JPS60223251A - Insertion system of data selection register - Google Patents

Abstract

PURPOSE:To decrease the delivery time of data high in priority by comparing the degree of data stored in a register at each node with the delivered data, and transmitting data by starting in order from the data high in priority. CONSTITUTION:A data frame F1 containing a priority degree mark A1 is sent to a node N from a transmission line 1. In this case, the node N compares the mark A1 with a priority degree mark A2 if a data frame F2 containing the mark A2 which is going to be sent by an own station exists at the node N. Then the data frame high in priority is transmitted with priority. In this example, A1<A2 is satisfied and therefore the node N stores the frame F1 in its own station. At the same time, the frame F2 of the station of the node N itself is sent to a transmisson line. Then the frame F1 is transmitted to the transmission line.

Description

[Detailed Description of the Invention] Technical Field of the Invention The present invention relates to a register insertion method in a local area network, and in particular, when each node is provided with a register and data is queued, in the case of high-priority data, the other party The present invention relates to a data selection register insertion method that reduces the time required to reach the data selection register.

Prior Art and Problems In a local area network, a loop-shaped transmission path 1 has a large number of stations (nodes) N1. N2゜---, Nn
and a station (supervisor node) SV having a monitoring function are arranged as shown in FIG. 1, and communication between the stations is performed by transmitting data in a fixed direction. As a communication method in this case, for example, in the case of a token method, first, a specific pattern of fleet tokens is sent from the supervisor node Sv or the parent notebook. When a node that wants to send data receives a 1.-- token, it changes it to a busy token that does not indicate occupancy of the transmission path and re-sends it, and immediately thereafter sends the data. When other nodes receive a busy token, they cannot send data themselves. An address indicating the other node is added to the beginning of the data, and by identifying this, the other node can receive the data. If the other node does not transmit, it changes the busy token to a free token and sends it to the transmission path.

The above is the case of the single token method in which only one free token is sent out between transmission lines, but in the case of the multi-token method, the node that sends data sends out a free token at the end of the data. is added and sent.

As a result, other nodes cannot transmit data themselves at the location of the transmitted data, but when they receive the fleet token transmitted from the node, they can transmit data using the same procedure. The single token method and the multi-token method are used depending on the purpose.

As the amount of data transmitted in such local area networks increases, the frequency and time that data travels through the transmission path increases. As a result, even if a node attempts to send data, it has to wait until the data that is flowing has finished, resulting in a problem in which the sending of urgent data is delayed.

On the other hand, there is a method in which each node is provided with a register, in which data sent from other nodes is temporarily stored, and the data of the own node can be sent out with priority. Figure 2 conceptually shows such a conventional data storage method. In this case, data is simply given a specific code to indicate the beginning and end of the data, and the data is identified by these codes. Import or resend your own station's register. In FIG. 2, node N is shown to take in the transmitted data frame F into its register R and send out its own data frame F2. According to this method, data from other stations can be temporarily queued in a register, and the own station's data can be sent out with priority, so if the own station has highly urgent data to send, , each node can send data relatively freely,
This has the advantage that the efficiency of using the transmission path can be improved.

However, if such a register insertion method is adopted, on the other hand, it is unknown when the data will reach the other party, and if the registers and transmission path of each node become congested, the data will not be sent to the other party. Since it may take some time for fluorine to arrive, this will also cause problems in the case of highly urgent data.

Purpose of the Invention The present invention attempts to solve the problems of the prior art, and its purpose is to enable each node to determine the priority of data and send the data. Therefore, it is an object of the present invention to provide a method that can shorten the arrival time for high-priority data.

Structure of the Invention The data selection register insertion method of the present invention adds, for example, to the beginning of the data sent by each node a code or symbol indicating the priority of the data, and each node determines the priority of the data in the register. Second, the priority of the sent data is compared and the data is sent out in order starting from the highest priority.

Embodiment of the Invention FIG. 3 shows a frame structure of an embodiment of the data selection register insertion method of the invention.

In the figure, A indicates a priority symbol, and D indicates data. The priority symbol A is, for example, A, , A2, . . . depending on the urgency of the data. -. etc. are assigned different priority levels, and the larger the subscript of each priority symbol, the higher the priority.

FIG. 4 conceptually shows an embodiment of the data selection register insertion method of the present invention. If data frame F1 with priority symbol A1 is now sent from transmission path l to node N, data with priority symbol A2 that the own station is about to send to node N. When there is frame F2, node N compares the priority symbols of both data frames and sends out the data frame with higher priority preferentially. in this case,
Since A,<A2, node N stores data frame F, sent from the transmission path, in its own register R, and sends its own data frame F2 to the transmission path. The data frame Fl stored in the register R is sent out to the transmission line 1 after sending out the data frame F2 of the local station.

Furthermore, if, for example, a priority symbol A3 is attached to the data frame F3 sent from the transmission path l to the node N, then the priority comparison result at the node N is A2<
Since it is A3, No 1" N retransmits the data frame F3 sent from the transmission path 1 with priority, and then transmits its own data frame F2.

As described in detail, according to the data selection register insertion method of the present invention, a symbol indicating the priority is attached to the data sent from each node, and each node selects the data sent from the previous node. The priority of the data to be sent from the own node is compared with the priority of the data to be sent from the own node, and if the priority of the data of the own node is high, the data of the previous node is waited for in the register and the data of the own node is sent out. This has the advantage that the time required for high priority data to reach the other node can be shortened.

[Brief explanation of the drawing]

The first is a diagram showing an example of the configuration of a local area network,
Figure 2 is a diagram conceptually showing the conventional data storage method, Figure 3
FIG. 4 is a diagram showing a frame structure of an embodiment of the data selection register insertion method of the present invention, and FIG. 4 is a diagram conceptually showing an embodiment of the data selection register insertion method of the invention. 1: Transmission line, N, N + + N 2, -, N n
: node, sV: super high the node, R: register,
F,,F2. F3. -: Data frame, A, A1+
A2. A3. − :Priority symbol, ■〕：Data patent applicant Fujitsu Ltd. Company agent Patent attorney Gobe Tamamushi (1 other person) 1s1 Figure 1 Figure 2 Figure 3 Figure 4

Claims (1)

[Claims] Data sent from each node in a local area network configured such that each node is equipped with a register so that the data sent from the previous node can be waited for in the register and the data of the own node can be sent out. A symbol indicating the priority is attached to each node, and each node compares the priority of the data sent from the previous node with the priority of the data to be sent from the own node and determines the priority of the data of the own node. This data selection register insertion method is characterized in that, when the degree is high, the data of the previous node is waited for in the register and the data of the own node is sent out.