公开(公告)号：US06597700B2

公开(公告)日：2003-07-22

申请号：US09340477

申请日：1999-06-30

申请人： Sandeep P. Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis ,  Timothy Cunningham ,  Manish Patel

发明人： Sandeep P. Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis ,  Timothy Cunningham ,  Manish Patel

IPC分类号： H04L1256

CPC分类号： H04L29/12047 ,  H04L29/12009 ,  H04L45/742 ,  H04L49/351 ,  H04L61/15

摘要： A distributed address database management technique involves maintaining an address database by each of a number of interconnected modules. Each module maintains a number of locally owned address entries and a number of remotely owned address entries in the address database. Each module monitors the status of its locally owned address entries, maintains the locally owned address entries based upon the status, and provides the status to the other interconnected modules. Each module maintains the remotely owned address entries based upon the status received from the other interconnected modules. When a module adds a locally owned address entry to its address database, the module notifies the other interconnected modules, which in turn add a corresponding remotely owned address entry to their respective address databases. When a module purges a locally owned address entry from its address database, the module notifies the other interconnected modules, which in turn purge the corresponding remotely owned address entries from their respective address databases. Each module may periodically send a keep-alive message including a list of active addresses to the other interconnected modules, which maintain a persistence timer for each of the remotely owned address entries and purge a particular remotely owned address entry if the corresponding persistence timer expires before receiving a keep-alive message identifying the remotely owned address entry as an active remotely owned address entry. Upon receiving a keep-alive message, a module adds a remotely owned address entry for a particular address to its address database if such a remotely owned address entry is not already maintained in the address database. A module purges all remotely owned address entries from its address database if the module is reconfigured to operate in a stand-alone mode. A module purges all remotely owned address entries associated with a particular interconnected module if that particular interconnected module is removed.

公开(公告)号：US20050190754A1

公开(公告)日：2005-09-01

申请号：US10606847

申请日：2003-06-26

申请人： Sandeep Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis ,  Timothy Cunningham ,  Manish Patel

发明人： Sandeep Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis ,  Timothy Cunningham ,  Manish Patel

IPC分类号： H04L12/56 ,  H04L29/12 ,  H04Q11/00

CPC分类号： H04L29/12047 ,  H04L29/12009 ,  H04L45/742 ,  H04L49/351 ,  H04L61/15

摘要： A distributed address database management technique involves maintaining an address database by each of a number of interconnected modules. Each module maintains a number of locally owned address entries and a number of remotely owned address entries in the address database. Each module monitors the status of its locally owned address entries, maintains the locally owned address entries based upon the status, and provides the status to the other interconnected modules. Each module maintains the remotely owned address entries based upon the status received from the other interconnected modules. When a module adds a locally owned address entry to its address database, the module notifies the other interconnected modules, which in turn add a corresponding remotely owned address entry to their respective address databases. When a module purges a locally owned address entry from its address database, the module notifies the other interconnected modules, which in turn purge the corresponding remotely owned address entries from their respective address databases. Each module may periodically send a keep-alive message including a list of active addresses to the other interconnected modules, which maintain a persistence timer for each of the remotely owned address entries and purge a particular remotely owned address entry if the corresponding persistence timer expires before receiving a keep-alive message identifying the remotely owned address entry as an active remotely owned address entry. Upon receiving a keep-alive message, a module adds a remotely owned address entry for a particular address to its address database if such a remotely owned address entry is not already maintained in the address database. A module purges all remotely owned address entries from its address database if the module is reconfigured to operate in a stand-alone mode. A module purges all remotely owned address entries associated with a particular interconnected module if that particular interconnected module is removed.

公开(公告)号：US06888802B1

公开(公告)日：2005-05-03

申请号：US09340478

申请日：1999-06-30

申请人： Sandeep P. Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis

发明人： Sandeep P. Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis

IPC分类号： H04L12/24 ,  H04L12/56 ,  H04L29/12 ,  H04L12/28 ,  G06F7/00 ,  G06F17/30

CPC分类号： H04L29/12018 ,  H04L29/12009 ,  H04L29/12783 ,  H04L41/00 ,  H04L41/12 ,  H04L49/351 ,  H04L61/10 ,  H04L61/35 ,  Y10S707/99931

摘要： An address reporting technique for reporting address information in a distributed communication environment retrieves locally owned address information from each of a number of distributed address databases, sorts the address information according to a predetermined sorting scheme, and reports the sorted address information. Each address database is maintained by one of a plurality of interconnected modules. A reporting module reports address information by retrieving locally owned address information from its address database, retrieves locally owned address information from each of the other interconnected modules, sorts the address information according to a predetermined sorting scheme, and reports the sorted address information. The reporting module retrieves the locally owned address information from each of the other interconnected modules by sending a request message to the other interconnected modules and receiving a response message from each of the other interconnected modules including the locally owned address information from the module. A module that receives the request message retrieves locally owned address information from its address database, formats a response message, and sends the response message to the reporting module. The reporting module may indicate a starting address, in which case each module retrieves from its address database a predetermined number of locally owned address entries starting with a first locally owned address entry that is lexicographically greater than the starting address.

公开(公告)号：US07203176B2

公开(公告)日：2007-04-10

申请号：US10963779

申请日：2004-10-12

申请人： Sandeep P. Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis

发明人： Sandeep P. Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis

IPC分类号： H04L12/28 ,  H04L12/56

CPC分类号： H04L29/12018 ,  H04L29/12009 ,  H04L29/12783 ,  H04L41/00 ,  H04L41/12 ,  H04L49/351 ,  H04L61/10 ,  H04L61/35 ,  Y10S707/99931

摘要： An address reporting technique for reporting address information in a distributed communication environment retrieves locally owned address information from each of a number of distributed address databases, sorts the address information according to a predetermined sorting scheme, and reports the sorted address information. Each address database is maintained by one of a plurality of interconnected modules. A reporting module reports address information by retrieving locally owned address information from its address database, retrieves locally owned address information from each of the other interconnected modules, sorts the address information according to a predetermined sorting scheme, and reports the sorted address information. The reporting module retrieves the locally owned address information from each of the other interconnected modules by sending a request message to the other interconnected modules and receiving a response message from each of the other interconnected modules including the locally owned address information from the module. A module that receives the request message retrieves locally owned address information from its address database, formats a response message, and sends the response message to the reporting module. The reporting module may indicate a starting address, in which case each module retrieves from its address database a predetermined number of locally owned address entries starting with a first locally owned address entry that is lexicographically greater than the starting address.

摘要翻译： 用于在分布式通信环境中报告地址信息的地址报告技术从多个分布式地址数据库中的每一个检索本地拥有的地址信息，根据预定的排序方案对地址信息进行排序，并且报告排序的地址信息。 每个地址数据库由多个互连模块之一维护。 报告模块通过从其地址数据库检索本地拥有的地址信息来报告地址信息，从每个其他互连模块检索本地拥有的地址信息，根据预定的排序方案对地址信息进行排序，并报告排序的地址信息。 报告模块通过向其他互连模块发送请求消息并从每个其他互连模块接收包括来自模块的本地拥有的地址信息的响应消息来从每个其他互连的模块中检索本地拥有的地址信息。 接收请求消息的模块从其地址数据库中获取本地拥有的地址信息，格式化响应消息，并将响应消息发送到报告模块。 报告模块可以指示起始地址，在这种情况下，每个模块从其地址数据库中获取预定数量的本地拥有的地址条目，该地址条目以字面大于起始地址的第一本地拥有的地址条目开始。

公开(公告)号：US06519231B1

公开(公告)日：2003-02-11

申请号：US09229116

申请日：1999-01-12

申请人： Da-Hai Ding ,  Nicholas Ilyadis ,  Nelson Kong

发明人： Da-Hai Ding ,  Nicholas Ilyadis ,  Nelson Kong

IPC分类号： H04L1228

CPC分类号： H04L45/245 ,  H04L12/44 ,  H04L45/02 ,  H04L45/18 ,  H04L45/48 ,  Y02D50/30

摘要： An enhanced spanning tree protocol for data communications networks having a multi-link trunk. In one embodiment, configuration messages are transmitted from boxes of the data communications network. In one embodiment, the configuration messages that are transmitted through all physical links of the same logical link, or multi-link trunk, include the same port Identifier. A network device that receives the configuration messages is therefore able to identify all of the physical links of a logical link. The enhanced spanning tree protocol according to one embodiment of the present invention considers all of the physical links of a multi-link trunk as a single logical link when identifying and removing loops in the data communications network to form a spanning tree.

摘要翻译： 一种用于具有多链路中继线的数据通信网络的增强型生成树协议。 在一个实施例中，从数据通信网络的框传输配置消息。 在一个实施例中，通过相同逻辑链路或多链路中继线的所有物理链路传输的配置消息包括相同的端口标识符。 因此，接收配置消息的网络设备能够识别逻辑链路的所有物理链路。 根据本发明的一个实施例的增强型生成树协议在识别和去除数据通信网络中的环路以形成生成树时将多链路中继线的所有物理链路视为单个逻辑链路。

