Showing papers by "Arista Networks published in 2013"

System and method for sharing vxlan table information with a network controller

Abstract: A method and system for sharing host entries between virtual tunnel endpoints (VTEPs). The method includes making a first determination that an NLHE is present in a locally learned host entry table on a VTEP where the NHLE is associated with a first timestamp, and making a second determination that a first entry corresponding to the NHLE is present in a Host-Specific Portion of Global Host Entry Table (HSPT) on the VTEP, where the first entry is associated with a second timestamp. Based on the second determination, making a third determination, using the timestamps, that the NHLE is more recent than the first entry and based on the third determination updating an active forwarding table on the first VTEP to include a second entry corresponding to the NHLE and to remove the first entry and sending the NHLE to a VXLAN controller operatively connected to the VTEP.

Media Access Control and Resource Allocation: For Next Generation Passive Optical Networks

Abstract: This book focuses on various Passive optical networks (PONs) types, including currently deployed Ethernet PON (EPON) and Gigabit PON (GPON) as well as next generation WDM PON and OFDM PON. Also this book examines the integrated optical and wireless access networks. Concentrating on two issues in these networks: media access control (MAC) and resource allocation. These two problems can greatly affect performances of PONs such as network resource utilization and QoS of end users. Finally this book will discuss various solutions to address the MAC and resource allocation issues in various PON networks.

Method and system for managing switch workloads in a cluster

Abstract: In general, embodiments of the invention relate to a switch that includes a processor, ports, and memory that includes instructions, which when executed by the processor perform a method. The method includes obtaining, via a port, a global task-server mapping from a first server, detecting that one of the ports is congested. The method further includes, based on the detecting, identifying a task associated with the one of the ports using the global-task server mapping, generating a task listing based on the identifying, generating an alert including the task listing, and transmitting the alert to an administrator.

Standards-compliant EPON sleep control for energy efficiency: Design and analysis

Abstract: Owing to environmental concerns, reducing energy consumption of optical access networks has become an important problem for network designers. This paper focuses on reducing energy consumption of optical network units (ONUs) in an Ethernet passive optical network (EPON). In an EPON, the optical line terminal (OLT) located at the central office broadcasts the downstream traffic to all ONUs, each of which checks all arriving downstream packets so as to obtain the downstream packets destined to itself. Thus, receivers at ONUs always have to stay in the awake status and consume a large amount of energy. To address the downstream challenge, we propose a novel sleep control scheme that can efficiently put ONU receivers into sleep without modifying the standardized EPON media access control protocol. The proposed scheme contains two main parts: downstream traffic scheduling rules at the OLT and sleep control schemes at ONUs. By letting ONUs be aware of the downstream traffic scheduling rules, ONUs can infer their own downstream queue status and switch into the sleep status properly; by letting the OLT know the sleep control scheme implemented at ONUs, the OLT can accurately infer the sleep status of ONUs and buffer traffic of asleep ONUs accordingly. We also theoretically analyze the impacts of different parameters in the sleep control scheme on the delay and energy-saving performances by using semi-Markov chains. It is shown that, with proper settings of sleep control parameters, the proposed scheme can save as much as 50% of the ONU receiver energy.

System and method for determining a cause of network congestion

Abstract: A method and apparatus of a device that determines a cause and effect of congestion in this device is described. In an exemplary embodiment, the device measures a queue group occupancy of a queue group for a port in the device, where the queue group stores a plurality of packets to be communicated through that port. In addition, the device determines if the measurement indicates a potential congestion of the queue group, where the congestion prevents a packet from being communicated within a time period. If potential congestion exists on that queue group, the device further gathers information regarding packets to be transmitted through that port. For example, the device can gather statistics packets that are stored in the queue group and/or new enqueue packets.

Method and system for using json with a cli for managing network devices

Abstract: A method for executing a command line interface (CLI) command by receiving a hyper text transport protocol (HTTP) comprising the CLI command from a controller, extracting the CLI command from the HTTP request, and executing, by a network device, the CLI command to generate a populated model comprising results generated from executing the CLI command. The method also executes the CLI command by converting the populated model into a JSON format using a JSON engine to obtain a JSON result; encapsulating the JSON result in a JSON Remote Procedure Call (RPC), and transmitting the JSON RPC as a HTTP response to the controller.

Method and system for multichassis link aggregation in-service software update

Abstract: A method for performing an in-service software update in a MLAG domain. The method includes restarting the first switch using a second version of software, detecting by a second switch that the first switch is restarting and, in response to the detection, SSO. After restarting the first switch, prior to the first switch performing graceful reinsertion into the MLAG domain, setting all non-peer ports on the first switch to an error-disabled state and selecting a common MLAG protocol version supported by the first switch and the second switch and performing graceful reinsertion, which includes reestablishing a peering relationship between the first switch and the second switch using the common MLAG protocol, and after reestablishing the peering relationship, synchronizing a control plane state of the first switch with the control plane state of the second switch and setting all non-peer ports on the first switch to an active state.

