CN115378758B - Multi-node SRIO bus self-adaptive flow control method based on priority strategy - Google Patents
Multi-node SRIO bus self-adaptive flow control method based on priority strategy Download PDFInfo
- Publication number
- CN115378758B CN115378758B CN202210888143.5A CN202210888143A CN115378758B CN 115378758 B CN115378758 B CN 115378758B CN 202210888143 A CN202210888143 A CN 202210888143A CN 115378758 B CN115378758 B CN 115378758B
- Authority
- CN
- China
- Prior art keywords
- node
- priority
- transmission
- receiving
- flow control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L12/40143—Bus networks involving priority mechanisms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/003—Transmission of data between radar, sonar or lidar systems and remote stations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a multi-node SRIO bus self-adaptive flow control method based on a priority strategy, which mainly solves the problems that in the radar SRIO data transmission process, the task amount of a certain SRIO receiving node is increased suddenly to reduce the system processing efficiency and a plurality of SRIO sending nodes occupy buses simultaneously to cause the SRIO link abnormality, and mainly comprises the following steps: the scheduling module sets the initial priority of each node and completes the communication handshake between the sending node and the receiving node; the scheduling module sends a transmission enabling signal to each sending node according to the initial priority, and meanwhile, data flow control is carried out among transmission periods of each sending node; data flow control is carried out between each sending node and different receiving nodes and between the minimum data transmission periods; the scheduling module readjusts the priority strategies of each sending node and each receiving node in the sector according to the task quantity change of each sending node and each receiving node in the sector; the scheduling module starts the data stream control transmission and priority strategy adjustment of the next sector.
Description
Technical Field
The invention belongs to the field of radar communication transmission.
Background
The SRIO interconnection framework is used as an open interconnection protocol standard based on reliability, and can provide a solution for high-bandwidth and low-delay data transmission among devices of a communication system according to the characteristics of high efficiency, high stability, low system cost and the like. The SRIO has the switching function, has complete packet switching, response, interruption and fault tolerance mechanisms, has high reliability and higher transmission efficiency than PCIE and gigabit Ethernet, and can provide high-performance interconnection for chip to chip and board to board.
With the increasing complexity of modern radar systems, the exchange mode of SRIO data is gradually changed from single node to single node and from single node to multiple node and from multiple node to multiple node. In the application occasion of single node to multi-node data transmission, the order of data transmission of each receiving node is generally designed according to the ID number of the node, when the receiving order is positioned at the final node to process the rapid increase of the task quantity, the task processing of other nodes is required to wait for the final node all the time after the task processing of other nodes is completed, so that the processing efficiency of the system is reduced; in the application occasion of multi-node to multi-node data transmission, each node transmits data without paying attention to the bus state of the SRIO switching network, the data of the node is directly sent to a receiving node through the SRIO switching network, when a plurality of SRIO sending nodes occupy buses at the same time, the problems that the SRIO network loses data packets and the buses are busy and cannot be recovered are caused, and the SRIO network can be recovered to be normal only by a power-off restarting mode. Aiming at the problem that the processing efficiency of a system is reduced due to the steep increase of the task quantity of a certain node and the problem that a plurality of SRIO transmitting nodes occupy buses at the same time to cause the abnormality of SRIO links, the priority strategies of each transmitting node and each receiving node are adaptively adjusted according to the change of the task quantity of a sector in an adjacent radar period, so that the processing efficiency of the system is improved, and a multistage flow control mechanism is designed between the data transmission periods of the adjacent transmitting nodes, between the data transmission periods of a single transmitting node and different receiving nodes and between the data transmission periods of the minimum data packets, so that the data among multiple nodes can be reliably transmitted in an SRIO switching network.
Disclosure of Invention
Aiming at the problems that the system processing efficiency is reduced due to the abrupt increase of the task quantity of a certain SRIO receiving node in the radar SRIO data transmission process and the SRIO links are abnormal due to the fact that a plurality of SRIO sending nodes occupy buses simultaneously, a multi-node SRIO bus self-adaptive flow control method based on a priority strategy is provided.
