公开(公告)号：US06487562B1

公开(公告)日：2002-11-26

申请号：US09467354

申请日：1999-12-20

申请人： Robert S. Mason, Jr. ,  Yuval Ofek

发明人： Robert S. Mason, Jr. ,  Yuval Ofek

IPC分类号： G06F1730

CPC分类号： G06F3/0629 ,  G06F3/0605 ,  G06F3/0689 ,  Y10S707/99931 ,  Y10S707/99956

摘要： A system and method for dynamically modifying parameters in a data storage system such as a RAID system. Such parameters include QOS (Quality of Service) parameters, which control the speed in which system operations are performed for various parts of a data storage system. The storage devices addressable as logical volumes can be individually controlled and configured for preferred levels of performance and service. The parameters can be changed at any time while the data storage system is in use, with the changes taking effect very quickly. These parameter changes are permanently stored and therefore allow system configurations to be maintained. A user interface (UI) allows a user or system administrator to easily observe and configure system parameters, preferably using a graphic user interface which allows a user to select system changes along a scale from minimum to a maximum.

摘要翻译： 一种用于动态修改诸如RAID系统的数据存储系统中的参数的系统和方法。 这些参数包括QOS（服务质量）参数，其控制对数据存储系统的各个部分执行系统操作的速度。 可寻址为逻辑卷的存储设备可以单独控制和配置为优化性能和服务级别。 在数据存储系统正在使用时，可以随时更改参数，并使更改生效非常快。 这些参数更改将被永久存储，因此可以维护系统配置。 用户界面（UI）允许用户或系统管理员容易地观察和配置系统参数，优选地使用图形用户界面，其允许用户沿着从最小到最大的比例来选择系统变化。

公开(公告)号：US20050204108A1

公开(公告)日：2005-09-15

申请号：US11120469

申请日：2005-05-03

申请人： Yuval Ofek ,  Zoran Cakeljic ,  Haim Bitner ,  Sharon Galtzur ,  Michael Hirsch ,  Nadav Kedem ,  Samuel Krikler ,  Dan Arnon

发明人： Yuval Ofek ,  Zoran Cakeljic ,  Haim Bitner ,  Sharon Galtzur ,  Michael Hirsch ,  Nadav Kedem ,  Samuel Krikler ,  Dan Arnon

IPC分类号： G06F11/14 ,  G06F12/08

CPC分类号： G06F11/1448 ,  G06F11/1458 ,  G06F11/1466 ,  Y10S707/99953 ,  Y10S707/99955

摘要： Method and apparatus are disclosed for copying and backing up logical objects in a computer storage system. The logical objects are comprised of data blocks. The data blocks may be copied in any order. The data blocks may be copied or written from a storage media, such as a tape, in parallel.

摘要翻译： 公开了用于在计算机存储系统中复制和备份逻辑对象的方法和装置。 逻辑对象由数据块组成。 数据块可以以任何顺序复制。 可以并行地从诸如磁带的存储介质复制或写入数据块。

公开(公告)号：US06493796B1

公开(公告)日：2002-12-10

申请号：US09388328

申请日：1999-09-01

申请人： Dan Arnon ,  Yuval Ofek ,  Douglas E. LeCrone

发明人： Dan Arnon ,  Yuval Ofek ,  Douglas E. LeCrone

IPC分类号： G06F1200

CPC分类号： G06F11/2064 ,  G06F11/2069 ,  G06F11/2071 ,  G06F2201/82

摘要： In one embodiment, mirroring communication from a second source storage device to a second target storage device in a data mirroring system is disabled when mirroring communication from a first source storage device to a first target storage device is disabled. In another embodiment, information is stored in a data mirroring system identifying at least one subset of a plurality of mirrored source storage devices for which a consistent representation of data is desired to be maintained on at least one corresponding subset of a plurality of target storage devices. In yet another embodiment, at least one of a plurality of mirrored source storage devices is placed in one of a first state, a second state, and a third state. In response to a source storage system receiving a write-requesting command chain directed to a mirrored source storage device in the first state, the command chain is permitted to commit and data written by the command chain is transferred to a corresponding target storage device. In response to the source storage system receiving a write-requesting command chain directed to a mirrored source storage device in the second state, the command chain is prevented from committing. In response to the source storage system receiving a write-requesting command chain directed to a mirrored source storage device in the third state, the command chain is permitted to commit without transferring data written by the command chain to a corresponding target storage device.