System And Method For Determining An Effect Of Network Congestion

Abstract: A method and apparatus of a device that determines a cause and effect of congestion in this device is described. The device determines an effect of congestion in the device. The device measures a queue group occupancy of a queue group for a port in the device, where the queue group stores a plurality of packets to be communicated through that port. The device further determines if congestion exists on that queue group using the measurement, where the congestion prevents a packet of the plurality of packets from being communicated within a time period. If the congestion exists on that queue group, the device additionally gathers information regarding packets to be transmitted through that port. For example, the device can gather statistics packets that are stored in the queue group and/or new enqueue packets.

Method and system for active fabric management using unicast reachability monitoring

Abstract: A method for active network fabric management. The method includes receiving a probe packet by a termination beacon, where the probe packet is associated with a stream, the stream is identified using an origin beacon identification (ID) for an origin beacon, a stream source IP address, a stream destination IP address, an L2 origin interface, and a TTL value or an IP Hop value. The method further includes generating, after receiving the probe packet and after the expiration of a probe rate request (PRR) refresh timer, a rate control packet (RCP) by the termination beacon where the RCP includes a PRR for the stream, and sending the RCP to the origin beacon using an origin beacon IP address, where the origin beacon IP address is different than the stream source IP address.

Method and system for routing packets

Abstract: A system for routing packets that includes leaf network devices, spine network devices, and a border gateway protocol controller to perform a method for routing packets in a network. The method includes receiving packets at a leaf device and, using the destination IP address of the packet to determine to which spine network device the packet is to be sent. The spine network devices each include a non-overlapping portion of a routing table. The spine network devices include functionality to determine a route for the packet based on its destination IP address, to determine to which leaf network device the packet is to be sent, and to send the packet to the discovered leaf network device. The leaf network device that receives the packet includes functionality to, based on the destination MAC address of the packet, determine out of which leaf network device interface to send the packet.

Method and system for auto-provisioning network devices in a data center using network device location in network topology

Abstract: A non-transitory computer readable medium includes instructions, which, when executed by a processor, perform a method on a network device. The method includes receiving, from a configuration server, a master configuration script that includes an instruction set, a network topology for network devices, and a dictionary. The dictionary includes network device specific configuration scripts for the network devices. The method also includes executing the instruction set on the network device to configure the network device. Executing the instruction set includes obtaining link layer discovery protocol (LLDP) information for the network device, determining a most common interface (MCI) connected to the network device using the LLDP information, determining a network device identity using the MCI, obtaining, from the dictionary, a network device specific configuration script for the network device based on the network device identity, and executing the network device specific configuration script to configure the network device.

System and method for device failure notification

Abstract: A method and apparatus of a device that notifies another device of a failed device is described. In an exemplary embodiment, a network element detects that a first device is unavailable, where the network element couples the first device to the second device. In response to detecting that the first device is unavailable, the network element configures a proxy for the first device. The network element additionally receives network data that is destined for the first device, where the second device originated the network data. If the proxy can process the network data, the network element transmits a response to the second device from the proxy, where the response indicates that the first device is unavailable, where the first response includes an address of the first device. If the proxy cannot process the network data, the network element drops the network data.

System and method for access control list conversion

Abstract: A method and apparatus of a device that converts an ordered ACL to an unordered ACL is described. In an exemplary embodiment, a network element receives an ordered access control list that includes a set of ordered rules, where each of the ordered rules includes an address range and an action. Furthermore, if two address ranges for two of the ordered rules overlap, a corresponding action of a preceding rule overrules a corresponding action of a subsequent rule for an overlapping range of addresses. The network element further converts the ordered access control list to an unordered access control list, where the unordered access control list includes a plurality of independent rules and each of the plurality of independent rules include a corresponding address range that is non-overlapping with other address ranges of the plurality of independent rules. In addition, the network element stores the unordered access control list, where the unordered access control list is used by the network element to make forwarding decisions for processing network data.

Method and system for zero touch replacement of network infrastructure

Abstract: A method for configuring a switch. The method includes receiving a configuration request from a switch, where the configuration request includes switch neighbor information (SNI) for the switch and a Media Access Control (MAC) address for the switch, identifying a replacement entry including a second MAC address and the SNI. The method further includes, based on the identification obtaining configuration information associated with the replacement entry, where the configuration information specifies a configuration of a second switch associated with the second MAC address, generating a configuration script using the configuration information and sending the configuration script to the switch, where the configuration script is executed by the switch to configure the switch.

Media Access Control and Resource Allocation in GPON

Abstract: By taking advantage of the huge bandwidth provision of wavelength channels, wavelength division multiplexing (WDM) passive optical network (PON) has become a promising future-proof access network technology to meet the rapidly increasing traffic demands resulted from the popularization of Internet and sprouting of bandwidth-demanding applications [7, 126]. In WDM PON, a number of wavelengths are used to provision bandwidth to ONUs in both upstream and downstream, rather than sharing a single wavelength in each stream in TDM PON. Since ONUs may share the usage of a number of wavelengths, a MAC layer control protocol is needed to coordinate the traffic transmission such that the collision between traffic from different ONUs can be avoided.

