JPH03288951A - High-speed communication buffering control method - Google Patents

Abstract

PURPOSE:To improve real transmission efficiency for the amount of data to be really sent out to a transmission line by preparing a real packet only by reloading the pointer of a high-order layer for each layer. CONSTITUTION:When the data of each layer is equipped with the same processing and the same header, the data of application is divided into packets and the data is transferred while reloading the pointer of the data, which is divided into packets, shown by the same header based on a control table. For example, when an n is defined as a positive integer number, the data 11 in the n th layer is dispatched to the (n-1)th layer while adding the header 12 in the (n-1)th layer and further while adding the header 14 in the (n-2)th layer to the dispatched data, the data is dispatched to the (n-2)th layer 15. Thus, the real transmission efficiency can be improved for the amount of the data to be really sent out to the transmission line.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a high-speed communication buffering control method that utilizes a network to which processing devices are connected.

[Prior art] Local area network (hereinafter referred to as LAN)
A system is currently being constructed that organically connects processing devices (hereinafter referred to as nodes) such as computers, image terminals, word processors, workstations, print servers, disk servers, etc. that are connected via communication channels such as .

Further, standardization of each layer is progressing in LAN, and the standardization concept for file transfer, job transfer operations, etc. is also becoming solidified.

A common layered model is the International Organization for Standardization (ISO) open system interconnection or open system interconnection (Open System Interconnection) as shown in Table 1.
Systems Interconnection)
A reference model called O3I (hereinafter referred to as O3I reference model) is known.

This O8I reference model consists of seven layers, from communication line control to business-dependent communication functions, sequentially from the upper layer: application (level 7), presentation (level 6), session (level 5), transport ( It is layered into the following protocols: level 4), network (level 3), link (level 3), and physical (level 1).

FIG. 11 shows a communication procedure between a transmitting station and a receiving station using such a conventional layered protocol.

At the transmitting station, data 3 is first transmitted according to the application eyebrow and presentation waste protocols.
1 is created.

Thereafter, a session level header 32a is added to the data 31 by the session layer protocol to create session layer data 32, and a transport level header 33a is added to the data 32 by the transport layer protocol to create the transport layer data 32. data 33 is created, and a network level header 34a is added to the data 33 by the network layer protocol to create network layer data 34.

Finally, a data link level header 35a is added to the data 34 according to the data link layer protocol to create data link layer data 35. This data 35 is transmitted to the receiving station via a transmission medium using an interface method defined in the physical layer.

At the receiving station, the data link level header 35a1 added at the transmitting station and the network level header 3
4a. The transport level header 33a1 and the session level header 32a are sequentially removed at each layer, and the data 31 is reproduced in the application and presentation view.

Each header 35a to 32a is used as control information at the receiving station. Note that each header 35a to 32a provides
It becomes possible to connect with many network systems and provide future interoperability.

In this case, each station is configured so that a plurality of modular protocol software are linked, and data is actually copied between each layer to save it and pass it on to the next goose.

[Problems to be Solved by the Invention] However, in the above-mentioned conventional method, the same data is copied at each layer, which increases the data storage area and makes the copying time longer than the protocol processing time.
There is a problem that the execution speed decreases. Further, the header increases as it progresses from the upper layer to the lower layer, and the original data to be transferred is compressed within the packet.

Furthermore, if the standardization plans of each station are completely covered with respect to protocols, all protocols of multiple classes must be implemented. In this case, software is not actually created for each class, but the same software is used for common parts, so as the number of classes increases, the class selection processing flow appears frequently, causing overhead. .

Therefore, in the above conventional method, the header 32a of each layer
Since .about.35a is large, the effective transmission efficiency of the amount of data actually sent to the transmission path is reduced, and since there are many layers, there is a problem that the processing time until communication is long.

In view of the above-mentioned conventional problems, an object of the present invention is to provide high-speed communication that can improve the actual transmission efficiency of the amount of data actually sent to the transmission path and shorten the processing time until communication. An object of the present invention is to provide a buffering control device.

[Means for Solving the Problems] According to the present invention, the object is to provide a high-speed communication buffering control method having a layered network structure, which controls data in each layer based on a first management table. If the data has the same processing and the same header, the application data is divided into packets, the pointer of the divided data indicated by the same header is rewritten based on the second management table, and the data is divided into packets. This is achieved by a high-speed communication buffering control method characterized by transferring.

[Operation] Manages data in each layer based on the first management table,
If the data has the same processing and the same header, the application data is divided into packets, the pointer of the divided data indicated by the same header is rewritten based on the second management table, and the data is transferred. On the other hand, if the data does not have the same processing and the same header, it performs protocol processing and header creation, writes header information in the first management table, and moves to the next lower layer.

