Abstract: In a method used for maximizing performance of a storage system, saturation points of the storage system for I/O requests of different types and sizes are identified. Normalized tokens are determined based on the saturation points. Unique numbers of normalized tokens are associated with the I/O requests of different types and sizes. A number of normalized tokens for a queue depth limit of a storage device is determined. From the queue depth limit, normalized tokens are allocated to each node in the storage device. I/O requests are processed according to the allocations of normalized tokens.

Abstract: A method, computer program product, and computing system for forecasting a temperature of a storage object of a storage system using a machine learning model. The storage object may be divided into a plurality of storage sub-objects. A temperature may be determined for each storage sub-object using a simple moving average. A portion of the temperature of the storage object may be projected onto the temperature of each of the plurality of storage sub-objects based upon, at least in part, the temperature determined for each storage sub-object and the temperature determined for each storage object.

Abstract: Techniques for providing multi-tier heat maps in a storage system. The techniques include obtaining a temperature of a storage object using a first heat map of data IO activity at a storage object level of the data, and determining that the temperature of the storage object exceeds a predetermined threshold. The techniques further include, in response to determining that the temperature of the storage object exceeds the predetermined threshold, obtaining at least one temperature of at least one storage element associated with the storage object using a second heat map of data IO activity at a storage element level of the data, and performing a storage operation on the storage object based on the temperature of the storage object and/or the temperature of the storage element. Such use of multi-tier heat maps allow accurate temperature predictions to be made in a manner that conserves and adapts to available system resources.

Abstract: A method, computer program product, and computing system for determining a respective past activity level associated with a plurality of storage objects. The plurality of storage objects are divided into a plurality of storage object groups based upon, at least in part, the respective past activity level associated with the plurality of storage objects. Input/output (IO) performance data for a first storage object group of the plurality of storage object groups is forecasted using a first machine learning model. IO performance data for a second storage object group of the plurality of storage object groups is forecasted using a statistical method.

Abstract: Techniques for providing multi-tier heat maps in a storage system. The techniques include obtaining a temperature of a storage object using a first heat map of data IO activity at a storage object level of the data, and determining that the temperature of the storage object exceeds a predetermined threshold. The techniques further include, in response to determining that the temperature of the storage object exceeds the predetermined threshold, obtaining at least one temperature of at least one storage element associated with the storage object using a second heat map of data IO activity at a storage element level of the data, and performing a storage operation on the storage object based on the temperature of the storage object and/or the temperature of the storage element. Such use of multi-tier heat maps allow accurate temperature predictions to be made in a manner that conserves and adapts to available system resources.

Abstract: Techniques for providing effective utilization of different drive capacities in storage appliances. The techniques include providing a storage drive array that has a first set of storage drives and a second set of storage drives. Each storage drive in the first set has a first drive capacity and each storage drive in the second set has a second drive capacity. The first drive capacity is higher than the second drive capacity. The techniques include allocating, within the first drive capacity, at least a first sub-capacity and a second sub-capacity. The first sub-capacity is equal to the second drive capacity. The techniques include placing blocks of hot data in the first sub-capacities of the storage drives in the first set and/or the second drive capacities of the storage drives in the second set, and placing blocks of cold data in the second sub-capacities of the storage drives in the first set.

Abstract: Techniques for managing storage may comprise: receiving a request for a first amount of free capacity, wherein the request includes a first priority denoting a purpose for which the first amount of free capacity is requested; determining whether a current utilization of storage exceeds a first threshold associated with the first priority; responsive to determining the current utilization of storage is less than the first threshold associated with the first priority, performing first processing including: determining whether there is a sufficient amount of existing free capacity to grant the first amount; and responsive to determining there is a sufficient amount of existing free capacity to grant the first amount, granting the first amount of free capacity; and responsive to determining the current utilization of storage is not less than the first threshold associated with the first priority, rejecting the request and not granting the first amount of free capacity.

Abstract: A data storage system can use non-volatile solid state drives (SSDs) to provide backend storage. The data storage system and SSDs can implement log structured systems (LSSs) experiencing write amplification (WA). The aggregated WA of the LSSs can be minimized when the WAs of both LSSs of the system and SSDs are equal, within a specified tolerance. An amount of storage capacity which the LSS of the data storage system is allowed to use can be limited and vary based on the system's data capacity denoting the storage capacity with valid data. Pm can denote a percentage of Cs, the advertised capacity of the SSDs, storing valid data. Po can be a percentage of Cs denoting the upper bound of the system's used capacity. Po and Pm, as well as the utilization and WA of both the data storage system and SSDs, can be evaluated and adjusted adaptively and holistically.

Abstract: A data storage system can use non-volatile solid state drives (SSDs) to provide backend storage. The data storage system and SSDs can implement log structured systems (LSSs) experiencing write amplification (WA). The aggregated WA of the LSSs can be minimized when the WAs of both LSSs of the system and SSDs are equal, within a specified tolerance. An amount of storage capacity which the LSS of the data storage system is allowed to use can be limited and vary based on the system’s data capacity denoting the storage capacity with valid data. Pm can denote a percentage of Cs, the advertised capacity of the SSDs, storing valid data. Po can be a percentage of Cs denoting the upper bound of the system’s used capacity. Po and Pm, as well as the utilization and WA of both the data storage system and SSDs, can be evaluated and adjusted adaptively and holistically.

