CN107547417A - A kind of message processing method, device and base station - Google Patents
A kind of message processing method, device and base station Download PDFInfo
- Publication number
- CN107547417A CN107547417A CN201610496288.5A CN201610496288A CN107547417A CN 107547417 A CN107547417 A CN 107547417A CN 201610496288 A CN201610496288 A CN 201610496288A CN 107547417 A CN107547417 A CN 107547417A
- Authority
- CN
- China
- Prior art keywords
- message
- heading
- forwarded
- service
- processing unit
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a kind of message processing method, device and base station, is related to intelligent network communication field, and methods described includes：Network accelerator unit is separated the heading of service message and message body, and preserves heading and message body after separation respectively；The message header processing of the service message of preservation is the heading for message forwarding by processing unit；The processing unit is according to common process mode, the heading for message forwarding and the message body are spliced and forwarded, or, according to distributed processing mode, the heading for message forwarding and the message body are spliced and forwarded using the network accelerator unit.By using network accelerator unit disassociation service message and splicing service message, cpu resource is saved, improves processing and the forward efficiency of service message.
Description
Technical field
The present invention relates to intelligent network communication field, more particularly to a kind of message processing method, device and base station.
Background technology
With the fast development of mobile communication data business, the application of particularly the 5th generation mobile communication technology is also compeled in eyebrow
Eyelash, impact of the big traffic of big data to the processor (Central Processing Unit, CPU) in base station influence also more next
It is bigger.Under this base band big flow scene, the contradiction between CPU disposal abilities and business demand is also more and more obvious, CPU
The excavation of energy and each software developer need the place being especially concerned about, processor is meeting the same of business primary demand
When, further it is also contemplated that the treatment effeciency to service message.
Accelerate in common message with retransmission method, software calculates the message belonging to message using Hash (Hash) algorithm
Type, then the type known to, which is tabled look-up, finds corresponding message and further handles, and also has some to fully rely on hardware device and does
Message classification processing, then transfers to CPU to continue with.
In the case where cpu resource is enough, above-mentioned common method can solve the processing and forwarding of message substantially.But
Under base band big flow scene, cpu resource often turns into bottleneck, therefore the processing of business needs to be distributed to multiple processing units
On (being in most cases CPU), nonetheless, higher requirement is still proposed to the performance of each processing unit.Therefore, it is anxious
The problem of CPU present in base band big flow scene is to Message processing and transfer capability deficiency need to be overcome.
The content of the invention
The technical problem that the technical scheme provided according to embodiments of the present invention solves is CPU processing and E-Packets ability not
The problem of sufficient.
A kind of message processing method provided according to embodiments of the present invention, including：
Network accelerator unit is separated the heading of service message and message body, and preserves the report after separation respectively
Literary head and message body；
The message header processing of the service message of preservation is the heading for message forwarding by processing unit；
The processing unit enters according to common process mode to the heading for message forwarding and the message body
Row splices and forwarded, or, according to distributed processing mode, the message that is used for is forwarded using the network accelerator unit
Heading and the message body spliced and forwarded.
Preferably, described the step of preserving heading and message body after separating respectively, includes：
The heading of the service message after separation is stored in cache area by the network accelerator unit
Domain, the message body of the service message after separation is stored in non-high-speed cacheable memory region.
Preferably, the processing unit is according to common process mode, to the heading for message forwarding and described
Message body is spliced and forwarded, or, according to distributed processing mode, it is used for using the network accelerator unit to described
The heading and the message body of message forwarding are spliced and included the step of forwarding：
The processing unit determines whether the service message needs by the heading of the service message after separation
Handled according to distributed processing mode；
If desired handled according to distributed processing mode, then the processing unit utilizes the network accelerator unit, right
The heading for message forwarding is packaged, and by the heading for being used for message forwarding after encapsulation, is stored in non-high-speed
The message body of cacheable memory region is spliced and forwarded；
Otherwise handled according to common process mode, the processing unit by the heading forwarded for message, be stored in it is non-
The message body of cache area is spliced and forwarded.
Preferably, in addition to：
The business datum descriptor for Service control that the processing unit adds it in the service message is protected
Deposit to the cache area, wherein, in the cache area, the storage of the business datum descriptor is empty
Between and the heading memory space it is separate.