[Example J Hereinafter, the present invention will be described in detail with reference to the drawings.

FIG. 1 schematically shows data exchange between layers according to a high-speed communication buffering control method according to an embodiment of the present invention.

In FIG. 1, where n is a positive integer, the data 11 of the nth layer 1 is added with the header 12 of the (n-1)th layer (
The data is passed to the (n-1) 7113, and the (n-2)th li header 14 is added to the passed data, and the data is passed to the (n-2) layer 15.

FIG. 2(a) shows the physical structure in the high-speed communication buffering control method of FIG. 1, and FIG. 2(b) shows the physical structure included in the physical structure of FIG. The layer pointer 16, the data storage pointer 17 of each layer, and the data (
A management disc libter table D as a table means having an area 18 as an inclined plate for storing header) length.
Indicates T.

Next, the physical structure first includes nth layer data 19 of length DLn written from address An. Hereinafter, the (n-1)-th header 20 of length D L n-1 written from address A n-1 in order from the upper layer,
Length written from address A n-2 D L n-
It is composed of a second (n-2) Mi header 21 and the like.

Further, the physical structure is a pointer DT n+1 of the next (n+1) layer written from address DTn, nil
data storage pointer An, data length DLn of the n-th JI
, and sequentially from the upper layer, address D T
Pointer DTn of the next nth layer written from n-1
, the (n-1)th 71st data storage pointer An-1,
Data length DL n-1, next (n-1)H pointer DT n-1 written from address DTn-2,
A management disc libter table DT is provided which includes a data storage pointer An-2 of the (n-2)th layer, a data length DLn-2, and the like.

Figure 3 is the first! The configuration of each layer from the data link layer as m to the application layer as the second layer is shown.

In the data link J122 shown in FIG. 3(a),
Pointer NP to the next network eyebrow 23 (NextP
oin+et), a data storage pointer DP of the data link layer, and a data length DL are created.

In the network j123 shown in FIG. 3(b),
A pointer NP to the next transport layer 24, a network waste data storage pointer DP, and a data length DL are created.

In the transport It24 shown in FIG. 3(C), a pointer NP to the next session 1i25, a data storage pointer DP of the transport J124, and a data length DL are created.

In the session Ji25 shown in FIG. 3(d), the pointer NP to the next presentation layer 26, the data storage pointer DP of the session layer 25, and the data length D
L is created.

In the presentation J126 shown in FIG. 3(e), the pointer NP to the next application layer 27 and the data storage pointer D of the presentation Hi26 are
P and data length DL are created.

Finally, the application layer 27 shown in FIG. 3(f)
Then, for each packet, the last pointer FFFFH of the data storage area, the data storage pointer DPI-DP3 of the application layer 27, and the data length DLL-
DL3 is created.

FIG. 4 shows the application layer 28 shown in FIG. 3(f).
The data pointer of each packet is managed by the data pointer management table 29.

Therefore, according to the embodiments of this publication, an actual packet is created by simply rewriting the pointer NP of the upper layer for each layer, and the connection state and actual state of the data and header of each layer are determined by the management disk list table. Can be managed individually.

FIG. 5(a) and FIG. 5(b) show the creation process of the tube ring disc ribber table DT at the time of transmission.

In FIG. 5(a), first, the start pointer of the data storage area is obtained from the application (step 41).
, find the data storage pointer DP for each packet and create the management disc libter table DT (Step 42)
, a data pointer management table 29 is created using this data storage pointer DP (step 43).

The subsequent processing of each layer (step 44) differs depending on the protocol, but as shown in FIG. 5(b), if the header and processing are basically the same, no header is intentionally created. Simply write the pointer NP of the next upper layer of the data storage pointer DP in the management disk libter table DT to proceed to the next lower layer (steps 441 and 4421).
．． 445').

When transmitting large-capacity divided packets, the above-described processing is performed to divide only the application layer data.

On the other hand, if the header is not the same or the process is not the same, the protocol processing and header creation are performed (step 443), the header information is entered in the management disk printer table DT (step 444), and the next lower layer is Proceed (step 445).

When the processing of each layer (step 44) is completed, the fifth
Returning to figure (a), the preparation of the packet for transmission is completed,
Send all data (steps 45-47). Therefore, processing can be performed faster than conventional processing for each layer.

FIG. 6 shows the procedure for transmitting the above-mentioned transmission packet to the transmission medium. When a transmission request is generated from the communication LSI or hardware, the packet transmission is performed by chaining the areas of each layer of the management disk printer table DT (step 4).
8), the next packet is data pointer management table 2
9, only the pointer NP in the upper layer of the management disc libter table DT is rewritten (step 52).

FIGS. 7(a) and 7(b) show the process of creating a discriminator table at the time of reception.

