公开(公告)号：US20170091035A1

公开(公告)日：2017-03-30

申请号：US15248493

申请日：2016-08-26

Applicant: International Business Machines Corporation

Inventor： Asimuddin Kazi ,  Ravi V. Khadiwala ,  Jason K. Resch

IPC: G06F11/10 ,  G06F3/06 ,  H03M13/15

CPC classification number: G06F3/0653 ,  G06F3/0611 ,  G06F3/0614 ,  G06F3/0619 ,  G06F3/064 ,  G06F3/0659 ,  G06F3/0661 ,  G06F3/067 ,  G06F8/65 ,  G06F11/1092 ,  H03M13/1515 ,  H03M13/154 ,  H03M13/3761 ,  H04L63/061 ,  H04L67/02 ,  H04L67/06 ,  H04L67/1097 ,  H04L67/32 ,  H04L67/34 ,  H04L67/42

Abstract: A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN) begins by detecting, by an access module, a write failure of an encoded data slice to a storage unit of a set of DSN storage units. The method continues when detecting the write failure, by adding by the access module, an error entry to an error list. The method continues by recovering, by an integrity module, the error entry from the error list. The method continues by generating, by the integrity module, a rebuilt encoded data slice for the encoded data slice of the write failure. The method continues by facilitating storage of the rebuilt encoded data slice in the storage unit associated with the write failure.

公开(公告)号：US20170091033A1

公开(公告)日：2017-03-30

申请号：US15272968

申请日：2016-09-22

Applicant: International Business Machines Corporation

Inventor： Wesley B. Leggette

IPC: G06F11/10 ,  G06F3/06

CPC classification number: G06F3/0653 ,  G06F3/0611 ,  G06F3/0614 ,  G06F3/0619 ,  G06F3/064 ,  G06F3/0659 ,  G06F3/0661 ,  G06F3/067 ,  G06F8/65 ,  G06F11/1092 ,  H03M13/1515 ,  H03M13/154 ,  H03M13/3761 ,  H04L63/061 ,  H04L67/02 ,  H04L67/06 ,  H04L67/1097 ,  H04L67/32 ,  H04L67/34 ,  H04L67/42

Abstract: A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN) begins by identifying an unrecoverable encoded data slice of a data segment stored in a set of DSN storage units, where a region of a data object includes a plurality of data segments, and where the plurality of data segments includes the data segment. The method continues by determining whether the data segment is recoverable. The method continues, when recoverable, by salvaging the region by indicating that the region has corruption, updating a directory and replacing the data segment with filler data, and when not recoverable, by not salvaging the region by indicating that the region has been eliminated.

公开(公告)号：US20170091032A1

公开(公告)日：2017-03-30

申请号：US15249130

申请日：2016-08-26

Applicant: International Business Machines Corporation

Inventor： Andrew G. Peake

IPC: G06F11/10 ,  G06F3/06

CPC classification number: G06F3/0653 ,  G06F3/0611 ,  G06F3/0614 ,  G06F3/0619 ,  G06F3/064 ,  G06F3/0659 ,  G06F3/0661 ,  G06F3/067 ,  G06F8/65 ,  G06F11/1092 ,  H03M13/1515 ,  H03M13/154 ,  H03M13/3761 ,  H04L63/061 ,  H04L67/02 ,  H04L67/06 ,  H04L67/1097 ,  H04L67/32 ,  H04L67/34 ,  H04L67/42

Abstract: A method for execution by a computing device of a dispersed storage network. The method begins by determining whether frequency of access to a set of encoded data slices exceeds a frequently accessed threshold. The method continues, when the frequency of access exceeds the frequently accessed threshold, by determining an access amount indicative of a degree that the frequency of access exceeds the frequently accessed threshold. The method continues by generating a number of additional encoded data slices and storing the number of additional encoded data slices in a number of additional storage units, wherein the set of storage units and the number of additional storage units produce an expanded set of storage units. The method continues by sending a plurality of data access requests to subsets of the expanded set of storage units in a distributed manner to improve processing efficiency of the plurality of data access requests.

