公开(公告)号：US09170740B2

公开(公告)日：2015-10-27

申请号：US12851641

申请日：2010-08-06

申请人： Ross Zwisler ,  Brian McKean ,  Kevin Kidney

发明人： Ross Zwisler ,  Brian McKean ,  Kevin Kidney

IPC分类号： G06F12/08 ,  G06F3/06 ,  G06F12/16

CPC分类号： G06F3/0608 ,  G06F3/064 ,  G06F3/0686 ,  G06F12/08

摘要： The present invention is a system and method which allows for a VTL system that supports thin provisioning to implicitly unmap unused storage. Such unmap operations may occur even though the VTL system does not receive any explicit unmap requests from its initiators. For example, if a system administrator knows that once a virtual tape drive of the VTL system has been partially overwritten, all previously written data sets on that virtual tape drive will never again be accessed, the system administrator may configure the VTL system so that it unmaps the entire remainder of the virtual tape drive on the first data overwrite.

摘要翻译： 本发明是允许支持精简配置的VTL系统隐含地取消对未使用的存储器的映射的系统和方法。 即使VTL系统没有从其启动器接收到任何明确的未映射请求，也可能发生这种取消映射操作。 例如，如果系统管理员知道一旦VTL系统的虚拟磁带驱动器被部分覆盖，则该虚拟磁带驱动器上的所有先前写入的数据集将不再被访问，系统管理员可以配置VTL系统，使其 在第一个数据覆盖时，将虚拟磁带驱动器的剩余部分取消映射。

公开(公告)号：US08201001B2

公开(公告)日：2012-06-12

申请号：US12462425

申请日：2009-08-04

申请人： Brian McKean ,  Kevin Kidney ,  Ross Zwisler

发明人： Brian McKean ,  Kevin Kidney ,  Ross Zwisler

IPC分类号： G06F1/32

CPC分类号： G06F3/064 ,  G06F3/061 ,  G06F3/0625 ,  G06F3/0634 ,  G06F3/0689 ,  G06F11/1076 ,  G06F2211/1059 ,  Y02D10/154

摘要： The present invention is a method for drive management and data placement in an archival storage system having a set of drives. The method includes mapping redundant data stripes onto the drives. A first active data stripe, located on a first subset of the drives, is then selected from the mapped data stripes. The first subset is placed into a normal power state and a second subset of the drives is placed into a low power state. Data is then written to the first active data stripe. Before the first active data stripe is fully used, the method includes selecting a next active/second active data stripe from the mapped data stripes, the second active data stripe being at least partially located on the second subset. The method may be performed by a system which implements MAID techniques for drive management and CRUSH for data placement.

摘要翻译： 本发明是一种具有一组驱动器的档案存储系统中的驱动器管理和数据放置方法。 该方法包括将冗余数据条纹映射到驱动器上。 然后从映射的数据条带中选择位于驱动器的第一子集上的第一活动数据条带。 将第一子集置于正常功率状态，驱动器的第二子集置于低功率状态。 然后将数据写入第一个活动数据条带。 在完全使用第一活动数据条带之前，该方法包括从映射的数据条带中选择下一个活动/第二活动数据条带，第二活动数据条纹至少部分地位于第二子集上。 该方法可以由实现用于驱动器管理的MAID技术的系统和用于数据放置的CRUSH来执行。

公开(公告)号：US20120036321A1

公开(公告)日：2012-02-09

申请号：US12851641

申请日：2010-08-06

申请人： Ross Zwisler ,  Brian McKean ,  Kevin Kidney

发明人： Ross Zwisler ,  Brian McKean ,  Kevin Kidney

IPC分类号： G06F12/00 ,  G06F12/08

CPC分类号： G06F3/0608 ,  G06F3/064 ,  G06F3/0686 ,  G06F12/08

摘要： The present invention is a system and method which allows for a VTL system that supports thin provisioning to implicitly unmap unused storage. Such unmap operations may occur even though the VTL system does not receive any explicit unmap requests from its initiators. For example, if a system administrator knows that once a virtual tape drive of the VTL system has been partially overwritten, all previously written data sets on that virtual tape drive will never again be accessed, the system administrator may configure the VTL system so that it unmaps the entire remainder of the virtual tape drive on the first data overwrite.

