Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a wireless communication device may identify one or more multiplexing restriction parameters for communication in a wireless network. The wireless communication device may determine to ignore the one or more multiplexing restriction parameters for full duplex communication in the wireless network. The wireless communication device may communicate in a full duplex communication mode based at least in part on the determination to ignore the one or more multiplexing restriction parameters. Numerous other aspects are described.

Abstract: A digital information management system allows users to share contact information with specific contact groups. The system comprises a communications network, a first computing device with a first user interface, a first processor, and a first memory, and a second computing device with a second user interface, a second processor, and a second memory. The second computing device receives two sets of user contact information with different contact type designations and generates contact card data for each set. The system then allows users to send the contact card data to the first computing device via the communications network, where it can be displayed on the first user interface. This system provides a convenient and efficient way for users to share contact information with specific groups.

Abstract: Techniques and apparatus for data networking are described. In one example, a method of queuing Remote Direct Memory Access (RDMA) packets includes receiving a first RDMA packet having a first quality-of-service (QoS) data field; based on a value of the first QoS data field, queueing the first RDMA packet in a first queue of a plurality of queues; receiving a second RDMA packet having a second QoS data field; and based on a value of the second QoS data field, queueing the second RDMA packet in a second queue of the plurality of the queues, the second queue being different than the first queue.

Abstract: A switch for transmitting digital data in the form of frames, each frame having an identification field and being of a first type conforming to an ARINC 664 P7 type protocol or of a second type conforming to an IEEE 802 type protocol. The switch comprising a plurality of input ports, a plurality of output ports, and a configuration table comprising for each identification value of the transmission parameters of the frames having this identification value. The switch is able to switch each frame between an input port and at least one output port exclusively on the basis of the transmission parameters corresponding to the identification value of this frame in the configuration table, independently of the type of this frame.

Abstract: Host data stream assignment with space-leveling across storage block containers. In one example, a data storage device including an electronic processor that, when executing a space-leveling scheme, is configured to receive a first host data stream, store the first host data stream in a block container assignment queue (BCAQ), detect a next storage block container switching event, responsive to detecting the next storage block container switching event, randomly select a location of the BCAQ, responsive to randomly selecting the location of the BCAQ, assign a second host data stream located at the location of the BCAQ that is selected to a storage block container of a memory, and control the memory to store the second host data stream in the storage block container that is assigned.

Abstract: A control unit architecture and a method in which a communication connection takes place between at least two control units, in particular in a vehicle. The method includes receiving the data packet by the first interface controller; determining, by a data analyzer, a transmission strategy for the data packet, the transmission strategy including at least one of the following actions: rejecting the data packet, and/or sending the data packet to at least one of the second interface controllers, and/or sending the data packet to at least one of the buffer stores, and/or fragmenting the data packet and sending it to at least one of the buffer stores, and/or sending the content of the at least one buffer store to at least one of the second interface controllers; implementing the transmission strategy for the data packet.

Abstract: In a processing system, a conversion circuit coupled to a system bus generates a flow control unit (FLIT) and provides the FLIT to a link interface circuit for transmission over an external link. The external link may be a peripheral component interface (PCI) express (PCIe) link coupled to an external device comprising a cache or memory. The conversion circuit generates the FLIT, including write information based on the write instruction, metadata associated with at least one cache line, and cache line chunks, including bytes of a cache line. The cache line chunks may be chunks of one of the at least one cache line. Including the metadata in the FLIT avoids separately transmitting the at least one cache line and the metadata over the external link, which improves performance compared to generating separate transmissions. In some examples, the FLIT corresponds to a compute express link (CXL) protocol FLIT.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for implementing a blockchain system on a switch. The method includes establishing a first blockchain node and a second blockchain node on the switch, where the first blockchain node includes a first ingress port and a first egress port, and the second blockchain node includes a second ingress port and a second egress port. The method further includes receiving a broadcast or multicast request from a user device through a user port of the switch. The method further includes sending the broadcast or multicast request to the first ingress port of the first blockchain node and the second ingress port of the second blockchain node. Through the embodiments of the present disclosure, a blockchain system can be implemented on a switch, so as to reduce the latency of the blockchain system.

