scispace - formally typeset
Search or ask a question

Showing papers on "Fast packet switching published in 2007"


Patent
29 Jun 2007
TL;DR: In this article, the authors propose a method for selectively redirecting a data packet to a port on a switching device which is associated with a corresponding network service, based on whether the data packet is to be flooded from the switching device.
Abstract: A method for selectively redirecting a data packet to a port on a switching device which is associated with a corresponding network service. In one embodiment, the data packet is redirected to an intrusion prevention service (IPS) for security analysis of the data packet. In another embodiment, the switching device performs a data link layer redirecting of the data packet based at least in part on whether the data packet is to be flooded from the switching device.

163 citations


Proceedings ArticleDOI
Dennis Abts1, Deborah Weisser2
10 Nov 2007
TL;DR: The Cray XT router packet aging algorithm is described which allows globally fair arbitration by incorporating "age" in the packet output arbitration and it is shown that an efficient aging algorithm reduces both the average packet latency and the variance in packet latency on communication-intensive benchmarks.
Abstract: As applications scale to increasingly large processor counts, the interconnection network is frequently the limiting factor in application performance. In order to achieve application scalability, the interconnect must maintain high bandwidth while minimizing variation in packet latency. As the offered load in the network increases with growing problem sizes and processor counts, so does the expected maximum packet latency in the network, directly impacting performance of applications with any synchronized communication. Age-based packet arbitration reduces the variance in packet latency as well as average latency. This paper describes the Cray XT router packet aging algorithm which allows globally fair arbitration by incorporating "age" in the packet output arbitration. We describe the parameters of the aging algorithm and how to arrive at appropriate settings. We show that an efficient aging algorithm reduces both the average packet latency and the variance in packet latency on communication-intensive benchmarks.

118 citations


Patent
11 Apr 2007
TL;DR: In this article, a general method for processing data packets in a computer network is described, which includes receiving a data packet, examining the data packet to classify the packet, including classifying the packet as a L2 or L3 packet and including determining at least one zone associated with the packet.
Abstract: Methods and apparatus for processing data packets in a computer network are described. One general method includes receiving a data packet; examining the data packet to classify the data packet including classifying the data packet as a L2 or L3 packet and including determining at least one zone associated with the packet; processing the packet in accordance with one or more policies associated with the zone; determining forwarding information associated with the data packet; and if one or more policies permit, forwarding the data packet toward an intended destination using the forwarding information.

114 citations


Patent
14 Mar 2007
TL;DR: An error correction system determines a level of error correction protection to apply to a frame of video data to be transmitted by a sending endpoint to a receiving endpoint based on the predicted impact of packet loss as well as the importance of the frame based on inter-frame dependencies, frame size, packet loss probability, historical packet loss pattern, central processing unit (CPU) load, and available network bandwidth as mentioned in this paper.
Abstract: An error correction system determines a level of error correction protection to apply to a frame of video data to be transmitted by a sending endpoint to a receiving endpoint based on the predicted impact of packet loss as well as the importance of the frame based on inter-frame dependencies, frame size, packet loss probability, historical packet loss pattern, central processing unit (CPU) load, and available network bandwidth. At the receiving endpoint, when packet loss is detected for a particular frame, the receiving endpoint will attempt to recover the frame using protection packets received along with the video data.

75 citations


Patent
14 Nov 2007
TL;DR: In this paper, the authors present methods, apparatus, computer-readable media, mechanisms, and means for instrumenting real-time customer packet traffic, which can be used to determine whether or not the performance of a packet switching device and/or network meets desired levels, especially for complying with a Service Level Agreement.
Abstract: Disclosed are, inter alia, methods, apparatus, computer-readable media, mechanisms, and means for instrumenting real-time customer packet traffic. These measured delays can be used to determine whether or not the performance of a packet switching device and/or network meets desired levels, especially for complying with a Service Level Agreement.

