Showing papers on "Fast packet switching published in 2004"

An arrangement and a method relating to flow of packets in communication systems

Abstract: The present invention relates to an arrangement comprising means for handling switching of data packets or flows of data packets in a communication system supporting communication of packet data to functional units or processing arrangements for performing operations on the data packets. It comprises core processing means (10) with classifying means (13) for classifying packets/packet flows and defining the processing flow sequences applicable for the packets/packet flows, distributing means (12;19;22) for distributing or switching the packets/packet flows to the appropriate functional units or processing arrangements according to the applicable flow sequence, indication providing means for indicating the current position of the respective packets/packet flows in the respective applicable processing flow sequence and means (11) for detecting or retrieving packet flow sequence information such that re-classification of already classified packets can be avoided.

Switching device, method, and computer program for efficient intrusion detection

Abstract: A switching device, method, and computer program utilizes a copy technique to detect unauthorized access to a communications network. An interface of the switching device is connected to receive an original packet and copy the original packet to create a copied packet. A processor within the switching device is operable to analyze information related to the original packet or the copied packet to detect an anomaly related to the original packet or the copied packet. The processor is further operable to cause the copied packet to be forwarded to an intrusion detection system within the communications network upon detecting the anomaly.

Packet processing in switched fabric networks

Abstract: Methods and apparatus, including computer program products, implementing techniques for forming an Advanced Switching (AS) packet by applying AS path binding information to a packet received over a Peripheral Component Interconnect-Express (PCIe) fabric according to a downstream port identifier associated with the packet, and sending the AS packet to an AS fabric. Methods and apparatus, including computer program products, implementing techniques for processing an AS packet received over an AS fabric by comparing an AS payload of the AS packet with one or more memory spaces associated with port identifiers, determining whether the AS payload comprises a base packet to be transmitted to the PCIe fabric based on the comparison, and if so, removing an AS header from the AS packet to reveal the base packet.

Quality monitoring of video over a packet network

Abstract: We consider monitoring the quality of compressed video transmitted over a packet network from the perspective of a network service provider. Our focus is on no-reference methods, which do not access the original signal, and on evaluating the impact of packet losses on quality. We present three methods to estimate mean squared error (MSE) due to packet losses directly from the video bitstream. NoParse uses only network-level measurements (like packet loss rate), QuickParse extracts the spatio-temporal extent of the impact of the loss, and FullParse extracts sequence-specific information including spatio-temporal activity and the effects of error propagation. Our simulation results with MPEG-2 video subjected to transport packet losses illustrate the performance possible using the three methods.

Fast and adaptive packet processing device and method using digest information of input packet

Abstract: A packet processing device is formed by a digest information generation unit configured to extract a plurality of prescribed bit sequences from an input packet, and generate a digest information capable of specifying at least a part of a processing to be applied to the input packet, according to values of the plurality of prescribed bit sequences; and a packet processing unit configured to process the input packet using an instruction sequence to be applied to the input packet that is obtained according to the digest information generated by the digest information generation unit, where the digest information generation unit generates the digest information with respect to a next input packet while the packet processing unit carries out a processing for one packet.

Using TCP/IP offload to accelerate packet filtering

Abstract: A method and apparatus for filtering a packet on a connection within a computing system. In one embodiment, the method includes: receiving the packet; delegating the packet to an offload unit for filtering the packet; and determining, by the offload unit, whether the connection is a delegated connection.

Optimal packet size in error-prone channel for IEEE 802.11 distributed coordination function

Abstract: With the popularity of the IEEE 802.11 based wireless network, it has become increasingly important to analyze the performance of the IEEE 802.11 protocol accurately. Throughput and delay are key measures, reflecting the performance of a wireless network. In this paper, we analyze the performance of the IEEE 802.11 distributed coordination function (DCF) in the saturated traffic condition, and consider the effects of packet size, the number of contention nodes, transmission collision probability and channel conditions. Under this analytical framework, we evaluate the impact of error-prone channel on unsuccessful transmission probability and its impact on the performance. A trade-off exists between the desire to reduce the ratio of overhead in the data packet by adopting larger packet size, and the need to reduce the packet error rate in the error-prone environment by using smaller packet length. An optimal packet size can be derived to maximize the throughput of the IEEE 802.11 DCF under various channel conditions and network configurations. To validate our analytical results, we have done extensive simulations, and the simulation results are observed to match very well with the analytical results.

