CN118200767A - Data exchange and monitoring method for optical fiber network - Google Patents
Data exchange and monitoring method for optical fiber network Download PDFInfo
- Publication number
- CN118200767A CN118200767A CN202211605543.7A CN202211605543A CN118200767A CN 118200767 A CN118200767 A CN 118200767A CN 202211605543 A CN202211605543 A CN 202211605543A CN 118200767 A CN118200767 A CN 118200767A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- port
- switch
- level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 273
- 238000000034 method Methods 0.000 title claims abstract description 46
- 239000013307 optical fiber Substances 0.000 title claims abstract description 28
- 238000007726 management method Methods 0.000 claims abstract description 67
- 230000005540 biological transmission Effects 0.000 claims abstract description 29
- 238000004891 communication Methods 0.000 claims abstract description 26
- 230000007246 mechanism Effects 0.000 claims description 8
- 230000008713 feedback mechanism Effects 0.000 claims description 6
- 239000000835 fiber Substances 0.000 claims 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012913 prioritisation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a data exchange and monitoring method of an optical fiber network, belonging to the field of computer communication. The optical fiber network comprises cascaded multi-stage switches; the data exchange and monitoring method comprises the following steps: each level of switch provides cascade ports, and all adjacent upper and lower levels of switches are cascaded through corresponding cascade ports; each level of switch respectively carries out buffer management on the monitoring and exchanging data, realizes the level monitoring through the level monitoring port, and realizes the whole network monitoring through the cascade port cross-level transmission monitoring data. The invention provides the monitoring cascade port and the monitoring port by utilizing all levels of switches in the network, and broadcasts the monitoring data to the directions of arrow and ground so as to realize the non-missing monitoring of the full-exchange network domain; and a buffer management method is adopted for monitoring and exchanging data, and the buffer management method is used for respectively managing and controlling transmission, so that the controllability of the network state is improved while the whole network monitoring is realized.
Description
Technical Field
The invention belongs to the field of computer communication, and particularly relates to a data exchange and monitoring method of an optical fiber network.
Background
The data bus technology is a key technology for electronic integration of military weapon systems, and provides a real-time and high-reliability communication link for information exchange between electronic systems. At present, the research field of bus technology has been expanded to various platforms such as vehicle-mounted, airborne, satellite-borne, carrier-borne, rocket, missile and the like, and the essence of the technology is a real-time network transmission technology.
In the topology architecture of data bus transmission, the common architecture includes three kinds of point-to-point architecture, arbitration ring architecture and switching architecture. The switching network routes the message to the destination N port by judging the address of the destination N port where the source N port sends the message. The switching network can establish a plurality of connections among N ports, so that data communication can select a plurality of paths without arbitration, and the reliability is higher; 1600 ten thousand devices can be connected through the cascade of the switches, so that the requirement of large-scale interconnection of the missile/rocket-borne system is fully met; the method has the characteristics of hot plug, can realize plug and play of equipment, and ensures higher certainty than an arbitration ring.
With the continuous development of aerospace electronic systems, the switching demands in switching network systems are also increasing. The increasing number of devices, bandwidth, data throughput and transmission rate place higher and more comprehensive demands on listening to port data streams. In the traditional switch structure, the output port of the switch is used for storing and forwarding the most of the switching data and the monitoring data with the same property, and the differential scheduling is not carried out, so that the monitoring service has an influence on the normal communication service performance of the switch, and the performance of the switch is influenced; and the monitoring port of each level switch can only monitor the device data flow connected with the level switch. However, in the application of increasingly complex missile/rocket-borne systems, network connection of the whole control system by using a multi-stage switch is often established, controllability of network state and communication efficiency need to be improved, and devices in each stage of switching may have any device connected in the whole switching network, namely, whole network monitoring.
Disclosure of Invention
In view of the above analysis, the present invention aims to provide a data exchange and monitoring method for an optical fiber network, in which each level of switches in the network perform buffer management on monitored and exchanged data respectively, so as to increase the controllability of the network and avoid network congestion of the exchanged data; each level of switch provides a monitoring cascade port and a monitoring port, and the monitoring data in the local switch network domain is broadcasted to the arrow and the ground through the monitoring cascade port of the switch, so that the non-missing monitoring of the full switch network domain is realized.
The invention provides a data exchange and monitoring method of an optical fiber network, wherein the optical fiber network comprises cascaded multistage switches; the data exchange and monitoring method comprises the following steps:
each level of switch provides cascade ports, and all adjacent upper and lower levels of switches are cascaded through corresponding cascade ports;
each level of switch respectively carries out buffer management on the monitoring and exchanging data, realizes the level monitoring through the level monitoring port, and realizes the whole network monitoring through the cascade port cross-level transmission monitoring data.
Further, the cascade connection of the adjacent upper and lower switches through the corresponding cascade ports includes: adjacent upper and lower switches are cascaded through two ports, namely an independent switching cascade port and an independent monitoring cascade port, or are cascaded through a switching and monitoring mixed cascade port.
