54 results about "Fair queuing" patented technology

A system and method of moving information units from an output flow control toward a data transmission network in a prioritized sequence which accommodates several different levels of service. The present invention includes a method and system for scheduling the egress of processed information units (or frames) from a network processing unit according to service based on a weighted fair queue where position in the queue is adjusted after each service based on a weight factor and the length of frame, a process which provides a method for and system of interaction between different calendar types is used to provide minimum bandwidth, best effort bandwidth, weighted fair queuing service, best effort peak bandwidth, and maximum burst size specifications. The present invention permits different combinations of service that can be used to create different QoS specifications. The "base" services which are offered to a customer in the example described in this patent application are minimum bandwidth, best effort, peak and maximum burst size (or MBS), which may be combined as desired. For example, a user could specify minimum bandwidth plus best effort additional bandwidth and the system would provide this capability by putting the flow queue in both the NLS and WFQ calendar. The system includes tests when a flow queue is in multiple calendars to determine when it must come out.

A processor includes a scheduler operative to schedule data blocks for transmission from a plurality of queues or other transmission elements, utilizing at least a first table and a second table. The first table may comprise at least first and second first-in first-out (FIFO) lists of entries corresponding to transmission elements for which data blocks are to be scheduled in accordance with a first scheduling algorithm, such as a weighted fair queuing scheduling algorithm. The scheduler maintains a first table pointer identifying at least one of the first and second lists of the first table as having priority over the other of the first and second lists of the first table. The second table includes a plurality of entries corresponding to transmission elements for which data blocks are to be scheduled in accordance with a second scheduling algorithm, such as a constant bit rate or variable bit rate scheduling algorithm. Association of a given one of the transmission elements with a particular one of the second table entries establishes a scheduling rate for that transmission element. The scheduler maintains a second table pointer identifying a current one of the second table entries that is eligible for transmission.

In a packet-queue management system, a bandwidth allocation approach fairly addresses each of n flows that share the outgoing link of an otherwise congested router. According to an example embodiment of the invention, a buffer at the outgoing link is a simple FIFO, shared by packets belonging to the n flows. A packet priority-reduction (e.g., packet dropping) process is used to discriminate against the flows that submit more packets/sec than is allowed by their fair share. This packet management process therefore attempts to approximate a fair queuing policy. The embodiment is advantageously easy to implement and can control unresponsive or misbehaving flows with a minimum overhead.

A packet switch for switching cells comprising fixed-size data packets. The packet switch comprises: 1) N input ports for receiving and storing cells in input queues; 2) N output ports for receiving and storing cells from the N input ports in output queues; 3) a switch fabric for transferring the cells from the N input ports to the N output ports, the switch fabric comprising an internally buffered crossbar having N×N internal buffers, wherein each internal buffer is associated with a crosspoint of one of the N input ports and one of the N output ports; and 4) a scheduling controller for selecting a first one of a plurality of queued head-of-line (HOL) cells from the input queues to be transmitted to a first one of the N×N internal buffers according to a fair queuing algorithm in which each of the queued HOL cells is allocated a weight of R_ij and wherein the scheduling controller selects a first one of a plurality of HOL cells buffered in a second one of the N×N internal buffers to be transmitted to a first one of the output queues according to a fair queuing algorithm in which each of the internally buffered HOL cells is allocated a weight of R_ij.

The present invention is directed toward methods and apparatus for packet transmission scheduling in a data communication network. In one aspect, received data packets are assigned to an appropriate one of a plurality of scheduling heap data structures. Each scheduling heap data structure is percolated to identify a most eligible data packet in each heap data structure. A highest-priority one of the most-eligible data packets is identifying by prioritizing among the most-eligible data packets. This is useful because the scheduling tasks may be distributed among the hierarchy of schedulers to efficiently handle data packet scheduling. Another aspect provides a technique for combining priority schemes, such as strict priority and weighted fair queuing. This is useful because packets may have equal priorities or no priorities, such as in the case of certain legacy equipment.

Various communication systems may benefit from buffer management. For example, systems employing a packet data convergence protocol may be enhanced with network-side buffer management that is configured to manipulate transmission control protocol packet senders. A method can include receiving a plurality of packets at a buffer of a buffer manager. The method can also include manipulating, by the buffer manager, pacing of transmission control protocol senders of the packets. The method can further optionally include fair queuing the packets and/or performing flow incubation on the packets.

