公开(公告)号：US20050094559A1

公开(公告)日：2005-05-05

申请号：US10981815

申请日：2004-11-05

申请人： Qingming Ma ,  Saravanan Agasaveeran ,  Satish Gannu

发明人： Qingming Ma ,  Saravanan Agasaveeran ,  Satish Gannu

IPC分类号： H04L12/56 ,  H04J3/14 ,  H04L12/28

CPC分类号： H04L49/90

摘要： A method includes a step of (A) determining which of multiple network interfaces indicates readiness to transmit a data element to a network and which of the multiple network interfaces indicates receipt of a data element from the network. The method further includes a step of (B) running, for each network interface indicating readiness to transmit a data element to the network, a transmit interrupt handler to load that network interface with a data element for transmission if such a data element is available for transmission within the data communications device, in response to giving higher priority to handling transmit interrupts relative to handling receive interrupts. The method further includes a step of (C) after step B, running, for at least one network interface which indicates receipt of a data element from the network, a receive interrupt handler to process that data element.

摘要翻译： 一种方法包括以下步骤：（A）确定多个网络接口中的哪一个指示准备将数据元素发送到网络，以及多个网络接口中的哪一个指示从网络接收数据元素。 该方法还包括以下步骤：（B）对于指示准备将数据元素发送到网络的每个网络接口，传送中断处理程序将该网络接口加载用于传输的数据元素，如果这样的数据元素可用于 响应于相对于处理接收中断处理发送中断的优先级更高，数据通信设备内的传输。 该方法还包括步骤B（C）之后，对于指示从网络接收到数据元素的至少一个网络接口，运行接收中断处理程序来处理该数据元素。

公开(公告)号：US07558278B2

公开(公告)日：2009-07-07

申请号：US11264883

申请日：2005-11-01

申请人： Zhanhe Shi ,  Qingming Ma ,  Saravanan Agasaveeran ,  Steven H. Berl

发明人： Zhanhe Shi ,  Qingming Ma ,  Saravanan Agasaveeran ,  Steven H. Berl

IPC分类号： H04L12/56

CPC分类号： H04L47/522 ,  H04L47/50 ,  H04L47/521

摘要： Controlling congestion in a networking device having a plurality of input interface queues comprises estimating, in each of one or more sampling states, a data arrival rate for each of the plurality of input interface queues with respect to incoming data packets received on corresponding input interfaces, obtaining a set of estimated arrival rates for the plurality of the input interface queues, determining, for each polling state associated with a respective sampling state, the sequence in which the plurality of input interface queues should be polled using the set of estimated data arrival rates of the plurality of input interface queues, and polling the plurality of interface queues in accordance with the determined sequence. The sequence indicates when, during a single polling cycle, each of the input interface queues should be polled in relation to every other of the input interface queues.

摘要翻译： 控制具有多个输入接口队列的网络设备中的拥塞包括在一个或多个采样状态中的每一个中估计相对于在相应输入接口上接收到的输入数据分组的多个输入接口队列中的每一个的数据到达速率， 获得多个输入接口队列的估计到达速率的集合，对于与相应采样状态相关联的每个轮询状态，确定使用估计数据到达速率的集合来轮询多个输入接口队列的顺序 的多个输入接口队列，并且根据所确定的序列轮询多个接口队列。 该序列指示在单个轮询周期期间，每个输入接口队列应当相对于输入接口队列中的每一个进行轮询。

公开(公告)号：US06798743B1

公开(公告)日：2004-09-28

申请号：US09274091

申请日：1999-03-22

申请人： Qingming Ma ,  Saravanan Agasaveeran ,  Zhanhe Shi ,  Steven Berl

发明人： Qingming Ma ,  Saravanan Agasaveeran ,  Zhanhe Shi ,  Steven Berl

IPC分类号： H04J116

CPC分类号： H04L47/10 ,  H04L47/2416 ,  H04L47/2433 ,  H04L47/2441 ,  H04L47/50 ,  H04L49/90

摘要： A two-phase packet processing technique is provided for routing traffic in a packet-switched, integrated services network which supports a plurality of different service classes. During Phase I, packets are retrieved from the router input interface and classified in order to identify the associated priority level of each packet and/or to determine whether a particular packet is delay-sensitive. If it is determined that a particular packet is delay-sensitive, the packet is immediately and fully processed. If, however, it is determined that the packet is not delay-sensitive, full processing of the packet is deferred and the packet is stored in an intermediate data structure. During Phase II, packets stored within the intermediate data structure are retrieved and fully processes. The technique of the present invention significantly reduces packet processing latency, particularly with respect to high priority or delay-sensitive packets. It is easily implemented in conventional routing systems, imposes little computational overhead, and consumes only a limited amount of memory resources within such systems.

