Abstract: An apparatus includes a plurality of memory die and a controller coupled to the plurality of memory die. The controller is configured to selectively process a plurality of random read commands in such a way to reduce a total time required to execute the random read commands.

Abstract: Aspects of a storage device are provided which allow a read command to be identified for execution from multiple read commands received from a host. The storage device includes a memory configured to store a plurality of data units each comprising one or more data fragments, and metadata associated with the data units. A controller is configured to receive from the host a plurality of read commands each requesting one of the data units. The controller is further configured to identify one of the read commands based on the metadata, and to transfer the data unit associated with the identified read command to the host before transferring the data unit associated with the other read commands.

Abstract: Systems and methods are disclosed for predictive caching of media data for seek operations or scroll operations. In certain embodiments, a data storage device includes a non-volatile memory, a buffer, and a controller configured to receive from a host a seek command associated with playback of a media file, the seek command including a seek interval. The controller can be further configured to determine a number of seek points; estimate respective logical block address (LBA) ranges corresponding to one or more seek points based on the seek interval; determine respective control pages corresponding to the estimated LBA ranges; load the control pages to the buffer in parallel; load data corresponding to the estimated LBA ranges to the buffer in parallel based on the loaded control pages; and provide the loaded data to the host.

Abstract: Systems, storage devices, and methods for application-based storage device configuration settings are described. A storage device may receive a storage command and dynamically select an application set of configuration settings for processing the storage command, where the configuration settings include trim parameters for writing data units to the storage medium of the storage device.

Abstract: Systems and methods for distributed storage and processing systems using estimate-based schedulers are described. A node receives estimated processing data for each storage device including redundant copies of data chunks for a data unit. The node determines, based on the estimated processing data and data paths to each data chunk, a task time estimate for data paths to each data chunk and selects data paths for at least one copy of each data chunk to be processed using a corresponding set of compute tasks. The compute tasks are sent for processing based on the assignments of the node.

Abstract: Example storage systems, storage devices, and methods provide dynamic redundant array of independent disks (RAID) stripe allocation based on memory device health conditions. A device health condition is assigned to each data chunk of a RAID stripe before the data chunk is sent to the target storage device. The write command indicates the device health condition and the receiving storage device selects the storage location for the data chunk corresponding to the device health condition.

Abstract: Aspects of a multi-protocol storage device including a controller are provided which handle mode switches after a shutdown resulting in a large amount of unfinished work by phasing the work during and after initialization. The controller operates in a first mode such as an SD mode and a second mode such as a NVMe mode. In the event of a shutdown in the second mode resulting in unfinished work, the controller initializes in the first mode. During initialization, the controller determines whether a completion time for the unfinished work exceeds an initialization time in the first mode. When the completion time exceeds the initialization time, the controller performs a first portion of the work during initialization and postpones performance of at least a second portion of the unfinished work until after initialization. As a result, initialization timeouts in the first mode due to the unfinished work may be avoided.

Abstract: Systems and methods are disclosed for predictive caching of media data for seek operations or scroll operations. In certain embodiments, a data storage device includes a non-volatile memory, a buffer, and a controller configured to receive from a host a seek command associated with playback of a media file, the seek command including a seek interval. The controller can be further configured to determine a number of seek points; estimate respective logical block address (LBA) ranges corresponding to one or more seek points based on the seek interval; determine respective control pages corresponding to the estimated LBA ranges; load the control pages to the buffer in parallel; load data corresponding to the estimated LBA ranges to the buffer in parallel based on the loaded control pages; and provide the loaded data to the host.

Abstract: Systems and methods for distributed storage and processing systems using storage controllers for load sharing are described. A host processor may receive a function request that corresponds to a plurality of compute tasks, such as map compute tasks targeting data in local storage. The host processor may fetch the data from local storage devices through storage controllers. At least one storage controller, such as a non-volatile memory express (NVMe) interface controller, may be configured to execute overflow tasks for the function request. Another storage controller may be configured for executing other processing and management activities, such as reduce compute tasks.

Abstract: A storage system and method for using host-assisted variable zone speed grade modes to minimize overprovisioning are provided. In one embodiment, a controller of the storage system is configured to receive a request from a host for creation of a zone of memory; in response to the request, create the zone to avoid overprovisioning the zone; determine speed grades of a plurality of usage modes of the zone; inform the host of the speed grades of the plurality of usage modes of the zone; and receive, from the host, a command to write data in the zone pursuant to one of the plurality of usage modes. Other embodiments are provided.

