公开(公告)号：US08380065B2

公开(公告)日：2013-02-19

申请号：US12582083

申请日：2009-10-20

申请人： Michitaka Okuno ,  Koji Wakayama ,  Kenichi Sakamoto ,  Hiroki Ikeda

发明人： Michitaka Okuno ,  Koji Wakayama ,  Kenichi Sakamoto ,  Hiroki Ikeda

IPC分类号： H04J14/00

CPC分类号： H04Q11/0067 ,  H04J2203/0058 ,  H04L43/0864 ,  H04Q2011/0079 ,  H04Q2011/0088

摘要： Provided is an optical access system comprising: an optical line terminal connected to another network; a plurality of optical network units, each connected to a user terminal; and at least one of an optical switching unit and an optical splitter, which is installed between the optical line terminal and the plurality of optical network units. The optical line terminal allocates a length of time to a discovery phase for detecting the plurality of optical network units, and a length of time to data transmission phases for transferring data from the plurality of optical network units; and changes a ratio of the length of time of the discovery phase to the length of time of the data transmission phases so that the length of time of the discovery phase is shortened in the case where a number of the optical network units that are registered in the optical line terminal increase.

摘要翻译： 提供一种光接入系统，包括：连接到另一网络的光线路终端; 多个光网络单元，各自连接到用户终端; 以及安装在光线路终端与多个光网络单元之间的光交换单元和分光器中的至少一个。 光线路终端将用于检测多个光网络单元的发现阶段的时间长度分配给从多个光网络单元传送数据的数据传输阶段的时间长度; 并且将发现阶段的时间长度与数据传输阶段的时间长度的比率进行改变，使得在注册的光网络单元的数量的情况下，发现阶段的时间长度被缩短 光线路终端增加。

公开(公告)号：US08401384B2

公开(公告)日：2013-03-19

申请号：US12503884

申请日：2009-07-16

申请人： Koji Wakayama ,  Hiroki Ikeda ,  Michitaka Okuno ,  Kenichi Sakamoto

发明人： Koji Wakayama ,  Hiroki Ikeda ,  Michitaka Okuno ,  Kenichi Sakamoto

IPC分类号： H04J14/00 ,  H04B10/00

CPC分类号： H04Q11/0067 ,  H04Q2011/0045 ,  H04Q2011/0064

摘要： Provided is an optical access system, including: an optical line terminal, a plurality of optical network units and an optical switching unit. The optical line terminal sends to the optical switching unit a control frame including a switching time when the optical switching unit is to make a switch from one of the optical communication paths between the optical line terminal and the plurality of optical network units to another, and an identifier of an optical communication path to which the switch is made in order to switch the optical communication paths between the optical line terminal and the plurality of optical network units. The optical switching unit switches the optical communication paths between the optical line terminal and the plurality of optical network units based on the switching time and the identifier of the optical communication path after switching which are included in the control frame.

摘要翻译： 提供一种光接入系统，包括：光线路终端，多个光网络单元和光交换单元。 光线路终端向光交换单元发送包括切换时间的控制帧，当光交换单元从光线路终端与多个光网络单元之间的光通信路径之一进行切换时，切换时间为 为了切换光线路终端与多个光网络单元之间的光通信路径而进行交换的光通信路径的标识符。 光切换单元基于包括在控制帧中的切换时间和切换后的光通信路径的标识符，切换光线路终端与多个光网络单元之间的光通信路径。

公开(公告)号：US08135004B2

公开(公告)日：2012-03-13

申请号：US12010703

申请日：2008-01-29

申请人： Michitaka Okuno

发明人： Michitaka Okuno

IPC分类号： H04L12/50 ,  H04Q11/00

CPC分类号： H04L49/552 ,  H04L49/1523 ,  H04L49/3027 ,  H04L49/3072 ,  H04L49/508

摘要： Disclosed herewith is a multi-plane cell switch fabric system in which each switching unit functions asynchronously with others. The system executes distribution/restoration operations without lowering the switching capacity to reorder cells that arrive in random order from a plurality of switches just as they were in original flows and packets respectively with a small hardware capacity. In the system, the distribution unit divides each variable length packet addressed to the same destination into fixed length cells and sends those divided cells by a unit of integer multiple of the number of switches. On the other hand, the reordering unit, while holding cells that arrive in random order from each switching unit (switching units 1 to M) in a receive buffer, separates only the header information from each cell and holds the header information in a retry queue. The reordering unit, upon finding the header information of a head cell of a flow in an ordering check at the time of receiving or in a retry check in the retry queue, extracts the corresponding cell bodies from the receive buffer to restore the original order of those cells in the subject packet.

