87 results about "Weighted round robin" patented technology

An adaptive load balancer intelligently steers data traffic through a software defined network (SDN) to which the load balancer is operatively coupled. The network has egress ports to which a plurality of servers is connected. The network has an SDN controller which generates statistical information concerning the network. The adaptive load balancer includes a weighted round robin scheduler module which receives client requests and, based on the statistical information generated by the SDN controller, determines a weight to be attributed to each server of the plurality of servers connected to the network. The adaptive load balancer operates in a passive port mode, a passive path mode, an active path mode and an active path with quality of service (QoS) overlay mode.

A network switch configured for switching data frames across multiple ports utilizes an efficient arbiter to store the data frames. Each port possesses queuing logic for requesting a free pointer from a free buffer queue. A multi-level arbitration logic arbitrates all the requests of equal priority from the network switch ports in a round robin scheme. The arbitration logic comprises a plurality of cells that cascaded to output an acknowledgement signal in response to an inhibit signal and a request signal as well as a counter that is incremented upon an asserted acknowledgement signal.

A method and system for servicing data traffic in wireless local area networks (such as IEEE 802.11 networks) in multiple queues having different levels of priority. These queues include at least a low priority queue for 'best effort' traffic, a medium priority queue for streaming data such as video pictures, and a high priority queue for voice traffic, and are serviced in order of decreasing priority. To prevent the 'best effort' traffic in the low priority queue from being 'starved', a bit is set to indicate when such a condition is likely to occur, and the low priority queue is served first when that bit has been set. Alternatively, low and medium priority traffic is handled on a weighted round-robin basis, and high priority traffic is given strict priority over both. Transmit and receive queues are handled on a rotating priority basis.

A network device includes a group of queues, each having a weighted round robin mechanism. The priority queues on a port detect an overflow condition and transfer a flag to the weighted round robin device in response to detecting the overflow condition. The weighted round robin mechanism adjusts the weight associated with one or more of the priority queues in response to receiving the flag and transfers data from the queues based on the adjusted weights.

An adaptive weighted round robin scheduling apparatus and method schedules variable-length frame transmissions from a plurality of output queues having different transmission priorities by first allocating, for each queue, a number of bandwidth segments for a bandwidth cycle and a number of transmission opportunities for a round robin cycle, and then processing the queues consecutively in a round-robin fashion, beginning with a highest priority queue, until none of the queues has any bandwidth remaining. More specifically, during each iteration of a round robin cycle, a queue is permitted to transmit a frame if the queue has at least one remaining transmission opportunity, the queue has a frame ready for transmission, and the queue has at least one remaining bandwidth segment, and furthermore the number of transmission opportunities for the queue is decremented by at least one. Upon transmitting a frame, the number of bandwidth segments for the queue is decreased by the number of bandwidth segments in the frame. If a queue has no frame ready for transmission, then the queue may be either penalized, in which case the number of bandwidth segments for the queue is reduced, or forced to forfeit its bandwidth segments, in which case any remaining bandwidth segments are reallocated to other queues and the number of bandwidth segments and the number of transmission opportunities for the queue are set to zero.

The invention provides a dynamic weighted round robin scheduling policy method based on priorities. Through utilization of the method, a network resource utilization rate is high, bandwidth resource allocation is fair and network resource scheduling is reasonable and efficient. The method is realized through adoption of the following technical scheme that for data streams of different priorities,the dynamic weighted round robin scheduling policy method based on the priorities comprises a queue management module and a round robin scheduling module; the queue management module divides all business in a network into sub-queues of n priorities; after backbone network nodes receive business data packets, the priorities of the data packets arriving at the backbone network nodes are judged according to QoS demands of the business, and the business data packets are inserted into the corresponding cache sub-queues according to the priorities; the round robin scheduling module carries out periodic round robin; and the busy degree of each sub-queue is calculated according to the current queue lengths Q of the sub-queues, the busy degree is arranged, round robin weight values of the sub-queues are dynamically adjusted according to a busy degree arrangement result, the round robin is carried out on each sub-queue in sequence, and the data packets are sent.

A weighted round-robin scheduler includes a round-robin table that stores a plurality of cycle link lists. Each cycle link list includes a head flow identification (FLID) value identifying a first flow of the cycle link list, and a tail FLID value identifying a last flow of the cycle link list. A flow table is provided having a plurality of flow table entries. Each flow table entry is associated with a corresponding flow. Each flow table entry stores a parameter that identifies the weight assigned to the associated flow. A packet queue is associated with each flow table entry, wherein each packet queue is capable of storing a plurality of packets. The weighted round-robin scheduler also includes an idle cycle register having an idle cycle entry corresponding with each of the cycle link lists, wherein each idle cycle entry identifies the corresponding cycle link list as active or idle.

