-
61.发明申请公开(公告)号：US20170060687A1
公开(公告)日：2017-03-02
申请号：US15350946
申请日：2016-11-14
Applicant: Amazon Technologies, Inc.
CPC classification number: G06F11/1076 , G06F3/0619 , G06F3/064 , G06F3/067 , G06F11/1088 , G06F11/167 , G06F2211/1028 , G06F2211/104 , H03M13/1515 , H03M13/154 , H03M13/616
Abstract: Techniques described and suggested herein include systems and methods for precomputing regeneration information for data archives (“archives”) that have been processed and stored using redundancy coding techniques. For example, regeneration information, such as redundancy code-related matrices (such as inverted matrices based on, e.g., a generator matrix for the selected redundancy code) corresponding to subsets of the shards, is computed for each subset and, in some embodiments, stored for use in the event that one or more shards becomes unavailable, e.g., so as to more efficiently and/or quickly regenerate a replacement shard.
Abstract translation: 本文描述和提出的技术包括用于使用冗余编码技术预处理和存储的数据归档（“档案”）的再计算再生信息的系统和方法。 例如，针对每个子集计算对应于碎片子集的冗余代码相关矩阵（诸如基于例如用于所选择的冗余码的生成矩阵的倒排矩阵）的再生信息，并且在一些实施例中， 存储用于在一个或多个分片变得不可用的情况下使用，例如，以便更有效地和/或快速地再生替换分片。
-
公开(公告)号：US09552254B1
公开(公告)日：2017-01-24
申请号：US14500582
申请日：2014-09-29
Applicant: Amazon Technologies, Inc.
Inventor： Paul David Franklin , Jonathan Robert Collins, II
CPC classification number: G06F11/1004 , G06F11/1012 , H03M13/09 , H03M13/1515 , H03M13/3761
Abstract: Erasure encoded fragments are originally generated by applying an erasure encoding scheme to a data file. An erasure encoded fragment is subsequently generated directly from previously generated erasure encoded fragments or by reconstructing the original data file and then erasure encoding the reconstructed data file. The integrity or fidelity of such a subsequently generated erasure encoded fragment is verified by newly generating an error detection code, such as but not limited to a checksum, for the subsequently generated erasure encoded fragment, and comparing that subsequently error detection code against an error detection code previously generated for a previous or original version of the erasure encoded fragment. Each error detection code is preferably stored in association with its corresponding erasure encoded fragment and with one or more other erasure encoded fragments. Thus, each error detection code is saved in at least two locations.
Abstract translation: 最初通过对数据文件应用擦除编码方案来生成擦除编码的片段。 随后，从先前生成的擦除编码片段直接生成擦除编码片段，或通过重构原始数据文件，然后擦除对重构数据文件进行编码。 通过对随后生成的擦除编码片段新生成诸如但不限于校验和的差错检测码来验证随后生成的擦除编码片段的完整性或保真度，并将随后的错误检测码与错误检测进行比较 以前为擦除编码片段的先前或原始版本生成的代码。 优选地，每个错误检测码与其相应的擦除编码片段和一个或多个其它擦除编码片段相关联地存储。 因此，每个错误检测码被保存在至少两个位置。
-
63.发明授权公开(公告)号：US09495249B1
公开(公告)日：2016-11-15
申请号：US14675471
申请日：2015-03-31
Applicant: Amazon Technologies, Inc.
CPC classification number: G06F11/1076 , G06F3/0619 , G06F3/064 , G06F3/067 , G06F11/1088 , G06F11/167 , G06F2211/1028 , G06F2211/104 , H03M13/1515 , H03M13/154 , H03M13/616
Abstract: Techniques described and suggested herein include systems and methods for precomputing regeneration information for data archives (“archives”) that have been processed and stored using redundancy coding techniques. For example, regeneration information, such as redundancy code-related matrices (such as inverted matrices based on, e.g., a generator matrix for the selected redundancy code) corresponding to subsets of the shards, is computed for each subset and, in some embodiments, stored for use in the event that one or more shards becomes unavailable, e.g., so as to more efficiently and/or quickly regenerate a replacement shard.
Abstract translation: 本文描述和提出的技术包括用于使用冗余编码技术预处理和存储的数据归档（“档案”）的再计算再生信息的系统和方法。 例如，针对每个子集计算对应于碎片子集的冗余代码相关矩阵（诸如基于例如用于所选择的冗余码的生成矩阵的倒排矩阵）的再生信息，并且在一些实施例中， 存储用于在一个或多个分片变得不可用的情况下使用，例如，以便更有效地和/或快速地再生替换分片。
-
公开(公告)号：US09098446B1
公开(公告)日：2015-08-04
申请号：US13898066
申请日：2013-05-20
Applicant: Amazon Technologies, Inc.
Inventor： Bryan James Donlan , Paul David Franklin
IPC: G06F11/14 , H03M13/29 , H03M13/37 , H03M13/03 , H03M13/15 , H03M13/11 , H03M13/09 , H03M13/00 , H03M13/35
CPC classification number: H03M13/35 , G06F11/1451 , G06F11/1456 , G06F11/2094 , G06F2201/83 , H03M13/03 , H03M13/09 , H03M13/1102 , H03M13/1111 , H03M13/1191 , H03M13/15 , H03M13/1515 , H03M13/2906 , H03M13/293 , H03M13/356 , H03M13/373 , H03M13/3761 , H03M13/6356 , H03M13/6362
Abstract: If none of the fragments of an erasure-coded data file have become corrupted then the original data file can be readily reconstructed. If one or more fragments of an erasure-coded data file have become corrupted it may still be possible to find a combination of fragments that reconstruct the original data file, but the number of possible combinations may be impracticably large. If an attempt with a first set of fragments fails, an efficient approach is to use an independent set of fragments for the second attempt. Then, for further attempts, the results of a current attempt are compared with previous results. If a match is found then the original data file has been reconstructed. An original data file may also be reconstructed by separately recovering each data block of the data file from corresponding fragment blocks and assembling the data file from the recovered data blocks.
-
-
-
Search Results
64
records
(took 0.016 seconds)
