公开(公告)号：US07526570B2

公开(公告)日：2009-04-28

申请号：US11097678

申请日：2005-03-31

Applicant: Mo Rooholamini ,  Randeep Kapoor ,  Ward McQueen

Inventor： Mo Rooholamini ,  Randeep Kapoor ,  Ward McQueen

IPC: C06F153/173

CPC classification number: H04L49/35 ,  H04L45/00 ,  H04L45/125 ,  H04L47/15 ,  H04L47/70 ,  H04L47/822 ,  H04L49/253

Abstract: An embodiment of the present invention may comprise a method to calculate current bandwidth usage by existing connections in a switching fabric between endpoints in a device, calculate available bandwidth for a new connection, and select a path from the multiple paths based on the bandwidth calculations. Some embodiments may be a device, comprising a port to connect the device to paths in an advanced switching fabric, a module to determine current bandwidth usage on the paths, calculate a cumulative bandwidth usage on the paths, calculate available bandwidth for a new connection, and select one of multiple paths available for the new connection.

Abstract translation: 本发明的实施例可以包括一种通过设备中的端点之间的交换结构中的现有连接来计算当前带宽使用的方法，计算新连接的可用带宽，以及基于带宽计算从多个路径中选择路径。 一些实施例可以是包括将设备连接到高级交换结构中的路径的端口的设备，用于确定路径上的当前带宽使用的模块，计算路径上的累积带宽使用量，计算新连接的可用带宽， 并选择可用于新连接的多个路径之一。

公开(公告)号：US07492765B2

公开(公告)日：2009-02-17

申请号：US11154372

申请日：2005-06-15

Applicant: Thomas Edsall ,  Claudio Desanti

Inventor： Thomas Edsall ,  Claudio Desanti

IPC: H04L12/28

CPC classification number: H04L67/1006 ,  H04L49/253 ,  H04L49/357 ,  H04L49/45 ,  H04L49/552 ,  H04L67/1002 ,  H04L67/1034

Abstract: Some embodiments of the present invention provide blade servers having blade switches that function as switches in the data plane, but do not have a Domain_ID. Control plane switching functions are performed by a fabric switch (e.g., a core switch) to which the blade server is attached. A fabric switch to which a blade switch is attached may perform address assignment functions for blades of the blade server. The blade switch preferably converts FLOGI requests to FDISC requests that are forwarded to an attached fabric switch. Some implementations provide for the multiple fabric switches, all of which are configured for communication with at least one blade switch, to establish and maintain the state of a virtual Domain_ID.

Abstract translation: 本发明的一些实施例提供具有刀片式交换机的刀片服务器，该刀片交换机用作数据平面中的交换机，但不具有Domain_ID。 控制平面切换功能由刀片服务器附接到的交换机（例如，核心交换机）执行。 连接有刀片交换机的光纤交换机可以为刀片服务器的刀片执行地址分配功能。 刀片式交换机优选地将FLOGI请求转换成FDISC请求，该FDISC请求被转发到连接的结构交换机。 一些实施方案提供了多个结构交换机，所有这些交换机被配置为与至少一个刀片交换机通信，以建立和维护虚拟Domain_ID的状态。

公开(公告)号：US20080310417A1

公开(公告)日：2008-12-18

申请号：US12196909

申请日：2008-08-22

Applicant: Robert Friskney ,  Nigel Bragg ,  Simon Parry ,  Peter Ashwood Smith ,  David Allan ,  Simon Brueckheimer

Inventor： Robert Friskney ,  Nigel Bragg ,  Simon Parry ,  Peter Ashwood Smith ,  David Allan ,  Simon Brueckheimer

IPC: H04L12/56

CPC classification number: H04L41/0823 ,  H04L12/4645 ,  H04L45/00 ,  H04L45/16 ,  H04L45/54 ,  H04L45/64 ,  H04L45/66 ,  H04L45/72 ,  H04L49/205 ,  H04L49/253 ,  H04L49/254 ,  H04L49/351 ,  H04L49/354

Abstract: The invention relates to enabling differential forwarding in address-based carrier networks such as Ethernet networks. There is described a method of and connection controller for establishing connections (76, 77) in a frame-based communications network comprising nodes (71-75 and 78) such as Ethernet switches. The connections are established by configuring, in various of the nodes, mappings for forwarding data frames, such as Ethernet frames. The mappings are from a combination of a) a destination (or source) address corresponding to a destination (or source) node (73) of the connection and b) an identifier, such as a VLAN tag. The mappings are to selected output ports of the various nodes. By using the combination of destination (or source) address AND identifier, the mappings enable data frames belonging to different connections (76, 77) to be forwarded differentially (ie forwarded on different output ports) at a node (75) despite the different connections having the same destination node. This enables flexibility in routing connections and the ability to perform traffic engineering.