Furthermore, the cross-stage transmission of the monitoring data through the cascade port realizes the whole network monitoring, and the method comprises the following steps: when the data received by the input port of the exchanger is exchange data, the exchanger copies the exchange data into monitoring data and sends the monitoring data to the monitoring port of the current level and the cascade port, the monitoring port of the current level sends the monitoring data to the monitoring equipment of the current level, and the cascade port sends the monitoring data to the upper-level exchanger and the lower-level exchanger.
Furthermore, the cross-stage transmission of the monitoring data through the cascade port realizes the whole network monitoring, and the method also comprises the following steps,
When the data received by the input port of the switch is the monitoring data from the upper-level switch, the switch sends the received monitoring data to the current-level monitoring port and sends the received monitoring data to the lower-level switch through the cascade port connected with the lower-level switch;
When the data received by the input port of the switch is the monitoring data from the lower-level switch, the switch sends the received monitoring data to the current-level monitoring port and sends the received monitoring data to the upper-level switch through the cascade port connected with the upper-level switch.
Further, the switches of each stage respectively adopt a cache management method for monitoring and exchanging data, and the method comprises the following steps:
Setting a shared buffer memory at the input end of the switch for storing the switching data and the monitoring data received by all the input ports of the switch; setting a queue at each output port of the switch output end for storing management information of the exchange data and the monitoring data of the corresponding output port;
Based on the shared buffer and the queue, each output port adopts different management mechanisms to send corresponding exchange data and monitoring data.
Further, the setting the shared buffer memory at the input end of the switch for storing the switching data and the listening data corresponding to all the input ports includes: based on a crossbar architecture, a shared cache ram is set at the input end of the switch and is used for storing switching data and monitoring data corresponding to all input ports.
Further, the setting the queue at each output port of the switch output end for storing management information of the exchange data and the listening data of the corresponding output port includes: and setting a switching management queue and a monitoring management queue at each output port of the switch, wherein the switching management queue and the monitoring management queue are respectively used for storing management information of switching data and management information of monitoring data corresponding to the output ports.
Further, the sending the exchange data and the listening data by adopting different management mechanisms includes:
The target output port of the monitoring data sends the monitoring data according to the first-in first-out sequence at the port;
and the target output port for exchanging data sends the exchanged data at the port by using an optical fiber network communication control method with a feedback mechanism.
Further, the method for controlling optical fiber network communication with feedback mechanism is used for transmitting exchange data, and comprises the following steps:
Determining a load priority of the frame based on the load size; determining an application priority of the frame based on the priority specified by the application layer; wherein a frame refers to exchanging data.
Authorizing the frame to be transmitted based on the number of load priority levels, the level of load priority and the level of application priority of the frame to be transmitted;
judging the link congestion condition based on the time interval average value of the local receiving primitive R_RDY and the upper limit value of the replying R_RDY time;
Based on the link congestion status and the local credit feedback control link communication, it is determined whether to transmit an authorized frame to be transmitted.
Further, the determining the load priority of the frame based on the load size includes:
Determining the priority of a frame with the number of load bytes less than or equal to l 1 bytes as a first load priority; wherein l 1 is a preset value, l 1 is less than 32;
Determining the priority of frames with the number of load bytes being greater than l 1 bytes and less than or equal to l 2 bytes as a second load priority, wherein l 2 is a preset value, and 480 < l 2 < 1024;
the priority of the frame with the load byte number larger than l 2 bytes is determined as the third load priority.
The invention can realize at least one of the following beneficial effects:
By utilizing all levels of switches in the network to provide a monitoring cascade port and a monitoring port, each level of switch broadcasts the monitoring data in the local switching network domain to the arrow and the ground through the monitoring cascade port, so that the non-missing monitoring of the full switching network domain is realized.
The exchanger adopted by the invention uses an exchanger buffer management method for distinguishing the monitoring and the exchanging data, respectively manages and controls the sending of the monitoring data and the exchanging data, increases the controllability of the network state while realizing the whole network monitoring, avoids the influence of the monitoring service on the normal communication service performance of the exchanger, and avoids the network congestion of the exchanging data; by respectively storing and forwarding the exchange data and the monitoring data, the monitoring data can be rapidly positioned when the switch fails, and the failure diagnosis efficiency of the switch is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, like reference numerals being used to refer to like parts throughout the several views.
FIG. 1 is a flow chart of a data exchange and monitoring method of an optical fiber network according to the present invention;
FIG. 2 is a switching cascade topology of a switching and listening hybrid cascade mode of the present invention;
FIG. 3 is a schematic diagram of a full-network full-missing listening data flow in a mixed tandem mode of switching and listening according to the present invention;
FIG. 4 is a switching cascade topology of the split mode of the switching cascade and listening cascade of the present invention;
Fig. 5 is a schematic diagram of the full-network full-missing listening data flow in the switch-cascade and listening-cascade split mode of the present invention.
Detailed Description
The following detailed description of preferred embodiments of the application is made in connection with the accompanying drawings, which form a part hereof, and together with the description of the embodiments of the application, are used to explain the principles of the application and are not intended to limit the scope of the application.
Method embodiment
Example 1
The invention discloses a data exchange and monitoring method of an optical fiber network, wherein the optical fiber network comprises cascaded multistage switches; the data exchange and monitoring method comprises the following steps:
step S01, each level of switch provides a cascade port, and all adjacent upper and lower levels of switches are cascaded through corresponding cascade ports.