摘要翻译： 提供了一种两相分组处理技术，用于在支持多个不同服务类别的分组交换综合业务网络中路由业务。 在阶段I期间，从路由器输入接口检索分组，并将其分类以识别每个分组的相关优先级和/或确定特定分组是否具有延迟敏感性。 如果确定特定分组是延迟敏感的，则该分组被立即并且被完全处理。 然而，如果确定分组不是延迟敏感的，则分组的完全处理被延迟并且分组被存储在中间数据结构中。 在阶段II期间，存储在中间数据结构内的数据包被检索并完全处理。 本发明的技术显着地减少了分组处理等待时间，特别是在高优先级或延迟敏感分组方面。 它在传统的路由系统中很容易实现，几乎没有计算开销，并且在这样的系统内仅消耗有限量的存储器资源。

公开(公告)号：US06757897B1

公开(公告)日：2004-06-29

申请号：US09515198

申请日：2000-02-29

申请人： Zhanhe Shi ,  Qingming Ma ,  Saravanan Agasaveeran

发明人： Zhanhe Shi ,  Qingming Ma ,  Saravanan Agasaveeran

IPC分类号： G06F900

CPC分类号： G06F9/4881 ,  G06F9/4843 ,  H04L49/90 ,  H04L69/12

摘要： The invention provides unique mechanisms and techniques for a computing device to perform various tasks in a multi-tasking or time sliced environment. A general task scheduling algorithm can select various time slices or priorities for task performance. However, in a dedicated device such as a data communications device, a primary task such as a data transfer task may be so heavily favored by the general task scheduling algorithm, such as in heavy network traffic conditions, that other tasks may be starved of processor time. As such, the system of the invention allows the primary task, to track a first time period Y, and upon expiration of this time period Y, to generate a yield signal to a yielding scheduler. The yielding scheduler can then disable performance of the primary task(s) and track a second time period X during which other tasks may be performed. At the expiration of the second time period X, the primary task(s) which were disabled upon the occurrence of the yield signal are then re-enabled for performance and the yielding scheduler selects a task for performance. Generally, the primary task will again be selected over, for example, lower priority tasks. However, the lower priority tasks will have had a chance to perform irrespective of the general task scheduling algorithm since the primary task(s), which may be heavily scheduled, can control the yielding of processor time. By selecting various values for the time periods X and Y, different aspects of device operation can be controlled to provide a balanced system that can greatly avoid task starvation while also meeting the response time requirements of the primary task and the other lower priority task(s). Since the tasks themselves are given control over the ability to yield time to other tasks, flexibility is provided by the system of the invention.

摘要翻译： 本发明提供用于计算设备在多任务或时间切片环境中执行各种任务的独特机制和技术。 一般任务调度算法可以选择各种时间片或优先级进行任务执行。 然而，在诸如数据通信设备的专用设备中，诸如数据传输任务的主要任务可能被诸如在重型网络业务状况中的一般任务调度算法那么大地受到其他任务可能缺乏处理器 时间。 因此，本发明的系统允许主要任务跟踪第一时间段Y，并且在该时间段Y期满时，生成到收益调度器的收益信号。 然后，生产调度器可以禁用主要任务的性能，并跟踪可执行其他任务的第二时间段X. 在第二时间段X到期时，在产生信号发生时被禁用的主要任务然后被重新启用以执行性能，并且生产调度器选择执行任务。 通常，主要任务将再次通过例如较低优先级的任务进行选择。 然而，较低优先级的任务将具有执行的机会，而不考虑通用任务调度算法，因为可能被大量调度的主要任务可以控制处理器时间的产生。 通过选择时间段X和Y的各种值，可以控制设备操作的不同方面，以提供一个平衡的系统，可以大大避免任务匮乏，同时满足主要任务和其他较低优先级任务的响应时间要求 ）。 由于任务本身可以控制对其他任务产生时间的能力，因此本发明的系统提供了灵活性。

公开(公告)号：US06594709B1

公开(公告)日：2003-07-15

申请号：US09405612

申请日：1999-09-24

申请人： Saravanan Agasaveeran ,  Rajesh Agrawal ,  James Balestriere ,  Steven Berl ,  Gordon Cox ,  Satish Gannu ,  Aniruddha Khare ,  M. Salim Olime ,  John G. Waclawsky

发明人： Saravanan Agasaveeran ,  Rajesh Agrawal ,  James Balestriere ,  Steven Berl ,  Gordon Cox ,  Satish Gannu ,  Aniruddha Khare ,  M. Salim Olime ,  John G. Waclawsky

IPC分类号： G06F1310

CPC分类号： G06F11/1492 ,  G06F9/54 ,  G06F11/004 ,  G06F11/1487

摘要： The invention is directed to techniques for transferring data using a device driver that is arranged to prevent improper operation of a non-primary routine (e.g., an administrative operation) from causing improper operation of a primary routine (e.g., a data transfer operation). Accordingly, the primary routine can continue to operate properly after a failure of the non-primary routine. In one arrangement, a data communications device transfers data. The data communications device includes a port that couples to a network, and a processor coupled to the port. The data communications device further includes memory, coupled to the processor, that stores a device driver. The device driver has a first set of instructions that directs the processor to perform a data transfer routine that moves data between memory and the port, and a second set of instructions that directs the processor to perform an administrative routine. The second set of instructions is arranged to prevent improper operation of the administrative routine from causing improper operation of the data transfer routine. In particular, execution and communication mechanisms enable the primary and administrative routines to operate in such a fault-tolerant manner.

