International Business Machines Corporation

Pure Storage, Inc.

Joseph M Kaczmarek

Ilya Volvovski

Andrew D Baptist

Jason K Resch

Manish Motwani

Ravi V Khadiwala

Greg R Dhuse

Bruno Hennig Cabral

Yogesh Ramesh Vedpathak

Ethan S Wozniak

Thomas Darrel Cocagne

Asimuddin Kazi

Praveen Viraraghavan

Michael Colin Storm

Trevor J Vossberg

Renars W Narubin

Anthony J Baldocchi

A computing device includes an interface configured to interface and communicate with a storage network, a memory that stores operational instructions, and a processing module operably coupled to the interface and memory such that the processing module, when operable within the computing device based on the operational instructions, is configured to perform various operations. A computing device receives a data access request for an encoded data slice associated with a data object, determines whether the encoded data slice is stored in the first memory and in response to a determination that the encoded data slice is not stored in the first memory, issues another data access request for the encoded data slice to a second memory, where the first memory includes access characteristics that are faster than the second memory. When a data access response including the encoded data slice is received from the second memory, a response including the encoded data slice is transmitted.

Utilizing memories of different operational speeds in a vast storage network

A method for updating software of storage units of a set of storage units in a storage network. In an embodiment, each storage unit of the set of storage units determines a data slice storage status for data slices stored in the storage unit (e.g., by monitoring rebuilding messages relating to the data slices). A processing module of the storage network obtains the data slice storage status of the storage units of the set of storage units and determines whether to perform a software update to software of the storage units of the set of storage units. Determining whether to perform the software update includes determining, based on the data slice storage status of the storage units, whether a threshold number of storage units are associated with a favorable data slice storage status. In response to determining that a threshold number of storage units are associated with a favorable data slice storage status, the processing module indicates to perform the software update.

Updating the configuration of storage units of a storage network

A computing device includes an interface configured to interface and communicate with a dispersed storage network (DSN), a memory that stores operational instructions, and a processing module operably coupled to the interface and memory such that the processing module, when operable within the computing device based on the operational instructions, is configured to perform various operations. A computing device receives a data access request for an encoded data slice (EDS) associated with a data object. The computing device compares a slice name of the data access request with slice names stored within RAM. When the data access request slice name compares unfavorably with those stored slice names, the computing device transmits an empty data access response that includes no EDS to the other computing device without needing to access a hard disk drive (HDD) that stores EDSs. Alternatively, the computing device transmits a data access response that includes the EDS.

Storage unit including memories of different operational speeds for optimizing data storage functions

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 detects at least one available memory device within a storage unit (SU). The computing device identifies storage capacities of each of the memory devices within the SU and identifies a DSN address range associated with the SU. The computing device maps the DSN address range to each of the memory devices within the SU based on the storage capacities to generate a memory mapping of the memory devices within the SU. The computing device then facilitates redistribution of some EDS from a first memory device to the at least one available memory device within the SU.

Predictive rebalancing according to future usage expectations

Utilizing fast memory devices to optimize different functions

Systems and Methods for data storage in a distributed storage network are disclosed. Unexpected errors can adversely affect consistency of both the content of a write (including the slice data), and the synchronicity between the written slices and metadata structures. To maintain consistency between these data structures, a sequencing of the order of writes and flushes to the memory devices for the different data structures may be enforced as follows: First: Slice content data is first written to the volatile memory (e.g. a cache memory) of a DS unit; Second: the Slice content data stored in volatile memory is 'flushed' to a non-volatile bin (which bin is associated with a group of physical memory blocks in non-volatile memory); Third: after the flush of the slice content data to the bin (i.e. data is durable on the media device): metadata relating to the data is written.

