公开(公告)号：JP2007233961A

公开(公告)日：2007-09-13

申请号：JP2006058259

申请日：2006-03-03

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： INAGAKI TAKESHI

IPC: G06F12/00

CPC classification number: G06F11/1461 ,  G06F11/1451

Abstract: PROBLEM TO BE SOLVED: To shorten and even out time for individual backups while holding the number of media required for restoration within a predetermined number. SOLUTION: A system comprising a data storage part 11 for storing backup target data, a backup medium 15 for recording backup data, and a first access part 13 and a second access part 14 for backing up and restoring data between the data storage part 11 and the backup medium 15 is provided with the function of deciding data to be backed up. The function comprises an information storage part 16 for storing management information about backup jobs that have been executed, an acquisition part 17 for acquiring the management information, a decision part 18 for specifying data that has not been backed up for a fixed period according to the management information to decide that the data be backed up, and an updating part 19 for updating the management information. COPYRIGHT: (C)2007,JPO&INPIT

Abstract translation: 要解决的问题：为了缩短和排除单个备份的时间，同时保持在预定数量内恢复所需的媒体数量。 解决方案：一种系统，包括用于存储备份目标数据的数据存储部分11，用于记录备份数据的备份介质15，以及用于在数据存储器之间备份和恢复数据的第一访问部分13和第二访问部分14 部分11和备份介质15具有确定要备份的数据的功能。 该功能包括用于存储关于已经执行的备份作业的管理信息的信息存储部分16，用于获取管理信息的获取部分17，用于根据所述用于指定固定时间段未被备份的数据的判定部分18 决定备份数据的管理信息，以及更新管理信息的更新部19。 版权所有（C）2007，JPO＆INPIT

公开(公告)号：JP2007156850A

公开(公告)日：2007-06-21

申请号：JP2005351415

申请日：2005-12-06

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： MIWA YOICHI ,  MINAMI AYA ,  INAGAKI TAKESHI

IPC: G06F15/80 ,  G06F15/173

CPC classification number: H04L45/14

Abstract: PROBLEM TO BE SOLVED: To configure a communication network comprising a plurality of communication nodes more efficiently. SOLUTION: The communication system is provided with: a communication link for connecting interactively the plurality of communication nodes arranged at adjacent grid points when the plurality of communication nodes and the respective plurality of communication nodes are arranged at pre-determined grid points in grid space composing a three-dimensional rectangular solid; and a shortcut link for connecting a communication node composing one side and a communication composing the other with respect to two sides at least which are not terminal sides in the grid space out of sides comprising the communication nodes in which no communication node is arranged at any adjacent grid points. COPYRIGHT: (C)2007,JPO&INPIT

Abstract translation: 要解决的问题：更有效地配置包括多个通信节点的通信网络。 解决方案：通信系统设置有：当多个通信节点和相应的多个通信节点布置在预定的网格点时交互地连接布置在相邻网格点处的多个通信节点的通信链路 网格空间构成三维矩形实体; 以及快速链接，用于将构成一侧的通信节点和构成另一方的通信至少不在网格空间中的不包括没有通信节点布置在任何通信节点的通信节点的边的两侧 相邻网格点。 版权所有（C）2007，JPO＆INPIT

公开(公告)号：JP2004005068A

公开(公告)日：2004-01-08

申请号：JP2002158262

申请日：2002-05-30

Applicant: IBM

Inventor： INAGAKI TAKESHI

IPC: G06F3/06 ,  G06F11/14 ,  G06F12/00 ,  G06F13/00 ,  G06F15/177 ,  H04L29/08

Abstract: PROBLEM TO BE SOLVED: To provide a backup management device for efficiently performing the backup of data to a remote place while dispersing the load of a network. SOLUTION: In this backup management device, the data to be backed up, which is stored in a backup original recording device, is transmitted to at least one backup designation recording device through the network and backed up. This device has: a load derivation part for determining the load distribution of the network; a backup designation selection part for selecting at least one backup designation recording device that is the transmitting designation of the data from a plurality of backup designation candidate recording devices; and a data transmission part for transmitting the data to at least the one backup designation recording device selected by the backup designation selection part. COPYRIGHT: (C)2004,JPO

公开(公告)号：JP2003345644A

公开(公告)日：2003-12-05

申请号：JP2002155136

申请日：2002-05-29

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーション

Inventor： INAGAKI TAKESHI

IPC: G06F3/06 ,  G06F12/00 ,  G06F13/00 ,  G06F15/16 ,  G06F15/177

CPC classification number: G06F3/0607 ,  G06F3/0613 ,  G06F3/0635 ,  G06F3/067

Abstract: PROBLEM TO BE SOLVED: To provide an inexpensive, high-speed, and large-capacity file system which is expansible in functions and can redundantly store data.
SOLUTION: A connection switching device 5 is provided on the side of a communication line 2 of a plurality of file servers 3a and 3b, and is equipped internally with: a communication control part 31; a signal processing part 33 which imparts a code indicating a head to the file identifier of the communication packet at the head; a switching part 34 which switches connections for selecting a communication packet; a file server switching order storage part 35; and a table storage part 38 which stores file identifiers set by files stored in the file servers 3a and 3b in the form of a table. Then the connection switching device 5 forms, when reading files out of the file servers 3a and 3b, a table in the table storage part 28 and sends the files read out of the file servers in the order of the table.
COPYRIGHT: (C)2004,JPO