摘要翻译： 本发明是允许支持精简配置的VTL系统隐含地取消对未使用的存储器的映射的系统和方法。 即使VTL系统没有从其启动器接收到任何明确的未映射请求，也可能发生这种取消映射操作。 例如，如果系统管理员知道一旦VTL系统的虚拟磁带驱动器被部分覆盖，则该虚拟磁带驱动器上的所有先前写入的数据集将不再被访问，系统管理员可以配置VTL系统，使其 在第一个数据覆盖时，将虚拟磁带驱动器的剩余部分取消映射。

公开(公告)号：US20110035605A1

公开(公告)日：2011-02-10

申请号：US12462425

申请日：2009-08-04

申请人： Brian McKean ,  Kevin Kidney ,  Ross Zwisler

发明人： Brian McKean ,  Kevin Kidney ,  Ross Zwisler

IPC分类号： G06F1/00 ,  G06F12/00

CPC分类号： G06F3/064 ,  G06F3/061 ,  G06F3/0625 ,  G06F3/0634 ,  G06F3/0689 ,  G06F11/1076 ,  G06F2211/1059 ,  Y02D10/154

摘要： The present invention is a method for drive management and data placement in an archival storage system having a set of drives. The method includes mapping redundant data stripes onto the drives. A first active data stripe, located on a first subset of the drives, is then selected from the mapped data stripes. The first subset is placed into a normal power state and a second subset of the drives is placed into a low power state. Data is then written to the first active data stripe. Before the first active data stripe is fully used, the method includes selecting a next active/second active data stripe from the mapped data stripes, the second active data stripe being at least partially located on the second subset. The method may be performed by a system which implements MAID techniques for drive management and CRUSH for data placement.

摘要翻译： 本发明是一种具有一组驱动器的档案存储系统中的驱动器管理和数据放置方法。 该方法包括将冗余数据条纹映射到驱动器上。 然后从映射的数据条带中选择位于驱动器的第一子集上的第一活动数据条带。 将第一子集置于正常功率状态，驱动器的第二子集置于低功率状态。 然后将数据写入第一个活动数据条带。 在完全使用第一活动数据条带之前，该方法包括从映射的数据条带中选择下一个活动/第二活动数据条带，第二活动数据条纹至少部分地位于第二子集上。 该方法可以由实现用于驱动器管理的MAID技术的系统和用于数据放置的CRUSH来执行。

公开(公告)号：US20060020720A1

公开(公告)日：2006-01-26

申请号：US10897526

申请日：2004-07-23

申请人： David Stallmo ,  Brian McKean ,  Ross Zwisler

发明人： David Stallmo ,  Brian McKean ,  Ross Zwisler

IPC分类号： G06F13/14

CPC分类号： G06F13/385

摘要： A system and method for communication amongst a device and multiple controllers. A controller may use a direct communication path to the device or may route the communication to another controller that has a faster communication path to the device. Such a system and method is particularly useful when the device takes a long time to switch from a communication path with the second controller to a communication path with the first controller.

摘要翻译： 一种用于设备和多个控制器之间通信的系统和方法。 控制器可以使用到设备的直接通信路径，或者可以将通信路由到具有到设备的更快通信路径的另一个控制器。 当设备花费很长时间从与第二控制器的通信路径切换到与第一控制器的通信路径时，这种系统和方法特别有用。

