公开(公告)号：US20060090116A1

公开(公告)日：2006-04-27

申请号：US10960607

申请日：2004-10-07

申请人： James Gallagher ,  Binh Hua ,  Sivarama Kodukula ,  Bruce Ratcliff

发明人： James Gallagher ,  Binh Hua ,  Sivarama Kodukula ,  Bruce Ratcliff

IPC分类号： H03M13/00

CPC分类号： H03M13/09 ,  H04L1/004 ,  H04L1/0061 ,  H04L2001/0094

摘要： Method, system and computer program product for protecting the integrity of data transferred between an input/output bus of a data processing system and an external network. A method for protecting the integrity of data transferred between an input/output bus and a network includes generating a Cyclic Redundancy Check (CRC) value on an interface between the input/output bus and an adapter for data being transferred from the input/output bus to the network, and checking a CRC value on the interface between the input/output bus and the adapter for data being transferred from the network to the input/output bus. By adding a CRC generator and a CRC checker on the interface between the input/output bus and the adapter, end-to-end data integrity protection is provided for data transferred between the input/output bus and the network.

摘要翻译： 用于保护在数据处理系统的输入/输出总线与外部网络之间传送的数据完整性的方法，系统和计算机程序产品。 一种用于保护在输入/输出总线和网络之间传输的数据的完整性的方法包括在输入/输出总线与适配器之间的接口上产生循环冗余校验（CRC）值，以便从输入/输出总线 并且检查输入/输出总线和适配器之间的接口上的CRC值，以便数据从网络传输到输入/输出总线。 通过在输入/输出总线和适配器之间的接口上添加CRC生成器和CRC校验器，为输入/输出总线和网络之间传输的数据提供端到端的数据完整性保护。

公开(公告)号：US20050010837A1

公开(公告)日：2005-01-13

申请号：US10616848

申请日：2003-07-10

申请人： James Gallagher ,  Binh Hua ,  Sivarama Kodukula

发明人： James Gallagher ,  Binh Hua ,  Sivarama Kodukula

IPC分类号： G06F11/00 ,  G06F11/20

CPC分类号： G06F11/2005 ,  G06F11/2017

摘要： A method, apparatus and computer instructions for handling a failure of a primary adapter in a data processing system. The primary adapter is monitored for the failure by the device driver. A standby adapter handled by the device driver is switched in place of the primary adapter in response to detecting the failure.

摘要翻译： 一种用于处理数据处理系统中的主适配器的故障的方法，装置和计算机指令。 监视主适配器的设备驱动程序的故障。 响应于检测到故障，由设备驱动程序处理的备用适配器被替换为主适配器。

公开(公告)号：US20070233930A1

公开(公告)日：2007-10-04

申请号：US11375493

申请日：2006-03-14

申请人： James Gallagher ,  David Galvin ,  Binh Hua ,  Sivarama Kodukula

发明人： James Gallagher ,  David Galvin ,  Binh Hua ,  Sivarama Kodukula

IPC分类号： G06F13/40

CPC分类号： G06F13/4018

摘要： A peripheral component Interconnect (PCI) switch that has at least one control logic device that is capable of changing, on-demand, widths of dedicated buses is provided. The buses are PCI Express buses and thus, are composed of lanes. The control logic device is a lane enable register (LER). Each location in the LER corresponds to a lane of a dedicated bus and is used to enable or disable the corresponding lane. Consequently, widths of dedicated buses are changed by using the switch of the invention to add or subtract one or more lanes from the buses.

摘要翻译： 提供了具有能够改变专用总线宽度的至少一个控制逻辑器件的外围部件互连（PCI）交换机。 公共汽车是PCI Express巴士，因此由车道组成。 控制逻辑器件是通道使能寄存器（LER）。 LER中的每个位置对应于专用总线的通道，并用于启用或禁用相应的通道。 因此，通过使用本发明的开关来改变专用总线的宽度以从总线中增加或减少一个或多个车道。

公开(公告)号：US20060077950A1

公开(公告)日：2006-04-13

申请号：US10960586

申请日：2004-10-07

申请人： James Gallagher ,  Binh Hua ,  Hong Hua ,  Sivarama Kodukula

发明人： James Gallagher ,  Binh Hua ,  Hong Hua ,  Sivarama Kodukula

IPC分类号： H04L12/28

CPC分类号： H04L47/10 ,  H04L47/283

摘要： Method, system and computer program product for transferring data in a data processing system network. A method for transferring data in a data processing system network according to the invention includes determining an adapter among a plurality of adapters that has the lowest transmit latency, and assigning data to be transferred to the adapter determined to have the lowest transmit latency. The data to be transferred is then transferred by the assigned adapter. The present invention utilizes network adapters to transfer data in a more efficient manner.