The invention is realized by adopting the following technical scheme:
step one: the scheduling module enumerates all nodes in the SRIO topology, initializes the priority of each node, and informs the sending node of completing communication handshake with the corresponding receiving node according to the initial priority;
step two: the scheduling module sends a transmission enabling signal to each sending node according to the initial priority order of each node in the current radar sector, and meanwhile, a flow control time slot is inserted between the transmission periods of each sending node;
preferably, in the second step, the method for inserting the flow control time slot between transmission periods of each sending node includes: the scheduling module receives the nth transmissionAfter the end of the sending data fed back by the node, entering a data flow control stage of a sending node stage, wherein the flow control time for the end of the sending of the nth sending node is T send (n) the calculation formula is:
T send (n)＝0.05*[T(n) begin -T(n) end ],n＝1…N-1；
wherein T (n) begin T (n) is the transmission enabling initiation time of the scheduling module to the nth transmitting node end And when the scheduling module receives the data transmission end doorbell time of the nth transmitting node, N is the number of the transmitting nodes.
Step three: each sending node starts data transmission according to the transmission enabling of the scheduling module, and a flow control time slot is inserted between the current sending node and the data transmission periods of different receiving nodes and between the minimum data transmission periods until all data transmission of the current radar sector is finished, and a transmission end doorbell is sent to the scheduling module;
preferably, the method for inserting the flow control time slot between the data transmission periods of the sending node and the different receiving nodes in the third step comprises the following steps: when the current SRIO sending data corresponds to a plurality of receiving data nodes, finishing sending the data to the mth receiving node, entering a data flow control stage of the receiving node level, wherein the flow control time is t recv (m) the calculation formula is:
t recv (m)＝0.05*[t(m) begin -t(m) end ],m＝1…M-1
wherein t (m) begin A transmission enabling initiation time, t (m), for a current transmitting node to an mth receiving node end The method comprises the steps that when the transmission enabling end time from a current sending node to an mth receiving node is reached, M is the number of the receiving nodes; the method for inserting the flow control time between the minimum data transmission periods comprises the following steps: after the current transmitting node finishes transmitting the minimum transmission packet, the current transmitting node enters a data flow control stage of the minimum transmission packet level, and the flow control time between the two minimum transmission packets is T pack The calculation formula is as follows: t (T) pack ＝1/f clk *64, where f clk The frequency of the reference clock is sent for SRIO.
Step four: after receiving the transmission end doorbell of all the data nodes sent by the current sector in the current radar period, the scheduling module enters a priority strategy adjustment stage of the current sector, adjusts the priorities of all the sending nodes and the receiving nodes in the current sector according to the task quantity change of all the sending nodes and the receiving nodes in the current sector, stores the adjusted priority strategy, and adopts the adjusted priorities to carry out data transmission on the sector in the next radar period;
preferably, in the fourth step, the task amounts of the corresponding receiving nodes of the nth transmitting node of the kth sector of the current radar period are summed to obtain Q SendCur (k,n)，Q SendCur The calculation formula of (k, n) is:
wherein Q is RecvCur (k, n, i) is the task amount of the ith receiving node corresponding to the nth transmitting node of the kth sector; summing the task amounts of the nth transmitting node corresponding to each receiving node of the kth sector of the previous radar period to obtain Q SendPrev (k,n)，Q SendPrev The calculation formula of (k, n) is:
wherein Q is RecvPrev (k, n, i) is the task amount of the ith receiving node corresponding to the nth transmitting node of the kth sector of the last radar period; calculating the ratio R of the task amount of the nth transmitting node of the kth sector in the current period and the last period of the radar send (k, n) as follows:
R send (k,n)＝Q SendCur (k,n)/Q SendPrev (k,n),k＝1:K,n＝1:N；
wherein K is the number of sectors, N is the number of transmitting nodes of the kth sector, according to R send The (k, N) value adjusts the priority of all transmitting nodes in the kth sector, the priority value of the N transmitting nodes is 1 to N,the value 1 indicates the lowest priority, and the value N indicates the highest priority; priority P of nth transmitting node of kth sector send The calculation formula of (k, n) is:
P Send (k,n)＝Ind Send (k,Ind SendPrio (k,n)),n＝1:N；
Ind SendPrio (k,n)＝FindInd(R Send (k,n),R SendSort (k,1:N)),n＝1:N；
[R SendSort (k,1:N),Ind Send (k,1:N)]＝Sort(R Send (k,1:N))。
step five: and starting the flow control transmission and priority strategy adjustment flow of the data of the next sector until the data transmission of all radar sectors is completed.
