Abstract: Instead of an arbitration over the link not considering bursts, a smart scheduler in a solid state drive (SSD) host interface is burst aware. The scheduler considers the type of transactions that are going to be sent over the interface. The scheduler sends the transactions in the most efficient way while maximizing the efficiency over the host DRAM. The schedulers may be calibrated from time to time on-the-fly to find the optimal configurations adapted to the current workload. The scheduler will organize the packets selected by the arbitration module so that the data transfers are sent in a burst of a predetermined sized to the host for optimum performance. For further optimization other packet types are sent in bursts as well.

Abstract: Instead of maximizing the possible bandwidth of device, utilize time slice credits (TSC), to ensure bandwidth average over a sliding window. When the average is ensured over a sliding window, the device should not care when the host decides to sample a 100 mSec for example, as the average will always be correct. By utilizing set percentage of predetermined allotment for the average bandwidth requirement, the system can give out credit on a predetermined interval. The credit is given out based on usage and once credit is depleted, data cannot be sent until more credit is accumulated. When data is not sent, the system is given a chance to accumulate credit to increase the amount of data sent. Once credit is at a level high enough to send data the device will send the data, but not at a speed that will surpass the average bandwidth requirement.

Abstract: Instead of handing gaming/streaming operations and I/O operations using the same error correction code (ECC) scheme, use a different ECC scheme for different cases. When for gaming/streaming user data cases, ECC is not required, and the protection information (PI) provided by the host is used instead. If the host does not provide the PI for the specific command for gaming/streaming user data, the logic generates and injects ECC transparently to the rest of the logic. For I/O operations the standard ECC scheme will be used, which will include adding cyclic redundancy check (CRC) to the data. Once the CRC is added to the data, the data and the CRC will be encrypted. After a header is added to the data and the CRC all of the information is protected with flash memory unit (FMU) CRC (FMU-CRC).

Abstract: Instead of the firmware (FW) monitoring for both an overlap read command and a write protected (WP) overlapped write command, the FW can monitor the overlap table only. The controller will receive a read command or an overlap read command. If the command is not an overlap read command, then the controller will process the command normally. If the command is an overlap read command, then the controller will look for the write command that is being overlapped. When passing the write overlap of write protect (WP) into the data path instead of the exception queue, the FW is limited to monitoring the overlap table. As such, when the WP command is completed the entry is removed by the data path. As a result, the FW can limit monitoring to when the data path clears the overlap table.

Abstract: The present disclosure generally relates to memory management during SGL fetching. When a data storage device is required to fetch an SGL from a host device, the data storage device cannot determine how much memory will be required to be allocated. The disclosure herein reduces the impact of the problem of under or over allocating memory and over-fetching, thereby reducing performance of the device during transfers. The disclosure provides guidance on how to implement an adaptive learning process based upon statistic collection of SGL fetches. By maintaining a table of statistics, the data storage device controller may learn and more closely predict an amount of memory to allocate for SGL fetching.

Abstract: The present disclosure generally relates to improved address translation. Rather than fetching translated addresses using ATS/ATC, a HIM address translation search engine (HATS) is used through implementing the ATC in a layer above per an NVMe command. The HATS is an engine that will monitor pointers with untranslated addresses and will fetch the translated addresses for the pointers. Once the translated addresses are fetched for the pointer, the HATS will overwrite the untranslated address with the translated address. The HATS will then update the status of the pointers. When a translation request fails, the device will use PRI to request the translated address. During a translation request fail the device will drain any incoming requests while skipping the data transfer phase. The device will not block any other requests in a queue. Once that translated address is received through the PRI flow, the status of the pointer will be updated.

Abstract: The present disclosure generally relates to a XTS cache operation during a power down event. Upon detection of power loss, data that is waiting to be encrypted needs to be flushed to the memory device. For any unaligned data or data less than a flash management unit (FMU) size, the data is grouped together and, if necessary, padded to reach the FMU size and then encrypted, merged with other data FMUs, and written to the memory device. Grouping the unaligned data reduces the amount of padding necessary to reach FMU size and also reduces the amount of data to be encrypted. As such, data flushing can be accomplished using the limited amount of remaining power during the power loss event.

Abstract: Improved automation can be achieved using command-parts. Rather than using a command to determine which key to use, command partitioning will generate a task-ID based on a key index table to determine what key to use. Based on the task-ID, an encryption engine (XTS) will know which key to use. The command is split into partitions with the same attributes. The amount of task-IDs created will equal the amount of partitions. Automation will be based on the task-IDs to create a completion for a host. The controller will then return to the key index table to count the completed commands and send the completion to the host.

Abstract: A data storage device implements a Zoned Namespace (ZNS) storage architecture. The data storage device delays the execution of write commands that are received out of sequence instead of rejecting the write commands. The write commands that are received out of sequence are reordered according to a logical block address (LBA) associated with each write command. The data storage device also checks for deadlock conditions that may arise due to the execution of the write commands being delayed and/or due to the write commands being reordered.

Abstract: Instead of handling resources with one generic method, the controller can use a static method or dynamic method to handle the resources. The controller communicates to the host as to the number of resources the controller has for keeping doorbell times. The controller will also communicate with the host how those resources are used. The static method focuses on creating dedicated submission queues (SQ), while the dynamic method provides a hint during the doorbell execution. The static method further focuses on improving priority, while the dynamic method focuses on canceling commands that have timed out. The static method and the dynamic method can be combined to further support the hosts requirements.

