公开(公告)号：US09298376B2

公开(公告)日：2016-03-29

申请号：US14083163

申请日：2013-11-18

Applicant: PURE Storage, Inc.

Inventor： John Colgrove ,  John Hayes ,  Bo Hong ,  Feng Wang ,  Ethan Miller ,  Craig Harmer

IPC: G06F3/06 ,  G06F11/07 ,  G06F11/10 ,  G06F11/34 ,  G06F12/08 ,  G06F11/30

CPC classification number: G06F3/0611 ,  G06F3/061 ,  G06F3/0613 ,  G06F3/0629 ,  G06F3/0653 ,  G06F3/0655 ,  G06F3/0659 ,  G06F3/0688 ,  G06F11/0727 ,  G06F11/0751 ,  G06F11/1076 ,  G06F11/3034 ,  G06F11/3055 ,  G06F11/3409 ,  G06F11/3485 ,  G06F12/0804 ,  G06F12/0866 ,  G06F2212/262 ,  G06F2212/502

Abstract: A system and method for effectively scheduling read and write operations among a plurality of solid-state storage devices. A computer system comprises client computers and data storage arrays coupled to one another via a network. A data storage array utilizes solid-state drives and Flash memory cells for data storage. A storage controller within a data storage array comprises an I/O scheduler. The characteristics of corresponding storage devices are used to schedule I/O requests to the storage devices in order to maintain relatively consistent response times at predicted times. In order to reduce a likelihood of unscheduled behaviors of the storage devices, the storage controller is configured to schedule proactive operations on the storage devices that will reduce a number of occurrences of unscheduled behaviors.

公开(公告)号：US09251066B2

公开(公告)日：2016-02-02

申请号：US14537709

申请日：2014-11-10

Applicant: PURE Storage, Inc.

Inventor： John Colgrove ,  John Hayes ,  Ethan Miller ,  Cary Sandvig ,  Joseph S. Hasbani ,  Feng Wang

IPC: G06F17/30 ,  G06F12/02 ,  G06F3/06

CPC classification number: G06F12/0253 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/0641 ,  G06F3/065 ,  G06F3/0665 ,  G06F3/067 ,  G06F3/0688 ,  G06F17/30156 ,  G06F2212/702

Abstract: A system and method for performing garbage collection. A system includes a storage medium, a first table including entries which map a virtual address to locations in the storage medium, and a second table with entries which include a reverse mapping of a physical address in a data storage medium to one or more virtual addresses. A storage controller is configured to perform garbage collection. During garbage collection, the controller is configured to identify one or more entries in the second table which correspond to a segment to be garbage collected. In response to determining the first table includes a valid mapping for a virtual address included in an entry of the one of the one or more entries, the controller is configured to copy data from a first location identified in the entry to a second location in the data storage medium, and reclaim the first storage location.

公开(公告)号：US11262929B2

公开(公告)日：2022-03-01

申请号：US16730066

申请日：2019-12-30

Applicant: PURE STORAGE, INC.

Inventor： Cary A. Sandvig ,  Constantine P. Sapuntzakis ,  Feng Wang

IPC: G06F12/00 ,  G06F3/06 ,  G06F12/02

Abstract: An implementation of the disclosure provides a system comprising a storage array comprising a storage controller coupled to the storage array. The storage controller comprising a processing device to remap a plurality of deduplication references in a deduplication map to point to an earlier occurrence of duplicate data of a data block for the deduplication map. The processing device further to update an entry of the deduplication map associated with the plurality of deduplication references with a record indicating that the entry is no longer referenced and trim the entry from the deduplication map that is associated with the record.

公开(公告)号：US10528280B1

公开(公告)日：2020-01-07

申请号：US15420726

申请日：2017-01-31

Applicant: Pure Storage, Inc.

