High speed pipeline architecture with high update rate of associated memories
    1.
    发明申请
    High speed pipeline architecture with high update rate of associated memories 审中-公开
    高速流水线架构具有较高的相关记忆率

    公开(公告)号:US20050038908A1

    公开(公告)日:2005-02-17

    申请号:US10916508

    申请日:2004-08-12

    CPC分类号: G06F15/8053

    摘要: A high speed pipeline architecture comprising a plurality of successive processing stages or pipestages (Stage 1-n) coupled in cascade to forward user packets of data. Each pipestage is adapted to be coupled to at least one memory unit (Data 1-n) storing a forwarding table. The memory unit is preferably of the RDRAM memory technology, and the forwarding table preferably an IP packet forwarding table. A data manager (DM) is used to update the memory units by transferring maintenance data through the pipestages. Since the maintenance actions on the memory units are passed through the same pipeline that forwards the user packets, these operations are mutually ordered and high update rates on the memory units can be achieved without losing any incoming user packets.

    摘要翻译: 一种高速流水线架构,包括多个连续的处理级或分段(阶段1-n)级联耦合以转发用户数据分组。 每个管道适于耦合到存储转发表的至少一个存储器单元(数据1-n)。 存储器单元优选地是RDRAM存储器技术,并且转发表优选地是IP分组转发表。 数据管理器(DM)用于通过传送维护数据来更新存储单元。 由于对存储器单元的维护动作通过转发用户分组的相同流水线,这些操作是相互排序的,并且可以在不丢失任何传入的用户分组的情况下实现存储器单元上的高更新速率。

    Layer-2 network with virtual private LAN service
    2.
    发明申请
    Layer-2 network with virtual private LAN service 失效
    具有虚拟专用LAN服务的二层网络

    公开(公告)号:US20050220077A1

    公开(公告)日:2005-10-06

    申请号:US11098689

    申请日:2005-04-05

    IPC分类号: H04L12/46 H04L12/56

    CPC分类号: H04L12/4641

    摘要: A method to provide a loop-free telecommunication network comprising end-users (U1, U2) interconnected through one or more Metropolitan Area Network (MAN) and/or Wide Area Network (WAN) providing Virtual Private Local Area Network (LAN) Service (VPLS) and possible geographically dispersed Layer-2 networks (K, L). To prevent the VPLS-networks (VPLS1, VPLS2) to create loops, the method comprises the step of using a predetermined protocol, e.g. the Rapid Spanning Tree Protocol (RSTP) as defined in the standard IEEE 802.1D-2003. The method further comprises the steps of grouping internal node ports of each node of a VPLS-network into a port arrangement (mPorts) in order to model a virtual LAN inside the VPLS-network, of calculating, for each port arrangement, the sum of weight factors or port Path Cost towards a root bridge, of selecting as primary node the node having an external node port with the lowest port path cost, and of disabling (cutting) the paths of the other external node ports towards the root bridge. In case two or more nodes of a VPLS-network have an identical port path cost, the method takes into account the node number or node ID for selecting the primary node.

    摘要翻译: 一种提供无环路电信网络的方法,包括通过提供虚拟专用局域网(LAN)的一个或多个城域网(MAN)和/或广域网(WAN)互连的终端用户(U 1,U 2) 服务(VPLS)和可能​​的地理分散的二层网络(K,L)。 为了防止VPLS网络(VPLS1,VPLS2)创建环路,该方法包括使用预定协议的步骤,例如, 标准IEEE 802.1D-2003中定义的快速生成树协议(RSTP)。 该方法还包括以下步骤:将VPLS网络的每个节点的内部节点端口分组成端口布置(mPorts),以便对VPLS网络内部的虚拟LAN进行建模,以计算每个端口布置的总和 权重因子或端口路径根桥的成本,选择具有最低端口路径开销的外部节点端口的节点作为主节点,以及禁止(切割)到根网桥的其他外部节点端口的路径。 如果VPLS网络的两个或多个节点具有相同的端口路径开销,则该方法考虑到用于选择主节点的节点号或节点ID。