公开(公告)号：US20100100677A1

公开(公告)日：2010-04-22

申请号：US12288037

申请日：2008-10-16

申请人： Brian McKean ,  Ross Zwisler

发明人： Brian McKean ,  Ross Zwisler

IPC分类号： G06F12/02 ,  G06F12/00 ,  G06F12/16 ,  G06F13/00

CPC分类号： G06F3/0647 ,  G06F3/0611 ,  G06F3/0625 ,  G06F3/0689 ,  G06F11/2056 ,  G06F11/3485 ,  Y02D10/154 ,  Y02D10/34

摘要： The present invention is a method for storing data. The method includes the step of dividing data into a plurality of uniformly-sized segments. The method further includes storing said uniformly-sized segments on a plurality of storage mechanisms. The method includes the steps of monitoring access to the uniformly-sized segments stored on the plurality of storage mechanisms to determine an access pattern; monitoring access patterns between the plurality of disks and monitoring performance characteristics of the plurality of storage mechanisms to determine a performance requirement for the plurality of storage mechanisms. Finally, the method includes the step of migrating at least one segment of the plurality of uniformly-sized segments from a first storage mechanism of the plurality of storage mechanisms to a second storage mechanism of the plurality of storage mechanisms in response to at least one of the access patterns or the performance requirements.

摘要翻译： 本发明是用于存储数据的方法。 该方法包括将数据划分成多个均匀大小的段的步骤。 该方法还包括将所述均匀尺寸的段存储在多个存储机构上。 该方法包括以下步骤：监视对存储在多个存储机构上的均匀大小的段的访问以确定访问模式; 监视所述多个盘之间的访问模式并监视所述多个存储机构的性能特征，以确定所述多个存储机构的性能要求。 最后，该方法包括将多个均匀大小的段中的至少一个段从多个存储机构的第一存储机制迁移到多个存储机构中的第二存储机制的步骤， 访问模式或性能要求。

公开(公告)号：US08495348B2

公开(公告)日：2013-07-23

申请号：US12215223

申请日：2008-06-26

申请人： Ross Zwisler ,  Brian McKean

发明人： Ross Zwisler ,  Brian McKean

IPC分类号： G06F9/00 ,  G06F15/177 ,  G06F1/24 ,  G06F21/00 ,  H04L29/06

CPC分类号： G06F9/4408 ,  G06F11/2056

摘要： A system and method for root booting includes a plurality of computing devices that each boot from a read-only base volume of an attached storage device that includes data common to the computing devices. The attached storage device also includes a plurality of volumes, each dedicated to one of the computing devices, which are redirect on write snapshots of the read-only base volume including unique items for the respective computing device. The read-only base volume may be stored in one or more solid state drives which may be configured as a RAID (redundant array of independent disks) and/or mirrored with one or more other storage drives. The plurality of volumes may each be stored in one or more hard disk drives which may be configured as a RAID. The attached storage device may be operable to add common data to the read-only base volume.

摘要翻译： 用于根引导的系统和方法包括多个计算设备，每个计算设备每个从附加存储设备的只读基本卷引导，其包括计算设备公用的数据。 连接的存储设备还包括多个卷，每个卷专用于计算设备中的一个，其在仅读基本卷的写入快照上重定向，包括用于各个计算设备的唯一项。 只读基本卷可以存储在可被配置为RAID（独立磁盘的冗余阵列）和/或与一个或多个其他存储驱动器镜像的一个或多个固态驱动器中。 多个卷可以各自存储在可被配置为RAID的一个或多个硬盘驱动器中。 附加的存储设备可以用于将公共数据添加到只读基本卷。

公开(公告)号：US20090327685A1

公开(公告)日：2009-12-31

申请号：US12215223

申请日：2008-06-26

申请人： Ross Zwisler ,  Brian McKean

发明人： Ross Zwisler ,  Brian McKean

IPC分类号： G06F15/177

CPC分类号： G06F9/4408 ,  G06F11/2056

摘要： A system and method for root booting includes a plurality of computing devices that each boot from a read-only base volume of an attached storage device that includes data common to the computing devices. The attached storage device also includes a plurality of volumes, each dedicated to one of the computing devices, which are redirect on write snapshots of the read-only base volume including unique items for the respective computing device. The read-only base volume may be stored in one or more solid state drives which may be configured as a RAID (redundant array of independent disks) and/or mirrored with one or more other storage drives. The plurality of volumes may each be stored in one or more hard disk drives which may be configured as a RAID. The attached storage device may be operable to add common data to the read-only base volume.