Abstract: Systems, methods, and computer-readable storage media for automatic port identification. The present technology can involve determining that a wireless device has connected to a network device on a network, and determining which of the ports on the network device the wireless device has connected to. The determining the port connected to the wireless device can involve determining respective traffic patterns to be provided to selected ports on the network device, determining a traffic pattern transmitted by the wireless device, determining that the traffic pattern transmitted by the wireless device has a similarity to a traffic pattern from the respective traffic patterns, and based on the similarity, determining that a port associated with the traffic pattern is connected to the wireless device. The present technology can also involve selecting a port policy for the port.

Abstract: Systems and methods for providing input and output ports to connect to channels are provided. Input and output ports are the basic building blocks to create more complex data routing IP blocks. By aggregating these modular ports in different ways, different implementations of crossbar or Network on Chip (NoC) can be implemented, allowing flexible routing structure while maintaining all the benefits of channels such as robustness against delay variation, data compression and simplified timing assumptions.

Abstract: This application describes a network device, a controller, a queue management method, and a traffic management chip. The method may be applied to a traffic management chip that uses an HQoS technology, and can include receiving a queue management instruction sent by a controller, where the queue management instruction includes an identifier of a first scheduler and an identifier of a first queue, and the first scheduler is one of multiple first-level schedulers. The method may also include controlling, according to the queue management instruction, scheduling of the first queue by the first scheduler, where a queue scheduled by the first scheduler belongs to a queue resource pool of the TM chip, and the queue resource pool includes at least one to-be-allocated queue. In this application, decoupling between queue allocation and the first-level schedulers is implemented, flexibility of queue allocation is improved, and utilization of queue resources is improved.

Abstract: A machine learning module receives inputs comprising attributes of a storage controller, wherein the attributes affect allocation of a plurality of resources to a plurality of interfaces. In response to a predetermined number of I/O operations occurring in the storage controller, a generation is made via forward propagation through a plurality of layers of the machine learning module, of an output value corresponding to a number of resources to allocate to an interface. A margin of error is calculated based on comparing the generated output value to an expected output value that is generated from an indication of a predetermined function based at least on a number of I/O operations that are waiting for a resource and a number of available resources. An adjustment is made of weights of links that interconnect nodes of the plurality of layers via back propagation, to reduce the margin of error.

Abstract: A plurality of interfaces that share a plurality of resources in a storage controller are maintained. In response to an occurrence of a predetermined number of operations associated with an interface of the plurality of interfaces, an input is provided on a plurality of attributes of the storage controller to a machine learning module. In response to receiving the input, the machine learning module generates an output value corresponding to a number of resources of the plurality of resources to allocate to the interface in the storage controller.

Abstract: The described embodiments include systems, methods, and apparatuses for increased efficiency processing flow. One method includes a plurality of stages configured to process an execution graph that includes a plurality of logical nodes with defined properties and resources associated with each logical node of the plurality of logical nodes, a recirculating ring buffer, wherein the recirculating ring buffer is configured to holding only any one of a control information, input, and, or out data necessary to stream a temporary data between each logical node of the execution graph, and a data producer, wherein the data producer is configured to stall from writing control information into a command buffer upon the command buffer being full, preventing command buffer over-writing.

Abstract: A method for communicating over a WiFi channel. In some embodiments, the method includes determining, by a non-access point station, that a first skipping criterion is met; in response to determining that the first skipping criterion is met, skipping N1 target wait time service periods, N1 being a positive integer; after skipping N1 target wait time service periods, determining, by the non-access point station, whether a second skipping criterion is met; and in response to determining that the second skipping criterion is met, skipping N2 subsequent target wait time service periods, N2 being a positive integer greater than N1.

Abstract: Example methods are provided for a network device to perform path maximum transmission unit discovery (PMTU) in a software-defined networking (SDN) environment. One example method may comprise detecting an egress packet that includes an inner header. The method may also comprise: in response to determination that a first maximum transmission unit (MTU) associated with a path between the first node and the second node is exceeded by a total size of the egress packet and an encapsulation overhead, generating an error packet that specifies a second MTU that is configured to be less than the first MTU based on the encapsulation overhead. The error packet may be sent to the first node to cause the first node to size a subsequent egress packet to the second inner address based on the second MTU.