Preferably, the task amount of the nth transmitting node of the kth sector corresponding to the mth receiving node is Q RecvCur (k, n, m) according to Q RecvCur The (k, n, M) values are used for adjusting the priorities of all receiving nodes corresponding to the nth transmitting node of the kth sector, the priority values of the M receiving nodes are 1 to M, the value 1 represents the lowest priority, and the value M represents the highest priority; priority P of mth transmitting node of kth sector recv The calculation formula of (k, m) is:
P Recv (k,m)＝Ind Recv (k,Ind RecvPrio (k,m))；
Ind RecvPrio (k,m)＝FindInd(R Recv (k,m),R RecvSort (k,1:N)),m＝1:M
[R RecvSort (k,1:M),Ind Recv (k,1:M)]＝Sort(R Recv (k,1:M))；
wherein c=findind (a, B) represents the index of the search value a in the vector B, the search result being stored in C; [ C, B ] =sort (a) indicates that the vector a is up-ordered, the up-ordered result is stored in the vector C, and the index of the up-ordered result is stored in the vector B.
Aiming at the problem that the processing efficiency of a system is reduced due to the steep increase of the task quantity of a certain node and the problem that a plurality of SRIO transmitting nodes occupy buses at the same time to cause the abnormality of SRIO links, the priority strategies of each transmitting node and each receiving node are adjusted according to the change of the task quantity of a sector in an adjacent radar period, so that the processing efficiency of the system is improved, and a multistage flow control mechanism is designed between the data transmission periods of adjacent transmitting nodes, between the data transmission periods of a single transmitting node and different receiving nodes and between the minimum data packet transmissions, so that the data among multiple nodes can be reliably transmitted in an SRIO switching network.
Drawings
FIG. 1 is a flow chart of a multi-node SRIO bus adaptive flow control method based on a priority policy;
FIG. 2 is an exemplary diagram of the present invention for adaptive adjustment of a single node task volume increase priority policy;
fig. 3 is a diagram illustrating a multi-stage flow control transmission according to the present invention.
Detailed Description
The processing flow of the multi-node SRIO bus self-adaptive flow control method based on the priority strategy is shown in figure 1, and the embodiment of the method is specifically described by combining a flow chart and an embodiment, and the process is as follows:
step one: initializing the priority of each node, and carrying out communication handshake between the nodes;
the scheduling module enumerates all nodes in the SRIO topology, initializes the priority of each sending node and each receiving node, and for the nodes which simultaneously send and receive data, the two priorities need to be initialized to respectively correspond to the order of sending the data and the order of receiving the data. The scheduling module informs each sending node of completing communication handshake with the corresponding receiving node according to the priority, and each receiving node replies a handshake success signal to the sending node and feeds back priority information of the receiving node to the sending node.
Step two: the scheduling module performs data flow control transmission;
the scheduling module sends a transmission enabling signal to each sending node according to the priority order, and meanwhile, the flow control time is inserted between the transmission periods of each sending node, and the method comprises the following steps: after receiving the end of the transmission data fed back by the nth transmission node, the scheduling module enters a data flow control stage of the transmission node stage, and the nth transmission node transmits the data flow control stageThe flow control time for ending the sending of the sending node is T send (n) the calculation formula is T send (n)＝0.05*[T(n) begin -T(n) end ]N= … N-1, where T (N) begin T (n) is the transmission enabling initiation time of the scheduling module to the nth transmitting node end And when the scheduling module receives the data transmission end doorbell time of the nth transmitting node, N is the number of the transmitting nodes.
