Error detection and recovery in a storage driver
    1.
    发明申请
    Error detection and recovery in a storage driver 有权
    存储驱动程序中的错误检测和恢复

    公开(公告)号:US20050223279A1

    公开(公告)日:2005-10-06

    申请号:US10819416

    申请日:2004-04-06

    IPC分类号: G06F11/00 G06F11/14

    CPC分类号: G06F11/1435 G06F11/1487

    摘要: A command is received, at a network storage driver, from an operating system storage stack, wherein the command is for communication with a target storage device over a connection across a network. The command is selectively executed, a plurality of times over the connection, for communicating with the target storage device, in response to a determination that the command failed to successfully communicate with the target storage device within a threshold period of time.

    摘要翻译: 在网络存储驱动器处接收来自操作系统存储堆栈的命令,其中该命令用于通过网络上的连接与目标存储设备进行通信。 响应于在阈值时间段内确定命令未能成功地与目标存储设备通信的确定,该命令被选择性地执行连接多次以用于与目标存储设备通信。

    Load balancing and failover
    2.
    发明申请
    Load balancing and failover 失效
    负载平衡和故障切换

    公开(公告)号:US20050259632A1

    公开(公告)日:2005-11-24

    申请号:US10815349

    申请日:2004-03-31

    IPC分类号: H04L12/28 H04L29/08

    摘要: Provided are techniques for static load balancing. For each data path in a network adapter team, a load balancing value is computed. A maximum value of the computed load balancing values is determined. A data path with the maximum value is selected for use in routing data. Also provided are techniques for dynamic load balancing. An actual load balancing share is computed for each data path in a network adapter team. For each data path, it is determined whether a load balancing share for the data path is less than the actual load balancing share for the data path and when the load balancing share is less than the actual load balancing share, the load balancing share of the data path is adjusted. Furthermore, provided are techniques for failover processing. It is determined whether a command may be routed through a first network adapter. The command is routed through the first network adapter in response to determining that the command may be routed through the first network adapter. The command is routed through a second network adapter in response to determining that the command may not be routed through the first network adapter.

    摘要翻译: 提供了静态负载平衡的技术。 对于网络适配器组中的每个数据路径,计算负载平衡值。 确定计算出的负载平衡值的最大值。 选择具有最大值的数据路径用于路由数据。 还提供了用于动态负载平衡的技术。 为网络适配器组中的每个数据路径计算实际负载均衡份额。 对于每个数据路径,确定数据路径的负载均衡共享是否小于数据路径的实际负载平衡共享,并且当负载平衡共享小于实际负载平衡共享时,负载均衡份额 数据路径被调整。 此外,提供了用于故障转移处理的技术。 确定命令是否可以通过第一个网络适配器进行路由。 响应于确定该命令可以通过第一网络适配器路由,该命令被路由通过第一网络适配器。 响应于确定该命令可能不通过第一网络适配器路由,该命令被路由通过第二网络适配器。

    Load balancing and failover
    3.
    发明授权
    Load balancing and failover 失效
    负载平衡和故障切换

    公开(公告)号:US07760626B2

    公开(公告)日:2010-07-20

    申请号:US10815349

    申请日:2004-03-31

    IPC分类号: H04L12/28

    摘要: Provided are techniques for static load balancing. For each data path in a network adapter team, a load balancing value is computed. A maximum value of the computed load balancing values is determined. A data path with the maximum value is selected for use in routing data. Also provided are techniques for dynamic load balancing in which, when a load balancing share of a data path is less than an actual load balancing share, the load balancing share of the data path is adjusted. Furthermore, provided are techniques for failover processing in which a command is routed through a second network adapter in response to determining that the command may not be routed through a first network adaptor.

