公开(公告)号：US20160127267A1

公开(公告)日：2016-05-05

申请号：US14927103

申请日：2015-10-29

Applicant: Broadcom Corporation

Inventor： Amit Kumar ,  William Brad Matthews ,  Bruce Hui Kwan ,  Puneet Agarwal

IPC: H04L12/933 ,  H04L12/947 ,  H04L12/935 ,  H04L12/873

CPC classification number: H04L49/10 ,  H04L49/252

Abstract: A distributed switch architecture supports very high bandwidth applications. For instance, the distributed switch architecture may be implemented for cloud networks. The architecture scales by organizing traffic management components into tiled structures with distributed buffering. The tile structures are replicated and interconnected to perform transfers from ingress to egress using an interconnect bandwidth scheduling algorithm. Bandwidth scaling may be achieved by adding more tiles to achieve higher bandwidth. The interconnect in the architecture may be swapped out depending on implementation parameters, e.g., physical efficiency.

Abstract translation: 分布式交换机架构支持非常高带宽的应用。 例如，可以为云网络实现分布式交换机体系结构。 架构通过将流量管理组件组织到具有分布式缓冲的平铺结构中进行扩展。 复制和互连瓦片结构，以使用互连带宽调度算法执行从入口到出口的传输。 可以通过添加更多的瓦片来实现更高的带宽来实现带宽缩放。 结构中的互连可以根据实现参数例如物理效率来交换。

公开(公告)号：US20150222531A1

公开(公告)日：2015-08-06

申请号：US14259230

申请日：2014-04-23

Applicant: BROADCOM CORPORATION

Inventor： Rupa Budhia ,  Puneet Agarwal

IPC: H04L12/723 ,  H04L12/781

CPC classification number: H04L45/507 ,  H04L45/7453

Abstract: A system and method is provided for creating and detecting prefix-based entropy labels in a multi-protocol label switching communication network. Each label in a label stack is provided with at least a common prefix field and a computed hash field without the use of entropy label indicators (ELIs). Label stacks generated are processed by transit LSRs in an MPLS communications network where the transit LSR uses the first N labels of the label stack to determine the hash computations for load balancing. By scattering prefix-based entropy labels throughout the label stack, the transit LSR uses one or more prefix-based entropy labels for the hash computation.

Abstract translation: 提供了一种用于在多协议标签交换通信网络中创建和检测基于前缀的熵标签的系统和方法。 标签堆栈中的每个标签至少提供有公共前缀字段和计算的散列字段，而不使用熵标签指示符（ELI）。 生成的标签堆栈由MPLS通信网络中的传输LSR处理，其中传输LSR使用标签栈的前N个标签来确定用于负载平衡的哈希计算。 通过在标签堆栈中散布基于前缀的熵标签，传输LSR使用一个或多个基于前缀的熵标签进行散列计算。

公开(公告)号：US09083655B2

公开(公告)日：2015-07-14

申请号：US13803918

申请日：2013-03-14

Applicant: Broadcom Corporation

Inventor： William Brad Matthews ,  Puneet Agarwal ,  Bruce Hui Kwan

IPC: H04L12/26 ,  H04L12/741

CPC classification number: H04L45/74 ,  H04L47/10 ,  H04L49/3018 ,  H04L49/3027 ,  H04L49/506

Abstract: Processing techniques in a network switch help reduce latency in the delivery of data packets to a recipient. The processing techniques include internal cut-through. The internal cut-through may bypass input port buffers by directly forwarding packet data that has been received to an output port. At the output port, the packet data is buffered for processing and communication out of the switch.

Abstract translation: 网络交换机中的处理技术有助于减少向接收方传送数据包的延迟。 处理技术包括内部切入。 内部切断可以通过直接转发已经接收的分组数据到输出端口来旁路输入端口缓冲器。 在输出端口，数据包数据被缓冲，用于处理和通信交换机。

公开(公告)号：US09065755B2

公开(公告)日：2015-06-23

申请号：US13724361

申请日：2012-12-21

Applicant: Broadcom Corporation

Inventor： Bruce Kwan ,  Puneet Agarwal

IPC: H04L12/815 ,  H04L12/933

CPC classification number: H04L47/22 ,  H04L49/10

Abstract: Disclosed are systems and methods for cut-through switching in port-speed-mismatched networks. Specifically, systems and methods are described in which data packets from an ingress device are paced, thereby matching the data rate of the ingress device with the data rate of the egress device.

