公开(公告)号：US20060224734A1

公开(公告)日：2006-10-05

申请号：US11378298

申请日：2006-03-20

Applicant: Masaaki Aono

Inventor： Masaaki Aono

IPC: G06F15/173

CPC classification number: G06F11/079 ,  G06F11/0727 ,  G06F11/201

Abstract: A failure analysis system includes a controller A that sends a control command A, a looped interface A, the controller A being selectively connectable to the looped interface A, a node device A that is selectively connectable to the looped interface A, a node device B that is selectively connectable to the looped interface A, and an enclosure service device A that receives the control command A via the node device A. If a failure occurs, the enclosure service device A disconnects the node device B from the looped interface A, and one of: maintains the node device A connected to the looped interface A, and disconnects and subsequently re-connects the node device A to the looped interface A.

Abstract translation: 故障分析系统包括：控制器A，其发送控制命令A，循环接口A，控制器A可选择性地连接到环路接口A;节点设备A，其可选择性地连接到环路接口A;节点设备B 可选择地连接到环路接口A，以及通过节点设备A接收控制命令A的机箱服务设备A.如果故障发生，机箱服务设备A将节点设备B与循环接口A断开连接，并且 其中之一：维护连接到循环接口A的节点设备A，并断开并随后将节点设备A重新连接到循环接口A.

公开(公告)号：US07117310B2

公开(公告)日：2006-10-03

申请号：US10780971

申请日：2004-02-18

Applicant: Paresh Chatterjee ,  Chayan Biswas ,  Ragendra Mishra ,  Senthil Thangaraj

Inventor： Paresh Chatterjee ,  Chayan Biswas ,  Ragendra Mishra ,  Senthil Thangaraj

IPC: G06F12/00

CPC classification number: G06F11/2089 ,  G06F11/201 ,  G06F12/0804 ,  G06F12/0831 ,  G06F12/0866 ,  G06F12/0875

Abstract: Systems and methods for maintaining cache coherency between a first controller and a redundant peer controller while reducing communication overhead processing involved in the coherency message exchange. Header or meta-data information is accumulated in a buffer in a first controller along with updated cache data (if any) and forwarded to the peer controller. The accumulating information may be double buffered so that a buffer is filling as a previously filled buffer is transmitting to the peer controller. The peer controller processes the received information to update its mirror cache to maintain coherency with the first controller's cache memory with respect to dirty data. The method and systems avoid the need to update cache coherency in response to every flush operation performed within the first controller to thereby improve overall system performance.

Abstract translation: 用于在第一控制器和冗余对等控制器之间维持高速缓存一致性的系统和方法，同时减少一致性消息交换中涉及的通信开销处理。 标题或元数据信息与更新的高速缓存数据（如果有的话）一起累积在第一控制器的缓冲器中并转发给对等控制器。 积累的信息可以被双重缓冲，使得缓冲器正在填充，因为先前填充的缓冲器正在发送到对等控制器。 对等控制器处理接收到的信息以更新其镜像高速缓存，以保持与第一控制器的高速缓冲存储器相对于脏数据的一致性。 该方法和系统避免了响应于在第一控制器内执行的每次刷新操作来更新高速缓存一致性，从而提高整体系统性能。

公开(公告)号：US07111120B2

公开(公告)日：2006-09-19

申请号：US11188004

申请日：2005-07-25

Applicant: Kazuhisa Fujimoto ,  Akira Fujibayashi ,  Nobuyuki Minowa

Inventor： Kazuhisa Fujimoto ,  Akira Fujibayashi ,  Nobuyuki Minowa

IPC: G06F12/00

CPC classification number: G06F3/0658 ,  G06F3/061 ,  G06F3/0626 ,  G06F3/0635 ,  G06F3/0689 ,  G06F11/1666 ,  G06F11/2007 ,  G06F11/201 ,  G06F12/084 ,  G06F12/0866

Abstract: This invention relates to a disk array controller. There has been demand for a large scale memory device system operable without interruption. Further, in order to cope with the recent trend toward open systems, scalability of performance and capacity in such systems is needed.Conventionally, internal buses such as ones which connect the channel interface section to the shared memory section, and the disk interface section to the shared memory section, have been mounted on one platter, and the channel interface and other packages have been mounted thereon. If the internal buses have failed, the operation of the whole system must be stopped. There has been another problem that the performance of the internal buses is fixed.A disk array controller according to this invention comprises an interface platter on which a channel interface section and a disk interface section are mounted, a memory platter on which a shared memory section is mounted, and a cable which connects the interface platter to the memory platter in order to solve the above problems.

