Switchcore, A.b.

Peter Tufvesson

Ulf Ahlfors

Anders Fyhn

The invention relates to a method and an apparatus for distribution of bandwidth in a switch or router. More particularly, the invention relates to a scheduler and an associated algorithm for distributing bandwidth over data traffic directed to output ports and received in various traffic classes and flows. The switch has a switching fabric. Preferably, the bandwidth scheduler is located before output queues, and the method includes: receiving a stream of data from the switching fabric; subjecting the stream to a decision making algorithm in the bandwidth scheduler resulting in that the stream is forwarded or interrupted (accepted or rejected). Preferably, the stream of data includes identifiable data packets and the decision making algorithm in the bandwidth scheduler results in the data packet being accepted or rejected. The bandwidth scheduler may be located before the output queues leading to early discarding of packets and efficient use of output buffer memory. The algorithm includes logical rules operating on counters and variables recording the accepted traffic to implement the bandwidth distribution. The algorithm enables weighted distribution and short term as well as long term fairness.

Method and apparatus for distribution of bandwidth in a switch

The invention relates to a method for flow control in a switch and a switch controlled thereby. In order to ensure that no or few packets are dropped in a switch because of a congested internal memory, pause frames or stop command messages are sent to upstream senders. When to send pause frames are determined by monitoring the buffer contents of the switch and estimating the total expected contents of the links between the senders and the switch. The pause frames are sent to the most offending senders, i.e. the senders causing the largest queues in the switch. The switch comprises: a number of input ports, each receiving data cells on a respective link; a number of output ports sharing a buffer space in which each output port can reserve space for an output queue, wherein incoming data cells are switched to an appropriate output queue; a flow control means for pausing and un-pausing senders on selected links; and the method includes the steps of: monitoring the remaining available buffer space AS of the shared buffer; estimating the expected total content LE of the links; calculating a free margin (FM) as the remaining available buffer space minus the expected total content of the links FM=AS&#x2212;LE. If the free margin sinks below a threshold AS&#x2212;LE&#x3c;A, then a selected link is paused; and if the free margin thereafter raises above a threshold AS&#x2212;LE&#x3e;B, then a selected paused link is un-paused.

Method for flow control in a switch and a switch controlled thereby

The invention relates to a method and means for managing packet queues in switches. The switch has a shared memory split in a small internal memory and a large external memory. There is limited bandwidth to the external memory. The method comprises the steps of dividing a data stream incoming on the input ports intended for respective output ports into two parts, of which the first part is to be sent to an internal queue belonging to at least one output port and the second part is to be sent to the external memory. The incoming data stream may be identified as belonging to flow groups and the division of the data stream is then performed e.g. such that flow groups with a higher priority than a division threshold are sent to said internal queues in the first part, while flow groups with priority lower than said threshold are sent to the external memory in the second part.

Method and arrangement for managing packet queues in switches

The invention relates to a scheduler method and device for handling output queues in a switch. The invention incorporates a number of co-operating techniques such as weighted and deficit driven round-robin and interleaving. The invention provides a scheduling method in a switch in which an input data stream is received and stored in a number of output queues, the method comprising the steps of: polling all queues in order; if the polled queue contains data, refilling a deficit value indicating a maximum amount of data that may be sent from this queue; if the deficit value permits, sending data, and decreasing the deficit value a corresponding amount for the polled queue, else disabling the queue; if any queue is permitted to send after all the queues have been polled, going to a local round, else start polling the first queue of the order again. The invention enables e.g. priority treatment of queues, fairness with regard to varying packet lengths and avoids burstiness.

Growing community of inventors

Lund, Sweden

Peter Tufvesson