WO2017016300A1 - Procédé et appareil de traitement d'application de jeton, support d'enregistrement informatique - Google Patents

Procédé et appareil de traitement d'application de jeton, support d'enregistrement informatique Download PDF

Info

Publication number
WO2017016300A1
WO2017016300A1 PCT/CN2016/083507 CN2016083507W WO2017016300A1 WO 2017016300 A1 WO2017016300 A1 WO 2017016300A1 CN 2016083507 W CN2016083507 W CN 2016083507W WO 2017016300 A1 WO2017016300 A1 WO 2017016300A1
Authority
WO
WIPO (PCT)
Prior art keywords
application
request
token
sent
flow queue
Prior art date
Application number
PCT/CN2016/083507
Other languages
English (en)
Chinese (zh)
Inventor
张锐
Original Assignee
深圳市中兴微电子技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳市中兴微电子技术有限公司 filed Critical 深圳市中兴微电子技术有限公司
Publication of WO2017016300A1 publication Critical patent/WO2017016300A1/fr

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/215—Flow control; Congestion control using token-bucket

Definitions

  • the present invention relates to the field of communications, and in particular, to a token application processing method, apparatus, and computer storage medium.
  • the packet After the packet is forwarded to the packet, the packet is encapsulated into a cell and sent to the switching network for processing.
  • the end of the packet to the switching network is usually called the access end.
  • the cell After the cell is sent to the switching network, it is sent to the other end according to the carried destination information, and then reassembled into a packet and leaves the routing device.
  • This terminal is usually called the destination.
  • Whether the switching network works in a good state is an important factor to ensure the quality of service. When a large number of data exchanges between the access terminals and the destination end are performed on the switching network, how to avoid the network bandwidth and services caused by the congestion of the switching network The quality is reduced, which is an important function of the traffic management module of the switching network.
  • the traffic management module of the switching network needs to be divided into a plurality of flow queues according to the packet attributes, and the data is sent according to the size of the flow queue. command.
  • the application command includes an application token or a stop application token, and these commands are finally exchanged to the destination in the form of token request cells.
  • the destination end of the switching network delivers the tokens in an orderly manner according to the token application status and the priority attribute of the access end flow queue.
  • the access terminal obtains the token flow queue and can be dequeued. Otherwise, it continues to wait for authorization.
  • the real export capability of the end to effectively control the data traffic sent to the switching network, and determine the order of the flow queue services according to different priorities, can effectively achieve the purpose of avoiding congestion and improving service quality.
  • Some token applications occupy bandwidth due to other token requests, and cannot be sent in time. Therefore, the token cannot be delivered in time, which ultimately leads to a decline in service quality and performance.
  • the embodiments of the present invention are expected to provide a token application processing method, apparatus, and computer storage medium to solve the problem that the token application delay is large and the transmission congestion phenomenon is obvious.
  • a first aspect of the embodiments of the present invention provides a token application processing method, where the method includes:
  • the operation of adding the first identifier information to the sending sequence triggered by the application command is blocked;
  • the sending sequence is used to record the identifier information of each flow queue of the to-be-sent token application.
  • One of the identifiers in the sending sequence indicates that the flow queue corresponding to the identifier information has a pending token request.
  • the first identifier information is added to the sending sequence.
  • the method further includes:
  • the application request for controlling the token request is an application request of the last application command sent by the first flow queue.
  • the method further includes:
  • the method further includes:
  • the first identifier that is triggered by the application command is blocked. Information is added to the operation in the transmission sequence.
  • the method further includes:
  • tag information can be used to characterize whether the first identification information is located in the sending sequence
  • the method further includes:
  • the method further includes:
  • the request to be sent of each of the flow queues is sequentially executed according to the sequence in which the identification information of each flow queue enters the transmission sequence.
  • a second aspect of the embodiments of the present invention provides a token application processing apparatus, where the apparatus includes:
  • the determining unit is configured to: when receiving the application command of the first flow queue, determine whether the first identifier information of the first flow queue is included in the sending sequence;
  • a processing unit configured to: if the first identifier information is included in the sending sequence, masking an operation of adding the first identifier information to the sending sequence triggered by the application command;
  • the sending sequence is used to record identifier information of each flow queue of the token request to be sent;
  • the identifier information in the sending sequence indicates that the flow queue corresponding to the identifier information has a token request to be sent.
  • the processing unit is further configured to add the first identifier information to the sending sequence if the first identifier information is not included in the sending sequence.
  • the device further includes:
  • a recording unit configured to record an application request of a previous sent token request of the first flow queue
  • the first comparison unit is configured to compare whether the application request of the token request to be sent in the current flow queue is the same as the application request of the previous sent token request of the first flow queue;
  • the terminating unit is configured to terminate the first request if the application request of the token request to be sent in the current flow queue is the same as the application request of the previous sent token request of the first flow queue The sending of the token request to be sent this time in the flow queue.
  • the device further includes:
  • a recording unit configured to record an application request of a previous sent token request of the first flow queue
  • a second comparison unit configured to compare whether the application request in the application command of the first flow queue is the same as the application request of the previous sent token request
  • the processing unit is further configured to: if the application request in the application command of the first flow queue is the same as the application request of the previous sent token request, shielding the first application triggered by the application command The identification information is added to the operation in the transmission sequence.