Abstract translation: 本发明涉及一种磁盘阵列控制器。 需要大量的存储器件系统可操作而不中断。 此外，为了应对最近开放系统的趋势，需要这种系统的性能和容量的可扩展性。 通常，将一个将通道接口部分连接到共享存储器部分的内部总线和共享存储器部分的盘接口部分安装在一个盘片上，并且其上安装了通道接口和其他包装。 如果内部总线出现故障，整个系统的运行必须停止。 另外还有一个问题是内部总线的性能是固定的。 根据本发明的磁盘阵列控制器包括其上安装有通道接口部分和磁盘接口部分的接口拼盘，其上安装有共享存储器部分的存储器盘片和将接口盘连接到存储器盘片的电缆 以解决上述问题。

公开(公告)号：US07089345B1

公开(公告)日：2006-08-08

申请号：US10131387

申请日：2002-04-23

Applicant: William E. Lynn

Inventor： William E. Lynn

IPC: G06F13/00

CPC classification number: G06F3/0635 ,  G06F3/0617 ,  G06F3/0689 ,  G06F11/201 ,  G06F11/2089

Abstract: A method and an apparatus for providing multiple ports to a single port device are provided. According to the present invention, single port devices that are incapable of communicating across a shared communication bus, and therefore require a point to point communication channel, may be interconnected to multiple hosts using a switch assembly. The switch assembly selectively establishes a communication path between a single host and a device. Additionally, the present invention provides a method and apparatus by which computer subsystems, such as RAID storage subsystems, may be implemented using inexpensive storage devices. Furthermore, the present invention provides a method and apparatus for providing a high reliability computer subsystem by configuring the subsystem such that no single active component failure will result in the failure of the entire subsystem.

Abstract translation: 提供了一种用于向单个端口设备提供多个端口的方法和装置。 根据本发明，不能通过共享通信总线进行通信并因此需要点对点通信信道的单端口设备可以使用开关组件互连到多个主机。 开关组件选择性地建立单个主机和设备之间的通信路径。 另外，本发明提供了可以使用廉价的存储设备来实现计算机子系统（诸如RAID存储子系统）的方法和装置。 此外，本发明提供了一种用于通过配置子系统来提供高可靠性计算机子系统的方法和装置，使得没有单个活动组件故障将导致整个子系统的故障。

公开(公告)号：US07088703B2

公开(公告)日：2006-08-08

申请号：US09814642

申请日：2001-03-22

Applicant: Jeremy J. O'Hare ,  Mark J. Halstead

Inventor： Jeremy J. O'Hare ,  Mark J. Halstead

IPC: H04L12/28

CPC classification number: G06F11/2012 ,  G06F3/0605 ,  G06F3/0635 ,  G06F3/0659 ,  G06F3/067 ,  G06F11/201

Abstract: A computer system may include one or more hosts and a plurality of data storage devices for providing multihop system calls. The data storage devices are interconnected and also connected to the one or more hosts. Each data storage device classifies a data operation as a system call, a remote system call, or a multihop system call. Also described is a multipath multihop system call in which one or more communication paths may be selected using predetermined and/or dynamic communication path selection techniques. The number of communication paths determined may be in accordance with parameters that are included in a multipath multihop system call, tunable system parameters, or a combination of the foregoing.

