Showing papers on "Fast packet switching published in 2014"

Circuit switching under the radar with REACToR

Abstract: The potential advantages of optics at high link speeds have led to significant interest in deploying optical switching technology in data-center networks. Initial efforts have focused on hybrid approaches that rely on millisecond-scale circuit switching in the core of the network, while maintaining the flexibility of electrical packet switching at the edge. Recent demonstrations of microsecond-scale optical circuit switches motivate considering circuit switching for more dynamic traffic such as that generated from a top-of-rack (ToR) switch. Based on these technology trends, we propose a prototype hybrid ToR, called REACToR, which utilizes a combination of packet switching and circuit switching to appear to end-hosts as a packet-switched ToR.In this paper, we describe a prototype REACToR control plane which synchronizes end host transmissions with end-to-end circuit assignments. This control plane can react to rapid, bursty changes in the traffic from end hosts on a time scale of 100s of microseconds, several orders of magnitude faster than previous hybrid approaches. Using the experimental data from a system of eight end hosts, we calibrate a hybrid network simulator and use this simulator to predict the performance of larger-scale hybrid networks.

Measurement and analysis on the packet delivery performance in a large-scale sensor network

Abstract: Understanding the packet delivery performance of a wireless sensor network (WSN) is critical for improving system performance and exploring future developments and applications of WSN techniques. In spite of many empirical measurements in the literature, we still lack in-depth understanding on how and to what extent different factors contribute to the overall packet losses for a complete stack of protocols at large scale. Specifically, very little is known about: 1) when, where, and under what kind of circumstances packet losses occur; 2) why packets are lost. As a step toward addressing those issues, we deploy a large-scale WSN and design a measurement system for retrieving important system metrics. We propose MAP, a step-by-step methodology to identify the losses, extract system events, and perform spatial-temporal correlation analysis by employing a carefully examined causal graph. MAP enables us to get a closer look at the root causes of packet losses in a low-power ad hoc network. This study validates some earlier conjectures on WSNs and reveals some new findings. The quantitative results also shed lights for future large-scale WSN deployments .

16.1 A 340mV-to-0.9V 20.2Tb/s source-synchronous hybrid packet/circuit-switched 16×16 network-on-chip in 22nm tri-gate CMOS

Abstract: Energy-efficient networks-on-chip (NoCs) are key enablers for exa-scale computation by shifting power budget from communication toward computation. As core counts scale into the 100s, on-chip interconnect fabrics must support increasing heterogeneity and voltage/clock domains. Synchronous NoCs require either a single clock distributed globally or clock-crossing data FIFOs between clock domains [1]. A global clock requires costly full-chip margining and significant power and area for clock distribution, while synchronizing data FIFOs add power, performance, and area overhead per clock crossing. Source-synchronous NoCs mitigate these penalties by forwarding a local clock along with each packet, but still suffer from high data storage power due to packet switching. Circuit switching removes intra-route data storage, but suffers from low network utilization due to serialized channel setup and data transfer [2]. Hybrid packet/circuit switching parallelizes these operations for higher network utilization. A 16×16 mesh, 112b data, 256 voltage/clock domain NoC with source-synchronous operation, hybrid packet/circuit-switched flow control, and ultra-low-voltage optimizations is fabricated in 22nm tri-gate CMOS [3] to enable: i) 20.2Tb/s total throughput at 0.9V, 25°C, ii) a 2.7× increase in bisection bandwidth to 2.8Tb/s and 93% reduction in circuit-switched latency at 407ps/hop through source-synchronous operation, iii) a 62% latency improvement and 55% increase in energy efficiency to 7.0Tb/s/W through circuit switching, iv) a peak energy efficiency of 18.3Tb/s/W for near-threshold operation at 430mV, 25°C, and v) ultra-low-voltage operation down to 340mV with router power scaling to 363μW.