Abstract translation: 本发明涉及在诸如以太网的基于地址的运营商网络中启用差分转发。 描述了在包括诸如以太网交换机的节点（71-75和78）的基于帧的通信网络中建立连接（76,77）的方法和连接控制器。 通过在各种节点中配置用于转发数据帧（例如以太网帧）的映射来建立连接。 映射来自a）与该连接的目的地（或源）节点（73）对应的目的地（或源）地址的组合，以及b）诸如VLAN标签的标识符。 映射到各个节点的选定输出端口。 通过使用目的地（或源）地址AND标识符的组合，映射使得属于不同连接（76,77）的数据帧能够在节点（75）处差分地转发（即，在不同的输出端口上转发），尽管不同的连接 具有相同的目的地节点。 这使得路由连接的灵活性和执行流量工程的能力。

公开(公告)号：US20080285450A1

公开(公告)日：2008-11-20

申请号：US12123138

申请日：2008-05-19

Applicant: Ryota MOTOBAYASHI

Inventor： Ryota MOTOBAYASHI

IPC: H04L12/26 ,  H04L12/56 ,  H04L12/28

CPC classification number: H04L49/505 ,  H04L12/5602 ,  H04L49/253 ,  H04L49/254 ,  H04L49/30 ,  H04L49/3081 ,  H04L49/503 ,  H04L2012/5632 ,  H04L2012/5681 ,  H04Q11/0478

Abstract: In an asynchronous transfer mode switch, a plurality of queues is provided for accumulating transfer cells, and a queue assignment processing section, receives a message for establishing a connection and assigns to the connection one of the queues having a forwarding rate close to a declared rate included in the message and not exceeding the declared rate.

Abstract translation: 在异步传输模式切换中，提供多个队列用于累积传送单元，并且队列分配处理部分接收用于建立连接的消息，并且向连接中分配具有接近宣告速率的转发速率的一个队列 包含在消息中，不超过申报费率。

公开(公告)号：US07453810B2

公开(公告)日：2008-11-18

申请号：US10898989

申请日：2004-07-27

Applicant: Milan Zoranovic ,  Brian McBride ,  Peter Rabinovitch

Inventor： Milan Zoranovic ,  Brian McBride ,  Peter Rabinovitch

IPC: H04L1/00 ,  H04L12/56

CPC classification number: H04L49/30 ,  H04L49/253 ,  H04L49/506

Abstract: A backpressure mechanism uses a TDM backpressure bus with each port card being assigned time slot. During its time slot, each ingress card/port writes on the bus the number of packets it transmitted to an egress ports during the last data refresh cycle. This information is read by the egress ports and used to compute current depth of the switch fabric output queues. In addition to information received from ingress cards, egress cards keep count of number of packets received from the appropriate switch fabric port and based on it estimate/calculate the current depth of the switch fabric output queue. Congestion states are calculated for all queues by comparing the queue depth with a respective threshold. Each egress card uses these congestion states to generate backpressure signals to ingress cards. Ingress card are using these signals to make decision whether to send or not traffic to destination egress card/port.

Abstract translation: 背压机构使用TDM背压总线，每个端口卡被分配时隙。 在其时隙期间，每个入口卡/端口在总线上写入在最后一次数据刷新周期期间发送到出口端口的数据包数。 此信息由出口端口读取，用于计算交换结构输出队列的当前深度。 除了从入口卡接收到的信息外，出卡卡还保留从适当的交换机端口接收到的数据包数量，并且基于它估计/计算交换矩阵输出队列的当前深度。 通过将队列深度与相应的阈值进行比较，为所有队列计算拥塞状态。 每个出口卡都使用这些拥塞状态来向入口卡生成背压信号。 入口卡正在使用这些信号来决定是否将流量发送到目的地出口卡/端口。

公开(公告)号：US20080240137A1

公开(公告)日：2008-10-02

申请号：US12138308

申请日：2008-06-12

Applicant: Stuart B. Berman

Inventor： Stuart B. Berman

IPC: H04L12/28 ,  H04L12/56

CPC classification number: H04L49/357 ,  H04L5/14 ,  H04L12/427 ,  H04L12/4637 ,  H04L45/24 ,  H04L45/30 ,  H04L45/745 ,  H04L49/101 ,  H04L49/253 ,  H04L49/254 ,  H04L49/3009 ,  H04L49/351 ,  H04L49/352 ,  H04L49/604 ,  H04Q11/0066 ,  H04Q2011/0073 ,  H04Q2011/0092