Abstract translation: 要解决的问题：提供廉价，高速和大容量的文件系统，其可扩展的功能并且可以冗余地存储数据。 解决方案：连接切换装置5设置在多个文件服务器3a和3b的通信线路2的一侧，并且内部配备有通信控制部分31; 信号处理部33，其将表示头部的代码赋予头部的通信包的文件标识; 切换部分34，其切换用于选择通信分组的连接; 文件服务器切换顺序存储部35; 以及表存储部分38，其以表格的形式存储由存储在文件服务器3a和3b中的文件所设置的文件标识符。 然后，当从文件服务器3a和3b中读出文件时，连接切换装置5形成表存储部分28中的表，并以表的顺序发送从文件服务器读出的文件。 版权所有（C）2004，JPO

公开(公告)号：JP2009098941A

公开(公告)日：2009-05-07

申请号：JP2007269971

申请日：2007-10-17

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： WATANABE TERUE ,  FUJIWARA SHINOBU ,  INAGAKI TAKESHI ,  MIMA SHINSUKE ,  TSURUTA KAZUHIRO

IPC: G06F12/00 ,  G06F3/06

CPC classification number: G06F11/3485 ,  G06F3/0605 ,  G06F3/065 ,  G06F3/0653 ,  G06F3/0685 ,  G06F11/3419 ,  G06F11/3452

Abstract: PROBLEM TO BE SOLVED: To provide a technique for selecting the optimum storage device among the plurality of storage devices as the copy or movement source of data.
SOLUTION: A controller for connecting the different kinds of storage devices includes: a performance information storage part for storing performance information of each storage device; a list storage part for storing the list of data in each storage device; a monitor part for monitoring the load states of each storage device and the controller; a detecting part; an estimating part; and a determining part. When data is copied, etc., with respect to a certain storage device, the detecting part detects the storage devices for storing the data to be copied, based on the list. The estimating part estimates copying time with respect to the detected each storage device, based on performance information and load information. The determining part determines the storage device to be the copy source, based on the estimation result.
COPYRIGHT: (C)2009,JPO&INPIT

Abstract translation: 要解决的问题：提供一种用于选择多个存储装置中的最佳存储装置作为数据的复制或移动源的技术。 解决方案：用于连接不同种类的存储设备的控制器包括：性能信息存储部分，用于存储每个存储设备的性能信息; 列表存储部，用于存储每个存储装置中的数据列表; 用于监视每个存储设备和控制器的负载状态的监视器部分; 检测部 估计部分; 和决定部分。 当相对于某个存储装置复制数据等时，检测部分根据列表来检测用于存储要复制的数据的存储装置。 估计部分基于性能信息和负载信息来估计相对于检测到的每个存储设备的复制时间。 决定部基于估计结果来确定存储装置为复制源。 版权所有（C）2009，JPO＆INPIT

公开(公告)号：JP2008165531A

公开(公告)日：2008-07-17

申请号：JP2006355054

申请日：2006-12-28

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： MIWA YOICHI ,  MINAMI AYA ,  INAGAKI TAKESHI

IPC: G06F11/20

Abstract: PROBLEM TO BE SOLVED: To provide a method for restoration of a defective node in a torus type computer system. SOLUTION: When one of calculation nodes is broken during execution of calculation in a computer system including a torus network and a tree network including a plurality of IO nodes, each of the calculation nodes forming a link with a terminal IO node of the tree network, an IO node which forms a link with the defective node is reported as an alternate node specified by a one-dimension increased address of the address of the defective node to a node adjacent to the defective node. When the adjacent node receives a packet for the defective node, the packet is routed to the alternate node, and a job designated by the packet which reached the alternate node is processed in the alternate node. The alternate node confirms an address of calculation node to which a packet including the processing result of the job is transmitted, and transmits the packet from the calculation node connected to the alternate node to a calculation node closest to the address. COPYRIGHT: (C)2008,JPO&INPIT

Abstract translation: 要解决的问题：提供一种用于恢复环面型计算机系统中的缺陷节点的方法。 解决方案：当在包括环面网络和包括多个IO节点的树网络在内的计算机系统中执行计算期间计算节点中的一个被破坏时，每个计算节点与该终端IO节点形成链接 与缺陷节点形成链接的IO节点被报告为由缺陷节点的地址的一维增加地址指定到与缺陷节点相邻的节点的备用节点。 当相邻节点接收到缺陷节点的分组时，将分组路由到备用节点，并且在备用节点中处理由到达备用节点的分组指定的作业。 备用节点确认发送包括作业的处理结果的分组的计算节点的地址，并将连接到备用节点的计算节点的分组发送到最靠近该地址的计算节点。 版权所有（C）2008，JPO＆INPIT

公开(公告)号：JPH10289083A

公开(公告)日：1998-10-27

申请号：JP9185697

申请日：1997-04-10

Applicant: IBM

Inventor： INAGAKI TAKESHI

IPC: G06F3/14 ,  G06F3/048

Abstract: PROBLEM TO BE SOLVED: To make a user trace a sentence in a long document without losing the sight of it. SOLUTION: When a voice recognizing device 2 recognizes a voice that is 'proceed' which is spoken by a user, a document format interpreting device 4 extracts one sentence unit and performs an output display layout with the extracted sentence as a foreground. A display part extracting device 10 calculates a relative coordinate of an extraction window to a background image based on the coordinates of the start and end points of the foreground. A document imaging device 6 generates a foreground bit image based on output display layout specification after change and stores it in a foreground image storage area 8. An image synthesizer 9 synthesizes the foreground bit image in the area 8 with a background bit image in a background image storage area 7, and the device 10 extracts a display part from a synthetic image in accordance with the extraction window and shows it on a display device 11.