Preferably, the processing unit is according to common process mode, to the heading for message forwarding and described
Message body is spliced and forwarded, or, according to distributed processing mode, it is used for using the network accelerator unit to described
The heading and the message body of message forwarding are spliced and included the step of forwarding：
The processing unit determines whether the service message needs by the heading of the service message after separation
Handled according to distributed processing mode；
If desired handled according to distributed processing mode, then the processing unit utilizes the network accelerator unit, right
The heading for being used for message forwarding is packaged, and by the heading for being used for message forwarding after encapsulation, is stored in and is delayed at a high speed
The business datum descriptor for rushing storage region, the message body for being stored in non-high-speed cacheable memory region are spliced and forwarded；
Otherwise handled according to common process mode, the processing unit by the heading forwarded for message, be stored in height
The business datum descriptor of fast cacheable memory region, the message body for being stored in non-high-speed cacheable memory region are spliced and turned
Hair.
The storage medium provided according to embodiments of the present invention, it stores the program for realizing above-mentioned message processing method.
A kind of message process device provided according to embodiments of the present invention, including：
Network accelerator unit, for the heading of service message and message body to be separated, and message separation respectively
Heading and message body afterwards；
Processing unit, for being the heading for message forwarding by the message header processing of the service message of preservation；
Wherein, the processing unit is according to common process mode, to the heading for message forwarding and the report
Style is spliced and forwarded, or, according to distributed processing mode, using the network accelerator unit, it is used for described
The heading and the message body of message forwarding are spliced and forwarded.
Preferably, the heading of the service message after separation is stored in speed buffering by the network accelerator unit
Storage region, the message body of the service message after separation is stored in non-high-speed cacheable memory region.
Preferably, the processing unit determines the service message by the heading of the service message after separation
Whether need to handle according to distributed processing mode, if desired handled according to distributed processing mode, then added using the network
Fast device unit, the heading for message forwarding is packaged, by the heading for being used for message forwarding after encapsulation, protected
The message body that non-high-speed cacheable memory region be present is spliced and forwarded, and is otherwise handled according to common process mode, will be used for
The heading of message forwarding, the message body for being stored in non-high-speed cacheable memory region are spliced and forwarded.
Preferably, the processing unit is additionally operable to the business for Service control for adding it in the service message
Data descriptor is preserved to the cache area, wherein, in the cache area, the business datum is retouched
State symbol memory space and the heading memory space it is separate.
Preferably, the processing unit determines the service message by the heading of the service message after separation
Whether need to handle according to distributed processing mode, if desired handled according to distributed processing mode, then added using the network
Fast device unit, the heading for message forwarding is packaged, by the heading for being used for message forwarding after encapsulation, protected
The business datum descriptor that cache area be present, the message body for being stored in non-high-speed cacheable memory region are spliced
And forward, otherwise handled according to common process mode, by the heading forwarded for message, be stored in cache area
Business datum descriptor, the message body that is stored in non-high-speed cacheable memory region spliced and forwarded.
The base station provided according to embodiments of the present invention, including above-mentioned message process device.
Technical scheme provided in an embodiment of the present invention has the advantages that：
The embodiment of the present invention saves by using network accelerator unit disassociation service message and splicing service message
Cpu resource, improve processing and the forward efficiency of service message, i.e., can efficient process service message, especially suitable for base band
Big flow scene.
Brief description of the drawings
Fig. 1 is message processing method block diagram provided in an embodiment of the present invention；
Fig. 2 is message process device block diagram provided in an embodiment of the present invention；
Fig. 3 is business multiplied unit structural representation provided in an embodiment of the present invention；
Fig. 4 is business processing flow figure provided in an embodiment of the present invention；
Fig. 5 is across the buffer area message schematic illustration of tissue of chain type provided in an embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing to a preferred embodiment of the present invention will be described in detail, it will be appreciated that described below is excellent
Select embodiment to be merely to illustrate and explain the present invention, be not intended to limit the present invention.
Fig. 1 is message processing method block diagram provided in an embodiment of the present invention, as shown in figure 1, step includes：
Step S101：Network accelerator unit is separated the heading of service message and message body, and is preserved respectively
Heading and message body after separation.
Before step S101 is performed, network accelerator unit is right according to the feature field in the heading of service message
Service message carries out classification processing, the service message of different service types is branched into corresponding queue, so as to follow-up corresponding position
Reason unit is handled.
Step S101 is specifically, network accelerator unit is divided the heading of the service message received and message body
From, and the heading of the service message after separation is stored in cache area, i.e. cache regions, it will separate
The message body of the service message afterwards is stored in non-high-speed cacheable memory region, i.e., non-cache regions.
The present embodiment is directed to big flow service message feature, and business is indifferent to message payload (equivalent to message body), can
To extract heading and message body respectively in receiving terminal, and this data header part resource (equivalent to heading) is configured
For cache regions, accelerate CPU processing.