Inventor： Cary A. Sandvig ,  Constantine P. Sapuntzakis ,  Feng Wang

IPC: G06F12/00 ,  G06F3/06 ,  G06F12/02

Abstract: An implementation of the disclosure provides a system comprising a storage array comprising a plurality of data blocks and a storage controller coupled to the storage array. The storage controller comprising a processing device to identify a canonical instance of a data block in a vector associated with a deduplication map. The vector represents a plurality of updates to the deduplication map over a determined time period. A deduplication reference representing duplicate data of the data block in the storage array is select from the deduplication map. The deduplication reference is remapped in the deduplication map to point to the canonical instance. Based on the remapping, an entry in the deduplication map for the deduplication reference is updated with a record. Responsive to detecting that the entry is in a location associated with an original entry of the data block in the deduplication map, delete the entry with the record.

公开(公告)号：US09940060B1

公开(公告)日：2018-04-10

申请号：US15331181

申请日：2016-10-21

Applicant: Pure Storage, Inc.

Inventor： John Colgrove ,  Ronald Karr ,  Ethan L. Miller ,  Vinay K. Perneti ,  Cary A. Sandvig ,  Feng Wang ,  Wei Zhang

IPC: G06F12/00 ,  G06F3/06

CPC classification number: G06F3/0641 ,  G06F3/0608 ,  G06F3/0611 ,  G06F3/0652 ,  G06F3/067 ,  G06F3/0685

Abstract: The method includes storing data including an index summary (IS) and a deduplication map (DDM) in volatile memory of a deduplication system. The method also includes detecting that the stored data exceeds a data allocation size limit for the volatile memory. The method includes evicting the data from the volatile memory using a memory eviction policy to meet the data allocation size limit. The method further includes performing a first eviction by evicting the DDM levels from an oldest DDM level to a newest DDM level until a first one of the data allocation size limit or a DDM threshold is met. The method also includes performing a second eviction by evicting the IS levels from an oldest IS level to a newest IS level until a first one of the data allocation size limit or IS threshold is met in response to the data allocation size limit not being met by the first eviction.

公开(公告)号：US09304694B2

公开(公告)日：2016-04-05

申请号：US14260059

申请日：2014-04-23

Applicant: PURE Storage, Inc.

Inventor： John Colgrove ,  John Hayes ,  Bo Hong ,  Feng Wang ,  Ethan Miller ,  Craig Harmer

IPC: G06F3/06 ,  G06F11/10 ,  G06F11/07

CPC classification number: G06F3/0611 ,  G06F3/061 ,  G06F3/0613 ,  G06F3/0617 ,  G06F3/0634 ,  G06F3/0659 ,  G06F3/0665 ,  G06F3/0688 ,  G06F3/0689 ,  G06F11/0751 ,  G06F11/076 ,  G06F11/1076

Abstract: A system and method for effectively scheduling read and write operations among a plurality of solid-state storage devices. A computer system comprises client computers and data storage arrays coupled to one another via a network. A data storage array utilizes solid-state drives and Flash memory cells for data storage. A storage controller within a data storage array comprises an I/O scheduler. The characteristics of corresponding storage devices are used to schedule I/O requests to the storage devices in order to maintain relatively consistent response times at predicted times. Should a device exhibit an unscheduled behavior which may be indicative of the device being in an unknown state, the scheduler may schedule one or more reactive operations on the device configured to cause the device to enter a known state.

Abstract translation: 一种用于在多个固态存储设备之间有效地调度读取和写入操作的系统和方法。 计算机系统包括经由网络彼此耦合的客户端计算机和数据存储阵列。 数据存储阵列利用固态驱动器和闪存单元进行数据存储。 数据存储阵列中的存储控制器包括I / O调度器。 相应的存储设备的特性用于将I / O请求调度到存储设备，以便在预测时间内保持相对一致的响应时间。 如果设备呈现可能指示设备处于未知状态的非计划行为，则调度器可以对被配置为使设备进入已知状态的设备上的一个或多个无效操作进行调度。

公开(公告)号：US20150067286A1

公开(公告)日：2015-03-05

申请号：US14537709

申请日：2014-11-10

Applicant: PURE Storage, Inc.

