Abstract: A methods and apparatus for remote management of switching network nodes in a stack via in-band messaging are presented. Switching nodes in the stack default to reserved switching node identifiers and stacking ports default to a blocking state upon startup, restart, and reset. Each command frame received via a blocking state is forwarded to a command engine at each switching node and is acknowledged with the current switching node identifier. Each acknowledgement frame bearing the reserved network node identifier triggers configuration of the acknowledging switching node. Switching nodes and the management processor track interrupt state vectors regarding events. An interrupt acknowledgement process is employed to track raised interrupts. Configuration of switching node is performed via command frames transmitted by the management processor and destined to a command engine associated with the switching node.

Abstract: A high availability backplane architecture. The backplane system includes redundant node boards operatively communicating with redundant switch fabric boards. Uplink ports of the node boards are logically grouped into trunk ports at one end of the communication link with the switch fabric boards. The node boards and the switch fabric boards routinely perform link integrity checks when operating in a normal mode such that each can independently initiate failover to working ports when a link failure is detected. Link failure is detected either by sending a link heartbeat message after the link has had no traffic for a predetermined interval, or after receiving a predetermined consecutive number of invalid packets. Once the link failure is resolved, operation resumes in normal mode.

Abstract: A hardware-based failover scheme enabling rapid end-to-end recovery is provided. Hardware logic periodically generates, transmits, receives, and processes heartbeat packets, sent from one end of the communications network to another, and then returned back. If a communications network node or communications link failure is being experienced along the transport path, then the hardware logic rapidly swaps the affected traffic conveyed to a pre-established backup transport path, typically within microseconds. Advantages are derived from the rapid failover effected end-to-end which enables continued delivery of provisioned communications services improving the resiliency and/or availability of a communications network.

Abstract: A two-chip/single-die switch architecture and a method for accessing a DDR SDRAM memory store in a switching environment are presented. The two-chip/single-die architecture includes an internal memory storage block on the single-die, an external memory storage interface to a Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), an external memory manager, and a packet data transfer engine effecting packet data transfers between an internal memory store and the external DDR SDRAM memory. The packet data transfer engine operates as an adaptation layer addressing issues related to employing appropriate: addressing schemes, granule sizes, memory transfer burst sizes, access timing, etc. The packet data transfer engine includes a minimal number of dual mode operational blocks such as: a queue manager, and adaptation receive and transmit blocks.

Abstract: A packet switching node in a pipelined architecture processing packets received via an input port associated with the packet switching node performs a method, which includes: determining a packet frame type; selectively extracting packet header field values specific to a packet frame type, including packet addressing information; ascribing to the packet a preliminary action to be performed; searching packet switching information tracked by the packet switching node based on extracted packet addressing information; formulating a preliminary switch response for the packet; classifying the packet into a packet flow; modifying the preliminary switch response in accordance with one of the preliminary action, the packet flow into which the packet was classified, and a default port action corresponding to the input port; modifying the packet header in accordance with one of the preliminary action, the packet flow, and the default port action; and processing the packet.

Abstract: A two-chip/single-die switch architecture and a method for accessing a DDR SDRAM memory store in a switching environment are presented. The two-chip/single-die architecture includes an internal memory storage block on the single-die, an external memory storage interface to a Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), an external memory manager, and a packet data transfer engine effecting packet data transfers between an internal memory store and the external DDR SDRAM memory. The packet data transfer engine operates as an adaptation layer addressing issues related to employing appropriate: addressing schemes, granule sizes, memory transfer burst sizes, access timing, etc. The packet data transfer engine includes a minimal number of dual mode operational blocks such as: a queue manager, and adaptation receive and transmit blocks.

Abstract: A two-chip/single-die switch architecture and a method for accessing a DDR SDRAM memory store in a switching environment are presented. The two-chip/single-die architecture includes an internal memory storage block on the single-die, an external memory storage interface to a Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), an external memory manager, and a packet data transfer engine effecting packet data transfers between an internal memory store and the external DDR SDRAM memory. The packet data transfer engine operates as an adaptation layer addressing issues related to employing appropriate: addressing schemes, granule sizes, memory transfer burst sizes, access timing, etc. The packet data transfer engine includes a minimal number of dual mode operational blocks such as: a queue manager, and adaptation receive and transmit blocks.

Abstract: Disclosed is an apparatus and method for storing and searching computer node addresses in a computer network system. In one embodiment, the apparatus comprises a frame forwarding device such as a switch. The switch includes two MAC address tables including a primary MAC address table and secondary MAC address table both for storing and searching MAC addresses. The primary table stores records that contain compressed values of MAC addresses. The records are contained in storage locations that are referenced using the compressed value of the MAC address as a search index. In order to account for searching collisions that may result from different MAC addresses compressing to the same value, each record in the primary address table is linked to a chain of records in the secondary table. The records in the secondary table store the full value of the MAC address. Each chain of records in the secondary address table contains MAC addresses the present invention.

Abstract: Disclosed is an apparatus and method for storing and searching computer node addresses in a computer network system. In one embodiment, the apparatus comprises a frame forwarding device such as a switch. The switch includes two MAC address tables including a primary MAC address table and secondary MAC address table both for storing and searching MAC addresses. The primary table stores records that contain compressed values of MAC addresses. The records are contained in storage locations that are referenced using the compressed value of the MAC address as a search index. In order to account for searching collisions that may result from different MAC addresses compressing to the same value, each record in the primary address table is linked to a chain of records in the secondary table. The records in the secondary table store the full value of the MAC address. Each chain of records in the secondary address table contains MAC addresses the present invention.