    摘要翻译: 提供了静态负载平衡的技术。 对于网络适配器组中的每个数据路径,计算负载平衡值。 确定计算出的负载平衡值的最大值。 选择具有最大值的数据路径用于路由数据。 还提供了用于动态负载平衡的技术,其中当数据路径的负载平衡共享小于实际负载平衡共享时,调整数据路径的负载平衡份额。 此外,提供了用于故障转移处理的技术,其中通过第二网络适配器路由命令以响应于确定该命令可能不通过第一网络适配器路由。

    Error detection and recovery in a storage driver
    4.
    发明授权
    Error detection and recovery in a storage driver 有权
    存储驱动程序中的错误检测和恢复

    公开(公告)号:US07373549B2

    公开(公告)日:2008-05-13

    申请号:US10819416

    申请日:2004-04-06

    IPC分类号: G06F11/00

    CPC分类号: G06F11/1435 G06F11/1487

    摘要: A command is received, at a network storage driver, from an operating system storage stack, wherein the command is for communication with a target storage device over a connection across a network. The command is selectively executed, a plurality of times over the connection, for communicating with the target storage device, in response to a determination that the command failed to successfully communicate with the target storage device within a threshold period of time.

    摘要翻译: 在网络存储驱动器处接收来自操作系统存储堆栈的命令,其中该命令用于通过网络上的连接与目标存储设备进行通信。 响应于在阈值时间段内确定命令未能成功地与目标存储设备通信的确定,该命令被选择性地执行连接多次以用于与目标存储设备通信。

    Management of offload operations in a network storage driver
    5.
    发明申请
    Management of offload operations in a network storage driver 审中-公开
    管理网络存储驱动程序中的卸载操作

    公开(公告)号:US20050246443A1

    公开(公告)日:2005-11-03

    申请号:US10815897

    申请日:2004-03-31

    IPC分类号: G06F15/16 H04L29/06 H04L29/08

    CPC分类号: H04L69/12 H04L69/32

    摘要: A network storage driver requests a connection from an offload application, wherein the offload application interfaces with a first network stack implemented in an operating system and a second network stack implemented in a hardware device. The connection is received from the offload application, wherein the received connection is an offloaded connection and is reserved for the network storage driver. Data is communicated over the offloaded connection through the hardware device.

    摘要翻译: 网络存储驱动程序请求卸载应用程序的连接,其中卸载应用程序与在操作系统中实现的第一网络堆栈和在硬件设备中实现的第二网络堆栈进行接口。 从卸载应用接收连接,其中所接收的连接是卸载连接,并且被保留给网络存储驱动器。 通过硬件设备通过卸载的连接传送数据。

    Method and apparatus for supporting port aggregation of serial attached SCSI wide ports via virtual ports
    6.
    发明申请
    Method and apparatus for supporting port aggregation of serial attached SCSI wide ports via virtual ports 审中-公开
    用于通过虚拟端口支持串行连接的SCSI宽端口的端口聚合的方法和装置

    公开(公告)号:US20060194386A1

    公开(公告)日:2006-08-31

    申请号:US11065972

    申请日:2005-02-25

    IPC分类号: H01L21/336

    摘要: An SAS RAID adapter comprises an input-output processor (IOP) and at least two SAS input-output controllers (IOCs). Wherein SAS links coupled to each of the IOCs form “virtual ports” in order to increase performance and maintain availability. The virtual ports across the at least two IOCs have wide port SAS link capability so as to provide performance enhancements similar to a standard SAS wide port. Even if a single IOC failure occurs, downshifting to N/2 links is provided with degraded aggregated bandwidth (data throughput) instead of a failover and/or system shutdown.

    摘要翻译: SAS RAID适配器包括输入输出处理器(IOP)和至少两个SAS输入 - 输出控制器(IOC)。 其中连接到每个IOC的SAS链接形成“虚拟端口”,以便提高性能并保持可用性。 至少两个IOC的虚拟端口具有宽端口SAS链路能力,以提供类似于标准SAS宽端口的性能增强。 即使发生单个IOC故障,降档到N / 2链路也会提供降级的聚合带宽(数据吞吐量),而不是故障转移和/或系统关闭。