As shown in FIG. 7(a), as in the case of transmission, first the start pointer of the data storage area is acquired from the application (step 61), the data pointer management table 29 is prepared (step 62), and then the packet is When received (step 63), the process moves to each layer (
Step 64, steps 641 to 645 in FIG. 7(b)
).

The processing of each layer is basically the same header and processing as in the case of reception, so if the processing is the same, no header is intentionally created.
Simply pointer NP to the next layer of data storage pointer DP
Proceed to the next upper layer by simply entering the information in the management disk libter table DT (steps 641, 642, and 645).
.

If the header is not the same or the process is not the same, the protocol processing and header creation are performed (step 643), and the header information is entered in the management disk printer table DT (step 644), and the next upper layer is processed. Proceed (step 645).

When the processing of each layer (step 64) is completed, FIG.
), the preparation for receiving the packet is completed and all data can be received (steps 65 and 66).

FIG. 8 shows the procedure for receiving a packet from a transmission medium. When a reception interrupt occurs from the communication LSI or hardware, the header section is cut out from the packet data and stored in the header storage area of each layer. Step 67) The data pointer is stored in the data storage area to create the management disc libter table DT (step 68), and is entered in the data pointer management table 29 (step 70).

According to this embodiment, at the time of reception, only the data is already stored consecutively in the data storage area, so only when processing in each layer progresses and permutation conversion or retransmission occurs, the data storage area is The inside is manipulated.

Therefore, it is possible to reduce unnecessary headers and processing in each layer for the application, and by extracting only the data included in the packet, unnecessary copying of data between layers can be reduced and communication processing can be performed at high speed. An intelligent board system in which network protocols up to a predetermined hierarchy shown in FIG. 9 are processed by another processor, and a communication LS shown in FIG.
Processing can also be performed in a non-intelligent board system where I supports up to the data link layer and the main CPU processes the upper layer.

In the intelligent board system shown in FIG. 9, the application layer, presentation layer, and session layer among the upper protocol layers are simple main transfer protocol (SMTP), file transfer protocol (FTP), and chillnet (TEL).
NET) is divided into parts of the intelligent board system, including the transport layer, network layer and data link layer, Transmission Control Protocol (TCP),
It is divided into parts of the intelligent board system including Internet Protocol (IP), User Datagram Protocol (UDP), Address Resolution Protocol (ARP) and Internet Control Message Protocol (ICMP). Also, the 10th
In the non-intelligent board system shown in the figure, each layer of the upper protocol layer from the application layer to the network layer is shared by the host/support area of the non-intelligent board system, and the data link layer is handled by the LAN board of the non-intelligent board system. It is shared.

[Effect of the invention] Data in each layer is managed based on the first management table,
If the data has the same processing and the same header, the application data is divided into packets, the pointer of the divided data indicated by the same header is rewritten based on the second management table, and the data is transferred. , there is no need to copy the data in each layer, which shortens the processing time until communication, and also minimizes the data movement process, so the data storage area can be minimized. The actual transmission efficiency of the amount of data sent to the transmission path can be improved.

Table 1

[Brief explanation of the drawing]

FIG. 1 is an explanatory diagram showing the reception and passing of data between layers in a high-speed communication buffering control device according to an embodiment of the present invention, and FIG. 2(a) is an explanatory diagram showing the high-speed communication buffering control of FIG. FIG. 2(b) is an explanatory diagram showing the actual physical structure of the device, and FIG. 3 is an explanatory diagram showing the management disc libter table included in the physical structure of FIG. 2(a).
An explanatory diagram showing the discriminator table of each layer from the data link layer to the application layer. Figure 4 is an explanatory diagram showing the pointer to the next application layer in the presentation layer. Figures 5 and 6 are the operations at the time of transmission. 7 and 8 are flowcharts showing the operation at the time of reception, and FIGS. 9 and 10 are explanatory diagrams showing the hardware to which the high-speed communication buffering control device of the present invention is applied, respectively. , FIG. 11 is an explanatory diagram showing the operation of a conventional transmitting station and a receiving station. 11... data of the nth layer, 12... header of the (n-1)th layer, 13... the (n-1)th layer, 14-... the (n-1)th layer,
n-2) layer header, 15th... (n-2)th it,
16...Next upper layer pointer, 17...Data storage pointer, 18...Data length storage area, DT.
...Management disc libter table, 29...Data pointer management table. 1 (b) Figure 7 Figure 6 Figure 8

Claims (1)

[Claims] A high-speed communication buffering control method having a layered network structure, in which data in each layer is managed based on a first management table, and if the data has the same processing and the same header, an application A high-speed communication buffering control method comprising dividing data into packets, rewriting a pointer of the divided data indicated by the same header based on a second management table, and transferring the data.