Optionally, adjacent upper and lower switches can be cascaded through two ports, namely an independent switching cascade port and an independent monitoring cascade port, or can be cascaded through a switching and monitoring mixed cascade port.
And step S02, each level of switch respectively carries out buffer management on the monitored and exchanged data, realizes the level monitoring through the level monitoring port, and realizes the whole network monitoring through the cascade port cross-level transmission of the monitored data.
Specifically, the performing cache management on the monitored and exchanged data respectively includes:
Setting a shared buffer memory at the input end of the exchanger for storing the exchange data and the monitoring data corresponding to all the input ports; setting a queue at each output port of the switch output end for storing management information of the exchange data and the monitoring data of the corresponding output port;
Based on the shared buffer and the queue, each output port adopts different management mechanisms to send corresponding exchange data and monitoring data.
Specifically, setting a shared buffer memory at the input end of the switch for storing the switching data and the monitoring data corresponding to all the input ports includes:
based on a crossbar architecture, a shared cache ram shared by all input ports is set at the input end of the switch, and is used for storing switching data and monitoring data corresponding to all the input ports. Wherein, the monitoring data refers to the monitoring data obtained after the exchange data is copied by the monitoring function of the switch.
Optionally, the size of the shared buffer is determined based on the credit value of each input port, the maximum value of the single-pin load, and the port number.
Preferably, when the credit value of each input port of the switch is the same, the size of the shared buffer is set as follows: not less than (credit value of input port x maximum value of single frame load x port number;) wherein Shan Zhen refers to single exchange data or listening data.
Optionally, when the credit value of each input port of the switch is different, the size of the shared buffer is set as follows: Σ credit value per port single pin load maximum value.
Specifically, setting a queue at each output port of the switch output end for storing management information of the switching data and the listening data of the corresponding output port includes:
And setting a switching management queue and a monitoring management queue at each output port of the switch, wherein the switching management queue and the monitoring management queue are respectively used for storing management information of switching data and management information of monitoring data corresponding to the output ports.
Specifically, the management information of the exchange data includes ram storage address information of the exchange data, target output port information of the exchange data and priority of the exchange data; the management information of the interception data comprises ram storage address information of the interception number and target output port information of the interception data.
Alternatively, each output port of the switch may be configured as a separate listening port, a separate switching interface, or a switching listening hybrid port, respectively. And setting queues to store management information of the exchange data and management information of the monitoring data respectively at each output port.
Specifically, each queue has equal usage rights for the shared cache.
Specifically, based on the shared buffer and the queue, each output port adopts different management mechanisms to send corresponding exchange data and monitoring data, including:
Storing the exchange data entering the input port of the exchanger into a shared cache and storing corresponding management information into an exchange management queue corresponding to the target output port; meanwhile, the exchange data is copied and converted into monitoring data, and the monitoring data is stored in the shared buffer memory, and corresponding management information of the monitoring data is stored in a monitoring management queue corresponding to a monitoring data target output port.
Specifically, storing the monitor data into the shared buffer memory and storing the corresponding management information thereof into the monitor management queue of the monitor data target output port includes: based on a preset target output port, ram storage address information and target output port information of the monitoring data are stored in a monitoring management queue corresponding to the target output port; wherein the monitoring management queue is a FIFO queue.
Preferably, the target output port of the monitoring data is a dedicated monitoring port, each monitoring port distributes the monitoring data by adopting first-in first-out, and the ram memory address of the corresponding monitoring data is found based on the sequence of the monitoring management queue of the monitoring port to acquire the monitoring data and sequentially send the monitoring data.
Specifically, storing the switching data entering the input port of the switch in the shared buffer memory and storing the corresponding management information in the switching management queue corresponding to the target output port includes: searching a routing table to determine a target output port of the exchange data, and storing ram storage address information, target output port information and priority of the exchange data into an exchange management queue corresponding to the target output port; the exchange management queue is a FIFO queue.
Preferably, the destination output port for exchanging data is a separate switch port. Optionally, each target output port uses an optical fiber network communication control method with a feedback mechanism to judge forwarding order of the exchange data, obtains and sends the exchange data based on ram storage addresses of the corresponding exchange data in the exchange management queue, and ensures high-speed operation of normal communication to the greatest extent.
Specifically, the method for judging forwarding order of the exchange data by using the optical fiber network communication control method with the feedback mechanism comprises the following steps:
Determining a load priority of the frame based on the load size; determining an application priority of the frame based on the priority specified by the application layer; wherein a frame refers to exchanging data.
Authorizing the frame to be transmitted based on the number of load priority levels, the level of load priority and the level of application priority of the frame to be transmitted;
judging the link congestion condition based on the time interval average value of the local receiving primitive R_RDY and the upper limit value of the replying R_RDY time;
Based on the link congestion status and the local credit feedback control link communication, it is determined whether to transmit an authorized frame to be transmitted.
Specifically, determining a load priority of the frame based on the load size; determining the application priority of the frame based on the priority specified by the application layer includes:
specifically, determining the load priority of the frame based on the load size includes: the load priority is inversely related to the number of load bytes, and the smaller the number of load bytes, the higher the load priority.