Abstract translation: 计算机系统可以包括用于提供多跳系统呼叫的一个或多个主机和多个数据存储设备。 数据存储设备互连并且也连接到一个或多个主机。 每个数据存储设备将数据操作分类为系统调用，远程系统调用或多跳系统调用。 还描述了多径多跳系统调用，其中可以使用预定和/或动态通信路径选择技术来选择一个或多个通信路径。 确定的通信路径的数量可以根据包括在多径多跳系统呼叫，可调系统参数或前述的组合中的参数。

公开(公告)号：US20060174061A1

公开(公告)日：2006-08-03

申请号：US11396640

申请日：2006-04-04

Applicant: Kentaro Shimada

Inventor： Kentaro Shimada

IPC: G06F12/00

CPC classification number: G06F3/0613 ,  G06F3/0656 ,  G06F3/0689 ,  G06F11/2005 ,  G06F11/2007 ,  G06F11/201 ,  G06F11/2092 ,  G06F12/0866 ,  G06F12/0891

Abstract: Disclosed is a disk array system that can be expanded effectively in scale by increasing the number of input/output channels and disk adapters and improved in such performance as the number of input/output operations per second, data transfer rate. The disk array system is provided with input/output channels to be coupled to a host computer, cache memories coupled to each of input/output channels respectively and used to store input/output data temporarily, disk drives, disk adapters coupled to the disk drives, and network switches used to couple the input/output channels to the disk adapters.

公开(公告)号：US20060117159A1

公开(公告)日：2006-06-01

申请号：US11138299

申请日：2005-05-27

Applicant: Shigeyoshi Ohara ,  Kazunori Masuyama

Inventor： Shigeyoshi Ohara ,  Kazunori Masuyama

IPC: G06F13/28

CPC classification number: G06F3/0689 ,  G06F3/0605 ,  G06F3/0619 ,  G06F3/0629 ,  G06F3/0665 ,  G06F3/0683 ,  G06F11/201 ,  G06F11/2089 ,  G06F12/0866

Abstract: A storage system has a plurality of control modules for controlling a plurality of storage devices, which make mounting easier with maintaining low latency response even if the number of control modules increases. A plurality of storage devices are connected to the second interface of each control module using back end routers, so that redundancy for all the control modules to access all the storage devices is maintained. Also the control modules and the first switch units are connected by a serial bus, which has a small number of signals, constituting the interface by using the back panel. By this, mounting on the printed circuit board becomes possible.

Abstract translation: 存储系统具有用于控制多个存储设备的多个控制模块，即使控制模块的数量增加，这也使得安装更容易，同时保持较低的延迟响应。 使用后端路由器将多个存储设备连接到每个控制模块的第二接口，从而保持所有控制模块对所有存储设备的冗余。 此外，控制模块和第一开关单元通过使用后面板构成接口的具有少量信号的串行总线连接。 由此，可以在印刷电路板上安装。

公开(公告)号：US20060075156A1

公开(公告)日：2006-04-06

申请号：US10994339

申请日：2004-11-23

Applicant: Takuya Okaki ,  Hirofumi Nakamura ,  Hironori Dohi ,  Masayuki Tanabe

Inventor： Takuya Okaki ,  Hirofumi Nakamura ,  Hironori Dohi ,  Masayuki Tanabe

IPC: G06F3/00

CPC classification number: G06F11/201

Abstract: The present invention prompts path switching in accordance with the state of occurrence of intermittent failures, and prevents the responsiveness of a storage system from declining, or the like. Here, it is supposed, for example, that a host 1 is performing data communications with a storage device 2 by means of the path P1, and that an intermittent failure such as a communications time-out has occurred in path P1 on a number of occasions equal to or exceeding the prescribed threshold value. In this case, the controller 3 sends back a hardware error response in reply to an access from the host 1. Upon receiving a hardware error response from the storage device 2, the path control section 1B switches from the path P1 where the intermittent failure was detected (the original path) to a path P2 that is functioning normally (the target path), and then re-attempts the access command. In this way, it is possible to prompt the host 1 to switch the communications path in accordance with the state of occurrence of an intermittent failure, and therefore the responsiveness of the storage device 2 can be maintained.