摘要翻译： 这里公开了一种多平面单元交换结构系统，其中每个开关单元与其他单元异步地起作用。 系统执行分配/恢复操作，而不降低交换容量，以便按照原始流和分组具有小的硬件容量的分组从多个交换机以随机顺序重新排序到达的小区。 在系统中，分配单元将寻址到同一目的地的每个可变长度分组划分为固定长度的小区，并将这些分割的小区发送为交换机数量的整数倍的单位。 另一方面，重新排序单元在从接收缓冲器中的每个切换单元（交换单元1至M）以随机顺序保持的小区保持仅分离来自每个小区的报头信息并将报头信息保存在重试队列中 。 重新排序单元在接收到或在重试队列中的重试检查中查找排序检查中的流的头单元的头信息时，从接收缓冲器中提取相应的单元体，以恢复原始顺序 主题包中的那些单元格。

公开(公告)号：US20080159149A1

公开(公告)日：2008-07-03

申请号：US11878279

申请日：2007-07-23

申请人： Michitaka Okuno

发明人： Michitaka Okuno

IPC分类号： G08C15/00

CPC分类号： H04L47/24 ,  H04L47/11 ,  H04L47/30 ,  H04L47/32 ,  H04L49/254 ,  H04L49/3072 ,  H04L49/351 ,  H04L49/503

摘要： In a congestion state where a specific destination in a switch fabric is congested, high priority data is allowed to pass at a low delay or high throughput while in a non-congestion state where the specific destination in the switch fabric is not congested, full use of switching bandwidth is made regardless of priority. In a switch fabric which includes plural transmitting source nodes each having not less than two output queues by the priority on a destination-by-destination basis, a switch for evenly distributing data units delivered from the plurality of the transmitting source nodes on the destination-by-destination basis, and plural destination nodes for receiving the data units from the switch, the respective transmitting source nodes assume that a relevant destination is in a congestion state when an available capacity of a receive-buffer of the switch, controlled by the respective transmitting source nodes, on the destination-by-destination basis, falls short of a set congestion threshold, thereby restricting data output from the output queues by the priority to the relevant destination up to a preset bandwidth according to priority while the respective transmitting source nodes assume that the congestion state of the relevant destination is dissolved when the available capacity of the receive-buffer of the switch, on the destination-by-destination basis, exceeds the set congestion threshold, thereby dissolving restriction on the bandwidth, according to the priority.

摘要翻译： 在交换结构中的特定目的地拥塞的拥塞状态下，高优先级数据被允许以低延迟或高吞吐量通过，而交换结构中的特定目的地不拥塞的非拥塞状态，充分使用 无论优先级如何，都会进行切换带宽。 在包括多个发送源节点的交换结构中，每个发送源节点每个目的地都按优先权具有不少于两个输出队列;交换机，用于将从多个发送源节点发送的数据单元均匀分布在目的地 - 以及用于从交换机接收数据单元的多个目的地节点，各个发送源节点假设相关目的地处于拥塞状态，当交换机的接收缓冲器的可用容量由相应的 在逐个目的地的基础上发送源节点不到设置的拥塞阈值，从而根据优先级将来自输出队列的输出的数据优先地限制到相关目的地直到预设带宽，而各个发送源节点 假设相关目的地的拥塞状态在接收的可用容量时解散 基于目的地的交换机的缓存超过设置的拥塞阈值，从而根据优先级来解除对带宽的限制。

公开(公告)号：US20140010068A1

公开(公告)日：2014-01-09

申请号：US13391424

申请日：2011-03-23

申请人： Michitaka Okuno ,  Takeki Yazaki

发明人： Michitaka Okuno ,  Takeki Yazaki

IPC分类号： H04L12/24

CPC分类号： H04L41/0668 ,  H04L49/557

摘要： Between network node apparatuses that operate as a duplex system, when a failure occurs in an information processing unit of one system, the service is maintained and continued in an information processing unit of the other system without interruption of the service. In a system using an active system network node apparatus 100-1 and a standby system network node apparatus 100-2 both in an operating state, a switch processing unit 110 has a transfer processing unit 112 that copies and transfers a packet flow to be a subject of information processing in the information processing unit 200 to two output destinations, when the switch processing unit operates as an active system. The information processing unit 200 has a mutual monitoring processing unit 203 that checks mutual operating states between the active system and the standby system, determines that a failure has occurred when the active system does not return a response and causes the standby system to operate as an active system, and a halt processing unit that, upon operation as the information processing unit of the standby system, halts output of a packet to be a subject of information processing.