Specifically, the short frame with small load has the highest priority, and is preferably the first load priority, and the priority of the frame with the number of load bytes less than or equal to l 1 bytes is preferably the first load priority; wherein l 1 is a preset value, 1 < l 1 < 32, optionally, using a register to store the value l 1, and modifying according to the requirement; preferably, i 1 =16, such frames are general instruction frames in the aerospace system, and the processing response time is fast, so that the bandwidth and buffer occupation can be reduced by rapid processing.
The priority of frames with the number of load bytes being greater than l 1 bytes and less than or equal to l 2 bytes is the second load priority; wherein l 2 is a preset value, and 480 is less than 2 and less than 1024; optionally, a register is used to store the l 2 value; alternatively, l 2 =1024;
The frame with large load has the lowest priority, and optionally, the priority of the frame with the number of load bytes being greater than l 2 bytes is the third load priority.
Specifically, determining the application priority of the frame based on the priority specified by the application layer includes: the priority designated by the application layer refers to preset different application priorities for different frames according to actual application conditions; alternatively, high, medium, low, no application priority may be set.
Specifically, authorizing the frame to be transmitted based on the number of load priority levels, the level of load priority, and the level of application priority of the frame to be transmitted includes:
when only the first load priority frame transmits a request, authorizing the first load priority frame to be transmitted;
when there are more than 2 frames with load priority levels, determining a level of load priority authorizing the frame to be transmitted and authorizing the frame to be transmitted based on the historical transmission times and the current local credit value, including:
In principle one, when the local credit value is greater than or equal to w 1% of the threshold value of the local credit value, only the first load priority frame is authorized to be sent; if the first load priority frame does not exist, the frame to be sent is not authorized; wherein w 1 is a preset value, w 1 is more than 70 and less than or equal to 90; optionally, a register is used for storing the w 1 value, and the value is modified according to the requirement;
When the local credit value is greater than or equal to w 2% of the threshold value and less than w 1% of the threshold value, the first load priority frame is not continuously transmitted for the last i times before the next transmission, the first load priority frame is still authorized to be transmitted, and otherwise, the second load priority frame is authorized to be transmitted; generally, the third load priority is not authorized for the frame to be transmitted; wherein i is a preset value, 1< m <20; optionally, a register is used for storing the i value, and modification is carried out according to the requirement; wherein w 2 is a preset value, w 2 is more than 60 and less than or equal to 70; optionally, a register is used for storing the w 1 value, and the value is modified according to the requirement;
Third, when the local credit value is greater than or equal to w 3% of the threshold value and less than w 2% of the threshold value, when the historical transmission times of the first load priority frame is less than or equal to j and the first load priority frame is not continuously transmitted for the last i times before the current transmission, the first load priority frame is authorized to be transmitted, otherwise, the second load priority frame or the third load priority frame is authorized to be transmitted; if and only if the frame to be transmitted with the third load priority waits for authorization and the historical transmission times are 0, authorizing the frame to be transmitted with the third load priority, otherwise authorizing the frame to be transmitted with the second load priority; wherein, the historical transmission times refer to the times of the total transmission of the load priority frames in a period of time, and the period of time refers to the sum of the transmission processing times of k transmission frames before the current times; wherein j and k are preset values, 1<j and k are less than 30; optionally, a register is used for storing the values of j and k, and modification is carried out according to the requirement; w 3 is a preset value, w 3 is more than 30 and less than or equal to 60; optionally, a register is used for storing the w 3 value, and the value is modified according to the requirement;
And fourthly, when the credit value is locally smaller than w 3% of the threshold value, on the basis of authorizing according to the load priority, each load priority frame is transmitted alternately when the following conditions are met: the first load priority frame can not be continuously transmitted for more than j times, the second load priority frame can not be continuously transmitted for more than t times, and the historical transmission times of the third load priority frame are not less than s times; wherein t and s are preset values, 1<t and s <15; optionally, a register is used to store the values of t and s, and the values are modified according to requirements.
Specifically, in the allocation principle, when each stage of load priority frame is authorized, the frames are further ordered based on the application priority thereof for authorization; wherein the order of application prioritization from high to low is: high application priority, medium application priority, low application priority, no application priority.
Optionally, the threshold value of the local credit value is a preset constant value; optionally, a register is used to store a threshold value of the local credit value, modified according to requirements.
Specifically, determining the link congestion condition based on the time interval average value of the local reception primitive r_rdy and the upper limit value of the reply r_rdy time includes:
specifically, r_rdy is a common primitive signal transmitted by the link layer, belongs to a signal specified by the FC protocol, and is used for flow control in the transport layer; restoring a local credit when a primitive R_RDY is received locally according to the FC_AE protocol specification; therefore, the time interval of receiving the primitive can intuitively feed back the congestion condition of the current link.
Specifically, the local timer is used to calculate the time of receiving the primitive r_rdy; setting a local list, adopting a first-in first-out queue structure, and recording the time of each primitive R_RDY of which one frame is sent and the message reply is received for the last h times and the interval time between the time and the receiving time of the previous primitive; based on all h interval times, removing the maximum value and the minimum value, and calculating to obtain an average value; wherein h is a preset value, 1< h <20; optionally, a register is used to store the h value, and modifications are made as needed.