Method for handling IP multicast packets in network switch

Abstract: A method of switching packets in a network switch includes the step of receiving a packet on a source port of a network switch. Thereafter, the method includes the step of determining whether the network switch has sufficient memory capacity to process the data packet; and if memory capacity is sufficient, then the method reads a selected portion of the packet to determine if the packet is to be sent to a mirrored port. If mirroring is determined, then the method sends the data packet to the mirrored port. The method also includes the step of determining whether the packet is to be sent to a remote CPU for further handling, and sending the data packet to the remote CPU if appropriate. The method additionally includes the step of determining whether the packet is a unicast packet, and if so, placing the packet on an internal communication channel within the network switch for appropriate storing and forwarding. If the packet is not a unicast packet, then the method determines if the packet is a multicast packet. If the packet is determined to be a multicast packet, then performing simultaneous lookups and switching using layer 2 lookup tables and addresses, and layer 3 lookup tables and addresses, thereby providing hybrid multicast handling of the packet.

FFPF: fairly fast packet filters

Abstract: FFPF is a network monitoring framework designed for three things: speed (handling high link rates), scalability (ability to handle multiple applications) and exibility. Multiple applications that need to access overlapping sets of packets may share their packet buffers, thus avoiding a packet copy to each individual application that needs it. In addition, context switching and copies across the kernel boundary are minimised by handling most processing in the kernel or on the network card and by memory mapping all buffers to userspace, respectively. For these reasons, FFPF has superior performance compared to existing approaches such as BSD packet lters, and especially shines when multiple monitoring applications execute simultaneously. Flexibility is achieved by allowing expressions written in different languages to be connected to form complex processing graphs (not unlike UNIX processes can be connected to create complex behaviour using pipes). Moreover, FFPF explicitly supports extensibility by allowing new functionality to be loaded at runtime. By also implementing the popular pcap packet capture library on FFPF, we have ensured backward compatibility with many existing tools, while at the same time giving the applications a significant performance boost.

Combined pipelined classification and address search method and apparatus for switching environments

Abstract: A packet switching node having a pipelined packet processing architecture processing packets received via an input port associated with the packet switching node is presented. The method performed by the apparatus includes: determining a packet frame type of the packet received; selectively extracting packet header field values specific to a packet frame type, the extracted packet header field value including packet addressing information; ascribing to the packet a preliminary action to be performed in respect of the packet; searching packet switching information tracked by the packet switching node based on extracted packet addressing information; formulating a preliminary switch response for the packet; classifying the packet into one of a plurality of packet flows; modifying the preliminary switch response in accordance with one of the preliminary action, the packet flow into which the packet was classified, and a default port action corresponding to the input port; modifying the packet header in accordance with one of the preliminary action, the packet flow, and the default port action; and processing the packet in accordance with the switch response. Advantages are derived from: pipelined processing of packets which enables short-cutting the rest of the processing for improper packets; a flexible frame type determination which is fast for well know frame types yet flexible in support of new frame types delaying obsolescence of a particular implementation; an early determination of a processing action which is successively refined by subsequent stages; a combined Layer-2 and Layer-3 network addressing search engine operating on short bit length indexed Layer-2 and Layer-3 network addresses reducing network address table storage requirements, requiring a reduced data transfer bandwidth for network address table access, a large external hashed primary network address table, and a small internal secondary network address table; an early determination of a switch response; and packet-classification-based switch response and packet header modification.