公开(公告)号：US20050169194A1

公开(公告)日：2005-08-04

申请号：US10963779

申请日：2004-10-12

申请人： Sandeep Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis

发明人： Sandeep Golikeri ,  Da-Hai Ding ,  Nicholas Ilyadis

IPC分类号： H04L12/24 ,  H04L12/56 ,  H04L29/12 ,  H04L12/28

CPC分类号： H04L29/12018 ,  H04L29/12009 ,  H04L29/12783 ,  H04L41/00 ,  H04L41/12 ,  H04L49/351 ,  H04L61/10 ,  H04L61/35 ,  Y10S707/99931

摘要： An address reporting technique for reporting address information in a distributed communication environment retrieves locally owned address information from each of a number of distributed address databases, sorts the address information according to a predetermined sorting scheme, and reports the sorted address information. Each address database is maintained by one of a plurality of interconnected modules. A reporting module reports address information by retrieving locally owned address information from its address database, retrieves locally owned address information from each of the other interconnected modules, sorts the address information according to a predetermined sorting scheme, and reports the sorted address information. The reporting module retrieves the locally owned address information from each of the other interconnected modules by sending a request message to the other interconnected modules and receiving a response message from each of the other interconnected modules including the locally owned address information from the module. A module that receives the request message retrieves locally owned address information from its address database, formats a response message, and sends the response message to the reporting module. The reporting module may indicate a starting address, in which case each module retrieves from its address database a predetermined number of locally owned address entries starting with a first locally owned address entry that is lexicographically greater than the starting address.

摘要翻译： 用于在分布式通信环境中报告地址信息的地址报告技术从多个分布式地址数据库中的每一个检索本地拥有的地址信息，根据预定的排序方案对地址信息进行排序，并且报告排序的地址信息。 每个地址数据库由多个互连模块之一维护。 报告模块通过从其地址数据库检索本地拥有的地址信息来报告地址信息，从每个其他互连模块检索本地拥有的地址信息，根据预定的排序方案对地址信息进行排序，并报告排序的地址信息。 报告模块通过向其他互连模块发送请求消息并从每个其他互连模块接收包括来自模块的本地拥有的地址信息的响应消息来从每个其他互连的模块中检索本地拥有的地址信息。 接收请求消息的模块从其地址数据库中获取本地拥有的地址信息，格式化响应消息，并将响应消息发送到报告模块。 报告模块可以指示起始地址，在这种情况下，每个模块从其地址数据库中获取预定数量的本地拥有的地址条目，该地址条目以字面大于起始地址的第一本地拥有的地址条目开始。

公开(公告)号：US07974192B2

公开(公告)日：2011-07-05

申请号：US11274514

申请日：2004-02-02

申请人： Da-Hai Ding

发明人： Da-Hai Ding

IPC分类号： G01R31/08 ,  H04L12/28 ,  H04J3/16 ,  H04J3/24

CPC分类号： H04L12/18 ,  H04L45/16

摘要： A technique for multicast switching in a distributed communication system having a plurality of cooperating modules enables a module to forward multicast packets associated with a multicast stream without using a centralized module or control logic by determining all network interfaces and remote modules associated with the multicast stream and forwarding multicast packets to only those network interfaces and remote modules associated with the multicast stream. IGMP snooping may be used to determine the network interfaces and remote modules associated with the multicast stream, and may also be used to determine host addresses, router addresses, and an IGMP version for each network interface and for each remote module. In order to generate IGMP messages, the module learns a multicast device address from received IGMP messages and uses the multicast device address to send the IGMP messages. The module decides whether to send IGMP version 1 messages or IGMP version 2 messages on a particular interface based upon the IGMP version of IGMP messages received over the interface.

摘要翻译： 在具有多个协同模块的分布式通信系统中的组播切换技术使得模块能够通过确定与多播流相关联的所有网络接口和远程模块来转发与多播流相关联的多播分组，而不使用集中式模块或控制逻辑， 将组播数据包转发到与组播流相关联的那些网络接口和远程模块。 IGMP侦听可用于确定与组播流相关联的网络接口和远程模块，还可用于确定每个网络接口和每个远程模块的主机地址，路由器地址和IGMP版本。 为了生成IGMP消息，该模块从接收到的IGMP消息中学习组播设备地址，并使用组播设备地址发送IGMP消息。 该模块基于通过接口接收的IGMP消息的IGMP版本决定是否在特定接口上发送IGMP版本1消息或IGMP版本2消息。

公开(公告)号：US20060146823A1

公开(公告)日：2006-07-06

申请号：US11274514

申请日：2004-02-02

申请人： Da-Hai Ding

发明人： Da-Hai Ding

IPC分类号： H04L12/56

CPC分类号： H04L12/18 ,  H04L45/16

摘要： A technique for multicast switching in a distributed communication system having a plurality of cooperating modules enables a module to forward multicast packets associated with a multicast stream without using a centralized module or control logic by determining all network interfaces and remote modules associated with the multicast stream and forwarding multicast packets to only those network interfaces and remote modules associated with the multicast stream. IGMP snooping may be used to determine the network interfaces and remote modules associated with the multicast stream, and may also be used to determine host addresses, router addresses, and an IGMP version for each network interface and for each remote module. In order to generate IGMP messages, the module learns a multicast device address from received IGMP messages and uses the multicast device address to send the IGMP messages. The module decides whether to send IGMP version 1 messages or IGMP version 2 messages on a particular interface based upon the IGMP version of IGMP messages received over the interface.