Step three: the sending node carries out data stream control transmission on different receiving nodes;
each sending node starts data transmission according to the transmission enabling of the scheduling module, and the method for inserting the flow control time between the sending node and the data transmission periods of different receiving nodes comprises the following steps: when the current SRIO sending data corresponds to a plurality of receiving data nodes, finishing sending the data to the mth receiving node, entering a data flow control stage of the receiving node level, wherein the flow control time is t recv (m) the calculation formula is: t is t recv (m)＝0.05*[t(m) begin -t(m) end ],m＝1…M-1，t(m) begin A transmission enabling initiation time, t (m), for a current transmitting node to an mth receiving node end The method comprises the steps that when the transmission enabling end time from a current sending node to an mth receiving node is reached, M is the number of the receiving nodes; the method for inserting the flow control time between the minimum data transmission periods by the sending node comprises the following steps: after the current transmitting node finishes transmitting the minimum transmission packet, the current transmitting node enters a data flow control stage of the minimum transmission packet level, and the flow control time between the two minimum transmission packets is T pack The calculation formula is as follows: t (T) pack ＝1/f clk *64, where f clk The frequency of the reference clock is sent for SRIO. And carrying out data transmission according to the two-stage flow control mechanism until all data transmission is finished, and sending a transmission end doorbell to the scheduling module.
Step four: adjusting the priority of the node according to the task quantity;
after receiving the transmission end doorbell of all the data nodes sent by the current sector in the current radar period, the scheduling module enters a priority strategy adjustment stage of the current sector, and the scheduling module calculates the task quantity of each sending node and each receiving node in the current sector according to the task quantity of each sending node and each receiving node in the current sectorAnd (3) readjusting the priority strategies of each sending node and each receiving node in the current sector, and adopting the adjusted priority to carry out data transmission on the sector in the next radar period. The processing procedure of the priority adjustment of the sending node is as follows: summing the task amounts of the nth transmitting node corresponding to each receiving node of the kth sector of the current radar period to obtain Q SendCur (k,n)，Q SendCur The calculation formula of (k, n) isWherein Q is RecvCur (k, n, i) is the task amount of the ith receiving node corresponding to the nth transmitting node of the kth sector; summing the task amounts of the nth transmitting node corresponding to each receiving node of the kth sector of the previous radar period to obtain Q SendPrev (k,n)，Q SendPrev The formula of (k, n) is +.>Wherein Q is RecvPrev (k, n, i) is the task amount of the ith receiving node corresponding to the nth transmitting node of the kth sector of the last radar period; calculating the ratio R of the task amount of the nth transmitting node of the kth sector in the current period and the last period of the radar send (k, n) with a formula R send (k,n)＝Q SendCur (k,n)/Q SendPrev (K, N), k=1:k, n=1:n, where K is the number of sectors and N is the number of transmitting nodes of the kth sector, according to R send The (k, N) value adjusts the priority of all the transmitting nodes in the kth sector, the priority value of the N transmitting nodes is 1 to N, the value 1 indicates the lowest priority, and the value N indicates the highest priority. Priority P of nth transmitting node of kth sector send The calculation formula of (k, n) is:
P Send (k,n)＝Ind Send (k,Ind SendPrio (k,n)),n＝1:N
Ind SendPrio (k,n)＝FindInd(R Send (k,n),R SendSort (k,1:N)),n＝1:N
[R SendSort (k,1:N),Ind Send (k,1:N)]＝Sort(R Send (k,1:N))
the processing procedure of the priority adjustment of the receiving node is as follows: the task quantity of the nth transmitting node of the kth sector corresponding to the mth receiving node is Q RecvCur (k, n, m) according to Q RecvCur The (k, n, M) values adjust the priorities of all receiving nodes corresponding to the nth transmitting node of the kth sector, the priority values of the M receiving nodes are 1 to M, the value 1 represents the lowest priority, and the value M represents the highest priority. Priority P of mth transmitting node of kth sector recv The calculation formula of (k, m) is:
P Recv (k,m)＝Ind Recv (k,Ind RecvPrio (k,m))
Ind RecvPrio (k,m)＝FindInd(R Recv (k,m),R RecvSort (k,1:N)),m＝1:M
[R RecvSort (k,1:M),Ind Recv (k,1:M)]＝Sort(R Recv (k,1:M))
wherein c=findind (a, B) represents the index of the search value a in the vector B, the search result being stored in C; [ C, B ] =sort (a) indicates that the vector a is up-ordered, the up-ordered result is stored in the vector C, and the index of the up-ordered result is stored in the vector B.