Abstract translation: 本发明根据间歇性故障的发生状况提示路径切换，防止存储系统的响应性下降等。 这里，例如假设主机1通过路径P 1与存储装置2进行数据通信，并且在路径P 1上发生诸如通信超时的间歇性故障 次数等于或超过规定的阈值。 在这种情况下，控制器3回复来自主机1的访问的硬件错误响应。在从存储设备2接收到硬件错误响应时，路径控制部分1B从路径P 1切换到间歇 检测到正常运行的路径P 2（目标路径）的故障（原始路径），然后重新尝试访问命令。 以这种方式，可以根据间歇性故障的发生状态提示主机1切换通信路径，因此可以保持存储装置2的响应性。

公开(公告)号：US20060047712A1

公开(公告)日：2006-03-02

申请号：US10930869

申请日：2004-09-01

Applicant: Hidehisa Shitomi ,  Yuichi Yagawa

Inventor： Hidehisa Shitomi ,  Yuichi Yagawa

IPC: G06F17/30

CPC classification number: G06F11/201 ,  G06F11/1662 ,  G06F11/2069 ,  G06F11/2094 ,  Y10S707/99953

Abstract: A system and method for automatic failure recovery in a storage system that includes replicating data stored in a first storage volume at a storage system into a second storage volume at the storage system, the first storage volume handling Input/Output (I/O) operations between the storage system and a host device. A failure is detected in the I/O operations with the first storage volume and a recovery process initiated that includes identifying a path from the host device to the second storage volume or a third storage volume to allow continuation of the I/O operations automatically. The third storage volume containing data recovered from the second storage volume.

Abstract translation: 一种用于存储系统中的自动故障恢复的系统和方法，包括将存储在存储系统中的第一存储卷中的数据复制到存储系统处的第二存储卷中的第一存储卷处理输入/输出（I / O）操作 在存储系统和主机设备之间。 在具有第一存储卷的I / O操作中检测到​​故障，并且发起恢复过程，其包括标识从主机设备到第二存储卷的路径或第三存储卷，以允许自动继续I / O操作。 第三个存储卷包含从第二个存储卷恢复的数据。

公开(公告)号：US07000070B2

公开(公告)日：2006-02-14

申请号：US10341446

申请日：2003-01-14

Applicant: Norihiko Moriwaki ,  Kazuhisa Fujimoto

Inventor： Norihiko Moriwaki ,  Kazuhisa Fujimoto

IPC: G06F12/00

CPC classification number: G06F11/201

Abstract: Disclosed herewith is a scalable disk array controller inter-connection network to be employed for a disk array system in which a plurality of disk array controllers connected to each another are expected to be operated as one disk array controller. The inter-connection network enables such disk array controllers to be added/removed without service interruption while the system reliability is kept as is. Each of the plurality of disk array controllers comprises a channel IF unit; a disk IF unit; a cache memory unit; a shared memory unit; means for connecting the channel IF unit/disk IF unit and the cache memory unit; and means for connecting the channel IF unit/disk IF unit and the shared memory unit. The inter-connection network comprises a plurality of switches to be increased in a scalable manner. Each of the switches is inter-connected with other switches with use of a redundant path having a separated physical route. In addition, each of the switches has an output destination table used to set redundant paths and switches between paths after the inter-connection network is modified due to the addition/removal of the above switches. The disk array controller becomes cost-scalable because the disk array controller units can be added/removed to/from the system as required without service interruption while the system reliability is kept as is.

Abstract translation: 本文公开了一种可用于磁盘阵列系统的可扩展磁盘阵列控制器互连网络，其中预期彼此连接的多个磁盘阵列控制器作为一个磁盘阵列控制器操作。 互连网络使这样的磁盘阵列控制器能够在没有服务中断的情况下被添加/删除，同时保持系统的可靠性。 多个盘阵列控制器中的每一个包括一个信道IF单元; 磁盘IF单元; 高速缓冲存储器单元; 共享存储单元; 用于连接信道IF单元/盘IF单元和高速缓冲存储器单元的装置; 以及用于连接信道IF单元/盘IF单元和共享存储器单元的装置。 互连网络包括以可扩展方式增加的多个交换机。 每个交换机使用具有分离的物理路由的冗余路径与其他交换机互连。 此外，每个交换机具有输出目的地表，用于设置由于上述交换机的添加/删除而在互连网络被修改之后的路径之间的冗余路径和交换机。 磁盘阵列控制器具有成本可扩展性，因为可以根据需要在系统中添加/删除磁盘阵列控制器单元，而不会在没有服务中断的情况下保持系统的可靠性。