摘要翻译： 用于根引导的系统和方法包括多个计算设备，每个计算设备每个从附加存储设备的只读基本卷引导，其包括计算设备公用的数据。 连接的存储设备还包括多个卷，每个卷专用于计算设备中的一个，其在仅读基本卷的写入快照上重定向，包括用于各个计算设备的唯一项。 只读基本卷可以存储在可被配置为RAID（独立磁盘的冗余阵列）和/或与一个或多个其他存储驱动器镜像的一个或多个固态驱动器中。 多个卷可以各自存储在可被配置为RAID的一个或多个硬盘驱动器中。 附加的存储设备可以用于将公共数据添加到只读基本卷。

公开(公告)号：US20110029729A1

公开(公告)日：2011-02-03

申请号：US12512642

申请日：2009-07-30

申请人： Ross E. Zwisler ,  Brian McKean ,  Kevin Kidney

发明人： Ross E. Zwisler ,  Brian McKean ,  Kevin Kidney

IPC分类号： G06F12/06 ,  G06F12/16

CPC分类号： G06F3/0647 ,  G06F3/0608 ,  G06F3/0632 ,  G06F3/064 ,  G06F3/0665 ,  G06F3/0689 ,  G06F11/1008

摘要： A set of data is allocated into a plurality of data chunks, wherein the plurality of data chunks is thinly provisioned and erasure coded. A plurality of storage devices is divided into a first and a second set of storage devices, wherein the first set of storage devices is powered up and the second set of storage devices is powered down. The data chunks are distributed on the first set of storage devices to equally load each of the first set of storage devices. A storage device from the second set of storage devices is powered up to reassign the storage device from the second set of storage devices to the first set of storage devices. Data chunks are migrated to a reassigned storage device until the data chunks are evenly distributed on the first set of storage devices and the reassigned storage device.

摘要翻译： 一组数据被分配到多个数据块中，其中多个数据块被稀疏地配置和擦除编码。 多个存储设备被分成第一和第二组存储设备，其中第一组存储设备被加电并且第二组存储设备被断电。 数据块被分布在第一组存储设备上以平均地加载第一组存储设备中的每一个。 来自第二组存储设备的存储设备被上电以将存储设备从第二组存储设备重新分配到第一组存储设备。 将数据块迁移到重新分配的存储设备，直到数据块均匀分布在第一组存储设备和重新分配的存储设备上。

公开(公告)号：US08478911B2

公开(公告)日：2013-07-02

申请号：US13017177

申请日：2011-01-31

申请人： Brian McKean ,  Donald Humlicek

发明人： Brian McKean ,  Donald Humlicek

IPC分类号： G06F3/00

CPC分类号： G06F3/0604 ,  G06F3/0647 ,  G06F3/0685

摘要： Methods and systems for migrating data between storage tiers may include various operations, including, but not limited to: determining at least one activity index of at least one data storage region; receiving an input/output request addressing at least one data segment included in the at least one data storage region; qualifying a data segment addressed by the input/output request for migration to at least one higher-performing storage device; and adding a data segment reference associated with a qualified data segment to a priority queue according to the at least one activity index.

摘要翻译： 用于在存储层之间迁移数据的方法和系统可以包括各种操作，包括但不限于：确定至少一个数据存储区域的至少一个活动索引; 接收寻址包含在所述至少一个数据存储区域中的至少一个数据段的输入/输出请求; 限定由输入/输出请求寻址的数据段以迁移到至少一个更高性能的存储设备; 以及根据所述至少一个活动索引将与限定数据段相关联的数据段引用添加到优先级队列。