Inventor： John Colgrove ,  John Hayes ,  Ethan Miller ,  Cary Sandvig ,  Joseph S. Hasbani ,  Feng Wang

IPC: G06F12/02 ,  G06F3/06

CPC classification number: G06F12/0253 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/0641 ,  G06F3/065 ,  G06F3/0665 ,  G06F3/067 ,  G06F3/0688 ,  G06F17/30156 ,  G06F2212/702

Abstract: A system and method for performing garbage collection. A system includes a storage medium, a first table including entries which map a virtual address to locations in the storage medium, and a second table with entries which include a reverse mapping of a physical address in a data storage medium to one or more virtual addresses. A storage controller is configured to perform garbage collection. During garbage collection, the controller is configured to identify one or more entries in the second table which correspond to a segment to be garbage collected. In response to determining the first table includes a valid mapping for a virtual address included in an entry of the one of the one or more entries, the controller is configured to copy data from a first location identified in the entry to a second location in the data storage medium, and reclaim the first storage location.

Abstract translation: 一种用于执行垃圾回收的系统和方法。 系统包括存储介质，包括将虚拟地址映射到存储介质中的位置的条目的第一表以及包括数据存储介质中的物理地址与一个或多个虚拟地址的反向映射的条目的第二表 。 存储控制器被配置为执行垃圾收集。 在垃圾收集期间，控制器被配置为识别第二表中与要被垃圾收集的段相对应的一个或多个条目。 响应于确定第一表包括包含在一个或多个条目中的一个条目的条目中的虚拟地址的有效映射，控制器被配置为将数据从条目中标识的第一位置复制到第 数据存储介质，并回收第一存储位置。

公开(公告)号：US20150032958A1

公开(公告)日：2015-01-29

申请号：US14513007

申请日：2014-10-13

Applicant: PURE Storage, Inc.

Inventor： John Colgrove ,  John Hayes ,  Bo Hong ,  Feng Wang ,  Ethan Miller ,  Craig Harmer

IPC: G06F3/06

CPC classification number: G06F3/0619 ,  G06F3/061 ,  G06F3/0613 ,  G06F3/0646 ,  G06F3/0659 ,  G06F3/0665 ,  G06F3/0688 ,  G06F3/0689 ,  G06F11/0727 ,  G06F11/0751 ,  G06F11/1076 ,  G06F12/0804 ,  G06F2003/0697

Abstract: A system and method for effectively scheduling read and write operations among a plurality of solid-state storage devices. A computer system comprises client computers and data storage arrays coupled to one another via a network. A data storage array utilizes solid-state drives and Flash memory cells for data storage. A storage controller within a data storage array comprises an I/O scheduler. The storage controller is configured to receive a read request targeted to the data storage medium, and identify at least a first storage device of the plurality of storage devices which contains data targeted by the read request. In response to either detecting or predicting the first storage device will exhibit variable performance, the controller is configured to generate a reconstruct read request configured to obtain the data from one or more devices of the plurality of storage devices other than the first storage device.

Abstract translation: 一种用于在多个固态存储设备之间有效地调度读取和写入操作的系统和方法。 计算机系统包括经由网络彼此耦合的客户端计算机和数据存储阵列。 数据存储阵列利用固态驱动器和闪存单元进行数据存储。 数据存储阵列中的存储控制器包括I / O调度器。 存储控制器被配置为接收针对数据存储介质的读取请求，并且识别包含读取请求所针对的数据的多个存储设备中的至少第一存储设备。 响应于检测或预测第一存储设备将呈现可变性能，控制器被配置为生成重构读取请求，其被配置为从除第一存储设备之外的多个存储设备中的一个或多个设备获得数据。

公开(公告)号：US20140229673A1

公开(公告)日：2014-08-14

申请号：US14260059

申请日：2014-04-23

Applicant: PURE Storage, Inc.

