公开(公告)号：US06956852B1

公开(公告)日：2005-10-18

申请号：US09339963

申请日：1999-06-25

申请人： Andreas V. Bechtolsheim ,  Howard M. Frazier ,  Thomas J. Edsall

发明人： Andreas V. Bechtolsheim ,  Howard M. Frazier ,  Thomas J. Edsall

IPC分类号： H04L12/00 ,  H04L12/413 ,  H04L12/46

CPC分类号： H04L12/4641 ,  H04L12/4633

摘要： A high speed communications interface divides data into a plurality of lanes, each lane encoded with clocking information, serialized, and sent to an interface. During cycles when there is no available data to send, IDLE_EVEN and IDLE_ODD cells are sent on alternating cycles. Data is transmitted by sending a header which spans all lanes and includes a START symbol. The final data transaction includes a Frame Check Sequence (FCS) which operates over the entire header and data. The packet is terminated by an END symbol, which is sent after the final data, and the remainder of the lanes are padded with IDLE_EVEN, IDLE_ODD, IDLE_EVEN_BUSY, or IDLE_ODD_BUSY cycles. The interface has a variable clock rate.

摘要翻译： 高速通信接口将数据划分成多个通道，每个通道用时钟信息编码，串行化并发送到接口。 在没有可用数据发送的周期期间，IDLE_EVEN和IDLE_ODD单元是以交替周期发送的。 通过发送跨越所有通道的头部并包括START符号来发送数据。 最终数据事务包括在整个报头和数据上操作的帧校验序列（FCS）。 数据包由END符号终止，该符号在最终数据之后发送，剩余的通道以IDLE_EVEN，IDLE_ODD，IDLE_EVEN_BUSY或IDLE_ODD_BUSY循环填充。 该接口具有可变的时钟速率。

公开(公告)号：US07573916B1

公开(公告)日：2009-08-11

申请号：US10804349

申请日：2004-03-17

申请人： Andreas V. Bechtolsheim ,  Howard M. Frazier ,  Thomas J. Edsall

发明人： Andreas V. Bechtolsheim ,  Howard M. Frazier ,  Thomas J. Edsall

IPC分类号： H04J3/02 ,  H04L12/56 ,  H04L12/66 ,  H04Q11/00

CPC分类号： H04L12/4641 ,  H04L12/4633

摘要： A high speed communications interface divides data into a plurality of lanes, each lane encoded with clocking information, serialized, and sent to an interface. During cycles when there is no available data to send, IDLE_EVEN and IDLE_ODD cells are sent on alternating cycles. Data is transmitted by sending a header which spans all lanes and includes a START symbol. The final data transaction includes a Frame Check Sequence (FCS) which operates over the entire header and data. The packet is terminated by an END symbol, which is sent after the final data, and the remainder of the lanes are padded with IDLE_EVEN, IDLE_ODD, IDLE_EVEN_BUSY, or IDLE_ODD_BUSY cycles. The interface has a variable clock rate.

摘要翻译： 高速通信接口将数据划分为多个通道，每个通道用时钟信息编码，串行化并发送到接口。 在没有可用数据发送的周期期间，IDLE_EVEN和IDLE_ODD单元是以交替周期发送的。 通过发送跨越所有通道的头部并包括START符号来发送数据。 最终数据事务包括在整个报头和数据上操作的帧校验序列（FCS）。 数据包由END符号终止，该符号在最终数据之后发送，剩余的通道以IDLE_EVEN，IDLE_ODD，IDLE_EVEN_BUSY或IDLE_ODD_BUSY循环填充。 该接口具有可变的时钟速率。

公开(公告)号：US07644179B1

公开(公告)日：2010-01-05

申请号：US11292684

申请日：2005-12-01

申请人： Ankur Jain ,  Thomas J. Edsall ,  Subrata Banerjee ,  Vinay Gaonkar ,  Madhava Rao Cheethirala ,  Badrinarayanan Ramaswamy

发明人： Ankur Jain ,  Thomas J. Edsall ,  Subrata Banerjee ,  Vinay Gaonkar ,  Madhava Rao Cheethirala ,  Badrinarayanan Ramaswamy

IPC分类号： G06F15/173 ,  G06F15/177 ,  G06F15/16 ,  H04L12/28

CPC分类号： H04L61/2535 ,  H04L29/12424 ,  H04L29/12886 ,  H04L61/6045 ,  H04L67/1097

摘要： Disclosed are apparatus and methods for facilitating communication between two devices from two different VSANs by propagating each device's presence from a first VSAN to the other device's different VSAN using a network address translation (NAT) mechanism. For instance, a first device, such as a host H1, from VSAN_A is allowed to access data from a second device, such as disk D1, of VSAN_B by propagating D1's presence into VSAN_A and H1's presence into VSAN_B. This awareness is accomplished by propagating an identifier for each device into the edge VSAN of the other device, as well as into any transit VSAN. So as to not duplicate identifiers in any one of the VSANs, a device's presence is propagated into a particular VSAN by assigning an unused domain for use by such device in the particular VSAN.