摘要翻译： 在具有多个协同模块的分布式通信系统中的组播切换技术使得模块能够通过确定与多播流相关联的所有网络接口和远程模块来转发与组播流相关联的多播分组，而不使用集中式模块或控制逻辑， 将组播数据包转发到与组播流相关联的那些网络接口和远程模块。 IGMP侦听可用于确定与组播流相关联的网络接口和远程模块，还可用于确定每个网络接口和每个远程模块的主机地址，路由器地址和IGMP版本。 为了生成IGMP消息，该模块从接收到的IGMP消息中学习组播设备地址，并使用组播设备地址发送IGMP消息。 该模块基于通过接口接收的IGMP消息的IGMP版本决定是否在特定接口上发送IGMP版本1消息或IGMP版本2消息。

公开(公告)号：US06981034B2

公开(公告)日：2005-12-27

申请号：US09343299

申请日：1999-06-30

申请人： Da-Hai Ding ,  Luc A. Pariseau ,  Brenda A. Thompson

发明人： Da-Hai Ding ,  Luc A. Pariseau ,  Brenda A. Thompson

IPC分类号： H04L12/24 ,  G06F15/173

CPC分类号： H04L41/00 ,  H04L41/0213

摘要： A decentralized management model enables a plurality of interconnected modules to be managed and controlled as an integrated unit without requiring any one of the interconnected modules to operate as a fully centralized manager. One of the interconnected modules is configured to operate as a base module, which coordinates certain network management operations among the interconnected modules. Each of the interconnected modules is capable of sending and receiving management and control information. Each of the interconnected modules maintains a segmented management database containing network management parameters that are specific to the particular module, and also maintains a shadowed management database containing network management parameters that are common to all of the interconnected modules in the stack. Management and control operations that do not require synchronization or mutual exclusion among the various interconnected modules are typically handled by the module that receives a management/control request. Management and control operations that require synchronization or mutual exclusion among the various interconnected modules are handled by the base module.

摘要翻译： 分散管理模型使多个互连的模块能够作为集成单元进行管理和控制，而不需要互连模块中的任何一个作为完全集中的管理器运行。 互连模块中的一个被配置为作为基本模块进行操作，该基本模块协调互连模块之间的某些网络管理操作。 每个互连的模块能够发送和接收管理和控制信息。 每个互连的模块维护包含特定于特定模块的网络管理参数的分段管理数据库，并且还维护包含堆叠中所有互连模块所共有的网络管理参数的阴影管理数据库。 不需要在各种互连模块之间进行同步或互斥的管理和控制操作通常由接收管理/控制请求的模块来处理。 需要在各种互连模块之间进行同步或互斥的管理和控制操作由基本模块来处理。

公开(公告)号：US06678437B2

公开(公告)日：2004-01-13

申请号：US09823811

申请日：2001-03-30

申请人： Dahong Qian ,  Marc Hertzberg ,  Da-Hai Ding ,  Wayne Wong ,  Amit Burstein

发明人： Dahong Qian ,  Marc Hertzberg ,  Da-Hai Ding ,  Wayne Wong ,  Amit Burstein

IPC分类号： G02B626

CPC分类号： G02B6/3588 ,  G02B6/3512 ,  G02B6/3556 ,  G02B6/359 ,  H04Q11/0005 ,  H04Q2011/003 ,  H04Q2011/0039 ,  H04Q2011/0043 ,  H04Q2011/0083

摘要： A novel optical path switching system, architecture and technique wherein light beam data traffic is to be switched by MEMS mirrors between source and destination nodes, and test ports are used to set up optical paths even before the real data traffic is propagated, with a combination of an electrical mirror-sensing feedback loop for controlling coarse mirror positioning, and an optical path power-sensing feedback loop for controlling fine adjustments in the mirror position.

摘要翻译： 一种新颖的光路切换系统，架构和技术，其中光源数据业务将由源和目的节点之间的MEMS镜进行切换，而测试端口即使在实际数据流量传播之前也被用于建立光路， 用于控制粗镜定位的电镜面感测反馈回路，以及用于控制镜位置的微调的光路功率感测反馈回路。