Optical Packet and Circuit Integrated Networks and Software Defined Networking Extension

Abstract: An optical packet and circuit integrated network (OPCInet) provides both high-speed, inexpensive services and deterministic-delay, low-data-loss services according to the users’ usage scenarios, from the viewpoint of end users. From the viewpoint of network service providers, this network provides large switching capacity with low energy consumption, high flexibility, and efficient resource utilization with a simple control mechanism. This paper presents the recent progress made in the development of OPCInet and its extension to software-defined networking (SDN). We have developed OPCI nodes, which are capable of layer 3 switching from/to an Ethernet frame to/from an optical packet in the optical packet edge part and a burst-tolerant optical amplifier and an optical buffer with optical fiber delays in 100 Gbps optical packet switching part. The OPCI node achieves a packet error rate less than $10^{-4}$ and is used as a node in a lab-network that has access to the Internet. A distributed automatic control works in a control plane for the circuit switching part and in a moving boundary control between optical packet resources and circuit resources. Our optical system for packet and circuit switching works with a centralized control mechanism as well as a distributed control mechanism. We have shown a packet-based SDN system that configures mapping between IP addresses and OPCI node identifiers and switching tables according to the requests from multiple service providers via a web interface.

Systems and methods for software defined networking service function chaining

Abstract: Systems and methods are disclosed for steering packet traffic through an online network. One method includes receiving, at a switch of a network, a packet of data; classifying, by the switch, the packet to a service function chain based on fields of a packet header of the packet, the service function chain including a set of service functions to be performed on the packet; setting, by the switch, fields of the packet header to identify the service function chain classified; and transmitting, by the switch over the network, the packet to a service function device that performs a service function on the packet, the service function being in the set of service functions.

Method and Apparatus for Time Limited Messages in Packet Communications

Abstract: The present disclosure includes systems and methods for direct packet communications and store and forward packet communications including packets which have attributes which determine the lifetime of the packet contents and these lifetimes are optionally a function of the recipient. Example methods are given featuring the transmission of packets with limited lifetime, the storing and retransmission of packets to one or more recipients and confirmation of deletion of packet contents. It is also shown that cryptography may be employed to ensure that timed presentation of packet contents to recipients takes place and is authenticated by the sender.

Low-cost flow matching in software defined networks without tcams

Abstract: Various exemplary embodiments relate to a method for processing data packets by a first-hop switch in a data network, including: receiving a first data packet associated with a flow; determining whether the flow associated with the first data packet is found in a flow table in the first-hop switch; modifying the first data packet by replacing a packet header field with flow definition information; and transmitting the modified first data packet based upon the flow definition information.

Data Matching Using Flow Based Packet Data Storage

Abstract: A system for matching data using flow based packet data storage includes a communications interface and a processor. A communications interface receives a packet between a source and a destination. The processor identifies a flow between the source and the destination based on the packet. The processor determines whether some of packet data of the packet indicates a potential match to data in storage using hashes. The processor then stores the data from the most likely data match and second most likely data match without a packet header in a block of memory in the storage based on the flow.

Caching of service decisions

Abstract: Some embodiments provide a method for processing a packet received by a managed forwarding element. The method performs a series of packet classification operations based on header values of the received packet. The packet classifications operations determine a next destination of the received packet. When the series of packet classification operations specifies to send the packet to a network service that performs payload transformations on the packet, the method (1) assigns a service operation identifier to the packet that identifies the service operations for the network service to perform on the packet, (2) sends the packet to the network service with the service operation identifier, and (3) stores a cache entry for processing subsequent packets without the series of packet classification operations. The cache entry includes the assigned service operation identifier. The network service uses the assigned service operation identifier to process packets without performing its own classification operations.

Early packet loss detection and feedback

Abstract: A video encoding device (e.g., a wireless transmit/receive unit (WTRU)) may transmit an encoded frame with a frame sequence number using a transmission protocol. The video encoding device, an application on the video encoding device, and/or a protocol layer on the encoding device may detect a packet loss by receiving an error notification. The packet loss may be detected at the MAC layer. The packet loss may be signaled using spoofed packets, such as a spoofed NACK packet, a spoofed XR packet, or a spoofed ACK packet. A lost packet may be retransmitted at the MAC layer (e.g., by the encoding device or another device on the wireless path). Packet loss detection may be performed in uplink operations and/or downlink operations, and/or may be performed in video gaining applications via the cloud. The video encoding device may generate and send a second encoded frame based on the error notification.