公开(公告)号：US20170091030A1

公开(公告)日：2017-03-30

申请号：US15218743

申请日：2016-07-25

Applicant: International Business Machines Corporation

Inventor： Harsha Hegde ,  Wesley B. Leggette

IPC: G06F11/10 ,  G06F3/06

CPC classification number: G06F3/0653 ,  G06F3/0611 ,  G06F3/0614 ,  G06F3/0619 ,  G06F3/064 ,  G06F3/0659 ,  G06F3/0661 ,  G06F3/067 ,  G06F8/65 ,  G06F11/1092 ,  H03M13/1515 ,  H03M13/154 ,  H03M13/3761 ,  H04L63/061 ,  H04L67/02 ,  H04L67/06 ,  H04L67/1097 ,  H04L67/32 ,  H04L67/34 ,  H04L67/42

Abstract: Methods for use in a dispersed storage network (DSN) to enable rapid retrieval of data. A first set of storage units of the DSN is configured as a performance optimized internal vault that utilizes dispersed error encoding/decoding parameters which provide improved data access performance in relation to a second set of storage units. Upon receiving a data object for storage, a computing device of the DSN determines, based on at least one performance criterion, to store the data object in the performance optimized internal vault as opposed to the second set of storage units. The data object is then dispersed storage error encoded, in accordance with dispersal parameters associated with storage of data in the internal vault, to produce a plurality of sets of performance encoded data slices, wherein the data object is segmented and each resulting data segment is encoded into a respective set of performance encoded data slices.

公开(公告)号：US09606870B1

公开(公告)日：2017-03-28

申请号：US14230405

申请日：2014-03-31

Applicant: EMC Corporation

Inventor： David Meiri ,  Anton Kucherov ,  Vladimir Shveidel

IPC: G06F11/00 ,  G06F11/10 ,  G11C29/52

CPC classification number: G06F3/0638 ,  G06F3/0608 ,  G06F3/0619 ,  G06F3/0661 ,  G06F3/0688 ,  G06F11/1068 ,  G06F11/108 ,  G06F11/1092 ,  G06F11/2069 ,  G06F2201/85 ,  G06F2211/1014 ,  G11C29/52 ,  G11C2207/102

Abstract: In one aspect, a method includes splitting empty RAID stripes into sub-stripes and storing pages into the sub-stripes based on a compressibility score. In another aspect, a method includes reading pages from 1-stripes, storing compressed data in a temporary location, reading multiple stripes, determining compressibility score for each stripe and filling stripes based on the compressibility score. In a further aspect, a method includes scanning a dirty queue in a system cache, compressing pages ready for destaging, combining compressed pages in to one aggregated page, writing one aggregated page to one stripe and storing pages with same compressibility score in a stripe.

公开(公告)号：US20170060689A1

公开(公告)日：2017-03-02

申请号：US15252444

申请日：2016-08-31

Applicant: International Business Machines Corporation

Inventor： Jason K. Resch

IPC: G06F11/10 ,  G06F3/06

CPC classification number: G06F3/0619 ,  G06F3/061 ,  G06F3/0611 ,  G06F3/0622 ,  G06F3/0635 ,  G06F3/0637 ,  G06F3/064 ,  G06F3/0644 ,  G06F3/0659 ,  G06F3/0665 ,  G06F3/067 ,  G06F3/0689 ,  G06F11/1076 ,  G06F11/1092 ,  G06F11/3034 ,  G06F11/3409 ,  G06F12/1408 ,  G06F2212/1052 ,  H03M13/1515 ,  H04L67/1097

Abstract: A method begins by determining whether at least one encoded data slice of a corresponding set of encoded data slices associated with a primary storage unit requires rebuilding and includes one or more excess encoded data slices of the set of encoded data slices stored in a secondary storage unit. The method continues by identifying the excess encoded data slices based on scan response messages from the secondary storage units. The method continues by assigning, for each data segment associated with at least one of an encoded data slice requiring rebuilding and an excess encoded data slice, a priority level in accordance with a prioritization scheme. The method continues by facilitating, for each data segment, rebuilding of the encoded data slices requiring rebuilding and deletion of excess encoded data slices requiring deletion in accordance with the assigned priority level of the data segment.

