A computing device includes a volatile memory that includes a first cache, a non-volatile storage that includes a second cache, and a cache service. The cache service, responsive to a cache miss, retrieves that asset and writes that asset to the first cache and not the second cache. The cache service reads the asset from the first cache responsive to requests for the asset until the asset is evicted from the first cache or until the asset is promoted to the second cache. The cache service promotes the asset to the second cache upon determining that a set of one or more criteria are satisfied including a predefined number of cache hits for the asset when it is in the first cache. The cache service reads the asset from the second cache responsive to requests for the asset until the asset is evicted from the second cache.

This disclosure relates to a data storage method and apparatus, and a server. The method includes receiving, by a first server, a write instruction sent by a second server, storing target data in a cache of a controller, detecting a read instruction for the target data, and storing the target data in a storage medium of a non-volatile memory based on the read instruction. In other words, when the second server needs to write the target data to the first server, the target data is not only written to the cache of the first server, but also written to the storage medium of the first server. This can ensure that the data in the cache is written to the storage medium promptly.

Physical storage devices may be managed for spontaneous de-staging from a cache, for example, by determining a background task threshold (UBTT), and controlling one or more physical storage devices to use the UBTT instead of the VBTT in determining when to enter background task mode. The determined UBTT may be less than the VBTT, which may cause the physical storage device to enter into background task mode earlier, which means that background tasks like garbage collection and write leveling may be performed more frequently. An ability to turn on and turn off management of physical storage devices for spontaneous de-staging of a cache may be provided. It may be desirable to turn off physical storage device management for spontaneous de-staging, for example, during peak workload hours, to prevent physical storage devices from entering into background task mode more frequently during certain times.

One embodiment facilitates a write operation in a shingled magnetic recording device. During operation, the system receives, by the storage device, data to be written to the storage device and access-frequency information associated with the data, wherein the storage device includes a plurality of concentric tracks. The system distributes a plurality of spare sector pools among the plurality of concentric tracks. The system selects a track onto which to write the data based on the access-frequency information, wherein data with a highest access-frequency is written to an outer track. The system appends the data at a current write pointer location of the selected track, thereby facilitating an enhanced data placement for subsequent access in the storage device.

Disclosed herein are methods, systems, and processes to provide coherency across disjoint caches in clustered environments. It is determined whether a data object is owned by an owner node, where the owner node is one of multiple nodes of a cluster. If the owner node for the data object is identified by the determining, a request is sent to the owner node for the data object. However, if the owner node for the data object is not identified by the determining, selects a node in the cluster is selected as the owner node, and the request for the data object is sent to the owner node.

A method, hybrid server system, and computer program product, prefetch data. A set of prefetch requests associated with one or more given datasets residing on the server system are received from a set of accelerator systems. A set of data is prefetched from a memory system residing at the server system for at least one prefetch request in the set of prefetch requests. The set of data satisfies the at least one prefetch request. The set of data that has been prefetched is sent to at least one accelerator system, in the set of accelerator systems, associated with the at least one prefetch request.

Physical storage devices may be managed for spontaneous de-staging from a cache, for example, by determining a background task threshold (UBTT), and controlling one or more physical storage devices to use the UBTT instead of the VBTT in determining when to enter background task mode. The determined UBTT may be less than the VBTT, which may cause the physical storage device to enter into background task mode earlier, which means that background tasks like garbage collection and write leveling may be performed more frequently. An ability to turn on and turn off management of physical storage devices for spontaneous de-staging of a cache may be provided. It may be desirable to turn off physical storage device management for spontaneous de-staging, for example, during peak workload hours, to prevent physical storage devices from entering into background task mode more frequently during certain times.

A method and system for intelligent control of read-ahead cache for a client application is provided. The method receives an application profile of the client application, the application profile indicating thresholds for determining a plurality of access patterns of the client application. The method also determines a current access pattern of the client application based on the thresholds and a historical access pattern of the client application. The current access pattern and the historical access pattern are one of the plurality of access patterns. The method further dynamically enables and disables read-ahead cache for the client application based on a transition between the historical access pattern and the current access pattern.

A computing device includes a volatile memory that includes a first cache, a non-volatile storage that includes a second cache, and a cache service. The cache service, responsive to a cache miss, retrieves that asset and writes that asset to the first cache and not the second cache. The cache service reads the asset from the first cache responsive to requests for the asset until the asset is evicted from the first cache or until the asset is promoted to the second cache. The cache service promotes the asset to the second cache upon determining that a set of one or more criteria are satisfied including a predefined number of cache hits for the asset when it is in the first cache. The cache service reads the asset from the second cache responsive to requests for the asset until the asset is evicted from the second cache.

A method is disclosed for recovering data, the method comprising: retrieving a mapping structure associated with a volume in a storage system, the mapping structure including a plurality of entries, each entry including a respective short hash digest of a data block stored in the volume and an identifier of a location where the data block is stored; generating a plurality of long hash digests, each of the long hash digests being generated based on a different one of a plurality of data blocks that are stored in the storage system; comparing each of the long hash digests to a short hash digest of a missing data block, and adding the long hash digest to a candidate list when the long hash digest matches the short hash digest of the missing data block; generating a filtered candidate based on the candidate list; and recovering the missing data.