摘要翻译： 在一个实施例中，当从第一源存储设备到第一目标存储设备的通信镜像被禁用时，禁止从数据镜像系统中的第二源存储设备到第二目标存储设备的镜像通信。 在另一个实施例中，信息被存储在数据镜像系统中，标识多个镜像源存储设备的至少一个子集，期望在多个目标存储设备的至少一个对应子集上保持一致的数据表示 。 在另一个实施例中，多个镜像源存储设备中的至少一个被放置在第一状态，第二状态和第三状态之一中。 响应于源存储系统接收到处于第一状态的镜像源存储设备的写请求命令链，允许命令链提交，并且由命令链写入的数据被传送到相应的目标存储设备。 响应于源存储系统在第二状态下接收到指向镜像源存储设备的写请求命令链，防止命令链提交。 响应于源存储系统接收到处于第三状态的镜像源存储设备的写请求命令链，允许命令链提交而不将命令链写入的数据传送到相应的目标存储设备。

公开(公告)号：US06424999B1

公开(公告)日：2002-07-23

申请号：US09268494

申请日：1999-03-11

申请人： Dan Arnon ,  Yuval Ofek

发明人： Dan Arnon ,  Yuval Ofek

IPC分类号： G06F1516

CPC分类号： G06F11/1469 ,  Y10S707/99953

摘要： A system comprising a mass storage subsystem, as a master device and backup subsystem, as a slave device, the slave device transferring data items to the master device during a restore operation. Each data item to be restored is identified by a data item identifier. The master device initially provides the slave device with a list of data item identifiers and the slave device receives the data item identifier list from the master device and order the data item identifiers thereon in an optimal order for transfer to the master device, the ordering based on the ordering of the data items on storage media on which they are stored. The master device, in each of a plurality of iterations, receives from the slave device data item identifiers identifying a data item transferred during a previous iteration and a data item to be transferred during the current iteration and requests the slave device to transfer the data item to be transferred. The master device uses the data item identifier that it receives from the slave device identifying the data item transferred during the previous iteration to confirm that the data item corresponded to the data item that was to have been transferred during the previous iteration. The slave device, in each iteration, provides the master device with the data item identifiers identifying the data item transferred during the previous iteration and the data item to be transferred during the current iteration, and transfers the data item to be transferred during the iteration to the master device when requested by the master device.

摘要翻译： 一种包括作为主设备和备用子系统的大容量存储子系统作为从设备的系统，所述从设备在恢复操作期间将数据项传送到主设备。 要恢复的每个数据项由数据项标识符标识。 主设备最初向从设备提供数据项标识符的列表，并且从设备从主设备接收数据项标识符列表，并以最佳顺序对数据项标识符进行命令以传送到主设备，基于排序 关于在存储介质上的数据项的排序。 在多个迭代中的每一个中，主设备从从设备接收标识在先前迭代期间传送的数据项的数据项标识符和当前迭代期间要传送的数据项，并请求从设备传送数据项 被转移。 主设备使用从从设备接收的数据项标识符，标识在先前迭代期间传送的数据项，以确认该数据项对应于在先前迭代期间被传送的数据项。 在每次迭代中，从设备为主设备提供标识在前一次迭代期间传送的数据项的数据项标识符和当前迭代期间要传送的数据项，并将要在迭代期间传送的数据项传送到 主设备在主设备请求时。

公开(公告)号：US06920537B2

公开(公告)日：2005-07-19

申请号：US10196867

申请日：2002-07-17

申请人： Yuval Ofek ,  Zoran Cakeljic ,  Haim Bitner ,  Sharon Galtzur ,  Michael Hirsch ,  Nadav Kedem ,  Samuel Krikler ,  Dan Arnon

发明人： Yuval Ofek ,  Zoran Cakeljic ,  Haim Bitner ,  Sharon Galtzur ,  Michael Hirsch ,  Nadav Kedem ,  Samuel Krikler ,  Dan Arnon

IPC分类号： G06F11/14 ,  G06F12/16

CPC分类号： G06F11/1448 ,  G06F11/1458 ,  G06F11/1466 ,  Y10S707/99953 ,  Y10S707/99955

摘要： Method and apparatus are disclosed for copying and backing up logical objects in a computer storage system. The logical objects are comprised of data blocks. The data blocks may be copied in any order. The data blocks may be copied or written from a storage media, such as a tape, in parallel.

