Abstract: A method and apparatus are provided for connection-oriented switching in a communications network wherein a pre-established path is established between a select pair of an ingress switch and an egress switch. The use of pre-established paths enables a reduction in the total number of connections required inside the switch cloud, reduces the CPU load on trunk switches, and shortens the time for connection setup. In the embodiment described, the DA/SA fields of a MAC frame data packet are replaced with a "virtual path", which identifies the pre-established path between the ingress and egress switches. A "virtual circuit" is provided in another field of the modified packet which specifies the out-port and out-header on the egress switch for demultiplexing the modified packet upon receipt at the egress switch. The virtual circuit is exchanged between the ingress and egress switches at connection setup. The virtual path is assumed to already be in place, and known to both switches, prior to connection setup.

Abstract: Method and apparatus for establishing restricted broadcast groups in a switched network. The method assigns different virtual LAN identifiers (VLAN-IDs) to different subsets of associated end systems or access ports. Tables are maintained for mapping the VLAN-IDs with associated end systems and access ports. When a broadcast packet is received at a first switch, it is encapsulated with a VLAN header, including the VLAN-IDs, and sent out a multicast channel to all other switches in the network (domain). The original packet is sent out the other access ports of the receiving switch for the designated VLAN-IDs. The switches receiving the VLAN packet remove the header and send the original packet out access ports associated with the VLAN-IDs extracted from the header. The method provides a mechanism for forwarding broadcast packets of a protocol not supported by the switching mechanism, as well as multicast packets and unicast packets from undiscovered end systems.

Abstract: A new packet filtering system associates domain identifiers with respective sets of addresses. A set of domain prefixes defines the set of addresses associated with a given domain identifier. Domain prefixes are found matching the source address and destination address of each received packet. These prefixes are associated with a source domain identifier and destination domain identifier respectively. The system similarly associates sets of one or more protocol types and port ranges with respective protocol domain identifiers. The protocol type, source port and destination port of the received packet determine source and destination protocol domain identifiers for the received packet. The system includes a filtering matrix including one or more entries, each indicating whether an associated received packed should be filtered.

Abstract: Method and apparatus for coordinating access to a shared object amongst a plurality of processes in a distributed system. One process is identified as a lock owner process controlling a lock associated with the shared object. When a process needs to access the shared object, it requests control of the lock from the lock owner process. When no other process controls the lock, the lock owner process grants control to the requesting process. When another process controls the lock, the lock owner process places the requesting process in a queue and waits for the lock to become available. All accesses to the shared object are processed through the lock owner processes thus assuring coordination and synchronization among the processes.

Abstract: A computer system includes a gateway which provides integration between a network management platform and a system management platform. Such a gateway facilitates sharing of network management and system management events and alarms, as well as sharing of network management and system management display views. From the shared events and alarms, each platform may correlate such shared events and alarms with other data available to the platform. Thus, each platform has the advantage of using its own data in combination with data from the other platform to more effectively perform its functionality.

Abstract: A data transmission network having a port-based default VLAN that limits flooding to other VLANs. The default VLAN receives a data packet, ascertains the destination address of the packet, and then determines if the destination port is one of the default VLAN ports. The data packet is transmitted to the destination port if it is one of the default VLAN ports, or to each of the default VLAN ports if the destination port is not one of the default VLAN ports. The data packet is not transmitted to any other non-default VLAN port.

Abstract: A scheme for protecting memory stored in a DRAM using a combination of horizontal and vertical parity data to detect and correct errors in a protected space of memory in which code is stored. The DRAM memory of this scheme is architected with the code stored in horizontally contiguous bytes and the vertical parity, generated when the code is compiled, also stored in horizontally contiguous bytes, but in a row of DRAM memory separate from those in which the code is stored.

Abstract: A packet of data is received from a LAN and transmitted over a WAN, by retaining the native LAN frame format of the packet during transmission across the WAN. Thus, LAN data may be transmitted over a SONET point-to-point link within a WAN network without the interim steps of creating ATM cells or other WAN transport packaging protocols. Instead, the LAN data may be transmitted directly over the SONET link as raw data, and reconstructed directly at the receiving end of the SONET link. A first buffer stores data from the LAN so that a corresponding packet size may be determined, and a second buffer stores data from the WAN to account for any speed difference between the LAN circuitry and WAN circuitry.

Abstract: A system determines that a frame relay connection exists between an interface on a first interface device and an interface on a second interface device, for example by comparing addresses resident in routing tables of the interface devices. The system then queries each of the first and second interface devices, to determine the amount of traffic that is communicated by each channel of each of the two interfaces. This data is then correlated to determine the relative amount of data by each channel on each of the two interfaces, and the pair of channels having the best correlation are determined to represent an actual connection.

Abstract: A switch is provided for use in a virtual communications system having multiple local area networks interconnected by multiple switches through a trunk, which has one or more trunk stations connected directly thereto. The switch includes a first communications port connected directly to a first local area network and a second communications port connected directly to the trunk. The first local area network is within a virtual area network configured to include a second local area network and a trunk station. A switch control detects a communication from the first local area network having a multicast address representing desired destination addresses. The switch control appends a VLAN header having a destination address different than but corresponding to the multicast address to the communication to form a VLAN communication and directs transmission of the VLAN communication to the second communication port for delivery to the multicast addressees.