  • the device further includes:
  • the control unit is configured to, when the token request of the first flow queue is sent based on the sending sequence, control an application request of the token request as an application request of the application command sent by the first flow queue last time.
  • the device further includes:
  • the rate limiting unit is configured to send a to-be-sent token request corresponding to the identifier information in the sending sequence according to the sending rate threshold.
  • the determining unit is configured to query the tag information, wherein the tag information can be used to indicate whether the first identifier information is located in the sending sequence; and based on the information content of the tag information, Whether the first identification information is located in the sending sequence.
  • the device further includes:
  • an updating unit configured to update the information content of the tag information based on whether the first identifier information is located in the sending sequence.
  • the device further includes:
  • a sending unit configured to enter the sending sequence according to the identification information of each of the flow queues In the order of sequence, the to-be-sent token requests of each of the flow queues are sequentially executed.
  • An embodiment of the present invention provides a computer storage medium, where the computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute at least one of the token application processing methods.
  • the token application processing method and apparatus and the computer storage medium determine whether the first identification information of the first flow queue that sends the application command is located in the transmission sequence, and if the first identification information is already in the transmission sequence, the shielding is performed.
  • the first identification information is added to the operation in the transmission sequence. In this way, the identification information of the same flow queue can be prevented from being added to the transmission sequence again, thereby avoiding the formation of multiple repeated token requests to be sent, reducing the probability of sending duplicate token requests by the same flow queue and reducing the redundant token application and The bandwidth occupied by the redundant token request. In this way, it is possible to reduce the transmission delay and transmission congestion caused by the bandwidth request of the normal token application by the redundant token application.
  • FIG. 1 is a schematic flowchart of a token application processing method according to an embodiment of the present invention
  • FIG. 2 is a second schematic flowchart of a token application processing method according to an embodiment of the present invention.
  • FIG. 3A is a schematic diagram of a flow of repeated token application filtering according to an embodiment of the present invention.
  • FIG. 3B is a second schematic diagram of a flow of repeated token application filtering according to an embodiment of the present invention.
  • FIGS. 4A to 4E are schematic diagrams showing the structure of a token application processing apparatus according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of another token application processing apparatus according to an embodiment of the present disclosure.
  • FIG. 6 is a third schematic flowchart of a token application processing method according to an embodiment of the present invention.
  • the token request needs to be sent.
  • the access terminal may send the application multiple times in a short period of time.
  • the action of the token can be sent once to achieve the purpose of applying for the token.
  • the transmission of the token will inevitably result in wasted bandwidth.
  • the flow queue of other application tokens must wait for the application of the flow queue to be sent before sending, which will result in The application delay is increased, so that the period of the token service is extended, which will inevitably lead to a decline in service quality.
  • the token application may have persistent congestion, which will result in the failure of many flow queue token requests to be communicated in time, resulting in a series of management failures.
  • the embodiment of the present invention provides a token application processing method.
  • a flow queue can be restricted to have only one pending token request at a time, that is, a flow queue can only send an order through an application command at a time.
  • Card application to avoid multiple duplicate token requests for the same stream queue. This can effectively reduce the total number of token applications in the switching network, avoid the flooding of token applications, and reduce the bandwidth occupied by duplicate token requests, thereby providing more bandwidth resources to send non-repeating token requests.
  • the problem of flooding and delay of token application is solved once.
  • the destination can also avoid the processing of duplicate token requests, which can improve the processing efficiency of token applications.
  • this embodiment provides a token application processing method, where the method includes:
  • Step S110 When receiving the application command of the first flow queue, determine whether the transmission sequence is Include first identification information of the first flow queue;
  • Step S120 If the first identifier information is included in the sending sequence, the operation of adding the first identifier information to the sending sequence triggered by the application command is blocked;
  • the sending sequence is used to record identifier information of each flow queue of the token request to be sent;
  • the identifier information in the sending sequence indicates that the flow queue corresponding to the identifier information has a token request to be sent.
  • the first flow queue does not specifically refer to a certain flow queue, but refers to any one of all flow pairs.
  • the first identifier information is an identifier of the first flow queue, and specifically may be information such as a queue number or a queue name of the first flow queue that can distinguish the first flow queue.
  • the first identification information is information used to identify the first flow queue among the plurality of identification information of the sending sequence. When a token request is sent, the identification information of the flow queue corresponding to the token request in the sequence is deleted.
  • the sending sequence may be a first in first out (FIFO) queue, and the sending queue sequentially adds the identification information of the corresponding stream queue to the sending sequence according to the received application command.
  • the duplicate token application formed by repeatedly sending the application command is firstly performed in step S110 of the embodiment. It is determined whether the first identifier information of the first flow queue has been included in the sending queue. If the first identifier information is included in the sequence, the first flow queue is considered to have a token request to be sent, and the request to trigger the formed token application has a large probability that the duplicate token application is caused. Therefore, the step of masking the first identification information into the transmission sequence is masked in step S120.