摘要翻译： 公开了用于在计算机存储系统中复制和备份逻辑对象的方法和装置。 逻辑对象由数据块组成。 数据块可以以任何顺序复制。 可以并行地从诸如磁带的存储介质复制或写入数据块。

公开(公告)号：US06772198B2

公开(公告)日：2004-08-03

申请号：US10142478

申请日：2002-05-10

申请人： Dan Arnon ,  Yuval Ofek

发明人： Dan Arnon ,  Yuval Ofek

IPC分类号： G06F1516

CPC分类号： G06F11/1469 ,  Y10S707/99953

摘要： In a system that includes a back-up subsystem comprising back-up media, a mass storage subsystem connected to the back-up subsystem, and a host connected to the mass storage subsystem, the mass storage subsystem, as master and independent of the host, requests the restore operation by providing to the back-up subsystem, as slave, data identifiers identifying multiple data items to be transferred during the restore operation. The back-up subsystem determines its preferred ordering for retrieval of the requested plurality of data items from the back-up media. The back-up subsystem provides the requested data items to the mass storage subsystem in the determined preferred order in a plurality of iterations, each iteration identified by a data item identifier for the data item to be transferred in the current iteration.

摘要翻译： 在包括备份子系统的系统中，包括备份介质，连接到备用子系统的大容量存储子系统和连接到大容量存储子系统的主机，大容量存储子系统作为主机并且独立于主机 通过向备用子系统提供标识要在还原操作期间要传送的多个数据项的数据标识符来请求恢复操作。 备份子系统确定其从备份介质检索所请求的多个数据项的优选顺序。 备用子系统以多个迭代以确定的优选顺序向大容量存储子系统提供所请求的数据项，每个迭代由在当前迭代中要传送的数据项的数据项标识符标识。

公开(公告)号：US06321308B1

公开(公告)日：2001-11-20

申请号：US08822971

申请日：1997-03-21

申请人： Dan Arnon ,  Yuval Ofek

发明人： Dan Arnon ,  Yuval Ofek

IPC分类号： G06F1200

CPC分类号： G06F3/0613 ,  G06F3/0659 ,  G06F3/0689

摘要： A method of managing a storage system which includes a local and remote systems is provided. Link services between the two subsystems are provided though the use of a task queue. The task queue resides in a global memory of the local storage system and receives requests from the various host controllers, device, and remote controllers connected to the local storage. The remote controllers of the local storage service the requests placed in the task queue to enable data transfer between the local and remote storage systems. The task queue may be a doubly linked list of records including forward and backward pointers in addition to the request data. A two level locking scheme is employed to prevent the addition of incompatible requests to the queue and to enable maximum parallelism in servicing requests in the queue. The first level of locking applies to the entire queue and is used when records are added to and deleted from the queue. The second level of locking applies to the individual queue records. Each queue record is locked when being serviced by an associated controller. Locked records and records corresponding to device requests having another locked record are ignored by the servicing controllers.

摘要翻译： 提供了一种管理包括本地和远程系统的存储系统的方法。 通过使用任务队列来提供两个子系统之间的链接服务。 任务队列驻留在本地存储系统的全局存储器中，并接收来自连接到本地存储器的各种主机控制器，设备和远程控制器的请求。 本地存储服务的远程控制器将请求放置在任务队列中，以实现本地和远程存储系统之间的数据传输。 任务队列可以是除了请求数据之外的包括前向和后向指针的记录的双向链接列表。 采用两级锁定方案来防止向队列中添加不兼容的请求，并且能够在服务请求队列中实现最大的并行性。 第一级锁定适用于整个队列，并在将记录添加到队列中并从其中删除时使用。 第二级锁定适用于各个队列记录。 当由关联的控制器服务时，每个队列记录被锁定。 与具有另一个锁定记录的设备请求相对应的锁定记录和记录被服务控制器忽略。

公开(公告)号：US07107395B1

公开(公告)日：2006-09-12

申请号：US09224637

申请日：1998-12-31

申请人： Yuval Ofek ,  Zoran Cakeljic ,  Haim Bitner ,  Sharon Galtzur ,  Ariel J. Ish-Shalom ,  Nadav Kedem ,  Samuel Krikler ,  Dan Arnon

