Abstract: A method includes receiving a workload in a multi-tier enterprise storage system. The workload including a database. A processor determines if historical query logs present for the workload. Upon a determination that historical query logs are present for the workload: the processor analyzes a query log of historical queries for the database; an inter- and intra-query weighted column relationship graph is created based on the analyzing; and weights are assigned to the weighted column relationship graph based on an optimization process that maximizes performance for the historical queries in a training window.

Abstract: A method includes receiving a workload in a multi-tier enterprise storage system. The workload including a database. A processor determines if historical query logs present for the workload. Upon a determination that historical query logs are present for the workload: the processor analyzes a query log of historical queries for the database; an inter- and intra-query weighted column relationship graph is created based on the analyzing; and weights are assigned to the weighted column relationship graph based on an optimization process that maximizes performance for the historical queries in a training window.

Abstract: A method includes separating a file into multiple blocks. Each block of the multiple blocks are separated into at least two correlated sub-blocks. Intra-file block organized storage placement on different types of memory devices is determined for the at least two correlated sub-blocks in a file system metadata layout. The intra-file block organized storage placement is based on a predictive column data block placement model that considers multiple attributes of column data blocks.

Abstract: A technique relates to flash-optimized data layout of a dataset for queries. Selection columns are stored in flash memory according to a selection optimized layout, where the selection optimized layout is configured to optimize predicate matching and data skipping. The selection optimized layout, for each selection column, is formed by storing a selection column dictionary filled with unique data values in a given selection column, where the unique data values are stored in sorted order in the selection column dictionary. Row position designations are stored corresponding to each row position that the unique data values are present within the given selection column, without duplicating storage of any of the unique data values that occur more than once in the given selection column.

Abstract: A technique relates to flash-optimized data layout of a dataset for queries. Selection columns are stored in flash memory according to a selection optimized layout, where the selection optimized layout is configured to optimize predicate matching and data skipping. The selection optimized layout, for each selection column, is formed by storing a selection column dictionary filled with unique data values in a given selection column, where the unique data values are stored in sorted order in the selection column dictionary. Row position designations are stored corresponding to each row position that the unique data values are present within the given selection column, without duplicating storage of any of the unique data values that occur more than once in the given selection column.

Abstract: A technique relates to flash-optimized data layout of a dataset for queries. Selection columns are stored in flash memory according to a selection optimized layout, where the selection optimized layout is configured to optimize predicate matching and data skipping. The selection optimized layout, for each selection column, is formed by storing a selection column dictionary filled with unique data values in a given selection column, where the unique data values are stored in sorted order in the selection column dictionary. Row position designations are stored corresponding to each row position that the unique data values are present within the given selection column, without duplicating storage of any of the unique data values that occur more than once in the given selection column.

Abstract: A method and computer program product for managing energy management costs of a data center is disclosed. The method and computer program product include computing an energy cost estimate based on available energy rates which include wholesale electricity prices for periods of time of an hour. Embodiments of the method and computer program product include establishing fees for processing jobs. The fees are based on at least one wholesale electricity price. Embodiments of the method and computer program product include processing jobs based on scheduling-factors. Example scheduling-factors include factors related to timing, duration, environment, cost, or priority.

Abstract: A method includes separating a file into multiple blocks. Each block of the multiple blocks are separated into at least two correlated sub-blocks. Intra-file block organized storage placement on different types of memory devices is determined for the at least two correlated sub-blocks in a file system metadata layout. The intra-file block organized storage placement is based on a predictive column data block placement model that considers multiple attributes of column data blocks.

Abstract: Embodiments of the invention relate to intra-block organized storage placement. One embodiment includes obtaining a file in a file system. The file is separated into multiple blocks. The multiple blocks are separated into at least two correlated sub-blocks. Intra-file block organized storage placement on different memory devices is determined for the at least two correlated sub-blocks in a file system metadata layout.

Abstract: A technique relates to flash-optimized data layout of a dataset for queries. Selection columns are stored in flash memory according to a selection optimized layout, where the selection optimized layout is configured to optimize predicate matching and data skipping. The selection optimized layout, for each selection column, is formed by storing a selection column dictionary filled with unique data values in a given selection column, where the unique data values are stored in sorted order in the selection column dictionary. Row position designations are stored corresponding to each row position that the unique data values are present within the given selection column, without duplicating storage of any of the unique data values that occur more than once in the given selection column.

Abstract: A technique relates to flash-optimized data layout of a dataset for queries. Selection columns are stored in flash memory according to a selection optimized layout, where the selection optimized layout is configured to optimize predicate matching and data skipping. The selection optimized layout, for each selection column, is formed by storing a selection column dictionary filled with unique data values in a given selection column, where the unique data values are stored in sorted order in the selection column dictionary. Row position designations are stored corresponding to each row position that the unique data values are present within the given selection column, without duplicating storage of any of the unique data values that occur more than once in the given selection column.

Abstract: Methods and arrangements for predictively placing columns of a large database in a multi-tier storage system. Aspects include receiving a database to be stored in the multi-tier storage system, wherein the database comprises a plurality of columns and the multi-tier storage system comprises at least two storage devices and evaluating one or more attributes of each of the plurality of columns of the database. Aspects also include storing each of the plurality of columns of the database on one of the at least two storage devices, wherein a determination of which of the at least two storage devices to store each of the plurality of columns is based on the one or more attributes of each of the columns, a predictive model based on the weighted columnar relationship graph, and the characteristics of the storage devices.

Abstract: Embodiments of the invention relate to intra-block organized storage placement. One embodiment includes obtaining a file in a file system. The file is separated into multiple blocks. The multiple blocks are separated into at least two correlated sub-blocks. Intra-file block organized storage placement on different memory devices is determined for the at least two correlated sub-blocks in a file system metadata layout.

Abstract: A technique relates to flash-optimized data layout of a dataset for queries. Selection columns are stored in flash memory according to a selection optimized layout, where the selection optimized layout is configured to optimize predicate matching and data skipping. The selection optimized layout, for each selection column, is formed by storing a selection column dictionary filled with unique data values in a given selection column, where the unique data values are stored in sorted order in the selection column dictionary. Row position designations are stored corresponding to each row position that the unique data values are present within the given selection column, without duplicating storage of any of the unique data values that occur more than once in the given selection column.

Abstract: Methods and arrangements for predictively placing columns of a large database in a multi-tier storage system. Aspects include receiving a database to be stored in the multi-tier storage system, wherein the database comprises a plurality of columns and the multi-tier storage system comprises at least two storage devices and evaluating one or more attributes of each of the plurality of columns of the database. Aspects also include storing each of the plurality of columns of the database on one of the at least two storage devices, wherein a determination of which of the at least two storage devices to store each of the plurality of columns is based on the one or more attributes of each of the columns, a predictive model based on the weighted columnar relationship graph, and the characteristics of the storage devices.

Abstract: A method and computer program product for managing energy management costs of a data center is disclosed. The method and computer program product include computing an energy cost estimate based on available energy rates which include wholesale electricity prices for periods of time of an hour. Embodiments of the method and computer program product include establishing fees for processing jobs. The fees are based on at least one wholesale electricity price. Embodiments of the method and computer program product include processing jobs based on scheduling-factors. Example scheduling-factors include factors related to timing, duration, environment, cost, or priority.

Abstract: Techniques for performing operations on migrated files without triggering a recall of the migrated data. For example, embodiments of the present invention can perform a copy, move, or delete operation on a migrated file without recalling the migrated data associated with the file.