90results about How to "Efficient forwarding" patented technology

This invention is directed to a parallel, control-information generation, distribution and processing system. This scalable, pipelined control and switching system efficiently and fairly manages a plurality of incoming data streams, and applies class and quality of service requirements. The present invention also uses scalable MLML switch fabrics to control a data packet switch, including a request-processing switch used to control the data-packet switch. Also included is a request processor for each output port, which manages and approves all data flow to that output port, and an answer switch which transmits answer packets from request processors back to requesting input ports.

Under the present invention, a method, computer program product, and system for non-blocking dynamic update of statically-typed class-based object-oriented software executing as byte-code on a virtual machine within an actively running computer system is provided. A set of objects instantiated from an existing module or multiple modules (identifiable collections of application resources and class definitions in the form of byte-code representations) is ready for execution on a virtual machine in an actively running computer system. New versions of one or more modules corresponding to those already loaded into the actively running virtual machine are dynamically loaded into the virtual machine for the purpose of updating the running software. The class definitions within the loaded modules are prepared for dynamic update by inserting byte-code that enables; transparent state transfer and shared object identity between objects of a former version and the new version of a class. On the event of a software update, the objects instantiated from a former version of an updated class become un-initialized surrogate objects with the potential to redirect to their future corresponding objects. Corresponding objects are created lazily on first access of the declaring class members. Besides lazy redirection of the behavior of objects and classes, non-blocking dynamic update is achieved by lazy migration of the state of former objects and classes while locking on a temporary field access lock. Thus, the algorithm for controlling field access and state migration is completely lock-free both before and after state migration; hence the performance degradation is minimal. Finally, any unreferenced objects are removed from memory.

According to certain embodiments of the present invention, Wireless Mobility Gateway (MOGW) method and apparatus determines whether a wireless connection has been requested by a mobile terminal. As a consequence it performs security functions to authenticate the mobile user and grant access. If requested by the mobile user it then also creates a wireless connection to allow it to perform IP packet transmission and reception and therefore make use of mobile data services. The MOGW is able to directly route packets to Internet and Corporate Networks, thus rendering the whole mobile network more efficient and simpler to construct and manage. The MOGW generates a special tunnel identifier to identify the wireless connection that must be contained in all packets received from the RAN. The MOGW generates such a tunnel identifier by concatenating a number of values that characterize the connection. Therefore, simply by reading this tunnel identifier, the MOGW can more efficiently forward packets appropriately. The Mobility protocol and function between MOGWs allows Mobile terminals to easily move between geographical areas served by different MOGWs.

A method and apparatus for building a packet grooming and aggregation engine is disclosed. The grooming and aggregation engine can be applied to the network for providing flexible aggregation and service multiplexing functions. A method and apparatus achieves the intended function that is easy to implement and easy for the network operator to manage, yet provides enough flexibility to mix and match various services at the edge node of the network. One specific embodiment of the patent is an Ethernet over SONET mapping system where user traffic is aggregated and groomed into SONET transport virtual concatenation channels.

A system and method for efficiently forwarding client requests from a proxy server in a TCP / IP computing environment is described. A plurality of transient requests are received from individual sending clients into a request queue. Each request is commonly addressed to an origin server. Time estimates of TCP overhead, slow start overhead, time-to-idle, and request transfer time for sending the requests over each of a plurality of managed connections to the origin server are dynamically calculated, concurrent to receiving and during processing of each request. The managed connection is chosen from, in order of preferred selection, a warm idle connection, an active connection with a time-to-idle less than a slow start overhead, a cold idle connection, an active connection with a time-to-idle less than a TCP overhead, a new managed connection, and an existing managed connection with a smallest time-to-idle. Each request is forwarded to the origin server over the selected managed connection.

The present invention intends to provide a polishing pad and a multi-layer polishing pad that can particularly effectively suppress scratch from occurring. The polishing pad of the invention comprises at least one part selected from a groove (a) having at least one kind of shape selected from annular, lattice-like and spiral form on a polishing surface side, a concave portion (b) and a through hole (c). In the above, surface roughness of an inner surface of the part is 20 mum or less and the polishing pad is used for chemical mechanical polishing.

Embodiments of the present invention generally relate to a system and method for selecting the best server to realize the best user-experience for the client. The selection of this server is selected based on the quality of each user's connection to each server. Embodiments of the present invention also generally relate to a system and method to facilitate efficient transmission and carry each user's stream to the selected server.

For each high-level protocol, a respective mesh of Transmission Control Protocol (TCP) connections is set up for a cluster of server computers for the forwarding of client requests. Each mesh has a respective pair of TCP connections in opposite directions between each pair of server computers in the cluster. The high-level protocols, for example, include the Network File System (NFS) protocol, and the Common Internet File System (CIFS) protocol. Each mesh can be shared among multiple clients because there is no need for maintenance of separate TCP connection state for each client. The server computers may use Remote Procedure Call (RPC) semantics for the forwarding of the client requests, and prior to the forwarding of a client request, a new unique transaction ID can substituted for an original transaction ID in the client request so that forwarded requests have unique transaction IDs.