摘要翻译： 本发明涉及用于使用被设置为防止非主要例程（例如，管理操作）的不正确操作导致主程序（例如，数据传送操作）的不正确操作的设备驱动程序来传送数据的技术。 因此，主程序可以在非主程序故障之后继续正常运行。 在一种布置中，数据通信设备传送数据。 数据通信设备包括耦合到网络的端口和耦合到该端口的处理器。 数据通信设备还包括存储设备驱动器的存储器，其耦合到处理器。 设备驱动器具有指导处理器执行在存储器和端口之间移动数据的数据传输例程的第一组指令，以及指示处理器执行管理程序的第二组指令。 第二组指令被设置为防止管理程序的不正常操作导致数据传输例程的不正确操作。 特别地，执行和通信机制使主要和管理例程能够以这样的容错方式运行。

公开(公告)号：US07395356B2

公开(公告)日：2008-07-01

申请号：US10981815

申请日：2004-11-05

申请人： Qingming Ma ,  Saravanan Agasaveeran ,  Satish Gannu

发明人： Qingming Ma ,  Saravanan Agasaveeran ,  Satish Gannu

IPC分类号： G06F15/16 ,  G06F15/173 ,  H04L12/56

CPC分类号： H04L49/90

摘要： A method includes a step of (A) determining which of multiple network interfaces indicates readiness to transmit a data element to a network and which of the multiple network interfaces indicates receipt of a data element from the network. The method further includes a step of (B) running, for each network interface indicating readiness to transmit a data element to the network, a transmit interrupt handler to load that network interface with a data element for transmission if such a data element is available for transmission within the data communications device, in response to giving higher priority to handling transmit interrupts relative to handling receive interrupts. The method further includes a step of (C) after step B, running, for at least one network interface which indicates receipt of a data element from the network, a receive interrupt handler to process that data element.

摘要翻译： 一种方法包括以下步骤：（A）确定多个网络接口中的哪一个指示准备将数据元素发送到网络，以及多个网络接口中的哪一个指示从网络接收数据元素。 该方法还包括以下步骤：（B）对于指示准备将数据元素发送到网络的每个网络接口，传送中断处理程序将该网络接口加载到数据元素以进行传输，如果这样的数据元素可用于 响应于相对于处理接收中断处理发送中断的优先级更高，数据通信设备内的传输。 该方法还包括步骤B（C）之后，对于指示从网络接收到数据元素的至少一个网络接口，运行接收中断处理程序来处理该数据元素。

公开(公告)号：US20060062152A1

公开(公告)日：2006-03-23

申请号：US11264883

申请日：2005-11-01

申请人： Zhanhe Shi ,  Qingming Ma ,  Saravanan Agasaveeran ,  Steven Berl

发明人： Zhanhe Shi ,  Qingming Ma ,  Saravanan Agasaveeran ,  Steven Berl

IPC分类号： H04J1/16

CPC分类号： H04L47/522 ,  H04L47/50 ,  H04L47/521

摘要： A rate-based congestion control technique for internetworking devices having a plurality of input interface queues is disclosed. Rate-based polling comprises estimating the data arrival on each input interface queue while in a first sampling state, and separately, while in a second polling state, using the estimated data arrival rate on each input interface queue to determine both the sequence in which the input interface queues should be polled and the number of packets to be processed from each input interface queue. While in the polling state, data packet delay is averaged across the input interface queues so as to process the packets in their approximate arrival order irrespective of the input interface queue on which they arrive, thus enabling Quality of Service policies to be more effective. This is achieved by processing data from each input interface at a rate that is proportional to the data arrival rate at each input interface. Rate-based polling reduces possibly lengthy delay of a packet in an input interface queue, and also avoids possible packet loss caused by long waiting time of data packets in an input interface queue with limited buffer space.

