公开(公告)号：US07237076B2

公开(公告)日：2007-06-26

申请号：US10651633

申请日：2003-08-29

申请人： Takahiro Nakano ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi ,  Katsumi Hirezaki

发明人： Takahiro Nakano ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi ,  Katsumi Hirezaki

IPC分类号： G06F12/00

CPC分类号： G06F17/30067 ,  G06F11/1448 ,  G06F11/1464 ,  G06F2201/84 ,  Y10S707/99953 ,  Y10S707/99954

摘要： Snapshots are implemented by combining original data in a place where an operational volume has been updated with data in a place where the operational volume has not been updated. A snapshot management table maintains a value indicating that update has not been conducted, or a storage place of original data, for each of combinations of blocks in the operational volume and the snapshots. If there is a snapshot in which update has not been conducted in a update place at the time of update, then original data is copied and the snapshot management table is updated. The copied original data is managed by a difference block management table, which has a value indicating whether respective snapshots are referencing the data. If a snapshot is deleted, then the value indicating that the snapshot is referencing is altered in all entries in the difference block management table.

公开(公告)号：US07657721B2

公开(公告)日：2010-02-02

申请号：US11809113

申请日：2007-05-30

申请人： Takahiro Nakano ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi ,  Katsumi Hirezaki

发明人： Takahiro Nakano ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi ,  Katsumi Hirezaki

IPC分类号： G06F12/00

CPC分类号： G06F17/30067 ,  G06F11/1448 ,  G06F11/1464 ,  G06F2201/84 ,  Y10S707/99953 ,  Y10S707/99954

摘要： Snapshots are implemented by combining original data in a place where an operational volume has been updated with data in a place where the operational volume has not been updated. A snapshot management table maintains a value indicating that update has not been conducted, or a storage place of original data, for each of combinations of blocks in the operational volume and the snapshots. If there is a snapshot in which update has not been conducted in a update place at the time of update, then original data is copied and the snapshot management table is updated. The copied original data is managed by a difference block management table, which has a value indicating whether respective snapshots are referencing the data. If a snapshot is deleted, then the value indicating that the snapshot is referencing is altered in all entries in the difference block management table.

摘要翻译： 快照是通过将操作卷更新的地方的原始数据与操作卷未更新的地方的数据相结合来实现的。 对于操作卷和快照中的每个块的组合，快照管理表维护指示尚未进行更新的值或原始数据的存储位置。 如果在更新时没有在更新位置进行更新的快照，则会复制原始数据，并更新快照管理表。 复制的原始数据由差分块管理表管理，差分块管理表具有指示各个快照是否参考数据的值。 如果快照被删除，则表示快照正在引用的值在差异块管理表的所有条目中被更改。

公开(公告)号：US20070233978A1

公开(公告)日：2007-10-04

申请号：US11809113

申请日：2007-05-30

申请人： Takahiro Nakano ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi ,  Katsumi Hirezaki

发明人： Takahiro Nakano ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi ,  Katsumi Hirezaki

IPC分类号： G06F12/00

CPC分类号： G06F17/30067 ,  G06F11/1448 ,  G06F11/1464 ,  G06F2201/84 ,  Y10S707/99953 ,  Y10S707/99954

摘要： Snapshots are implemented by combining original data in a place where an operational volume has been updated with data in a place where the operational volume has not been updated. A snapshot management table maintains a value indicating that update has not been conducted, or a storage place of original data, for each of combinations of blocks in the operational volume and the snapshots. If there is a snapshot in which update has not been conducted in a update place at the time of update, then original data is copied and the snapshot management table is updated. The copied original data is managed by a difference block management table, which has a value indicating whether respective snapshots are referencing the data. If a snapshot is deleted, then the value indicating that the snapshot is referencing is altered in all entries in the difference block management table.