Abstract: Methods and apparatus for Fibre Channel interconnection is provided between a plurality of private loop devices through a Fibre Channel private loop device interconnect system. In the preferred embodiments, the Fibre Channel private loop device interconnect system is a fabric or an intelligent bridging hub. In one aspect of this invention, a Fibre Channel private loop device is connected to two or more Arbitrated Loops containing, or adapted to contain, one or more private loop devices. Preferably, the interconnect system includes a routing filter to filter incoming Arbitrated Loop physical addresses (ALPAs) to determine which Fibre Channel frames must attempt to be routed through the fabric. Numerous topologies of interconnect systems may be achieved. In another aspect of this invention, a method is provided for implementing a logical loop of private loop devices by segmenting the logical loop into a plurality of sets, assigning each set to a physical Arbitrated Loop and connecting the Arbitrated Loops to a Fibre Channel private loop device interconnect system. Additional methods are provided for restricting attached devices to Arbitrated Loop physical addresses within certain ranges. Additionally, methods are provided for resetting hosts, the method generally comprising the steps of detecting the addition of a storage device to a first Arbitrated Loop, and thereafter, resetting the Arbitrated Loop or loops on which a host or hosts reside on second Arbitrated Loop. Methods for operation with use of SCSI initiators generate a link service reject when no address match is found, or when an address match is found, but where no device with the destination ALPA exists on the Arbitrated Loop corresponding to the destination.

Abstract translation: 用于光纤通道互连的方法和设备通过光纤通道专用环路设备互连系统在多个私有环路设备之间提供。 在优选实施例中，光纤通道专用环路设备互连系统是结构或智能桥接集线器。 在本发明的一个方面，光纤通道专用环路设备连接到包含一个或多个私有环路设备的两个或多个仲裁环路，或者适于包含一个或多个专用环路设备。 优选地，互连系统包括用于过滤传入的仲裁环物理地址（ALPA）的路由过滤器，以确定哪些光纤通道帧必须尝试通过该结构路由。 可以实现多种互连系统的拓扑。 在本发明的另一方面，提供了一种用于通过将逻辑环路分割为多个集合来实现私有环路设备的逻辑环路的方法，将每个集合分配给物理仲裁环路并将仲裁环路连接到光纤通道专用环路 设备互连系统。 提供了额外的方法，用于将连接的设备限制在某些范围内的仲裁环物理地址。 此外，提供了用于重置主机的方法，该方法通常包括以下步骤：检测存储设备到第一仲裁环路的添加，然后重置仲裁循环或主机或主机驻留在第二仲裁环路上的循环。 使用SCSI启动器进行操作的方法在找不到地址匹配时，或者当找到地址匹配时，但在对应于目的地的仲裁环路上没有存在目的地ALPA的设备时，会生成链路服务拒绝。

公开(公告)号：US20080219249A1

公开(公告)日：2008-09-11

申请号：US12031585

申请日：2008-02-14

Applicant: Edward C. McGlaughlin

Inventor： Edward C. McGlaughlin

IPC: H04L12/50

CPC classification number: H04L49/357 ,  H04L49/101 ,  H04L49/253 ,  H04L49/30

Abstract: A method and a Fibre Channel switch element are provided that allows communication between a host system and a target device attached to a proprietary switch fabric in a network. The Fibre Channel switch element includes a first port that communicates with the target device through the proprietary switch fabric by logging on behalf of the host system so that the proprietary switch behaves as if it was directly communicating with the host system; and a second port that communicates with the host system and collects host bus adapter (“HBA”) identification information, wherein the HBA identification information is used to map the first port to the second port so that when the host system communicates with the target device the Fibre Channel switch element is transparent to the proprietary switch fabric.

Abstract translation: 提供了一种方法和光纤通道交换机元件，其允许主机系统和连接到网络中的专用交换机结构的目标设备之间的通信。 光纤通道交换机元件包括第一端口，其通过专用交换结构与目标设备进行通信，代表主机系统进行登录，使得专用交换机的行为就好像直接与主机系统通信; 以及与所述主机系统通信并收集主机总线适配器（“HBA”）识别信息的第二端口，其中所述HBA识别信息用于将所述第一端口映射到所述第二端口，使得当所述主机系统与所述目标设备通信时 光纤通道交换机元件对于专用交换矩阵是透明的。

公开(公告)号：US20070253334A1

公开(公告)日：2007-11-01

申请号：US11380271

申请日：2006-04-26

Applicant: Chetan Mehta ,  Nan Ni

Inventor： Chetan Mehta ,  Nan Ni

IPC: H04L12/26 ,  H04L12/50

CPC classification number: H04L49/552 ,  H04L49/1515 ,  H04L49/253

Abstract: A computer implemented method, data processing system, and computer usable program code are provided for routing a packet in a switch system. A set of paths through the switch system to a destination address are determined. The set of paths are analyzed to identify a path with a least used link, where the least used link leads to a next stage of the switch system. The routing to the destination address is set through the path with the least used link to form a selected path in order to improve congestion control and load balancing in response to identifying the path with a least used link.