Step five: and starting the flow control transmission and priority strategy adjustment flow of the data of the next sector until the data transmission of all radar sectors is completed.
The effects of the invention are further illustrated by the following examples:
in fig. 2 (a), 3 receiving nodes, namely 1# receiving node, 2# receiving node and 3# receiving node, are arranged in the system, the processing time of data of each receiving node is the same as the transmission time, the task amount of the 3 receiving nodes is the same in the initial stage of the system, and the transmission time and the processing time of data of each node are defined as T p . The initial priority settings for the 3 receiving nodes are as follows: the priority of the 1# receiving node is 3, the priority of the 2# receiving node is 2, the priority of the 3# receiving node is 1, and the larger the priority value is, the higher the representative priority is. When the task quantity of the 3# node is T p T3 times p When the original priority is adopted, 3 receivers as shown in FIG. 2 (b)The time required for completing all task processing of the node is T b ＝8*T p By counting the task amount of the 3# receiving node, the priority thereof is adjusted from 1 to 3, and as shown in fig. 2 (c), the time required for completing the task processing of all the 3 receiving nodes is T c ＝6*T p The processing efficiency of the system is improved by eta, eta= delta T/T b ＝(T b -T c )/T c As can be seen from the analysis of the above examples, the present embodiment adaptively adjusts the priority of the 3# node according to the change of the task amount of the 3# node, so that the processing efficiency of the system is improved by 25%, which illustrates the effectiveness of the method provided by the present embodiment.
Claims (3)
1. The multi-node SRIO bus self-adaptive flow control method based on the priority strategy is characterized in that:
step one: the scheduling module enumerates all nodes in the SRIO topology, initializes the priority of each node, and informs the sending node of completing communication handshake with the corresponding receiving node according to the initial priority;
step two: the scheduling module sends a transmission enabling signal to each sending node according to the initial priority order of each node in the current radar sector, and meanwhile, a flow control time slot is inserted between the transmission periods of each sending node;
step three: each sending node starts data transmission according to the transmission enabling of the scheduling module, and a flow control time slot is inserted between the current sending node and the data transmission period of different receiving nodes and between the transmission period of the minimum data packet until all data transmission of the current radar sector is finished, and a transmission end doorbell is sent to the scheduling module;
step four: after receiving the transmission end doorbell of all the data nodes sent by the current sector in the current radar period, the scheduling module enters a priority strategy adjustment stage of the current sector, and adjusts the priorities of all the sending nodes and the receiving nodes in the current sector according to the task quantity change of all the sending nodes and the receiving nodes in the current sector, wherein the specific adjustment method of the priorities of the sending nodes is as follows: for the kth fan of the current radar periodSumming task amounts of each receiving node corresponding to the nth transmitting node of the zone to obtain Q SendCur (k,n)，Q SendCur The calculation formula of (k, n) is:
wherein Q is RecvCur (k, n, i) is the task amount of the ith receiving node corresponding to the nth transmitting node of the kth sector; summing the task amounts of the nth transmitting node corresponding to each receiving node of the kth sector of the previous radar period to obtain Q SendPrev (k,n)，Q SendPrev The calculation formula of (k, n) is:
wherein Q is RecvPrev (k, n, i) is the task amount of the ith receiving node corresponding to the nth transmitting node of the kth sector of the last radar period; calculating the ratio R of the task amount of the nth transmitting node of the kth sector in the current period and the last period of the radar send (k, n) as follows:
R send (k,n)＝Q SendCur (k,n)/Q SendPrev (k,n),k＝1:K,n＝1:N；
wherein K is the number of sectors, N is the number of transmitting nodes of the kth sector, according to R send The (k, N) value adjusts the priority of all the transmitting nodes in the kth sector, the priority value of the N transmitting nodes is 1 to N, the value 1 represents the lowest priority, and the value N represents the highest priority; priority P of nth transmitting node of kth sector send The calculation formula of (k, n) is:
P Send (k,n)＝Ind Send (k,Ind SendPrio (k,n)),n＝1:N；
Ind SendPrio (k,n)＝FindInd(R Send (k,n),R SendSort (k,1:N)),n＝1:N；
[R SendSort (k,1:N),Ind Send (k,1:N)]＝Sort(R Send (k,1:N))，
the specific adjustment method of the priority of the receiving node comprises the following steps: the task quantity of the nth transmitting node of the kth sector corresponding to the mth receiving node is Q RecvCur (k, n, m) according to Q RecvCur The (k, n, M) values are used for adjusting the priorities of all receiving nodes corresponding to the nth transmitting node of the kth sector, the priority values of the M receiving nodes are 1 to M, the value 1 represents the lowest priority, and the value M represents the highest priority; priority P of mth receiving node of kth sector recv The calculation formula of (k, m) is:
P Recv (k,m)＝Ind Recv (k,Ind RecvPrio (k,m))；
Ind RecvPrio (k,m)＝FindInd(R Recv (k,m),R RecvSort (k,1:M)),m＝1:M；
[R RecvSort (k,1:M),Ind Recv (k,1:M)]＝Sort(R Recv (k,1:M))；
wherein c=findind (a, B) represents the index of the search value a in the vector B, the search result being stored in C; [ C, B ] = Sort (a) means that the vector a is arranged in ascending order, the ascending order result is stored in the vector C, the index of the ascending order result is stored in the vector B, after the priority adjustment of each transmitting node and each receiving node in the current sector is completed, the adjusted priority policy is stored, and the data transmission is performed on the sector by adopting the adjusted priority in the next radar period;
step five: and starting the flow control transmission and priority strategy adjustment flow of the data of the next sector until the data transmission of all radar sectors is completed.
2. The multi-node SRIO bus adaptive flow control method based on priority policy of claim 1, wherein: in the second step, the method for inserting the flow control time slot between the transmission periods of each sending node comprises the following steps: after receiving the end of the transmission data fed back by the nth transmission node, the scheduling module enters a data flow control stage of the transmission node stage, and the flow control time of the end of the transmission of the nth transmission node is T send (n) the calculation formula is:
T send (n)＝0.05*[T(n) begin -T(n) end ],n＝1…N-1；
wherein T (n) begin T (n) is the transmission enabling initiation time of the scheduling module to the nth transmitting node end And when the scheduling module receives the data transmission end doorbell time of the nth transmitting node, N is the number of the transmitting nodes.
3. The multi-node SRIO bus adaptive flow control method based on priority policy of claim 1, wherein: the method for inserting the flow control time slot between the data transmission periods of the sending node and the different receiving nodes in the step three is as follows: when the current SRIO sending data corresponds to a plurality of receiving data nodes, finishing sending the data to the mth receiving node, entering a data flow control stage of the receiving node level, wherein the flow control time is t recv (m) the calculation formula is:
t recv (m)＝0.05*[t(m) begin -t(m) end ],m＝1…M-1
wherein t (m) begin A transmission enabling initiation time, t (m), for a current transmitting node to an mth receiving node end The method comprises the steps that when the transmission enabling end time from a current sending node to an mth receiving node is reached, M is the number of the receiving nodes; the method for inserting the flow control time between the transmission periods of the minimum data packet comprises the following steps: after the current transmitting node finishes transmitting the minimum transmission packet, the current transmitting node enters a data flow control stage of the minimum transmission packet level, and the flow control time between the two minimum transmission packets is T pack The calculation formula is as follows: t (T) pack ＝1/f clk *64, where f clk The frequency of the reference clock is sent for SRIO.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210888143.5A CN115378758B (en) | 2022-07-27 | 2022-07-27 | Multi-node SRIO bus self-adaptive flow control method based on priority strategy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210888143.5A CN115378758B (en) | 2022-07-27 | 2022-07-27 | Multi-node SRIO bus self-adaptive flow control method based on priority strategy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115378758A CN115378758A (en) | 2022-11-22 |
| CN115378758B true CN115378758B (en) | 2023-09-26 |
Family