发明人： Yuval Ofek ,  Zoran Cakeljic ,  Haim Bitner ,  Sharon Galtzur ,  Ariel J. Ish-Shalom ,  Nadav Kedem ,  Samuel Krikler ,  Dan Arnon

IPC分类号： G06F13/14

CPC分类号： G06F11/1464 ,  G06F3/0601 ,  G06F11/1451 ,  G06F11/1456 ,  G06F11/1469 ,  G06F11/2056 ,  G06F2003/0697 ,  Y10S707/99953 ,  Y10S707/99955

摘要： Method and apparatus are disclosed for a computer system including host computers and storage elements. The host computers may be configured into a host domain and the storage elements configured into a storage domain. The storage domain includes a plurality of primary storage devices and a secondary storage device. The secondary storage device may be coupled to a plurality of the primary storage devices through a network. In another embodiment, the secondary storage device may send and receive information from a heterogeneous set of host computers. In another embodiment, connections for transfer of data onto the secondary storage element are created automatically.

摘要翻译： 公开了一种包括主计算机和存储元件的计算机系统的方法和装置。 主计算机可以被配置成主机域，并且将存储元件配置到存储域中。 存储域包括多个主存储设备和辅助存储设备。 辅助存储设备可以通过网络耦合到多个主存储设备。 在另一个实施例中，辅助存储设备可以从异构的主机计算机集合发送和接收信息。 在另一个实施例中，自动地创建用于将数据传送到辅助存储元件上的连接。

公开(公告)号：US06487561B1

公开(公告)日：2002-11-26

申请号：US09224896

申请日：1998-12-31

申请人： Yuval Ofek ,  Zoran Cakeljic ,  Samuel Krikler ,  Sharon Galtzur ,  Michael Hirsch ,  Dan Arnon ,  Peter Kamvysselis

发明人： Yuval Ofek ,  Zoran Cakeljic ,  Samuel Krikler ,  Sharon Galtzur ,  Michael Hirsch ,  Dan Arnon ,  Peter Kamvysselis

IPC分类号： G06F1730

CPC分类号： G06F11/1451 ,  G06F11/1464 ,  G06F17/30067 ,  Y10S707/99952 ,  Y10S707/99953 ,  Y10S707/99955

摘要： Method and apparatus for copying, transferring, backing up and restoring data are disclosed. The data can be copied, backed up or restored in segments sizes larger than the data blocks which comprise a logical object. In some embodiments, the segment can correspond to a track of a primary storage device and the data blocks to a fixed size block. In some instances, copying, storage and transfer of the segments which include multiple data blocks can result in transfer of a data block not in a logical object.

摘要翻译： 公开了用于复制，传送，备份和恢复数据的方法和装置。 可以以大于构成逻辑对象的数据块的段大小复制，备份或还原数据。 在一些实施例中，段可以对应于主存储设备的轨道，并且将数据块对应到固定大小的块。 在一些情况下，包括多个数据块的段的复制，存储和传送可导致不在逻辑对象中的数据块的传送。

公开(公告)号：US06598134B2

公开(公告)日：2003-07-22

申请号：US09943052

申请日：2001-08-30

申请人： Yuval Ofek ,  Moshe Yanai ,  Douglas E. LeCrone

发明人： Yuval Ofek ,  Moshe Yanai ,  Douglas E. LeCrone

IPC分类号： G06F1206

CPC分类号： G06F3/0607 ,  G06F3/0647 ,  G06F3/067 ,  G06F3/0689 ,  G06F12/0638 ,  G06F12/08 ,  G06F12/0866 ,  G11B5/86 ,  G11B19/02

摘要： A system and method for providing on-line, real-time, transparent data migration from an existing storage device to a replacement storage device. The existing and replacement storage devices are connected as a composite storage device that is coupled to a host, network or other data processing system. The replacement storage device includes a table which identifies data elements that have migrated to the replacement storage device. When a host system makes a data transfer request for one or more data elements, the replacement storage device determines whether the data elements have been migrated. If the data elements have migrated, the replacement storage device responds to the data transfer request independently of any interaction with the existing storage device. If the data elements have not migrated, the replacement storage device migrates the requested data elements and then responds to the data request and updates the data element map or table. When not busy servicing other requests, the replacement storage device operates in a background mode to migrate data elements so the data migration can occur concurrently with and transparently to system operations.