  • step S110 when it is determined whether the sending sequence includes the first identifier information, the first identifier information may be compared with each identifier information in the sending sequence to be confirmed one by one.
  • the first identification information may be added again in the transmission sequence.
  • the first flow queue can only have one pending token request at a time, and only one token request is sent at a time when the pending token application is sent; this can greatly reduce the duplicate token request and avoid the token application.
  • the method further includes:
  • Step S130 If the first identifier information is not included in the sending sequence, add the first identifier information to the sending sequence.
  • the step S130 and the step S120 are parallel operation steps, and there is no certain order.
  • adding the first identifier information to the sending sequence so that by updating the sending sequence, the first stream queue may be assigned to form a to-be-sent token request and Send a token request opportunity.
  • each stream pair has an opportunity to send a token request to the target end, which improves the fairness of the token application process.
  • the rate and probability of response which can increase the communication rate, reduce information leakage, and improve communication quality.
  • the method further includes:
  • the application request for controlling the token request is an application request of the application command sent last time by the first flow queue.
  • the application request is included in each application command.
  • the application request generally includes two types of requesting a request token and requesting to stop the application token.
  • the application request of the token application is the application request in the last application command.
  • the application request for the application token is ON, and the application request for stopping the application token is OFF.
  • a flow queue continuously sends four application commands, and the application requests for the four application commands are ON-ON-ON-ON.
  • the application request of the token request is ON in the final application command.
  • the application request in the four application commands sent by the flow queue is ON-OFF-ON-OFF, etc., when the token request of the first flow queue is sent, the application request of the token application is OFF in the final application command. can.
  • the first flow queue forms 4 application commands. If the method according to the prior art is used, 4 token applications should be sent, so that there are 4 token requests of the first flow queue in the exchange network; and the 4 tokens The application is for 4 duplicate token requests or two or two invalid token requests.
  • the number of tokens is first reduced, and secondly, the congestion and bandwidth occupation caused by the duplicate token application, the invalid token application, and the interference to the destination end are reduced.
  • the method further includes:
  • Step S101 Record an application request of a previous sent token request of the first flow queue
  • Step S102 Compare whether the application request of the token application to be sent this time is the same as the application request of the previous sent token application;
  • Step S103 If the application request of the token application to be sent is the same as the application request of the previous sent token request, the sending of the token request triggered by the application command is terminated.
  • the two in this mode refer to the application request of the token application to be sent this time and the application request of the previous sent token request.
  • the method further includes:
  • Step S201 Record an application request of a previous sent token request of the flow queue
  • Step S202 Compare whether the application request in the application command of the first flow queue is the same as the application request of the previous sent token application
  • Step S203 If the application request in the application command of the first flow queue is the same as the application request of the previous sent token request, then the first identification information triggered by the application command is added to the Send the operation in the sequence.
  • the two in this mode refer to the application request in the application command of the first flow queue and the application request of the previous sent token application.
  • the token request that is sent to the same destination and the application request is the same is also filtered, and the record of the application request of the previous token application is also passed, and this time
  • the comparison of application requests for application orders avoids repeated transmissions to reduce redundant token requests again.
  • the application request is ON.
  • the application request of the first flow queue is received again, and the application command also indicates that the application request is ON to the target A. brand.
  • you respond directly it will also result in a duplicate token request.
  • the application timing of the foregoing first mode and the second mode in this embodiment is when the previous sent token request has not received the destination end response. If the previous token request has been responded and the first stream queue data is being sent or sent, this time is equivalent to re-applying the token again and will not form a duplicate token request.
  • each time a flow queue sends a token application command the application request sent this time is recorded, and the queue is stored for storage.
  • the distinguishing queue storage can be understood as requesting for different flow queues and storing separately.
  • the application request of the flow queue A and the application request of the flow queue B are separately stored.
  • an area is allocated from the RAM for storing the application request of the flow queue A, and another area is used for storing the application of the flow queue B. begging.
  • the application request sent last time needs to be read first, and compared with the application request to be sent this time. If it is found that the application request sent twice is the same, then this time is considered The token application is unnecessary.
  • the token application sent by the application command is filtered out, or the token request formation and sending operation triggered by the token application is blocked.
  • the method is further improved, in order to avoid the one-time sending of too many token applications, causing congestion.
  • the method further includes:
  • the transmission rate here can be understood as the rate at which the number of token requests is sent, and can also be understood as the transmission rate of the data amount. If the transmission rate is the rate of the number of token requests, the transmission restriction control is performed by counting the number of transmissions and the number of transmissions of the token request. If the data rate is sent, it may be necessary to calculate the number of token requests and each data amount to limit the transmission rate.