ID=84064646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210888143.5A Active CN115378758B (en) | 2022-07-27 | 2022-07-27 | Multi-node SRIO bus self-adaptive flow control method based on priority strategy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115378758B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104486005A (en) * | 2014-11-30 | 2015-04-01 | 华南理工大学 | Multi-node rapid communication method suitable for contention channel underwater acoustic network |
| CN107528798A (en) * | 2016-06-22 | 2017-12-29 | 宁波工程学院 | Optimization Scheduling based on RS485 bus systems |
| CN108632911A (en) * | 2018-04-12 | 2018-10-09 | 浙江大学 | Adaptive conflict avoidance real-time media access control method based on overall scheduling |
| CN109450943A (en) * | 2018-12-25 | 2019-03-08 | 重庆邮电大学 | Industrial time sensitive network multi-level safety data scheduling method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10531477B2 (en) * | 2017-03-30 | 2020-01-07 | Mitsubishi Electric Research Laboratories, Inc. | Interference free scheduling for multi-controller multi-control-loop control systems over wireless communication networks |
-
2022
- 2022-07-27 CN CN202210888143.5A patent/CN115378758B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104486005A (en) * | 2014-11-30 | 2015-04-01 | 华南理工大学 | Multi-node rapid communication method suitable for contention channel underwater acoustic network |
| CN107528798A (en) * | 2016-06-22 | 2017-12-29 | 宁波工程学院 | Optimization Scheduling based on RS485 bus systems |
| CN108632911A (en) * | 2018-04-12 | 2018-10-09 | 浙江大学 | Adaptive conflict avoidance real-time media access control method based on overall scheduling |
| CN109450943A (en) * | 2018-12-25 | 2019-03-08 | 重庆邮电大学 | Industrial time sensitive network multi-level safety data scheduling method |
Non-Patent Citations (1)
| Title |
|---|
| "基于排队论的数据链网络节点入退网时隙分配算法研究".《电声技术》.2022,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115378758A (en) | 2022-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7545740B2 (en) | Two-way link aggregation | |
| US8571063B2 (en) | Method and system for configurable data rate via inter-packet gap adjustment to support energy efficient networks | |
| US8284799B2 (en) | Method and system for supporting a variable and energy efficient data rate using a duty cycling technique and multiple power states on an Ethernet link | |
| US8068731B2 (en) | Dynamic bandwidth allocation method of Ethernet passive optical network | |
| US20100115295A1 (en) | Method And System For Energy Efficient Communication Among One Or More Interfaces In A Communication Path | |
| US8571070B2 (en) | Method and system for speed negotiation for twisted pair links in fibre channel sytems | |
| US8532139B2 (en) | Method and system for indicating a transition in rate and/or power consumption utilizing a distinct physical pattern on one or more idle channel(s) | |
| US20060198299A1 (en) | Flow control and congestion management for random scheduling in time-domain wavelength interleaved networks | |
| CN1498461A (en) | System and method for dynamic bandwidth allocation | |
| CN110061929B (en) | Data center load balancing method for asymmetric network | |
| WO2021120796A1 (en) | Traffic control method, electronic device, and storage medium | |
| US5379291A (en) | Apparatus for fiber distributed data interface dynamic station bypass via skipping and hopping | |
| CN115378758B (en) | Multi-node SRIO bus self-adaptive flow control method based on priority strategy | |
| US20090073873A1 (en) | Multiple path switch and switching algorithms | |
| CN113691391A (en) | Underwater acoustic network medium access control method with variable node number based on Q learning | |
| Liu et al. | A reconfigurable high-performance optical data center architecture | |
| JP2839024B2 (en) | Buffer control device | |
| CN1165135C (en) | Telecommunication network | |
| US7990873B2 (en) | Traffic shaping via internal loopback | |
| CN101202634A (en) | Single board improving data utilization ratio and system and method of data transmission | |
| CN111371663A (en) | Ring network communication system and communication method for multi-level converter control system | |
| JP2000209250A (en) | Flow control system in switching hub | |
| US20140186054A1 (en) | Transporting multiple low-speed data streams across a high-speed communication link | |
| CN111770515A (en) | SDN controller deployment method based on network cost optimization | |
| CN105024941A (en) | Multi-priority multichannel MAC protocol self-adaptive jitter method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 210003 No. 346, Zhongshan North Road, Jiangsu, Nanjing Applicant after: 724 Research Institute of China Shipbuilding Corp. Address before: 210003 No. 346, Zhongshan North Road, Jiangsu, Nanjing Applicant before: 724TH RESEARCH INSTITUTE OF CHINA SHIPBUILDING INDUSTRY Corp. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |