Multiplex communications – Pathfinding or routing – Switching a message which includes an address header
Reexamination Certificate
2000-03-29
2003-12-30
Kizou, Hassan (Department: 2662)
Multiplex communications
Pathfinding or routing
Switching a message which includes an address header
C370S360000, C370S401000, C370S411000, C370S422000, C709S236000
Reexamination Certificate
active
06671280
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Technical Field
The present invention relates in general to improving management of communication networks and in particular to a method and system for integrating multiple data transport mechanisms within a telecommunications network. More particularly, the present invention relates to a method and system for efficiently converting and routing data units between frame-based and Asynchronous Transfer Mode (ATM) networks.
2. Description of the Related Art
Electronic data networks are increasingly utilized to accommodate divergent types of network traffic including computer data, voice, and video. Such networks enable the interconnection of vast numbers of computer workstations, telephony endstations, television systems, multimedia teleconferencing systems, and other facilities over common data links. Such systems or workstations are typically interconnected by Local-Area Networks (LANs) such as Ethernet or Token Ring. Wide-Area Networks (WANs) are utilized to construct global interconnections over metropolitan, national, or international boundaries.
LANs and WANs are interconnected by telecommunications infrastructure devices such as hubs, bridges, and routers. In accordance with Systems Network Architecture (SNA) and Open Systems Interface (OSI) telecommunications models, a “hub” is a device providing Physical Link Layer (Layer
1
) interconnection among network nodes, while bridges utilize the Data Link Layer (Layer
2
), and routers operate within the Network Layer (Layer
3
). The Physical and Data Link connectivity provided by hubs and bridges are confined within a particular data transport “network” type (Ethernet, for example). The Network Layer connectivity provided by routers requires higher-level functionality for providing internetwork communication (converting between ATM and Ethernet protocol, for example) and also for selecting optimal routes for data packets or cells individually. Because hubs and bridges operate on data units formatted in a single protocol, routers can identity and process data which may be in one of several possible protocols. Routers are therefore often referred to as “multiprotocol” devices.
Frame-Based Technologies
A set of telecommunications standards, known as the IEEE 802 standards, have been developed by the Institute for Electrical and Electronics Engineers (IEEE) for defining methods of access and control on LANs. Ethernet is a widely utilized LAN technology for which the IEEE 802.3 standard was developed and continues to evolve. The IEEE 802.3 standard corresponds to the Physical and Data Link layers of the SNA and OSI layered-protocol models. Typically, Ethernet protocols divide the Data Link layer into two sublayers: a logic link control (LLC) sublayer, and a media access control (MAC) sublayer. The LLC sublayer facilitates station-to-station connections, control message exchanges, and error control. The MAC sublayer addresses network access and collision detection and may vary among different IEEE 802 standards.
As utilized herein, a “frame” refers to a variable-length packet of information transmitted as a single unit within a LAN. Each frame follows the same basic format and organization. Along with a data field “payload,” a frame includes control information fields for address verification, error checking, synchronization, etc. Ethernet frame encapsulation is well known in the art as a technique whereby a message or a data packet that is constructed in accordance with a higher level protocol, such as Internet Protocol (IP), can be subsumed as an undifferentiated stream of bits that is packaged in accordance with a lower protocol level data unit, such as an Ethernet frame. Variable data packet size is a characteristic of frame-based technologies such as Ethernet.
Asynchronous Transfer Mode (ATM)
ATM is a rapidly developing network technology capable of providing real-time transmission of data, video, and voice traffic. ATM is connection-oriented and utilizes cell-switching technology that offers high speed and low latency required for the support of real-time data, voice, and video traffic. Cell-switched networks, such as ATM, utilize a fixed-length data packet known as a “cell.” An ATM cell is typically 53 bytes in length, five of which are virtual routing information and the other 48 of which are data.
ATM serves a broad range of applications very efficiently by allowing an appropriate Quality of Service (QoS) to be specified for differing applications. Various service categories have been developed to help characterize network traffic including: Constant Bit Rate (CBR), Variable Bit Rate (VBR), Unspecified Bit Rate (UBR), and Available Bit Rate (ABR). In addition, ATM provides for the automatic and guaranteed assignment of bandwidth to meet the specific needs of applications, making it ideally suited for supporting multimedia as well as for interconnecting LANs. Due to its inherent speed and switching efficiency characteristics, ATM is increasingly utilized as a backbone network for connecting frame-based LANs.
Multiprotocol Networking
In response to ever-increasing support needs of communications networks which are growing in terms of geographic dispersion and complexity, the functionality of several network infrastructure devices including hubs, bridges, and routers are increasingly integrated within a single device referred to hereinafter as a “network processor.” Such network processors may include means for integrating several different types of data transport mechanisms (referred to hereinafter as “transport protocols”) such as the frame-based data flows utilized in Ethernet technologies and fixed-length cell flows utilized in ATM. As multiprotocol switched networks become more prevalent, there is a corresponding need for a network processor in which differing data transport mechanisms can be integrated with minimal processing and data storage overhead.
The ability to integrate these differing protocols in a network processor provides the potential for greater flexibility and scalability within telecommunications networks, but also presents traffic management problems. The data throughput speed of a network processor is substantially reduced when the network processor must convert flows between differing transport protocols (Ethernet frames to ATM cells, for example) in addition to directing internetwork traffic within a LAN or WAN. Conventional network processors require substantial internal buffer storage capacity and additional data processing overhead in order to address protocol conversion problems which are particularly acute when frame-based data flows are combined with high-speed cell-switched ATM flows. Unable to maintain “wirespeed,” such conventional network processors may thus become a network traffic bottleneck.
One approach to accommodate the high throughput requirements of frame-to-cell conversion within a centralized network processing device is to convert all incoming traffic into ATM cell format. This solution requires additional processing overhead for converting and reconverting non-ATM traffic. For ATM-to-frame conversion, ATM cells are typically collected and assembled into Ethernet frames prior to switching. Incoming or “upside” ATM ports may be simultaneously receiving several thousand flows, each comprising cells that may arrive at the upside port at unpredictable and widely varying time intervals. Conventional data routing devices have therefore required large ingress or “upside” data storage capacity to provide adequate collection and assembly point for ATM-cell-to-Ethernet-frame conversion.
In order to enhance the practicability and quality of multiprotocol telecommunications networks, it would be desirable to provide an efficient method and system for integrating ATM and Ethernet flows within a network processor device whereby upside memory and overhead processing requirements are minimized.
SUMMARY OF THE INVENTION
A method and system are disclosed for integrating ATM and frame-based traffic flows within a telecommunications network that includes a network pro
Bass Brian Mitchell
Calvignac Jean Louis
Gallo Anthony Matteo
Heddes Marco C.
Siegel Michael Steven
Bracewell and Patterson
Kizou Hassan
Levitan Dmitry
LandOfFree
Network processor for multiprotocol data flows does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Network processor for multiprotocol data flows, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Network processor for multiprotocol data flows will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3143076