The present invention provides a very simple and scalable architecture which gives a substantially optimal solution for an IP over ATM network service, by exploiting the QoS of the ATM network, providing shortcut communication when necessary, reducing connection setup delay and smoothing migration from the current deployments, while retaining simplicity. This is achieved by introducing three additional functions to the normal operation of the Classical IP model, namely: flow classification/detection, explicit indication of ATM address and QoS, to the receiver, prior to connection setup and receiver initiated connection setup. The present invention also provides, a multi-cast architecture based on an extension to the Multi-cast Address Resolution Service (MARS) architecture known from IETF.
This invention relates to an IP processor, and more particularly, provides an IP processor that reduces network load when a plurality of IP processors connected to ATM switches are used in edge portion of an IP network. The IP processor is comprised of a line interface unit for interfacing with an ATM switch, an IP packet buffer unit for temporarily storing an IP packet from the line interface unit, and sending out the IP packet after address resolution to the line interface unit, and an IP address resolution unit that responds to address resolution request from the IP packet buffer unit and returns the destination address information after address resolution, wherein the IP packet buffer unit sends out, when destination address information cannot be retrieved from the IP address resolution unit, the temporarily stored IP packet to a transfer route for direct transfer between IP processors.
A method and apparatus for ensuring end-to-end QoS for user applications operating in multi-transport protocol environments while using PVC or SVC connection management procedures. A user application at a workstation having specific QoS requirements can selectively connect to one of a plurality of servers having varying QoS profiles, regardless of the transport protocols used in the underlying network. The user application initiates a session with a first QoS negotiator and a first QoS selector. The first QoS negotiator queries a second QoS negotiator for the QoS profile of a connected server. The second QoS negotiator, in conjunction with a second QoS selector, notifies the server of the address of the second QoS negotiator. The second QoS negotiator, in conjunction with the second QoS selector, sends a response to the first QoS negotiator and the first QoS selector indicating QoS profile and connection information of the server. The first QoS selector stores the received QoS profile and connection information in a database. The database is then queried by the user application to determine if a server having the desired QoS profile exists. If such a server does not exist, the QoS selection and negotation procedures are repeated and the database is updated. If a server having the desired QoS profile does exist, a PVC or SVC connection is established between the first and second QoS negotiators and QoS selectors, thereby ensuring end-to-end QoS for the user application and allowing the application to exchange data with the server using the PVC or SVC connection.
A system and method to provide node-to-node connectivity in a communications network are disclosed. A virtual connection is established between a source node coupled to a client and a destination node within the connection-oriented network using standards-based signaling. A communication session is then activated between the client and the destination node on the virtual connection.