Abstract translation: 公开了用于端口速度不匹配网络中的直通切换的系统和方法。 具体地说，描述了来自入口设备的数据分组被起步的系统和方法，从而使入口设备的数据速率与出口设备的数据速率相匹配。

公开(公告)号：US20150092591A1

公开(公告)日：2015-04-02

申请号：US14042220

申请日：2013-09-30

Applicant: Broadcom Corporation

Inventor： Brad MATTHEWS ,  Mohan Kalkunte ,  Puneet Agarwal

IPC: H04L12/26

CPC classification number: H04L43/062 ,  H04L47/11 ,  H04L47/30

Abstract: A system and method to monitor network congestion is provided. The system includes a plurality of ingress, egress ports, and a plurality of queues coupled to the ingress and egress ports and configured to store incoming and outgoing packets. The system also includes a monitoring unit configured to monitor at least one attribute of packets in at least one queue when a start condition occurs, stop monitoring the attribute when an end condition occurs, determine a flow that caused the start condition based on the monitored attribute, and report the monitored attribute and the flow.

Abstract translation: 提供了一种监控网络拥塞的系统和方法。 该系统包括多个入口，出口端口和耦合到入口和出口端口的多个队列，并且被配置为存储输入和输出分组。 该系统还包括监视单元，该监视单元被配置为当发生开始条件时监视至少一个队列中的分组的至少一个属性，当结束条件发生时停止监视该属性，基于所监视的属性确定导致开始条件的流 并报告监控的属性和流程。

公开(公告)号：US20140254385A1

公开(公告)日：2014-09-11

申请号：US13857534

申请日：2013-04-05

Applicant: BROADCOM CORPORATION

Inventor： Vahid Tabatabaee ,  Bruce Hui Kwan ,  Puneet Agarwal

IPC: H04L12/801

CPC classification number: H04L47/12 ,  H04L43/062 ,  H04L43/0882 ,  H04L47/11 ,  H04L47/20 ,  H04L47/25 ,  H04L47/26 ,  H04L47/52 ,  H04L47/522 ,  H04L49/15

Abstract: In various embodiments, a system includes a switch comprising a resource that is shared between multiple objects. The switch comprises circuitry that determines a congestion metric for the switch in response to an amount of used of the resource by the objects. The circuitry determines a feedback parameter that is responsive to the congestion metric. The circuitry generates a congestion notification message that comprises a congestion feedback value responsive to the feedback parameter.In further embodiments, a system includes a switch that processes data for a first data link layer access network. The switch includes circuitry that identifies whether a received packet originated from a source device that shares the same network layer access layer as the switch. If the source device shares the same network layer access network as the switch, the circuitry generates a congestion notification message comprising a congestion feedback value for the switch.

Abstract translation: 在各种实施例中，系统包括包括在多个对象之间共享的资源的交换机。 交换机包括响应于由对象使用的资源量来确定交换机的拥塞度量的电路。 电路确定响应于拥塞度量的反馈参数。 电路产生包含响应于反馈参数的拥塞反馈值的拥塞通知消息。 在另外的实施例中，系统包括处理第一数据链路层接入网络的数据的交换机。 交换机包括识别接收到的分组是否源自与交换机共享相同网络层接入层的源设备的电路。 如果源设备与交换机共享相同的网络层接入网络，则电路产生包含交换机的拥塞反馈值的拥塞通知消息。

公开(公告)号：US20140233382A1

公开(公告)日：2014-08-21

申请号：US13827988

申请日：2013-03-14

Applicant: BROADCOM CORPORATION

Inventor： William Brad Matthews ,  Puneet Agarwal ,  Bruce Hui Kwan

IPC: H04L12/70

CPC classification number: H04L47/11 ,  H04L43/0835 ,  H04L43/0882 ,  H04L47/12 ,  H04L47/2458 ,  H04L47/28 ,  H04L49/00

Abstract: Aspects of oversubscription monitoring are described. In one embodiment, oversubscription monitoring includes accumulating an amount of data that arrives at a network component over at least one epoch of time. Further, a core processing rate at which data can be processed by the network component is calculated. Based on the amount of data and the core processing rate, it is determined whether the network component is operating in an oversubscribed region of operation. In one embodiment, when the network component is operating in the oversubscribed region of operation, certain quality of service metrics are monitored. Using the monitored metrics, a network operation display object may be generated for identifying or troubleshooting network errors during an oversubscribed region of operation of the network component.