Abstract translation: 方法开始于确定与主要存储单元相关联的对应的一组编码数据片段的至少一个编码数据片段是否需要重建，并且包括存储在辅助存储单元中的编码数据片段集合中的一个或多个过量编码的数据片段 。 该方法通过基于来自辅助存储单元的扫描响应消息来识别多余的编码数据片断而继续。 该方法通过根据优先化方案为与需要重建的编码数据切片和超量编码数据切片中的至少一个相关联的每个数据段分配优先级等级。 该方法继续促进对于每个数据段，根据分配的数据段的优先级重建需要重构和删除需要删除的多余编码数据片的编码数据片。

公开(公告)号：US20170060466A1

公开(公告)日：2017-03-02

申请号：US15350904

申请日：2016-11-14

Applicant: International Business Machines Corporation

Inventor： Wesley B. Leggette ,  Jason K. Resch ,  Sebastien Vas

IPC: G06F3/06

CPC classification number: G06F3/0637 ,  G06F3/0619 ,  G06F3/0622 ,  G06F3/064 ,  G06F3/0659 ,  G06F3/067 ,  G06F11/008 ,  G06F11/1076 ,  G06F11/1092 ,  G06F2211/109 ,  H03M13/1515 ,  H03M13/3761

Abstract: A method includes issuing, by a managing unit of a dispersed storage network (DSN), a vault access restriction to a set of storage units of the DSN regarding a logical storage vault supported by the set of storage units. While the vault access restriction is active, the method continues by receiving, by a storage unit of the set of storage units, a data access request to the vault. The method continues by determining, by the storage unit, whether the data access request is regarding a rebuilding operation. When the data access request is regarding a rebuilding operation, the method continues by processing, by the storage unit, the data access request. When data access request is not regarding a rebuilding operation, the method continues by denying, by the storage unit, the data access request.

Abstract translation: 一种方法包括：通过分散存储网络（DSN）的管理单元向所述DSN的一组存储单元发布关于由所述一组存储单元支持的逻辑存储库的保管库访问限制。 当文件库访问限制处于活动状态时，该方法通过由该组存储单元的存储单元接收到该文件库的数据访问请求来继续。 该方法通过由存储单元确定数据访问请求是否涉及重建操作来继续。 当数据访问请求涉及重建操作时，该方法继续通过存储单元处理数据访问请求。 当数据访问请求不涉及重建操作时，该方法通过由存储单元拒绝数据访问请求来继续。

公开(公告)号：US20170052828A1

公开(公告)日：2017-02-23

申请号：US15341722

申请日：2016-11-02

Applicant: International Business Machines Corporation

Inventor： Andrew D. Baptist ,  Greg R. Dhuse ,  S. Christopher Gladwin ,  Gary W. Grube ,  Wesley B. Leggette ,  Manish Motwani ,  Jason K. Resch ,  Thomas F. Shirley, JR. ,  Ilya Volvovski

IPC: G06F9/50 ,  H04L29/08

CPC classification number: G06F9/5083 ,  G06F3/0619 ,  G06F3/064 ,  G06F3/067 ,  G06F9/5077 ,  G06F11/1008 ,  G06F11/1076 ,  G06F11/1092 ,  G06F11/1451 ,  G06F11/2058 ,  G06F11/2069 ,  G06F21/602 ,  G06F21/6218 ,  G06F2211/1028 ,  H03M13/09 ,  H03M13/1515 ,  H04L63/0428 ,  H04L63/06 ,  H04L63/08 ,  H04L63/10 ,  H04L67/10 ,  H04L67/1017 ,  H04L67/1097

Abstract: A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN), by selecting a number of distributed storage and task execution (DST) EX units to favorably execute partial tasks of the corresponding tasks. The method continues by determining task partitioning based on one or more of distributed computing capabilities of the selected DST EX units. The method continues by determining processing parameters of the data based on the task partitioning. The method continues by partitioning the task(s) based on the task partitioning to produce the partial tasks. The method continues by processing the data in accordance with the processing parameters to produce slice groupings and sending the slice groupings and corresponding partial tasks to the DST EX units in accordance with a pillar mapping.

Abstract translation: 通过选择分散存储和任务执行（DST）EX单元的数量来有利地执行相应任务的部分任务的用于由分散存储网络（DSN）的一个或多个计算设备的一个或多个处理模块执行的方法。 该方法通过基于所选DST EX单元的分布式计算能力中的一个或多个来确定任务划分来继续。 该方法通过基于任务分区确定数据的处理参数来继续。 该方法通过基于任务分区划分任务以产生部分任务来继续。 该方法通过根据处理参数处理数据来继续，以根据柱映射产生切片分组并将切片分组和相应的部分任务发送到DST EX单元。

公开(公告)号：US09569131B2

公开(公告)日：2017-02-14

申请号：US14814280

申请日：2015-07-30

Applicant: Tintri Inc.

Inventor： Shobhit Dayal ,  Edward K. Lee ,  Mark G. Gritter

IPC: G06F12/00 ,  G06F3/06 ,  G06F11/22 ,  G06F11/30 ,  G06F11/10 ,  G06F12/02 ,  G06F12/08 ,  G06F13/16 ,  G06F11/07

CPC classification number: G06F3/0611 ,  G06F3/0632 ,  G06F3/0634 ,  G06F3/065 ,  G06F3/0653 ,  G06F3/0659 ,  G06F3/0683 ,  G06F3/0689 ,  G06F11/0727 ,  G06F11/0757 ,  G06F11/1088 ,  G06F11/1092 ,  G06F11/22 ,  G06F11/3055 ,  G06F12/0246 ,  G06F12/0897 ,  G06F13/1694

Abstract: Avoiding long access latencies in redundant storage systems is disclosed, including: determining a first device associated with a request is in a slow access period; and reconstructing data associated with the request from one or more other devices comprising a redundant storage system in which the first device and the one or more other devices are included.

Abstract translation: 公开了避免在冗余存储系统中的长访问延迟，包括：确定与请求相关联的第一设备处于缓慢的访问时段; 以及重建与来自一个或多个其他设备的请求相关联的数据，所述其他设备包括其中包括第一设备和一个或多个其他设备的冗余存储系统。

公开(公告)号：US09563511B1

公开(公告)日：2017-02-07

申请号：US14662385

申请日：2015-03-19

Applicant: EMC Corporation

Inventor： Robert Foley ,  Peter Puhov ,  Socheavy Heng

IPC: G06F11/20 ,  G06F11/10 ,  G06F3/06 ,  G06F11/14

CPC classification number: G06F11/1092 ,  G06F3/061 ,  G06F3/0655 ,  G06F3/0659 ,  G06F3/0689 ,  G06F11/1456 ,  G06F11/2058 ,  G06F11/2094

Abstract: A technique configures data storage equipment to (i) allow host I/O operations to start on storage devices while a credit tally is less than a predefined credit quota and (ii) block host I/O operations from starting on the storage devices while the tally is greater than the quota. The technique further involves, while a rebuild procedure is not being performed on the storage devices, (i) allocating host I/O credits at equal weight to the tally upon starting host I/O operations and (ii) de-allocating the credits at equal weight from the tally upon completion of the operations. The technique further involves, while the rebuild procedure is being performed on the storage devices, (i) allocating host I/O credits at greater than equal weight to the tally upon starting host I/O operations and (ii) de-allocating the credits at greater than equal weight from the tally upon completion of the operations.

Abstract translation: 一种技术配置数据存储设备以（i）允许主机I / O操作在存储设备上启动，而信用计数小于预定义的信用配额，以及（ii）阻止主机I / O操作在存储设备上启动，而 配额大于配额。 该技术还涉及在不在存储设备上执行重建过程的同时，（i）在启动主机I / O操作时，以相等的权重分配主机I / O信用，并且（ii）在 完成操作后的计数相等。 该技术进一步涉及在存储设备上执行重建过程时，（i）在启动主机I / O操作时将主机I / O信用分配给大于等于重量的计数，以及（ii）取消分配信用 在完成操作后，从计数大于等于重量。