Step S102：The message header processing of the service message of preservation is the message for message forwarding by processing unit
Head.
Step S103：According to distributed processing mode or common process mode, to the heading for message forwarding
Spliced with the message body, and obtained spliced service message is subjected to forward process.
The processing unit enters according to common process mode to the heading for message forwarding and the message body
Row splices and forwarded, or, according to distributed processing mode, the message that is used for is forwarded using the network accelerator unit
Heading and the message body spliced and forwarded.Specifically, processing unit passes through the service message after separation
Heading, determine whether the service message needs to handle according to distributed processing mode.If desired according to distributed treatment
Mode is handled, then processing unit carries out heading encapsulation, message splicing and forward process using network accelerator unit, further
Say, by the network accelerator unit according to the channel table being pre-created, the encapsulation heading for message forwarding, will seal
The heading for being used for message forwarding after dress, the message body for being stored in non-high-speed cacheable memory region are spliced, and according to envelope
The heading of dress forwards the spliced service message, such as sends to other processing unit processes.If need not according to point
Cloth processing mode processing, then handled according to common process mode, i.e., processing unit by the heading forwarded for message, preserve
Message body in non-high-speed cacheable memory region is spliced, and obtained spliced service message is forwarded, such as
It is forwarded to core net.
Above-mentioned distributed processing mode is that the processing of business is distributed on multiple processing units, current processing unit processing knot
Shu Hou, the present embodiment are forwarded to other processing units until business processing knot after carrying out message splicing using network accelerator unit
Beam.Above-mentioned common process mode is that processing unit carries out message header processing and message splicing and forwarding, such as is forwarded to core net,
Without being transmitted to other processing units.
As another embodiment, what processing unit can also add it in the service message is used for Service control
Business datum descriptor (be used for describe the processing that the processing unit is done to the service message) preserve to the speed buffering
Memory block, wherein, in the cache area, the memory space of the business datum descriptor and the heading
Memory space is separate, i.e., described business datum descriptor and the heading are stored in the difference in cache area
Storage area.Now, processing unit determines whether the service message needs by the heading of the service message after separation
To be handled according to distributed processing mode.If desired handled according to distributed processing mode, then processing unit utilizes network acceleration
Device unit carries out heading encapsulation, message splicing and forward process, specifically, by the network accelerator unit according in advance
The channel table of establishment, after encapsulating the heading for message forwarding, by the heading forwarded for message after encapsulation, protect
The business datum descriptor that cache area be present, the message body for being stored in non-high-speed cacheable memory region are spelled
Connect, and the spliced service message is forwarded according to the heading of encapsulation, such as send to other processing unit processes.If no
Need to handle according to distributed processing mode, then handled according to common process mode, i.e., processing unit will forward for message
Heading, the business datum descriptor for being stored in cache area, the message for being stored in non-high-speed cacheable memory region
Body is spliced, and obtained spliced service message is forwarded.
Above-mentioned processing unit can be the CPU or CPU of base station kernel.
The present embodiment reduces parsing classification processing losses of the CPU to service message by using network accelerator unit.
The present embodiment enters the separation of wardrobe body to service message using network accelerator unit, to heading in a manner of cache
Accelerate the processing of business unit, message body is deposited according to non-cache modes, reduces the impact to cache resources, improve
Cache hit probability.
The network accelerator unit of the present embodiment is sent out the heading and message body of separation according to chain intermittent mode
Send, exemplified by splicing heading and message body, network accelerator unit is that heading and message body are respectively provided for linking number
According to descriptor, be used to link the descriptors of data according to this, heading and message body linked, and after sending link
Service message.The present embodiment carries out message splicing and transmission processing in network accelerator unit, can reduce the CPU of copy link
Resource loss and processor bandwidth lose.
The network accelerator unit of the present embodiment utilizes channel table, and the heading of service message to be forwarded is sealed
Dress, reduce the CPU losses that encapsulated message headband comes.
Can be with it will appreciated by the skilled person that realizing that all or part of step in above-described embodiment method is
The hardware of correlation is instructed to complete by program, described program can be stored in computer read/write memory medium, should
Program upon execution, including step S101 to step S103.Wherein, described storage medium can be ROM/RAM, magnetic disc, light
Disk etc..
Fig. 2 is message process device block diagram provided in an embodiment of the present invention, as shown in Fig. 2 including：
Network accelerator unit 10, for the heading of service message and message body to be separated, and message point respectively
Heading and message body from after；
Processing unit 20, for being the message for message forwarding by the message header processing of the service message of preservation
Head；
Wherein, wherein, the processing unit 20 according to common process mode, to the heading for message forwarding and
The message body is spliced and forwarded, or, it is right using the network accelerator unit 10 according to distributed processing mode
It is described to be spliced and forwarded for the heading of message forwarding and the message body.
