Abstract: A computer-implemented to control access to data on an off-premises storage system. The method includes defining an access policy for a plurality of files in a file system stored in an on-premises storage system. The method further includes registering the access policy with a first off-premises storage system. The method also includes creating a resource-based cloud access policy based on an on-premise access policy. The method includes determining a set of files from the plurality of files to migrate to the off-premises storage. The method also includes obtaining, for the set of files, an access policy as access metadata. The method further includes migrating the set of files and the access metadata to the off-premises storage.

Abstract: A computer-implemented method, according to one embodiment, is for restoring operation of a data storage system at a disaster recovery site. The computer-implemented method includes: in response to a disaster event occurring at a primary site, receiving an inode list from a cloud storage site, and receiving configuration information from the cloud storage site. The cloud storage site includes a backup copy of data that is stored at the primary site. Moreover, the inode list and the configuration information are used to construct a filesystem at the disaster recovery site. The filesystem at the disaster recovery site does not include a copy of the data that is stored at the primary site, but rather the filesystem includes a plurality of metadata stubs. The filesystem is further used to satisfy I/O commands that are received.

Abstract: A method, computer system, and a computer program product for block prediction are provided. A computer receives a first retrieval request for retrieving data from storage blocks. The computer performs a cosine similarity comparison of the first retrieval request compared to prior data retrievals. The computer selects a matching data retrieval of the prior data retrievals. The matching data retrieval has a closest match to the first retrieval request based on the cosine similarity comparison. The computer identifies another storage block from the matching data retrieval as a predicted block for the first retrieval request. The computer transmits a prefetch request to prefetch data from the predicted block.

Abstract: A computer-implemented to control access to data on an off-premises storage system. The method includes defining an access policy for a plurality of files in a file system stored in an on-premises storage system. The method further includes registering the access policy with a first off-premises storage system. The method also includes creating a resource-based cloud access policy based on an on-premise access policy. The method includes determining a set of files from the plurality of files to migrate to the off-premises storage. The method also includes obtaining, for the set of files, an access policy as access metadata. The method further includes migrating the set of files and the access metadata to the off-premises storage.

Abstract: A computer-implemented method, according to one embodiment, includes: identifying block addresses which are associated with a given object, and combining the block addresses to a first set in response to determining that at least one token is currently issued on one or more of the identified block addresses. A first portion of the block addresses is transitioned to a second set, where the first portion includes ones of the block addresses determined as having a token currently issued thereon. Moreover, a second portion of the block addresses is divided into equal chunks, where the second portion includes the block addresses remaining in the first set. The chunks in the first set are allocated across two or more parallelization units. Furthermore, the block addresses in the second set are divided into equal chunks, and the chunks in the second set are allocated to at least one dedicated parallelization unit.

Abstract: A computer-implemented method, according to one embodiment, is for restoring operation of a data storage system at a disaster recovery site. The computer-implemented method includes: in response to a disaster event occurring at a primary site, receiving an inode list from a cloud storage site, and receiving configuration information from the cloud storage site. The cloud storage site includes a backup copy of data that is stored at the primary site. Moreover, the inode list and the configuration information are used to construct a filesystem at the disaster recovery site. The filesystem at the disaster recovery site does not include a copy of the data that is stored at the primary site, but rather the filesystem includes a plurality of metadata stubs. The filesystem is further used to satisfy I/O commands that are received.

Abstract: A computer-implemented method, according to one embodiment, includes: identifying block addresses which are associated with a given object, and combining the block addresses to a first set in response to determining that at least one token is currently issued on one or more of the identified block addresses. A first portion of the block addresses is transitioned to a second set, where the first portion includes ones of the block addresses determined as having a token currently issued thereon. Moreover, a second portion of the block addresses is divided into equal chunks, where the second portion includes the block addresses remaining in the first set. The chunks in the first set are allocated across two or more parallelization units. Furthermore, the block addresses in the second set are divided into equal chunks, and the chunks in the second set are allocated to at least one dedicated parallelization unit.

Abstract: A computer-implemented method, according to one embodiment, includes: receiving an operation request which corresponds to a given object, identifying multiple block addresses which are associated with the given object, determining whether any one or more of the identified block addresses have a token currently issued thereon, and combining the multiple block addresses to a first set in response to determining that at least one token is currently issued on one or more of the identified block addresses. A first portion of the block addresses determined as having a token currently issued thereon is transitioned to a second set. A remaining portion of the block addresses is also divided into equal chunks. The chunks are allocated in the first set across parallelization units, and the block addresses in the second set are divided into equal chunk. Furthermore, the chunks in the second set are allocated to a dedicated parallelization unit.

Abstract: A computer-implemented method, according to one embodiment, includes: receiving an operation request which corresponds to a given object, identifying multiple block addresses which are associated with the given object, determining whether any one or more of the identified block addresses have a token currently issued thereon, and combining the multiple block addresses to a first set in response to determining that at least one token is currently issued on one or more of the identified block addresses. A first portion of the block addresses determined as having a token currently issued thereon is transitioned to a second set. A remaining portion of the block addresses is also divided into equal chunks. The chunks are allocated in the first set across parallelization units, and the block addresses in the second set are divided into equal chunk. Furthermore, the chunks in the second set are allocated to a dedicated parallelization unit.