System and method for slow link flap detection

Abstract: A method and apparatus of a device that monitors a link for a slow link flap event is described. In an exemplary embodiment, a device detects a link flap in a current time interval of a link that couples a pair of devices. In addition, the current time interval is one of a plurality of time intervals that are used to monitor the link for a slow link flap. Furthermore, a slow link flap event results from detecting a maximum number of link flap violations over the plurality of time intervals. The device additionally increments a number of detected link flaps for the current time interval. If the number of detected link flaps for the current time interval is greater than a maximum number of slow link flap violations, the device marks the current time interval as a possible slow link flap interval. In addition, if the total number of intervals among the current time interval and one or more preceding time intervals, which are marked as possible slow flap intervals, equals the maximum number of slow flap intervals, the device brings the link down.

Video Processing in an FPGA-Enabled Ethernet Switch

Abstract: Carriage of uncompressed high-definition video using Internet protocol (IP) holds great potential for enhancing the flexibility of broadcast plants while reducing the number of cables required through aggregation of signals using statistical multiplexing. The broadcast industry is just beginning to determine the appropriate architectures to best use professional video-over-IP capabilities. The Arista 7124FX application switch is a 10 Gbit Ethernet data center-class Ethernet switch that also supports application acceleration through the use of an onboard field programmable gate array (FPGA) without adding network jitter. A proof of concept has been developed to show how an FPGA-enabled switch can perform frame-accurate video stream switching of SMPTE ST 2022-6:2012 realtime protocol flows.

Media Access Control and Resource Allocation in EPON and 10G-EPON

Abstract: IEEE802.3ah standardized the MultiPoint Control Protocol (MPCP) as the MAC layer control protocol for EPON [138], and IEEE802.3av specified MAC layer protocols for 10G EPON. For the MAC layer and layers above, in order to achieve backward compatibility such that network operators are encouraged to upgrade their services, 10G-EPON keeps the EPON frame format, MAC layer, MAC control layer, and all the layers above almost unchanged from 1G-EPON [104, 131]. This further implies that similar network management system (NMS), PON-layer operations, administrations, and maintenance (OAM) system, and dynamic bandwidth allocation (DBA) used in EPON can be applied to 10G-EPON as well.

Hybrid Optical and Wireless Access

Abstract: Optical access networking provisions high bandwidth in order to meet increasing traffic demands of end users. However, the optical solution lacks mobility, and thus limits the last mile penetration. By provisioning mobility, a rather desirable feature, to optical access, hybrid optical and wireless networks are becoming an attractive solution for wireline access network operators to expand their subscriber base [74, 99–101, 128].

Overview of Broadband Access Technologies

Abstract: Over the past decade of unprecedented advances in information and communications technology (ICT), a variety of bandwidth-demanding applications, including Internet access, e-mail, e-commerce, voice over internet protocol (VoIP), video conferencing, Internet Protocol Television (IPTV), and online gaming, have emerged and been rapidly deployed in the network. As the Internet traffic grows, it is becoming urgent to efficiently manage, move, and store increasing amount of mission-critical information, thus accelerating the demand for data storage systems. Consequently, the traffic in both public and private communication networks has experienced dramatic growth. As reported by Cisco’s visual networking index, the Internet traffic in 2011 has reached around 28 k petabytes per month while it was less than 200 petabytes per month in 2001 [1]. According to the sixth annual Cisco(R) Visual Networking Index (VNI) Forecast (2011–2016) [2], global IP traffic has increased eightfold over the past 5 years, and will increase 4-fold over the next 5 years. In 2016, global IP traffic will reach 1.3 zettabytes per year or 109.5 exabytes per month. Overall, IP traffic will grow at a compound annual growth rate (CAGR) of 29% from 2011 to 2016. Therefore, to meet the challenge caused by the increased network traffic, telecommunication service providers and enterprises are driven to enhance their networks in providing enough bandwidth for new arising services.

Green Passive Optical Networks

Abstract: The future sees a clear trend of data rate increase in both wireless and wireline broadband access. These access networks may experience a dramatic increase of energy consumption in provisioning higher bandwidth as well as for other reasons [8, 28, 61]. For example, to guarantee a sufficient signal-to-noise ratio (SNR) at the receiver side for accurate recovery of high data rate signals, advanced transmitters with high transmitting signal power and advanced modulation schemes are required, thus consequently resulting in high energy consumption of the devices. Also, to provision a higher data rate, more power will be consumed by electronic circuits in network devices to facilitate fast data processing. Besides, high-speed data processing incurs fast heat buildup and high heat dissipation that further incurs high energy consumption for cooling. It is estimated that the access network energy consumption increases linearly with the provisioned data rate. It has also been reported that the LTE base station (BS) consumes more energy in data processing than the 3G UMTS systems [108, 119], and the 10 Gb/s Ethernet PON (EPON) system consumes much more energy than the 1 Gb/s EPON system. This chapter focuses on green passive optical networks, the wireline aspect discoursed in great details on how to green broadband access networks [30].