A method, computer program product, and system for non-blocking dynamic update of statically-typed class-based object-oriented software executing as byte-code on a virtual machine within an actively running computer system is provided. A set of objects instantiated from an existing module or multiple modules (identifiable collections of application resources and class definitions in the form of byte-code representations) is ready for execution on a virtual machine in an actively running computer system. New versions of one or more modules corresponding to those already loaded into the actively running virtual machine are dynamically loaded into the virtual machine for the purpose of updating the running software. The class definitions within the loaded modules are prepared for dynamic update by inserting byte-code that enables; transparent state transfer and shared object identity between objects of a former version and the new version of a class.

There is disclosed a manner of managing the active topology, that is the scheme for forwarding data, in a computer network such as an Ethernet local area network. A root bridge is selected from a plurality of bridges in the network; the root bridge calculating at least one spanning tree from a topology database that has been populated by bridge neighbor information gleaned from link state advertising messages. The root bridge may also calculate an alternate topology for implementation in the event a failure condition that affects the primary spanning tree is detected. The root bridge then advertises the spanning tree and remotely configures the port states of the bridges in the spanning tree through tree advertising messages that the bridges are arranged to process and set their ports accordingly.

Provided is a packet relay device for efficiently transferring a communication packet transmitted from a plurality of terminals connected with a network. The packet relay device is positioned in the network, in which a plurality of local networks are connected with each other through a global network, and at the boundary between the local network and the global network. The packet relay device comprises an acquisition unit for specifying the terminal of a transmission source from a broadcast packet transmitted by the terminal in the local network thereby to acquire group information on the group, to which the specified terminal belongs, a conversion unit for converting the broadcast packet into a virtual multicast packet corresponding to the group information acquired beforehand, a transfer unit for transferring the virtual multicast packet to another corresponding relay device, and a packet conversion unit for converting the virtual multicast packet into a corresponding real broadcast packet.

An intermediate network node is configured to forward a plurality of packets concurrently, e.g., as a vector, rather than one packet at a time. As such, the node can load a single sequence of forwarding instructions that may be repeatedly executed for packets in the vector. In addition, the intermediate network node adaptively controls the rate at which it processes data packets through a directed forwarding graph. To that end, the intermediate node is configured to dynamically select the number of packets per vector, i.e., vector size, processed at each node of the forwarding graph. Further, the intermediate node also may be configured to dynamically select timing intervals for one or more “node timers” used to control the rate at which packets traverse through the graph. Illustratively, the vector size and node-timer intervals are selected so that the average latency through the forwarding graph is less than a predetermined target latency, e.g., 50 microseconds (μs).

A Wireless Mobility Gateway (MOGW) creates a wireless connection to allow a mobile terminal to perform IP packet transmission and reception and make use of mobile data services. The MOGW is able to directly route packets to the Internet and Corporate Networks, thus rendering the whole mobile network more efficient and simpler to construct and manage. The MOGW generates a special tunnel identifier to identify the wireless connection that must be contained in all packets received from the RAN. The MOGW generates such a tunnel identifier by concatenating a number of values that characterize the connection. Therefore, simply by reading this tunnel identifier, the MOGW can more efficiently forward packets appropriately. The Mobility protocol and function between MOGWs allows Mobile terminals to easily move between geographical areas served by different MOGWs.

A packet forwarding apparatus (L2SW) having a frame segmentation function of converting a extended Ethernet frame such as a MAC-in-MAC frame into a plurality of fragment frames when a payload length of the received frame exceeds a standard MTU size communicable in an Ethernet network to be a forwarding destination, by segmenting the received frame into a plurality of data blocks having a size not longer than the MTU size, and a frame assembling function of restoring an original extended frame from a series of fragment frames received from the Ethernet network.

An embodiment of the invention provides a message forwarding method and system in an information center network. The method mainly includes that an explorer inquires a service registry managed by the explorer according to a service mark in a service request packet; the service request packet is forwarded to a corresponding outlet according to service provider information corresponding to the service mark in the service registry when that the service corresponding to the service mark is in the autonomous domain is determined through inquiry; when that the service corresponding to the service mark is not in the autonomous domain is determined through inquiry, an inter-domain path mark directing to the next autonomous domain of the service provider corresponding to the service mark and related forwarding port information are obtained and the service request packet is forwarded to the next autonomous domain. According to the embodiment of the invention, analysis, searching and forwarding in the explorer of the service request packet in the information center network are realized. Each RM only needs to manage registered information including service marks and the like, so that RM load of operation of registration, update, deletion and like of service content is reduced.