摘要翻译： 快照是通过将操作卷更新的地方的原始数据与操作卷未更新的地方的数据相结合来实现的。 对于操作卷和快照中的每个块的组合，快照管理表维护指示尚未进行更新的值或原始数据的存储位置。 如果在更新时没有在更新位置进行更新的快照，则会复制原始数据，并更新快照管理表。 复制的原始数据由差分块管理表管理，差分块管理表具有指示各个快照是否参考数据的值。 如果快照被删除，则表示快照正在引用的值在差异块管理表的所有条目中被更改。

公开(公告)号：US20050027819A1

公开(公告)日：2005-02-03

申请号：US10808921

申请日：2004-03-24

申请人： Takahiro Nakano ,  Junichi Hara ,  Tsuyoshi Aoyama ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi

发明人： Takahiro Nakano ,  Junichi Hara ,  Tsuyoshi Aoyama ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi

IPC分类号： G06F15/16

CPC分类号： G06F3/0611 ,  G06F3/0608 ,  G06F3/064 ,  G06F3/068 ,  G06F3/0689 ,  G06F11/1446 ,  G06F2201/84 ,  Y10S707/99953 ,  Y10S707/99954

摘要： In a storage system with a server apparatus having at least one CPU, a memory, at least one network interface, and at least one storage interface, and, at least one disk connected to the storage interface, the server apparatus has a snapshot management part which maintains and manages snapshot of the disk apparatus, the disk apparatus has an operational volume which performs ordinary read/write and a differential volume which stores differential data of snapshot of the operational volume, the snapshot management part stores data on the operational volume in the differential volume, provides a preceding copy area to store its location information, and when free area on the differential volume becomes insufficient discards the stored location information and uses the preceding copy area as an free area.

摘要翻译： 在具有至少一个CPU，存储器，至少一个网络接口和至少一个存储接口的服务器装置的存储系统中，以及连接到存储接口的至少一个盘，所述服务器装置具有快照管理部分 维护和管理磁盘装置的快照，磁盘装置具有执行普通读/写的操作量和存储操作卷的快照差异数据的差分卷，快照管理部存储关于操作卷的操作卷的数据 差分卷提供前一个复制区域来存储其位置信息，并且当差分卷上的空闲区域变得不足时，丢弃存储的位置信息，并将前一个复制区域用作空闲区域。

公开(公告)号：US07266654B2

公开(公告)日：2007-09-04

申请号：US10808921

申请日：2004-03-24

申请人： Takahiro Nakano ,  Junichi Hara ,  Tsuyoshi Aoyama ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi

发明人： Takahiro Nakano ,  Junichi Hara ,  Tsuyoshi Aoyama ,  Koji Sonoda ,  Yoshiaki Eguchi ,  Takashi Horiuchi

IPC分类号： G06F12/00

CPC分类号： G06F3/0611 ,  G06F3/0608 ,  G06F3/064 ,  G06F3/068 ,  G06F3/0689 ,  G06F11/1446 ,  G06F2201/84 ,  Y10S707/99953 ,  Y10S707/99954

摘要： In a storage system with a server apparatus having at least one CPU, a memory, at least one network interface, and at least one storage interface, and, at least one disk connected to the storage interface, the server apparatus has a snapshot management part which maintains and manages snapshot of the disk apparatus, the disk apparatus has an operational volume which performs ordinary read/write and a differential volume which stores differential data of snapshot of the operational volume, the snapshot management part stores data on the operational volume in the differential volume, provides a preceding copy area to store its location information, and when free area on the differential volume becomes insufficient discards the stored location information and uses the preceding copy area as an free area.

