Abstract: Systems and methods disclosed herein allow for efficiently managing unmapped blocks to extend life of solid-state drives. In one aspect, a method includes: measuring a level of over-provisioning (“OP”) in a storage device and operating it in a first mode of operation while the OP satisfies a first threshold. The method also includes: changing to a second mode of operation if the OP does not satisfy the first threshold. While operating in the second mode of operation, the method includes: (i) determining an unmapped portion of a declared storage capacity of the storage device; and (ii) determining whether processing a write command would reduce the unmapped portion to less than a second threshold. If processing the write command wouldn't reduce the unmapped portion to less than the second threshold, the method includes: accepting and processing the write command. Else, the method includes: forgoing acceptance and processing of the write command.

Abstract: Systems and methods disclosed herein allow for efficiently managing unmapped blocks to extend life of solid-state drives. In one aspect, a method includes: determining a quantity of unmapped storage units in the storage device and operating the storage device in a first mode of operation while the quantity satisfies a first threshold. The method also includes: changing to a second mode of operation if the quantity of unmapped storage units doesn't satisfy the first threshold. While operating in the second mode of operation, the method includes: determining whether processing a write command would reduce the quantity of unmapped storage units to a quantity less than a second threshold. If processing the write command wouldn't reduce the quantity of unmapped storage units to a quantity less than the second threshold, the method includes: accepting and processing the write command. Else, the method includes: forgoing acceptance and processing of the write command.

Abstract: Systems, methods, and/or devices are used to manage a storage system. In one aspect, the method includes, during a first time period: maintaining a credit pool for the first time period; limiting bandwidth used for transmitting data between a storage device of the storage system and a host operatively coupled with the storage device according to a status of the credit pool, where the storage device includes one or more memory devices; monitoring a temperature of the storage device; and, in accordance with a determination that a current temperature of the storage device exceeds a predetermined threshold temperature and the current temperature of the storage device satisfies one or more temperature criteria, reducing an initial value of the credit pool for a second time period according to a first adjustment factor corresponding to the predetermined temperature threshold, where the second time period is subsequent to the first time period.

Abstract: Systems, methods, and/or devices are used to manage a storage system. In one aspect, the method includes receiving, from a host to which a storage device of the storage system is operatively coupled, a request to perform a first memory operation on one or more memory devices of the storage device. The method includes determining a count of credits corresponding to the first memory operation. If a current count of credits in the first credit pool is greater than or equal to the count of credits corresponding to the first memory operation and a current count of credits in the second credit pool is greater than or equal to the count of credits corresponding to the first memory operation, the method includes: performing the first memory operation; and decrementing the first and second credit pools according to the count of credits corresponding to the first memory operation.

Abstract: Systems and methods disclosed herein allow for efficiently managing unmapped blocks to extend life of solid-state drives. In one aspect, a method includes: determining a quantity of unmapped storage units in the storage device and operating the storage device in a first mode of operation while the quantity satisfies a first threshold. The method also includes: changing to a second mode of operation if the quantity of unmapped storage units doesn't satisfy the first threshold. While operating in the second mode of operation, the method includes: determining whether processing a write command would reduce the quantity of unmapped storage units to a quantity less than a second threshold. If processing the write command wouldn't reduce the quantity of unmapped storage units to a quantity less than the second threshold, the method includes: accepting and processing the write command. Else, the method includes: forgoing acceptance and processing of the write command.

Abstract: Systems and methods disclosed herein allow for efficiently managing unmapped blocks to extend life of solid-state drives. In one aspect, a method includes: measuring a level of over-provisioning (“OP”) in a storage device and operating it in a first mode of operation while the OP satisfies a first threshold. The method also includes: changing to a second mode of operation if the OP does not satisfy the first threshold. While operating in the second mode of operation, the method includes: (i) determining an unmapped portion of a declared storage capacity of the storage device; and (ii) determining whether processing a write command would reduce the unmapped portion to less than a second threshold. If processing the write command wouldn't reduce the unmapped portion to less than the second threshold, the method includes: accepting and processing the write command. Else, the method includes: forgoing acceptance and processing of the write command.