  • the step S110 may further include:
  • identifier information can be used to identify whether the first identifier information is located in the sending sequence
  • a method for determining whether the first identification information is located in the transmission sequence is provided.
  • one tag information is set for each of the stream queues; the tag information may correspond to one or more tag bits, and the value of the tag bit is the information content.
  • the transmission sequence may be considered to include the identification information of the flow queue C. Otherwise, the identification information of the flow queue C is not included in the transmission sequence. Avoiding the first identification information and each marking information in the transmission sequence by setting the marking information The comparison is performed one by one, so that the judgment efficiency of step S110 can be improved.
  • the method further comprises updating the information content of the tag information based on whether the first identification information is located in the transmission sequence.
  • the identifier information is removed from the sending sequence, and the subsequent operations are facilitated accordingly, and the marking information is also updated accordingly.
  • the marking information is also updated, so that the marking confidence is updated to indicate that the first identification information is included in the sending sequence.
  • the sending sequence may be selected as a FIFO sequence.
  • the processing device when the processing device forms and sends the token request, the processing device performs the order according to the sending order of the application commands of the respective flow queues, so that the order can be performed. management. Therefore, the method further includes: performing the to-be-sent token application of the flow queue in sequence according to the sequence of the identification information of each of the flow queues entering the sending sequence.
  • the current device includes three flow queues, which are Q1, Q2, and Q3 respectively. If the order of four application commands sent by the three flow queues is Q2, Q1, Q1, and Q3, the information is sorted in the sending sequence. In turn, Q2, Q1, and Q3; the order in which token requests are sent is Q2, Q1, and Q3.
  • the present embodiment provides a token application method, which can reduce redundant token applications, reduce congestion caused by redundant token applications, improve response rate and processing efficiency of token applications, and improve communication service quality.
  • the embodiment provides a token application processing apparatus, and the apparatus includes:
  • the determining unit 110 is configured to: when receiving the application command of the first flow queue, determine whether the first identification information of the first flow queue is included in the sending sequence;
  • the processing unit 120 is configured to: if the first identification information is included in the sending sequence, the screen And an operation of adding the first identification information to the sending sequence triggered by the application command;
  • the sending sequence is used to record identifier information of each flow queue of the token request to be sent;
  • the identifier information in the sending sequence indicates that the flow queue corresponding to the identifier information has a token request to be sent.
  • the specific structure of the determining unit 110 and the processing unit 120 may include a processor or a processing circuit.
  • the processing circuit can include an application specific integrated circuit ASIC.
  • the processor may include processing results such as an application processor AP, a central processing unit CPU, a microprocessor MCU, a digital signal processor DSP, or a programmable array PLC.
  • the processor is coupled to the storage medium via an internal communication bus.
  • the processor executable instructions are stored on the storage medium, and the processor reads and executes the executable instructions, and the functions of the determining unit 110 and the processing unit 120 can be respectively implemented.
  • the transmit sequence can be a FIFO queue.
  • the same flow queue can be effectively prevented from repeatedly forming multiple identical token requests in a short period of time, thereby reducing
  • the redundant token application saves the bandwidth resources occupied by the redundant token application and improves the response rate and communication service quality.
  • the processing unit 120 is further configured to add the first identifier information to the sending sequence if the first identifier information is not included in the sending sequence.
  • the first identifier information is added to the sending sequence, so that the fairness of sending the token request by each stream queue is improved. It avoids the problem that some flow queues can not preempt the corresponding resources and cannot send token requests or the transmission probability is small and timely.
  • the apparatus is further improved, and the following two structures are further improved.
  • the device further includes:
  • the recording unit 131 is configured to record an application request of the previous sent token request of the first flow queue
  • the first comparison unit 132 is configured to compare whether the application request of the token application to be sent this time is the same as the application request of the previous sent token request;
  • the termination unit 133 is configured to terminate the token request to be sent if the application request of the token request to be sent in the first flow queue is the same as the application request of the previous sent token request. Send.
  • the recording unit 131 may include a storage medium, which may be a storage medium such as a RAM or a flash memory, configured to store an application request for a previous sent token request.
  • a storage medium such as a RAM or a flash memory
  • the first comparison unit 132 can include a processor or processing circuitry.
  • the processing circuit can include a comparator. By comparing the two application requests, it is determined whether the application request of the two previous sent token requests is the same as the request request of the token request to be sent this time. If the same, if the sending operation continues, the redundancy will be caused.
  • the token application in this embodiment, is further provided that the termination unit will terminate the transmission of the token request.
  • the structure corresponding to the termination unit may also be a processor or a processing circuit.
  • the device further includes:
  • the recording unit 131 is configured to record an application request of the previous sent token request of the first flow queue
  • the second comparison unit 141 is configured to compare whether the application request in the application command of the first flow queue is the same as the application request of the previous sent token request;