Abstract: A method and apparatus may be used in wireless communications. The apparatus may be an access point (AP), and may transmit a power save frame. The power save frame may include one or more Uplink (UL) Transmission Times (ULT)s. The apparatus may determine that a station (STA) did not transmit during its respective ULT. The AP may transmit another power save frame. The other power save frame may include a modified ULT. The modified ULT may be for a STA that did not transmit during its respective ULT. The other power save frame may include an unmodified ULT. The unmodified ULT may be for a STA that did not transmit.

Abstract: The described embodiments include systems, methods, and apparatuses for increased efficiency processing flow. One method includes a plurality of stages configured to process an execution graph that includes a plurality of logical nodes with defined properties and resources associated with each logical node of the plurality of logical nodes, a recirculating ring buffer, wherein the recirculating ring buffer is configured to holding only any one of a control information, input, and, or out data necessary to stream a temporary data between each logical node of the execution graph, and a data producer, wherein the data producer is configured to stall from writing control information into a command buffer upon the command buffer being full, preventing command buffer over-writing.

Abstract: A hub is connected to first and second networks where first-type and second-type frames are transmitted following first and second communication protocols. The hub sequentially receives each of the first-type and second-type frames, and stores data in first and second reception buffers. If the destination of data stored in the first and second reception buffers is the first network, the hub stores the data in a first transmission buffer. If the destination is the second network, the hub stores the data in a second transmission buffer. If the first transmission buffer is a priority transmission buffer, the hub transmits first yet-to-be-transmitted data in the first transmission buffer with priority. If the second transmission buffer is the priority transmission buffer, the hub transmits second yet-to-be-transmitted data in the second transmission buffer with priority.

Abstract: The disclosure is related to a bandwidth management method performed in a network switch and a network system. In the method, a total bandwidth usage is firstly metered, and it is determined if the total bandwidth usage reaches a threshold for triggering a flow-limit process. This threshold acts as a bandwidth-usage threshold obtained by multiplying a total bandwidth by a meter-triggering threshold. The flow-limit process is triggered if the total bandwidth usage reaches the threshold; otherwise, the system will not intervene with the usage of bandwidth if the total bandwidth usage does not reach the threshold. In the flow-limit process, the class of a user is identified. Guaranteed bandwidth is provided for a prioritized user. A normal user will be restricted to using the bandwidth aside from the guaranteed bandwidth. The bandwidth provided for the normal user may exceed the available bandwidth based on an adjustable system parameter.

Abstract: Embodiments of apparatuses and methods for traffic prediction and bandwidth aggregation are described. In various embodiments, an apparatus may include a first network interface and a second network interface with support of a multipath transport protocol. The apparatus may further include a control module to determine whether to aggregate bandwidth of the first and second network interfaces under a same transport layer connection, using the multipath transport protocol, based at least in part on a traffic prediction of the first network interface. Other embodiments may be described and/or claimed.

Abstract: In some embodiments, a system includes a set of servers, a set of switches within a switch fabric, and an optical device. The optical device is operatively coupled to the set of servers via a first set of optical fibers. Each server from the set of servers is associated with at least one wavelength from a set of wavelengths upon connection to the optical device. The optical device is operatively coupled to each switch from a set of switches via an optical fiber from a second set of optical fibers. The optical device, when operative, wavelength demultiplexes optical signals received from each switch from the set of switches, and sends, for each wavelength from the set of wavelengths, optical signals for that wavelength to the server from the set of servers.

Abstract: A method for beacon information provisioning, transmissions and protocol enhancements includes defining multiple level beacons based on the attributes of beacon information fields/elements. A short beacon may be used in addition to a primary beacon in space-time block code (STBC) modes, non-STBC modes and in multiple bandwidth modes. The short beacons may also be used for Fast Initial Link Setup (FILS) and to extend system coverage range. Beacon transmissions may use adaptive modulation and coding set/scheme (MCS).

Abstract: In some examples, a method includes determining, with a Software-Defined Network (SDN) controller of an SDN, a Maximum Transmission Unit (MTU) value for switches along a routing path for a data flow based on packet overhead for the data flow and transmitting MTU installation instructions to the switches along the routing path to install the determined MTU value on the switches of the routing path.

Abstract: A wavelength demultiplexer is equipped with a spectroscopic means (which separates light that is input from multiple input light paths, and outputs the light to multiple output light paths) and a light path switching device (a device that switches the light paths that are input to the spectroscopic means, with the switching being performed by an external operation), and the light path switching device may be a device that distributes the input from one input port to multiple output ports. The light path switching device and the spectroscopic means are polarization-independent, with the input light paths, the output light paths, and the light paths between the light path switching device and the spectroscopic means being polarization-maintaining light paths, so the relative polarization configuration is the same for the input light and the output light.

