Abstract: Various example embodiments for supporting dynamic control of network topologies are presented. Various example embodiments for supporting dynamic control of network topologies may be configured to support dynamic control of a network topology for a network of routers supporting a set of servers (e.g., a web scale network, a datacenter network, or the like). Various example embodiments for supporting dynamic control of network topologies may be configured to support dynamic control of a network topology based on integration of tunable optical ports into routers and connection of the tunable optical ports to optical buses. Various example embodiments for supporting dynamic control of network topologies may be configured to support dynamic control of a network topology based on dynamic configuration of tunable optical ports of routers to support communication over optical buses according to the network topology.

Abstract: A method includes forwarding one or more packets from a first addressable computing element to at least a second addressable computing element based on a topology-aware address assigned to the second addressable computing element. The topology-aware address includes a set of identifiers representing one or more topology attributes associated with the second addressable computing element.

Abstract: Various exemplary embodiments relate to a system for hashing a value into a cache, the system including a processor for performing a series of instructions; a memory; and the cache including a plurality of slots, each slot including two locations to store values, each location comprising a tag value and an index, the cache in communication with the memory and the processor, the cache configured to calculate a target slot in the cache for an object, determine if a location is available, store a characteristic of the object in the index of the location, and update the tag value of the location.

Abstract: A capability is provided for statelessly load balancing Transmission Control Protocol (TCP) connections across a set of servers. A load balancer receives a TCP SYN packet from a client, selects a server for a TCP connection for the client, forms a modified TCP SYN packet including an address of the client, and propagates the modified TCP SYN packet toward the server. The server receives the modified TCP SYN packet, forms a TCP SYN+ACK packet including an identifier (e.g., n bits of an address, an n-bit server index based on mapping information of the load balancer, or the like) of the server, and propagates the modified TCP SYN+ACK packet toward the load balancer. The load balancer receives a TCP packet from the client on the TCP connection, determines a server associated with the TCP connection based on information included within the TCP packet, and propagates the TCP packet toward the server.

Abstract: A capability is provided for statelessly load balancing Transmission Control Protocol (TCP) connections across a set of servers. A load balancer receives a TCP SYN packet from a client, selects a server for a TCP connection for the client, forms a modified TCP SYN packet including an address of the client, and propagates the modified TCP SYN packet toward the server. The server receives the modified TCP SYN packet, forms a TCP SYN+ACK packet including an identifier (e.g., n bits of an address, an n-bit server index based on mapping information of the load balancer, or the like) of the server, and propagates the modified TCP SYN+ACK packet toward the load balancer. The load balancer receives a TCP packet from the client on the TCP connection, determines a server associated with the TCP connection based on information included within the TCP packet, and propagates the TCP packet toward the server.

Abstract: A capability is provided for statelessly recognizing Transmission Control Protocol (TCP) keep-alive packets. A server receives a TCP SYN packet including an initial client sequence number and selects an initial server sequence number for the TCP connection based on the parity of the initial client sequence number and a parity rule. A server receives a TCP packet from a client and uses a parity rule for determining whether to manipulate a TCP response packet to be sent by the server to the client responsive to the received TCP packet (to ensure that the next TCP packet to be sent by the client is not incorrectly identified as a TCP keep-alive packet). A network device receives a TCP packet and uses a parity rule to determine whether the TCP packet is a TCP keep-alive packet. The parity rule is indicative of an expected parity of TCP keep-alive packets.

Abstract: Various embodiments provide a method and apparatus for providing SDN flow distribution without requiring per-connection state in the network. In particular, the SDN flow distribution is realized in network elements within the forwarding path of packets by providing in those network elements with a controller capable of mapping traffic flows onto a set of target servers.

Abstract: Various exemplary embodiments relate to a system for hashing a value into a cache, the system including a processor for performing a series of instructions; a memory; and the cache including a plurality of slots, each slot including two locations to store values, each location comprising a tag value and an index, the cache in communication with the memory and the processor, the cache configured to calculate a target slot in the cache for an object, determine if a location is available, store a characteristic of the object in the index of the location, and update the tag value of the location.

Abstract: In one embodiment, a first network device is configured for communication with at least a second network device, and implements a gateway. The gateway may comprise, for example, a software gateway. The gateway is configured to receive a packet in a format of a first protocol and to determine if the packet includes an identifier of the gateway, for example, encoded within a destination address of the received packet. If the received packet does not include the gateway identifier, the packet is forwarded in the format of the first protocol. If the received packet does include the gateway identifier, a network address translation operation is applied to reconfigure the packet in a format of a second protocol different than the first protocol, and the reconfigured packet is forwarded in the format of the second protocol. The first and second protocols may comprise Internet protocols such as IPv6 and IPv4, respectively.

Abstract: Various exemplary embodiments relate to a device for routing an incoming packet to a destination, the device comprising a processor associated with a storage, in communication with a network interface, the processor being configured to receive the incoming packet; access from the storage a plurality of at least two server bits, each server bit representing a possible next hop to the destination, where if the quantity of possible next hops to the destination is less than a power of two then the quantity of server bits is equal to the next highest power of two, and wherein a quantity n is equal to the exponent of the next highest power of two; determine one or more hash bits calculated from a hash value derived from a source address, a destination address, a source port, and a destination port of the packet, wherein the quantity of hash bits is half the number of server bits; and repeatedly, for n repetitions, determine one or more output bits from a plurality of at least two inputs bits and the one or more has

Abstract: Various exemplary embodiments relate to a device for routing an incoming packet to a destination, the device comprising a processor associated with a storage, in communication with a network interface, the processor being configured to receive the incoming packet; access from the storage a plurality of at least two server bits, each server bit representing a possible next hop to the destination, where if the quantity of possible next hops to the destination is less than a power of two then the quantity of server bits is equal to the next highest power of two, and wherein a quantity n is equal to the exponent of the next highest power of two; determine one or more hash bits calculated from a hash value derived from a source address, a destination address, a source port, and a destination port of the packet, wherein the quantity of hash bits is half the number of server bits; and repeatedly, for n repetitions, determine one or more output bits from a plurality of at least two inputs bits and the one or more has

Abstract: Various exemplary embodiments relate to a method, network node, and non-transitory machine-readable storage medium including one or more of the following: receiving, at the host device, a first received message including a first identification of a first network function; removing the first identification of the first network function from the first received message to create a first modified message; and transmitting the first modified message to a first network function device for performance of the first network function with respect to the first modified message. Various embodiments are described wherein: the first received message includes a bitmap including a plurality of bit positions respectively corresponding to a plurality of network functions, and the first indication of a first network function comprises a bit within the bitmap at a bit position corresponding to the first network function.

Abstract: A method includes forwarding one or more packets from a first addressable computing element to at least a second addressable computing element based on a topology-aware address assigned to the second addressable computing element. The topology-aware address includes a set of identifiers representing one or more topology attributes associated with the second addressable computing element.

Abstract: A capability is provided for performing distributed multi-level stateless load balancing. The stateless load balancing may be performed for load balancing of connections of a stateful-connection protocol (e.g., Transmission Control Protocol (TCP) connections, Stream Control Transmission Protocol (SCTP) connections, or the like). The stateless load balancing may be distributed across multiple hierarchical levels. The multiple hierarchical levels may be distributed across multiple network locations, geographic locations, or the like.

Abstract: A load balancer selects a processing device from a set of processing devices in a communication network to serve a request received by the load balancer from a client device. The load balancer forwards the request to the selected processing device such that the selected processing device can provide at least one response to the client device without the response passing through the load balancer. The response comprises a value inserted therein that is unique to the selected processing device. An acknowledgement is received at the load balancer from the client device, wherein the acknowledgement comprises the unique value associated with the selected processing device. The acknowledgement with the unique value is forwarded from the load balancer to the selected processing device such that the selected processing device can delete state information associated with the request. Selection of the processing device may be based on content of the request.

Abstract: A method includes sending substantially simultaneously two or more session requests from a first processing device respectively to two or more groups of virtual resources of a communication network, wherein the two or more groups of virtual resources represent two or more paths to a second processing device, such that a single session can be established between a first user and a second user based on one of the two or more session requests.

Abstract: In one embodiment, a first network device is configured for communication with at least a second network device, and implements a gateway. The gateway may comprise, for example, a software gateway. The gateway is configured to receive a packet in a format of a first protocol and to determine if the packet includes an identifier of the gateway, for example, encoded within a destination address of the received packet. If the received packet does not include the gateway identifier, the packet is forwarded in the format of the first protocol. If the received packet does include the gateway identifier, a network address translation operation is applied to reconfigure the packet in a format of a second protocol different than the first protocol, and the reconfigured packet is forwarded in the format of the second protocol. The first and second protocols may comprise Internet protocols such as IPv6 and IPv4, respectively.

Abstract: Various embodiments provide a method and apparatus for providing redundant data access. In particular, a response to a client request for a data item includes selecting the data segments of the data item to be provided to the client by each of a corresponding select plurality of servers. In particular, the data segments are smaller in size as compared to the data item and are configured such that the data item may be constructed using a proper subset of the transmitted data segments.

Abstract: Various embodiments provide a method and apparatus for providing SDN flow distribution without requiring per-connection state in the network. In particular, the SDN flow distribution is realized in network elements within the forwarding path of packets by providing in those network elements with a controller capable of mapping traffic flows onto a set of target servers.

Abstract: A capability is provided for statelessly recognizing Transmission Control Protocol (TCP) keep-alive packets. A server receives a TCP SYN packet including an initial client sequence number and selects an initial server sequence number for the TCP connection based on the parity of the initial client sequence number and a parity rule. A server receives a TCP packet from a client and uses a parity rule for determining whether to manipulate a TCP response packet to be sent by the server to the client responsive to the received TCP packet (to ensure that the next TCP packet to be sent by the client is not incorrectly identified as a TCP keep-alive packet). A network device receives a TCP packet and uses a parity rule to determine whether the TCP packet is a TCP keep-alive packet. The parity rule is indicative of an expected parity of TCP keep-alive packets.