摘要翻译： 在作为双工系统工作的网络节点设备之间，当在一个系统的信息处理单元中发生故障时，在另一个系统的信息处理单元中维护并继续该服务，而不会中断服务。 在使用活动系统网络节点设备100-1和备用系统网络节点设备100-2的系统中，在操作状态下，交换处理单元110具有传送处理单元112，其将数据包流复制并传送到 信息处理单元200中的信息处理到两个输出目的地，当切换处理单元作为活动系统工作时。 信息处理单元200具有相互监视处理单元203，其检查活动系统和备用系统之间的相互操作状态，当活动系统没有返回响应时，确定发生了故障，并使备用系统作为 活动系统和停止处理单元，其在作为备用系统的信息处理单元的操作时停止作为信息处理对象的分组的输出。

公开(公告)号：US20090198864A1

公开(公告)日：2009-08-06

申请号：US12276677

申请日：2008-11-24

申请人： Isao Kimura ,  Mitsuo Yamamoto ,  Michitaka Okuno

发明人： Isao Kimura ,  Mitsuo Yamamoto ,  Michitaka Okuno

IPC分类号： G06F13/00

CPC分类号： G06F13/4022

摘要： A network switch with a plurality of crossbar switches that is available to suppress increase in the circuit scale is provided. The network switch has: the plurality of crossbar switches that transfer unit data in a specified format; a receiving side transfer unit that transfers data received from a network to the plurality of crossbar switches in the unit data basis; and a plurality of transmitting side transfer units that transmit data transferred from the plurality of crossbar switches to the network. The receiving side transfer sets a consecutive serial number to the unit data in transfer sequence, and distributes the unit data to the plurality of crossbar switches. Each of the plurality of transmitting side transfer units has a plurality of queues for the respective crossbar switches that stores the transferred unit data, and extracts the unit data with smallest serial number of the unit data stored in the queues when all of the queues store the unit data.

摘要翻译： 提供一种具有多个交叉开关的网络开关，其可用于抑制电路规模的增加。 网络交换机具有：以指定格式传送单元数据的多个交叉开关; 接收侧传送单元，以单元数据为基础将从网络接收的数据传送到所述多个交叉开关; 以及多个发送侧传送单元，其将从多个交叉开关传送的数据发送到网络。 接收侧传送以传输顺序将连续的序列号设置为单元数据，并将单元数据分配给多个交叉开关。 多个发送侧传送单元中的每一个具有用于存储传送的单元数据的各个交叉开关的多个队列，并且当所有队列存储在队列中时提取存储在队列中的单元数据的最小序列号的单元数据 单位数据。

公开(公告)号：US20060253606A1

公开(公告)日：2006-11-09

申请号：US11411023

申请日：2006-04-26

申请人： Michitaka Okuno

发明人： Michitaka Okuno

IPC分类号： G06F15/173

CPC分类号： H04L45/54 ,  H04L45/02 ,  H04L45/60 ,  H04L45/742

摘要： In a packet transfer apparatus, a larger number of entries can be registered to routing tables without increasing the overall memory volume required for the routing tables to record transfer information of packets. A routing table search is conducted at a high speed. Each line card of the packet transfer apparatus includes two kinds of routing tables, i.e., first and second routing tables having mutually different functions. The first routing tables are local routing tables to record frequently used transfer information in groups. The second routing tables are shared distributed routing tables and record the transfer information in a distributed way without an overlapped part of the transfer information between the line cards. The sum of the distributed transfer information matches the overall transfer information kept in the packet transfer apparatus.

公开(公告)号：US20050074005A1

公开(公告)日：2005-04-07

申请号：US10956089

申请日：2004-10-04

申请人： Michitaka Okuno

发明人： Michitaka Okuno

IPC分类号： H04L12/701 ,  G11C15/00 ,  H04L12/747 ,  H04L12/773 ,  H04L12/56

CPC分类号： H04L45/00 ,  H04L45/60 ,  H04L49/3009

摘要： In order to perform cache processing for the received packets, a network apparatus is provided with a network-processor accelerator for caching the process result of a network processor. Accordingly, the network apparatus of the present invention ensuring higher packet-processing throughput can be realized by improving the packet-processing throughput without increase in the chip area, increase in the power consumption, and shortage in an external connected memory bandwidth.