Abstract: In one embodiment, a decapsulating network device receives a plurality of encapsulated packet fragments of an original packet, and decapsulates them into respective decapsulated packet fragments. The decapsulating network device caches an inner header of the original packet from one of the decapsulated packet fragments, and in response to caching the inner header, and for each particular decapsulated packet fragment as it is received and decapsulated: prepends the inner header and fragmentation information to the particular decapsulated packet fragment; and forwards the particular decapsulated packet fragment with the prepended inner header and fragmentation information from the decapsulating network device toward a destination of the original packet.

Abstract: Embodiments include detecting an increase in delay of a flow assigned to a first queue of a network device, where the increase is sufficient to cause the flow rate of the flow to decrease if the flow is delay-sensitive. Embodiments further include determining whether an amount of bandwidth consumed by the flow decreases sufficiently after the increase is detected, and assigning the flow to a second queue based, at least in part, on determining the amount of bandwidth consumed by the flow does not decrease sufficiently. Specific embodiments include evaluating a series of two or more bandwidth measurements of the flow according to a bandwidth reduction measure to determine whether the amount of bandwidth consumed by the flow decreases by sufficiently. More specific embodiments include the first queue being configured to receive delay-sensitive flows and the second queue being configured to receive delay-insensitive nice flows.

Abstract: The present invention discloses an optical signal control method and apparatus, and an optical switch matrix control method and apparatus. A first optical coupler performs optical coupling processing on an optical signal input from an input port, to split the optical signal into two paths of optical signals; a phase shifter performs phase processing on the two paths of optical signals, so that a phase difference exists between the two paths of optical signals on which phase processing has been performed; and a second optical coupler performs optical coupling processing on the two paths of optical signals between which the phase difference exists, to output an optical signal from a first output port and/or a second output port. In this way, a problem of a low reaction speed of an existing optical switch cell that exists when the optical switch cell implements optical signal broadcast can be resolved.

Abstract: Embodiments include methods, apparatus, and systems for managing resources in a physical storage library behind a virtual storage library. In one embodiment, priorities are assigned to copy applications and rules determine which when applications are assigned to resources in the physical storage library.

Abstract: A data transfer control apparatus controls data transfers between different modules, and includes a module DMA controller configured for a predetermined module, a function DMA controller that provides a function absent in the module DMA controller, and a temporary memory coupled to the module DMA controller and the function DMA controller. When the temporary memory is input with data acquired by the module DMA controller from the predetermined module in order of acquisition, the temporary memory outputs the acquired data to the function DMA controller in order of input. When the temporary memory is input with data to be transferred to the predetermined module from the function DMA controller, the temporary memory outputs the data to be transferred to the module DMA controller in order of input.

Abstract: A system, a method, a device, and a computer program product for transmission of data packets between a user device and a server. A communication link between the user device and the server is established in accordance with a transmission control protocol for transmission of a data packet between the user device and the server. The data packet is transmitted utilizing the transmission control protocol.

Abstract: A demultiplexing device includes a first demultiplexer configured to demultiplex a first input signal, a second demultiplexer configured to demultiplex a second input signal, and a switching circuit configured to set an input destination of signals demultiplexed and output by each of the first demultiplexer and the second demultiplexer based on data rates of the first and second input signals. A multiplexing device includes a first multiplexer configured to multiplex a first input signal, a second multiplexer configured to multiplex a second input signal, and a switching circuit configured to set an input destination of signals multiplexed and output by the first multiplexer and the second multiplexer based on data rates of the first and second input signals.

Abstract: A communication control method used in a cellular mobile communication system that supports inter-terminal communication that is direct radio communication capable of being performed between user terminals in a state where a radio connection with a network is established, comprises a step of determining, by the network, a method for assigning a radio resource in the inter-terminal communication in accordance with a characteristic of an application used in the inter-terminal communication.