Optical packet switching

Abstract: In this talk we will describe the motivation, background and state-of-the-art in optical packet switching architectures, the underlying technology and challenges. Recent optical packet switching demonstration at data rates from 2.5 Gbps to 160 Gbps will be described.

On integrating fluid models with packet simulation

Abstract: Fluid models have been shown to he efficient and accurate in modelling large IP networks. However, unlike packet models, it is difficult to extract packet-level information from them. In this paper, we present a hybrid simulation method that maintains the performance advantage of fluid models while providing detailed packet level information for selected packet traffic flows. We propose two models to account for the interaction between background TCP traffic in a fluid network and foreground packet traffic of interest. The first assumes that the packet traffic poses a negligible load on the fluid network whereas the second accounts for the added load by transforming the packet traffic into fluid flows and solving the resulting enhanced fluid model. The first of these yields an efficient one pass solution algorithm whereas the second requires an additional pass to account for the packet traffic load. We establish the correctness of both approaches and present their implementation within ns-2. Comparisons between the hybrid models and a classical packet simulation show the two pass approach to be quite accurate and computationally efficient.

Data Link Layer Tunneling Technique for High-Speed Data in a Noisy Wireless Environment

Abstract: A data link layer tunneling technique improves the throughput of high speed data in noisy wireless environments. Recovering lost frames transmitted between a packet sending unit and a packet receiving unit in a data communications system generally comprises (a) identifying a failure to successfully receive a missed frame at the packet receiving unit; (b) establishing a logical tunnel channel at the packet receiving unit to acknowledge the next successfully received frame; (c) starting a first timer at the packet receiving unit; (c) upon receiving a tunnel establishment request from the packet receiving unit, the packet sending unit resending the missed frame on the logical tunnel channel and starting a second timer; and (d) the packet sending unit resending the missed frame a specified number of times until receiving an acknowledgement from the packet receiving unit.

Packet loss effects in passive telepresence systems

Abstract: This paper focuses on the effects of packet loss in passive bilateral telepresence systems with force feedback. The substantial impact of packet loss and subsequently applied packet processing algorithms on the energy balance and thereby stability and performance of passive telepresence systems is studied. As an example for a class of non-energy preserving packet processing algorithms, the hold last sample (HLS) strategy, is shown to generate energy. A sufficient condition for the non-passivity of HLS is derived and passifying compensation is discussed.

Apparatus and method for packet error correction

Abstract: A packet error correcting apparatus includes a retransmission request controlling unit controlling a timing of transmission of a retransmission request to a packet transmitting apparatus from a retransmission request transmitting unit according to whether an error correcting unit can restore the lost packet within a predetermined time period when loss of the packet is detected. In a packet receiving apparatus supporting both Forward Error Correction (FEC) and Automatic Repeat reQuest (ARQ), it is possible to control a timing of transmission of a retransmission request when packet loss occurs, thereby to regenerate video and/or voice with the most suitable delay time while suppressing transmission of unnecessary retransmission requests.

Packet reordering, high speed networks and transport protocol performance

Abstract: We performed end-to-end measurements of UDP/IP flows across an Internet backbone network. Using this data, we characterized the packet reordering processes seen in the network. Our results demonstrate the high prevalence of packet reordering relative to packet loss, and show a strong correlation between packet rate and reordering on the network we studied. We conclude that, given the increased parallelism in modern networks and the demands of high performance applications, new application and protocol designs should treat packet reordering on an equal footing to packet loss, and must be robust and resilient to both in order to achieve high performance

Apparatus and method for receiving control message on packet data control channel in a mobile communication system supporting packet data service

Abstract: An apparatus and method for receiving a packet data control channel in a mobile communication system that transmits packet data and has the packet data control channel for transmitting control information related to transmission of packet data are provided. A receiver receives and despreads a signal on the packet data channel and a signal on the packet data control channel, separately outputs the signals, and estimates a noise of a received signal. A signal level detector receives a noise estimation value and samples of the packet data control channel signal from the receiver, and outputs a validity signal for detecting whether information is received over the packet data control channel. A packet data control channel decoder decodes the packet data control channel signal if the validity signal received from the signal level detector is valid.

Method for providing broadcast service over packet data channel in a wireless communication system

Abstract: Disclosed is a method for receiving by a mobile station a broadcast service from a base station that transmits in the same time period data on a packet data channel and a packet data control channel corresponding to the packet data channel. In the method, the mobile station receives a broadcast service parameter message including parameters for a broadcast service, and transmits desired broadcasting data along with a packet data channel assignment request message based on the parameters. Further, the mobile station receives a packet data channel assignment message for the desired broadcast service in response to the packet data channel assignment request message. Thereafter, the mobile station decodes reception data on a packet data control channel corresponding to the assigned packet data channel to acquire control information, receives packet data on a packet data channel for the broadcast service according to the control information, and processes the received packet data as broadcast service data.

Linear Types for Packet Processing

Abstract: We present PacLang: an imperative, concurrent, linearly-typed language designed for expressing packet processing applications. PacLang’s linear type system ensures that no packet is referenced by more than one thread, but allows multiple references to a packet within a thread. We argue (i) that this property greatly simplifies compilation of high-level programs to the distributed memory architectures of modern Network Processors; and (ii) that PacLang’s type system captures that style in which imperative packet processing programs are already written. Claim (ii) is justified by means of a case-study: we describe a PacLang implementation of the IPv4 unicast packet forwarding algorithm.

Fast filtering processor for a highly integrated network device

Abstract: A method of handling data packets in a network device is disclosed. The method includes the steps of receiving an incoming packet at a port of the network device, determining a destination address for the incoming packet based on fields in the incoming packet and filtering the incoming packet through a fast filtering processor through the application of filter masks to determine at least one label of a virtual channel label and a differentiated services label. The method also includes modifying the at least one label and a classification of the incoming packet based when a result returned from a rules table indicates that the at least one label should be changed, producing an outgoing packet based on the filtering of the incoming packet; and discarding or forwarding the outgoing packet based upon the filtering.

A case for run-time adaptation in packet processing systems

Abstract: Most packet processing applications receive and process multiple types of packets. Today, the processors available within packet processing systems are allocated to packet types at design time. In this paper, we explore the benefits and challenges of adapting allocations of processors to packet types in packet processing systems. We demonstrate that, for all the applications and traces considered, run-time adaptation can reduce energy consumption by 70--80% and processor provisioning level by 40--50%. The adaptation benefits are maximized if processor allocations can be adapted at fine time-scales and if the total available processing power can be allocated to packet types in small granularities. We show that, of these two factors, allocating processing power to packet types is small granularity is more important---if the allocation granularity is large, then even a very fine adaptation time-scale yields meager benefits.

Method and apparatus for measuring one-way delay at arbitrary points in network

Abstract: Timestamps are inserted into trace packet expiration messages to identify delay in a network. A Time To Live (TTL) value in the trace packet is varied to intentionally cause an intermediate node in the network to discard the trace packet and send back the packet expiration message. The intermediate node sending the packet expiration message inserts a time value in the message indicating when the intermediate node received the trace packet. The time value is then used to determine the time required for the trace packet to reach the intermediate node.

Scalable packet digesting schemes for IP traceback

Abstract: Identifying the sources of an attack is an important task in the Internet security area. An attack could consist of a large number of packet streams generated by many compromised slaves that consume resources associated with various network elements to deny normal services or a few offending packets to disable a system. Several techniques based on probabilistic samples of transit packets have been developed, to determine the sources of large packet flows. It seems that logging of packet digests is necessary for traceback of an individual packet. A clever technique based on Bloom filters has recently been proposed to generate the audit trails for each individual packet within the network. The scheme is effective. However, the storage requirement is approximately 0.5% of the link capacity, which becomes a problem as link capacity increases. In this paper, we propose packet digesting schemes for flows and sets of packets sharing the same source and destination addresses. Compared with the individual packet digesting scheme, these schemes can achieve similar goals and are much more scalable. Simulations with real Internet traffic show that the storage requirements of our proposed schemes are one to two orders of magnitude lower.

Reliable audio-video transmission system using multi-media diversity

Abstract: A system and method for switching data packet traffic distribution across diverse transmission medium according to detected quality of service characteristics for a given data packet rate from server to client. It should be recognized that diverse medium are not interdependent with regard to fading or signal strength considerations. One mode of switching comprises switching all the data packets from transmission on a first medium to transmission over a second diverse medium. In a second mode of switching the distribution is changed according to a media-time coding mechanism in which typically data is being transmitted simultaneously across more than one of the multiple diverse medium. The data packet transmissions preferably comprise audio-video data packet streams, such as MPEG-2 streams. By way of example, the diverse transmission medium may comprise a wireless connection (i.e. WiFi) used in combination with a power-line network connection, such as within a home network.

Network authentication apparatus and network authentication system

Abstract: A network authentication apparatus has a network interface unit connected with a network and transmitting/receiving a packet, and a packet relay unit for relaying a received packet in accordance with a destination address of the received packet. It further includes a filtering processing unit for judging whether to relay the received packet to the packet relay unit or discard the packet in accordance with two or more of a destination MAC address, destination IPv6 address, source MAC address, source IPv6 address and source IPv6 interface ID contained in the received packet.

Video compression for lossy packet networks with mode switching and a dual-frame buffer

Abstract: Video codecs that use motion compensation benefit greatly from the development of algorithms for near-optimal intra/inter mode switching within a rate-distortion framework. A separate development has involved the use of multiple-frame prediction, in which more than one past reference frame is available for motion estimation. In this paper, we show that using a dual-frame buffer (one short-term frame and one long-term frame available for prediction) together with intra/inter mode switching improves the compression performance of the coder. We improve the mode-switching algorithm with the use of half-pel motion vectors. In addition, we investigate the effect of feedback in making more informed and effective mode-switching decisions. Feedback information is used to limit drift errors due to packet losses by synchronizing the long-term frame buffers of both the encoder and the decoder.

Network device architecture for centralized packet processing

Abstract: A method and system for centralized packet processing is disclosed. The method includes transferring a packet received at a port interface of a network device (1100) to an uplink interface of the network device (1110), and sending the packet to an uplink from the uplink interface (1120). The transferring and the sending are performed irrespective of a destination of the packet.

Method for performing packet flooding at wireless ad hoc network

Abstract: A method for packet re-flooding in a wireless ad hoc network for transmitting a broadcast packet from a source node to a destination node. In order to determine the respective nodes received with the broadcast packet from the source node into a certain number of power levels in accordance with the receiving power of the signal carrying the received packet, the packet re-flooding method includes the steps of setting a power level reference by which the power level increases as the receiving power increases, obtaining the receiving power of the signal carrying the packet received from the respective nodes but not the source node, determining power levels based on the power level reference and the obtained receiving power, calculating a back-off delay time in accordance with the power levels of the respective nodes but not the source node, and re-flooding the received packet when the calculated back-off delay time of the respective nodes excluding the source node expires and when the received packet is the first packet that is received. Accordingly, the possibility of having collisions due to re-flooding of the respective nodes is reduced, and also, overall power consumption of the network decreases.

A dynamically reconfigurable folded-path time delay buffer for optical packet switching

Abstract: A novel all-optical buffer based on adjustable time delay line is proposed and experimentally demonstrated. This physically compact buffer can be used in optical packet routers and is dynamically reconfigurable within nanoseconds. By using a flexible folded-path architecture design, packets are controlled to exit the buffer immediately or after a variable delay time. Furthermore, this functionality is achieved without sacrificing the scalability and compactness of the design.