Packet Processing in an OpenFlow Switch

Abstract: A technique for packet ingress processing and packet egress processing in an OpenFlow, OF, switch is presented. A method aspect directed to packet ingress processing comprises receiving a packet at an OF port. The packet is associated with one of multiple logical flow entities, such as logical ports, allocated to the OF port. In a next step, the logical flow entity associated with the received packet is determined. Then, metadata for the packet is tagged with an identifier for the logical flow entity associated with the packet. The tagging controls handling of the packet at egress processing. The packet handling, in turn, may include a selective dropping or passing of the packet.

Packet flow modification

Abstract: Methods, systems, and computer readable media for packet flow modification are disclosed. According to one method, the method includes receiving one or more packets associated with a packet flow. The method also includes modifying payload information in the one or more packets. The method further includes receiving a subsequent packet associated with the packet flow. The method also includes modifying transport layer or higher layer information in the subsequent packet using information associated with the modified payload information or the packet flow.

Congestion control for coded transport layers

Abstract: United States. Dept. of Defense. Assistant Secretary of Defense for Research & Engineering (United States. Air Force Contract FA8721-05-C-0002)

Congestion control enforcement in a virtualized environment

Abstract: In a data network congestion control in a virtualized environment is enforced in packet flows to and from virtual machines in a host. A hypervisor and network interface hardware in the host are trusted components. Enforcement comprises estimating congestion states in the data network attributable to respective packet flows, recognizing a new packet that belongs to one of the data packet flows, and using one or more of the trusted components and to make a determination based on the congestion states that the new packet belongs to a congestion-producing packet flow. A congestion-control policy is applied by one or more of the trusted components to the new packet responsively to the determination.

A novel SDN enabled hybrid optical packet/circuit switched data centre network: The LIGHTNESS approach

Abstract: Current over-provisioned and multi-tier data centre networks (DCN) deploy rigid control and management platforms, which are not able to accommodate the ever-growing workload driven by the increasing demand of high-performance data centre (DC) and cloud applications In response to this, the EC FP7 project LIGHTNESS (Low Latency and High Throughput Dynamic Network Infrastructures for High Performance Datacentre Interconnects) is proposing a new flattened optical DCN architecture capable of providing dynamic, programmable, and highly available DCN connectivity services while meeting the requirements of new and emerging DC and cloud applications LIGHTNESS DCN comprises all-optical switching technologies (Optical Packet Switching (OPS) and Optical Circuit Switching (OCS)) and hybrid Top-of-the-Rack (ToR) switches, controlled and operated by a Software Defined Networking (SDN) based control plane for enhanced programmability of heterogeneous network functions and protocols Harnessing the power of optics enables DCs to effectively cope with the high-performance applications' demands The programmability and flexibility provided by the SDN based control plane allow to fully exploit the benefits of the LIGHTNESS multi-technology optical DCN, while provisioning on-demand, dynamic, flexible and highly resilient network services inside DCs

Multi-layer SDN on a commercial Network Control Platform for Packet Optical Networks

Abstract: We apply a hierarchical SDN controller to demonstrate multi-layer orchestration of a commercial Optical Network Control platform. We show dynamic allocation of transport resources for bandwidth on demand and congestion control of packet services.

Scalable hybrid packet/circuit switching network architecture

Abstract: Systems and methods for packet switching in a network, including two or more hybrid packet/circuit switching network architectures configured to connect two or more core level switches in the network architectures, the network architectures being controlled and managed using a centralized software defined network (SDN) control plane. An optical ring network may be configured to interconnect the two or more hybrid network architectures, and one or more hybrid electrical/optical packet/circuit switches configured to perform switching and traffic aggregation. One or more high-speed optical interfaces and one or more low-speed electrical/optical interfaces may be configured to transmit data.

