021-06-04 | 山东英信计算机技术有限公司 | Decompression method, system and medium based on circuit state |
| CN113452708A (en) * | 2021-06-28 | 2021-09-28 | 苏州科达科技股份有限公司 | Data analysis method, system, data server and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101005370A (en) * | 2006-01-16 | 2007-07-25 | 北京速能数码网络技术有限公司 | Dynamic copying and sending device of asymmetric cross net section multiple path data stream |
| CN101196832A (en) * | 2007-12-29 | 2008-06-11 | 北京航空航天大学 | Resource proxy machine facing illumination variant equipment |
| CN101217520A (en) * | 2007-12-29 | 2008-07-09 | 华为技术有限公司 | A wireless packet domain gateway performance self-adapting method and device |
| CN101359333A (en) * | 2008-05-23 | 2009-02-04 | 中国科学院软件研究所 | Parallel data processing method based on latent dirichlet allocation model |
| CN101957780A (en) * | 2010-08-17 | 2011-01-26 | 中国电子科技集团公司第二十八研究所 | Resource state information-based grid task scheduling processor and grid task scheduling processing method |
| CN103020258A (en) * | 2012-12-21 | 2013-04-03 | 中国科学院计算机网络信息中心 | Method and system for training LDA (latent dirichlet allocation) model by multi-core cluster |
| CN103605568A (en) * | 2013-10-29 | 2014-02-26 | 北京奇虎科技有限公司 | Multithread management method and device |
| CN104850456A (en) * | 2015-05-27 | 2015-08-19 | 苏州科达科技股份有限公司 | Multi-process decoding method and multi-process decoding system |
| CN105978968A (en) * | 2016-05-11 | 2016-09-28 | 山东合天智汇信息技术有限公司 | Real-time transmission processing method, server and system of mass data |
-
2017
- 2017-04-28 CN CN201710299966.3A patent/CN107147635A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101005370A (en) * | 2006-01-16 | 2007-07-25 | 北京速能数码网络技术有限公司 | Dynamic copying and sending device of asymmetric cross net section multiple path data stream |
| CN101196832A (en) * | 2007-12-29 | 2008-06-11 | 北京航空航天大学 | Resource proxy machine facing illumination variant equipment |
| CN101217520A (en) * | 2007-12-29 | 2008-07-09 | 华为技术有限公司 | A wireless packet domain gateway performance self-adapting method and device |
| CN101359333A (en) * | 2008-05-23 | 2009-02-04 | 中国科学院软件研究所 | Parallel data processing method based on latent dirichlet allocation model |
| CN101957780A (en) * | 2010-08-17 | 2011-01-26 | 中国电子科技集团公司第二十八研究所 | Resource state information-based grid task scheduling processor and grid task scheduling processing method |
| CN103020258A (en) * | 2012-12-21 | 2013-04-03 | 中国科学院计算机网络信息中心 | Method and system for training LDA (latent dirichlet allocation) model by multi-core cluster |
| CN103605568A (en) * | 2013-10-29 | 2014-02-26 | 北京奇虎科技有限公司 | Multithread management method and device |
| CN104850456A (en) * | 2015-05-27 | 2015-08-19 | 苏州科达科技股份有限公司 | Multi-process decoding method and multi-process decoding system |
| CN105978968A (en) * | 2016-05-11 | 2016-09-28 | 山东合天智汇信息技术有限公司 | Real-time transmission processing method, server and system of mass data |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108196956A (en) * | 2017-12-28 | 2018-06-22 | 郑州云海信息技术有限公司 | A kind of NAS service nodes realize the method and system of NAS services |
| CN109783255A (en) * | 2019-01-07 | 2019-05-21 | 中国银行股份有限公司 | Data parse diostribution device and high concurrent data processing method |
| CN109783255B (en) * | 2019-01-07 | 2021-02-23 | 中国银行股份有限公司 | Data analysis and distribution device and high-concurrency data processing method |
| CN110322391A (en) * | 2019-07-08 | 2019-10-11 | 上海天诚比集科技有限公司 | Visual alarm affair analytical method based on multithreading |
| CN110322391B (en) * | 2019-07-08 | 2023-07-11 | 上海天诚比集科技有限公司 | Video alarm event analysis method based on multithreading |
| CN112905324A (en) * | 2021-02-10 | 2021-06-04 | 山东英信计算机技术有限公司 | Decompression method, system and medium based on circuit state |
| CN113452708A (en) * | 2021-06-28 | 2021-09-28 | 苏州科达科技股份有限公司 | Data analysis method, system, data server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107147635A (en) | The protocol analysis processing method and system for significantly improving the up file data of magnanimity based on multithreading | |
| CN108833299B (en) | Large-scale network data processing method based on reconfigurable switching chip architecture | |
| CN103905311B (en) | Flow table matching method and device and switch | |
| CN108809854B (en) | Reconfigurable chip architecture for large-flow network processing | |
| CN105553977B (en) | Processing, sending method and the device of request message | |
| CN1875585B (en) | Dynamic unknown L2 flooding control with MAC limits | |
| CN103412786B (en) | High performance server architecture system and data processing method thereof | |
| CN104601696B (en) | Service processing method, service calling system, device and system | |
| CN110768829B (en) | Method for realizing linear increase of traffic analysis service performance based on DPDK | |
| CN106357726B (en) | Load-balancing method and device | |
| CN102656850A (en) | Method for processing a plurality of data and switching device for switching communication packets | |
| CN107800768A (en) | Open platform control method and system | |
| CN104199912B (en) | A kind of method and device of task processing | |
| US11456970B1 (en) | Augmenting data plane functionality with field programmable integrated circuits | |
| CN107241305A (en) | A kind of network protocol analysis system and its analysis method based on polycaryon processor | |
| CN109347745A (en) | A kind of flow table matching process and device based on OpenFlow interchanger | |
| CN106131141B (en) | A kind of distributed type assemblies load balancing parallel dispatch system and method | |
| CN105191212B (en) | A kind of data stream statistics mthods, systems and devices | |
| CN109729021A (en) | A kind of message processing method and electronic equipment | |
| CN107864391A (en) | Video flowing caches distribution method and device | |
| CN103248636B (en) | The system and method downloaded offline | |
| CN108737177A (en) | A kind of implementation method mobile Internet real-time streaming data acquisition and analyzed | |
| CN105099735B (en) | A kind of method and system for obtaining magnanimity more detailed logging | |
| CN108900607A (en) | A kind of processing method, device and the server of SMB agreement request | |
| CN107832149A (en) | A kind of Receive side Scaling circuits for polycaryon processor Dynamic Packet management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: 201616 Shanghai city Songjiang District Sixian Road No. 3666 Applicant after: Shanghai Feixun Data Communication Technology Co., Ltd. Address before: 201616 Shanghai City, Songjiang District Road No. 3666 Applicant before: Shanghai Feixun Data Communication Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| 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: 20170908 |
|
| RJ01 | Rejection of invention patent application after publication |