65 citations


Patent
11 Apr 2007
TL;DR: In this paper, the authors proposed a packet-based rate-limited radio link (RLS) protocol for packet based communications, which is applicable to packet based, rate limited radio links, such as satellite or terrestrial wireless digital communications systems.
Abstract: This invention is applicable to packet based, rate limited radio links, such as satellite or terrestrial wireless digital communications systems. These communications networks concurrently carry time-critical traffic, such as voice or multimedia, and non time- critical traffic, such as generic data traffic, between two or more communication end points. The communication end points may be connected through a number of heterogenous networks and the end to end throughput characteristics may vary over time. A first aspect of the invention concerns a method for generating packets. In other aspects the invention concerns a computer system for use in packet based communications, a computer protocol for packet based communications and a communications packet. The invention involves determining a 'time slice' packet size from the link speed and the interval of time extending between the times at which packets are selected for output from a buffer to the transmission interface. It also involves creating a network packet from frames of time-critical data generated during the interval, where the packet is synchronised to both existing timing requirements of the time-critical frames and the link speed. Then, adding non time-critical data to the network packet if its size had not exceeded the determined 'time slice' packet size.

58 citations


Patent
20 Mar 2007
TL;DR: In this paper, a receiver sends hybrid automatic repeat request (H-ARQ) feedback for a current packet and at least one previous packet, whereby an error is detected based on the HARQ feedback.
Abstract: A receiver sends hybrid automatic repeat request (H-ARQ) feedback for a current packet and at least one previous packet, whereby an error is detected based on the H-ARQ feedback. The receiver sends H-ARQ feedback with an identification of the packet or a sequence number of a packet that the receiver expects to receive next. The receiver stores a packet in a memory before combining the packet with a previously received packet, and decodes the stored packet after failing to decode a combined packet to avoid a corruption error. The receiver may set a timer when sending a NACK. If the receiver fails to receive a packet until expiration of the timer, the receiver initiates a process for recovering the packet. Each H-ARQ feedback may be associated with other attributes. Some H-ARQ processes may operate in an asynchronous mode while others in a synchronous mode in the same direction.

57 citations


Patent
30 Nov 2007
TL;DR: In this paper, the MPLS labels are determined as functions of addresses of forwarding equivalence classes (FECs) and used in forwarding of packets, without running Label Distribution Protocol (LDP) or another label publishing protocol.
Abstract: Disclosed are, inter alia, methods, apparatus, computer-readable media, mechanisms, and means for deterministically determining MPLS labels as functions of addresses of Forwarding Equivalence Classes (FECs), and using these determined labels in the forwarding of packets. By each packet switching device in a network deterministically determining the same MPLS label to use for each FEC, each packet switching device knows what label will be used by the other packet switching devices, without running Label Distribution Protocol (LDP) or another label publishing protocol. Additionally, this knowledge extends to all packet switching devices in a network, not merely neighboring packet switching devices, which allows a packet switching device to specify a stack of labels to define a desired path through the network for explicit path routing and/or fast rerouting of traffic without having to previously establish a tunnel or path using Resource Reservation Protocol (RSVP), for example.

52 citations


Journal ArticleDOI
TL;DR: An analysis that yields the packet loss statistics of the non-acknowledgement mode of the IEEE 802.15.4 standard is provided, based on a non-stationary Markov chain model.
Abstract: Transmission of the acknowledgement frame after a packet reception is optional in the IEEE 802.15.4 standard. Considering a set of sensor nodes, each of which has a packet to transmit at the beginning of an active period, we provide an analysis that yields the packet loss statistics of the non-acknowledgement mode of the standard. The analysis is based on a non-stationary Markov chain model and its accuracy is verified by ns-2 simulations

51 citations


Patent
17 Jul 2007
TL;DR: In this paper, a method and apparatus for measuring performance parameters of a Label Switch Path (LSP) using an Operation & Maintenance (OAM) performance monitoring packet in a Multi-Protocol Label Switching (MPLS) network is presented.
Abstract: Provided is a method and apparatus for measuring performance parameters of a Label Switch Path (LSP) using an Operation & Maintenance (OAM) performance monitoring packet in a Multi-Protocol Label Switching (MPLS) network, and more particularly, a method and apparatus for measuring packet loss, packet transfer delay, and jitter of an LSP set between two Label Switch Routers (LSRs) using an MPLS OAM packet. Accordingly, the present invention can overcome the limitation that existing MPLS OAM technology is dedicated to only identify malfunction of an LSP, and by also adding parameters (packet loss ratio, packet transfer delay and jitter related to SLA to a payload of an MPLS OAM packet as new required fields, provides a performance measurement method capable of measuring SLA performance parameters based on the newly added fields.