The workflow of described device is：Network accelerator unit 10 is according to the tagged word in the heading of service message
Section, branches to corresponding queue, so that follow-up respective handling unit 20 is handled by the service message of different service types.Net
Network accelerator unit 10 is separated the heading of the service message of respective queue and message body, and by the industry after separation
The heading of business message is preserved to cache regions, and the message body of the service message after separation is preserved to non-cache areas
Domain.Processing unit 20 by the message header processing of the service message of preservation be for message forwarding heading after, pass through
Heading, determines whether the service message needs to handle according to distributed processing mode.If desired according to distributed treatment side
Formula is handled, then processing unit 20 carries out heading encapsulation, message splicing and forward process using the network accelerator unit 10,
Specifically, network accelerator unit 10 is according to the channel table being pre-created, the encapsulation heading for message forwarding, and
The heading for being used for message forwarding after encapsulation, the message body for being stored in non-high-speed cacheable memory region are spliced, and turned
Send out obtained spliced service message.If need not be handled according to distributed processing mode, at common process mode
Reason, i.e. processing unit 20 are spelled the heading forwarded for message, the message body for being stored in non-high-speed cacheable memory region
Connect, and forward spliced service message, such as be forwarded to core net.
As another embodiment, what processing unit 20 was additionally operable to add it in the service message is used for Service control
Business datum descriptor (be used for describe the processing that the processing unit is done to the service message) preserve to the speed buffering
Memory block, wherein, in the cache area, the memory space of the business datum descriptor and the heading
Memory space is separate.So, during being handled according to distributed processing mode, network accelerator unit 10 is carrying out chain type report
, it is necessary to by the heading for being used for message forwarding after encapsulation, be stored in the business datum of cache area when text is sent
Descriptor, the message body for being stored in non-high-speed cacheable memory region are spliced, and according to the heading forwarding splicing of encapsulation after
Service message, such as be forwarded to other processing units.Similarly, during being handled according to common process mode, processing unit 20
Need the heading for being used for message forwarding after encapsulation, be stored in the business datum descriptor of cache area, protect
The message body that non-high-speed cacheable memory region be present is spliced, and obtained spliced service message is forwarded.
The present embodiment is disposed in processing unit to service message, and needs to be transmitted to another processing unit and continue to locate
During reason, according to passage table search object processing unit address, and by the way that the service message network accelerator unit that disguises oneself as can be added
The message of speed processing realizes that service message forwards, wherein, using segmentation chain type pass-through mode during forwarding service message.
The embodiment of the present invention additionally provides a kind of base station, and it includes above-mentioned Message processing and retransmission unit.
Fig. 3 is business multiplied unit structural representation provided in an embodiment of the present invention, as shown in figure 3, including interchange mode
Block and multiple baseband processing units, the baseband processing unit (i.e. processing unit described in Fig. 2) at least two, such as at base band
Manage unit 1 and baseband processing unit 2.Wherein, network equipment device (i.e. network accelerator described in Fig. 2 is set on Switching Module
Unit).
Job step includes：
The first step：Feature field of the service message in heading is categorized into by specified team by network equipment device
Row, while the head (i.e. heading) for extracting service message is placed on cache regions, for subsequent processing units 1 (equivalent to base band
Processing unit 1) on business fast operating head.
Second step：, it is necessary to be transmitted at business after Service Processing Unit 1 (equivalent to baseband processing unit 1) completion processing
Unit 2 (equivalent to baseband processing unit 2) is managed, by way of creating channel table in advance, network equipment device is completed message
The addition of head.
3rd step：If business increases control field, the needs that E-Packet are heading and the increased control field of business
And message body is transmitted to processing unit 2 by chain type through network equipment device.If business does not increase control field, forwarding report
Text needs heading and message body to be transmitted to processing unit 2 through the network equipment by chain type.
The content of above-mentioned control field is stored in the business datum descriptor space in cache regions.
Some specific fields (i.e. feature field) can also be increased in heading, quickly identification sorts out this for the 4th step
Kind service message.
4th step：Service Processing Unit 2 receives Service Processing Unit 1 (equivalent to baseband processing unit 2) (equivalent to base
Tape handling unit 1) forwarding message after, still according to head body separation mode stored messages, continued with for business, this process
Can continuous iteration, until the business processing for being distributed in multiple processing units finishes.