A method and system for prioritizing connection data that is associated with different classes of service for transmission in a frame based communication system. These classes of service can include CBR, nrt-VBR, MGR, and UPR traffic. One embodiment of the scheduling method and system uses hierarchical round-robin (HRR) with deficit round-robin (DRR). In this embodiment, the scheduling method and system guarantees minimum rates of nrt-VBR and MGR traffic to the connections. The excess bandwidth is then fairly allocated between the existing connections and their classes of service. For example, the excess is allocated for UBR traffic and for the excess demands of the nrt-VBR and MGR connections. In one embodiment, the scheduling method and system allocates the excess bandwidth in a frame to the existing connections using weighted round robin to differentiate between different classes of service. In one embodiment, excess allocation to nrt-VBR and MGR connections is rolled back into the deficit counters for the minimum guaranteed rates of nrt-VBR and MGR connections.

Device-wide performance guarantees may be implemented in a network element using a pull forwarding scheme by using separate proceses on the network element communicating via handshake signals to enable coordination between the aspects of the network element. One class of processes execute at the ingress queues, a second class of process execut at junction points, and a final class of processes execute at the egress ports. The combination of these separate processes leads to the correct scheduling of frames in a device-wide manner as if there were a centralized scheduler with complete information about all queued frames. As a result, the performance guarantees of the intended scheduling algorithm are preserved and are provided in a device-wide manner. The scheduling algorithms that are supported include round-robin, deficit round robin, negative deficit round robin, weighted round robin, and strict priority.

This invention provides one Ethernet exchange buffer and transfer method, which comprises the following steps: receiving data pack from input end; cutting data pack into certain length signal element by cut unit; storing signal element into central memory unit; adopting equal time lag transfer through end and line transfer unit and turning output end by each time lag; adopting run require or transfer of different lines at one output end; after getting transfer, reading signal element from common central buffer unit and the data pack resets the signal element sent to the linkage. This invention also provides one Ethernet exchange buffer and transfer device.

A scheduler for shared network resources implementing a plurality of user selectable data scheduling schemes within a single hardware device. The schemes include strict priority, priority for one class plus smooth deficit weighted round robin for the other classes, bandwidth limited strict priority and smooth deficit weighted round robin for all user classes. The network operator selects one of the four schemes by enabling or disabling certain bits in the hardware device.

A distributed crawler task scheduling method based on a weighted round-robin algorithm at least includes the following steps: (1) according to different scales, network crawlers are divided into five types of crawlers, i.e. a stand-alone multi-thread crawler, a homogeneous centralized crawler, a heterogeneous centralized crawler, a small-scale distributed crawler and a large-scale distributed crawler; (2) a master-slave architecture is deployed; (3) when a crawler node is connected to a master node for the first time, the master node gives an initial weight to the crawler node; (4) according to the scheduling algorithm based on weighted round-robin, the master node continuously chooses a crawler node and assigns a URL (Uniform Resource Locator) task to be crawled to the crawler node; (5) each time when a URL task is crawled by a crawler node, a result is returned to the master node, and the weight of the crawler node is updated by the master node, and the like. The distributed crawler scheduling policy based on the weighted round-robin algorithm, which is put forward by the invention, is designed for small-scale distributed crawlers and can ensure the load balance of each crawler node and ensure that crawler nodes have flexible scalability and fault tolerance.

The embodiment of the invention discloses a hardware accelerator and a chip. The hardware accelerator comprises an interface circuit, and an accelerator core which is coupled to the interface circuit; the interface circuit is used for receiving a first task request and decoding the first task request so as to obtain marking information, as well as configuring the first task request into an FIFO array in match with the marking information according to the marking information; a scheduling controller is used for determining a target channel set with at least one second task request to be treated in the n cycle from at least two channel sets, receiving the time parameters fed back by the accelerator core and respectively corresponding to the targeted channel sets, and scheduling the at least one second task request of the targeted channel sets according to the time parameters and the weighted round robin algorithm; the accelerator core is used for responding to the at least one second task request after scheduling. With the adoption of the hardware accelerator, the isolation in the configuration process can be effectively achieved, so that the mutual influence can be avoided.