50 citations


Patent
25 May 2007
TL;DR: In this paper, the effect of packet transmission impairments, including packet loss, on the subjective quality of a video transmission where frames of data relating to the same video frame or field are permitted to span more than one packet.
Abstract: The present invention relates to the problem of estimating the effect of packet transmission impairments, including packet loss, on the subjective quality of a video transmission where frames of data relating to the same video frame or field are permitted to span more than one packet. The invention provides a method of assessing quality of a video signal comprising a sequence of video frames received via a packet switched network using a parameter which is a weighted sum of two counters where the first counter is incremented in dependence of the total number of packets in frames determined to have been received with one or more lost packets and the second counter is incremented in dependence of the number of packets following the first lost packet in each frame and the lost packet itself.

Patent
11 May 2007
TL;DR: In this paper, a method and system for wireless communication in which a plurality of media access control (MAC) packet data units (PDUs) corresponding to the plurality of wireless communication connections are received is presented.
Abstract: A method and system for wireless communication in which a plurality of media access control (“MAC”) packet data units (“PDUs”) corresponding to a plurality of wireless communication connections are received. The plurality of MAC PDUs is grouped into a relay packet and the relay packet is transmitted. Such grouping and transmission of the relay packet is performed by one or more relay nodes. The traffic control for the transmission can also be based on centralized or decentralized routing control and/or centralized or decentralized QoS control.

Proceedings ArticleDOI
Yaxuan Qi1, Bo Xu1, Fei He1, Baohua Yang1, Jianming Yu1, Jun Li1 
03 Dec 2007
TL;DR: This paper presents a design of high-performance flow-level packet processing system based on multi-core network processors, and proposes a high performance flow classification algorithm optimized for network processors and an efficient flow state management scheme leveraging memory hierarchy to support large number of concurrent flows.
Abstract: There is a growing interest in designing high-performance network devices to perform packet processing at flow level. Applications such as stateful access control, deep inspection and flow-based load balancing all require efficient flow-level packet processing. In this paper, we present a design of high-performance flow-level packet processing system based on multi-core network processors. Main contribution of this paper includes: a) A high performance flow classification algorithm optimized for network processors; b) An efficient flow state management scheme leveraging memory hierarchy to support large number of concurrent flows; c) Two hardware-optimized order-preserving strategies that preserve internal and external per-flow packet order. Experimental results show that: a) The proposed flow classification algorithm, AggreCuts, outperforms the well-known HiCuts algorithm in terms of classification rate and memory usage; b) The presented SigHash scheme can manage over 10M concurrent flow states on the Intel IXP2850 NP with extremely low collision rate; c) The performance of internal packet order-preserving scheme using SRAM queue-array is about 70% of that of external packet order-preserving scheme realized by ordered-thread execution.

Patent
19 Jan 2007
TL;DR: In this paper, a router system, method and computer program product are provided to determine whether a flow associated with a received packet is new and if it is new, at least a portion of the packet is routed or switched utilizing a second module that costs at least 10 times less than the first module.
Abstract: A router system, method and computer program product are provided. In use, it is determined whether a flow associated with a received packet is new. If it is determined that the flow associated with the packet is new, at least a portion of the packet is routed utilizing a first module. If, on the other hand, it is determined that the flow associated with the packet is not new, at least a portion of the packet is routed or switched utilizing a second module that costs at least 10 times less than the first module.

Patent
12 Jul 2007
TL;DR: In this article, a switch and a method are described that are capable of performing the following steps: (a) receiving the unicast packet which is a L3 routed packet at a port in a first Virtual Local Area Network (VLAN); routing the received packet to a loopback port in another VLAN; receiving the routed packet, which is now a L2 multicast packet from the loop back port in the second VLAN.
Abstract: A switch and a method are described herein that are capable of performing the following steps: (a) receiving the unicast packet which is a L3 routed packet at a port in a first Virtual Local Area Network (VLAN); (b) routing the received packet to a loopback port in a second VLAN; (c) receiving the routed packet which is now a L2 multicast packet from the loopback port in the second VLAN; and (d) bridging the routed packet to multiple ports in the second VLAN.

BookDOI
01 Jan 2007
TL;DR: Theoretical Performance of Input Queued Switches Using Lyapunov Methodology and the Combined Input and Crosspoint Queued Switch and Time-Space Label Switching Protocol.
Abstract: Architectures of Internet Switches and Routers Theoretical Performance of Input Queued Switches Using Lyapunov Methodology Adaptive Batched Scheduling for Packet Switching with Delays Geometry of Packet Switching: Maximal Throughput Cone Scheduling Algorithms Fabric on a Chip: A Memory Management Perspective Packet Switch with Internally-bufferer Crossbars Dual Scheduling Algorithm in a Generalized Switch: Asymptotic Optimality and Throughput Optimality The Combined Input and Crosspoint Queued Switch Time-Space Label Switching Protocol (TSL-SP) Hybrid Open Hash Tables for Network Processors

Patent
Sami Uskela1, Hannu T. Jokinen1
11 Sep 2007
TL;DR: In this paper, a packet data address is activated for a terminal for transmitting data packets between the terminal and an external network, and the packet is transmitted (207) from the node towards the destination address if the addresses are identical or the source address belongs to the set of allowed packet data addresses.
Abstract: In a packet radio network a packet data address is activated for a terminal for transmitting data packets between the terminal and an external network. Information on the activated packet data address is stored at least in the edge nodes of the network. To prevent spoofing, i.e. misrepresentation of sender data, the method and network node of the invention comprise checking (206) in the node whether the source address of the packet transmitted from the terminal is the same as the packet data address used in the transmission of the packet or does the source address belong to a set of allowed packet data addresses. The packet is transmitted (207) from the node towards the destination address only if the addresses are identical or the source address belongs to the set of allowed packet data addresses.

Journal ArticleDOI
TL;DR: This paper describes the design and implementation of a new dynamic packet filtering solution that allows users to specify several IP filters simultaneously with almost no packet loss even on highly-loaded gigabit links.
Abstract: One problem encountered while monitoring gigabit networks, is the need to filter only those packets that are interesting for a given task while ignoring the others. Popular packet filtering technologies enable users to specify complex filters but do not usually allow multiple filters to be specified. This paper describes the design and implementation of a new dynamic packet filtering solution that allows users to specify several IP filters simultaneously with almost no packet loss even on highly-loaded gigabit links. The advantage is that modern traffic monitoring applications such as P2P, IPTV, and VoIP, monitoring and lawful interception can dynamically set packet filters to efficiently discard packets into the operating system kernel according to traffic, calls, and users being monitored.

Patent
17 Aug 2007
TL;DR: In this article, a control packet is only sent with a retransmission of a data packet where the previously transmitted data packet is not completely received, and the control packet contains information related to a previously transmitted packet.
Abstract: A method for wireless communications where a control packet is not transmitted for all transmissions of a new data packet. A control packet is only sent with a retransmission of a data packet where the previously transmitted data packet is not completely received. The control packet contains information related to a previously transmitted data packet. The previously transmitted data packet and the retransmission data packet are derived from common data. The common data is derived based on the information related to the previously transmitted data packet, wherein the previously transmitted data packet and the retransmission data packet are associated with a series of data packets.

Patent
02 Mar 2007
TL;DR: In this article, a method and apparatus for classifying packets, e.g., at wire speed, is described, where the method receives a packet and processes the packet through a hardware-based packet classifier having at least one evolving rule.
Abstract: A method and apparatus for classifying packets, e.g., at wire speed are disclosed. The method receives a packet and processes the packet through a hardware-based packet classifier having at least one evolving rule. The method then processes the packet through a software-based packet classifier if the hardware-based packet classifier is unable to classify the packet. In one embodiment, the at least one evolving rule is continuously modified in accordance with learned traffic characteristics of the received packets.

Journal ArticleDOI
TL;DR: This paper models a packet scheduling and queuing system for a general input process in linear time-invariant systems and proposes an energy-efficient packet scheduling policy that takes the correlation into account.
Abstract: In this paper, we study the problem of packet scheduling in a wireless environment with the objective of minimizing the average transmission energy expenditure under individual packet delay constraints. Most past studies assumed that the input arrivals followed a Poisson process or were statistically independent. However, traffic from a real source typically has strong time correlation. We model a packet scheduling and queuing system for a general input process in linear time-invariant systems. We propose an energy-efficient packet scheduling policy that takes the correlation into account. Meanwhile, a slower transmission rate implies that packets stay in the transmitter for a longer time, which may result in unexpected transmitter overload and buffer overflow. We derive the upper bounds of the maximum transmission rate under an overload probability and the upper bounds of the required buffer size under a packet drop rate. Simulation results show that the proposed scheduler improves up to 15 percent in energy savings compared with the policies that assume statistically independent input. Evaluation of the bounds in providing QoS control shows that both deadline misses and packet drops can be effectively bounded by a predefined constraint.

Patent
27 Jun 2007
TL;DR: In this paper, the packet switch operating methods and packet switches activate the particular tunnel indicated by the received control packet on the packet switches, which is a signal that a particular one of the tunnels is active on the other packet switch.
Abstract: Packet switch operating methods and packet switches receive, at a packet switch, a control packet from another packet switch. The packet switch and the other packet switch are coupled together by two or more tunnels. The control packet indicates that a particular one of the tunnels is active on the other packet switch. In response, the packet switch operating methods and packet switches activate the particular tunnel indicated by the received control packet on the packet switch.

Patent
26 Jun 2007
TL;DR: In this paper, a QoS-aware service flow mapping in an access network is presented, where a message is received from an access device at a gateway in the access network, and the message includes a traffic flow specification.
Abstract: In one embodiment, techniques provide QoS-aware service flow mapping in an access network. A message is received from an access device at a gateway in the access network. The message includes a traffic flow specification. The traffic flow specification may include packet filter information, which is used to install a packet filter to route traffic to the access device. The gateway creates a session and associates the packet filter with it. When an incoming packet is received at the network device, the packet is matched to the packet filter. The incoming packet is then sent to the access device for the session. The traffic flow specification may also specify QoS parameters that are desired. The QoS parameters may then be applied to the packet sent to the access device. The gateway and access device may negotiate to determine a QoS to apply.

Proceedings ArticleDOI
26 Mar 2007
TL;DR: This paper uses a validated Petri net model of a commercial network processor, Intel IXP 2400, to determine the extent of packet reordering for IPv4 forwarding application and proposes an alternative scheme, packet sort, which guarantees complete packet ordering while achieving a throughput of 2.5 Gbps.
Abstract: Network processors today consist of multiple parallel processors (micro engines) with support for multiple threads to exploit packet level parallelism inherent in network workloads. With such concurrency, packet ordering at the output of the network processor cannot be guaranteed. This paper studies the effect of concurrency in network processors on packet ordering. We use a validated Petri net model of a commercial network processor, Intel IXP 2400, to determine the extent of packet reordering for IPv4 forwarding application. Our study indicates that in addition to the parallel processing in the network processor, the allocation scheme for the transmit buffer also adversely impacts packet ordering. In particular, our results reveal that these packet reordering results in a packet retransmission rate of up to 61%. We explore different transmit buffer allocation schemes namely, contiguous, strided, local, and global which reduces the packet retransmission to 24%. We propose an alternative scheme, packet sort, which guarantees complete packet ordering while achieving a throughput of 2.5 Gbps. Further, packet sort outperforms the in-built packet ordering schemes in the IXP processor by up to 35%.

Proceedings ArticleDOI
16 Oct 2007
TL;DR: A scheme is proposed that will correct error if occurs at the same bit location of the erroneous copies of the packet combining scheme, which when combined with ARQ protocol will offer higher throughput.
Abstract: Packet combining scheme is a well defined simple error correction scheme with erroneous copies at the receiver. It offers higher throughput combined with ARQ protocols in networks than that of basic ARQ protocols. But packet combining scheme fails to correct errors when occur in the same bit locations of two erroneous copies. In the present work, we propose a scheme that will correct error if occurs at the same bit location of the erroneous copies. The proposed scheme when combined with ARQ protocol will offer higher throughput.

Proceedings ArticleDOI
03 Sep 2007
TL;DR: This work dis-cusses trade-offs on using circuit and packet switching, arguing in favor of the former with fixed packet size and proposes and justifies the replacement of virtual channels by replicated channels, based on the abundance of wires expected in current and future deep sub-micron technologies.
Abstract: A considerable number of NoC designs are available, focusing on different aspects of this type of communication infrastructure. Example of relevant aspects considered during NoC design are quality-of-service achievement, the choice of synchronization method to employ between routers, power consumption reduction and application modules mapping. However, some design choices are common to many if not most NoC proposals: wormhole packet switching and the use of virtual channels. This work dis-cusses trade-offs on using circuit and packet switching, arguing in favor of the former with fixed packet size. Next, it proposes and justifies the replacement of virtual channels by replicated channels, based on the abundance of wires expected in current and future deep sub-micron technologies. Finally, the work proposes the use of a session layer coupled to circuit switching. Results point out to reduced latency and router area, leading to a router architecture adapted for high-performance NoCs.

Journal ArticleDOI
TL;DR: A novel optical packet switching buffer architecture that is composed of multiple building-block modules, allowing for a large degree of scalability and supporting independent and simultaneous read and write processes without packet rejection or misordering is introduced.
Abstract: We introduce a novel optical packet switching buffer architecture that is composed of multiple building-block modules, allowing for a large degree of scalability. The buffer supports independent and simultaneous read and write processes without packet rejection or misordering and can be considered a fully functional packet buffer. It can easily be programmed to support two prioritization schemes: first-in first-out (FIFO) and last-in first-out (LIFO). Because the system leverages semiconductor optical amplifiers as switching elements, wideband packets can be routed transparently. The operation of the system is discussed with illustrative packet sequences, which are then verified on an actual implementation composed of conventional fiber-optic componentry

Patent
13 Sep 2007
TL;DR: In this paper, a packet buffering scheme for hop-by-hop retransmission in a multi-hop relay system is presented, where a first buffer buffer buffers a user packet until the user packet is successfully transmitted to a next node, and a second buffer buffers the user packets until the successful transmission to an MS.
Abstract: A packet buffering apparatus and method in a multi-hop relay system supporting hop-by-hop retransmission are provided. In the buffering apparatus and method, a first buffer buffers a user packet until the user packet is successfully transmitted to a next node, and a second buffer buffers the user packet until the user packet is successfully transmitted to an MS, after the user packet is successfully transmitted to the next node. Accordingly, time delays and transmission costs are reduced.

Patent
22 Mar 2007
TL;DR: In this paper, a method for handling retransmissions used in a transmitter of a wireless communications system includes initiating a Hybrid Automatic Repeat Request process (302), transmitting a packet with a first sequence number (304), and transmitting the packet with another sequence number and marking the packet as a new packet when a transmission number of the packet in the first sequence of numbers reaches a configured maximum number of transmissions (306).
Abstract: A method for handling retransmissions used in a transmitter of a wireless communications system includes initiating a Hybrid Automatic Repeat Request process (302), transmitting a packet with a first sequence number (304), and transmitting the packet with a second sequence number and marking the packet as a new packet when a transmission number of the packet with the first sequence number reaches a configured maximum number of transmissions (306).

Journal ArticleDOI
TL;DR: A useful framework for the cross-layer design and analysis of wireless networks where ARQ and AMC schemes are employed, which tries to satisfy the required packet loss probability by each user and minimize the average packet transmission error rate.
Abstract: In this paper, we propose a useful framework for the cross-layer design and analysis of wireless networks where ARQ (automatic repeat reQuest) and AMC (adaptive modulation and coding) schemes are employed. To capture the joint effect of the packet transmission error rate at the PHY layer and the packet loss probability at the MAC layer, we introduce the effective bandwidth function of the packet service process. Base on queueing analysis with this effective bandwidth function, our cross-layer design tries to satisfy the required packet loss probability by each user and minimize the average packet transmission error rate. Numerical examples are provided to show the usefulness and characteristics of our framework.