The present embodiment can be such that base band business processing efficiency is further lifted, and meet the impact of performance of base band business model.
The present embodiment uses network equipment device, saves cpu resource, by the way that service message is split as into head (quite
In heading) and payload (equivalent to message body), and cache areas and non-cache areas are individually positioned in, improve whole system
Cache hit probability.
The present embodiment sends message by chain type, reduces the CPU losses that copy heading and message body are brought.
Fig. 4 is business processing flow figure provided in an embodiment of the present invention, as shown in figure 4, step includes：
Step S201：Network equipment device receives according to message special field and shunts service message.
Step S202：Service message is split as heading and message body by network equipment device, and is preserved respectively to cache
Region and non-cache regions.
Step S203：Service Processing Unit 1 (i.e. processing unit 1 or baseband processing unit 1) is to the heading in cache regions
Handled.
Step S204：Judge whether to need to carry out service distribution formula processing to the service message, if desired to the business report
Text carries out service distribution formula processing, then performs step S205, otherwise performs step S209.
Step S205：The software (i.e. business) of Service Processing Unit 1 pretends such business according to the channel table created in advance
Message is that network equipment device can do the message that head addition accelerates processing.
Step S206：Network equipment device sends the heading for being segmented storage and message body to business processing according to chain type
Unit 2 (i.e. processing unit 2 or baseband processing unit 2).As another embodiment, if Service control field, network be present
Apparatus sends the data of three kinds of heading, Service control field, message body segmentation storages according to chain type.
Step S207：Network equipment device sorts out such message according to the special field extraction in service message, goes forward side by side
Wardrobe body separates.
Step S208：Service Processing Unit 2 (i.e. processing unit 2 or baseband processing unit 2) continues iteration until processing is tied
Beam vouchsafes me message.
Step S209：According to common message flow processing.
That is, into service message after base band by network equipment device according to special service fields (i.e. special word
Section) sort out and, heading and message body can be stored separately by network equipment device, and heading is stored in cache regions, right
Non- cache regions are stored in the unconcerned message body of business, are also assigned with one piece of service message that cache regions be present in addition
Descriptor space uses for Service control, and business is distributed in other processing units after to heading modification operation, it is necessary to be given to
On business module.If message, now without forwarding, walks regular traffic handling process i.e. without subsequent processing units processing
Can, the message for needing distributed treatment, it can now be sent by the passage created in advance, this passage is originally
For handling the passage of medium surface upstream data, will can E-Packet disguise as medium surface upstream data, can so cheat
Network equipment device enters the encapsulation of wardrobe addition to passage message, reduces the expense that CPU does head addition.
Wherein, the purpose of heading encapsulation is in order to be sent to processing unit where the business specified, as shown in figure 3, business
The message that different processing units handle each stage is distributed in, describes 2 grades of business processing models in figure, method of the invention can open up
Open up multi-stage service processing model.
When message is sent to target service processing unit, directly by the message of segmented mode storage by network equipment device
A complete message is spliced into send.The chain intermittent storage of message is as shown in figure 5, such a mode can be reduced is copied by CPU
Shellfish forms a message and sends the loss brought again, while prior factor is that the cache attributes of each memory paragraph differ
Cause, CPU need not pay close attention to non-cache data.A group chain message is moved by network equipment device, can largely be reduced because CPU is accessed
DDR accesses consumption in bus caused by cache miss.For CPU processor, the expense of saving is higher than CPU copy schemes
Loss.
After target service processing unit receives distributed treatment message, network equipment device equally can by such message according to
Special field Classification and Identification in heading goes out, and is again stored in cache and non-cache spaces in the way of head body separates
It is further processed.Multi-stage service processing unit completion processing is constantly iterated in this way.
The embodiment of the present invention further improves base band business processing efficiency, can meet the performance of business big flow model
Effect.Message is split as by head by using network port device device and payload part is individually positioned in cache areas and non-cache
Area, the cache hit probability of whole system is improved, by way of chain intermittent sends message, reduce the CPU that copy is brought
Loss.
Although the present invention is described in detail above, the invention is not restricted to this, those skilled in the art of the present technique
Various modifications can be carried out according to the principle of the present invention.Therefore, all modifications made according to the principle of the invention, all should be understood to
Fall into protection scope of the present invention.
Claims (11)
1. a kind of message processing method, including：
Network accelerator unit is separated the heading of service message and message body, and preserves the heading after separation respectively
With message body；
The message header processing of the service message of preservation is the heading for message forwarding by processing unit；
The processing unit is spelled according to common process mode to the heading for message forwarding and the message body
Connect and forward, or, according to distributed processing mode, using the network accelerator unit to the report for message forwarding
Literary head and the message body are spliced and forwarded.