A system and method for efficiently forwarding client requests from a proxy server in a TCP / IP computing environment is described. A plurality of transient requests are received from individual sending clients into a request queue. Each request is commonly addressed to an origin server. Time estimates of TCP overhead, slow start overhead, time-to-idle, and request transfer time for sending the requests over each of a plurality of managed connections to the origin server are dynamically calculated, concurrent to receiving and during processing of each request. The managed connection is chosen from, in order of preferred selection, a warm idle connection, an active connection with a time-to-idle less than a slow start overhead, a cold idle connection, an active connection with a time-to-idle less than a TCP overhead, a new managed connection, and an existing managed connection with a smallest time-to-idle. Each request is forwarded to the origin server over the selected managed connection.

Provided are an electronic mail server manager, and a system and method for coordinating operation of multiple electronic mail servers to efficiently store, process, and forward a high volume of electronic mail. The system for managing operation of multiple email servers in accordance with one embodiment may comprise an email message queue; a plurality of receiving email servers; a plurality of sending email servers; and an email server manager having a memory and a processor configured by the memory to perform the steps of storing received email messages in an email message queue; extracting destinations from the email messages; and delivering the email messages to the destinations by way of the sending email servers in correspondence to feedback received from the sending email servers and / or the destinations.

The invention relates to a named data network comprehensive routing method based on position information and content pushing, and belongs to the technical field of computer network routing optimization. The method comprises: arranging a network management server, determining the link state of each node and starting a link state timer; establishing an NDN whole network topological structure chart and starting a network topological timer; establishing a network topology application record table; establishing a matching list of the whole network data name and the content source name and startinga statistical interval timer; the user sending a position request interest packet and the network management server replying the position data packet; a user calculating a forwarding path and sendinga data request interest packet and a content source reply content data packet, a network management server evaluating data popularity and a content source pushing data name to supplement an FIB tableof an NDN node, and regularly detecting a link state to update a network topology and pushing a high popularity data name. The method is relatively low in complexity and relatively low in bandwidth overhead, and can realize rapid establishment of the FIB table and efficient forwarding of the interest packet.

An apparatus distributing multicast messages with a multicast address among the ports of a network device on the basis of, inter alia, virtual local area network (VLAN) associations among the ports. One or more VLANs within the network device are assigned to the multicast address. The apparatus comprises a lookup engine, a forwarding engine coupled to the lookup engine, and a plurality of translation engines. The lookup engine needs to map the multicast address to a unique index value assigned to the multicast address and a bit string representing the group of multicast destination ports only once. The forwarding engine distributes the multicast messages and the unique index value to the group of multicast destination ports of the network device in accordance with the bit string. The translation engines are associated with each port of the network device respectively. Each translation engine independently performs a VLAN identifier (VID) translation in parallel on each port of the network device from the unique index value, the destination port and a VID-select index.

Techniques for switching access states for accessing non-volatile are disclosed. A plurality of non-volatile memory portions can be effectively presented as: (a) a single logical unit in a first access state (“single unit access state”) and (b) as multiple logical units in a second access state (“multi-unit access state”). An access switching system can be provided for a device that includes a plurality of non-volatile storage portions. As a result, the device can be operable to effectively switch between the first and second access states. In the first access state, the plurality of non-volatile storage portions can be effectively presented as a single logical unit for access by another device, thereby allowing the other device to effectively access the plurality of non-volatile storage portions from a single access point. However, the device can also be operable to switch to a second access state in which the plurality of the non-volatile storage portions can be effectively presented to the other device as multiple logical units, thereby allowing the other device to access the plurality of non-volatile storage portions individually by using multiple access points respectively associated with the multiple logical units presented to the other device.

The embodiment of the invention discloses a method for realizing load balancing of a virtual network. The method comprises the following steps: creating a load balancer of the virtual network, generating a load balancing flow table by the load balancer, and when detecting that a virtual machine is started, issuing a generated openflow flow table to a server that the virtual machine belongs to; and when detecting that the virtual machine is offline, deleting the previously generated flow table. With the migration of the virtual machine, the corresponding openflow flow table is added or deleted, which accurately reflects the flow characteristics of the virtual machine and realizes the load balancing of the virtual network. The method of the invention not only reduces the complexity of routing configuration, effectively guides packet forwarding, and enhances the data forwarding rate, but also increases the flexibility and scalability of the virtual network, and is beneficial to improving the overall working rate and data security of the virtual network. In addition, the embodiment of the invention further provides a corresponding implementation device, which further makes the method more practical and the device has the corresponding advantages.

There is disclosed a method and apparatus for facilitating a network, such as an Ethernet LAN, for efficient forwarding of data traffic by collecting neighbor information, generating and distributing link state advertisements, populating a topology database for the network, and calculating trees for each bridge serving as a root bridge. In a preferred embodiment the method and system also prepare one or more backup topologies, and store them for use if they are needed due to a failure condition detected in the network. In a particularly preferred embodiment, probabilities are assigned to various potential failure conditions, and the probability values are used to decide which backup topologies to calculate, store, or use.

The invention provides a network traffic refined screening device and method, which are realized based on Cavium equipment and are applied to the technical field of internet network traffic filtering.The device comprises a message capturing module, a rule receiving and analyzing module, a traffic restoring module, a rule matching module, a message packaging module and a message forwarding module.According to the method, a traffic capture core is used for capturing a network traffic packet from an active optical port, a service processing core is used for carrying out rule matching on the network traffic packet, and through flexible combination of rules such as quintuple matching, multimode and regular matching, the network traffic hitting a matching rule is searched for and forwarded. According to the invention, high-performance refined screening and multi-port message forwarding of multi-user traffic can be realized for large-scale network traffic, and the operation and maintenancecost of network traffic screening is reduced.

A processor to a store constant value (immediate or literal) in a cache upon decoding a move immediate instruction in which the immediate is to be moved (copied or written) to an architected register. The constant value is stored in an entry in the cache. Each entry in the cache includes a field to indicate whether its stored constant value is valid, and a field to associate the entry with an architected register. Once a constant value is stored in the cache, it is immediately available for forwarding to a processor pipeline where a decoded instruction may need the constant value as an operand.

The invention discloses a named data network transmission method for a smart building. The named data network transmission method comprises the following steps: a transmission mode is judged; after the intermediate node receives the interest packet, if the intermediate node is in a Pull mode, CS, PIT and FIB are inquired in sequence, a forwarding interface is determined, and the interest packet issent to bottom-layer equipment; if the mode is a Push mode, CS and FIB are inquired in sequence, a forwarding interface is determined, and the interest packet is sent to a control center; the provider returns a matched data packet after receiving the interest packet; and after receiving the data packet, the intermediate node queries CS and PIT in sequence to complete a forwarding decision, completes data aggregation according to the name mark, and completes a caching decision by using a caching strategy. According to the invention, the named data network is adopted to carry out data transmission in a smart building scene, so that the transmission requirements of massive devices are met, and the data security is improved; on the basis, the two modes can cover all types of applications, andthe related naming mode, transmission process and caching strategy can effectively improve the data transmission efficiency and reduce the overhead.

Provided is a packet relay device for efficiently transferring a communication packet transmitted from a plurality of terminals connected with a network. The packet relay device is positioned in the network, in which a plurality of local networks are connected with each other through a global network, and at the boundary between the local network and the global network. The packet relay device comprises an acquisition unit for specifying the terminal of a transmission source from a broadcast packet transmitted by the terminal in the local network thereby to acquire group information on the group, to which the specified terminal belongs, a conversion unit for converting the broadcast packet into a virtual multicast packet corresponding to the group information acquired beforehand, a transfer unit for transferring the virtual multicast packet to another corresponding relay device, and a packet conversion unit for converting the virtual multicast packet into a corresponding real broadcast packet.

The invention provides a method and a device for realizing traverse of an IPv6 message to an IPv4 network. The method comprises the following steps: when receiving the IPv6 message sent by a client, judging whether an IPv6 session table has a session table item corresponding to the IPv6 message or not, so as to obtain a first judging result; if the first judging result is yes, increasing an IPv4 masthead to the IPv6 message to obtain an IPv4 message, and sending the IPv4 message to a BR device through an IPv6-in-IPv4 channel in the IPv4 network; and when the first judging result is no, increasing an IPv4 masthead to the IPv6 to obtain the IPv4 message according to the IPv4 addresses of the CE and BR devices, and sending the IPv4 message to the BR device through the IPv6-in-IPv4 channel and adding a session table item corresponding to the IPv6 message in the IPv6 session table as well as adding the session table item corresponding to the IPv4 in the IPv4 session table. According to the invention, the message processing efficiency in 6rd can be improved.

The embodiment of the invention relates to the field of computer networks and discloses a multicast message processing method and a multicast message processing device. The method comprises the following steps of: receiving a multicast message, and acquiring a local router interface corresponding to the multicast message according to multicast routing entries carried by the multicast message; andmaking the multicast message pass through the acquired local router interface, and forwarding the multicast message to a cluster routing system for transmission. A plurality of pieces of routing equipment can be clustered into a virtual routing system which is a single routing node supporting multicast service externally, so that high-efficiency and reliable routing forwarding of the multicast message can be realized in a virtually polymerized cluster routing system. Therefore, the cluster routing system can efficiently support the multicast service at high quality.