KR100221328B1 - Asynchronous transmission mode communication method Memory utilization method using receive buffer per connection in segmentation and recombination sublayer of network interface card - Google Patents

Abstract

According to the present invention, in a sublayer of a network interface card (NIC) of asynchronous transmission mode communication mode, the maximum transmission packet size is determined based on the connection data based on the connection characteristics when the connection is accepted. The buffer size is determined and used according to the traffic characteristics, which reduces the wasted memory and supports the use of a large number of connections. A method of efficiently utilizing memory through a method of using a memory in a sub-layer of a network interface card (NIC) in an asynchronous transmission mode communication method (NIC), and a maximum transmission packet (TS) of a connection when a connection is accepted. Determining a size of c); After the pointer to the buffer of the transmission packet TS is written in the buffering of the memory, a second step in which the memory is allocated and used corresponding to the pointer is characterized in that it comprises.

Description

Asynchronous transmission mode communication method Memory utilization method using receive buffer per connection in segmentation and recombination sublayer of network interface card

The present invention relates to a memory usage method according to data traffic for each connection in a sublayer of an asynchronous transmission mode communication network interface card. In particular, the present invention relates to a partitioning and recombination of an asynchronous transmission mode communication network interface card (NIC). In the sub-layer, when the connection is accepted, the maximum transport packet size is determined by reflecting the characteristics of the connection, and the buffer size according to the data traffic characteristics of the connection is appropriately used to reduce the waste of memory. The present invention relates to a method of using memory according to data traffic for each connection in a partitioning and recombination sublayer of an asynchronous transmission mode communication method network interface card capable of supporting a connection.

In general, the ATM Adaptation Layer (ATM) adapts the service provided by the ATM layer to the requirements of the upper layer user. Therefore, the ATM adaptation layer must provide support for the asynchronous transmission mode communication environment and the asynchronous transmission mode communication environment in addition to performing support of the user plane, the higher level control plane and the management plane.

In addition, the ATM adaptation layer maps the protocol data unit (PDU) of the upper layer to the payload section of the ATM cell, handles transmission errors, processes and flows control of lost and inserted cells. It provides timing control. The ATM adaptation layer is divided into two sublayers: a segmentation and reassembly (SAR) sublayer and a convergence sublayer (CS).

The convergence sublayer (CS) performs a function related to a specific service, and the partitioning and recombination (SAR) processes a function related to service segmentation and recombination by processing a function that is not related to service termination. Therefore, at the transmitting side, the convergent sublayer (CS) is applied as user information from an upper layer, attaches a header and a trailer, forms a convergent sublayer protocol data unit (CS-PDU), and sends it to a split and recombination (SAR) sublayer. This split and recombine (SAR) sublayer cuts it into the size of an ATM cell, attaches a header and a trailer to form a split and recombine protocol data unit (SAR-PDU) and transmits it through the ATM layer.

On the receiving side, the segmentation and recombination (SAR) sublayer extracts only the payload interval among the segmentation and recombination protocol data units (SAR-PDU) received through the ATM layer to form a convergence sublayer protocol data unit (CS-PDU). After that, the information is transferred to the convergence sublayer CS, and the convergence sublayer CS extracts only upper layer user information among the received convergence sublayer protocol data units CS-PDUs and delivers the information to the upper layer.

At this time, the header and the trailer attached to each sub-layer in the transmission process are related to error processing, buffer management, and sequence preservation. Will be passed to the layer.

On the other hand, ITU-T classifies user services into four types of A, B, C, and D according to constant bit rate (CBR), real time, and connectivity, and AAL type to correspond to these various services. It is defined by dividing into 1 to 4. In addition, the June 1992 ITU-T Conference newly discussed AAL Type 5 to support high-speed data communications.

In the AAL type 1, a real-time equal bit rate service is provided in a connected manner, and a service provided to a user is largely equal bit rate (CBR) data transfer, timing information transfer, user data structure information transfer, error recovery capability, and cannot be recovered. Display of information about errors and losses.

FIG. 1A illustrates a relationship between a large buffer ring and a large buffer pool in a memory of a partitioning and recombination sublayer of a general asynchronous transmission mode communication network interface card. FIG. Asynchronous Transfer Mode Communication A diagram illustrating a relationship between a small buffer ring and a small buffer pool in a memory of a partition and recombination sublayer of a network interface card.

Here, in Fig. 1A, reference numeral 10 denotes a large buffer ring, and 11 denotes a large buffer pool. In Fig. 1B, reference numeral 15 in the figure denotes a small buffer ring, and 16 denotes a small buffer pool.