摘要翻译： 为了对接收到的分组执行高速缓存处理，网络设备具有用于缓存网络处理器的处理结果的网络处理器加速器。 因此，可以通过提高分组处理吞吐量而不增加芯片面积，增加功耗以及外部连接的存储器带宽的不足来实现确保更高分组处理吞吐量的本发明的网络装置。

公开(公告)号：US09294342B2

公开(公告)日：2016-03-22

申请号：US13391424

申请日：2011-03-23

申请人： Michitaka Okuno ,  Takeki Yazaki

发明人： Michitaka Okuno ,  Takeki Yazaki

IPC分类号： G01R31/08 ,  H04L12/24 ,  H04L12/939

CPC分类号： H04L41/0668 ,  H04L49/557

摘要： Between network node apparatuses that operate as a duplex system, when a failure occurs in an information processing unit of one system, the service is maintained and continued in an information processing unit of the other system without interruption of the service. In a system using an active system network node apparatus 100-1 and a standby system network node apparatus 100-2 both in an operating state, a switch processing unit 110 has a transfer processing unit 112 that copies and transfers a packet flow to be a subject of information processing in the information processing unit 200 to two output destinations, when the switch processing unit operates as an active system. The information processing unit 200 has a mutual monitoring processing unit 203 that checks mutual operating states between the active system and the standby system, determines that a failure has occurred when the active system does not return a response and causes the standby system to operate as an active system, and a halt processing unit that, upon operation as the information processing unit of the standby system, halts output of a packet to be a subject of information processing.

摘要翻译： 在作为双工系统工作的网络节点设备之间，当在一个系统的信息处理单元中发生故障时，在另一个系统的信息处理单元中维护并继续该服务，而不会中断服务。 在使用活动系统网络节点设备100-1和备用系统网络节点设备100-2的系统中，在操作状态下，交换处理单元110具有传送处理单元112，其将数据包流复制并传送到 信息处理单元200中的信息处理到两个输出目的地，当切换处理单元作为活动系统工作时。 信息处理单元200具有相互监视处理单元203，其检查活动系统和备用系统之间的相互操作状态，当活动系统没有返回响应时，确定发生了故障，并使备用系统作为 活动系统和停止处理单元，其在作为备用系统的信息处理单元的操作时停止作为信息处理对象的分组的输出。

公开(公告)号：US08782239B2

公开(公告)日：2014-07-15

申请号：US13028282

申请日：2011-02-16

申请人： Michitaka Okuno ,  Takeki Yazaki ,  Yuji Tsushima ,  Hidetaka Aoki

发明人： Michitaka Okuno ,  Takeki Yazaki ,  Yuji Tsushima ,  Hidetaka Aoki

IPC分类号： G06F15/177 ,  G06F15/173

CPC分类号： H04L45/54 ,  G06F9/505 ,  H04L41/083 ,  H04L41/0833 ,  H04L45/02 ,  H04L45/38 ,  H04L67/34 ,  H04L69/22 ,  Y02D10/22

摘要： A system permitting alteration of the information processing position, where an existing information system is used, while minimizing alterations in configuration or the like, is to be provided. Intelligent nodes each having an information processing section and any desired address altering section are arranged on boundaries of a network where packets are likely to pass. This node has a flow table for recognizing as a flow a group of packets transmitted from each user's terminal, a flow status table for determining the connection state and the next destination address or the final destination address of each flow, and a module to observe the loaded state of its own information processing function. It rewrites the destination address of any flow not in a connection-established state in the flow status table to a less loaded one out of its own information processing function section or external information processing apparatus.

摘要翻译： 提供一种允许改变信息处理位置的系统，其中使用现有的信息系统，同时最小化配置等的改变。 每个具有信息处理部分和任何期望的地址改变部分的智能节点被布置在分组可能通过的网络的边界上。 该节点具有流表，用于将从每个用户终端发送的一组分组识别为流，用于确定连接状态的流状态表和下一目的地地址或每个流的最终目的地地址，以及观察该 加载状态自己的信息处理功能。 它将流状态表中不处于连接建立状态的任何流的目的地地址重写为其自己的信息处理功能部分或外部信息处理装置中较少加载的目的地址。