摘要:
The present disclosure generally discloses a data plane services support mechanism. The data plane services support mechanism may be configured to provide a data plane service for an application. The data plane services support mechanism may be configured to instantiate a virtual resource for the data plane service to be provided for the application, configure the data plane service on the virtual resource, and configure flow connectivity for the data plane service to support delivery of application traffic of the application to the data plane service. The data plane services support mechanism may be configured to support automatic scalability. The data plane services support mechanism may be configured to support improved communication of application traffic associated with providing the data plane service for the application. The improved communication of application traffic may be provided based on configuration of a virtual switch to support a network interface card (NIC) offloading capability.
摘要:
A switch schedules guaranteed-bandwidth, low-jitter-traffic characterized by a guaranteed rate table (GRT) method. A rate matrix generated from collected provisioning information is decomposed into schedule tables by a low jitter (LJ) decomposition method. The LJ decomposition method imposes a set of constraints for the schedule tables: schedule tables are partial permutation matrices, weighted sum of the partial permutation matrices is greater than or equal to the weighted sum of the rate matrix, and each entry in the rate matrix belongs to one element of the LJ decomposition schedule matrices. An integer LJ decomposition programming problem is employed to generate the schedule tables that are scheduled for each time slot of the period of the switch. Schedule tables are selected in turn based upon selecting eligible tables having the earliest finishing time. If necessary, the rate matrix is updated prior to decomposition for a subsequent period.
摘要:
A filter method for designating one of a plurality of packet filter rules contained in a router for routing a packet of information through a network, each packet characterized as having parameters, the method comprising: generating one or more partitioned sets, each partitioned set associated with a different packet parameter with each partition of a set having zero or more associated filter rules; generating a vector corresponding to each of the parameters, the vector defining structure indicating one or more potential filter rules to be applied; comparing each parameter of the received packet with each partition of a corresponding partitioned set and determining one or more potential filter rules to be applied to the packet for each parameter; and determining from each of the vectors one or more identical potential filter rules associated with each vector, one of the identical filter rules capable of being applied to the received packet, with the rule to be applied being the rule of greatest priority.
摘要:
Apparatus for routing packets in a communication network comprises a plurality of per-connection queues, each queue established for receiving packets from a respective source and temporarily storing received packets before routing to a particular destination; a weighted fair-queuing scheduler for servicing packets from each of the plurality of per-connection queues at guaranteed pre-allocated rates; a sensing device for sensing a presence or absence of packets in queues, the absence of packets in queues indicating availability of excess bandwidth; and, a state dependent scheduler for redistributing excess bandwidth upon sensing of queues absent packets, the state dependent scheduler servicing those queues in accordance with a state variable corresponding to a performance property of the queues, wherein delay and isolation properties for routing packets of respective queues in weighted fair-queuing is preserved.
摘要:
A network of nodes interconnected by links, such as a wavelength division multiplexing (WDM) ring network, is modeled by a delayed graph in which propagation delay between nodes is accounted for. Given the delayed graph, a traffic matrix for an admissible traffic pattern is scheduled over a frame period. Scheduling of the traffic matrix formulates a set of scheduling constraints based on the delays and decomposes the traffic matrix into a set of transmission matrices. Each of the set of transmission matrices is scheduled over the frame period.
摘要:
A packet filter for a router performs generalized packet filtering allowing range matches in two dimensions, where ranges in one dimension at least one dimension is defined as a power of two. To associate a filter rule with a received packet EP, the packet filter employs a 2-dimensional interval search and memory look-up with the filter-rule table. Values of sm of filter-rule rm=(sm,dm) in one dimension are desirably ranges that are a power of two, such as prefix ranges, which are represented by a binary value having a “length” defined as the number of bits to of the prefix. The dm may be single points, ranges defined as prefix ranges, and/or ranges defined as continuous ranges. The packet filter employs preprocessing of the filter-rules based on prefix length as a power of 2 in one dimension and decomposition of overlapping segments into non-overlapping intervals in the other dimension to form the filter-rule table. A preprocessing algorithm searches in one dimension through filter rules and arranges the corresponding filter-rule rectangle segments according to prefix length. Then, in the other dimension, the overlapping filter rectangle segments are decomposed into non-overlapping intervals, and the highest priority filter-rule overlapping each non-overlapping interval is associated with that interval. A filter-rule table is then constructed with entries ordered according to prefix length and non-overlapping interval, each entry associated with a particular filter-rule. A packet classification algorithm then matches the field or other parameter information in the packet to the filter-rule table entries to identify the filter-rule rectangle associated with the filter-rule to be applied to the packet.
摘要:
Provided is a method and devices for overload control in a cloud computing environment. The method includes receiving a first message from a network element associated with the cloud computing environment. The first message includes information associated with a target virtual machine and a list of sessions from the one or more sessions to move from the serving virtual machine to the target virtual machine. Associating one or more client addresses with an address associated with the target virtual machine based on the list of sessions. And, treating the target virtual machine as the serving virtual machine if processing sessions associated with the list of sessions.
摘要:
A system and method of rate adaptation is disclosed for energy efficiency. The system and method of rate adaptation for energy efficiency provides for parsing a heterogeneous network into rate-adaptation domains that are fully isolated with respect to the control of their operating states. The system and method is particularly useful for creating the conditions for the incremental introduction of rate-adaptive devices in existing networks; combining the best properties of sleep-state exploitation and rate scaling techniques by defining a class of state-setting policies for rate adaptation schemes that enforce tight deterministic bounds on the extra delay that the schemes may cause to network traffic at every node where they are deployed.
摘要:
The invention includes a method and apparatus for providing secure remote access to enterprise networks. An apparatus includes a network interface module adapted for maintaining a secure network connection with a network device independent of a power state of a host computer associated with the apparatus a storage module for storing information associated with the secure connection, and a processor coupled to the network interface and the memory where the processor is adapted for automatically initiating the secure connection without user interaction.
摘要:
A communications switch or router employs a replication server to perform batch processing of multicast connections. The replication server performs three distinct forms of processing using staging queues: packet arrival processing, packet replication processing, and per-interface transmission processing. Packet arrival processing queues arriving packets in session queues, adds new multicast sessions to a replication set, and assigns a counter equivalent to the fan-out of the multicast session. Packet replication processing assigns a descriptor to packets of each session in the replication set, and copies the descriptor to each per-interface queue. Per-interface transmission processing examines each descriptor in the per-interface queue, copies the corresponding packets for transmission by the interface, adjusts the counter as each packet is copied, and clears the packet in the switch based on the adjusted counter.