As mentioned above, the partitioning and recombination (SAR) sublayer of most asynchronous transmission mode communication network interface card (NIC) receivers repackages packets using the same size or limited number of buffers for all connections. Will be assembled. However, there is a problem in that a waste of memory occurs for a connection having a very small size compared to the size of the buffer.

Accordingly, the present invention is to solve the above problems, the size of the maximum transmission packet reflecting the characteristics of the connection at the time of accepting the connection in the sub-layer of the asynchronous transmission mode communication network interface card (NIC) sub-layer Sub-layer of asynchronous transmission mode communication interface card that can reduce the waste of memory and support many connections by determining the buffer size according to the data traffic characteristics of the connection. The purpose of the present invention is to provide a memory usage method according to data traffic for each connection.

In order to achieve the above object, the present invention provides a method of using a memory in a division and recombination sublayer of an asynchronous transmission mode communication interface network interface, wherein a virtual path identification number is included in header information of each ATM cell at connection acceptance. And a first step of determining a maximum transmission packet size of each traffic data based on the virtual channel identification number. And a second step of allocating a memory corresponding to the pointer after the pointers to the respective transmission packets are recorded in the buffering of the memory.

According to the present invention configured as described above, in a sublayer of a network interface card (NIC) of asynchronous transmission mode communication mode (NIC), after determining the size of the maximum transmission packet by reflecting the characteristics of the connection at the time of connection acceptance, it is determined. Based on the size of the buffer appropriately determined by the data traffic characteristics of the connection is used as a basis, it is possible to reduce the waste of memory and to support many connections.

FIG. 1A illustrates a relationship between a big buffer ring and a big buffer pool in a memory of a partitioning and recombination sublayer of a general asynchronous transmission mode communication network interface card. FIG.

FIG. 1B is a view illustrating a relationship between a small buffer ring and a small buffer pool in a memory of a partitioning and recombination sublayer of a general asynchronous transmission mode communication network interface card. FIG.

2 is a conceptual diagram illustrating a general ATM protocol reference model;

3A is a diagram showing a data format of an ATM cell;

3b is a diagram illustrating a header structure in a user network interface (UNI);

3C is a diagram illustrating a header structure at a network node interface (NNI);

4 is a diagram showing a data format for each layer in the asynchronous transmission mode communication method;

5 is a diagram illustrating a flow of messages related to call processing in a user network interface (UNI) of an asynchronous transmission mode communication network;

FIG. 6 is a view showing an embodiment of a memory usage method according to data traffic for each connection in a partitioning and recombination sublayer of an asynchronous transmission mode communication network interface card according to the present invention.

* Explanation of symbols for the main parts of the drawings

1: caller, 2: network,

3: called party, 10: big buffer ring,

11: big buffer pool, 15: small buffer ring,

16: small buffer pool, 20: buffer ring,

21: Buffer pool.

Hereinafter, with reference to the accompanying drawings, preferred embodiments of the present invention will be described in detail

First, to simplify the understanding of the present invention briefly described asynchronous transmission mode communication method to which the present invention is applied

2 is a conceptual diagram illustrating an ATM protocol reference model, wherein the conceptual diagram is composed of a management plane, a control plane, and a user plane, and the management plane is again hierarchical management. And planar management. In addition, the plane management means the overall management of the system, and the hierarchical management manages resource and usage variables and OAM information management.

In addition, the control plane manages call control and connection control information, and the user plane transmits user information. The protocol of the control plane and the user plane is composed of a higher layer, an ATM adaptation layer, an ATM layer, and a physical layer.

As shown in FIGS. 3A to 3C, the user's long message is divided into ATM cells and transmitted, and the received ATM cell is reassembled into one message and transmitted to the upper user. .

3A is a diagram illustrating a data format of an ATM cell, FIG. 3B is a diagram illustrating a header structure at a user network interface (UNI), and FIG. 3C is a diagram illustrating a header structure at a network node interface (NNI).

Here, the ATM cell is divided into a header section of 5 bytes (or octets) and a user information section of 48 bytes, and the header of 5 bytes is a user network interface (UNI) as shown in FIGS. 4B and 4C. Header structure in user network interface (UNI), where the first byte is a 4-bit generic flow control (GFC) and a 4-bit virtual path identification number (VPI) identifier).

The second byte is composed of a 4-bit virtual path identification number (VPI) and a 4-bit virtual channel identifier (VCI), and the third byte is an 8-bit virtual channel identification number (VCI). The fourth byte consists of a 4-bit virtual channel identification number (VCI), a 3-bit payload type (PT), and a 1-bit cell loss priority (CLP). The byte consists of 8 bits of header error control (HEC).