2. according to the method for claim 1, described the step of preserving heading and message body after separating respectively, includes：
The heading of the service message after separation is stored in cache area by the network accelerator unit, will
The message body of the service message after separation is stored in non-high-speed cacheable memory region.
3. according to the method for claim 2, the processing unit forwards according to common process mode to the message that is used for
Heading and the message body spliced and forwarded, or, according to distributed processing mode, utilize the network accelerator
The step of unit is spliced and forwarded to the heading for message forwarding and the message body includes：
The processing unit by the heading of the service message after separation, determine the service message whether need according to
Distributed processing mode processing；
If desired handled according to distributed processing mode, then the processing unit utilizes the network accelerator unit, to described
Heading for message forwarding is packaged, and by the heading for being used for message forwarding after encapsulation, is stored in non-high-speed buffering
The message body of storage region is spliced and forwarded；
Otherwise handled according to common process mode, the processing unit by the heading forwarded for message, be stored in non-high-speed
The message body of cacheable memory region is spliced and forwarded.
4. the method according to claim 11, in addition to：
The business datum descriptor for Service control that the processing unit adds it in the service message preserve to
The cache area, wherein, in the cache area, the memory space of the business datum descriptor and
The memory space of the heading is separate.
5. according to the method for claim 4, the processing unit forwards according to common process mode to the message that is used for
Heading and the message body spliced and forwarded, or, according to distributed processing mode, utilize the network accelerator
The step of unit is spliced and forwarded to the heading for message forwarding and the message body includes：
The processing unit by the heading of the service message after separation, determine the service message whether need according to
Distributed processing mode processing；
If desired handled according to distributed processing mode, then the processing unit utilizes the network accelerator unit, to described
Heading for message forwarding is packaged, and by the heading for being used for message forwarding after encapsulation, is stored in speed buffering and is deposited
The business datum descriptor in storage area domain, the message body for being stored in non-high-speed cacheable memory region are spliced and forwarded；
Otherwise handled according to common process mode, the processing unit by the heading forwarded for message, be stored in it is slow at a high speed
The business datum descriptor for rushing storage region, the message body for being stored in non-high-speed cacheable memory region are spliced and forwarded.
6. a kind of message process device, including：
Network accelerator unit, for the heading of service message and message body to be separated, and respectively after message separation
Heading and message body；
Processing unit, for being the heading for message forwarding by the message header processing of the service message of preservation；
Wherein, the processing unit is according to common process mode, to the heading for message forwarding and the message body
Spliced and forwarded, or, according to distributed processing mode, using the network accelerator unit, it is used for message to described
The heading of forwarding and the message body are spliced and forwarded.
7. device according to claim 6, the network accelerator unit is by the message of the service message after separation
Head is stored in cache area, and the message body of the service message after separation is stored in into non-high-speed buffer storage
Domain.
8. device according to claim 7, the processing unit is by the heading of the service message after separation, really
Whether the fixed service message needs to handle according to distributed processing mode, is if desired handled according to distributed processing mode, then
Using the network accelerator unit, the heading for message forwarding is packaged, message will be used for after encapsulation
The heading of forwarding, the message body for being stored in non-high-speed cacheable memory region are spliced and forwarded, otherwise according to common process
Mode is handled, and the heading forwarded for message, the message body for being stored in non-high-speed cacheable memory region are spliced and turned
Hair.
9. device according to claim 7, the processing unit is additionally operable to the use for adding it in the service message
Preserved in the business datum descriptor of Service control to the cache area, wherein, in the cache area
In, the memory space of the business datum descriptor and the memory space of the heading are separate.
10. device according to claim 9, the processing unit by the heading of the service message after separation,
Determine whether the service message needs to handle according to distributed processing mode, if desired handled according to distributed processing mode,
The network accelerator unit is then utilized, the heading for message forwarding is packaged, will be used to report after encapsulation
The heading of text forwarding, it is stored in the business datum descriptor of cache area, is stored in non-high-speed buffer storage
The message body in domain is spliced and forwarded, and is otherwise handled according to common process mode, by the heading forwarded for message, is preserved
Business datum descriptor in cache area, the message body for being stored in non-high-speed cacheable memory region are spliced simultaneously
Forwarding.
