3com Corporation

RamKrishna Vepa

Roman Baker

Sameer Nanda

Thomas Albert Maufer

James S Binder

Glenn William Connery

A method for detecting reachability of client computers communicatively coupled in a computer network to a server computer. A plurality of identifier tags are resident in the memory of the server. The server generates a data packet comprising an I.C.M.P. echo packet and selects a first identifier tag from among the plurality of identifier tags resident in memory, the first identifier tag being chosen to correspond to a first client computer. The server inserts the first identifier tag into the proper data segment of the echo packet and forwards the packet to the first client. After a predetermined time awaiting a responsive ping from the client, the server determines if the client is tag-compliant or non tag-compliant.

Tag echo discovery protocol to detect reachability of clients

A method to send and receive data packets over a network of computer systems (e.g., a plurality of virtual local area networks &lsqb;VLANs&rsqb; compliant with the IEEE 802.1Q standard) using a server computer system adapted to have a plurality of network interface cards (NICs) coupled thereto. An outgoing data packet is addressed using a first media access control (MAC) address, wherein the first MAC address is a virtual MAC address representing the plurality of NICs. A NIC is selected from the plurality of NICs using a load balancing scheme. The functionality of the selected NIC is verified using a fault tolerance scheme. The first MAC address in the outgoing data packet is replaced with a second MAC address, wherein the second MAC address represents the selected NIC. The outgoing data packet is then transmitted using the selected NIC. For an incoming data packet received at one of the plurality of NICs, the existing MAC address in the incoming data packet is replaced with the first MAC address. Thus, the present embodiment of the present invention provides a high performance method that supports multiple VLANs and elegantly combines a load balance scheme and a fault tolerance scheme into a software element implemented on a server computer system.

Combining virtual local area networks and load balancing with fault tolerance in a high performance protocol

A method for selecting a network interface card (NIC) to be used to send an outgoing data packet from a server computer system having a plurality of NICs coupled thereto. The outgoing data packet is addressed using an Internet Protocol (IP) address and a Transmission Control Protocol (TCP) port number. A load balancing scheme is executed in order to select a NIC from the plurality of NICs. In one embodiment, the load balancing scheme is a function of the IP address; in alternate embodiments, the load balancing scheme is a function of the IP address and either the destination or source TCP port number. The media access control (MAC) address that represents the selected NIC is inserted in the outgoing data packet. The data packet is then sent using the selected NIC.

High performance load balancing of outbound internet protocol traffic over multiple network interface cards

A method for load balancing incoming data packets in a server computer system adapted to have a plurality of network interface cards coupled thereto and communicatively coupled to client computer systems in a network. A first media access control (MAC) address for a first NIC is selected using a load balancing scheme. A first directed data packet containing the first MAC address and a network address for the server computer system is sent to a first client computer system. The first MAC address and the network address are stored in a protocol cache of the first client computer system. A second MAC address for a second NIC is also selected using the load balancing scheme. A second directed packet containing the second MAC address and the network address is sent to a second client computer system. The second MAC address and the network address are stored in a protocol cache of the second client computer system. Thus, the server computer system will receive an incoming data packet from the first client computer system over the first NIC and from the second computer system over the second NIC.

Receive load balancing and fail over with multiple network interface cards

A method and system for detecting a non-functioning network interface card (NIC) in a server computer system adapted to have a plurality of network interface cards coupled thereto and communicatively coupled to client computer systems in a network. A directed packet is sent from a first NIC to a second NIC, and a direct packet is also sent from the second NIC to the first NIC. The server computer system monitors the NICs to determine whether the directed packet from the first NIC is received by the second NIC. The server computer system also monitors the first NIC to determine whether the directed packet from the second NIC is received by the first NIC. The server computer system determines whether the first NIC is functioning using the results from the monitoring. When the first NIC is determined to be non-functioning, the functions of the first NIC are automatically switched from the first NIC to one of the plurality of NICs. A broadcast packet is sent from the server computer system to the client computer systems. The broadcast packet contains a media access control (MAC) address for the NIC that replaces the first NIC, and each client computer system replaces the MAC address for the first NIC with the MAC address for the second NIC in its memory cache.

Fail over with multiple network interface cards

A method for selecting a network interface card (NIC) to be used to send and receive data packets in an Internetwork Protocol Exchange (IPX) environment using a server computer system having a plurality of NICs coupled thereto. An outgoing data packet is addressed using an IPX address and a socket number. A load balancing scheme is executed in order to select a NIC from the plurality of NICs. In one embodiment, the load balancing scheme is a function of the IPX address; in alternate embodiments, the load balancing scheme is a function of the IPX address and either the destination or source socket number. The media access control (MAC) address that represents the selected NIC is inserted in the outgoing data packet. The data packet is then sent using the selected NIC. In one embodiment, the present invention also provides a system and method for fault tolerance and fail over support. The plurality of NICs each include a filter that is adapted to mask a portion of a MAC address in an incoming data packet received at a NIC such that the MAC address in the incoming data packet is equivalent to the MAC address representing the NIC.

Growing community of inventors

Danville, CA, United States of America

RamKrishna Vepa