Abstract: A method for actively detecting link failures on a high availability backplane architecture. The backplane system includes redundant node boards operatively communicating with redundant switch fabric boards. Uplink ports of the node boards are logically grouped into trunk ports at one end of the communication link with the switch fabric boards. A probe packet is sent, and a probing timer is set whenever either a specified number of bad packets are received, or an idle timer expires. If a response to the probe packet is received before the probe timer expires then the link is deemed valid, otherwise the link is presumed to have failed. Preferably, either the node boards or the switch fabric boards are configured to properly handle a probe pack, which preferably has identical source and destination addresses.

Abstract: A method of scheduling queue servicing in a data packet switching environment is provided. The method includes a sequence of cyclical steps. The output queues are scheduled for servicing on a least credit value basis. An output queue is selected from a group of output queues associated with a communications port. The selected output port has at least one Payload Data Unit (PDU) pending transmission and a lowest credit value associated therewith. At least one PDU having a length is transmitted from the selected output queue and the credit value is incremented taking the length of the transmitted PDU into consideration. The transmission of PDUs is divided into transmission periods. Once per transmission period credit values associated with output queues holding PDUs pending transmission are decremented in accordance with transmission apportionments assigned for each output queue. The method emulates weighted fair queue servicing with minimal computation enabling hardware implementation thereof.

Abstract: A method of utilizing shared memory resources in switching Protocol Data Units (PDUs) at a data switching node is presented. The method includes reserving: a temporary memory storage portion for storing PDUs prior to queuing for processing thereof, a Class-of-Service memory storage portion to provide support Quality-of-Service guarantees, a shared memory-pool portion and an input port memory storage portion enabling non-blocking input port flow control. Provisions are made for PDU discard decisions to be delayed until after PDU headers are inspected subsequent to the receipt of each PDU. Provisions are made for well-behaved data flows conveyed via an input port to be protected against blocking from misbehaving data flows conveyed via other input ports of the data switching node.

Abstract: A methods and apparatus for remote management of switching network nodes in a stack via in-band messaging are presented. Switching nodes in the stack default to reserved switching node identifiers and stacking ports default to a blocking state upon startup, restart, and reset. Each command frame received via a blocking state is forwarded to a command engine at each switching node and is acknowledged with the current switching node identifier. Each acknowledgement frame bearing the reserved network node identifier triggers configuration of the acknowledging switching node. Switching nodes and the management processor track interrupt state vectors regarding events. An interrupt acknowledgement process is employed to track raised interrupts. Configuration of switching node is performed via command frames transmitted by the management processor and destined to a command engine associated with the switching node.

Abstract: A hardware-based failover scheme enabling rapid end-to-end recovery is provided. Hardware logic periodically generates, transmits, receives, and processes heartbeat packets, sent from one end of the communications network to another, and then returned back. If a communications network node or communications link failure is being experienced along the transport path, then the hardware logic rapidly swaps the affected traffic conveyed to a pre-established backup transport path, typically within microseconds. Advantages are derived from the rapid failover effected end-to-end which enables continued delivery of provisioned communications services improving the resiliency and/or availability of a communications network.

Abstract: A packet switching node having a pipelined packet processing architecture processing packets received via an input port associated with the packet switching node is presented.

Abstract: A credit-based pacing scheme for heterogeneous speed frame forwarding. A control logic controls the transmission of data between a source device and a destination device in accordance with a handshaking protocol. Pacing logic paces the transmission of the data from the source device to the destination device to prevent congestion in the switching fabric. A credit scheme is used to arbitrate among multiple pacing modules per device, each forwarding data at a different rate.

Abstract: A two-chip/single-die switch architecture and a method for accessing a DDR SDRAM memory store in a switching environment are presented. The two-chip/single-die architecture includes an internal memory storage block on the single-die, an external memory storage interface to a Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), an external memory manager, and a packet data transfer engine effecting packet data transfers between an internal memory store and the external DDR SDRAM memory. The packet data transfer engine operates as an adaptation layer addressing issues related to employing appropriate: addressing schemes, granule sizes, memory transfer burst sizes, access timing, etc. The packet data transfer engine includes a minimal number of dual mode operational blocks such as: a queue manager, and adaptation receive and transmit blocks.

Abstract: A system and method for implementing a control channel in a packet switched communications network. In a computer network, such as a local area network (LAN) it is known to utilize the Ethernet for distributing communications between stations. The Ethernet employs a standard frame format that includes header frames and, in particular a preamble frame which may be used to provide synchronization information between switching devices or nodes. The preamble frame is not required in a Gigabit Ethernet implementation and the present invention employs a portion of the preamble frame to implement a control channel between switching devices.

Abstract: Disclosed is an apparatus and method for storing and searching computer node addresses in a computer network system. In one embodiment, the apparatus comprises a frame forwarding device such as a switch. The switch includes two MAC address tables including a primary MAC address table and secondary MAC address table both for storing and searching MAC addresses. The primary table stores records that contain compressed values of MAC addresses. The records are contained in storage locations that are referenced using the compressed value of the MAC address as a search index. In order to account for searching collisions that may result from different MAC addresses compressing to the same value, each record in the primary address table is linked to a chain of records in the secondary table. The records in the secondary table store the full value of the MAC address. Each chain of records in the secondary address table contains MAC addresses the present invention.

Abstract: A high availability backplane architecture. The backplane system includes redundant node boards operatively communicating with redundant switch fabric boards. Uplink ports of the node boards are logically grouped into trunk ports at one end of the communication link with the switch fabric boards. The node boards and the switch fabric boards routinely perform link integrity checks when operating in a normal mode such that each can independently initiate failover to working ports when a link failure is detected. Link failure is detected either by sending a link heartbeat message after the link has had no traffic for a predetermined interval, or after receiving a predetermined consecutive number of invalid packets. Once the link failure is resolved, operation resumes in normal mode.