摘要翻译： 公开了一种具有多个输入接口队列的互联网络设备的基于速率的拥塞控制技术。 基于速率的轮询包括在处于第一采样状态时估计每个输入接口队列上的数据到达，并且在第二轮询状态下分别使用每个输入接口队列上的估计数据到达速率来确定其中 输入接口队列应该被轮询，并从每个输入接口队列中处理的数据包数。 在轮询状态下，在输入接口队列之间对数据分组延迟进行平均，以便处理它们的近似到达顺序的分组，而不考虑它们到达的输入接口队列，从而使服务质量策略更有效。 这是通过以与每个输入接口处的数据到达速率成比例的速率处理来自每个输入接口的数据来实现的。 基于速率的轮询减少了输入接口队列中分组的可能的冗长延迟，并且还避免了由于具有有限缓冲空间的输入接口队列中的数据分组的长等待时间引起的可能的分组丢失。

公开(公告)号：US20120124430A1

公开(公告)日：2012-05-17

申请号：US12948457

申请日：2010-11-17

申请人： Srinivas Dharmasanam ,  Eitan Ben-Nun ,  Saravanan Agasaveeran

发明人： Srinivas Dharmasanam ,  Eitan Ben-Nun ,  Saravanan Agasaveeran

IPC分类号： G06F15/16 ,  G06F11/07

CPC分类号： H04L12/12 ,  H04L67/40 ,  Y02D50/30 ,  Y02D50/40

摘要： Consistent with embodiments of the present invention, a method may be provided comprising sending a first bind request with an association group ID of zero. A first association group with a first association group ID may then be created. The first association group ID may be switched to a second association group ID in an acknowledgement message. A second bind request may then be sent with the second association group ID. The second association group ID may be switched to the first association group ID in the second bind request after the bind request has been sent. After receiving the second bind request, it may be determined whether the association group ID in the second bind request is the same as the first association group ID. A failure message may be sent if the association group ID in the second bind request is not the same as the first association group ID.

摘要翻译： 根据本发明的实施例，可以提供一种方法，包括发送具有零的关联组ID的第一绑定请求。 然后可以创建具有第一关联组ID的第一关联组。 第一关联组ID可以切换到确认消息中的第二关联组ID。 然后可以用第二关联组ID发送第二绑定请求。 在发送绑定请求之后，第二关联组ID可以切换到第二绑定请求中的第一关联组ID。 在接收到第二绑定请求之后，可以确定第二绑定请求中的关联组ID是否与第一关联组ID相同。 如果第二绑定请求中的关联组ID与第一关联组ID不相同，则可以发送失败消息。

公开(公告)号：US07484011B1

公开(公告)日：2009-01-27

申请号：US10681870

申请日：2003-10-08

申请人： Saravanan Agasaveeran ,  Anantha Ramaiah

发明人： Saravanan Agasaveeran ,  Anantha Ramaiah

IPC分类号： G06F15/16

CPC分类号： H04L29/12377 ,  H04L61/2517 ,  H04L63/1441 ,  H04L63/166 ,  H04L67/02

摘要： A system for filtering transport layer connections with application layer connection outcomes provides a connection database to store information about connection requests and associated application layer outcomes. The system further includes a throttle filter populated with data from the connection database. The throttle filter is a list of connection requestor identifier, such as IP addresses or port numbers, to be used to identify connection requests to be blocked based on previous connection requests from the connection requesters. The system provides attack and overload protection and load balancing in embedded systems.

摘要翻译： 用于通过应用层连接结果过滤传输层连接的系统提供了连接数据库来存储有关连接请求和相关应用层结果的信息。 该系统还包括填充有来自连接数据库的数据的节流过滤器。 节流滤波器是根据来自连接请求者的先前连接请求，用于识别要阻止的连接请求的连接请求者标识符（例如IP地址或端口号）的列表。 该系统在嵌入式系统中提供攻击和过载保护和负载平衡。

公开(公告)号：US06977895B1

公开(公告)日：2005-12-20

申请号：US09533517

申请日：2000-03-23

申请人： Zhanhe Shi ,  Qingming Ma ,  Saravanan Agasaveeran ,  Steven H. Berl

发明人： Zhanhe Shi ,  Qingming Ma ,  Saravanan Agasaveeran ,  Steven H. Berl

IPC分类号： H04J1/16 ,  H04L12/56

CPC分类号： H04L47/522 ,  H04L47/50 ,  H04L47/521

摘要： The congestion control in a networking device having a plurality of input interface queues includes (a) estimating the data arrival rate on each of the plurality of input interface queues, and (b) determining, for each polling round, the sequence in which the plurality of input interface queues should be polled and the quantity of data to be processed from each of the plurality of input interface queues each time the input interface queue is polled, using the estimated data arrival rate on each of the plurality of input interface queues.

摘要翻译： 具有多个输入接口队列的网络设备中的拥塞控制包括（a）估计多个输入接口队列中的每一个上的数据到达速率，以及（b）为每个轮询轮确定多个 应当使用多个输入接口队列中的每个输入接口队列上的估计数据到达速率轮询每个输入接口队列并且每次输入接口队列轮询时从多个输入接口队列中的每个输入接口队列处理的数据量。