摘要翻译： 公开了通过使用网络地址转换（NAT）机制将每个设备的存在从第一VSAN传播到另一设备的不同VSAN来促进来自两个不同VSAN的两个设备之间的通信的装置和方法。 例如，允许来自VSAN_A的第一设备，例如主机H1，通过将D1的存在传播到VSAN_A和H1存在于VSAN_B中来访问来自VSAN_B的第二设备（例如盘D1）的数据。 该感知通过将每个设备的标识符传播到另一设备的边缘VSAN以及任何传输VSAN来实现。 为了不在任何一个VSAN中重复标识符，设备的存在通过分配一个未使用的域来传播到特定的VSAN中，供特定VSAN中的这种设备使用。

公开(公告)号：US07519062B1

公开(公告)日：2009-04-14

申请号：US10999823

申请日：2004-11-30

申请人： Ray Kloth ,  Thomas J. Edsall ,  Luca Cafiero

发明人： Ray Kloth ,  Thomas J. Edsall ,  Luca Cafiero

IPC分类号： H04L12/28 ,  H04L12/56

CPC分类号： H04L49/602 ,  H04L49/251 ,  H04L49/354

摘要： In one embodiment, a first packet is forwarded based on a network layer routing decision rendered by a router. A shortcut entry is generated based on a first header of the first packet. The shortcut entry is stored. In response to the shortcut entry, and absent a network layer routing decision rendered by a router, subsequent packets having a subsequent header are forwarded if the subsequent header has at least one field which matches a field of the first header. Such technique may be implemented by a switch coupled to the router.

摘要翻译： 在一个实施例中，基于由路由器呈现的网络层路由决定来转发第一分组。 基于第一分组的第一报头生成快捷条目。 快捷方式条目被存储。 响应于快捷项，并且缺少由路由器呈现的网络层路由决定，如果随后的报头具有与第一报头的字段匹配的至少一个字段，则转发具有后续报头的后续分组。 这种技术可以通过耦合到路由器的交换机来实现。

公开(公告)号：US07437507B2

公开(公告)日：2008-10-14

申请号：US11146457

申请日：2005-06-06

申请人： Samar Sharma ,  Dinesh Dutt ,  Sanjaya Kumar ,  Umesh Mahajan ,  Thomas J. Edsall

发明人： Samar Sharma ,  Dinesh Dutt ,  Sanjaya Kumar ,  Umesh Mahajan ,  Thomas J. Edsall

IPC分类号： G06F12/00

CPC分类号： G06F3/0632 ,  G06F3/0617 ,  G06F3/067

摘要： A technique is provided for implementing online restriping of a volume in a storage area network. A first instance of the volume is instantiated at a first port of the fibre channel fabric for enabling I/O operations to be performed at the volume. While restriping operations are being performed at the volume, the first port is able to concurrently perform I/O operations at the volume.

摘要翻译： 提供了一种用于实现存储区域网络中的卷的在线重新排列的技术。 该卷的第一个实例在光纤通道结构的第一个端口处被实例化，以便在卷上执行I / O操作。 当卷上执行重新启动操作时，第一个端口能够同时在卷上执行I / O操作。

公开(公告)号：US06950400B1

公开(公告)日：2005-09-27

申请号：US09879553

申请日：2001-06-12

申请人： Christina H. Tran ,  Daniel R. Ullum ,  Yichou Lin ,  Yan-ming Chen ,  Silvano Gai ,  Thomas J. Edsall

发明人： Christina H. Tran ,  Daniel R. Ullum ,  Yichou Lin ,  Yan-ming Chen ,  Silvano Gai ,  Thomas J. Edsall

IPC分类号： H04L12/26 ,  H04L12/56

CPC分类号： H04L47/10 ,  H04L47/22

摘要： A network traffic shaper provides high-speed, multi-level shaping. The traffic shaper is in communicating relationship with a forwarding engine, and includes a queue controller having a plurality of queues for storing messages, a scheduler for computing release times, at least one time-searchable memory and a corresponding memory controller. Each queue is preferably associated with a corresponding traffic specifier, and a release time is computed for each queue and stored in the time-searchable memory. When a stored release time expires, the message at the head of the corresponding queue is retrieved and is either moved into a different queue or forwarded by the network device. By moving messages through two or more queues, each having its own release time computed in response to a different traffic specifier, the traffic shaper can perform multi-level shaping on network messages.