  • the processing unit 120 is further configured to: if the application request in the application command of the first flow queue is the same as the application request of the previous sent token request of the first flow queue, An operation of adding the first identification information to the transmission sequence triggered by an application command.
  • the structure of the recording unit 131 can be as shown in the structure of the recording unit, and can also include various kinds of the storage medium.
  • the structure of the second comparing unit is similar to that of the first comparing unit, but the compared parameters are different.
  • two inputs of the second comparing unit one for the previous sent token application Request for application, another request for this application.
  • the process 120 will determine, based on the comparison, that when the two input application requests are the same, the first identification information is not added again in the transmission sequence, and the transmission of the redundant token application can also be reduced.
  • the device further includes:
  • the control unit 150 is configured to, when transmitting the token request of the first flow queue based on the sending sequence, control an application request of the token request as an application request of the last application request.
  • the specific structure of the control unit 150 may include a processor.
  • the application request of the token application is subject to the last application command, that is, the The application request for the token application is the application request for the last token application. This can more accurately reflect the current needs of the flow queue.
  • the device further includes:
  • the rate limiting unit 151 is configured to send a to-be-sent token request corresponding to the identifier information in the sending sequence according to the sending rate threshold.
  • the specific structure of the rate limiting unit 151 may include an information processing structure such as a communication interface and a counter, and can generally limit the sending rate of the token request, avoid congestion caused by too many token application transmissions, and ultimately result in an overall transmission rate. Low problem.
  • the determining unit 110 is configured to query whether the first identifier information is located in the sending sequence, and the marking information is based on the marking information.
  • the information content determines whether the first identification information is located in the sending sequence.
  • the determining unit 110 determines whether the transmission sequence includes the first identification information according to the marking information, so that the determination speed is fast and the determining step is simple.
  • the apparatus further includes: an updating unit, configured to update the information content of the tag information based on whether the first identification information is located in the sending sequence .
  • the structure of the update unit may include a processor or processing circuit and a storage medium, and the processor or processing circuit may be used to update identification information in the storage medium.
  • the device further includes:
  • the sending unit 152 is configured to sequentially execute the to-be-sent token request of each of the flow queues according to the sequence of the identification information of each of the flow queues entering the sending sequence.
  • the sending unit 152 may include a communication interface, where the communication interface is used to send the token request, but the sending order of the token request is consistent with the sending order of the identifier information in the sending sequence.
  • the transmission sequence is a FIFO sequence. If the identification information of a flow queue first enters the transmission sequence, the corresponding to-be-sent token request will be sent preferentially.
  • the embodiment provides a token application processing device, which can be used as a hardware device for implementing the token application processing method in the foregoing method embodiment, and has the same redundancy for reducing the token application in the switching network, thereby saving
  • the bandwidth resource of the redundant token application can realize the transmission and processing of the token application more fairly and more efficiently, and improve the communication service instruction and efficiency.
  • the present example provides a token request processing apparatus, and the apparatus includes at least a flow queue filtering module 301, a flow queue state filtering module 302, and a sending shaping module 303.
  • the flow queue filtering module 301 can be used to maintain a sending sequence and an application request form. Said hair In the sending sequence, according to the application command received from the pre-stage module 304, the identifier information of the flow queue for sending the application command is stored, and the identifier information may be a queue number or the like. The transmission sequence does not repeatedly store identification information of the same flow queue.
  • the application request form is stored as an application request for the last application request of the same flow queue.
  • the flow queue filtering module 301 herein may be a composition result of the foregoing determining unit 110.
  • the flow queue state filtering module 302 can be used to maintain a token status sending table.
  • the token status sending table stores an application request for the last time the token request has been sent by each stream queue.
  • the flow queue state filtering module 302 in this example may correspond to the recording unit, the first comparison unit, and the termination unit in the foregoing embodiment; or correspond to the recording unit, the second ratio comparison unit, and the processing unit in the foregoing embodiments.
  • the sending and shaping module 303 is configured to limit the sending rate of the token request, avoid the congestion caused by the excessive number of sent or the excessive number of token applications, and also send the token request to the suffix module.
  • the transmit shaping module 303 in this example may be an integral part of the aforementioned transmitting unit.
  • the pre-stage module 304 and the post-stage module 305 are provided for describing the present example device, and are not limiting to implement the technical solution of the present invention.
  • the location of the flow queue filter module 301 and the flow queue state filtering module 302 may be reversed, or the flow queue state filtering module 302 may not need to be used in a loose application scenario such as rich bandwidth resources.
  • This example is based on the token request processing apparatus shown in FIG. 5, and provides a token request processing method.
  • the method described in this example includes:
  • Step 210 The flow queue filtering module 301 receives the application command, and stores the application request queue in the application command in the application request form.
  • the current device forms three flow queues, which are Q1, Q2, and Q3, respectively.
  • the front-end module 304 sends Q1-ON, Q2-OFF, Q3-ON, Q2-ON, and Q1-OFF information in a short period of time. You can use a piece of RAM to store this information in a queue.
