Abstract: A method of forwarding packets in a network device is disclosed. The method comprises assigning a packet to a first packet processing thread; and determining a state of the first packet processing thread. Responsive to determining that the state of the first packet processing thread is a backlogged state, mapping the packet to a second packet processing thread from a pool of packet processing threads based on a load balancing scheme, wherein the pool of packet processing threads includes a subset of threads from the plurality of packet processing threads, and the state of each one of the packet processing threads from the pool is the backlogged state, processing the packet in the second packet processing thread, and forwarding the packet according to a predetermined order that is based on a position of the packet relative to positions of other packets at their receipt in the network device.

Abstract: Techniques for use in network incident identification are described. In response to an occurrence of an unknown network incident, a plurality of log messages (e.g. syslog messages) are received from a plurality of network components in one or more networks. In one illustrative example, a plurality of relationships between interfaces and events are derived from the received log messages and characterized as a plurality of graphical component relationships. One or more groups of connected components are determined from the graphical component relationships and network component connection data which indicate interface relationships of the network components. Here, groups of connected components may be logically joined based on the network component connection data indicating one or more interface relationships.

Abstract: In one embodiment, a method is implemented in a network element coupled to the SDN system, which contains a set of network elements processing traffic flows and a SDN controller managing the set of network elements. The method includes creating a set of virtual tables for processing packets of traffic flows at the network element based on a set of flow tables of the network element, where the set of flow tables is ordered in a sequence. The method further includes mapping each of the set of virtual tables to a single flow table of the set of flow tables, where the mapping causes at least one flow table being mapped to a plurality of the set of virtual tables. The method also includes forwarding packets of traffic flows to the set of virtual tables for processing.

Abstract: A method for forwarding packets in a network device is disclosed. The method comprises receiving a packet; mapping the packet to a bucket, where the bucket is associated with a packet processing thread from a plurality of packet processing threads; and determining whether the packet processing thread is oversubscribed. The method continues with, in response to determining that the packet processing thread is not oversubscribed, mapping the packet to the packet processing thread; and in response to determining that the packet processing thread is oversubscribed, the method comprises distributing the packet to one of the plurality of packet processing threads based on a predefined load balancing scheme, processing the packet in the one of the plurality of packet processing threads, and forwarding the packet according to a predetermined order, where the predetermined order is based on a position of the packet relative to other packets at their receipt.

Abstract: In one embodiment, a method for load balancing in a software-define networking (SDN) system includes, upon receiving a packet, determining whether a matching entry for the packet in a server distribution table contains both a current and new server selection. If the matching entry contains both, it is determined whether there is a matching entry for the packet in a transient flow table, where the transient flow table maintains server selections when at least one of the plurality of servers is reconfigured. Upon determining that there is no matching entry for the packet in the transient flow table, the method determines whether the packet is a first packet of a traffic flow. If the packet is the first packet of a traffic flow, the packet is forwarded according to the new server selection of the matching entry in the server distribution table, and the transient flow table is updated.

Abstract: Exemplary methods for performing service chaining include generating a plurality of service chaining (SC) next hops (NHs) by, for each SC NH hop, generating a plurality of SC maps, each SC map identifying a chain of one or more service modules, wherein each service module is to apply a corresponding service on a packet. The methods further include generating a plurality of hosted NHs, each hosted NH including forwarding information that causes the packet to be forwarded to a corresponding service module. The methods further include in response to receiving a first packet, identifying a SC NH of the plurality of SC NHs based on an Internet Protocol (IP) address of the first packet, and forwarding the first packet to a service module based on the identified SC NH.

Abstract: In some embodiments, an apparatus includes a flow control module configured to receive a first data packet from an output queue of a stage of a multi-stage switch at a first rate when an available capacity of the output queue crosses a first threshold. The flow control module is configured to receive a second data packet from the output queue of the stage of the multi-stage switch at a second rate when the available capacity of the output queue crosses a second threshold. The flow control module configured to send a flow control signal to an edge device of the multi-stage switch from which the first data packet or the second data packet entered the multi-stage switch.

Abstract: A method for implementing Ethernet operation, administration, and management (OAM) function in a network element coupled to a software-defined networking (SDN) system is disclosed. The method comprises adding a flow table entry for an OAM traffic flow to a flow table of the network element. The method continues with adding a group table entry for the OAM traffic flow to a group table of the network element, where the group table entry includes an instruction to send the packet to a set of ports, including a loopback port. The method continues with receiving the packet directing to the group table entry from the SDN controller, and sending the packet to the set of ports of the network element according to the group table entry, where the packet is to be looped back through the loopback port to the flow table periodically at a predetermined interval.

Abstract: A method for generating a high-precision packet train includes configuring an initial packet generation flow of duration T in a network node and sending a packet to a loopback port to initiate the initial packet generation flow in the network node, where the loopback port loops packets back to the network node or recirculates packets within the network node, and where the loopback port is configured for traffic shaping that establishes a pre-determined inter-packet gap for packets output by the loopback port. The method further includes configuring a main packet generation flow having a duration t1 that commences on expiration of the duration T. Looped back packets in the network node are sent to the loopback port for the entirety of durations T and t1, while one copy of each looped back packet in the network node is sent to a network port during the duration t1.

Abstract: In some embodiments, an apparatus includes a flow control module configured to receive a first data packet from an output queue of a stage of a multi-stage switch at a first rate when an available capacity of the output queue crosses a first threshold. The flow control module is configured to receive a second data packet from the output queue of the stage of the multi-stage switch at a second rate when the available capacity of the output queue crosses a second threshold. The flow control module configured to send a flow control signal to an edge device of the multi-stage switch from which the first data packet or the second data packet entered the multi-stage switch.

Abstract: A technique for packet ingress processing and packet egress processing in an OpenFlow, OF, switch is presented. A method aspect directed to packet ingress processing comprises receiving a packet at an OF port. The packet is associated with one of multiple logical flow entities, such as logical ports, allocated to the OF port. In a next step, the logical flow entity associated with the received packet is determined. Then, metadata for the packet is tagged with an identifier for the logical flow entity associated with the packet. The tagging controls handling of the packet at egress processing. The packet handling, in turn, may include a selective dropping or passing of the packet.

Abstract: Methods may be provided to forward data packets to a plurality of servers with each server being identified by a respective server identification (ID). A non-initial data packet of a data flow may be received, with the non-initial data packet including information for the data flow, and a bucket ID for the non-initial data packet may be computed as a function of the information for the data flow. Responsive to the bucket ID for the data packet mapping to first and second server identifications (IDs) of respective first and second servers and responsive to the non-initial data packet being a non-initial data packet for the data flow, the non-initial data packet may be transmitted to one of the first and second servers using one of the first and second server IDs based on a flow identification of the data flow being included in a transient table for the bucket ID.

Abstract: In one embodiment, a packet from a SDN controller is received at a network device. The packet is processed according to a flow table, which contains at least two entries that each matches the packet. The entries contain instructions to forward the packet according to group tables, and the entries are to expire after different time durations. The packet is to be forwarded according to a first group table and gets duplicated into two: one is transmitted to a first packet queue that transmits packets in a fixed interval to a loopback port that loops back the packets, while the other is forwarded to a first packet buffer that randomly drops packets at a probability prior to transmitting the remaining packets to generate a traffic pattern. The packet is received from the loopback port, and then forwarded according to a second group table to generate another traffic pattern.

Abstract: In one embodiment, a method for load balancing in a software-define networking (SDN) system includes, upon receiving a packet, determining whether a matching entry for the packet in a server distribution table contains both a current and new server selection. If the matching entry contains both, it is determined whether there is a matching entry for the packet in a transient flow table, where the transient flow table maintains server selections when at least one of the plurality of servers is reconfigured. Upon determining that there is no matching entry for the packet in the transient flow table, the method determines whether the packet is a first packet of a traffic flow. If the packet is the first packet of a traffic flow, the packet is forwarded according to the new server selection of the matching entry in the server distribution table, and the transient flow table is updated.

Abstract: In one embodiment, a packet is processed by three flow tables in a network device of a software-defined networking (SDN) system. In the first flow table, upon finding a match based at least partially on an IP address value of the packet, the network device adds a first identifier based on the IP address value to metadata of the packet and forwards the packet to a second flow table, where upon finding a match based at least partially on a port value of the packet, the network device adds a second identifier based on the port value to the metadata and forwards the packet to a third flow table. At the third flow table, upon finding a match based at least partially on a combination of the first and second identifiers, the network device performs one set of instructions of the matching entry on the packet.

Abstract: In one embodiment, a method for load balancing in a software-define networking (SDN) system includes, upon receiving a packet, determining whether a matching entry for the packet in a server distribution table contains both a current and new server selection. If the matching entry contains both, it is determined whether there is a matching entry for the packet in a transient flow table, where the transient flow table maintains server selections when at least one of the plurality of servers is reconfigured. Upon determining that there is no matching entry for the packet in the transient flow table, the method determines whether the packet is a first packet of a traffic flow. If the packet is the first packet of a traffic flow, the packet is forwarded according to the new server selection of the matching entry in the server distribution table, and the transient flow table is updated.

Abstract: A packet distribution scheme for forwarding incoming packets to servers in a network. Depending on a hash value of the incoming flow's identification parameters, a hash flow table or database is queried to determine the server to which the packet is to be forwarded. If multiple flows have the same hash index and are associated with different servers, a secondary flow table or database is queried for determining the server. In an example implementation, only the secondary flow table is configured to store fully qualified flow identification parameters whereas the hash flow table is operative to store reduced or compressed state information.

Abstract: In one embodiment, a method implemented in a software-defined networking (SDN) system includes determining that a packet is to be forwarded by a flow table that includes at least two sets of instructions in flow table entries. The method continues with determining values of a plurality of match key components extracted from the packet to match the flow table, where the plurality of match key components contains at least a pair of match key components in a same type, wherein values of the pair are determined based on numerical measures of the pair. The method continues with searching the flow table to find a matching entry for the packet and, upon finding it, selecting one of the at least two sets of instructions of the matching entry following the determination of the values of the plurality of match key components, and perform the selected set of instructions on the packet.

Abstract: A method of packet prioritization at a data network is disclosed. The data network contains a number of data plane nodes carrying user traffic and a control node managing the data plane nodes. The method starts with receiving a packet at a data plane node. The data plane node determines that it needs help from the control node for processing the received packet. It then quantizes a congestion level at the data plane node and encoding the quantized congestion level in the packet, where a number of bits in the packet indicates the quantized congestion level. It sends a portion of the packet from the data plane node to the control node, where the portion of the packet includes the number of bits encoding the quantized congestion level.

Abstract: In one embodiment, a method includes storing received packets at an electronic device in a plurality of packet buffers based on hashing the packets, where each of the plurality of packet buffers is implemented as a hash bucket of a hash table. The method includes identifying a packet buffer that has stored packets, selecting a first processing thread from a plurality of processing threads based on a load balancing mechanism, forwarding a plurality of packets from the identified packet buffer to the first processing thread, and setting an indication that the identified packet buffer is mapped to the first processing thread. The method includes determining that the first processing thread has completed processing the plurality of packets, selecting either the first processing thread or a second processing thread for processing subsequent packets from the identified packet buffer, and maintaining or updating the indication based on the selection.