Abstract: Executing a query in a disaggregated cluster. A query is received at the disaggregated cluster. A query graph is created based on the query that identifies a hierarchy of vertices, where each vertex is associated with a set of data responsive to at least a portion of the query. The compute nodes process the query graph by first identifying a minimum set of tables, files, and objects stored on the storage nodes required to retrieve data that satisfy the query. Next, the compute nodes selectively assign the identified tables, files, and objects to a leaf vertex of the query graph to optimize retrieving data from the storage nodes. Thereafter, the compute nodes process the retrieved data sets associated with each vertex using separate threads of execution for each vertex of the query graph such that leaf vertices are performed in parallel. The compute nodes then provide a result set.

Abstract: Systems, methods and/or devices are used to perform memory-efficient mapping of block/object addresses. In one aspect, a method of managing a storage system having one or more storage devices includes a tiered data structure in which each node has a logical ID and entries in the nodes reference other nodes in the tiered data structure using the logical IDs. As a result, when a child node is updated and stored to a new location, but retains its logical ID, its parent node does not need to be updated, because the logical ID in the entry referencing the child node remains unchanged. Further, the storage system uses a secondary mapping table to translate the logical IDs to the corresponding physical locations of the corresponding nodes. Additionally, the secondary mapping table is cached in volatile memory, and as a result, the physical location of a required node is determined without accessing non-volatile memory.

Abstract: Executing a query in a disaggregated cluster. A query is received at the disaggregated cluster. A query graph is created based on the query that identifies a hierarchy of vertices, where each vertex is associated with a set of data responsive to at least a portion of the query. The compute nodes process the query graph by first identifying all tables, files, and objects stored on the storage nodes whose access is required to retrieve data that satisfy the query. Next, the compute nodes selectively assign the identified tables, files, and objects to a leaf vertex of the query graph to optimize retrieving data from the storage nodes. Thereafter, the compute nodes process the retrieved data sets associated with each vertex using separate threads of execution for each vertex of the query graph such that leaf vertices are performed in parallel. The compute nodes then provide a result set.

Abstract: Apparatuses, systems, methods, and computer program products are disclosed for key-value stores with partial data access. An interface module is configured to receive a data object for storage in a key-value store. The data object may include a key and a value. A block object module is configured to generate a plurality of block objects smaller than the data object. A block object may include a new key and a new value. The new key may be based on the key for the data object and on metadata for the new value. The new value may be based on at least a portion of the value for the data object. A storage module is configured to store the block objects in the key-value store.

Abstract: Systems, methods and/or devices are used to perform memory-efficient mapping of block/object addresses. In one aspect, a method of managing a storage system having one or more storage devices includes a tiered data structure in which each node has a logical ID and entries in the nodes reference other nodes in the tiered data structure using the logical IDs. As a result, when a child node is updated and stored to a new location, but retains its logical ID, its parent node does not need to be updated, because the logical ID in the entry referencing the child node remains unchanged. Further, the storage system uses a secondary mapping table to translate the logical IDs to the corresponding physical locations of the corresponding nodes. Additionally, the secondary mapping table is cached in volatile memory, and as a result, the physical location of a required node is determined without accessing non-volatile memory.

Abstract: Systems, methods and/or devices are used to perform memory-efficient mapping of block/object addresses. In one aspect, a method of managing a storage system having one or more storage devices includes a tiered data structure in which each node has a logical ID and entries in the nodes reference other nodes in the tiered data structure using the logical IDs. As a result, when a child node is updated and stored to a new location, but retains its logical ID, its parent node does not need to be updated, because the logical ID in the entry referencing the child node remains unchanged. Further, the storage system uses a secondary mapping table to translate the logical IDs to the corresponding physical locations of the corresponding nodes. Additionally, the secondary mapping table is cached in volatile memory, and as a result, the physical location of a required node is determined without accessing non-volatile memory.