Method and apparatus for reducing redundant traffic in communication networks

Abstract: A capability is provided for reducing or even eliminating redundant traffic in cellular wireless networks. A method is provided for encoding a target packet in a manner for reducing redundancy of information in the target packet. The method includes identifying a region of the target packet that matches a region of a stored packet, removing, from the target packet, the identified region of the target packet from the target packet, and inserting, within the target packet, an encoding key comprising a hash of the stored packet. A method is provided for reconstructing a packet from an encoded packet that is encoded in a manner for reducing redundancy of information in a network. The method includes identifying an encoding key within the encoded packet, wherein the encoding key comprises a hash of a stored packet, retrieving the stored packet using the hash of the stored packet, removing the encoding key from the encoded packet, and inserting information from the stored packet within the encoded packet.

Packet rewriting apparatus, control apparatus, communication system, packet transmitting method and program

Abstract: The present invention contributes to facilitation of packet control between the tunnel end points of a tunneling protocol. A packet rewriting apparatus is located between a tunnel end point and a switch that refers to the content of the original header to determine a processing to be applied to a packet. The packet rewriting apparatus comprises: a packet rewriting rule storage unit that stores a packet rewriting rule for writing, into a predetermined area of the original header, information corresponding to a virtual network identifier included in an additional header of the packet outputted from the tunnel end point; and a packet rewriting unit that rewrites, according to the packet rewriting rule, the packet such that the information corresponding to the virtual network identifier is written into the original header of the transmitted packet.

Packet Labels For Identifying Synchronization Groups of Packets

Abstract: In one embodiment, packet labels are used to identify synchronization groups of packets, such as for, but not limited to, performing processing of packets based on their corresponding synchronization group, as the synchronization label of a packet may define a current characteristic of the packet stream which is taken into account performing processing related to the packet. A plurality of synchronization groups of packets are generated and sent, by a first packet switching device, to a second packet switching device, with each particular packet of the plurality of synchronization groups of packets including a same synchronization label in a label stack of said particular packet that is different than a synchronization label used with another of the plurality of synchronization groups of packets, and with each synchronization group of the plurality of synchronization groups of packets including a plurality of packets.

Consensus-based filter designing for wireless sensor networks with packet loss

Abstract: In wireless sensor networks (WSNs) and networked control systems (NCSs), packet loss is inevitable. If the node loses measurement data, then the estimation performance will degrade. In this paper, a novel filter based on consensus algorithm for packet loss is designed in order to increase estimation accuracy and reliability. Firstly we develop a packet loss model with a stochastic Bernoulli binary switching sequence. Then a novel filter that can tolerate packet loss is designed with consensus strategy and the orthogonal analysis approach. Finally, simulation results show that comparing with existing methods the proposed filter has superior performance.

Reducing packet reordering in flow-based networks

Abstract: The present disclosure provides for methods, network devices, and computer readable storage media for packet reordering. In one embodiment, a method includes receiving a first packet of a first flow at a network device and determining whether flow-identifying information extracted from the first packet matches an existing flow entry. The method also includes, in response to a determination that the flow-identifying information does not match any existing flow entries, generating a new transient flow entry that includes the flow-identifying information and packet-in state. The method also includes forwarding the first packet to a controller via a packet-in stream.

METHODS, SYSTEMS, AND COMPUTER READABLE MEDIA FOR PROVIDING N-NODE MULTI-SWITCH LINK AGGREGATION GROUPS (MLAGs)

Abstract: A system for providing at least one node of an n-node multi-switch link aggregation group (MLAG) includes a packet forwarding device for receiving a packet destined for at least one n-node MLAG, n being an integer greater than 2. The packet forwarding device includes a packet forwarding database for storing packet forwarding rules for the at least one n-node MLAG. The packet forwarding device further includes a processing element for forwarding, blocking forwarding of, or redirecting the packet in accordance with one of the packet forwarding rules defined for the n-node MLAG group in the packet forwarding database.

