Abstract: Various exemplary embodiments relate to a method and related network node including one or more of the following: receiving, by a load balancer, a plurality of metric values from a plurality of servers; calculating an average metric value based on the plurality of metric values; calculating a first error value based on the average metric value and a first metric value of the plurality of metric values; generating a first integral value by incorporating the first error value into a first previous integral value; and generating a first preference value for a first server of the plurality of servers based on the first integral value.

Abstract: Various exemplary embodiments relate to a method and related network node including one or more of the following: receiving, by a load balancer, a plurality of metric values from a plurality of servers; calculating an average metric value based on the plurality of metric values; calculating a first error value based on the average metric value and a first metric value of the plurality of metric values; generating a first integral value by incorporating the first error value into a first previous integral value; and generating a first preference value for a first server of the plurality of servers based on the first integral value.

Abstract: Management of a plurality of queues is made weighted and fair through the introduction of a system of credits. A credit is spent when a fixed-size unit of storage is served from a selected one of the queues. A scheduler selects a queue when an identifier of the queue reaches the head of a service queue. Credits are regained through a distinct credit management method that takes into account a weight associated with each queue. The arrival of new data in a previously empty queue can trigger the inclusion of the previously empty queue in data structures associated with the credit management method.

Abstract: A pressure-powered liquid pump is provided which includes a housing having opposite ends and configured to allow an actuator to move along a center axis. The pump also includes a first and second intake assembly, as well as a first and second discharge assembly, coupled to the actuator and respectively proximate to the opposite ends of the housing. At least one discharge conduit is coupled to the housing and extends to an atmosphere external to the liquid. The pump also has a piston configured to slide along the actuator so as to create a first chamber having a first variable pressure, and a second chamber having a second variable pressure. A method is also provided and includes the steps of submerging and maintaining the pump at an optimal depth, so as to create an inversely proportional oscillation between the first variable pressure and the second variable pressure.

Abstract: In a packet-based network node, traffic management functions are apportioned between an upstream device and a connected queuing device. The upstream device is responsible for receiving packets and optionally discarding them. The queuing device is responsible for enqueuing undiscarded packets into queues pending transmission, computing the congestion states of the queues, and communicating the congestion states to the upstream device. The upstream device bases its optional discarding on these computed congestion states and, optionally, on discard probabilities and an aggregate congestion level, which may also be computed by the queuing device. The upstream device may additionally mark packets as having experienced congestion based on congestion indication states, which may further be computed by the queuing device. Any statistics maintained by the upstream device may reflect packets discarded for any reason (e.g. at both OSI layers 2 and 3).

Abstract: Method and apparatus for traffic flow control in data switches are disclosed. Emission and loss priorities of cells to be switched are translated into a single discard priority, referred to as a bandwidth priority, which has consistent meaning across different emission priorities. This translation allows simultaneous consideration of loss and emission priority in determining which cells to discard when a switch becomes congested with cell traffic. Such consideration alleviates problems that can arise if cell discard decisions are based solely on either loss priority or emission priority. The invention is particularly useful for Asynchronous Transfer Mode (ATM) switches.

Abstract: A telecommunications switch for switching protocol data units across communications links connecting the switch into a communications network and supporting multiple service types concurrently is disclosed. The switch includes an ingress processor for receiving protocol data units from a communications link, an egress processor for transmitting protocol data units onto another communications link, and a switching fabric for routing protocol data units from the ingress processor to the egress processor. The switch includes a structure of queues and schedulers that is arranged to provide concurrent class-based and flow-based queuing and scheduling of the protocol data units. This arrangement allows an amount of switching bandwidth to be guaranteed to protocol data units belonging to a given flow and allows classes of service within the flow to be allocated a relative proportion of that bandwidth.

Abstract: A node in a packet network such as an ATM network receives a plurality of traffic classes and outputs them to an output link. The invention relates to a technique of scheduling the traffic classes in a time linked fashion at the node based on the bandwidth allocated to each traffic class. Traffic scheduling based strictly on priority may not satisfy delay and loss guarantees of traffic classes when there are many classes with many different priority levels. The rate based scheduling in a time-linked fashion solves these problems by limiting the bandwidth to which each class is accessible. According to one embodiment, the invention uses timeslot values and a linked list of the traffic classes.

Abstract: A random early detection (RED) methodology controls and avoids congestion in a packet network by anticipating congestion and periodically signaling congestion by marking or discarding packets. Sources respond to marked packets by slowing their transmission rates. Enhancements to the basic RED methodology improve performance and reduce buffer requirements in network switches. RED decisions are made as packets leave queues in switches, and RED marks can be accelerated from one packet to another. System response is linearized, and the RED process specifies a marking rate or period rather than a marking probability. A control algorithm permits a single queue operating point. Specific measures are provided for selecting which connection should be marked, and per-connection weight parameters allows customized treatment of connections.

Abstract: A distributed throttle for controlling the allocation of shared bus bandwidth to a number of data transmitting sources. Each source has a local throttle which monitors the amount of traffic on the bus, and generates a local maximum bandwidth allocation which is then self-imposed on the data transmitted by the source.