Also, in the header structure of the network node interface (NNI) as shown in FIG. 3C, the general flow control (GFC) in the first byte of the user network interface (NNI) is converted into a virtual path identification number (VPI). Except for being used, it can be seen that it is identical to the header structure of NNI. This asynchronous transmission mode communication method has a hierarchical structure as shown in Table 1 below and has standardized standards for each layer.

TABLE 1

As shown in Table 1, the asynchronous transmission mode communication method is divided into vertical structures such as a physical layer, an ATM layer, an ATM adaptation layer (AAL), and a higher protocol layer. It is divided into segmentation and reassembly sublayer (SAR) and convergence sublayer (CS) sublayer, and the physical layer is divided into physical medium (PM) and transmission convergence (TC) sublayer.

In addition, a service required by a user in an asynchronous transmission mode communication method may be classified as shown in Table 2 below according to its characteristics.

TABLE 2

The AAL protocol corresponding to the service is divided into AAL 1 to AAL 5 as shown in Table 3 below.

TABLE 3

In Table 3, the AAL layer is divided horizontally as AAL 1, AAL 2, AAL 3/4, and AAL 5 to efficiently process the corresponding service according to the type of service.

Here, the AAL layer 1 is a convergent sub-layer (CS) that transparently transmits a Class A service data unit (U-SDU) having a constant bit rate, detects transmission errors, and performs information identification and clock synchronization functions. A split and recombination sublayer (SAR) that divides variable-length data received from the convergence sublayer (CS), creates an ATM cell, transfers it to the ATM layer, and receives and reassembles the ATM cell from the ATM layer to recover the CS-PDU. Will be divided into

In addition, the convergence (CS) sublayer is a common part convergence sublayer (CPCS) in charge of functions common to connectivity and connectionless services, and a service specific convergence sublayer for providing a specific AAL user service. (SSCS: service specific convergence layer).

4 illustrates a data format for each layer in the asynchronous transmission mode communication method, in which a user service data unit (U-SDU) of a higher layer passes through an AAL service access point (AAL-SAP). After that, it is formed as AAL service data unit (AAL-SDU) and stored in AAL FIFO.In the AAL1 SAR layer, the CS-PDU is divided by 47 bytes according to the message to be transmitted by the user, and then added by adding 1 byte of SAR header. And a recombination protocol unit (SAR-PDU) is formed and sent down to the ATM layer via the ATM service access point (ATM-SAP). In the ATM layer, a 5-byte ATM header is attached to form a 53-byte ATM cell, and then transmitted to another terminal or ATM switch through an optical transmission path of the physical layer.

That is, AAL type 1 protocol transmits U-SDU of equal bit rate at the same bit rate along with related time information, so that clock information of information source can be extracted at the receiving side, and at the convergence part layer, the bit for high quality video or audio signal Error correction function is provided, and the division and reassembly sublayer divides the CS-PDU and adds a 1-byte header to send it to the ATM layer.

FIG. 5 is a diagram illustrating a call processing related message flow in a user network interface (UNI) of a synchronous transmission mode communication network. Here, the figure shows a call processing process between a calling party 1 and a network 2 and a called party.

First, a virtual channel connection (VCC) is formed through a signaling adaptation layer (VCalling ALL) in order to perform call and access control, and a payload ( user data) The connection for delivery is controlled. The message used for call / access control is used for B-ISDN call / access control as shown in the following Table 4, and for call / access control between N-ISDN and B-ISDN as shown in Table 5 below. There are messages to be used in the global call reference as shown in Table 6 below.

TABLE 4

TABLE 5

TABLE 6

In FIG. 5, the messages of Tables 4 to 6 generated according to Q.2931 are transmitted using the 'AAL-DATA-REQUE ST' primitive of the signal AAL (SAAL).

On the other hand, if a "SETUP" message is generated to establish a call from the caller 1 and then transferred to the network through the assigned signaling virtual channel (VCI = 5) and the timer T303 is started, the "call initialization" (Call Initiated state) ".

In this case, the "Setup" message includes a call reference, various information elements (eg, called part number) required for call processing, user cell speed of the asynchronous transmission mode communication network, broadband bearer capability, and the like. , Quality of service parameters (QoS), etc.]. If there is no response for the time set by the timer T303, the " setup " message is retransmitted, and if there is no response even after a predetermined number of times, the call processing is stopped.

After the "Setup" message is received from the network 2, a valid connection identifier (VPCI / VCI) is selected and assigned, and then a "SETUP" message is transmitted to the called party 3 again, and then the "call procedure." (CALL PROCEEDING) "message is sent to the sender (1). At this time, when a "call procedure" message is input from the caller 1, the timer T303 is stopped, and after the timer T310 is started, the state of the outgoing call procedure is entered.