Specifically, the time for the network to reply to the r_rdy normally should not exceed the upper limit value of the time for replying to the r_rdy.
Specifically, the upper limit value of the recovery r_rdy time is a preset constant value; optionally, a register is used to store the upper limit value of the reply r_rdy time, and modifications are made according to requirements.
Specifically, determining the link congestion condition based on the time interval average value of the local reception primitive r_rdy and the upper limit value of the reply r_rdy time includes:
1. calculating the interval time of the current latest receiving primitive R_RDY;
2. judging the link congestion condition:
If the latest interval time is smaller than a times of the average value, the current link is considered to be temporarily free from congestion, and the communication is normal; wherein a is a preset value, 1< a <5; optionally, a register is used to store the a value, modified as needed.
If the average value is more than or equal to a times of the average value and less than the upper limit value, determining that the link is congested, wherein the congestion is 1 degree;
if the congestion is equal to or greater than the upper limit value, the congestion is determined to be 2 degrees.
Specifically, determining whether to send an authorized frame to be sent based on the link congestion status and the local credit feedback control link communication includes:
When the local credit value and the link congestion degree do not support the frame transmission and credit use, skipping the transmission, and reserving the state to carry out the next transmission judgment; among these, the cases where frame transmission and credit use are not supported are: local credit value is full; the local credit value occupies less than full but more than or equal to x 1% of the threshold value, and the link is congested by 1 degree or 2 degrees; the local credit value occupies between x 2% which is more than or equal to the threshold value and x 1% which is less than the threshold value, and the congestion is 2 degrees; wherein x 1 and x 2 are preset values, and x 1≤99,50<x2 is 70< and is less than or equal to 70; optionally, the values x 1 and x 2 are stored by using registers, and modified according to requirements;
When the local credit value is greater than or equal to x 3% of the threshold value: if there is a frame of authorized first load priority, the frame of authorized first load priority may be sent until the local credit value is full; if the frame with the first authorized load priority is not available, skipping the transmission, and reserving the state to carry out the next transmission judgment; wherein x 3 is a preset value, x 3 is more than 70 and less than or equal to 99; optionally, a register is used for storing the x 3 value to be modified according to the requirement;
When the local credit value is less than x 3% of the threshold value: allowing the transmission of frames of various levels that have been authorized.
Specifically, the present level monitoring is realized through the present level monitoring port, the monitoring data is transmitted across the levels through the cascade port, and the whole network monitoring comprises:
Each stage of exchanger copies the received exchange data into monitoring data and sends the monitoring data to the monitoring port of the stage and the cascade port, the monitoring port of the stage sends the monitoring data to the monitoring equipment of the stage, and the cascade port sends the monitoring data to the upper and lower stage exchange networks.
Specifically, each stage of switch judges the source and the data type of the data received by the input port of the stage of switch, and performs different operations based on the source and the data type:
if the data received by the input port is the exchange data from the superior or inferior switch, preferably, the exchange data is only sent to the target output port without being copied into a monitoring frame, so that repeated monitoring of each layer is avoided;
if the data received by the input port is the exchange data from other network devices, the exchanger copies the received exchange data into monitoring data and sends the monitoring data to the local monitoring port and the cascade port, the local monitoring port sends the monitoring data to the local monitoring device, and the cascade port sends the monitoring data to the upper and lower exchange networks;
if the data received by the input port is the monitoring data from the upper-level switch, the switch sends the received monitoring data to the local monitoring port and to the lower-level switch through the cascade port connected with the lower-level switch; if the data received by the input port is the monitoring data from the lower-level switch, the switch sends the received monitoring data to the local monitoring port and to the upper-level switch through the cascade port connected with the upper-level switch.
Specifically, each level of switch performs the above operation on the data received by the input port, so that the monitoring data and the switching data can be respectively managed and controlled to be sent, the influence of the monitoring service on the normal communication service performance of the switch is avoided, and the network congestion of the switching data is avoided; meanwhile, the monitoring data are broadcast to the arrow and the ground through the cascade ports in the local switching network domain, and finally the non-missing monitoring of the full switching network domain is realized.
Example 2
The invention discloses a data exchange and monitoring method of an optical fiber network, wherein the optical fiber network comprises cascaded multistage switches; the data exchange and monitoring method comprises the following steps:
Step S21, each level of switch provides cascade ports, and all adjacent upper and lower levels of switches are cascaded through corresponding cascade ports.
Fig. 2 is a switching cascade topology structure of the present embodiment, where the switching cascade topology is a switching and listening hybrid cascade mode, and includes switches and listening devices at each stage. The monitoring device is used for receiving, storing and analyzing the monitoring information.
Specifically, each port of the switch can be respectively set as a current level switching port, a current level monitoring port, a switching and monitoring mixed port and a cascade port of switching and monitoring mixed; adjacent two-stage switches are connected through cascade ports in which two-stage switches are switched and listening are mixed.
Specifically, the switching port is used for transmitting switching data; the monitoring port is used for monitoring the data of the exchange domain of the current level; the switching and listening hybrid port can be used for transmitting switching data as well as for listening data to the local switching domain.