摘要翻译： 用于在数据处理系统网络中传输数据的方法，系统和计算机程序产品。 根据本发明的用于在数据处理系统网络中传送数据的方法包括：确定具有最低发射延迟的多个适配器之间的适配器，以及将要传送到适配器的数据分配给确定具有最低发射延迟的适配器。 要转让的数据然后由分配的适配器传输。 本发明利用网络适配器以更有效的方式传输数据。

公开(公告)号：US20050204080A1

公开(公告)日：2005-09-15

申请号：US10798934

申请日：2004-03-11

申请人： James Gallagher ,  Ron Gonzalez ,  Binh Hua ,  Sivarama Kodukula

发明人： James Gallagher ,  Ron Gonzalez ,  Binh Hua ,  Sivarama Kodukula

IPC分类号： G06F13/10

CPC分类号： G06F9/5016 ,  G06F2209/5011

摘要： A method, system, and computer program product in a data processing system are disclosed for dynamically selecting software buffers for aggregation in order to optimize system performance. Data to be transferred to a device is received. The data is stored in a chain of software buffers. Current characteristics of the system are determined. Software buffers to be combined are then dynamically selected. This selection is made according to the characteristics of the system in order to maximize performance of the system.

摘要翻译： 公开了一种数据处理系统中的方法，系统和计算机程序产品，用于动态选择用于聚合的软件缓冲器，以优化系统性能。 接收要传输到设备的数据。 数据存储在软件缓冲区链中。 确定系统的当前特性。 然后动态选择要组合的软件缓冲区。 该选择是根据系统的特性进行的，以便最大限度地提高系统性能。

公开(公告)号：US20080101217A1

公开(公告)日：2008-05-01

申请号：US11966390

申请日：2007-12-28

申请人： BINH HUA ,  Hong Hua ,  Sivarama Kodukula

发明人： BINH HUA ,  Hong Hua ,  Sivarama Kodukula

IPC分类号： H04L1/00

CPC分类号： H04L47/266 ,  H04L41/0672 ,  H04L47/18

摘要： A method, system, and computer program product are disclosed in a data processing system for avoiding data loss during network port recovery. A first network port is linked to a second network port via a network. The second network port transmits data to the first network port via the network. A determination is made that the first network port needs to be reinitialized. Prior to the first network port executing a re-initialization process, the first network port notifies the second network port to pause its data transmissions to the first network port.

摘要翻译： 在数据处理系统中公开了一种方法，系统和计算机程序产品，用于避免网络端口恢复期间的数据丢失。 第一个网络端口通过网络链接到第二个网络端口。 第二个网络端口通过网络向第一个网络端口发送数据。 确定第一个网络端口需要重新初始化。 在第一网络端口执行重新初始化过程之前，第一网络端口通知第二网络端口将其数据传输暂停到第一网络端口。

公开(公告)号：US20060085569A1

公开(公告)日：2006-04-20

申请号：US10965633

申请日：2004-10-14

申请人： Patrick Buckland ,  Binh Hua ,  Sivarama Kodukula

发明人： Patrick Buckland ,  Binh Hua ,  Sivarama Kodukula

IPC分类号： G06F13/28

CPC分类号： G06F13/28 ,  G06F12/1081

摘要： A number of DMA addresses are resolved to system memory addresses at a time to decrease latency time. The number of addresses resolved at a time is preferably correlated to the number of DMA addresses that can be stored in a single cache line. Additionally, system memory is allocated in larger blocks that can store all of the information from the DMA addresses in a cache line. No change is required to the operating system, which can continue to operate on the page size it is set for. All changes are made in the hardware mapping programs and in the device driver software.

摘要翻译： 一次DMA地址一次解析为系统内存地址，以减少延迟时间。 一次解析的地址的数量优选地与可以存储在单个高速缓存行中的DMA地址的数量相关。 另外，系统存储器被分配在较大的块中，其可以存储来自高速缓存行中的DMA地址的所有信息。 操作系统不需要更改，可以根据设置的页面大小继续操作。 所有更改都在硬件映射程序和设备驱动程序软件中进行。

公开(公告)号：US20050015564A1

公开(公告)日：2005-01-20

申请号：US10621931

申请日：2003-07-17

申请人： Herman Dierks ,  Binh Hua ,  Sivarama Kodukula

发明人： Herman Dierks ,  Binh Hua ,  Sivarama Kodukula

IPC分类号： G06F12/04 ,  G06F12/00

CPC分类号： G06F12/04

摘要： A method, apparatus, and computer instructions for transferring data from a memory to a network adapter. A request is received to transfer data to a network adapter. An offset is set for a starting address of the data to align the data with an end of a frame in the memory, wherein the frame is transferred from the memory to the network adapter.

摘要翻译： 一种用于将数据从存储器传送到网络适配器的方法，装置和计算机指令。 接收到将数据传送到网络适配器的请求。 为数据的起始地址设置偏移量以将数据与存储器中的帧的结尾对准，其中帧从存储器传送到网络适配器。

公开(公告)号：US20070195704A1

公开(公告)日：2007-08-23

申请号：US11363291

申请日：2006-02-23

申请人： Ron Gonzalez ,  Binh Hua ,  Sivarama Kodukula ,  Rakesh Sharma

发明人： Ron Gonzalez ,  Binh Hua ,  Sivarama Kodukula ,  Rakesh Sharma

IPC分类号： H04L12/26

CPC分类号： H04L41/0672 ,  G06F11/0709 ,  G06F11/0757 ,  H04L41/0677 ,  H04L43/0817 ,  H04L43/16

摘要： A computer implemented method, apparatus, and computer usable program code for monitoring health of a data processing system. A determination is made whether a response is received within a first time period in response to an I/O device sending a receive descriptor to the data processing system. A determination is made whether a second time period passes before the receive descriptor becomes available for sending to the data processing system in response to an unavailability of the receive descriptor for sending by the I/O device to the data processing system. A health check is performed on the data processing system if the first time period passes without receiving a response. A health check is performed on the data processing system if the second time period passes without a receive descriptor becoming available to send the data processing system.

摘要翻译： 一种用于监测数据处理系统的健康的计算机实现的方法，装置和计算机可用程序代码。 确定响应于向数据处理系统发送接收描述符的I / O设备在第一时间段内是否接收到响应。 响应于由I / O设备发送到数据处理系统的接收描述符的不可用性，确定在接收描述符可用于向数据处理系统发送之前第二时间段是否经过。 如果第一个时间段通过而不接收到响应，则在数据处理系统上执行健康检查。 如果第二时间段通过而没有接收描述符可用于发送数据处理系统，则在数据处理系统上执行健康检查。

公开(公告)号：US20070255819A1

公开(公告)日：2007-11-01

申请号：US11380993

申请日：2006-05-01

申请人： Binh Hua ,  Sivarama Kodukula

发明人： Binh Hua ,  Sivarama Kodukula

IPC分类号： G06F15/173

CPC分类号： H04L45/00 ,  H04L45/245 ,  H04L45/28 ,  Y02D50/30

摘要： Methods and arrangements to monitor communication components such as a network adapters for activity, and identify components that have lower than normal levels of activity are provided. An identified communication component can become suspect component and a candidate for further testing, including different forms of interrogation. Process for interrogating candidates can include generating and sending test packets having the media access control (MAC) address of the candidate to the candidate and if activity is not detected subsequent to the interrogation, the candidate can be flagged as a failed component. Correspondingly, the component can be deactivated and removed from service. In a further embodiment, a backup component can be activated and assume the role previously held by the failed component.

摘要翻译： 提供了监视诸如用于活动的网络适配器的通信组件以及识别具有低于正常活动水平的组件的方法和安排。 识别的通信组件可以成为可疑组件和进一步测试的候选者，包括不同形式的询问。 用于询问候选的过程可以包括生成并发送具有候选者的媒体访问控制（MAC）地址的测试分组给候选者，并且如果在询问之后没有检测到活动，则可以将候选者标记为失败的分量。 相应地，组件可以被禁用并从服务中移除。 在另一实施例中，可以激活备份组件并承担先前由故障组件保持的角色。