Patents by Inventor Vimalkumar P. Gajjar
Vimalkumar P. Gajjar has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20260104953Abstract: A method for a storage network begins by encoding a data file to generate a set of encoded data shares using a first threshold based secret sharing scheme in accordance with first secret sharing parameters, selecting a set of storage units of the storage network for storing the set of encoded data shares and sending the set of encoded data shares to the set of storage units. The method continues with a storage unit of the set of storage units receiving a first encoded data share of the set of encoded data shares and encoding the first encoded data share using a second threshold based secret sharing scheme to generate a set of encoded data sub-shares. Finally, the method continues with the storage unit storing the set of encoded data sub-shares in a set of memory devices of the first storage unit.Type: ApplicationFiled: December 15, 2025Publication date: April 16, 2026Applicant: Pure Storage, Inc.Inventors: Jason K. Resch, Vimalkumar P. Gajjar, S. Christopher Gladwin, Kumar Abhijeet
-
Patent number: 12498999Abstract: A method for a storage network computing device includes receiving a request to store a data object and generating a plurality of write slice requests, where the plurality of write slice requests includes a set of encoded data slices to be stored in the storage network and at least a decode threshold number of encoded data slices of the set of encoded data slices is required to recover a corresponding portion of a data object. The method continues by identifying a set of storage devices (from a plurality) for storage of the set of encoded data slices, where the plurality of storage devices includes one or more first memory devices local to the computing device and one or more second memory devices that are remote from the computing device. The method then continues, by storing the set of encoded data slices in the identified set of storage devices, generating a set of write slice responses relating to the set of encoded data slices and outputting the set of write slice responses.Type: GrantFiled: April 8, 2024Date of Patent: December 16, 2025Assignee: Pure Storage, Inc.Inventors: Jason K. Resch, Vimalkumar P. Gajjar, S. Christopher Gladwin, Kumar Abhijeet
-
Publication number: 20240256384Abstract: A method for a storage network computing device includes receiving a request to store a data object and generating a plurality of write slice requests, where the plurality of write slice requests includes a set of encoded data slices to be stored in the storage network and at least a decode threshold number of encoded data slices of the set of encoded data slices is required to recover a corresponding portion of a data object. The method continues by identifying a set of storage devices (from a plurality) for storage of the set of encoded data slices, where the plurality of storage devices includes one or more first memory devices local to the computing device and one or more second memory devices that are remote from the computing device. The method then continues, by storing the set of encoded data slices in the identified set of storage devices, generating a set of write slice responses relating to the set of encoded data slices and outputting the set of write slice responses.Type: ApplicationFiled: April 8, 2024Publication date: August 1, 2024Applicant: Pure Storage, Inc.Inventors: Jason K. Resch, Vimalkumar P. Gajjar, S. Christopher Gladwin, Kumar Abhijeet
-
Patent number: 10496480Abstract: A method for execution by a dispersed storage and task (DST) client module includes obtaining a data identifier for slice location identification. A source name corresponding to the data identifier is identified. A plurality of data segments are identified based on the source name. A set of slice names are generated for each of the plurality of data segments. A set of DST execution units are identified based on the sets of slice names. A set of query requests are generated for each data segment for transmission to the set of DST execution units. Query responses are received from the set of DST execution units. A storage record is generated that includes storage location information of the query responses. Migration of at least some encoded data slices associated with the sets of slice names is facilitated when the storage record compares unfavorably to a storage record requirement.Type: GrantFiled: June 7, 2018Date of Patent: December 3, 2019Assignee: PURE STORAGE, INC.Inventors: Vimalkumar P. Gajjar, Jason K. Resch
-
Publication number: 20190294494Abstract: Methods and devices for use in a dispersed storage network (DSN) to emulate storage units. In various examples, a storage unit or other computing device of the DSN receives a set of write slice requests including a set of encoded data slices for storage in the DSN and a set of slice names corresponding to the encoded data slices. The storage unit identifies a set of storage devices for storage of the set of encoded data slices using various described criteria. The identified storage devices include one or more memory devices of the storage unit and one or more temporary memory devices accessible by the storage unit. The storage unit stores the encoded data slices in the identified set of storage devices, generates a set of write slice responses relating to the set of encoded data slices and outputs the set of write slice responses to a requesting entity.Type: ApplicationFiled: June 13, 2019Publication date: September 26, 2019Inventors: Jason K. Resch, Vimalkumar P. Gajjar, S. Christopher Gladwin, Kumar Abhijeet
-
Publication number: 20180285194Abstract: A method for execution by a dispersed storage and task (DST) client module includes obtaining a data identifier for slice location identification. A source name corresponding to the data identifier is identified. A plurality of data segments are identified based on the source name. A set of slice names are generated for each of the plurality of data segments. A set of DST execution units are identified based on the sets of slice names. A set of query requests are generated for each data segment for transmission to the set of DST execution units. Query responses are received from the set of DST execution units. A storage record is generated that includes storage location information of the query responses. Migration of at least some encoded data slices associated with the sets of slice names is facilitated when the storage record compares unfavorably to a storage record requirement.Type: ApplicationFiled: June 7, 2018Publication date: October 4, 2018Inventors: Vimalkumar P. Gajjar, Jason K. Resch
-
Patent number: 10073737Abstract: A method for execution by a dispersed storage and task (DST) client module includes obtaining a data identifier for slice location identification. A source name corresponding to the data identifier is identified. A plurality of data segments are identified based on the source name. A set of slice names are generated for each of the plurality of data segments. A set of DST execution units are identified based on the sets of slice names. A set of query requests are generated for each data segment for transmission to the set of DST execution units. Query responses are received from the set of DST execution units. A storage record is generated that includes storage location information of the query responses. Migration of at least some encoded data slices associated with the sets of slice names is facilitated when the storage record compares unfavorably to a storage record requirement.Type: GrantFiled: August 28, 2017Date of Patent: September 11, 2018Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Vimalkumar P. Gajjar, Jason K. Resch
-
Publication number: 20170357546Abstract: A method for execution by a dispersed storage and task (DST) client module includes obtaining a data identifier for slice location identification. A source name corresponding to the data identifier is identified. A plurality of data segments are identified based on the source name. A set of slice names are generated for each of the plurality of data segments. A set of DST execution units are identified based on the sets of slice names. A set of query requests are generated for each data segment for transmission to the set of DST execution units. Query responses are received from the set of DST execution units. A storage record is generated that includes storage location information of the query responses. Migration of at least some encoded data slices associated with the sets of slice names is facilitated when the storage record compares unfavorably to a storage record requirement.Type: ApplicationFiled: August 28, 2017Publication date: December 14, 2017Inventors: Vimalkumar P. Gajjar, Jason K. Resch