Congestion mitigation in networks

A system enabled for congestion reduction in a network, the system comprising:

• a plurality of interconnected network nodes;
• a plurality of network switches, distributed within the network;
• the network switches configured for interconnecting network nodes in the network and for forwarding network data packets as datalink frames;
• the plurality of network switches comprising at least a first network switch at a first node interconnected to a second network switch at a second node in the network;
• the first network switch and the second network switch interconnected directly via a first port on the first switch connecting to a second port on the second switch;
• each of the plurality of network switches having a plurality of queues at its ports for storing and forwarding datalink frames based on, at least a priority or a quality of service (QOS) field within the datalink frames;
• the plurality of queues comprising at least a first queue for storing and forwarding a first datalink frames and a second queue for storing and forwarding a second datalink frames;
• and
• the network system is configured to implement a method for per queue congestion reduction over the directly interconnected network nodes:
• the method comprising:
• the first switch receiving a plurality of first datalink frames and a plurality of second datalink frames, in a first order, designated to be forwarded to the second switch from the first port of the first switch interconnecting to the second port of the second switch;
• the first datalink frames forwarded to the second switch are to be stored and forwarded from the at least the first queue of second switch;
• the second datalink frames are to be stored and forwarded from the at least the second queue of the second switch;
• the first switch receiving a third datalink frame as a delay request, from the second switch;
• the third datalink frame received indicative of congestion at the at least the first queue of the second switch wherein the at least the first queue is more loaded than the at least the second queue of the second switch;
• the first switch responding to the delay request received as the third datalink frame by delaying by pausing or stopping for a period, the sending of first datalink frames to the at least the first queue of the second switch while continuing to send the second datalink frames to the at least the second queue of the second switch;
• the first switch thereby sending the received plurality of first datalink frames and the plurality of second datalink frames to the second switch in a second order different from the first order.

A system for queue based congestion avoidance at a congestion point (CP) in a network implemented in a data center (DC), the system comprising

• the network, comprising a plurality of interconnected nodes;
• the plurality of interconnected nodes comprising at least a first node comprising a first network switch connecting via a first port to a second port of a second network switch at a second node in the network;
• the first network switch comprising a plurality of queues for storing and forwarding data link frames of flows of differing quality of service;
• the plurality of queues at the first network switch comprising a first queue configured to receive, store and forward a flow of a first datalink frames from the second network switch;
• the first network switch configured to generate a first request as a datalink frame comprising the identification of the first datalink flow to be sent to the second network switch when there is high network load indicative of congestion on the first queue of the first network switch;
• responsive to the first request the second switch is configured to delay, by stopping or pausing for a period the transmission of the identified first datalink frames of the flow to the first queue of the first switch, while continuing to enable the datalink frames of flows to other queues, that do not have high network load indicative of congestion on the first switch.

A system enabled for congestion avoidance in a network, the system comprising:

• a plurality of interconnected network nodes;
• a plurality of network switches, distributed within the network;
• each of the network switches configured for interconnecting network nodes in the network and for forwarding network packets;
• the plurality of network nodes comprising at least a plurality of end nodes within the network, one or more of the plurality of end nodes, being coupled to at least a processor and thereby having a capability to create network packets, and thereby being creators of network packets;
• the plurality of network nodes comprising at least a first network node and at least a second network node;
• the at least the first network node comprising a network switch;
• the at least a second network node configured as an end node configured as a creator of network packets;
• the network switch receiving a plurality of network packets comprising at least a set of first network packets and second network packets created by the plurality of end nodes configured as creators of network packets comprising at least the second network node;
• the network packets received by the network switch are to be forwarded over the network;
• the network switch having a plurality of queues at its network ports for storing and forwarding network packets based on a quality of service associated with each network packet;
• the plurality of queues of the network switch comprising at least a first queue for storing and forwarding the first network packets;
• the network system configured to implement a method for per queue congestion avoidance over the interconnected network nodes;
• the method comprising:
• the at least the network switch experiencing high network packet load at the at least the first queue;
• the high network packet load being an indicator of congestion;
• the at least the second network node being one of the creators of first and second network packets receiving a request in a data link frame;
• the second network node responding to the request by sending network packets which are to be forwarded using the plurality of queues of the network switch, other than the first network packets to be stored in the first queue of the at least the network switch to the first node, while delaying sending network packets which are to be forwarded using first queue in the network switch;
• the method thereby reducing the congestion by reducing the load in the first queue of the at least the network switch and preventing packet loss due to congestion.