Abstract: Systems, methods, and/or devices are used to store metadata in a storage system. In one aspect, a first user space module sends a logical memory request to a memory management module of a kernel space module. The logical memory request includes data and metadata. A second user space module obtains the metadata of the logical memory request. A storage engine of the second user space module determines, in accordance with the obtained metadata, a location in non-volatile memory for the data. A second user space module generates a physical memory request including an indication of the non-volatile memory for the data. The second user space module transmits the physical memory request to the kernel space memory management module.

Abstract: An apparatus includes a non-volatile memory and a controller coupled to the non-volatile memory. The controller is configured to receive a command from a device to perform a write operation at the non-volatile memory. The command indicates a plurality of logical addresses, data associated with the plurality of logical addresses, and a number of write operations associated with the command.

Abstract: A method includes accessing, in response to initiating an operation targeting data, auxiliary mapping data to determine whether the auxiliary mapping data includes an indication of a key associated with a node of a hierarchical data structure that is associated with the data. In response to the auxiliary mapping data including the indication of the key, the data is accessed from a memory using a node identification associated with the key. In response to the auxiliary mapping data not including the indication of the key, the data is accessed from the memory using a search operation.

Abstract: Systems, methods and/or devices are used to coalesce metadata and data writes via write serialization with device-level address remapping. In one aspect, a method of managing a storage system having one or more storage devices includes a serialized write operation to the storage system, in which a serialization segment accumulates data objects and mapping information until the segment is full, at which time the serialization segment is written to the storage system in a single contiguous write. As a result, the number of I/O operations is decreased from a minimum of two (one to write data and one to write updated mapping information) to a single write operation. Further, if the serialization segment contains existing valid data prior to accumulating data objects and mapping information, the valid data is moved to the beginning of the serialization segment using either a remap or xcopy operation.

Abstract: An apparatus includes a non-volatile memory and a controller coupled to the non-volatile memory. The controller is configured to receive a command from a device to perform a write operation at the non-volatile memory. The command indicates a plurality of logical addresses, data associated with the plurality of logical addresses, and a number of write operations associated with the command.

Abstract: A method of managing a storage system having one or more storage devices includes receiving a request to access, in a tiered data structure, a data object and one or more attributes of the data object and processing the access request. The request includes a first key value for the data object and respective second key values for the one or more attributes of the data object. Modified key values for the attributes of the data object are generated in accordance with at least a portion of the first key value and used to access tree entries for the data object attributes in one or more leaf nodes of the tiered data structure. A tree entry for the data object is also accessed from the same set of one or more leaf nodes.

Abstract: An apparatus includes a data sequencing engine configured to receive first data and an identification of a first data container associated with the first data and to allocate the first data to a first data stream of multiple data streams based on the identification. The apparatus further includes at least one memory configured to store the first data container. The data sequencing engine is further configured to cause the at least one memory to send data in the first data stream to a flash memory in response to detecting a data size of the first data stream satisfies a threshold.

Abstract: Systems, methods and/or devices are used to perform memory-efficient mapping of block/object addresses. In one aspect, a method of managing a storage system having one or more storage devices includes a tiered data structure in which each node has a logical ID and entries in the nodes reference other nodes in the tiered data structure using the logical IDs. As a result, when a child node is updated and stored to a new location, but retains its logical ID, its parent node does not need to be updated, because the logical ID in the entry referencing the child node remains unchanged. Further, the storage system uses a secondary mapping table to translate the logical IDs to the corresponding physical locations of the corresponding nodes. Additionally, the secondary mapping table is cached in volatile memory, and as a result, the physical location of a required node is determined without accessing non-volatile memory.

Abstract: Systems, methods and/or devices are used to coalesce metadata and data writes via write serialization with device-level address remapping. In one aspect, a method of managing a storage system having one or more storage devices includes a serialized write operation to the storage system, in which a serialization segment accumulates data objects and mapping information until the segment is full, at which time the serialization segment is written to the storage system in a single contiguous write. As a result, the number of I/O operations is decreased from a minimum of two (one to write data and one to write updated mapping information) to a single write operation. