Various implementations described herein relate to systems and methods for managing metadata for an atomic write operation, including determining metadata for data, queuing the metadata in an atomic list, in response to determining that atomic commit has occurred, moving the metadata from the atomic list to write lookup lists based on logical information of the data, and determining one of metadata pages of a non-volatile memory for each of the write lookup lists based on the logical information.

A data prefetching method and apparatus, and related storage device are provided. Data samples are collected. An AI chip trains the data samples to obtain a prefetching model. The AI chip then sends the prefetching model to a processor. The processor reads to-be-read data into a cache based on the prefetching model to reduce the computing burden of the processor.

Provided are a computer program product for managing tracks in a storage in a cache. An active track data structure indicates tracks in the cache that have an active status. An active bit in a cache control block for a track is set to indicate active for the track indicated as active in the active track data structure. In response to processing the cache control block, a determination is made, from the cache control block for the track, whether the track is active or inactive to determine processing for the cache control block.

A processor implementing techniques to supporting fault information delivery is disclosed. In one embodiment, the processor includes a memory controller unit to access an enclave page cache (EPC) and a processor core coupled to the memory controller unit. The processor core to detect a fault associated with accessing the EPC and generate an error code associated with the fault. The error code reflects an EPC-related fault cause. The processor core is further to encode the error code into a data structure associated with the processor core. The data structure is for monitoring a hardware state related to the processor core.

Data is stored at a cache portion of a cache memory of a memory sub-system responsive to a request to perform a write operation to write the data. A duplicate copy of the data is stored at a write buffer portion of the cache memory. The cache memory is partitioned into the cache portion and the write buffer portion. An entry that maps a location of the duplicate copy of the data stored at the write buffer portion of the cache memory to a location of the data stored at the cache portion of the cache memory is recorded in a write buffer record.

A system includes a first memory device having a region allocated as a first persistent memory region (PMR) having a first set of pages, a second memory device comprising a non-volatile memory device having a region allocated as a second PMR region having a second set of pages, and at least one processing device, operatively coupled to the first memory device and the second memory device, to implement a PMR mechanism to cause the second PMR region to be accessible through the first PMR region.

A storage system has volatile memory for use as a cache and can extend the available caching space by using a host memory buffer (HMB) in a host. However, because accesses to the HMB involve going through a host interface, there may be latencies in accessing the HMB, To reduce access latencies, the storage system views the volatile memory and the HMB as a two-level cache. In one use case, the storage system decides whether to store a logical-to-physical address table in the volatile memory or in the HMB based on a prediction of the likelihood that the table will be updated. If the likelihood for an update is above a threshold, the table is stored in the volatile memory, thereby eliminating the access latencies that would be encountered if the table needs to be updated and is stored in the HMB.

A memory expansion device operable with a host computer system (host) comprises a non-volatile memory (NVM) subsystem, cache memory, and control logic configurable to receive a submission from the host including a read command and specifying a payload in the NVM subsystem and demand data in the payload. The control logic is configured to request ownership of a set of cache lines corresponding to the payload, to indicate completion of the submission after acquiring ownership of the cache lines, and to load the payload to the cache memory. The set of cache lines correspond to a set of cache lines in a coherent destination memory space accessible by the host. The control logic is further configured to, after indicating completion of the submission and in response to a request from the host to read demand data in the payload, return the demand data after determining that the demand data is in the cache memory.

A method for maintaining statistics for data elements in a cache is disclosed. The method maintains a heterogeneous cache comprising a higher performance portion and a lower performance portion. The method maintains, within the lower performance portion, a ghost cache containing statistics for data elements that are currently contained in the heterogeneous cache, and data elements that have been demoted from the heterogeneous cache within a specified time interval. The method calculates a size of the ghost cache based on an amount of frequently accessed data that is stored in backend storage volumes behind the heterogeneous cache. The method alters the size of the ghost cache as the amount of frequently accessed data changes. A corresponding system and computer program product are also disclosed.

A processing device in a memory system determines to send system state information associated with the memory device to a host system and identifies a subset of a plurality of event entries from a staging buffer based on one or more filtering factors, the plurality of event entries corresponding to events associated with the memory device. The processing device further sends the subset of the plurality of event entries as the system state information to the host system over a communication pipe having limited bandwidth.