Inventor： John Colgrove ,  John Hayes ,  Bo Hong ,  Feng Wang ,  Ethan Miller ,  Craig Harmer

IPC: G06F3/06

CPC classification number: G06F3/0611 ,  G06F3/061 ,  G06F3/0613 ,  G06F3/0617 ,  G06F3/0634 ,  G06F3/0659 ,  G06F3/0665 ,  G06F3/0688 ,  G06F3/0689 ,  G06F11/0751 ,  G06F11/076 ,  G06F11/1076

Abstract: A system and method for effectively scheduling read and write operations among a plurality of solid-state storage devices. A computer system comprises client computers and data storage arrays coupled to one another via a network. A data storage array utilizes solid-state drives and Flash memory cells for data storage. A storage controller within a data storage array comprises an I/O scheduler. The characteristics of corresponding storage devices are used to schedule I/O requests to the storage devices in order to maintain relatively consistent response times at predicted times. Should a device exhibit an unscheduled behavior which may be indicative of the device being in an unknown state, the scheduler may schedule one or more reactive operations on the device configured to cause the device to enter a known state.

Abstract translation: 一种用于在多个固态存储设备之间有效地调度读取和写入操作的系统和方法。 计算机系统包括经由网络彼此耦合的客户端计算机和数据存储阵列。 数据存储阵列利用固态驱动器和闪存单元进行数据存储。 数据存储阵列中的存储控制器包括I / O调度器。 相应的存储设备的特性用于将I / O请求调度到存储设备，以便在预测时间内保持相对一致的响应时间。 如果设备呈现可能指示设备处于未知状态的非计划行为，则调度器可以对被配置为使设备进入已知状态的设备上的一个或多个无效操作进行调度。

公开(公告)号：US20140075115A1

公开(公告)日：2014-03-13

申请号：US14083161

申请日：2013-11-18

Applicant: PURE Storage, Inc.

Inventor： John Colgrove ,  John Hayes ,  Bo Hong ,  Feng Wang ,  Ethan Miller ,  Craig Harmer

IPC: G06F3/06

CPC classification number: G06F3/0619 ,  G06F3/061 ,  G06F3/0613 ,  G06F3/0646 ,  G06F3/0659 ,  G06F3/0665 ,  G06F3/0688 ,  G06F3/0689 ,  G06F11/0727 ,  G06F11/0751 ,  G06F11/1076 ,  G06F12/0804 ,  G06F2003/0697

Abstract: A system and method for effectively scheduling read and write operations among a plurality of solid-state storage devices. A computer system comprises client computers and data storage arrays coupled to one another via a network. A data storage array utilizes solid-state drives and Flash memory cells for data storage. A storage controller within a data storage array comprises an I/O scheduler. The storage controller is configured to receive a read request targeted to the data storage medium, and identify at least a first storage device of the plurality of storage devices which contains data targeted by the read request. In response to either detecting or predicting the first storage device will exhibit variable performance, the controller is configured to generate a reconstruct read request configured to obtain the data from one or more devices of the plurality of storage devices other than the first storage device.

Abstract translation: 一种用于在多个固态存储设备之间有效地调度读取和写入操作的系统和方法。 计算机系统包括经由网络彼此耦合的客户端计算机和数据存储阵列。 数据存储阵列利用固态驱动器和闪存单元进行数据存储。 数据存储阵列中的存储控制器包括I / O调度器。 存储控制器被配置为接收针对数据存储介质的读取请求，并且识别包含读取请求所针对的数据的多个存储设备中的至少第一存储设备。 响应于检测或预测第一存储设备将呈现可变性能，控制器被配置为生成重构读取请求，其被配置为从除第一存储设备之外的多个存储设备中的一个或多个设备获得数据。