The invention discloses a method for realizing addition of a traffic shaping token, which comprises the following steps: A. allocating a shaping rate to each data stream, converting the shaping rate to a shaping weight, and adding each data stream to a weighted fair queuing (WFQ) token distribution module according to the shaping weight of each data stream; and at the same time of performing step A, calculating the latest idle stream weight; B, according to the idle stream weight, adding the idle stream to the WFQ token distribution module; and C, adding a token to each data stream or idle stream by the WFQ token distribution module according to set intervals. The invention also discloses a corresponding device and a corresponding system. The method, the device and the system add tokens to each data stream and idle stream in a mode of allocating corresponding shaping rates and shaping weights to different data streams so as to realize the shaping of various data streams and achieve good effect.

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.

A scheduler for a network processor includes a scheduling queue in which weighted fair queuing is applied to define a sequence in which flows are to be serviced. The scheduling queue includes at least a first subqueue and a second subqueue. The first subqueue has a first range and a first resolution, and the second subqueue has an extended range that is greater than the first range and a lower resolution that is less than the first resolution. Flows that are to be enqueued within the range of highest precision to the current pointer of the scheduling queue are attached to the first subqueue. Flows that are to be enqueued outside the range of highest precision from the current pointer of the scheduling queue are attached to the second subqueue. Numerous other aspects are provided.

In one embodiment, a method comprises recursively selecting a child node of a previously selected node of a port tree and having a highest priority among nodes of a same level within the port tree, until the selected node has associated egress queues of an egress port. The method also includes outputting a number of packets from the associated egress queues of the selected node in a current processing cycle. The number of packets outputted is based on an allocated bandwidth for the associated egress queues, in which the allocated bandwidth accounts for a deficit from a previous processing cycle.

A system for scheduling data for transmission in a communication network includes a credit distributor and a transmit selector. The communication network includes a plurality of children. The transmit selector is communicatively coupled to the credit distributor. The credit distributor operates to grant credits to at least one of eligible children and children having a negative credit count. Each credit is redeemable for data transmission. The credit distributor further operates to affect fairness between children with ratios of granted credits, maintain a credit balance representing a total amount of undistributed credits available, and deduct the granted credits from the credit balance. The transmit selector operates to select at least one eligible and enabled child for dequeuing, bias selection of the eligible and enabled child to an eligible and enabled child with positive credits, and add credits to the credit balance corresponding to an amount of data selected for dequeuing.

The invention discloses a method and a system for bandwidth distribution. According to the method, child nodes accept first bandwidths which are distributed for the child nodes by a father child, wherein the first bandwidths are distributed by the father node according to the weighted values of the child nodes, and the child nodes distribute the first bandwidths according to the weighted value of each node of one or a plurality of nodes of the child nodes. The technical scheme is applicable to weighted fair queuing (WFQ) scheduling on multilevel and multi-service scenes and provides the flexible method for the bandwidth distribution for the multilevel and multi-service scenes.

There is disclosed a packet data switch which allows fair queuing, by assigning a priority value to received data, without requiring time-consuming searches, by storing pointers to the buffer memory in a first memory, and accessing the pointers through a second memory which is in the form of an array, addressable by the priority value. There is further disclosed a system which combines fair queuing and FIFO queuing, to avoid the need for excessive array size.

The device has a scheduling module for scheduling packets in a queue as a function of a priority. The scheduling is performed based on analyzing an incoming bit rate of flows relative to a fair bit rate and a fair queuing with priority algorithm. A fair bit rate value represents the bit rate achieved by a data flow. A priority load value is transmitted in a certain time period divided by duration of that time period. An Independent claim is also included for a method of treating packets of flows on a network link.

A system and method for adaptively assigning queue service weights to an ATM traffic management controller in order to reduce service weight update calculations. The implementation of a fair weighted queuing scheme on a network is divided into two functions: queue arbitration; and queue weight configuration. Queue arbitration is performed via a virtual time-stamped fair queuing algorithm. The queue weight configuration is performed via a reconfigurable weighted fair queuing controller wherein bandwidth requirements are calculated in response to connection setup and release values.