公开(公告)号：US06370142B1

公开(公告)日：2002-04-09

申请号：US08832042

申请日：1997-04-02

申请人： Derek Pitcher ,  Kishore K. Seshadri ,  Daniel A. Simone

发明人： Derek Pitcher ,  Kishore K. Seshadri ,  Daniel A. Simone

IPC分类号： H04L1228

CPC分类号： H04L12/5601 ,  H04L49/104 ,  H04L49/256 ,  H04L49/309 ,  H04L49/351 ,  H04Q11/0478

摘要： A method and apparatus for performing per-port Internet Protocol (IP) multicast pruning, proxying of IP multicast group membership reports, and generating pseudo membership queries for determining IP multicast group membership are provided. A switch may implement per-port IP multicast pruning by establishing a mapping of IP multicast groups to its ports. The mapping is based upon membership reports received from each end-station participating in an IP multicast group. Based upon the mapping, the switch forwards IP multicast packets only to those of the end-stations that are participating in the IP multicast group addressed. Once per-port IP multicast pruning is implemented, multicast routers must process membership reports from all end-stations participating in an IP multicast group. To reduce this burden, a switch may act as a proxy device. The switch receives a membership report identifying an IP multicast group. If the membership report is the first received for the IP multicast group after a membership query, then the switch forwards the membership report. However, if the membership report is not the first received, then the switch discards the membership report. To allow IP multicast group membership determination when no querier is present, a switch determines if another device is currently acting as a querier for a switched network. If not, the switch sends a membership query on one or more of its ports. Responsive to the membership query, an end-station transmits a membership report to the switch. The switch records the IP multicast group membership indicated in the membership report.

摘要翻译： 提供了一种用于执行每端口因特网协议（IP）组播剪枝的方法和装置，IP组播组成员报告的代理，以及生成用于确定IP组播组成员资格的伪成员查询。 交换机可以通过建立IP组播组到其端口的映射来实现每端口IP组播剪枝。 该映射基于从参与IP多播组的每个终端站接收的成员资格报告。 基于映射，交换机将IP组播数据包转发到正在参与IP组播组寻址的终端站。 一旦实现了每端口IP组播修剪，组播路由器必须处理参与IP组播组的所有终端的成员关系报告。 为了减轻这种负担，交换机可以用作代理设备。 交换机收到标识IP组播组的成员资格报告。 如果成员资格报告是成员查询后首次收到的IP组播组，则交换机转发成员资格报告。 但是，如果成员资格报告不是首次收到，则交换机将丢弃成员资格报告。 为了在不存在查询器的情况下允许IP组播组成员确定，交换机确定另一个设备当前是否作为交换网络的查询器。 如果没有，交换机会在其一个或多个端口上发送成员资格查询。 响应于成员查询，终端向交换机发送成员资格报告。 交换机记录会员报告中指定的IP组播组成员。

公开(公告)号：US20060165055A1

公开(公告)日：2006-07-27

申请号：US11376666

申请日：2006-03-15

申请人： Randy Ryals ,  Jeffrey Prince ,  H. Ferguson ,  Mike Noll ,  Derek Pitcher

发明人： Randy Ryals ,  Jeffrey Prince ,  H. Ferguson ,  Mike Noll ,  Derek Pitcher

IPC分类号： H04L12/50 ,  H04Q11/00 ,  H04L12/28

CPC分类号： H04L49/25 ,  H04L49/252 ,  H04L49/254 ,  H04L49/30 ,  H04L49/3009 ,  H04L49/3036 ,  H04L49/3045 ,  H04L49/40 ,  H04L49/90 ,  H04L49/901

摘要： A method and apparatus for managing the flow of data within a switching device is provided. The switching device includes network interface cards connected to a common backplane. Each interface card is configured to support the maximum transfer rate of the backplane by maintaining a “pending” queue to track data that has been received but for which the appropriate routing destination has not yet been determined. The switching device includes a switch controller that maintains a central card/port-to-address table. When an interface card receives data with a destination address that is not known to the interface card, the interface card performs a direct memory access over a bus that is separate from the backplane to read routing data directly from the central table in the switch controller. Each interface card builds and maintains a routing information table in its own local memory that only includes routing information for the destination addresses that the interface card is most likely to receive.

公开(公告)号：US06671279B1

公开(公告)日：2003-12-30

申请号：US09257075

申请日：1999-02-24

申请人： Jim Mangin ,  Mohan Kalkunte ,  Derek Pitcher

发明人： Jim Mangin ,  Mohan Kalkunte ,  Derek Pitcher

IPC分类号： H04L1228

CPC分类号： H04L12/5601 ,  H04L2012/5669

摘要： A technique for establishing a shortcut Virtual Channel Connection (VCC) in a Multi-Protocol Over ATM (MPOA) system detects a packet flow, and then determines whether to establish the shortcut VCC based upon an expected MPOA server response time. Specifically, an expected MPOA server response time is determined based upon an MPOA server response time history. The expected MPOA server response time is then compared to a predetermined MPOA server response time threshold to determine whether the expected MPOA server response time is within the predetermined MPOA server response time threshold. The shortcut VCC is established if the expected MPOA server response time is within the predetermined MPOA server response time threshold. Upon establishing the shortcut VCC, the MPOA server response time history is updated to reflect an actual MPOA server response time incurred when establishing the shortcut VCC.

摘要翻译： 在ATM多协议（MPOA）系统中建立快捷虚拟通道连接（VCC）的技术检测分组流，然后基于预期的MPOA服务器响应时间来确定是否建立快捷方式VCC。 具体地，基于MPOA服务器响应时间历史确定预期的MPOA服务器响应时间。 然后将预期的MPOA服务器响应时间与预定的MPOA服务器响应时间阈值进行比较，以确定预期的MPOA服务器响应时间是否在预定的MPOA服务器响应时间阈值内。 如果预期的MPOA服务器响应时间在预定的MPOA服务器响应时间阈值内，则建立快捷方式VCC。 建立快捷方式VCC后，更新MPOA服务器响应时间历史，以反映建立快捷方式VCC时产生的实际MPOA服务器响应时间。

公开(公告)号：US06760336B1

公开(公告)日：2004-07-06

申请号：US09252430

申请日：1999-02-18

申请人： James Mangin ,  Mohan Kalkunte ,  Derek Pitcher

发明人： James Mangin ,  Mohan Kalkunte ,  Derek Pitcher

IPC分类号： G06F1516

CPC分类号： H04L41/5022 ,  H04L43/00 ,  H04L43/062 ,  H04L45/24 ,  H04L45/302 ,  H04L47/24

摘要： A method and a system for improving communication performance between nodes in a network is disclosed. In one embodiment, the system includes routers, switches, and a communication interface. The communication interface detects a communication flow between a source and a destination in response to a flow criteria. Upon detecting the communication flow, the communication interface issues a resolution request for identifying data path. After receipt of a response to the resolution request, multiple connections between switches are established in response to levels of quality of service (QoS).

摘要翻译： 公开了一种提高网络节点间通信性能的方法和系统。 在一个实施例中，系统包括路由器，交换机和通信接口。 通信接口响应于流标准检测源和目的地之间的通信流。 在检测到通信流程时，通信接口发出用于识别数据路径的解析请求。 在接收到对解析请求的响应之后，响应于服务质量（QoS）的等级，建立交换机之间的多个连接。