11. a kind of base station, it includes message process device described in claim 6-10 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610496288.5A CN107547417A (en) | 2016-06-29 | 2016-06-29 | A kind of message processing method, device and base station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610496288.5A CN107547417A (en) | 2016-06-29 | 2016-06-29 | A kind of message processing method, device and base station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107547417A true CN107547417A (en) | 2018-01-05 |
Family
ID=60965933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610496288.5A Pending CN107547417A (en) | 2016-06-29 | 2016-06-29 | A kind of message processing method, device and base station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107547417A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110109852A (en) * | 2019-04-03 | 2019-08-09 | 华东计算技术研究所（中国电子科技集团公司第三十二研究所） | System and method for realizing TCP _ IP protocol by hardware |
| CN110417813A (en) * | 2019-08-23 | 2019-11-05 | 北京无极芯动科技有限公司 | It pops network processing unit and network data is popped processing method |
| CN110417812A (en) * | 2019-08-23 | 2019-11-05 | 北京无极芯动科技有限公司 | 5G protocol massages processor architecture and 5G protocol message processing method |
| CN114448892A (en) * | 2022-02-10 | 2022-05-06 | 珠海星云智联科技有限公司 | Software and hardware routing method and device |
| WO2022110112A1 (en) * | 2020-11-30 | 2022-06-02 | 华为技术有限公司 | Message processing method and device |
| WO2022116953A1 (en) * | 2020-12-01 | 2022-06-09 | 阿里巴巴集团控股有限公司 | Packet processing method, device, system, and storage medium |
| CN116016713A (en) * | 2022-12-13 | 2023-04-25 | 苏州盛科通信股份有限公司 | Message transmission method, device, network equipment and readable storage medium |
| CN116032861A (en) * | 2023-01-09 | 2023-04-28 | 苏州盛科通信股份有限公司 | Message processing method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4755986A (en) * | 1985-09-13 | 1988-07-05 | Nec Corporation | Packet switching system |
| US20060072563A1 (en) * | 2004-10-05 | 2006-04-06 | Regnier Greg J | Packet processing |
| US20060288202A1 (en) * | 2005-06-17 | 2006-12-21 | Mark Doran | Method for network restart |
| CN1889505A (en) * | 2006-07-17 | 2007-01-03 | 华为技术有限公司 | Method and system for aiding CPU to retransmit message |
| CN101022408A (en) * | 2007-02-01 | 2007-08-22 | 华为技术有限公司 | Method for transmitting point-to-point message and transmitting convergent node |
| US20090262739A1 (en) * | 2008-04-21 | 2009-10-22 | Kuo-Cheng Lu | Network device of processing packets efficiently and method thereof |
| CN103139752A (en) * | 2011-12-01 | 2013-06-05 | 中兴通讯股份有限公司 | Transmission channel table modification method and device |
| CN103957241A (en) * | 2014-04-16 | 2014-07-30 | 中国工商银行股份有限公司 | Communication method and device based on message data |
| CN104469315A (en) * | 2014-12-17 | 2015-03-25 | 浙江宇视科技有限公司 | CDN-based video data stream transmission method, device and system |
| CN105530127A (en) * | 2015-12-10 | 2016-04-27 | 北京奇虎科技有限公司 | Method and proxy server for processing network access request by proxy server |
-
2016
- 2016-06-29 CN CN201610496288.5A patent/CN107547417A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4755986A (en) * | 1985-09-13 | 1988-07-05 | Nec Corporation | Packet switching system |
| US20060072563A1 (en) * | 2004-10-05 | 2006-04-06 | Regnier Greg J | Packet processing |
| US20060288202A1 (en) * | 2005-06-17 | 2006-12-21 | Mark Doran | Method for network restart |
| CN1889505A (en) * | 2006-07-17 | 2007-01-03 | 华为技术有限公司 | Method and system for aiding CPU to retransmit message |
| CN101022408A (en) * | 2007-02-01 | 2007-08-22 | 华为技术有限公司 | Method for transmitting point-to-point message and transmitting convergent node |
| US20090262739A1 (en) * | 2008-04-21 | 2009-10-22 | Kuo-Cheng Lu | Network device of processing packets efficiently and method thereof |
| CN103139752A (en) * | 2011-12-01 | 2013-06-05 | 中兴通讯股份有限公司 | Transmission channel table modification method and device |
| CN103957241A (en) * | 2014-04-16 | 2014-07-30 | 中国工商银行股份有限公司 | Communication method and device based on message data |
| CN104469315A (en) * | 2014-12-17 | 2015-03-25 | 浙江宇视科技有限公司 | CDN-based video data stream transmission method, device and system |
| CN105530127A (en) * | 2015-12-10 | 2016-04-27 | 北京奇虎科技有限公司 | Method and proxy server for processing network access request by proxy server |
Non-Patent Citations (1)
| Title |
|---|
| 张晓明等: "高速网络路由器IP报文转发技术的研究与实现", 《计算机工程》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110109852B (en) * | 2019-04-03 | 2020-11-24 | 华东计算技术研究所（中国电子科技集团公司第三十二研究所） | Method for realizing TCP _ IP protocol by hardware |
| CN110109852A (en) * | 2019-04-03 | 2019-08-09 | 华东计算技术研究所（中国电子科技集团公司第三十二研究所） | System and method for realizing TCP _ IP protocol by hardware |
| CN110417813A (en) * | 2019-08-23 | 2019-11-05 | 北京无极芯动科技有限公司 | It pops network processing unit and network data is popped processing method |
| CN110417812A (en) * | 2019-08-23 | 2019-11-05 | 北京无极芯动科技有限公司 | 5G protocol massages processor architecture and 5G protocol message processing method |
| CN110417813B (en) * | 2019-08-23 | 2021-08-27 | 极芯通讯技术(南京)有限公司 | Pull-out network processor and network data pull-out processing method |
| CN110417812B (en) * | 2019-08-23 | 2021-11-23 | 极芯通讯技术(南京)有限公司 | 5G protocol message processor architecture and 5G protocol message processing method |
| WO2022110112A1 (en) * | 2020-11-30 | 2022-06-02 | 华为技术有限公司 | Message processing method and device |
| CN114640726A (en) * | 2020-12-01 | 2022-06-17 | 阿里巴巴集团控股有限公司 | Message processing method, device, system and storage medium |
| WO2022116953A1 (en) * | 2020-12-01 | 2022-06-09 | 阿里巴巴集团控股有限公司 | Packet processing method, device, system, and storage medium |
| CN114640726B (en) * | 2020-12-01 | 2023-12-01 | 阿里巴巴集团控股有限公司 | Message processing method, device, system and storage medium |
| CN114448892A (en) * | 2022-02-10 | 2022-05-06 | 珠海星云智联科技有限公司 | Software and hardware routing method and device |
| CN116016713A (en) * | 2022-12-13 | 2023-04-25 | 苏州盛科通信股份有限公司 | Message transmission method, device, network equipment and readable storage medium |
| CN116032861A (en) * | 2023-01-09 | 2023-04-28 | 苏州盛科通信股份有限公司 | Message processing method and device |
| CN116032861B (en) * | 2023-01-09 | 2025-03-07 | 苏州盛科通信股份有限公司 | A message processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107547417A (en) | A kind of message processing method, device and base station | |
| CN103414538B (en) | A kind of packet method for sorting of distributed environment lower network data communication | |
| CN105224692A (en) | Support the system and method for the SDN multilevel flow table parallel search of polycaryon processor | |
| CN103353850B (en) | Virtual machine thermal migration memory processing method, device and system | |
| CN111382327B (en) | Character string matching device and method | |
| CN103188042B (en) | A kind of matching process of IP packet and coupling accelerator | |
| CN103024819B (en) | Data distribution method of third-generation mobile communication core network based on user terminal IP (Internet Protocol) | |
| CN108431831A (en) | Loop code processor optimizes | |
| CN105490985A (en) | Implementation method and device for TCP long connection based on signal transmission | |
| CN105653484A (en) | Data block-oriented compression multi-path transmission method | |
| CN104350488A (en) | Systems and methods for selective data redundancy elimination for resource constrained hosts | |
| CN106850382B (en) | Flow traction method and device | |
| CN101841474A (en) | Device for realizing access control lists | |
| CN104601645B (en) | A data packet processing method and device | |
| CN114885045B (en) | Method and device for saving DMA channel resources in high-speed intelligent network card/DPU | |
| CN115225734A (en) | Message processing method and network equipment | |
| CN118264617B (en) | Method, system, equipment and storage medium for transmitting data of overlay network | |
| CN115514702A (en) | Method and device for quickly switching link, electronic equipment and storage medium | |
| CN105302780B (en) | A kind of SCD file edit methods of optimization | |
| CN107277062A (en) | The method for parallel processing and device of packet | |
| US11314711B2 (en) | Network switch with network analysis data producer-consumer shared memory | |
| US10284426B2 (en) | Method and apparatus for processing service node ability, service classifier and service controller | |
| CN116133159B (en) | GTP data packet processing method, device, computer equipment and storage medium | |
| CN108153597B (en) | LINUX equipment management device and method | |
| CN102655476A (en) | Internet protocol flow transmitting method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180105 |