Abstract translation: 描述超额认购监控的方面。 在一个实施例中，超额预订监视包括在至少一个时代上累积到达网络组件的数据量。 此外，计算网络组件可以处理数据的核心处理速率。 基于数据量和核心处理速率，确定网络组件是否在超额订购的操作区域中运行。 在一个实施例中，当网络组件在超额订购的操作区域中操作时，监视某些服务质量度量。 使用所监视的度量，可以生成网络操作显示对象，用于在网络组件的超额订购的操作区域期间识别或排除网络错误。

公开(公告)号：US20140126573A1

公开(公告)日：2014-05-08

申请号：US13834462

申请日：2013-03-15

Applicant: BROADCOM CORPORATION

Inventor： William Brad Matthews ,  Puneet Agarwal ,  Bruce Hui Kwan

IPC: H04L12/701

CPC classification number: G06Q30/0214 ,  G06Q30/0269 ,  H04L41/00 ,  H04L41/12 ,  H04L41/22 ,  H04L43/00 ,  H04L43/045 ,  H04L43/065 ,  H04L43/067 ,  H04L43/0817 ,  H04L43/10 ,  H04L43/106 ,  H04L45/00 ,  H04L47/10 ,  H04L47/20 ,  H04L47/22 ,  H04L47/522

Abstract: Network devices add annotation information to network packets as they travel through the network devices. The network devices may be switches, routers, bridges, hubs, or any other network device. The annotation information may be information specific to the network devices, as opposed to simply the kinds of information available at application servers that receive the network packets. As just a few examples, the annotation information may include switch buffer levels, routing delay, routing parameters affecting the packet, switch identifiers, power consumption, and heat, moisture, or other environmental data.

Abstract translation: 网络设备在网络数据包通过网络设备时添加注释信息。 网络设备可以是交换机，路由器，网桥，集线器或任何其他网络设备。 注释信息可以是网络设备特有的信息，而不是简单地在接收网络分组的应用服务器处可用的信息的种类。 作为仅举几个示例，注释信息可以包括切换缓冲器级别，路由延迟，影响分组的路由参数，切换标识符，功耗以及热，湿度或其他环境数据。

公开(公告)号：US20140126395A1

公开(公告)日：2014-05-08

申请号：US13827780

申请日：2013-03-14

Applicant: BROADCOM CORPORATION

Inventor： William Brad Matthews ,  Bruce Hui Kwan ,  Puneet Agarwal

IPC: H04L12/70

CPC classification number: H04L47/11 ,  H04L49/15

Abstract: Disclosed are various embodiments that relate to a network switch. The network switch obtains a network state metric, the network state metric quantifying a network traffic congestion associated with a switch. The network switch identifies a synchronous time stamp associated with the network state metric and generates an network state reporting message, the network state reporting message comprising the network state metric and the synchronous time stamp. The network state reporting message may be transmitted to a monitoring system.

Abstract translation: 公开了涉及网络交换机的各种实施例。 网络交换机获得网络状态度量，网络状态量度量化与交换机相关联的网络流量拥塞。 网络交换机识别与网络状态度量相关联的同步时间戳，并生成网络状态报告消息，网络状态报告消息包括网络状态度量和同步时间戳。 网络状态报告消息可以被发送到监视系统。

公开(公告)号：US20140043974A1

公开(公告)日：2014-02-13

申请号：US13724361

申请日：2012-12-21

Applicant: BROADCOM CORPORATION

Inventor： Bruce Kwan ,  Puneet Agarwal

IPC: H04L12/56

CPC classification number: H04L47/22 ,  H04L49/10

Abstract: Disclosed are systems and methods for cut-through switching in port-speed-mismatched networks. Specifically, systems and methods are described in which data packets from an ingress device are paced, thereby matching the data rate of the ingress device with the data rate of the egress device.

Abstract translation: 公开了用于端口速度不匹配网络中的直通切换的系统和方法。 具体地说，描述了来自入口设备的数据分组被起步的系统和方法，从而使入口设备的数据速率与出口设备的数据速率相匹配。