Abstract: A technique for improving utilization of a data link coupled to a network. Scores are generated for one or more data flows that transfer onto the network via the data link. The scores are kept in a “scorecard” that represents a pool of data flows that are eligible to transfer data onto the data link when the data link becomes idle. Each score represents a rating of a particular data flow's eligibility to transfer data onto the data link when it becomes idle. A check is performed to determine if the data link is idle, and, if so, data associated with the highest scoring data flow are transferred onto the data link.

Abstract: Presently disclosed is an apparatus and method for returning control of bandwidth allocation and packet scheduling to the routing engine in a network communications device containing an ATM interface. Virtual circuit (VC) flow control is augmented by the addition of a second flow control feedback signal from each virtual path (VP). VP flow control is used to suspend scheduling of all VCs on a given VP when traffic has accumulated on enough VCs to keep the VP busy. A new packet segmenter is employed to segment traffic while preserving the first in, first out (FIFO) order in which packet traffic was received. Embodiments of the invention may be implemented using a two-level (per-VC and per-VP) scheduling hierarchy or may use as many levels of flow control feedback-derived scheduling as may be necessitated by multilevel scheduling hierarchies.

Abstract: A data communications device interconnected for channelized communication overcomes the problems associated with message traffic starvation on outgoing traffic channels by forming arbitration, or speed groups of logical interfaces and allocating scheduling resources in proportion to the bandwidth attributed to each group relative to the total bandwidth of the device. Incoming messages have a transmission rate based on QOS, content type, or other constraints. A categorizer determines arbitration groups of the outgoing messages based on the transmission rate of the message. The scheduler allocates dequeue requests among the groups according to the proportion allocated to the arbitration group. A dequeue manager drains the outgoing messages from the arbitration groups at a rate in proportion to the total percentage of outgoing transmission bandwidth represented by the group by selecting a message from among the arbitration groups according to the computed proportion.

Abstract: Conventional schedulers employ designs allocating specific processor and memory resources, such as memory for configuration data, state data, and scheduling engine processor resources for specific aspects of the scheduler, such as layers of the scheduling hierarchy, each of which consumes dedicated processor and memory resources. A generic, iterative scheduling engine, applicable to an arbitrary scheduling hierarchy structure having a variable number of hierarchy layers, receives a scheduling hierarchy structure having a predetermined number of layers, and allocates scheduling resources such as instructions and memory, according to scheduling logic, in response to design constraints and processing considerations.

Abstract: Conventional schedulers propagate entries by either polling until an entry is ready, or alternatively, by attaching a so-called “readiness time” to entries. A scheduler which recognizes the readiness time avoids consuming a parent schedule with polling, or with burdening entries with a future readiness time. The system of the present invention employs a deferral queue for deferring entries in response to pop requests from a parent schedule. The child schedule defers entries via the deferral queue when it is not ready to push an entry to the parent schedule, and sets the readiness time corresponding to the entry. Upon the expiration of the readiness time, the child schedule redetermines whether to push the deferred entry corresponding to the deferral queue or optionally to push an interim entry having since arrived. Accordingly, a child schedule receiving a pop requests retains the ability to push an entry at an earlier or later readiness time, and further retains the ability to reconsider which entry to push.