Abstract: A method and apparatus for proactively forming flowlets for a flow in a communication network. The method includes monitoring one or more conditions associated with the flow and detecting a trigger signal. Upon detection of activation of the trigger signal, the method further includes transmitting a pause message.

Abstract: Methods and systems for load balancing of a communication network are described. Examples of the disclosed methods and systems may be topology agnostic (not specific to a particular network topology). Congestion information is obtained for a plurality of paths between two switches in the communication network. A selection probability is obtained for each path using the congestion information. A flowlet is assigned to a path based on the selection probabilities. Each path may be assigned to a path group, where each path group comprises paths of equal length. The selection probabilities may be computed for each path group and for each path within each path group, and the flowlet may be assigned by selecting a path group based on the selection probabilities of the path groups, and selecting a path within the selected path group.

Abstract: There is provided a method and apparatus to provide notification of change events for microburst mitigation. The method is used by a sending device and includes tracking changes in scheduled data to be sent in a traffic flow and identifying a positive change in an amount of scheduled data to be sent in the traffic flow. The sending device then marks one or more packets to be sent in the traffic flow with a notification field, and then transmits the one or more packets including the notification field. The notification field can then be used by a recipient device, for example a network element, to identify and mitigate microbursts in a proactive manner.

Abstract: The present disclosure describes methods and systems for proactively managing a distributed computer network based on learned relationships between state changes and network events. During an initial identification phase, information representing state changes occurring at host nodes, and network events occurring at network nodes, is collected and processed to generate a database of event probability signatures, each event probability signature indicating a respective probability that a specified event type will occur at a specified network node given a specified type of state change at one of the hosts. During a subsequent action phase, a smart network engine can interact with software drivers installed on each host node to actively monitor for state changes, and when a state change is detected, compare the type of state change with the types of state changes specified in the plurality of event probability signatures to select a matching event probability signature.

Abstract: Methods and systems related to construction and implementation of high radix topologies are disclosed. The nodes of the network topology are divided into a number of groups. Intra-group connections are constructed by connecting the nodes of each group according to a first complementary base graph. Inter-group connections are constructed based on a second complementary base graph and a plurality of permutation matrices. Each permutation matrix represents a pattern for selecting source group and destination group for each inter-group connection. One permutation matrix is randomly assigned to each edge of the second complementary base graph. An inter-group connection is constructed by identifying a source node and a destination node corresponding to a selected edge of the second complementary base graph, and identifying a source group and a destination group according to the permutation matrix assigned to the selected edge.

Abstract: Methods and systems for load balancing of a communication network are described. Examples of the disclosed methods and systems may be topology agnostic (not specific to a particular network topology). Congestion information is obtained for a plurality of paths between two switches in the communication network. A selection probability is obtained for each path using the congestion information. A flowlet is assigned to a path based on the selection probabilities. Each path may be assigned to a path group, where each path group comprises paths of equal length. The selection probabilities may be computed for each path group and for each path within each path group, and the flowlet may be assigned by selecting a path group based on the selection probabilities of the path groups, and selecting a path within the selected path group.