Specifically, the cascade port of the switching and monitoring mixture is used for realizing the data forwarding function of the cross-stage switch, and can transmit switching data and monitoring data; the monitoring data is transmitted through the cascade port, so that the monitoring data sharing of different switching domains can be completed, and the indifferent monitoring of each stage of the whole switching network is realized.
And S22, each level of switch respectively performs buffer management on the monitored and exchanged data, realizes the level monitoring through the level monitoring port, and realizes the whole network monitoring by transmitting the monitored data across levels through the cascade port.
Fig. 3 is a schematic diagram of the full-network full-missing listening data flow in the hybrid cascade mode. Ports 2 and 7 are used by each stage of switch in cascade with the upper and lower stages of switches, and ports 2 and 7 are configured to switch and monitor the hybrid ports.
As shown in fig. 3, port 0 of each stage of switch is a listening port. The listening port 0 of any stage can listen to the switching data, i.e. the communication frames, of all switching ports in the network domain composed of 3 switches.
Specifically, the monitoring mode is as follows:
When the monitored port receives the exchange data, the exchange data is stored in the shared buffer memory, corresponding management information is stored in an exchange management queue corresponding to the target output port, and the target output port manages and transmits the exchange data according to the management mechanism for the exchange data in the embodiment 1;
Meanwhile, copying and converting the exchange data into monitoring data, storing the monitoring data in a shared cache, and storing corresponding management information of the monitoring data in a monitoring management queue corresponding to a target output port of the monitoring data; the method comprises the steps of copying one part of exchange data into monitoring data, wherein the step of copying one part of exchange data is characterized in that the highest position 1 of a 23-bit ID number of a data frame head is the monitoring data for a receiving device to recognize, and the frame head format conforms to the frame head format specified by an FC-AE1553 protocol; specifically, the target output port of the snoop data manages and issues the snoop data according to the management mechanism for snoop data described in embodiment 1.
For example, the process of monitoring the whole network by using fig. 3 to monitor the exchange data received by the exchange 2 port 4 at the monitoring port 0 of the exchange 1,3 illustrates that each level of exchange transmits the monitoring data through the cascade port in a cross-level manner.
Specifically, in fig. 3, the solid line represents the interactive data flow direction, and the broken line represents the listening data flow direction.
Specifically, after the switch data (i.e., the communication frame) enters from the 4 ports of the switch 2:
the exchanger 2 carries out route forwarding according to the target ID information of the communication frame content, sends the information to a target output port 7 port of the exchanger 2, forwards the information to a cascade port 2 port of the exchanger 1 through a cascade port, and forwards the information to the target output port 7 port of the exchanger 1 according to the route information, so that the forwarding of the exchange data is realized;
The switch 2 copies and converts the switching data received by the 4 ports into monitoring data, and forwards the monitoring data to the local monitoring port 0 of the switch 2 and the cascade ports 2 and 7 of the switch 2:
The cascade port 2 of the switch 2 sends the received monitoring data downwards to the cascade port 7 of the connected lower-level switch 3, and the cascade port 7 of the switch 3 receives the monitoring data and sends the monitoring data to the monitoring port 0 of the switch 3;
the cascade port 7 of the switch 2 sends the received monitoring data upwards to the cascade port 2 of the connected upper-level switch 1, and the cascade port 2 of the switch 1 receives the monitoring data and sends the monitoring data to the monitoring port 0 of the switch 1;
Therefore, the switch 2 transmits the monitoring data in a cross-stage manner through the cascade ports, so that the monitoring ports of the switch 1 and the switch 3 can monitor the switching data input by all ports of the switch 2.
Similarly, the monitoring ports of each level of switch can monitor the data frames of all ports in the cascade switch, so that the whole network non-missing monitoring is realized.
Compared with the prior art, the data exchange and monitoring method of the optical fiber network provided by the embodiment has the advantages that the method is basically the same as that provided by the embodiment 1, and the method is not repeated here.
Example 3
The invention discloses a data exchange and monitoring method of an optical fiber network, wherein the optical fiber network comprises cascaded multistage switches; the data exchange and monitoring method specifically comprises the following steps:
Step S31, each level of switch provides cascade ports, and all adjacent upper and lower levels of switches are cascaded through corresponding cascade ports.
Fig. 4 is a switching cascade topology structure of the present embodiment, where the switching cascade and the listening cascade are in separate modes, and include switches and listening devices at different levels. The monitoring device is used for receiving, storing and analyzing the monitoring information.
Specifically, each port of the switch can be respectively set as a switching port, a monitoring port, a switching and monitoring mixed port, a switching cascade port and a monitoring cascade port; the adjacent two-stage switches are connected through the switching cascade ports and the monitoring cascade ports of the two-stage switches.
Specifically, the switching port is used for transmitting switching data; the monitoring port is used for monitoring the data of the exchange domain of the current level; the switching and listening hybrid port can be used for transmitting switching data as well as for listening data to the local switching domain.
Specifically, the switching cascade port and the monitoring cascade port are used for realizing a data forwarding function of the cross-stage switch and respectively transmitting switching data and monitoring data; the monitoring data sharing of different switching domains can be completed by transmitting the monitoring data through the monitoring cascade ports, and the indifferent monitoring of each stage of the whole switching network is realized.