Abstract: In a secure fast packet switch having a plurality of input ports and a plurality of output ports, a method of determining which port in the plurality of output ports data that is received on one input port in the plurality of input ports is to be sent to, the method including the steps of determining a physical layer address of a sending node, determining a physical layer address of a receiving node, determining an input port in the plurality of input ports that the data was received on, determining if the physical layer address of the sending node and the physical layer address of the receiving node are an allowed combination, determining the magnitude of the node identification number of the sending node, determining the magnitude of the node identification number of the receiving node, obtaining outbound port information from a first predetermined location in a data structure stored in a memory if the node identification number of the sending node is greater than the node identification number of the recei

Abstract: A repeater device for forwarding a data packet from a first Ethernet collision domain to a second Ethernet collision domain has a plurality of ports, each port for connection to an independent Ethernet collision domain, each port has an associated receive buffer and an associated transmit buffer, and there is a means for forwarding a data packet from the receive buffer of a receiving port to the transmit buffer of a transmitting port. A data packet received at the receiving port is then first stored in that port's the receive buffer, is forwarded to the transmit buffer of the transmitting port, and is then transmitted from the transmit buffer by the transmitting port.

Abstract: Method and apparatus for avoiding receive livelock and transmit starvation, and for minimizing packet loss and latency in a communication network station. The invention uses a combination of processing threads, polling and, in a preferred embodiment, a judicious use of interrupts, to allocate the use of processing resources fairly among competing functions. Real time processing threads are structured to execute for a preselected maximum time interval, based on numbers of units processed by each thread, and then to yield control to a thread scheduler, which selects and invokes a new thread for execution. Work to be done in the various threads is determined either by polling or by an interrupt system, and then posted to the threads for execution. If interrupts are used, interrupt service routines perform only the minimal processing needed to recognize an interrupt, other interrupt servicing functions being deferred for execution in a processing thread.

Abstract: A method for selecting a communication path over which to send a communication load between a first station and a second station in a communication network, in which the communication network has a plurality of possible communication paths between the first and second stations. The method comprises identifying at least one of the possible communication paths between the first and second stations, determining a first path metric for each identified path, the first path metric having a value that may vary as distribution of the load across the network varies and selecting one of the at least one identified paths based on the value of the first path metric for each identified path.

Abstract: Method and apparatus providing for load sharing in redundant communication networks. The method and apparatus may include detection of redundant communication links in the network topology and sharing communication load over those links. This may be accomplished through assignment of unique labels to each link in a group of redundant links and assignment to each data packet of a value corresponding to the label on just one of the links; the packet being forwarded on only that link. The method and apparatus are also suited to quick recovery from a change in state of a network topology.

Abstract: A scheme for interlocking two devices in a computer system for the performance of request/response transfers between the two devices. The scheme provides a request/response memory including a plurality of entries, each of the entries having a request storage memory space for storing a request and a response storage memory space for storing a corresponding response. Each request storage memory space and response storage memory space includes a preselected area for the storage of ownership information relating to the request/response pair stored in the respective entry so that ownership information can be read and written in the same read/write operations utilized in respect of the corresponding request/response pair.

Abstract: An arbitration scheme for providing deterministic bandwidth and delay guarantees in an input-buffered crossbar switch with speedup S is presented. Within the framework of a crossbar architecture having a plurality of input channels and output channels, the arbitration scheme determines the sequence of fixed-size packet (or cell) transmissions between the inputs channels and outputs channels satisfying the constraint that only one cell can leave an input channel and enter an output channel per phase in such a way that the arbitration delay is bounded for each cell awaiting transmission at the input channel. If the fixed-sized packets result from fragmentation of variable size packets, the scheduling and arbitration scheme determines deterministic delay guarantees to the initial variable size packets (re-assembled at the output channel) as well.

Abstract: An explicit rate congestion control system and method to support available bit rate service in asynchronous transfer mode (ATM) networks is provided. The system and method observe the maximum usage of different connections and incorporates both rate and queue length information to achieve a stable operation of the ATM network. The control of congestion and fairness is separated which permits the system and method to have a common framework to support multiple fairness criteria. The system and method may operate with switches implementing both aggregate and per connection queuing at their ports. In the method, the number of active connections at a bottleneck node is only used to normalize control and to redistribute spare bandwidth during transient conditions and does not affect the steady state fair rate used by each connection.

Abstract: A switch apparatus for optimizing the transfer of data packets between a plurality of local area networks (LANs). Apparatus of the present invention are comprised of multiple independent controllers, e.g., a receive controller and a transmit controller, which share common resources including a first memory (a packet memory) which stores the data packets, a second memory (a descriptor memory) which stores pointers to the stored data packets, and buffered data paths (preferably using FIFO buffers). The independent controllers operate essentially concurrently for most tasks while interleaving their use of the shared resources. Consequently, embodiments of the present invention can simultaneously receive and transmit data across multiple LAN data ports (e.g., 28 Ethernet ports comprised of 10/100 and/or 10 Mbps ports).

Abstract: A mechanism for avoiding an initiation of control read transactions on a system bus coupling a host system having a host memory and an interface connected to a peripheral unit as data is moved between the host system and the peripheral unit is presented. Control information associated with data memory portions in host memory is written to the interface for data memory portions storing outgoing data and data memory portions to receive incoming data. The interface includes a controller to move data between the host memory and the interface by first obtaining the control information for the associated data portions. The interface writes status reports in association with the movement of data between the interface and the host memory via the system bus. The mechanism thus enables data transfers to occur via the system without the initiation of control reads in absence of an exception condition.