International Business Machines Corporation

Pure Storage, Inc.

Daniel J Scholl

Ravi V Khadiwala

Greg R Dhuse

Wesley B Leggette

Adam Michael Gray

Jason K Resch

Scott Michael Horan

Andrew D Baptist

Bart Richard Cilfone

Franco Vincent Borich

Manish Motwani

Yogesh Ramesh Vedpathak

Harsha Hegde

Rohan P Shah

Tyler K Reid

Ilya Volvovski

Thomas Dubucq

Renars W Narubin

Jeremy S Jarczyk

Ethan S Wozniak

Praveen Viraraghavan

Kumar Abhijeet

Brian Frederick Ober

Mark Duane Seaborn

Amit H Lamba

Kevin Michael Freese

Lakshmi Krishna Priya Kala

A method for execution by a distributed storage network begins by receiving a request to transfer a copy of a set of encoded data slices from at least some associated virtual storage vaults to a destination virtual storage vault and continues by determining whether the destination storage unit supports a source virtual storage vault of the at least some source virtual storage vaults. When the destination storage unit supports the source virtual storage vault the method continues by determining a sub-set of encoded data slices of the set of encoded data slices for transfer and finally, by facilitating sending the sub-set of encoded data slices to the destination storage unit.

Synchronized vault management in a distributed storage network

A method for execution by a dispersed storage network (DSN). The method begins by obtaining a data object for synchronized storage within a plurality of storage vaults, identifying a plurality of storage vaults, encoding the data object for each storage vault, initiating storage of data slices for each storage vault and interpreting received data slice information from at least some of the storage vaults to determine a number of storage vaults that have successfully stored the corresponding plurality of sets of encoded data slices and when the vault threshold number of storage vaults have not successfully stored the corresponding plurality of sets of encoded data slices within a synchronization timeframe, initiating a rollback process to abandon storage of the data object in the plurality of storage vaults and a store data response to indicate unsuccessful synchronized storage of the data object in the plurality of storage vaults.

Handling failures when synchronizing objects during a write operation

A method includes identifying an existing logical storage vault having existing dispersed storage coding properties for vault transformation, where a first set of storage units support the existing logical storage vault, and a data object of first data objects stored within the first set of storage units is stored as a first plurality of sets of encoded data slices in accordance with the existing dispersed storage coding properties. The method includes identifying a new logical storage vault having new dispersed storage coding properties, wherein storage units support the new logical storage vault. The method includes transforming the first data objects from being in accordance with the existing dispersed storage coding properties to being in accordance with the new dispersed storage coding properties to produce transformed first data objects. The method includes storing the transformed first data objects in the new logical storage vault supported by the storage units.

Vault transformation within a storage network

A method begins with a processing module obtaining a data object from a user and identifying a plurality of virtual storage vaults (VSVs) for storage of the data object. The method continues with the processing module determining dispersal error encoding parameters associated with a first virtual storage vault and error encoding the data object in accordance with those dispersal error encoding parameters to produce a corresponding plurality of sets of encoded data slices (EDSs), issuing write slice requests for the EDSs and receiving EDS information from at least some of the plurality of VSVs. When the EDS information indicates that a threshold number of VSVs have successfully stored the plurality of sets of encoded data slices within a synchronization timeframe, the method continues with the processing module issuing a favorable response to the user, or when a threshold number of VSVs have not successfully stored the plurality of sets of encoded data slices initiating a retry process.

Synchronously storing data in a dispersed storage network

Systems and methods for replicating containers in object storage using intents are disclosed. A DS processing unit, upon reception of a write request may determine the location of replicated instances for the container. DS processing unit can then generate an intent for each fork, to indicate a specific write request received. The DS processing unit may save or persist intent objects within one of the containers, or in a dispersed data structure. A DS unit or DS processing unit may then check for intents whose operation has not been completed, and when resources to perform the operation are available, perform the operation specified in the intent. DS processing unit can remove a pending intent once the job or operation is complete. A clean-up agent could run periodically to complete unfinished jobs that are pending within DS processing unit or DS unit due to containers not being available for whatever reason.

Replicating containers in object storage using intents

A method includes registering, by a first computing device, with a distributed storage network (DSN) to indicate that a first storage site is connected via a common local area network with the first computing device and is the primary storage site for the first computing device. The method continues with the first computing device to store a write threshold number of encoded data slices (EDSs) to the first storage site, obtaining a first writing pattern for writing the write threshold number of EDSs to the first plurality of storage units, and transmitting at least a portion of a remaining number of EDSs to one or more storage units at a second storage site, where the remaining number of EDSs are EDSs not included in the write threshold number of EDSs and the second storage site and the first storage site are each one of a sharing group of storage sites.

Multiple writes using inter-site storage unit relationship

A method for execution by a dispersed storage (DS) cleanup unit includes determining a dead session of a DSN. A subset of a plurality of eventual consistency intent names is generated by identifying eventual consistency intent names that include a session identifier corresponding to the dead session in a prefix of the eventual consistency intent names, where the subset of the plurality of eventual consistency intent names corresponds to all eventual consistency intents of the dead session. A subset of storage units responsible for storing the all eventual consistency intents of the dead session is determined based on the prefix of the eventual consistency intent names in the subset. All eventual consistency intents of the dead session are retrieved from the subset of storage units, and execution of eventual consistency updates indicated in the all eventual consistency intents of the dead session is facilitated.

Eventual consistency intent cleanup in a dispersed storage network

A method for execution by a container instance manager (CIM) includes determining to create a new instance of a first data container, where the first data container is stored in a first memory location. Creation of the new instance of the first data container for storage in a second memory location is facilitated in response to the determining to create the new instance. The method further includes determining to remove a duplicate instance of a second data container. Deletion of the duplicate instance of the second data container from memory is facilitated in response to the determining to remove the duplicate instance.

Managing data container instances in a dispersed storage network

A method for execution by a dispersed storage and task (DST) processing unit includes generating contention level data by evaluating an update contention level in response to determining to update an entry of a node of a dispersed hierarchical index. The update of the node is executed when the contention level data indicates that the update contention level is favorable. An index update request is generated for transmission to an index update unit via a network when the contention level data indicates that the update contention level is unfavorable.

Utilizing a hierarchical index in a dispersed storage network

Systems and Methods for encrypting and decrypting data in a dispersed storage network are disclosed. A data object may be encrypted using a data object specific encryption key, a container specific encryption key, a tenant account specific encryption key, or a time based encryption key. This specific, or more generally, secondary encryption key can be derived from a master or primary encryption key. Encryption key metadata pertaining to the master encryption key and the specific encryption key is also created and stored in the DSN. When reading an encrypted data object, the master encryption key can be retrieved and, along with the encryption key metadata, used to derive the specific encryption key. The specific encryption key can then be used to decrypt the encrypted data object to recover the data object.

Use of key metadata during write and read operations in a dispersed storage network memory

A computing device includes an interface configured to interface and communicate with a dispersed storage network (DSN), a memory that stores operational instructions, and processing circuitry operably coupled to the interface and to the memory. The processing circuitry is configured to execute the operational instructions to perform various operations and functions. The computing device selects storage parameters for a multi-vault synchronization process from a first storage vault to a second storage vault. The computing device synchronizes storage of the set(s) of ingestion encoded data slices (EDSs) between the vaults and maintains storage of a portion of an ingestion data stream within the second storage vault. The computing device facilitates deletion of the set(s) of ingestion EDSs corresponding to the portion of an ingestion data stream from the first storage vault. the computing device performs additional multi-vault synchronization process(es) for any other portion(s) of the ingestion data stream.

Unidirectional vault synchronization to support tiering

A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN). The method begins by determining to recover a data object from one or more storage vaults of a plurality of storage vaults where the data object has been synchronously stored amongst the plurality of storage vaults. The method continues, for each storage vault, by determining a slice retrieval performance level and selecting two or more storage vaults of the plurality of storage vaults for retrieval based on the slice retrieval performance levels. The method continues by identifying a plurality of data segments for retrieval where the data object was divided into the plurality of data objects and assigning a storage vault for retrieval to produce assignment information and facilitating recovery of each data segment of the plurality of data segments from the selected two or more storage vaults.

Pessimistic reads and other smart-read enhancements with synchronized vaults

A method begins with a computing device of a distributed storage network (DSN) being designated to process a write request from a Decentralized, or Distributed, Agreement Protocol (DAP) and continues with the computing device retrieving a current policy for the storage units (SUs) associated with the write request, where the current policy specifies the current connectivity for the SUs. The method continues by using the current policy to configure a data structure to process the write request, where the data structure is based on scaling triggers and a load balancing scheme. The method continues with the data structure incorporating a primary queue and scaling the addition of secondary queues based on the scaling triggers and/or the load balancing scheme.

Scaling distributed queues in a distributed storage network

A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN). The method begins by receiving a portion of a data stream from a requesting entity for storage in a plurality of storage vaults. The method continues by encoding the portion of the data stream in accordance with dispersal parameters of the storage vault to produce a corresponding plurality of sets of encoded data slices. The method continues by facilitating storage of the corresponding plurality of sets of encoded data slices in the storage vault. The method continues by determining an ingestion rate capability level for the plurality of storage vaults and issuing stream pacing information to the requesting entity based on the ingestion rate capability level.

Keeping synchronized writes from getting out of synch

A method includes maintaining, by a storage unit, a plurality of source name based addressing maps regarding encoding data slice storage by a plurality of storage units. The method further includes receiving, by the storage unit, an access request for an encoded data slice having a source name corresponding to a DSN address. The method further includes accessing, by the storage unit, the source name based address maps to determine whether the encoded data slice is effected by the DAP redistribution operation. The method further includes, when the encoded data slice is effected by the DAP redistribution operation, determining, by the storage unit, to execute the access request, proxy the access request, or deny the access request. The method further includes, when the determination is to execute the access request, executing, by the storage unit, the access request for the encoded data slice.

Growing community of inventors

Chicago, IL, United States of America

Daniel J Scholl