Abstract: Read commands and write commands are issued by a data storage device, but sometimes a read command can begin execution prior to the data for the write command having been written to the memory device (or HMB DRAM). In such a scenario, the data for the read command is not in the memory device, but rather, is in cache waiting to be written to the memory device in a write cache operation. In order to ensure the correct data is read, the cache write operation can be paused so that the data can be retrieved from cache rather than the memory device. Alternatively, a placeholder can be used for the read command until the write cache operation has occurred.

Abstract: Adding a bypass module and a pattern detector module to a data path of a controller will increase the efficiency of both sanitize block erase audit and sanitize crypto erase audit operations. The sanitize crypto erase audit skips an end to end (E2E) protection module to provide decrypted data to a static random access memory (SRAM) buffer and ultimately a host device through a direct memory access (DMA) module. The sanitize block erase audit utilizes the pattern detector module to provide a known pattern to the SRAM buffer and host through the DMA module. The bypass module and pattern detector module feed into a multiplexer (Mux) prior to the SRAM buffer.

Abstract: Instead of entering lanes into an unused power state, enter unactive lanes into an unconnected power state to save more current during low power states. Using a small control logic will allow a controller to control unactive lanes in low power mode. When a lane is in an unactive power state or in an unused power state, an unactive lane controller (ULC) uses side-band signaling to place the unactive lane into either unused power state or unconnected power state. When a lane is in unused power state, then the ULC places the lane in unconnected power state. A single ULC is able to controller multiple lanes or you can have multiple ULC's, each controlling a single lane.

Abstract: Instead of using programmable block size aggregation, a lower multiple of page, and down to a page size aggregation is used. A bad block prediction unit in a controller is able to predict when a programmable block has a bad page. The bad block prediction unit can lower the aggregation size of a programmable block by monitoring the life cycle of the programmable block through bad block statistic collection. When the accumulation size passes a threshold, the bad block prediction unit lowers the aggregation size. The bad block prediction unit can also predict when to lower aggregation size based on the number of reconstructions. An aggregate size level is set at a page boundary, and once the number of reconstructions reaches that page boundary, the bad block prediction unit lowers the aggregation size to page aggregation. The bad block prediction unit is able to predict both life cycle threshold changes and reconstructions changes.

Abstract: Instead of using a bandwidth limiter for bandwidth allocation in an SSD, a dummy virtual function (VF) is used to transfer internal operations. A centralized logic such as the bandwidth limiter is incorporated in the device controller. This logic is responsible for controlling the bandwidth between the hosts. The logic is not just responsible for data transfers triggered by the hosts, but also for data transfers triggered by the device in internal operations such as garbage collection. In order to control the traffic trigged by internal operations, a dummy VF is created along with dummy submission queues. The internal operations are queued in the dummy submission queues, while the bandwidth limiter is responsible for the performance rate. Using this approach, bandwidth allocation is balanced between the hosts and SSD.

Abstract: Instead of handing each hot LBA separately, a hot LBA tracker is used to handle hot LBAs. As a command arrives, the controller classifies the command. If the command is classified as a hot LBA, then the hot LBA tracker will store the hot LBA in a separate location from where the executed commands are stored. In doing so, the hot LBA tracker will store completion information without executing the hot LBA. The hot LBAs that have a stored completion, but are not executed, are considered “skipped” hot LBAs. Once the controller determines that the hot LBA needs to be executed, the controller will execute the most recent hot LBA. After execution of the most recent hot LBA, the controller sends a completion for the most recent hot LBA and “skipped” hot LBAs.

Abstract: The present disclosure generally relates to improved fragment processing while command fetching is on-going. Rather than stopping command fetching, the controller uses a short fragment list, while command fetching can continue, to add a fragment. The controller first adds new fragments to the short list with the fragment information. The information is then checked for size. If the fragment information is smaller than the short fragment list, then the fragment list is updated during command fetching. As a command arrives, the controller does a binary search of a sorted fragment list. The results are stored and later scanned by the controller for matches with the short fragment list. If there are no matches in the short list, then the controller uses the stored results to update the search result. If there is a match in the short list then the controller uses the new results to update the search list.

Abstract: Adding a bypass module and a pattern detector module to a data path of a controller will increase the efficiency of both sanitize block erase audit and sanitize crypto erase audit operations. The sanitize crypto erase audit skips an end to end (E2E) protection module to provide decrypted data to a static random access memory (SRAM) buffer and ultimately a host device through a direct memory access (DMA) module. The sanitize block erase audit utilizes the pattern detector module to provide a known pattern to the SRAM buffer and host through the DMA module. The bypass module and pattern detector module feed into a multiplexer (Mux) prior to the SRAM buffer.

Abstract: In order to ensure that a bandwidth allocated to each tenant of a plurality of tenants of a data storage device is maintained, a controller of the data storage device may split a large read command, received from a host device, into a plurality of chunks, where each chunk corresponds to a distinct portion of the split large read command. Because the allocated bandwidth for a tenant is static, one or more chunks of the plurality of chunks, up to the allocated bandwidth, are executed, such that the bandwidth required to perform the one or more chunks does not exceed the allocated bandwidth for the particular tenant. Split information is added to the plurality of chunks in order to maintain coherency when executing the one or more chunks. Therefore, the agreed-upon allocated bandwidth for each tenant is maintained while performing large read commands requiring more bandwidth than allocated.

Abstract: A data storage device implements a Zoned Namespace (ZNS) storage architecture. The data storage device delays the execution of write commands that are received out of sequence instead of rejecting the write commands. The write commands that are received out of sequence are reordered according to a logical block address (LBA) associated with each write command. The data storage device also checks for deadlock conditions that may arise due to the execution of the write commands being delayed and/or due to the write commands being reordered.