Abstract: A content-aware storage system and method for use therewith are presented. In one embodiment, a storage system is provided comprising a memory and a controller. The controller is configured to receive an image; determine an amount of spare memory space; generate a lower-resolution version of the image, wherein a resolution level of the lower-resolution version of the image is based on the determined amount of spare memory space; and store the image and the lower-resolution version of the image in the memory. Other embodiments are provided.

Abstract: A content-aware storage system and method for use therewith are presented. In one embodiment, a storage system is provided comprising a memory and a controller. The controller is configured to receive an image; determine an amount of spare memory space; generate a lower-resolution version of the image, wherein a resolution level of the lower-resolution version of the image is based on the determined amount of spare memory space; and store the image and the lower-resolution version of the image in the memory. Other embodiments are provided.

Abstract: Aspects of a multi-protocol storage device including a memory and a controller are provided which allow for endurance and other storage requirements of a host to be maintained for different logical regions of memory without disruption due to protocol switching. The memory includes blocks that are each associated with a storage attribute such as high endurance, performance, or protection. While operating in a first mode such as NVMe, the controller receives a mapping of storage attributes to different logical regions and stores the mapping in memory. The controller also associates blocks to logical addresses based on the mapping. When the controller switches to a second mode such as SD in response to a host command, the controller reads the mapping from memory and similarly associates blocks to logical addresses based on the mapping in the second mode. Storage attributes thus remain applicable across modes when mapping and storing data.

Abstract: Aspects of a storage device including a plurality of dies and a controller are provided which allow for asymmetric die operation handling so that controller overheads associated with common resource intensive operations may be incurred in the background without delaying subsequent die operations. When the controller receives a command to perform an MLC operation such as programming a number of dies, the controller refrains from performing the MLC operation in one or more of the dies for a period of time while simultaneously performing the MLC operation in a remainder of the dies. Instead, the controller performs another operation, such as an SLC operation, another MLC operation, or a transfer operation, that involves a common resource in these dies during the period of time. Controller overheads associated with these other operations thus are incurred without creating bottlenecks when the number of dies is large, thereby improving storage device performance.

Abstract: A storage system and method for segregating outliers in a virtualization system are presented. In one embodiment, a storage system is provided comprising a memory and a controller. The controller is configured to track a write amplification caused by each of a plurality of virtual machines; determine that a write amplification of one of the plurality of virtual machines is outside of an acceptable write amplification range; and perform a corrective action to reduce write amplification of the one of the plurality of virtual machines. Other embodiments are provided.

Abstract: A storage system and method for segregating outliers in a virtualization system are presented. In one embodiment, a storage system is provided comprising a memory and a controller. The controller is configured to track a write amplification caused by each of a plurality of virtual machines; determine that a write amplification of one of the plurality of virtual machines is outside of an acceptable write amplification range; and perform a corrective action to reduce write amplification of the one of the plurality of virtual machines. Other embodiments are provided.

Abstract: A storage system and method for host-assisted memory block color coding for faster media search are provided. In one embodiment, a controller of the storage system is configured to receive an image and color properties of the image from a host and store the image in an area of memory associated with the color properties. Other embodiments are provided.

Abstract: A storage system, host, and method for optimizing storage of a sequence of images are provided. In one embodiment, a storage system is provided comprising a memory and a controller. The controller is configured to: receive, from a host, common image data that is shared by a plurality of images and delta image data that is different in each of the plurality of images; store the common image data and the delta image data in the memory; and create a map for the plurality of images, wherein each image of the plurality of images maps to a memory location of at least a part of the common image data and to a memory location of that image's delta image data. Other embodiments are provided.

Abstract: A storage system and method for multiprotocol handling are provided. In one embodiment, a computing device is provided comprising a plurality of communication channels configured to communicate with a storage system, wherein a first communication channel has a faster data transfer speed than a second communication channel. The computing device also comprises a processor configured to determine a priority level of a command; send the command with an indication of its priority level to the storage system; in response to the command being a high-priority command, use the first communication channel for transferring data for the command; and in response to the command being a low-priority command, use the second communication channel for transferring data for the command. Other embodiments are provided.

Abstract: On-chip XOR parity data management combines storage blocks in non-volatile memory. Multiple source storage blocks are selected to be combined and stored into a destination storage block. Each source storage block includes a data section and a parity section. The parity section includes XOR parity data that enables data recovery of physical pages of the source storage block. The source storage blocks are merged into the destination storage block, which is configured to store multiple bits per memory cell. Parity sections of one or more of the plurality of source storage blocks remain unchanged after merging into the destination storage block.