And S22, each level of switch respectively performs buffer management on the monitored and exchanged data, realizes the level monitoring through the level monitoring port, and realizes the whole network monitoring by transmitting the monitored data across levels through the cascade port.
Fig. 5 is a schematic diagram of the full-network full-missing listening data flow in the switch cascade and listening cascade split mode. Each stage of switch is cascaded with the upper stage of switch and the lower stage of switch by using ports 3 and 6 and ports 2 and 7; optionally, ports 3 and 6 are configured as switch tandem ports and ports 2 and 7 are configured as listening tandem ports.
As shown in fig. 5, port 0 of each stage of switch is a listening port. The listening port 0 of any stage can listen to the switching data, i.e. the communication frames, of all switching ports in the network domain composed of 3 switches.
For example, fig. 5 shows that the switch 2 port 4 receives the exchange data at the monitoring port 0 of the switch 1,3, so that each level of switch transmits the monitoring data through the cascade ports in a cross-level manner, and the whole network monitoring process is realized.
Specifically, in fig. 5, the solid line represents the interactive data flow direction, and the broken line represents the listening data flow direction.
Specifically, after the switch data (i.e., the communication frame) enters from the 4 ports of the switch 2:
The exchanger 2 carries out route forwarding according to the target ID information of the communication frame content, sends the information to a target output port 6 port of the exchanger 2, forwards the information to a switching cascade port 3 port of the exchanger 1 through a switching cascade port, and forwards the information to a target output port 7 port of the exchanger 1 according to the route information, so that the forwarding of the switching data is realized;
the switch 2 copies and converts the switching data received by the 4 ports into monitoring data, and forwards the monitoring data to the local monitoring port 0 of the switch 2 and the monitoring cascade ports 2 and 7 of the switch 2:
The monitoring cascade port 2 of the switch 2 sends the received monitoring data downwards to the monitoring cascade port 7 of the connected lower-level switch 3, and the monitoring cascade port 7 of the switch 3 receives the monitoring data and sends the monitoring data to the monitoring port 0 of the switch 3;
The monitoring cascade port 7 of the switch 2 transmits the received monitoring data to the monitoring cascade port 2 of the connected upper-level switch 1, and the monitoring cascade port 2 of the switch 1 receives the monitoring data and transmits the monitoring data to the monitoring port 0 of the switch 1;
Therefore, the switch 2 transmits the monitoring data in a cross-stage manner through the cascade ports, so that the monitoring ports of the switch 1 and the switch 3 can monitor the switching data input by all ports of the switch 2.
Similarly, the monitoring ports of each level of switch can monitor the data frames of all ports in the cascade switch, so that the whole network non-missing monitoring is realized.
Compared with the prior art, the data exchange and monitoring method of the optical fiber network provided by the embodiment has the advantages that the method is basically the same as that provided by the embodiment 1, and the method is not repeated here.
It should be noted that, the above embodiments are based on the same inventive concept, and the description is not repeated, and the description may be referred to each other.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. The data exchange and monitoring method of the optical fiber network is characterized in that the optical fiber network comprises cascaded multi-stage switches; the data exchange and monitoring method comprises the following steps:
each level of switch provides cascade ports, and all adjacent upper and lower levels of switches are cascaded through corresponding cascade ports;
each level of switch respectively carries out buffer management on the monitoring and exchanging data, realizes the level monitoring through the level monitoring port, and realizes the whole network monitoring through the cascade port cross-level transmission monitoring data.
2. The method for exchanging and monitoring data in a fiber optic network according to claim 1, wherein the cascading of the adjacent upper and lower switches through the corresponding cascading ports comprises: adjacent upper and lower switches are cascaded through two ports, namely an independent switching cascade port and an independent monitoring cascade port, or are cascaded through a switching and monitoring mixed cascade port.
3. The method for exchanging and monitoring data in an optical fiber network according to claim 1, wherein the cross-stage transmission monitoring data through a cascade port, implementing whole network monitoring, comprises: when the data received by the input port of the exchanger is exchange data, the exchanger copies the exchange data into monitoring data and sends the monitoring data to the monitoring port of the current level and the cascade port, the monitoring port of the current level sends the monitoring data to the monitoring equipment of the current level, and the cascade port sends the monitoring data to the upper-level exchanger and the lower-level exchanger.
4. The method for exchanging and monitoring data in a fiber optic network according to claim 3, wherein the cross-stage transmission of the monitored data through the cascade port implements whole network monitoring, further comprising,
When the data received by the input port of the switch is the monitoring data from the upper-level switch, the switch sends the received monitoring data to the current-level monitoring port and sends the received monitoring data to the lower-level switch through the cascade port connected with the lower-level switch;
When the data received by the input port of the switch is the monitoring data from the lower-level switch, the switch sends the received monitoring data to the current-level monitoring port and sends the received monitoring data to the upper-level switch through the cascade port connected with the upper-level switch.
5. The method for exchanging and monitoring data in an optical fiber network according to any one of claims 1 to 4, wherein each level of the switch adopts a buffer management method for monitoring and exchanging data, respectively, comprising:
Setting a shared buffer memory at the input end of the switch for storing the switching data and the monitoring data received by all the input ports of the switch; setting a queue at each output port of the switch output end for storing management information of the exchange data and the monitoring data of the corresponding output port;
Based on the shared buffer and the queue, each output port adopts different management mechanisms to send corresponding exchange data and monitoring data.