Abstract: The invention relates to a method for auto-configuring a wavelength selective switch (WSS) device having an output port and a plurality of input ports and coupled to a WSS controller. When connected to a WDM optical network, the WSS controller is programmed to utilize one or more optical channel monitors (OCM) coupled to the input and/or output ports to detect which of the wavelengths are present at the input ports. Wavelengths that are not detected on any input port are blocked by the WSS. Any wavelength detected as present at one and only one input port is switched by the WSS to the output port. If a wavelength is detected at two or more input ports, it is either blocked by the WSS at each of the input ports until user intervention, or is blocked at all but one of the input ports as defined by assigned port priorities.

Abstract: A hierarchical lookup forwarding model to induce a Layer (L2) forwarding look up in a post-routed virtual local area network (VLAN). In one example, a line card of a networking device receives a packet for routing from a first virtual local VLAN to a second VLAN. The line card determines that the packet is associated with a host route having a corresponding incomplete Layer 3 (L3) adjacency. The line card steers the packet to a fabric module of the networking device. The fabric module performs an L2 lookup on the packet and floods the packet to one or more of line cards of the networking devices. The one or more line cards flood the packet on a plurality of external ports of the networking device.

Abstract: Systems and methods for scheduling data for transmission over photonic switches are described herein. In one embodiment, an apparatus is provided that includes a node having M photonic interfaces. The node is configured to transmit a message having R requests. Each one of the R requests is a request to transmit data from the node to another node. R may be greater than M. Additionally or alternatively, each request may include a queue index corresponding to a respective queue in the node. The value of the queue index may be based on both a queue occupancy of the respective queue and a delay parameter.

Abstract: Embodiments of the present invention relate to a scalable interconnection scheme of multiple processing engines on a single chip using on-chip configurable routers. The interconnection scheme supports unicast and multicast routing of data packets communicated by the processing engines. Each on-chip configurable router includes routing tables that are programmable by software, and is configured to correctly deliver incoming data packets to its output ports in a fair and deadlock-free manner. In particular, each output port of the on-chip configurable routers includes an output port arbiter to avoid deadlocks when there are contentions at output ports of the on-chip configurable routers and to guarantee fairness in delivery among transferred data packets.

Abstract: A method in a communication device includes receiving from a station a request to enter a power save mode, and in response to receiving the request, enabling a set of services. The set of services includes buffering of data intended for the station. The method also includes, after enabling the set of services, receiving from the station an indicator that the station is awake, and in response to receiving the indicator, disabling the set of services. The method also includes, after disabling the set of services, receiving from the station an indicator that the station is no longer awake, in response to receiving the indicator, again enabling the set of services. The method also includes, after again enabling the set of services, receiving from the station a request to exit the power save mode, and in response to receiving the request, again disabling the set of services.

Abstract: A method and system for load balancing are provided. The method includes: receiving a tunnel frame from a traffic flow; determining whether the tunnel frame is one of a plurality of frames from a packet; if the frame is one of a plurality of frames, reassembling the plurality of frames associated with the packet to determine an inner IP header; load balancing the packet based on the inner IP header; and applying traffic policies to the packet. The system has: a traffic interface configured to receive a tunnel frame from the traffic flow; a subscriber load balancer configured to determine whether the tunnel frame is one of a plurality of frames from a packet; at least one IP reassembly engine configured to reassemble the plurality of frames associated with the packet to determine an inner IP header; and at least one flow policy engine configured to load balance the packet based on the inner IP header; and apply traffic policies to the packet.

Abstract: An arithmetic processing apparatus and method for high speed processing of an application are provided. The arithmetic processing apparatus may include a program control unit to store operation processing information necessary for application operation in a communication channel by executing an application code, and an operation processing unit to process the application operation using the operation processing information stored in the communication channel.

Abstract: A network processor includes an arbitration device, a processing device, and a pipeline. The arbitration device receives a first packet and a second packet. The second packet includes a first control message. The pipeline includes access devices, where the access devices include first and second access devices. The pipeline, based on a clock signal, forwards the first and second packets between successive ones of the access devices. The arbitration device: sets a timer based on at least one of (i) an amount of time for data to travel between the first and second access devices, or (ii) a number of pipeline stages between the first and second access devices; adjusts a variable based on (i) the clock signal, and (ii) transmission of the first packet from the arbitration device to the pipeline; and based on the timer and the variable, schedules transmission of the second packet through the pipeline.

Abstract: A network condition prompts a hybrid device to select a new path for a packet stream. A path update may occur in response to a change in network topology or a traffic loading condition (e.g., congestion or saturation of a link in the current path). Path selections may be made at each hybrid device in the path from a source hybrid device to a destination hybrid device. A path update procedure may be dependent upon path selection procedures that are optimized for a hybrid network in which multiple hybrid devices may be utilized for a particular path. Path update for load balancing may be dependent upon whether a packet stream is elastic or non-elastic.

Abstract: Automated techniques reduce packet fragmentation in a communications network environment, including a networking environment that uses tunnels. In a tunneling environment, a tunnel endpoint evaluates whether tunnel processing for an outbound packet will cause the packet to exceed a particular size such as a message transmission unit (“MTU”) size, which in turn would lead to error processing and/or fragmentation of the packet. Similar MTU and packet mismatch may occur in a system across the virtual machine and the hypervisor, a networking stack and the physical MTU possible on the network. If so, the tunnel endpoint or the network driver simulates an error condition and returns an error message to the protocol stack that prepared the packet, so that the packet size can be reduced before the packet is actually sent on the tunnel. Existing functionality is leveraged to perform the size reduction, thus obviating the need for administrator intervention.

Abstract: Packet processing is broken into two or more stages. In particular, the network processing unit 26 performs a first stage of packet processing related to packet forwarding and packet modification, and then performs a second stage of packet processing unrelated to packet forwarding and packet modification. Example processes unrelated to packet forwarding and packet modification may include state updates on the network element, such as statistics counter updates, stateful flow tracking, IPFix processing, MAC learning, and other processes important to operation of the network element, but which do not affect the appearance of the packet (e.g. packet format) and which do not affect the forwarding decision of the packet. Once the first stage of packet processing related to packet forwarding and packet modification has been completed, the flag associated with the packet is cleared in the scoreboard, to allow the packet to be transmitted from the reorder queue.

Abstract: A power management method of a station in a wireless local area network (WLAN) system and the station supporting the method are provided. The method includes: transmitting to an access point (AP) a power save configuration (PSC) request frame for reporting that the STA intends to transition to a power save (PS) mode; receiving from the AP a PSC response frame in response to the PSC request frame; and after receiving the PSC response frame, entering the PS mode.

Abstract: The invention is related to a method of transmitting data whereby a transmission channel towards an access point (10) is shared among a plurality of users (12), the data being transmitted using the Contention Resolution Diversity Slotted ALOHA (CRDSA) method. According to the invention the number of copies (14a,14b, 14c; 16a, 16b, 16c; 18a,18b,18c) of data packet (14, 16, 18) transmitted simultaneously by a user (12) within one frame is varied.

Abstract: One method includes: (a) providing a memory storage device having a plurality of storage locations for storing information received by a plurality of sub-ports of a base port of the network device, where the memory storage device is shared among the plurality of sub-ports such that each sub-port is given access to the memory storage device at a certain phase of a system clock cycle; (b) storing a packet or a portion thereof at one of the storage locations when a sub-port that receives the packet has access to one or more of the storage locations; and (c) scrambling addresses for the memory storage locations such that a different one of the storage location is available to the sub-port of step (b) for a next write operation in a next phase when the sub-port of step (b) is given access to the memory storage device.

Abstract: An embodiment may include circuitry to permit interruption, at least in part, of a first frame from a sender to an intended recipient in favor of transmitting, at least in part, a payload of a second frame from the sender to the intended recipient, and/or processing, at least in part, one or more incoming flow control notifications. The payload may be transmitted, at least in part, to the intended recipient in one or more frame fragments. Many modifications, variations, and alternatives are possible without departing from this embodiment.

Abstract: A packet buffering device includes: a queue for temporarily holding an arriving packet; a residence time predicting unit which predicts a length of time during which the arriving packet will reside in the queue; and a packet discarding unit which discards the arriving packet when the length of time predicted by the residence time predicting unit exceeds a first reference value.

Abstract: The present invention relates to a method of sorting data packets in a multi-path network having a plurality of ports; a plurality of network links; and a plurality of network elements, each network element having at least first and second separately addressable buffers in communication with a network link and the network links interconnecting the network elements and connecting the network elements to the ports, the method comprising: sorting data packets with respect to their egress port or ports such that at a network element a first set of data packets intended for the same egress port are queued in said first buffer and at least one other data packet intended for an egress port other than the egress port of the first set of data packets is queued separately in said second buffer whereby said at least one other data packet is separated from any congestion associated with the first set of data packets.