Electrical computers and digital processing systems: multicomput – Computer-to-computer data routing
Reexamination Certificate
1998-05-18
2002-01-29
Sheikh, Ayaz (Department: 2155)
Electrical computers and digital processing systems: multicomput
Computer-to-computer data routing
C709S242000, C709S250000
Reexamination Certificate
active
06343326
ABSTRACT:
BACKGROUND OF THE INVENTION
This invention relates to computer communication and networking and in particular to a method of transmitting, on a synchronous transfer mode (ATM) network, a packet which is formed in accordance with a protocol different from ATM and to a network system for transmitting the packet.
Increasingly communication over Internet network has become widely prevalent. Use of internet is bound to significantly increase further in the future. It is well known in the art that a typical network can be logically considered to comprise several layers including physical layer, data link layer, network layer, transmission layer, etc. In each of these layers different communication protocols are used. The Internet Protocol (IP) is used to carry out data transmission at the network layer of the internet. A Transmission Control Protocol (TCP) is used at the transport layer.
A synchronous transfer mode (ATM) is a high performance transmission protocol that can process a great deal of multimedia information. In such an ATM protocol, all information to be transferred is arranged within cells that have fixed lengths of 53 octets. A cell is composed of two fields; an information field and a header field. The information field is 48 octet long and a header field of 5 octet long. A message longer than 53 octets is divided into a plurality of cells.
Importantly, the ATM protocol has two hierarchical levels; a virtual channel level and a virtual path level. The virtual channel is a unidirectional transfer channel of an ATM cell which is specified by a unique value of an identifier. The identifier is called a virtual channel identifier (VCI) and is located within the header field.
Likewise, the virtual path is a unidirectional transfer path to which each virtual channel belongs and is specified by a virtual path identifier (VPI) which is also located within the header field. In an ATM all the cells having the same virtual channel connection and virtual path connection (VCC/VPC) are transferred through the same route in the network. The order of transmission of the ATM cells is maintained in the VCC. As a corollary, the ATM cell transmitted first is also received first.
On the other hand, a conventional IP network is implemented using routers. A message is divided into packets that have variable lengths, unlike an ATM cell. Each router receives a packet and from the address it determines an output port to which the packet is to be delivered. Therefore, in order to determine the output port, a great deal of processing is required in each router. This processing causes a bottleneck in data transmission in an IP network, affecting the transmission speed.
There have been several techniques suggested to remove such a bottleneck. Some of these techniques are aimed at utilizing the higher transmission speeds offered by ATM networks.
One such techniques is disclosed in Japanese Patent Unexamined Publication No. Hei 8-125692, namely, 125692/1996 (hereinafter, Reference 1). This technique uses a cell switch router (abbreviated to CSR). According to this technique, the CSR does not do an IP table look-up to detect an output port, as is done by normal IP routers. Instead CSR observes a certain attribute of each IP packet and selects an output port related to the attribute. It then extracts a VCI previously determined for this output port. Thereafter, the CSR converts the packet into a sequence of ATM cells. Each of these cells are provided with header information corresponding to the pre-determined VCI and then transferred. Thus, the CSR transfers IP packet in a manner similar to the ATM switch.
Using this technique, one can avoid the step of searching for the output port. Accordingly, this technique enables high speed transfer operation in comparison with the conventional technique that uses an IP router.
Herein, in the above-mentioned example, it should be noted that there are two important operations. Conversion and transfer operation by converting a network address of an IP packet (or a packet formed in accordance with a protocol of a different layer) into a simple virtual channel will be called a cut-through or a short-cut operation. Likewise, mapping an attribute of the network layer or an upper layer onto a VCI will be referred to as binding.
In addition, a mode and a path of the cut-through operation will be named a cut-through mode and a cut-through path respectively. These are also called a switched mode and a switched path, respectively.
When CSR is used, bindings associated with each attribute need to be determined a priori. In order to enable the binding, ATM connection setup needs to be carried out by either a PVC (Permanent Virtual Channel) or an SVC (Switched Virtual Channel).
In the other conventional techniques, such as IPOA (IP over ATM) and MPOA (Multi-Protocol over ATM), a virtual connection is also established between an origination point and a destination point for cut-through operations each time a sequence of packets is transmitted.
The conventional techniques mentioned above are disadvantageous at least in the sense that PVC based system needs to allocate a large number of VCs depending on network size and the number of attributes to be selected. Therefore, a PVC based system lacks scalability.
Likewise, an SVC based system has a shortcoming that the establishment of connection contributes to overheads that eviscerates the advantages resulting from a cut-through operation when the network session using ATM is short.
One conventional way of solving above-mentioned is disclosed in WO97/28505 (hereinafter, Reference 2) Therein, each node in a network comprises an ATM switch that has an IP routing module connected to it. This IP module identifies IP packet flow. In this event, each IP packet flow is defined by a combination of a transmission source address of an IP packet, a destination address, a port number on the TCP protocol. This IP packet flow is used to define a sequence of packets which form a session. According to a new version, IP v 6 of the IP Protocol, a flow identifier is also defined.
In the method of Reference 2, a default VC is used to transmit a flow. The default VC represents a PVC previously defined to send the flow to the router module of the node in question. Thus far, this method is similar to the operation carried out in a normal IP. The only difference being that the packet is transferred in the form of ATM cells.
Each successive node monitors continuation of the flow and simultaneously carries out signaling between its two adjacent nodes, namely the upstream node and the downstream node in accordance with a local protocol. This local protocol is called a flow management protocol and is not standardized. In this protocol the downstream node sends a signal to the node in question that shows the assignment of a VCI to the flow. In responsive to this signal, the node in question switches the flow from the default VC to a VC indicated by the downstream node.
When similar processing is repeated in each node on a hop-by-hop basis and is completed in all of the nodes, the flow in question is transferred in the cut-through mode through the cut-through path.
In this method, each node operates as a usual router when a flow is of a short duration and operates using an SVC in the cut-through mode when the flow is continued for a comparatively long time. This method does not have the loss of efficiency that occurs in other conventional methods mentioned above. Herein, it is to be noted that in the method of Reference 2 a signaling protocol is run for a period of time between the nodes to establish a virtual connection. During this time each node is operated as a router.
During a multicast operation, an important aspect of the IP protocol, a substantial problem is noted in methods that carry out signaling between nodes. Multicast operation is used for simultaneously delivering a packet to a plurality of reception nodes. Such a multicast operation is performed using protocols like IP multicast protocol, also known as a dense mode PIM (Protocol Independent Mult
Acharya Arup
Dighe Rajiv
NEC USA Inc.
Sheikh Ayaz
Tran Philip B.
LandOfFree
System and method of transferring internet protocol packets... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method of transferring internet protocol packets..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method of transferring internet protocol packets... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2834544