  • the access address of the RAM is the queue number of Q1, Q2, and Q3, and the application request such as ON or OFF is written.
  • the queue number here is equivalent to the aforementioned identification information or identification information.
  • ON indicates the application token
  • OFF indicates the stop token request. Multiple application requests for the same flow queue, subsequent application requests overwrite the previous values. Then the state stored in the final RAM during this period is: address Q1 is OFF, address Q2 is ON, and address Q3 is ON.
  • Step 220 The flow queue filtering module 301 uses a FIFO to implement the function of sending sequence queuing, and stores the queue number of the flow queue that sends the request request in the FIFO for transmission. At this time, it is necessary to judge whether a queue has been waiting for transmission in the FIFO by a tag. If it is already in the FIFO, it is not necessary to join the FIFO again, otherwise it is added to the FIFO and waits for transmission. This tag is one of the aforementioned tag information.
  • the specific operation is as follows: When a flow queue generates an application command and is ready to be sent to the destination end of the switching network, the queue number of the flow queue needs to exist in a FIFO, but before being stored in the FIFO, the flow queue needs to be read first.
  • the tag is used to determine whether the queue number of the stream queue has been written into the FIFO. When the flag is 1, the current queue is already in the FIFO, and the other 0 is not in the FIFO.
  • the tag is stored in a RAM, which is called a queue filter table, and its read/write address can correspond to the queue number of each stream queue.
  • the identifier of the read stream queue is 1, it indicates that the stream queue number has been written into the FIFO and does not need to be written again; if the read stream queue identifier is 0, it indicates that the stream queue number is not in the FIFO.
  • the queue number of the flow queue needs to be written into the FIFO to wait for the token request to be sent, and the identifier corresponding to the queue is set to 1, in case the queue number is written to the FIFO again.
  • the identifier of the flow queue needs to be set to 0, indicating that the queue has been read from the FIFO and allowed to be written again.
  • the current device forms three flow queues, which are Q1, Q2, and Q3.
  • the application command received by the flow queue filtering module 301 is: Q1-ON, Q2-OFF, Q3-ON, Q2-ON, Q1-OFF, etc., assuming that the queue number of Q1, Q2, and Q3 is not stored in the transmission sequence FIFO, then The first three transmissions will write Q1, Q2, and Q3 to the FIFO in turn, and will be If the identifier is set to 1, then the next two Q2 and Q1 will not be written into the FIFO again, thus achieving the purpose of filtering out the next two transmissions.
  • the queue number ranked first in the sending queue is taken out, then the application request stored in the application request table is read, the latest application request is taken out to form a token request, and the token is sent.
  • Application
  • Step 230 The flow queue sending status filtering module maintains a token request request sending table, and each time the token request is sent, the latest sent token request application request is updated to the token request request sending table.
  • the token request request sending table is queried according to the queue number in the sending sequence, and the request for the token request sent by the flow queue is determined, and the token application is the same.
  • the application request is compared with the application request of the previous token application, and if the two are the same, the current transmission is terminated; otherwise, the token request is sent, and the token status sending table is updated based on the application request of the token application. in.
  • the subsequent module 305 After receiving the token request request of the queue, the subsequent module 305 finally encapsulates the information into a message to be sent to the exchange network.
  • Step 240 The sending shaping module 303 sets an shaping value according to the average processing rate of the switching network to limit the sending rate of the token request.
  • the specific implementation may include: setting a configurable transmission rate threshold, implemented by a counting device, allowing a token application to be sent once every time a certain time is counted, and restricting the first two levels of token application by flow control at other times Send rate.
  • the average processing rate corresponds to the foregoing sending rate threshold, and the sending rate threshold may be set in advance, or may be dynamically set according to a processing rate of the switching network.
  • the token application processing device is mainly composed of three parts, namely, a flow queue filtering, a flow queue state filtering module 302, and a transmission shaping module 303.
  • the token application processing device can achieve good results by the interaction and supplement of the above three modules. Due to the presence of the transmit shaping module 303, the transmission rate is limited. The large number of application commands frequently generated by the pre-stage module 304 need to be queued and sent in the flow queue filtering module 301. In the queuing process, the status of the same flow queue is reduced by avoiding repeated queuing transmission of the same queue.
  • the flow queue status filtering module 302 Detecting the same flow queue twice to send an application request, If the request is the same, you can block the sending of the next token request.
  • the embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores computer executable instructions, and the computer executable instructions are used in at least one of the token application processing methods as described above, for example, FIG. At least one of the methods shown in FIG. 2, FIG. 3A, FIG. 3B, and FIG.
  • the computer storage medium may be a removable storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like, which can store program code. Selected as a non-transient storage medium.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner such as: multiple units or components may be combined, or Can be integrated into another system, or some features can be ignored or not executed.
  • the coupling, or direct coupling, or communication connection of the components shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, and may be electrical, mechanical or other forms. of.
  • the units described above as separate components may or may not be physically separated, and the components displayed as the unit may or may not be physical units, that is, may be located in one place or distributed to multiple network units; Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may be separately used as one unit, or two or more units may be integrated into one unit; the above integration
  • the unit can be implemented in the form of hardware. It can also be implemented in the form of hardware plus software functional units.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Small-Scale Networks (AREA)

