Abstract: Fragmented data on a storage device may be additionally stored in a cache. A cache weight for determining storage of a data unit can be determined. For example, a computing device can receive storage device characteristics from a storage device. A data unit comprising multiple fragments may be stored on the storage device. The computing device can receive data unit characteristics from the storage device. The computing device can determine a cache weight for the data unit. The computing device may output the cache weight for determining storage of the data unit in a cache.

Abstract: An example method may include receiving, in a virtualized execution environment, a data access request from a storage system, identifying, in view of a virtualized execution image associated with the virtualized execution environment, an application running in the virtualized execution environment, generating a cache classification that specifies whether data accessed by the application is suitable for cache compression, including, in the data access request, a tag indicating whether cached data is to be accessed in a compressed-memory cache, wherein the tag is determined in view of the cache classification, and sending, to a server of the storage system, the data access request. The application can be identified in view of metadata included in the virtualized execution image, where the metadata comprises one or more of an application name or an application version.

Abstract: An example method may include identifying one or more requested data items requested by a client system, identifying, in view of one or more requested data items, a plurality of predicted data items and, for each predicted data item, a respective probability that the predicted data item will be requested by a subsequent access request, identifying a plurality of cacheable data items, where the cacheable data items comprise one or more of the predicted data items, wherein each cacheable data item comprises a predicted data item that satisfies caching criteria, wherein the caching criteria are evaluated in view of the respective probability that the predicted data item will be requested by a subsequent access request, and storing each of the plurality of cacheable data items in a cache memory of a respective storage server at which the cacheable data item is located.

Abstract: Systems, methods, and apparatus are disclosed for management of data storage with stream based compressibility. In an example, an orchestrator including a storage controller managing one or more storage nodes executes on one or more processors. The orchestrator receives compression ratio measurements associated with attempts to compress data from a plurality of applications running on a plurality of service guests. The orchestrator receives a request for storing a first data stream from a first application running in a first service guest. Based on a compression ratio of previously stored data associated with the first application being less than a threshold, the orchestrator assigns a first compressibility setting to the first data stream. The first compressibility setting causes a storage node to store the first data stream without attempting to compress the first data stream.

Abstract: Data can be prefetched in a distributed storage system. For example, a computing device can receive a message with metadata associated with at least one request for an input/output operation from a message queue. The computing device can determine, based on the message from the message queue, an additional IO operation predicted to be requested by a client subsequent to the at least one request for the IO operation. The computing device can send a notification to a storage node of a plurality of storage nodes associated with the additional IO operation for prefetching data of the additional IO operation prior to the client requesting the additional IO operation.

Abstract: A container image is received, the container image including a container manifest referencing a first base operating system layer and an application layer. An execution compatibility is determined between the application layer and a second base operating system layer, different from the first operating system layer. An updated container image, an updated container manifest, or the updated container image and the updated container manifest is generated in which the first base operating system layer is replaced with the second base operating system layer.

Abstract: An example method may include receiving, in a virtualized execution environment, a data access request from a storage system, identifying, in view of a virtualized execution image associated with the virtualized execution environment, an application running in the virtualized execution environment, generating a cache classification that specifies whether data accessed by the application is suitable for cache compression, including, in the data access request, a tag indicating whether cached data is to be accessed in a compressed-memory cache, wherein the tag is determined in view of the cache classification, and sending, to a server of the storage system, the data access request. The application can be identified in view of metadata included in the virtualized execution image, where the metadata comprises one or more of an application name or an application version.

Abstract: Systems and methods are provided for managing write requests for drives in a cloud storage system. For example, a system can receive a plurality of write requests for writing a first set of data to a first drive of a plurality of drives. The first drive may be powered off. The system can write the first set of data to a cache in response to receiving the plurality of write requests. The system can determine that a number of the plurality of write requests exceeds a predetermined write request threshold. The system can power on the first drive in response to determining that the number of the plurality of write requests exceeds the predetermined write request threshold. The system can write the first set of data stored in the cache to the first drive.

Abstract: Data can be prefetched from a data storage system. For example, a computing device can receive a write request from a software application. The write request can be for writing a first data object to a storage device. The computing device can determine a second data object that is to be prefetched based on a read request for the first data object from the software application. The computing device can generate metadata for the first data object. The metadata can indicate that the second data object is to be prefeteched. The computing device can store the first data object with the metadata in the storage device.

Abstract: Metadata sizes for data objects in cloud storage systems can be reduced. For example, a computing system can receive, at a client device of a cloud storage system, a first object identifier associated with a data object in the cloud storage system. The computing system can use a reduction function to generate a second object identifier associated with the data object. The second object identifier can have a smaller byte size than the first object identifier. The computing system can transmit, to a server of the cloud storage system, the second object identifier to be stored in metadata associated with the data object in the cloud storage system.