Zone storage&#x2014;quickly returning to a state of consistency following an unexpected event

A method for execution by a storage unit of a dispersed storage network includes receiving a slice access request that includes a slice name. A first function is performed on the slice name to produce a bucket file identifier. A second function is performed on the slice name to produce a bucket identifier. A bucket file of a plurality of bucket files is accessed, where the bucket file is identified by utilizing the bucket file identifier. A bucket of a plurality of buckets within the bucket file is accessed, where the bucket is identified by utilizing the bucket identifier. It is determined to modify a number of buckets in the bucket file based on bucket utilization. An attribute of the second function is modified in response, where the attribute is associated with the number of buckets in the bucket file.

Modifying and utilizing a file structure in a dispersed storage network

A distributed storage network (DSN) employs one or more distributed storage task execution (DST EX) units for dispersed storage of encoded data slices. A delete-slice request associated with a first encoded data slice is received at a DST EX unit, the encoded data slice is packed into a common file with other encoded data slices, and the common file is stored in a distributed storage (DS) memory included in the DST EX unit. Each encoded data slice packed into the common file is associated with a file offset within the common file. The DST EX unit identifies a file offset of the first encoded data slice within the common file. The DST EX unit releases the portion of the DS memory associated with the particular file offset within the common file to a file system maintained by the DST EX unit.

Efficient resource reclamation after deletion of slice from common file

A method for execution by a dispersed storage and task (DST) execution unit that includes a processor includes receiving an access request that includes an authorization token from a computing device via a network. Authorization data is generated based on the access request. The access request is executed and a result of the access request is transmitted to the computing device via the network when the authorization data includes a verification indicator. An invalid token notification is generated for transmission to the computing device when the authorization data includes an invalid token indicator.

Verifying authorized access in a dispersed storage network

A method begins by a processing module of a dispersed storage and task (DST) execution unit receiving a data request for execution by the DST execution unit, the data request including a slice name associated with an encoded data slice of the data request. The method continues with the processing module generating a scoring resultant corresponding to each of a plurality of memories of the DST execution unit, in accordance with a ranking function and the slice name. The method continues with the processing module selecting one of the plurality of memories of the DST execution unit in accordance with a mapping function and executing the data request utilizing the one of the plurality of memories of the DST execution unit.

Selecting memory for data access in a dispersed storage network

A method includes receiving, by a storage unit of a dispersed storage network (DSN) an access request for an encoded data a slice of a set of encoded data slices from a computing device of the DSN. The method further includes queueing, by the storage unit, the access request for the encoded data slice. The method further includes, prior to executing the access request, determining, by the storage unit, whether a session associated with the access request is still active and whether execution the access request for encoded data slice is still needed. When the session is still active and the execution of the access request for the encoded data slice is still needed, the method further includes executing, by the storage unit, the access request for the encoded data slice.

Session execution decision

A method begins by a first computing device of a plurality of computing devices accessing a rebuild hierarchical index structure to identify a data object having encoded data slices requiring rebuilding, where the structure includes a plurality of nodes that organizes a plurality of data objects based on a level of need of rebuilding. The method continues with the first computing device utilizing a rebuilding function to rebuild one or more of the identified encoded data slices to be rebuilt to produce one or more rebuilt encoded data slices and sending a write request to memory of a dispersed storage network to store the one or more rebuilt encoded data slices. The method continues with the first or another computing device updating the level of need of rebuilding of the identified data object and updating the rebuild hierarchical index structure based on the updated level of need of rebuilding.

Prioritizing rebuilding of encoded data slices

A method for execution by a dispersed storage and task (DST) processing unit includes generating a plurality of access requests that include an execution deadline time for transmission via a network to a corresponding subset of a plurality of storage units. A first deadline error notification is received via the network from a first storage unit of the first subset. A new one of the plurality of storage units not included in the first subset is selected in response to receiving the first deadline error notification. A new access request that includes an updated execution deadline time is generated for transmission to the new one of the plurality of storage units via the network. The new access request is based on a one of the first plurality of access requests sent to the first storage unit of the first subset.

Growing community of inventors

Chicago, IL, United States of America

Joseph M Kaczmarek