Abstract: Techniques described herein manage failed storage devices. A number of failed storage devices is determined to exceed a number of redundancies in a storage configuration of the storage system. The status of a failed storage device is changed to permit solely read operations. Valid data from the failed storage device is copied to a spare storage device. Invalid data on the failed storage device is reconstructed based on corresponding data from other storage devices, and the reconstructed data is stored on the spare storage device. The failed storage device is removed from the storage system.

Abstract: A method, computer program product, and computer system for submitting, by a computing device, a write for a write-request equal to a size of valid data in a segment. The write-request may be decomposed into RAID elements and corresponding parity stripe elements. Parity for RAID stripes may be calculated using only valid RAID elements of the RAID elements. A write for all the valid RAID elements and the corresponding parity stripe elements may be issued. An unmap command may be issued to at least a portion of the segment that is invalid.

Abstract: A technique provides preferential treatment to metadata over user data when protecting data in a mapped-RAID system. The technique involves generating metadata based on user data, storing the metadata in mirrored storage of the mapped-RAID system (e.g., 2-way mirrored storage), and storing the user data in non-mirrored storage of the mapped-RAID system (e.g., writing user data with parity in accordance with RAID 6). The mapped-RAID system provides reliability preference toward maintaining the metadata over maintaining the user data while the metadata and the user data are stored within the mapped-RAID system. Accordingly, the technique is able to concurrently provide high reliability and high storage efficiency.

Abstract: A technique manages data within a storage array. The technique involves forming a hybrid tier within the storage array, the hybrid tier including SSD storage and HDD storage. The technique further involves, after the hybrid tier is formed, providing hybrid ubers (or Redundant Array of Independent Disks (RAID) extents) from the SSD storage and the HDD storage of the hybrid tier. The technique further involves, after the hybrid ubers are provided, accessing the hybrid ubers to perform data storage operations.

Abstract: Techniques are directed to managing Redundant Array of Independent Disks (RAID) storage space. One technique involves providing, by RAID circuitry, a storage space request to mapper circuitry; receiving, by the RAID circuitry, a storage space reply from the mapper circuitry in response to the storage space request; and performing, by the RAID circuitry, a follow-up operation based on the storage space reply from the mapper circuitry. Another technique involves, receiving, by mapper circuitry, a storage space request from RAID circuitry; performing, by the mapper circuitry, a storage space management operation in response to the storage space request; and providing, by the mapper circuitry, a storage space reply to the RAID circuitry, the storage space reply identifying a result of the storage space management operation.

Abstract: A technique performs Redundant Array of Independent Disks (RAID) transformation. The technique involves performing a garbage collection operation on a first uber within a storage array, the garbage collection operation freeing a set of disk slices of the first uber. The technique further involves, upon completing the garbage collection operation, reallocating storage of the set of disk slices from the first uber to a second uber within the storage array. The technique further involves, after the storage of the set of disk slices is reallocated from the first uber to the second uber, storing data within the second uber. Such leveraging of garbage collection when performing RAID transformation reduces overhead and wear without not negatively affecting system performance.

Abstract: Technology is disclosed for recovering the consistency of a RAID (Redundant Array of Independent Disks) metadata database when data corruption is detected in the RAID metadata database. The RAID metadata database includes super sectors, stage sectors, and a data region. Valid data within the data region is a contiguous set of sectors extending from a head sector to a tail sector. In response to data corruption in one of the two super sectors, a set of pointers contained in the other super sector is used to identify the head sector and tail sector. In response to data corruption in both super sectors, the head sector and tail sector are located based on the contents of the sectors in the data region. Techniques are also disclosed for recovering consistency when the data corruption occurs in the stage sectors and/or data region.

Abstract: Techniques for managing storage may comprise: receiving a request for a first amount of free capacity, wherein the request includes a first priority denoting a purpose for which the first amount of free capacity is requested; determining whether a current utilization of storage exceeds a first threshold associated with the first priority; responsive to determining the current utilization of storage is less than the first threshold associated with the first priority, performing first processing including: determining whether there is a sufficient amount of existing free capacity to grant the first amount; and responsive to determining there is a sufficient amount of existing free capacity to grant the first amount, granting the first amount of free capacity; and responsive to determining the current utilization of storage is not less than the first threshold associated with the first priority, rejecting the request and not granting the first amount of free capacity.

Abstract: In a method used for maximizing performance of a storage system, saturation points of the storage system for I/O requests of different types and sizes are identified. Normalized tokens are determined based on the saturation points. Unique numbers of normalized tokens are associated with the I/O requests of different types and sizes. A number of normalized tokens for a queue depth limit of a storage device is determined. From the queue depth limit, normalized tokens are allocated to each node in the storage device. I/O requests are processed according to the allocations of normalized tokens.

Abstract: A method, computer program product, and computer system for submitting, by a computing device, a write for a write-request equal to a size of valid data in a segment. The write-request may be decomposed into RAID elements and corresponding parity stripe elements. Parity for RAID stripes may be calculated using only valid RAID elements of the RAID elements. A write for all the valid RAID elements and the corresponding parity stripe elements may be issued. An unmap command may be issued to at least a portion of the segment that is invalid.

Abstract: In a method used for maximizing performance of a storage system, saturation points of the storage system for I/O requests of different types and sizes are identified. Normalized tokens are determined based on the saturation points. Unique numbers of normalized tokens are associated with the I/O requests of different types and sizes. A number of normalized tokens for a queue depth limit of a storage device is determined. From the queue depth limit, normalized tokens are allocated to each node in the storage device. I/O requests are processed according to the allocations of normalized tokens.