摘要翻译： 在具有至少一个CPU，存储器，至少一个网络接口和至少一个存储接口的服务器装置的存储系统中，以及连接到存储接口的至少一个盘，所述服务器装置具有快照管理部分 维护和管理磁盘装置的快照，磁盘装置具有执行普通读/写的操作量和存储操作卷的快照差异数据的差分卷，快照管理部存储关于操作卷的操作卷的数据 差分卷提供前一个复制区域来存储其位置信息，并且当差分卷上的空闲区域变得不足时，丢弃存储的位置信息，并将前一个复制区域用作空闲区域。

公开(公告)号：US20090144290A1

公开(公告)日：2009-06-04

申请号：US12361713

申请日：2009-01-29

申请人： Yoji NAKATANI ,  Koji Sonoda ,  Takahiro Nakano

发明人： Yoji NAKATANI ,  Koji Sonoda ,  Takahiro Nakano

IPC分类号： G06F17/30

CPC分类号： G06F3/0605 ,  G06F3/0643 ,  G06F3/0647 ,  G06F3/067 ,  G06F17/30079 ,  G06F2206/1012

摘要： Provided is a storage system as follows. A server holds a management table that serves to manage a mount point of a file system. The management table stores a file system identifier that uniquely identifies the file system within the storage system, mount point information that indicates the mount point of the file system, and a management server identifier that indicates an identifier of the server that manages the file system. The contents stored in the management table of each server are the same. Upon reception of a request to obtain a file handle, each server returns the file handle requested to be obtained. The file handle indicates, uniquely within the storage system, the storage area on the disk subsystem in which the file relating to the request is stored.

摘要翻译： 提供如下的存储系统。 服务器保存用于管理文件系统的安装点的管理表。 管理表存储唯一地标识存储系统内的文件系统的文件系统标识符，指示文件系统的安装点的安装点信息和指示管理文件系统的服务器的标识符的管理服务器标识符。 存储在每个服务器的管理表中的内容是相同的。 在接收到获取文件句柄的请求时，每个服务器返回请求获得的文件句柄。 文件句柄在存储系统中唯一地指示存储与请求相关的文件的磁盘子系统上的存储区域。

公开(公告)号：US07120767B2

公开(公告)日：2006-10-10

申请号：US10369690

申请日：2003-02-21

申请人： Junichi Hara ,  Takahiro Nakano ,  Koji Sonoda ,  Takayoshi Iitsuka ,  Yutaka Takata

发明人： Junichi Hara ,  Takahiro Nakano ,  Koji Sonoda ,  Takayoshi Iitsuka ,  Yutaka Takata

IPC分类号： G06F12/00

CPC分类号： G06F17/30067 ,  G06F11/1451 ,  G06F2201/84 ,  Y10S707/99953 ,  Y10S707/99955

摘要： In the storage-based snapshot creation, a block-selection specifying unit provided on a NAS processing unit specifies a block, which becomes necessary for the generation of snapshot data, to a specified-block analyzing unit within a disk apparatus. Moreover, a disk controller generates the snapshot data on the block specified as the snapshot target, while making an inquiry to the specified-block analyzing unit. This makes it possible to create the snapshot in a storage-capacity reduced manner, and to specify the snapshot creation in a partition, file, or directory unit.

摘要翻译： 在基于存储的快照创建中，在NAS处理单元上设置的块选择指定单元将生成快照数据所需的块指定给盘装置内的指定块分析单元。 此外，磁盘控制器在指定为快照目标的块上产生快照数据，同时对指定块分析单元进行查询。 这使得可以以减少存储容量的方式创建快照，并在分区，文件或目录单元中指定快照创建。

公开(公告)号：US07412578B2

公开(公告)日：2008-08-12

申请号：US11519877

申请日：2006-09-13

申请人： Junichi Hara ,  Takahiro Nakano ,  Koji Sonoda ,  Takayoshi Iitsuka ,  Yutaka Takata

发明人： Junichi Hara ,  Takahiro Nakano ,  Koji Sonoda ,  Takayoshi Iitsuka ,  Yutaka Takata

IPC分类号： G06F12/16

CPC分类号： G06F17/30067 ,  G06F11/1451 ,  G06F2201/84 ,  Y10S707/99953 ,  Y10S707/99955

摘要： In the storage-based snapshot creation, a block-selection specifying unit provided on a NAS processing unit specifies a block, which becomes necessary for the generation of snapshot data, to a specified-block analyzing unit within a disk apparatus. Moreover, a disk controller generates the snapshot data on the block specified as the snapshot target, while making an inquiry to the specified-block analyzing unit. This makes it possible to create the snapshot in a storage-capacity reduced manner, and to specify the snapshot creation in a partition, file, or directory unit.