The invention discloses a self-adaptive task scheduler and method, and belongs to the technical field of load balancing scheduling of distributed stream processing systems. The scheduler mainly comprises a performance monitoring data acquisition module, a smooth weighted polling task scheduling module and a task scheduling module based on an ant colony algorithm. According to a method for carryingout task scheduling by adopting the self-adaptive task scheduler, in the task running initial stage, a smooth weighted polling task scheduling algorithm is adopted, tasks are allocated according to the weights of nodes, and the nodes are not continuously selected under the condition that the number of times of selection is not changed. When the load of the cluster exceeds a set threshold value, in order to avoid delaying the overall completion time of the task set, an optimal task allocation scheme is calculated within a certain number of iterations by using a load balancing algorithm based on an ant colony algorithm, and when cluster resources are reduced to below the set threshold value, a smooth weighted polling algorithm is continued to be adopted.

A weighted round-robin arbitrator for a plurality of data queue includes an arbitration table comprising a plurality of entries. Each entry represents a time slot for the transmission of one data packet from a selected one of the plurality of data queues. There is one arbitration logic circuit for each of the plurality of entries in the arbitration table. Each arbitration logic circuit includes a first multiplexer receiving an output from a first table entry and an output from a second table entry in the arbitration table. A second multiplexer receives empty flags from each of the data queues, the flags indicating that there is no data to the sent from that queue. An output of the second multiplexer is coupled to a control input of the first multiplexer so that the first table entry value is output from the first multiplexer if the corresponding queue has data to be sent out and the second table entry value is sent out from the first multiplexer if the queue corresponding to that table entry has data to be sent out and the queue corresponding to the first entry has no data to be sent out.

The invention discloses a queue scheduling method based on a timer and MDRR, which is based on a differentiated service model and is mainly composed of three parts of a Time timer, a real-time weight updating algorithm a modified weighted round robin (MDRR) scheduling algorithm, wherein the Time timer is mainly used for controlling the scheduling of a high priority queue, ensures that the queue can obtain higher service quality and ensures fairness in the network; according to the real time situation of the data flow in the queue, the weight parameter in the MDRR scheduling algorithm can be dynamically changed; and when service amount is overlarge, the weight is properly enlarged to ensure effect on other queues is lowered to the minimum. The method realizes the scheduling with configurable support queue number and adjustable rate, and has good expandability and simple operation.

A scheduling apparatus flexibly integrates guaranteed-bandwidth (GB) and best-effort (BE) flows and comprises a combination of a primary weighted-round-robin (WRR) scheduler (PWS) and a secondary WRR scheduler (SWS). The PWS distributes service to the individual GB flows and determines the amount of service that the BE flow aggregate should receive during each frame. The SWS takes care of fairly distributing the service share of the BE aggregate over the individual BE flows. The scheduling apparatus divides the service frame in two subframes. In the first subframe, the PWS fulfills the bandwidth requirements of the GB flows. In the second subframe, the SWS distributes fair service to the BE flows. For each frame, the duration depends on the amount of bandwidth allocated to the GB flows and on the number of GB flows that are backlogged at the beginning of the frame. The amount of bandwidth globally available to BE flows (i.e., the duration of the second subframe) is dynamically adapted to the backlog state of the GB flows, increasing when the GB-flow activity is low, and decreasing when the GB-flow activity intensifies.

The invention discloses a dynamic queue scheduling device and method based on bandwidth borrowing and mainly solves a problem of low bandwidth utilization rate of an output port in the prior art. An implementation scheme of the invention comprises the following steps of reading a register with a configurable CPU through a CPU interface module (1) to obtain a bandwidth quota which is distributed to each queue; storing a bandwidth quota which is distributed to each first input first output queue through a bandwidth quota storage module (2); buffering a data packet at which each business flow arrives through a first input first output buffer queue module (3); scheduling the queue in a weighted round-robin manner through a scheduler module (4) according to the bandwidth quota which is distributed to each queue; and distributing the unused idle bandwidth quota in one scheduling period to a non-empty queue whose data packet is still not output in the scheduling period by a bandwidth borrowing module (5). According to the device and the method, the packet loss probability of a system is reduced, the utilization rate of the bandwidth resources is improved, and the device and the method can be used for routers and switches in a communication network.

A node in a network running a link-state routing protocol identifies certain routing control messages and stores the identified messages in separate queues. The queues are weighted such that each message type is allotted a predetermined amount of processing overhead to optimize the message processing by a node. In one embodiment, the node processor processes the queued messages in accordance with the entries in a weighted round robin polling table. An upper limit of processing time can be specified for each visit to a particular message queue.