Abstract

La présente invention concerne un procédé et un appareil de traitement d'une application de jeton, le procédé consistant à : lors de la réception d'une commande d'application en provenance d'une première file d'attente de flux, déterminer si des premières informations d'identifiant de la première file d'attente de flux sont incluses dans une séquence de transmission; si les premières informations d'identifiant sont incluses dans la séquence de transmission, masquer l'opération, déclenchée par la commande d'application, consistant à ajouter les premières informations d'identifiant à la séquence de transmission, ladite séquence de transmission étant utilisée pour enregistrer les informations d'identifiant de chaque file d'attente de flux qui doit transmettre l'application de jeton, et un élément des informations d'identifiant dans la séquence de transmission indiquant une application de jeton à transmettre dans la file d'attente de flux correspondant aux informations d'identifiant. Le mode de réalisation de la présente invention concerne également un support d'enregistrement informatique.
PCT/CN2016/083507 2015-07-29 2016-05-26 Procédé et appareil de traitement d'application de jeton, support d'enregistrement informatique WO2017016300A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510455946.1 2015-07-29
CN201510455946.1A CN107040478A (zh) 2015-07-29 2015-07-29 令牌申请处理方法及装置

Publications (1)

Publication Number Publication Date
WO2017016300A1 true WO2017016300A1 (fr) 2017-02-02

Family

ID=57884805

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/083507 WO2017016300A1 (fr) 2015-07-29 2016-05-26 Procédé et appareil de traitement d'application de jeton, support d'enregistrement informatique

Country Status (2)