摘要翻译： 在基于存储的快照创建中，在NAS处理单元上设置的块选择指定单元将生成快照数据所需的块指定给盘装置内的指定块分析单元。 此外，磁盘控制器在指定为快照目标的块上产生快照数据，同时对指定块分析单元进行查询。 这使得可以以减少存储容量的方式创建快照，并在分区，文件或目录单元中指定快照创建。

公开(公告)号：US07149922B2

公开(公告)日：2006-12-12

申请号：US10393293

申请日：2003-03-21

申请人： Koji Sonoda ,  Takahiro Nakano ,  Naoto Matsunami ,  Takayoshi Iltsuka ,  Yutaka Takata

发明人： Koji Sonoda ,  Takahiro Nakano ,  Naoto Matsunami ,  Takayoshi Iltsuka ,  Yutaka Takata

IPC分类号： G06F11/00

CPC分类号： G06F3/0635 ,  G06F3/0611 ,  G06F3/0617 ,  G06F3/067 ,  G06F11/1471 ,  G06F11/2089 ,  H04L67/1097

摘要： A file server has plural NAS nodes having three processors dispersed in function, a shared cache memory shared between the plural NAS nodes and backed up by a battery, and plural storage devices. A log area for storing data with respect to an access request received by each NAS node is arranged in the shared cache memory. A network processor stores the data with respect to the access request to the log area, and transfers the data of the memory by a DMA at a reading time. Even when a failure is happened in a certain NAS node, another NAS node restores a file system using the log and continues processing to store the data with respect to the access request to the shared cache memory.

摘要翻译： 文件服务器具有多个具有分散功能的处理器的NAS节点，在多个NAS节点之间共享并由电池备份的共享高速缓存存储器和多个存储设备。 用于存储关于由每个NAS节点接收的访问请求的数据的日志区域被布置在共享高速缓冲存储器中。 网络处理器将关于访问请求的数据存储到日志区域，并且在读取时间通过DMA传送存储器的数据。 即使在某个NAS节点发生故障时，另一个NAS节点使用该日志恢复文件系统，并继续处理以将关于访问请求的数据存储到共享高速缓冲存储器。

公开(公告)号：US20060129513A1

公开(公告)日：2006-06-15

申请号：US11068811

申请日：2005-03-02

申请人： Yoji Nakatani ,  Koji Sonoda ,  Takahiro Nakano

发明人： Yoji Nakatani ,  Koji Sonoda ,  Takahiro Nakano

IPC分类号： G06F17/30

CPC分类号： G06F3/0605 ,  G06F3/0643 ,  G06F3/0647 ,  G06F3/067 ,  G06F16/119 ,  G06F2206/1012

摘要： Provided is a storage system as follows. A server holds a management table that serves to manage a mount point of a file system. The management table stores a file system identifier that uniquely identifies the file system within the storage system, mount point information that indicates the mount point of the file system, and a management server identifier that indicates an identifier of the server that manages the file system. The contents stored in the management table of each server are the same. Upon reception of a request to obtain a file handle, each server returns the file handle requested to be obtained. The file handle indicates, uniquely within the storage system, the storage area on the disk subsystem in which the file relating to the request is stored.

摘要翻译： 提供如下的存储系统。 服务器保存用于管理文件系统的安装点的管理表。 管理表存储唯一地标识存储系统内的文件系统的文件系统标识符，指示文件系统的安装点的安装点信息和指示管理文件系统的服务器的标识符的管理服务器标识符。 存储在每个服务器的管理表中的内容是相同的。 在接收到获取文件句柄的请求时，每个服务器返回请求获得的文件句柄。 文件句柄在存储系统中唯一地指示存储与请求相关的文件的磁盘子系统上的存储区域。