Abstract: A storage device and method enable processing of un-map commands. In one aspect, the method includes (1) determining whether a size of an un-map command satisfies (e.g., is greater than or equal to) a size threshold, (2) if the size of the un-map command satisfies the size threshold, performing one or more operations of a first un-map process, wherein the first un-map process forgoes (does not include) saving a mapping table to non-volatile memory of a storage device, and (3) if the size of the un-map command does not satisfy the size threshold, performing one or more operations of a second un-map process, wherein the second un-map process forgoes (does not include) saving the mapping table to non-volatile memory of the storage device and forgoes (does not include) flushing a write cache to non-volatile memory of the storage device.

Abstract: Systems, methods, and/or devices are used to manage a storage system. In one aspect, the method includes, during a first time period: maintaining a credit pool for the first time period; limiting bandwidth used for transmitting data between a storage device of the storage system and a host operatively coupled with the storage device according to a status of the credit pool, where the storage device includes one or more memory devices; monitoring a temperature of the storage device; and, in accordance with a determination that a current temperature of the storage device exceeds a predetermined threshold temperature and the current temperature of the storage device satisfies one or more temperature criteria, reducing an initial value of the credit pool for a second time period according to a first adjustment factor corresponding to the predetermined temperature threshold, where the second time period is subsequent to the first time period.

Abstract: Systems, methods, and/or devices are used to manage a storage system. In one aspect, the method includes receiving, from a host to which a storage device of the storage system is operatively coupled, a request to perform a first memory operation on one or more memory devices of the storage device. The method includes determining a count of credits corresponding to the first memory operation. If a current count of credits in the first credit pool is greater than or equal to the count of credits corresponding to the first memory operation and a current count of credits in the second credit pool is greater than or equal to the count of credits corresponding to the first memory operation, the method includes: performing the first memory operation; and decrementing the first and second credit pools according to the count of credits corresponding to the first memory operation.

Abstract: A storage device and method enable processing of un-map commands. In one aspect, the method includes (1) determining whether a size of an un-map command satisfies (e.g., is greater than or equal to) a size threshold, (2) if the size of the un-map command satisfies the size threshold, performing one or more operations of a first un-map process, wherein the first un-map process forgoes (does not include) saving a mapping table to non-volatile memory of a storage device, and (3) if the size of the un-map command does not satisfy the size threshold, performing one or more operations of a second un-map process, wherein the second un-map process forgoes (does not include) saving the mapping table to non-volatile memory of the storage device and forgoes (does not include) flushing a write cache to non-volatile memory of the storage device.

Abstract: Methods and structure for task management in storage controllers of a clustered storage system. An initiator storage controller of the clustered storage system ships I/O requests for processing to a target storage controller of the system. Responsive to a need to abort a previously shipped I/O request, the initiator storage controller transmits a task management message to the target storage controller. The task management message identifies one or more previously shipped I/O requests to be aborted. The target storage controller processes the received task management message in due course of processing requests and completes processing for the aborted previously shipped request in an orderly manner. Resources associated with the aborted previously shipped requests are release within both controllers.

Abstract: Methods and structure for task management in storage controllers of a clustered storage system. An initiator storage controller of the clustered storage system ships I/O requests for processing to a target storage controller of the system. Responsive to a need to abort a previously shipped I/O request, the initiator storage controller transmits a task management message to the target storage controller. The task management message identifies one or more previously shipped I/O requests to be aborted. The target storage controller processes the received task management message in due course of processing requests and completes processing for the aborted previously shipped request in an orderly manner. Resources associated with the aborted previously shipped requests are release within both controllers.

Abstract: System and methods are disclosed for gathering debug information of a storage system of a computer system without requiring additional external hardware directly connected to the controller of the storage system.

Abstract: A plurality of modes is provided for communicating between a host system and a peripheral storage system controller. A first communication mode may be selected from the plurality of communication modes based on a bit length required to communicate a physical address. During runtime, a switch from the first communication mode to a second communication mode may be performed in order to improve the efficiency of processing address requests at the storage system controller.

Abstract: Methods and systems for improved lock processing in a storage controller. Storage controllers that provide storage management features such as RAID storage controllers may concurrently process I/O requests received from attached host systems and I/O requests generated internally by the management processing in the controller. Such concurrent processing is coordinated by lock processing that allows affected storage areas to be locked during processing of an I/O operation. Features and aspects hereof allow such lock processing to lock regions flexibly defined by the controller. The flexible definition of the regions to be locked allows variance in the granularity of the locks required. Smaller granularity permits more concurrent I/O requests to be processed.