Country Link
CN (1) CN107040478A (fr)
WO (1) WO2017016300A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114430362A (zh) * 2021-12-28 2022-05-03 东莞市李群自动化技术有限公司 链路切换的方法、fpga芯片、设备及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111556114A (zh) * 2020-04-26 2020-08-18 天津中新智冠信息技术有限公司 信息交互方法、装置和服务器

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050047425A1 (en) * 2003-09-03 2005-03-03 Yonghe Liu Hierarchical scheduling for communications systems
US7555579B2 (en) * 2004-05-21 2009-06-30 Nortel Networks Limited Implementing FIFOs in shared memory using linked lists and interleaved linked lists
CN101902487A (zh) * 2009-05-26 2010-12-01 中兴通讯股份有限公司 基于链表的队列调度方法与装置
CN103107996A (zh) * 2013-02-07 2013-05-15 北京中视广信科技有限公司 数字证书在线下载方法及系统、数字证书发放平台

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101808037B (zh) * 2010-03-15 2014-09-10 中兴通讯股份有限公司 交换网中流量管理的方法和装置
CN103188160B (zh) * 2013-04-18 2016-12-07 杭州华三通信技术有限公司 一种流量控制方法和转发单元

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050047425A1 (en) * 2003-09-03 2005-03-03 Yonghe Liu Hierarchical scheduling for communications systems
US7555579B2 (en) * 2004-05-21 2009-06-30 Nortel Networks Limited Implementing FIFOs in shared memory using linked lists and interleaved linked lists
CN101902487A (zh) * 2009-05-26 2010-12-01 中兴通讯股份有限公司 基于链表的队列调度方法与装置
CN103107996A (zh) * 2013-02-07 2013-05-15 北京中视广信科技有限公司 数字证书在线下载方法及系统、数字证书发放平台

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114430362A (zh) * 2021-12-28 2022-05-03 东莞市李群自动化技术有限公司 链路切换的方法、fpga芯片、设备及存储介质
CN114430362B (zh) * 2021-12-28 2024-04-12 东莞市李群自动化技术有限公司 链路切换的方法、fpga芯片、设备及存储介质

Also Published As

Publication number Publication date
CN107040478A (zh) 2017-08-11

Similar Documents

Publication Publication Date Title
US11799764B2 (en) System and method for facilitating efficient packet injection into an output buffer in a network interface controller (NIC)
KR102317523B1 (ko) 패킷 제어 방법 및 네트워크 기기
US9800513B2 (en) Mapped FIFO buffering
EP2466824B1 (fr) Dispositif et procédé de programmation de services
US8867559B2 (en) Managing starvation and congestion in a two-dimensional network having flow control
US10122623B2 (en) Control device and control method in SDN network
CN109684269B (zh) 一种pcie交换芯片内核及工作方法
CN104468401A (zh) 一种报文处理方法和装置
WO2022089175A1 (fr) Procédé et appareil de régulation d'encombrement de réseau
US11876859B2 (en) Controlling packet delivery based on application level information
WO2017016300A1 (fr) Procédé et appareil de traitement d'application de jeton, support d'enregistrement informatique
WO2019109902A1 (fr) Procédé et appareil de planification de file d'attente, dispositif de communication et support de stockage
WO2017000861A1 (fr) Procédé et appareil permettant l'apprentissage d'adresse mac dans un réseau local virtuel de commutateur
WO2023093805A1 (fr) Procédé de commande de stockage, contrôleur de stockage, puce de stockage, carte réseau et support lisible
WO2020082839A1 (fr) Procédé de traitement de message, dispositif associé et support de stockage informatique
CN113157465B (zh) 基于指针链表的消息发送方法及装置
CN113765796B (zh) 流量转发控制方法及装置
US9621487B2 (en) Method and apparatus for protection switching based on memory control in packet transport system
WO2021208101A1 (fr) Procédé et appareil de traitement de services dynamiques
US9674282B2 (en) Synchronizing SLM statuses of a plurality of appliances in a cluster
CN115396380B (zh) 基于时间敏感网络的数据流传输方法、装置及设备
WO2024011907A1 (fr) Procédé de programmation de données, dispositif électronique et support de stockage
WO2022227568A1 (fr) Procédé de transmission de données, nœud de réseau, système optique et support de stockage
WO2023207628A1 (fr) Procédé de transmission de paquets et dispositif de transfert de paquets
CN117749726A (zh) Tsn交换机输出端口优先级队列混合调度方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16829667

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16829667

Country of ref document: EP

Kind code of ref document: A1