Modeling and performance analysis of OPS data center network with flow management using Express Path

Abstract: Modeling and performance analysis of optical packet switching (OPS) data center networks (DCN) with flow management is presented. Hybrid optoelectronic packet routers (HOPR) are introduced in the data center network, which combines optical switching fabric and electronic buffers with 100 Gbit/s (25 Gbit/s × 4 wavelengths) links. A novel “Express Path”, an instant wavelength path on demand, is proposed to enable the flows bypassing label processors at intermediate nodes, whereas ordinary packets are switched with deflection routing algorithm for contention resolution. This architecture thus guarantees end-to-end Quality-of-Service of traffic on express path as well as reduces the latency and the power consumption. First, the combined architecture of flows on the express paths and ordinary packet switching is modeled. Next, through the numerical simulations of serve-to-server traffic in 4-dimensional (4-D) (=up to 4096-node) torus topology, the performance in terms of the throughput, packet dropping probability and the end-to-end delay will be discussed, in comparison with ordinary-packet-only OPS architecture.

Indefinitely expandable high-capacity data switch

Abstract: A data switch for a packet data switch includes switching nodes connected to each other in an interconnecting matrix, providing a multiplicity of data paths between an incoming data or telecom port and an outgoing data or telecom port of the data switch. The interconnecting switching nodes can achieve high capacity data switching by providing a partial switching solution at each node, distributing the switching load. A switching protocol for interconnecting switching nodes allows data packets to be selectively passed from any incoming port on an interconnecting switch node to any interconnecting switching node or outgoing port connected to it. In at least one example, the switching protocol has mechanisms in it to provide for the duplicating of the contents of the data packet and pass them to multiple interconnecting switching nodes or outgoing ports.

Optimized packet classification for Software-Defined Networking

Abstract: Recent trends, such as Software-Defined Networking (SDN), introduce programmability to the network with the opportunity to dynamically route traffic based on flow descriptions. Packet header lookup is the first phase in this process. In this paper, we illustrate improved header lookup and flow rule update speeds over conventional lookup algorithms. This is achieved by performing individual packet header field searches and combining the search results. We propose that individual algorithms should be selected for packet classification based on the application requirements. Improving the network processing performance with our configurable solution will directly support the proposed capability of programmability in SDN.

System and Method for Steering Packet Streams

Abstract: In one embodiment, a system for steering an input packet stream includes a traffic splitter configured to split an input packet stream into a first packet stream and a second packet stream, and a photonic switching fabric coupled to the traffic splitter, where the photonic switching fabric is configured to switch the first packet stream. The system may also include an electrical packet switching fabric coupled to the traffic splitter, where the electrical packet switching fabric is configured to switch the second packet stream, and a traffic combiner coupled to the photonic switching fabric and to the electrical packet switching fabric, where the traffic combiner is configured to merge the first switched packet stream and the second switched packet stream to produce a first packet flow.

Packet data connectivity control with volume charged service limitation

Abstract: Packet data connectivity control with volume charged service limitation A node of a wireless communication network (150; 160; 170; 210; 220; 230; 240) receives an indication from a user equipment (10). The indication indicates that a limitation of volume charged packet data services is required for the user equipment (10). Depending on the received indication, the node (150; 160; 170; 210; 220; 230; 240) prevents transmission of packet data associated with the volume charged packet data services and allows transmission of packet data associated with one or more other packet data services. (Fig. 1)

Method and system for data set migration over a circuit switching network

Abstract: A method for data set migration, implemented in a network device is disclosed. The method includes receiving a request at a network device to migrate a data set, and sending a signaling packet from a first data center toward a first in a series of circuit switching devices to reach a second data center, where the signaling packet includes metadata containing transmission selection and characteristics of the data set, where the signaling packet is processed through the series, each of which configures its forwarding path based at least on the metadata of the signaling packet. The method continues with waiting for a period long enough to allow each of the series to configure its forwarding path, where that circuit switching device releases the configured forwarding path after the migration duration. The method continues with sending the data set following the transmission selection of the signaling packet after the period expires.

Advantages and Control of Hybrid Packet Optical-Circuit-Switched Data Center Networks

Abstract: Modern Data Center networks must perform at near 100% utilization in order to economically support the high bandwidth, highly elastic traffic patterns and data flows seen in back-end networks. Hybrid Packet-OCS networks offer excellent CAPEX and OPEX advantages but require coordination of traffic between packet and circuit fabrics. This paper provides analysis of the economic benefits and describes a practical management and control plane architecture.