Abstract translation: 提供计算机实现的方法，数据处理系统和计算机可用程序代码用于在交换机系统中路由分组。 确定通过交换机系统到目的地址的一组路径。 分析路径集合以识别具有最少使用链路的路径，其中最少使用的链路导致交换系统的下一级。 通过具有最少使用的链路的路径来设置到目的地地址的路由以形成选择的路径，以便响应于识别具有最少使用链路的路径来改善拥塞控制和负载平衡。

公开(公告)号：US07233596B2

公开(公告)日：2007-06-19

申请号：US11411383

申请日：2006-04-25

Applicant: Sami Tilander

Inventor： Sami Tilander

IPC: H04L12/28

CPC classification number: H04L49/3081 ,  H04L49/253 ,  H04L49/254 ,  H04L49/255 ,  H04L49/355 ,  H04L2012/5626 ,  H04L2012/563 ,  H04Q11/0478

Abstract: The present invention relates to a switching method and apparatus for performing a switching operation in a telecommunication network, wherein a side information and a service information generated based on a received call is converted into a switching technology independent identification information for identifying a start point and an end point of a connection to be switched in the switching apparatus. Thus, the physical resources of the switch are abstracted to a logical model which provides a clear interface for call control and signaling applications. Logical resources are controlled by resource managers, such that the physical resources are hidden by the switching technology independent identification information of the start point and end point of the connection. Thereby, problems with different switching technologies can be solved, and the complexity and maintenance of call control applications can be reduced, since they handle logical resources independent of the switching techniques.

Abstract translation: 本发明涉及一种用于在电信网络中执行切换操作的切换方法和装置，其中，基于所接收的呼叫生成的侧信息和服务信息被转换为独立于交换技术的识别信息，用于识别起始点和 在切换装置中要切换的连接的终点。 因此，交换机的物理资源被抽象为逻辑模型，为呼叫控制和信令应用提供了清晰的接口。 逻辑资源由资源管理器控制，使得物理资源被连接的起始点和终点的切换技术独立的识别信息隐藏。 因此，可以解决不同交换技术的问题，并且可以减少呼叫控制应用的复杂性和维护，因为它们处理独立于交换技术的逻辑资源。

公开(公告)号：US07219183B2

公开(公告)日：2007-05-15

申请号：US10827622

申请日：2004-04-19

Applicant: Christopher J. Pettey ,  Asif Khan ,  Annette Pagan ,  Richard E. Pekkala ,  Robert Haskell Utley

Inventor： Christopher J. Pettey ,  Asif Khan ,  Annette Pagan ,  Richard E. Pekkala ,  Robert Haskell Utley

IPC: G06F13/00 ,  G06F3/00 ,  G06F5/00 ,  G06F15/16 ,  G06F15/173

CPC classification number: H04L49/25 ,  H04L49/253 ,  H04L49/254 ,  H04L49/602 ,  H04L49/604

Abstract: An apparatus and method for sharing I/O devices. The apparatus has a first plurality of I/O ports, a second I/O port, and core logic. The first plurality is coupled to a plurality of operating system domains through a load-store fabric. Each of the first plurality routes transactions between the operating system domains and the switching apparatus. The second I/O port is coupled to a first shared input/output endpoint. The first shared input/output endpoint requests/completes transactions for each of the plurality of operating system domains. The core logic is coupled to the first plurality of I/O ports and the second I/O port. The core logic routes the transactions between the first plurality of I/O ports and the second I/O port and associates each of the transactions with a corresponding one of the plurality of operating system domains (OSDs) by encapsulating an OS domain header within a transaction layer packet.

Abstract translation: 一种用于共享I / O设备的设备和方法。 该装置具有第一多个I / O端口，第二I / O端口和核心逻辑。 第一个多个通过加载存储结构耦合到多个操作系统域。 在操作系统域和交换设备之间的第一多个路由事务中的每一个。 第二个I / O端口耦合到第一个共享输入/输出端点。 第一共享输入/输出端点请求/完成多个操作系统域中的每一个的事务。 核心逻辑耦合到第一组多个I / O端口和第二I / O端口。 核心逻辑逻辑路由第一多个I / O端口和第二I / O端口之间的事务，并且通过将OS域头部封装在多个操作系统域（OSD）中，将每个事务与相应的一个操作系统域（OSD）相关联 事务层数据包。