6. The method for exchanging and monitoring data in a fiber optic network according to claim 5, wherein the setting a shared buffer at the input end of the switch for storing the exchanged data and the monitored data corresponding to all the input ports comprises: based on a crossbar architecture, a shared cache ram is set at the input end of the switch and is used for storing switching data and monitoring data corresponding to all input ports.
7. The method for exchanging and monitoring data in a fiber optic network according to claim 6, wherein the setting a queue at each output port of the switch output for storing management information of exchanged data and monitored data corresponding to the corresponding output port comprises: and setting a switching management queue and a monitoring management queue at each output port of the switch, wherein the switching management queue and the monitoring management queue are respectively used for storing management information of switching data and management information of monitoring data corresponding to the output ports.
8. The method for exchanging and listening data in a fiber optic network according to claim 7, wherein the sending the exchanged data and the listening data by different management mechanisms comprises:
The target output port of the monitoring data sends the monitoring data according to the first-in first-out sequence at the port;
and the target output port for exchanging data sends the exchanged data at the port by using an optical fiber network communication control method with a feedback mechanism.
9. The method for exchanging and monitoring data in an optical fiber network according to claim 8, wherein the method for controlling communication in an optical fiber network with a feedback mechanism is used for transmitting the exchanged data, comprising:
Determining a load priority of the frame based on the load size; determining an application priority of the frame based on the priority specified by the application layer; wherein a frame refers to exchanging data.
Authorizing the frame to be transmitted based on the number of load priority levels, the level of load priority and the level of application priority of the frame to be transmitted;
judging the link congestion condition based on the time interval average value of the local receiving primitive R_RDY and the upper limit value of the replying R_RDY time;
Based on the link congestion status and the local credit feedback control link communication, it is determined whether to transmit an authorized frame to be transmitted.
10. The method for exchanging and listening in a fiber optic network according to claim 9, wherein the determining the load priority of the frame based on the load size comprises:
Determining the priority of a frame with the number of load bytes less than or equal to l 1 bytes as a first load priority; wherein l 1 is a preset value, l 1 is less than 32;
Determining the priority of frames with the number of load bytes being greater than l 1 bytes and less than or equal to l 2 bytes as a second load priority, wherein l 2 is a preset value, and 480 < l 2 < 1024;
the priority of the frame with the load byte number larger than l 2 bytes is determined as the third load priority.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211605543.7A CN118200767A (en) | 2022-12-14 | 2022-12-14 | Data exchange and monitoring method for optical fiber network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211605543.7A CN118200767A (en) | 2022-12-14 | 2022-12-14 | Data exchange and monitoring method for optical fiber network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118200767A true CN118200767A (en) | 2024-06-14 |
Family
ID=91395520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211605543.7A Pending CN118200767A (en) | 2022-12-14 | 2022-12-14 | Data exchange and monitoring method for optical fiber network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118200767A (en) |
-
2022
- 2022-12-14 CN CN202211605543.7A patent/CN118200767A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2329542C (en) | System and method for scheduling message transmission and processing in a digital data network | |
| US7283471B2 (en) | System and method for regulating message flow in a digital data network | |
| EP0823166B1 (en) | Flow control protocol system and method | |
| US8041832B2 (en) | Network data distribution system and method | |
| US7042842B2 (en) | Fiber channel switch | |
| EP0823167B1 (en) | Method and apparatus for coordinating access to an output of a routing device in a packet switching network | |
| US6240096B1 (en) | Fibre channel switch employing distributed queuing | |
| US5502719A (en) | Path allocation system and method having double link list queues implemented with a digital signal processor (DSP) for a high performance fiber optic switch | |
| US6023471A (en) | Network interconnect device and protocol for communicating data among packet forwarding devices | |
| US6920146B1 (en) | Switching device with multistage queuing scheme | |
| US5592472A (en) | High performance path allocation system and method for a fiber optic switch for a fiber optic network | |
| CN109684269B (en) | PCIE (peripheral component interface express) exchange chip core and working method | |
| JPH0715435A (en) | Asynchronous-transfer-mode exchange device | |
| CN114679415B (en) | Non-blocking banyan network meeting AXI5-Lite protocol standard | |
| US7580354B2 (en) | Multi-speed cut through operation in fibre channel switches | |
| CN113014880A (en) | Multisource image sharing system based on high-speed data exchange | |
| US7046627B1 (en) | Method and apparatus for accumulating and distributing traffic and flow control information in a packet switching system | |
| CN118200767A (en) | Data exchange and monitoring method for optical fiber network | |
| KR20030050069A (en) | Method for Train Packet Generating in ATM Switch System | |
| CN118200265A (en) | Switch cache management method for distinguishing monitoring and exchanging data | |
| US6335940B1 (en) | Digital data exchange device | |
| US7382721B2 (en) | Nodal computer network | |
| JP7456603B2 (en) | switch device | |
| JPH11112560A (en) | Frame transfer control system and band managing method therefor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |