CN102104548A - Method and device for receiving and processing data packets - Google Patents
Method and device for receiving and processing data packets Download PDFInfo
- Publication number
- CN102104548A CN102104548A CN201110050489XA CN201110050489A CN102104548A CN 102104548 A CN102104548 A CN 102104548A CN 201110050489X A CN201110050489X A CN 201110050489XA CN 201110050489 A CN201110050489 A CN 201110050489A CN 102104548 A CN102104548 A CN 102104548A
- Authority
- CN
- China
- Prior art keywords
- packet
- traffic classification
- information
- message
- operating result
- 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.)
- Granted
Links
Images
Abstract
The invention provides a method for receiving and processing data packets, comprising the steps: receiving a data packet, extracting flow classification operation information in the procedure of receiving the data packet, slicing the data packet according to a predetermined size to obtain data slices, and storing each received data slice into a corresponding storage space of the data packet; after the data packet is received completely, performing a flow classification operation on the data packet according to the flow classification operation information; and after the flow classification operation result is obtained, extracting the relevant information to initiate the following operations. The invention further provides a device for receiving and processing data packets. By the method provided by the invention, the processing time of long packets can be obviously lessened, and the time delay of the system is reduced.
Description
Technical field
The present invention relates to data communication field.Particularly, be a kind of packet receiving handling method and device.
Background technology
High-speed data service requires the processing delay of system the smaller the better.When packet enters data service system, generally need through reception, traffic classification and three operations of storage.In this process, time that the reception of packet and storage operation are spent and memory space resource are all proportional with length of data package.According to the conventional method, the beginning of each step operation need to wait for finishing of previous action, for the very long packet of length, as 9600byte, in time with all be very big expense on the device ram in slice resource, even become the bottleneck of system.
When system adopted traditional processing mode, the time that receiving course spent of a packet was the time t1 that packet receives, the time t3 three sum that the time t2 of data packet stream sort operation and packet deposit buffer memory in, wherein:
The time t1:t1=len/v1 that packet receives, wherein, len is that the bag of packet is long, v1 is the input port speed of this packet;
The time t2 of data packet stream sort operation can regard as with length of data package irrelevant, is a fixed value;
Packet deposits the time t3:t3=len/v2 of buffer memory in, and wherein, len is that the bag of packet is long, and v2 is the memory rate of system cache.
Therefore the spent time of whole process is t1+t2+t3=len/v1+t2+len/v2.For a fixing system, v1, v2 is a fixed value, so determine that the spent time of whole process is length of data package len.
As the maximum Bao Changwei 9600byte that system supports, the packet input port is 1Gbps, when the memory rate of system cache is 20Gbps, from beginning to receive the maximum delay that buffer memory finishes is: 9600 * 8/ (10
9)+9600 * 8/ (2 * 10
10)+t2, promptly 8.064 * 10
-5+ t2 (s).
In addition, reception for packet, the device ram in slice resource that FPDP needs, should support two whole spaces of wrapping of data that maximum bag is long at least, i.e. 9600 * 8 * 2=153.6kb, if under more than one situation of the port number of system input, along with the increase of the number of port, the expense of this resource can become unacceptable gradually.
Summary of the invention
The technical problem to be solved in the present invention provides a kind of packet receiving handling method and device, reduces the data processing time delay.
In order to address the above problem, the invention provides a kind of packet receiving and processing device, comprise input control module, message processing module (MPM) and assure the reason module, wherein:
Described input control module is used for: receive packet, in the process that receives packet, extract the traffic classification operation information, by default size packet is cut into slices, whenever receive a data section and send it to the described reason module of assuring, after packet receives, described traffic classification operation information is sent to described message processing module (MPM); And, receive the traffic classification operating result of described packet, described traffic classification operating result is sent to assure the reason module;
Described message processing module (MPM) is used for: according to described traffic classification operation information described packet is carried out the traffic classification operation, the traffic classification operating result that obtains is sent to described input control module;
The described reason module of assuring is used for: when receiving the data slicer of the described packet that described input control module sends, store this packet corresponding memory space into; And, receive the traffic classification operating result of described packet after, extract relevant information and initiate subsequent operation.
Further, said apparatus also can have following characteristics, and described default size is the minimum unit of system cache operation or the multiple of minimum unit.
Further, said apparatus also can have following characteristics, described input control module also is used for: described data slicer is sent to the described reason module of assuring, with, described traffic classification operation information is sent to described message processing module (MPM), with, described traffic classification operating result sent to assure reason during module, the port identification information of carrying the input port of described packet;
Described message processing module (MPM) also is used for, and when receiving described traffic classification operation information and port identification information, preserves described port identification information, when sending described traffic classification operating result to described input control module, carries described port identification information;
The described reason module of assuring also is used for: receive described data slicer and port identification information, or when receiving described traffic classification operating result and port identification information, according to described port identification information described data slicer or traffic classification operating result are sent to corresponding FPDP and handle.
Further, said apparatus also can have following characteristics, and described traffic classification operating result comprises message modification information and message descriptor information;
The described reason module of assuring also is used for: the message of described packet is revised information stores in described packet corresponding memory space, and described extraction relevant information comprises the message descriptor information of extracting described packet.
Further, said apparatus also can have following characteristics, described input control module also is used for: in the process that receives packet, preserve the preceding N byte data of described packet, begin to cut into slices after N byte of described packet, described N is that described default size and described message are revised the information difference; After receiving the traffic classification operating result of described packet, the message modification information of N byte data before described and described packet is formed the first section of bag send to the described reason module of assuring;
The described reason module of assuring also is used for: when the data slicer of described packet is stored, keep the first memory block of described packet corresponding memory space; And, when receiving first section of bag of described packet, it is stored in the first memory block of described packet corresponding memory space.
Further, said apparatus also can have following characteristics, described input control module also is used for: after receiving a packet, wait also receives in the traffic classification operating result process of described packet, carry out the reception operation of next packet, and the data slicer that sends described next packet is to assuring the reason module;
The described reason module of assuring also is used for: receiving the data slicer of described packet, wait in the process of traffic classification operating result of described packet, when receiving the data slicer of next packet of described packet, be stored to described next packet corresponding memory space.
The present invention also provides a kind of packet receiving handling method, comprising:
Receive packet, in the process that receives packet, extract the traffic classification operation information, by default size packet being cut into slices obtains data slicer, whenever receives a data section and then stores this packet corresponding memory space into;
After described packet receives, according to described traffic classification operation information described packet is carried out traffic classification operation, obtain the traffic classification operating result after, extract relevant information and initiate subsequent operation.
Further, said method also can have following characteristics, and described default size is the minimum unit of system cache operation or the multiple of minimum unit.
Further, said method also can have following characteristics, and described method also comprises:
When handling the packet of a plurality of input ports, use port identification information to distinguish data slicer, traffic classification operation information and the traffic classification operating result of the packet of different input ports.
Further, said method also can have following characteristics, and described traffic classification operating result comprises message modification information and message descriptor information; Described extraction relevant information comprises the message descriptor information of extracting described packet;
Described method also comprises, the message of described packet is revised information stores in described packet corresponding memory space.
Further, said method also can have following characteristics, and described method also comprises: in the process that receives packet, preserve the preceding N byte data of described packet, begin to cut into slices after N byte of described packet, described N is that described default size and described message are revised the information difference; When the data slicer of described packet is stored, keep the first memory block of described packet corresponding memory space;
After obtaining the traffic classification operating result of described packet, the message modification information of N byte data before described and described packet is formed the first memory block that the first section of bag is stored in described packet corresponding memory space.
Further, said method also can have following characteristics, and described method also comprises, after receiving a packet, wait also receives in the traffic classification operating result process of described packet, carries out reception, section and the data slicer storage operation of next packet.
Adopt method of the present invention, compare, do not receive, just can carry out storage operation because packet does not need to wait for existing scheme, to a certain extent that memory time and time of reception is multiplexing.Therefore, the time that whole process spent, just be roughly time and the memory time that data are cut into slices that packet receives.For long bag, therefore, can significantly reduce the time of the processing of long bag the memory time of having saved packet basically, reduce the time-delay of system.
Simultaneously, owing to do not need to initiate storage operation again behind packet of complete reception, but only need to support the size of data of data caching just can finish from receiving the operation of buffer memory, therefore, the expense of device ram in slice resource, by two the significant spatial of long bag be reduced to two data sections.
In addition, the present invention revises information under the situation that is no more than the external memory space disposal ability with the partial results message of traffic classification operation, deposit in the external memory space with the message data entity, directly be transferred to output module then, without the queue management part, reduced the burden of queue management storage.
Description of drawings
Fig. 1 is a system block diagram of the present invention;
Fig. 2 is the interface schematic diagram of IPC of the present invention and PP;
Fig. 3 is the interface schematic diagram of IPC of the present invention and PMG;
Fig. 4 is the processing schematic diagram of IPC of the present invention;
Fig. 5 is the process chart of PMG of the present invention.
Embodiment
Because the check information of the whole packet of traffic classification action need, the end that must wait until packet enters system and could start, so the time of the reception of packet and traffic classification operation can not be saved, what can change is exactly that packet deposits this operation of buffer memory in.
Core concept of the present invention is: a kind of packet receiving handling method is provided, allowing packet storage operation and packet receive operation begins simultaneously, the operation that allows packet deposit buffer memory in needn't receive operation and traffic classification operation by the time and finish and carry out afterwards again, thereby saved the time of packet storage operation, reduced the processing delay and the resource consumption of system.
The invention provides a kind of packet receiving and processing device, as shown in Figure 1, comprise input control module (IPC), message processing module (MPM) (PP) and assure three parts of reason module (PMG), wherein:
Described IPC is used for: receive packet, in the process that receives packet, extract the traffic classification operation information, by default size packet is cut into slices, whenever receive a data section and send it to described PMG, after packet receives, described traffic classification operation information is sent to described PP; And, receive the traffic classification operating result of described packet, described traffic classification operating result is sent to PMG;
Described PP is used for: according to described traffic classification operation information described packet is carried out the traffic classification operation, the traffic classification operating result that obtains is sent to described IPC;
Described PMG is used for: when receiving the data slicer of the described packet that described input control module sends, store this packet corresponding memory space into; And, receive the traffic classification operating result of described packet after, extract relevant information and initiate subsequent operation.Packet can be stored in DDR (Double Data Rate, Double Data Rate synchronous DRAM); In, and in DDR, finish the reorganization of packet.
Described IPC also is used for: with described data slicer send to described PMG and, with described traffic classification operation information send to described PP and, when described traffic classification operating result is sent to PMG, the port identification information of carrying the input port of described packet;
Described PP also is used for, and when receiving described traffic classification operation information and port identification information, preserves described port identification information, when sending described traffic classification operating result to described IPC, carries described port identification information;
Described PMG also is used for: receive described data slicer and port identification information, or when receiving described traffic classification operating result and port identification information, according to described port identification information described data slicer or traffic classification operating result are sent to corresponding FPDP and handle.
Wherein, described PMG also is used for: the message of described packet is revised information stores in described packet corresponding memory space, and described extraction relevant information comprises the message descriptor information of extracting described packet.
Wherein, described input control module also is used for: in the process that receives packet, preserve the preceding N byte data of described packet, begin to cut into slices after N byte of described packet, described N is that described default size and described message are revised the information difference; After receiving the traffic classification operating result of described packet, the message modification information of N byte data before described and described packet is formed the first section of bag send to the described reason module of assuring;
The described reason module of assuring also is used for: when the data slicer of described packet is stored, keep the first memory block of described packet corresponding memory space; And, when receiving first section of bag of described packet, it is stored in the first memory block of described packet corresponding memory space.
Described port identification information is a port numbers.
The interface of IPC and PP as shown in Figure 2.The interface of IPC to PP comprises useful signal, traffic classification operation information, port numbers; The interface of PP to IPC comprises traffic classification operating result, port numbers and useful signal interface.The useful signal interface is used for transmission and enables control signal, and the port numbers interface is used for the transmit port identification information, and traffic classification operation information interface is used for transport stream sort operation information, and traffic classification operating result interface is used for transport stream sort operation information.
The interface of IPC and PMG as shown in Figure 3, comprise useful signal, data channel, initial signal, end signal, traffic classification sign and message descriptor information interface, wherein, the useful signal interface is used for transmission and enables control signal, data channel is used to transmit data slicer and the first section of bag (concrete implication is seen embodiment), the initial signal interface is used for the initial signal of transmits data packets, the end signal interface is used for the end signal of transmits data packets, whether traffic classification sign interface is used for sign the traffic classification operating result, and message descriptor information interface is used for the message transmission descriptor information.
The operating process at IPC place is as follows:
Step 101, IPC receives the data of input port, by default size, packet is cut into slices, and extracts traffic classification according to the requirement of PP and operate needed information, is called for short the traffic classification operation information;
Wherein, described default size is minimum unit or its integral multiple of system cache operation.
Step 102, IPC whenever receives the section of data, just this data slicer and port numbers is sent to PMG and carries out buffer memory;
Step 103 after packet receives, is sent to PP with the traffic classification operation information and the port numbers of packet;
Step 104, this data packet stream sort operation result that IPC waits for and reception PP passes back, and send PMG to, finish the transmission of this packet; Wait in this data packet stream sort operation result's that PP passes back the process at IPC, can carry out the reception and the caching of follow-up data bag.
The operating process at PP place is as follows:
Step 201, PP receives the port numbers that IPC sends traffic classification operation information and this packet of the packet that comes to;
Step 202, PP carries out the traffic classification operation of packet according to the traffic classification operation information;
Wherein, PP need guarantee that packet carries out the order (first in first out) of traffic classification operation.
Step 203, PP sends it back IPC with result and this packet corresponding port information of traffic classification operation;
The operation at PMG place is as follows:
Step 301, PMG receives the initial signal of the packet of IPC transmission, the application memory space;
Step 302, the data slicer that sends over of storing IP C is until the end signal that receives packet successively;
Step 303, PMG carries out the storage operation (repeating step 301 and step 302) of follow-up data bag, and the traffic classification operating result of while supervision packet;
Step 304 if receive the traffic classification operating result of packet, is revised information stores to this packet corresponding memory space with the message of packet, and is extracted corresponding information and initiate next step operation.
Corresponding information comprises the message descriptor information of packet.
In the whole process, packet deposits data in buffer in and in fact has been divided into the entity of packet and traffic classification operating result two parts of packet, the storage of the entity part of packet and packet receive and carry out simultaneously, and the class sort operation result's of packet storage is after packet receives end, and wait traffic classification operating result is passed IPC back and just can be carried out.
The present invention is not only applicable to the system of single port input, be equally applicable to the system of multiport input, only needing increases port identification information, just the data between each port numbers can be separated, and the processing mode of each port is consistent with the processing mode of single port.Under the single port situation, during transmission information between each module (data slicer, traffic classification operation information, traffic classification operation information), must not carry port identification information.
In order to be illustrated more clearly in technical scheme of the present invention, will introduce a kind of detailed process that realizes this scheme below, but not as a limitation of the invention.
Suppose that the FPDP of 20 1Gbps is arranged in the IPC side; The data that the processing of PP needs are the CRC check information of the preceding 128byte and the packet of packet, PP returns the front that 48byte message modification information is added on data message, support the message of back to revise, other transmits 66bit message descriptor information and offers the subsequent packet scheduling operation; The size of data of the each storage operation of DDR controller is 64byte (512bit), and therefore, can select the data bit width at IPC to PMG place is 64byte (512bit), and the size of data slicer is 64byte (512bit); It among the DDR is minimum space cell with 2048byte; The data packet length of system's support is 64btye-9600byte.
The handling process of IPC as shown in Figure 4, the concrete steps of single port handle packet are as follows:
After IPC receives the initial data of packet, deposit the preceding 16byte data of packet in default FIFO (First Input First Output, first-in first-out), this FIFO is called a head section FIFO;
Because message modification information is 48byte, therefore the size of a caching of less than needs the data of 16byte to form data slicer together, carries out caching.Because message is revised the front (being convenient to the message retouching operation) that information should leave message data in, therefore the preceding 16byte of message being intercepted out in advance buffer memory gets up, wait for when message modification information is returned to IPC, be assembled into the first section of bag, send PMG to and carry out buffer memory, transmit the message descriptor that the first section of this bag also can transmit this packet correspondence simultaneously.Certainly, the data of the 16byte that also can not prestore directly send to PMG with the first section of message modification information composition bag and carry out buffer memory.
IPC extracts the preceding 128byte of packet, deposits fixing memory space (distinguishing with port numbers) in, after the wait packet receives, gives PP with the CRC check result transmission, initiates the traffic classification operation;
IPC is that unit carries out the data slicer transmission from the 17byte of packet by 64byte, is sent to PMG in order, first data slicer is added the SOP signal, initial as new bag adds eop signal to last section of packet, shows that the entity information of packet receives;
The traffic classification operating result of supervision packet, and the traffic classification operating result that receives is dressed up packet head with first data set among the head section FIFO cut into slices, and, pass to PMG together and store and initiate next step operation the message descriptor information of corresponding 66bit.
The traffic classification operating result, be divided into two parts: 1, message is revised information, this part does not need the queue management part of the system of passing to, directly there be (among the DDR) in the external cache with message, alleviating the storage burden of queue management, the output module that is directly passed to system when data contract out group carries out message to be revised; 2, message descriptor information (66bit), the information that needs when queue management is handled.
IPC receives the traffic classification operating result, mainly carry out following operation: IPC to PMG two data passages are arranged, one is data channel, transmit the data and the message of message and revise information, then by the PMG buffer memory to DDR, one is the message descriptor information, behind PMG, add the PMAU sign (the DDR storage space information of message) of message correspondence, transmit the back queue management together.Wherein, the preceding 16byte data of message that message is revised information (48byte) and reserved, forming a data section (the first section of the bag of message) transmits, in this section of transmission, synchronous in message descriptor symbol information channel, the message descriptor information of this packet is passed to PMG.
PP is in this process, and the concrete steps of handling process are as follows:
The traffic classification operation information and the port numbers of the packet that reception IPC sends;
In order packet is carried out the traffic classification operation successively;
The traffic classification operating result of this packet and the port of this packet are mated synchronously, then traffic classification operating result and port numbers are sent back IPC.
The handling process of PMG as shown in Figure 5, concrete steps are as follows:
After PMG receives some data slicers,, data slicer is sent to corresponding FPDP by the port numbers of data slicer;
The type of PMG recognition data section: 1, the initial section of band SOP; 2, the end section of band EOP; 3, the band message is revised the first section of bag of information and descriptor information; 4, do not have the general data section of above information;
PMG receives the initial section that has SOP, applies for that a data memory space unit removes this packet of buffer memory, and with first address of this data space unit, keeps for the first section of bag, stores the data of initial section since second address; After the data slicer storage is finished, note the address (current address adds 1) that this port deposits data in next time; The first address of this packet memory space is placed among the FIFO (wrapping first slice address FIFO), offers the first section of back storage package and use;
PMG receives the general data section that does not have any control information, and the address according to the port information of data slicer is pointed out deposits among the DDR; After storage is finished, note the address (current address adds 1) that this port deposits data in next time; Packet is not also stored and is finished if the storage of space, current address is full, applies for that new address space continues storage; The address space of application manages and first node corresponding address is used so that the back to be provided as the sign of whole bag with the form of chained list;
PMG receives the initial section that has EOP, with this packet sign record, has stored with the bag entity that shows this packet and to finish, and can receive the information of next packet; Concrete, behind PMG storage EOP, meeting deposits the first address of the memory space of this packet in a specific FIFO, each port has a FIFO, be used to write down the first address in all message corresponding stored spaces, PMG receives the first section of bag of a message of this port, just the FIFO from correspondence takes out an address, should wrap first section and deposit this address in, Here it is sign that packet buffer finishes, pass to follow-up queue management module after the message descriptor information of this address information (as the sign of message) and correspondence can being finished together then, carry out next step operation.
PMG receives and has the first section of bag that message is revised information and message descriptor information, and first address of extracting the first slice address FIFO of bag simultaneously will be wrapped first section and be deposited in this address, so just finish the reorganization of data; Extract the information (first address of packet storage and packet descriptor information etc.) of corresponding packet simultaneously, initiate ensuing operation.
In the present embodiment, because the size of data slicer is the minimum unit of system operation, each data slicer takies a data memory space unit, when the size of data slicer is the integral multiple of minimum unit of system operation, each data slicer takies a plurality of data spaces unit, is called a memory block, at this moment, keep first memory block and be used for the first section of storage package, store the data slicer of packet entity since second memory block.If message is revised the memory space that the size of information surpasses a memory block, then reserve preceding a plurality of memory blocks of this packet corresponding memory space, be used for stored messages and revise information.
Because in the whole process, the minimum unit of operation is to be the data slicer of unit with 64byte, therefore, it is that unit carries out polled transmission that each port needs only with the data slicer, just can easily distinguish the port information that each data slicer is additional; The differentiation of packet in the port, main sequencing according to packet control information and packet itself; In PMG, the address situation that writes of each port needs separate management, according to control information, operates according to above-mentioned storage operation flow process, just can finish the reorganization of packet in the DDR space.
The present invention also provides a kind of packet receiving handling method, comprising:
Receive packet, in the process that receives packet, extract the traffic classification operation information, by default size packet being cut into slices obtains data slicer, whenever receives a data section and then stores this packet corresponding memory space into;
After described packet receives, according to described traffic classification operation information described packet is carried out traffic classification operation, obtain the traffic classification operating result after, extract relevant information and initiate subsequent operation.
Wherein, described default size is the minimum unit of system cache operation or the multiple of minimum unit.
Wherein, when handling the packet of a plurality of input ports, use port identification information to distinguish data slicer, traffic classification operation information and the traffic classification operating result of the packet of different input ports.
Wherein, described traffic classification operating result comprises message modification information and message descriptor information; Described extraction relevant information comprises the message descriptor information of extracting described packet; Described method also comprises, the message of described packet is revised information stores in described packet corresponding memory space.
Described method also comprises: in the process that receives packet, preserve the preceding N byte data of described packet, begin to cut into slices after N byte of described packet, described N is that described default size and described message are revised the information difference; When the data slicer of described packet is stored, keep the first memory block of described packet corresponding memory space; After obtaining the traffic classification operating result of described packet, the message modification information of N byte data before described and described packet is formed the first memory block that the first section of bag is stored in described packet corresponding memory space.
Described method also comprises, after receiving a packet, waits for and receives in the traffic classification operating result process of described packet, carries out reception, section and the data slicer storage operation of next packet.
Packet receiving handling method provided by the invention, allowing packet storage operation and packet receive operation begins simultaneously, the operation that allows packet deposit buffer memory in needn't receive operation and traffic classification operation by the time and finish and carry out afterwards again, thereby saved the time of packet storage operation, reduced the processing delay and the resource consumption of system.
In addition, the present invention can reduce also that packet receives and storing process remove device ram in slice resource overhead.Because the result of the CRC check when traffic classification operation only needs packet header (being the data of regular length in the packet) of packet and packet to receive, therefore need buffer memory is not very big.The consumption of the maximum of device ram in slice resource is on the flow process of the reception-buffer memory of packet.If adopt existing scheme, adopt to receive at packet and initiate caching again, system needs the device ram in slice resource of two long bags to finish this flow process at least so.When adopting the present invention program, reception-buffer memory carries out simultaneously, as long as promptly packet receives the data of enough doing a caching, just carries out the caching process of packet, the device ram in slice resource of this flow process is reduced to the size of the data of twice caching.
In addition, the present invention deposits space outerpace with not needing the part-message through queue management to revise information among the traffic classification result in the message entity, though increased the burden of space outerpace, has reduced the storage burden of queue management.Comparatively speaking, the ability of message administration module (PMG) is better than queue management module, and cost is relatively low.
Claims (12)
1. a packet receiving and processing device is characterized in that, comprise input control module, message processing module (MPM) and assure the reason module, wherein:
Described input control module is used for: receive packet, in the process that receives packet, extract the traffic classification operation information, by default size packet is cut into slices, whenever receive a data section and send it to the described reason module of assuring, after packet receives, described traffic classification operation information is sent to described message processing module (MPM); And, receive the traffic classification operating result of described packet, described traffic classification operating result is sent to assure the reason module;
Described message processing module (MPM) is used for: according to described traffic classification operation information described packet is carried out the traffic classification operation, the traffic classification operating result that obtains is sent to described input control module;
The described reason module of assuring is used for: when receiving the data slicer of the described packet that described input control module sends, store this packet corresponding memory space into; And, receive the traffic classification operating result of described packet after, extract relevant information and initiate subsequent operation.
2. device as claimed in claim 1 is characterized in that, described default size is the minimum unit of system cache operation or the multiple of minimum unit.
3. device as claimed in claim 1 is characterized in that,
Described input control module also is used for: described data slicer is sent to the described reason module of assuring, with, described traffic classification operation information is sent to described message processing module (MPM), with, described traffic classification operating result sent to assure reason during module, the port identification information of carrying the input port of described packet;
Described message processing module (MPM) also is used for, and when receiving described traffic classification operation information and port identification information, preserves described port identification information, when sending described traffic classification operating result to described input control module, carries described port identification information;
The described reason module of assuring also is used for: receive described data slicer and port identification information, or when receiving described traffic classification operating result and port identification information, according to described port identification information described data slicer or traffic classification operating result are sent to corresponding FPDP and handle.
4. device as claimed in claim 1 is characterized in that, described traffic classification operating result comprises message modification information and message descriptor information;
The described reason module of assuring also is used for: the message of described packet is revised information stores in described packet corresponding memory space, and described extraction relevant information comprises the message descriptor information of extracting described packet.
5. device as claimed in claim 4 is characterized in that,
Described input control module also is used for: in the process that receives packet, preserve the preceding N byte data of described packet, begin to cut into slices after N byte of described packet, described N is that described default size and described message are revised the information difference; After receiving the traffic classification operating result of described packet, the message modification information of N byte data before described and described packet is formed the first section of bag send to the described reason module of assuring;
The described reason module of assuring also is used for: when the data slicer of described packet is stored, keep the first memory block of described packet corresponding memory space; And, when receiving first section of bag of described packet, it is stored in the first memory block of described packet corresponding memory space.
6. as the arbitrary described device of claim 1 to 5, it is characterized in that,
Described input control module also is used for: after receiving a packet, wait for and receive in the traffic classification operating result process of described packet, carry out the reception operation of next packet, and the data slicer that sends described next packet is to assuring the reason module;
The described reason module of assuring also is used for: receiving the data slicer of described packet, wait in the process of traffic classification operating result of described packet, when receiving the data slicer of next packet of described packet, be stored to described next packet corresponding memory space.
7. a packet receiving handling method is characterized in that, comprising:
Receive packet, in the process that receives packet, extract the traffic classification operation information, by default size packet being cut into slices obtains data slicer, whenever receives a data section and then stores this packet corresponding memory space into;
After described packet receives, according to described traffic classification operation information described packet is carried out traffic classification operation, obtain the traffic classification operating result after, extract relevant information and initiate subsequent operation.
8. method as claimed in claim 7 is characterized in that, described default size is the minimum unit of system cache operation or the multiple of minimum unit.
9. method as claimed in claim 7 is characterized in that, described method also comprises:
When handling the packet of a plurality of input ports, use port identification information to distinguish data slicer, traffic classification operation information and the traffic classification operating result of the packet of different input ports.
10. method as claimed in claim 7 is characterized in that,
Described traffic classification operating result comprises message modification information and message descriptor information; Described extraction relevant information comprises the message descriptor information of extracting described packet;
Described method also comprises, the message of described packet is revised information stores in described packet corresponding memory space.
11. method as claimed in claim 10 is characterized in that,
Described method also comprises: in the process that receives packet, preserve the preceding N byte data of described packet, begin to cut into slices after N byte of described packet, described N is that described default size and described message are revised the information difference; When the data slicer of described packet is stored, keep the first memory block of described packet corresponding memory space;
After obtaining the traffic classification operating result of described packet, the message modification information of N byte data before described and described packet is formed the first memory block that the first section of bag is stored in described packet corresponding memory space.
12. as the arbitrary described method of claim 7 to 11, it is characterized in that,
Described method also comprises, after receiving a packet, waits for and receives in the traffic classification operating result process of described packet, carries out reception, section and the data slicer storage operation of next packet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110050489.XA CN102104548B (en) | 2011-03-02 | 2011-03-02 | Method and device for receiving and processing data packets |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110050489.XA CN102104548B (en) | 2011-03-02 | 2011-03-02 | Method and device for receiving and processing data packets |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102104548A true CN102104548A (en) | 2011-06-22 |
| CN102104548B CN102104548B (en) | 2015-06-10 |
Family
ID=44157085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110050489.XA Active CN102104548B (en) | 2011-03-02 | 2011-03-02 | Method and device for receiving and processing data packets |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102104548B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102780618A (en) * | 2012-07-23 | 2012-11-14 | 华为技术有限公司 | Method and device for data message transmission |
| CN103365654A (en) * | 2012-03-29 | 2013-10-23 | A10网络股份有限公司 | Hardware-based packet editor |
| US9661026B2 (en) | 2006-10-17 | 2017-05-23 | A10 Networks, Inc. | Applying security policy to an application session |
| US9942152B2 (en) | 2014-03-25 | 2018-04-10 | A10 Networks, Inc. | Forwarding data packets using a service-based forwarding policy |
| US9954899B2 (en) | 2006-10-17 | 2018-04-24 | A10 Networks, Inc. | Applying a network traffic policy to an application session |
| US10038693B2 (en) | 2013-05-03 | 2018-07-31 | A10 Networks, Inc. | Facilitating secure network traffic by an application delivery controller |
| US10268467B2 (en) | 2014-11-11 | 2019-04-23 | A10 Networks, Inc. | Policy-driven management of application traffic for providing services to cloud-based applications |
| US10341427B2 (en) | 2012-12-06 | 2019-07-02 | A10 Networks, Inc. | Forwarding policies on a virtual service network |
| CN113709061A (en) * | 2021-07-23 | 2021-11-26 | 合肥忆芯电子科技有限公司 | Message forwarding method and circuit |
| CN114168085A (en) * | 2021-12-16 | 2022-03-11 | 潍柴动力股份有限公司 | Variable processing method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1859275A (en) * | 2005-07-27 | 2006-11-08 | 华为技术有限公司 | Multiple port ethernet exchanging device and data transmission method |
| CN1972239A (en) * | 2005-11-24 | 2007-05-30 | 武汉烽火网络有限责任公司 | Ethernet cache exchanging and scheduling method and apparatus |
| CN101136854A (en) * | 2007-03-19 | 2008-03-05 | 中兴通讯股份有限公司 | Method and apparatus for implementing data packet linear speed processing |
-
2011
- 2011-03-02 CN CN201110050489.XA patent/CN102104548B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1859275A (en) * | 2005-07-27 | 2006-11-08 | 华为技术有限公司 | Multiple port ethernet exchanging device and data transmission method |
| CN1972239A (en) * | 2005-11-24 | 2007-05-30 | 武汉烽火网络有限责任公司 | Ethernet cache exchanging and scheduling method and apparatus |
| CN101136854A (en) * | 2007-03-19 | 2008-03-05 | 中兴通讯股份有限公司 | Method and apparatus for implementing data packet linear speed processing |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9954899B2 (en) | 2006-10-17 | 2018-04-24 | A10 Networks, Inc. | Applying a network traffic policy to an application session |
| US10305859B2 (en) | 2006-10-17 | 2019-05-28 | A10 Networks, Inc. | Applying security policy to an application session |
| US9661026B2 (en) | 2006-10-17 | 2017-05-23 | A10 Networks, Inc. | Applying security policy to an application session |
| US10069946B2 (en) | 2012-03-29 | 2018-09-04 | A10 Networks, Inc. | Hardware-based packet editor |
| CN103365654B (en) * | 2012-03-29 | 2017-11-07 | A10网络股份有限公司 | Hardware based Packet editor |
| US9742879B2 (en) | 2012-03-29 | 2017-08-22 | A10 Networks, Inc. | Hardware-based packet editor |
| CN103365654A (en) * | 2012-03-29 | 2013-10-23 | A10网络股份有限公司 | Hardware-based packet editor |
| CN102780618A (en) * | 2012-07-23 | 2012-11-14 | 华为技术有限公司 | Method and device for data message transmission |
| US10341427B2 (en) | 2012-12-06 | 2019-07-02 | A10 Networks, Inc. | Forwarding policies on a virtual service network |
| US10038693B2 (en) | 2013-05-03 | 2018-07-31 | A10 Networks, Inc. | Facilitating secure network traffic by an application delivery controller |
| US10305904B2 (en) | 2013-05-03 | 2019-05-28 | A10 Networks, Inc. | Facilitating secure network traffic by an application delivery controller |
| US9942152B2 (en) | 2014-03-25 | 2018-04-10 | A10 Networks, Inc. | Forwarding data packets using a service-based forwarding policy |
| US10268467B2 (en) | 2014-11-11 | 2019-04-23 | A10 Networks, Inc. | Policy-driven management of application traffic for providing services to cloud-based applications |
| CN113709061A (en) * | 2021-07-23 | 2021-11-26 | 合肥忆芯电子科技有限公司 | Message forwarding method and circuit |
| CN114168085A (en) * | 2021-12-16 | 2022-03-11 | 潍柴动力股份有限公司 | Variable processing method, device, equipment and storage medium |
| CN114168085B (en) * | 2021-12-16 | 2024-02-20 | 潍柴动力股份有限公司 | Variable processing method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102104548B (en) | 2015-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102104548B (en) | Method and device for receiving and processing data packets | |
| JP5863076B2 (en) | Method, apparatus, and system for reconstructing and reordering packets | |
| US6757791B1 (en) | Method and apparatus for reordering packet data units in storage queues for reading and writing memory | |
| JP4480845B2 (en) | TDM switch system with very wide memory width | |
| JP6978596B2 (en) | Data transmission | |
| CN103873550A (en) | Method for data transmission among ecus and/or measuring devices | |
| RU2009133323A (en) | VARIABLE LENGTH OF RADIO LINK CONTROL DATA PACKAGES | |
| CN103748845B (en) | Packet sending and receiving method, device and system | |
| CN108462649B (en) | Method and device for reducing high-priority data transmission delay in congestion state of ONU | |
| CN106685826A (en) | Interchanger stacking system, slave unit, switching chip and method for processing protocol message | |
| US9838500B1 (en) | Network device and method for packet processing | |
| EP3244578B1 (en) | Slave device control method | |
| US20130265869A1 (en) | Systems and Methods for Selective Data Redundancy Elimination for Resource Constrained Hosts | |
| CN106656714A (en) | Communication protocol method and system based on EtherCAT bus | |
| CN108462652A (en) | A kind of message processing method, device and the network equipment | |
| JP4516395B2 (en) | Memory management system with link list processor | |
| CN101964751B (en) | Transmission method and device of data packets | |
| CN106533976A (en) | Data packet processing method and device | |
| CN103634229B (en) | A kind of Inter-chip communication method and control device | |
| CN102595621B (en) | Method and apparatus for parameter storage control at uplink receiving terminal | |
| CN108667755A (en) | A kind of method and apparatus message fragment storage and recombinated | |
| CN110661745B (en) | Overhead transmission method, device, equipment and computer readable storage medium | |
| US20120320909A1 (en) | Sending request messages over designated communications channels | |
| CN107911317B (en) | Message scheduling method and device | |
| CN102546397A (en) | Method, apparatus and device for balancing traffic of uplink aggregation port |
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 | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20151116 Address after: 518057 Nanshan District Guangdong high tech Industrial Park, South Road, science and technology, ZTE building, Ministry of Justice Patentee after: ZTE Corp. Patentee after: SANECHIPS TECHNOLOGY Co.,Ltd. Address before: 518057 Nanshan District Guangdong high tech Industrial Park, South Road, science and technology, ZTE building, Ministry of Justice Patentee before: ZTE Corp. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221207 Address after: 518055 Zhongxing Industrial Park, Liuxian Avenue, Xili street, Nanshan District, Shenzhen City, Guangdong Province Patentee after: SANECHIPS TECHNOLOGY Co.,Ltd. Address before: 518057 Ministry of justice, Zhongxing building, South Science and technology road, Nanshan District hi tech Industrial Park, Shenzhen, Guangdong Patentee before: ZTE Corp. Patentee before: SANECHIPS TECHNOLOGY Co.,Ltd. |