Then, after the "setup" message is received from the called party 3, the "CALL PROCEEDING" and "ALERTING" messages are transmitted to the network 2, and the alerting message from the network 2 is transmitted. When received, it is transmitted to the caller 1 and is in the state of "Call Delivered". Then, when the "alerting" message is received from the caller 1, the timer T303 or T310 is stopped, and the call is delivered.

Then, when a "CONNECT" message is generated so that the connection is allowed from the called party 3 and then transmitted to the network 2, the network 2 transmits it to the sender 1 and the "connect acknowledgment." (CONNECT ACK) "message to the called party 3 side, and receives a" connect acknowledgment "message from the sender (1).

Through the call processing process as described above, a communication path (connection) authorized by the connection identifier (VPCI / VCI) is formed between the caller 1 and the called party 2 so that data transmission and reception can be performed.

On the other hand, when the data transmission is terminated or in progress, the user (recipient or caller) who wants to release the connection generates a "RELEASE" message and starts the timer T 308 to request the release of the connection to the network. After that, it becomes a "Release Request state", and when the network receives a "release" message, the network releases the connection to the virtual channel, transmits a "release" message to the other party, and informs it of the "release request (RELEASE COMPLETE). Message is sent to the release request and is in the "NULL" state.

In addition, when the user (sender or called party) requesting the disconnection receives the "RELEASE COMPLETE" message, the timer T 308 is stopped, the virtual channel, the call number, etc. are released, and the "NULL" state is received. At this point, the user or network can generate a "STATUS ENQUIRY" message at any time to request information about the network or other user's status, and receive a "STATUS ENQUIRY" message. Or the network generates a "STATUS" message indicating its status.

When accepting the connection as described above, the size of the maximum transmission packet is determined by reflecting the characteristics of the connection, and then the appropriate buffer size is determined based on this.

FIG. 6 is a diagram illustrating an embodiment of a memory using method according to data traffic for each connection in a partitioning and recombination sublayer of an asynchronous transmission mode communication network interface card according to the present invention.

Here, the memory usage method in the partitioning and recombination (SAR) sublayer of the asynchronous transmission mode communication network interface (NIC) is as follows. First, in the first step, when the connection is accepted, the maximum transmission packet of each traffic data is determined by a virtual path identifier (VPI) and a virtual channel identifier (VCI) among header information of each ATM cell. In the second step of determining the size of TS), after the pointers of the first to Nth connections to the respective transmission packets TS are written in the buffering of the memory, the memory is allocated corresponding to the pointers.

In addition, two buffers are allocated to the traffic data corresponding to the virtual path identification number (VPI) and the virtual channel identification number (VCI), and the size of the buffer is AAL layer common part convergence layer layer (CPCS) protocol data unit ( PDU) is determined by the size.

In the embodiment of the present invention, the size of the buffer is determined and used according to the data traffic characteristics of the connection, thereby reducing the waste of memory. Thus, it is possible to accept more connection acceptance requests in one memory record. On the other hand, due to the connection-oriented nature of the asynchronous transmission mode communication network, packets belonging to a specific connection are sequentially reached at the receiving end, so that the number of buffers for reassembly is two per connection. However, when the traffic density is very high, an extra buffer is prepared to prevent the loss of received packets.

As described above, in this embodiment, two buffers are allocated to the virtual path identifier (VPI) and the virtual channel identifier (VCI) of the header information of each ATM cell. do.

The size of the buffer is determined by the size of a common part convergence sublayer (CPCS) protocol data unit (PDU) at the time of accepting the connection. This reduces the waste of memory. Thus, more connections can be supported.

On the other hand, the reference numerals written in the components of the claims of the present application to facilitate the understanding of the present invention, and are not written in the intention to limit the technical scope of the present invention to the embodiments shown in the drawings.

Explained above

Claims (3)

Asynchronous Transfer Mode Communication Method A method of using a memory in a partition and recombination (SAR) sublayer of a network interface card (NIC), When the connection is accepted, the maximum transmission packet (TS) size of each connection distinguished by virtual path identifier (VPI) and virtual channel identifier (VCI) among header information of each ATM cell. Determining a first step; A sub-layer of the asynchronous transmission mode communication network interface card, comprising a second step of allocating a memory corresponding to the pointer after the pointers to the respective transmission packets TS are recorded in the buffering of the memory. Memory Usage by Using Receive Buffers per Connection in .NET 2. The partition of claim 1, wherein two buffers are allocated for each connection identified by the virtual path identification number (VPI) and the virtual channel identification number (VCI). And a method of utilizing memory by using a connection buffer for each connection in the recombination sublayer. 3. The partitioning and recombination unit of claim 2, wherein the buffer size is determined by a size of an AAL layer common part convergence layer layer (CPCS) protocol data unit (PDU). Memory utilization method using connection-specific receive buffer at layer.