Abstract: Garbage collection for a log-structured file system can be offloaded from a processor to an internal controller of a storage device, such as a solid-state drive. For example, an internal controller of a storage device can determine characteristics of a log-structured file system hosted by a processor that is external to the storage device. The characteristics can indicate how data is arranged in the log-structured file system. The internal controller can then execute, based on the characteristics, a garbage collection process with respect to the data of the log-structured file system on behalf of the processor.

Abstract: Aspects and features of the present disclosure can prefetch metadata in the nodes of a cloud-based storage system. At a node that stores at least one shard of a data object, metadata for the data object can be fetched from node storage and saved in a node cache prior to processing a read request for the shard. The metadata can be cached in response to a prefetch request transmitted to the node, for example, by the gateway that shards data objects for the storage system. Thus, the metadata can be available in the node cache when the read request for the data shard arrives later, reducing delays in accessing data object shards from the storage nodes of the system.

Abstract: Deduplication operations can be managed based on a likelihood of duplicability. For example, a computing device can generate, by a container of a storage system, an indication of duplicability corresponding to a likelihood of duplicability for the data unit in the storage system. The computing device can transmit the indication of duplicability to a storage node of the storage system for performing an operation based on the indication of duplicability.

Abstract: Data units can be relocated in scale-out storage systems. For example, a computing device can receive, at a first node of a scale-out storage system, a request for a data unit. The first node can include a metadata entry associated with the data unit. The computing device can determine, based on the metadata entry, that a second node of the scale-out storage system includes the data unit. The computing device can determine, from the metadata entry, that a number of versions of the data unit in the scale-out storage system meets or exceeds a threshold. The computing device can output a command to cause the data unit to be relocated to the first node with the metadata entry.

Abstract: Deduplication operations can be managed based on a likelihood of duplicability. For example, a computing device can generate, by a container of a storage system, an indication of duplicability corresponding to a likelihood of duplicability for the data unit in the storage system. The computing device can transmit the indication of duplicability to a storage node of the storage system for performing an operation based on the indication of duplicability.

Abstract: A technique for improving workload distribution by utilizing unused resources in a distributed computing system is described. In one example of the present disclosure, a system can determine that a computing entity of a distributed computing system includes an unused portion of a CPU capacity. The computing entity can have a first defined limit of the CPU capacity. The system can use the unused portion of the CPU capacity to improve a usage of a resource of the computing entity. The computing entity can have a second defined limit of the resource.

Abstract: Data requests can be serviced by multiple paths of smart network interface cards (NICs). For example, a system can receive a request for data at a first path of a smart NIC. The first path can be a hardware-implemented path. The system can send one or more parameters of the request to a second path of the smart NIC. The second path can be a slower path than the first path and configured to execute a routing algorithm for the request. The system can receive routing information for the request from the second path based on the routing algorithm and transmit the request to a storage node based on the routing information.

Abstract: Systems and methods are provided for managing prefetching operations for read requests for drives in a distributed storage system. For example, a system can determine that a first drive of a plurality of drives is powered on. Prior to receiving a read request for reading a first set of data from the first drive, the system can enable a prefetching operation for prefetching the first set of data from the first drive to be written to a cache. The system may power off the first drive. The system may receive a read request for reading the first set of data from the first drive of a plurality of drives. In response to receiving the read request, the system may read the first set of data from the cache.

Abstract: Systems and methods are provided for managing write requests for drives in a cloud storage system. For example, a system can receive a plurality of write requests for writing a first set of data to a first drive of a plurality of drives. The first drive may be powered off. The system can write the first set of data to a cache in response to receiving the plurality of write requests. The system can determine that a number of the plurality of write requests exceeds a predetermined write request threshold. The system can power on the first drive in response to determining that the number of the plurality of write requests exceeds the predetermined write request threshold. The system can write the first set of data stored in the cache to the first drive.

Abstract: Power consumption can be reduced by preventing a memory image from being destaged to a nonvolatile memory device. For example, a system can determine, subsequent to a computing device being in a first power mode and having a memory image stored in a first nonvolatile memory device that performs a caching function, that the computing device is in a second power mode that is a higher power mode than the first power mode. The system can, in response to determining that the computing device is in the second power mode, generate a first command to store the memory image in a volatile memory device and prevent the memory image from being stored in a second nonvolatile memory device. The system can, in response to generating the first command, store the memory image in the volatile memory device.