摘要翻译： 网络流量整形器提供高速，多层次的整形。 流量整形器与转发引擎处于通信关系中，并且包括具有用于存储消息的多个队列的队列控制器，用于计算释放时间的调度器，至少一个时间可搜索存储器和相应的存储器控​​制器。 每个队列优选地与对应的流量指示符相关联，并且为每个队列计算释放时间并将其存储在时间可搜索的存储器中。 当存储的释放时间到期时，检索相应队列头部的消息，并将其移动到不同的队列中或由网络设备转发。 通过将消息移动到两个或更多个队列中，每个队列具有响应于不同流量指示符计算的其自己的释放时间，流量整形器可以对网络消息执行多级整形。

公开(公告)号：US06807172B1

公开(公告)日：2004-10-19

申请号：US09469459

申请日：1999-12-21

申请人： Herman Levenson ,  Jonathan Davar ,  Ajit Sanzgiri ,  Thomas J. Edsall ,  Chingwei Chang ,  Rong-Lung Lue ,  Saravanakumar Rajendran ,  Tuan Thanh Nguyen ,  Claudette Lucille Surma

发明人： Herman Levenson ,  Jonathan Davar ,  Ajit Sanzgiri ,  Thomas J. Edsall ,  Chingwei Chang ,  Rong-Lung Lue ,  Saravanakumar Rajendran ,  Tuan Thanh Nguyen ,  Claudette Lucille Surma

IPC分类号： H04L1228

CPC分类号： H04L49/3009 ,  H04L49/101 ,  H04L49/30 ,  H04L49/351 ,  H04L49/354 ,  H04L49/40

摘要： A technique enables learning and switching of frames between line cards that are interconnected by a switch fabric of a distributed network switch. The network switch comprises a router and a plurality of forwarding engines, each having an associated forwarding table. The distributed learning and switching technique configures (i) the router to issue an extra copy of a routed frame to an ingress card having a port attached to the source of the frame; (ii) the router to ensure that the contents of a source index field of the routed frame header indicate that the frame originated from the ingress card; (iii) the router to assert a shortcut bit in the header of the routed frame; (iv) a forwarding engine on an egress card having a port attached to the destination of the frame to generate and issue a media access control notification frame to the ingress card and (v) a forwarding engine on the ingress card to mark an established entry in a layer 2 (L2) portion of its forwarding table as ineligible for normal L2 aging policies.

摘要翻译： 一种技术能够在由分布式网络交换机的交换结构互连的线路卡之间学习和切换帧。 网络交换机包括路由器和多个转发引擎，每个转发引擎具有相关联的转发表。 分布式学习和切换技术配置（i）路由器向已经连接到帧的源的端口的入口卡发布路由帧的额外副本; （ii）路由器，以确保路由帧头的源索引字段的内容指示帧来自入口卡; （iii）路由器在路由帧的头部中断言快捷位; （iv）在出口卡上的转发引擎，其具有连接到帧的目的地的端口，以生成并向入口卡发布媒体访问控制通知帧，以及（v）在入口卡上的转发引擎来标记已建立的条目 在其转发表的第2层（L2）部分不符合正常的L2老化策略。

公开(公告)号：US6147993A

公开(公告)日：2000-11-14

申请号：US951820

申请日：1997-10-14

申请人： Ray Kloth ,  Thomas J. Edsall ,  Luca Cafiero

发明人： Ray Kloth ,  Thomas J. Edsall ,  Luca Cafiero

IPC分类号： H04L12/56

CPC分类号： H04L49/602 ,  H04L49/251 ,  H04L49/354

摘要： A shortcut technique implements forwarding decision shortcuts at a switch for frames routed between subnetworks of a computer network. The switch monitors the flow of a first frame of a particular type to and from the router, which renders a forwarding decision for routing the frame. The switch records information stored in network layer header of a packet encapsulated within the first frame, and then compares that information with the information stored in network layer headers of packets contained within subsequent frames of that particular type. Forwarding decisions for these subsequent frames are then rendered by hardware logic circuits of the switch rather than by the router.

摘要翻译： 快捷方法技术在交换机上实现了在计算机网络的子网之间路由的帧的转发决策快捷方式。 交换机监视特定类型的第一帧到路由器和从路由器的流程，这使得路由帧的转发决定。 交换机记录存储在第一帧中封装的分组的网络层报头中的信息，然后将该信息与存储在该特定类型的后续帧中的分组的网络层报头中存储的信息进行比较。 然后，这些后续帧的转发决定由交换机的硬件逻辑电路而不是由路由器呈现。

公开(公告)号：US06868065B1

公开(公告)日：2005-03-15

申请号：US10391683

申请日：2003-03-18

申请人： Raymond J. Kloth ,  Thomas J. Edsall ,  Michael Fine ,  Dinesh G. Dutt

发明人： Raymond J. Kloth ,  Thomas J. Edsall ,  Michael Fine ,  Dinesh G. Dutt

IPC分类号： H04L12/56 ,  H04J1/16 ,  H04J3/14 ,  H04L1/00 ,  H04L12/26 ,  H04L12/28

CPC分类号： H04L47/41 ,  H04L45/7453 ,  H04L47/10 ,  H04L47/215 ,  H04L47/2408 ,  H04L47/2416 ,  H04L47/2441 ,  H04L47/30 ,  H04L47/32 ,  Y02D50/30

摘要： A method and apparatus for implementing Quality of Service (QoS) policy in a data communications network. An active flow content addressable memory (CAM) contains entries of flow information for each active flow of packets passing through a given node of the data communications network. The CAM has associated with each entry a packet counter, a byte counter, a token bucket, and a contract value. Each flow is assigned one of a plurality of output queues and optionally at least one output threshold value. A token bucket algorithm is employed on each flow to determine whether packets from that flow exceed the contract value. Such packets may be dropped or optimally modified to reflect an alternate output queue and/or alternate threshold before being sent to the selected output queue for transmission from the node.

摘要翻译： 一种用于在数据通信网络中实现服务质量（QoS）策略的方法和装置。 活动流内容可寻址存储器（CAM）包含通过数据通信网络的给定节点的每个活动流的流的信息条目。 CAM与每个条目相关联，分组计数器，字节计数器，令牌桶和合同值。 每个流被分配多个输出队列中的一个和可选的至少一个输出阈值。 在每个流中使用令牌桶算法来确定来自该流的分组是否超过了合同值。 在发送到所选择的输出队列以便从节点传输之前，可以丢弃或最佳地修改这样的分组以反映替代输出队列和/或替代阈值。

公开(公告)号：US06831898B1

公开(公告)日：2004-12-14

申请号：US09593566

申请日：2000-08-16

申请人： Thomas J. Edsall ,  Silvano Gai ,  Soei-Shin Hang

发明人： Thomas J. Edsall ,  Silvano Gai ,  Soei-Shin Hang

IPC分类号： H04L1228

CPC分类号： H04L47/34 ,  H04L45/00 ,  H04L45/16 ,  H04L45/24 ,  H04L45/28 ,  H04L47/2416

摘要： The invention replicates a packet requiring high availability and transmits it from two or more ports of a switch, for example a wiring closet Layer 2 switch. The parent packet carries a unique sequence number. The copies of the packet each carry the parent packet's unique sequence number. Each copy of the packet then travels on separate pathways through routers (Layer 3 network devices). The pathways are maintained separate by assigning high costs in a LSP routing sense to links connecting the two paths, and by assigning low costs to links along the desired paths. The two identical packets converge on the destination station. The destination station accepts the first packet with a particular sequence number, and discards any later packets with the same sequence number. In the event that a link in one path has a catastrophic failure, then the packet travelling along the other path reaches the destination station and service remains operative without interruption. The lost path is then recomputed by the a router (if any) still receiving the lost packet. A new non-converging path may be selected if any are available, depending upon the topology. After the disruption is repaired, the original dual pathways may once again be established.

摘要翻译： 本发明复制了需要高可用性的分组，并将其从交换机的两个或更多个端口（例如配线柜第2层交换机）发送。 父包携带唯一的序列号。 分组的副本每个携带父分组的唯一序列号。 然后，数据包的每个副本通过路由器（第3层网络设备）在不同的路径上传播。 通过将LSP路由意义中的高成本分配给连接两个路径的链路以及通过沿着期望路径为链路分配低成本来维持路径。 两个相同的数据包收敛在目的站。 目的站接收具有特定序列号的第一个分组，并丢弃具有相同序列号的任何后续分组。 在一条路径中的链路发生灾难性故障的情况下，沿着另一路径行进的分组到达目的站，并且服务保持无间断的运行。 丢失的路径然后被路由器（如果有的话）重新计算，仍然收到丢失的数据包。 根据拓扑结构，可以选择新的非会聚路径（如果有）。 破坏后修复，原来的双重路径可能再次成立。