-
公开(公告)号：US12001688B2
公开(公告)日：2024-06-04
申请号：US17034361
申请日：2020-09-28
申请人： PURE STORAGE, INC.
发明人： Robert Lee , John Colgrove , Bikash Roy Choudhury , Mandeep Arora , Roy Child , Purvaja Narayanaswamy , Cary A. Sandvig
IPC分类号： G06F3/06
CPC分类号： G06F3/0622 , G06F3/0604 , G06F3/0653 , G06F3/0659 , G06F3/067
摘要： A storage system has filtered views of data. The storage system receives a read request for a filtered view of data in memory. The read request is associated with one or more permissions for viewing the data. The storage system identifies a subset of the data, based on the one or more permissions. The storage system provides the filtered view. The filtered view includes the subset of the data.
-
公开(公告)号：US11449485B1
公开(公告)日：2022-09-20
申请号：US15641011
申请日：2017-07-03
申请人： PURE STORAGE, INC.
发明人： Robert Lee , Cary A. Sandvig
摘要： A method for tracking valid and invalid sequence numbers in a storage system, performed by a processor, is provided. The method includes establishing a table as a key value store in memory in the storage system. The table has sequence numbers as keys and represents valid sequence numbers and invalidated sequence numbers of an open-ended sequence relating to storage of data or metadata in the storage system. The method includes adding to the table an entry that records a first plurality of consecutive sequence numbers, as a first range-valued key associated with a first value indicating the first plurality of consecutive sequence numbers is valid. The method includes adding to the table an entry that records a deletion of a second plurality of consecutive sequence numbers, as a second range-valued key associated with a second value indicating the second plurality of consecutive sequence numbers is invalid.
-
公开(公告)号：US11281394B2
公开(公告)日：2022-03-22
申请号：US16450632
申请日：2019-06-24
申请人： Pure Storage, Inc.
发明人： Richard A. Hankins , Igor Ostrovsky , John Colgrove , Cary A. Sandvig , Ronald Karr , Victor Yip , Zong Miao , Abhishek Jain
摘要： A method of replication in a distributed storage system, performed by the distributed storage system is provided. The method includes managing a first index for data or metadata in a first storage system, the first storage system having a first partitioning scheme. The method includes managing a second index for data or metadata in a second storage system, the second storage system having a second partitioning scheme. The method includes replicating the data or metadata from the first storage system to the second storage system, translating an identifier of the data or metadata from the first storage system, and mapping the replicated data or metadata into the second partitioning scheme, via the translating of the identifier of the data or metadata from the first storage system.
-
公开(公告)号：US10942869B2
公开(公告)日：2021-03-09
申请号：US16725639
申请日：2019-12-23
申请人： Pure Storage, Inc.
发明人： Robert Lee , Cary A. Sandvig
IPC分类号： H03M7/00 , G06F12/14 , G06F3/06 , G06F16/36 , G06F16/901 , G06F16/903 , G06F16/28
摘要： A method for efficient name coding in a storage system is provided. The method includes identifying common prefixes, common suffixes, and midsections of a plurality of strings in the storage system, and writing the common prefixes, midsections and common suffixes to a string table in the storage system. The method includes encoding each string of the plurality of strings as to position in the string table of prefix, midsection and suffix of the string, and writing the encoding of each string to memory in the storage system for the plurality of strings, in the storage system.
-
公开(公告)号：US10915813B2
公开(公告)日：2021-02-09
申请号：US16449241
申请日：2019-06-21
申请人： Pure Storage, Inc.
发明人： Fabio Margaglia , Emily Watkins , Hari Kannan , Cary A. Sandvig
摘要： An apparatus for artificial intelligence acceleration is provided. The apparatus includes a storage and compute system having a distributed, redundant key value store for metadata. The storage and compute system having distributed compute resources configurable to access, through a plurality of authorities, data in the solid-state memory, run inference with a deep learning model, generate vectors for the data and store the vectors in the key value store.
-
公开(公告)号：US11995336B2
公开(公告)日：2024-05-28
申请号：US16397947
申请日：2019-04-29
申请人： Pure Storage, Inc.
CPC分类号： G06F3/065 , G06F3/061 , G06F3/0652 , G06F3/0679 , G06F11/1453
摘要： A method of operating an object-based storage system, practiced by the storage system, is provided. The method includes establishing a plurality of buckets for objects, in the storage system and establishing a plurality of bucket views in the storage system, each bucket view supporting access to objects of one of the plurality of buckets. The method includes accessing an object of a bucket through one of the plurality of bucket views.
-
公开(公告)号：US11262929B2
公开(公告)日：2022-03-01
申请号：US16730066
申请日：2019-12-30
申请人： PURE STORAGE, INC.
摘要： 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：US20200151164A1
公开(公告)日：2020-05-14
申请号：US16738356
申请日：2020-01-09
申请人： PURE STORAGE, INC.
IPC分类号： G06F16/23 , G06F16/174 , G06F16/901 , G06F3/06
摘要： System and methods for evicting and inserting eviction an entry for a deduplication table are described.
-
公开(公告)号：US10528280B1
公开(公告)日：2020-01-07
申请号：US15420726
申请日：2017-01-31
申请人： Pure Storage, Inc.
摘要： 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
申请人： Pure Storage, Inc.
发明人： John Colgrove , Ronald Karr , Ethan L. Miller , Vinay K. Perneti , Cary A. Sandvig , Feng Wang , Wei Zhang
CPC分类号： G06F3/0641 , G06F3/0608 , G06F3/0611 , G06F3/0652 , G06F3/067 , G06F3/0685
摘要： 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.
-
-
-
-
-
-
-
-
-
搜索结果
25 条记录 (耗时 0.027 秒)
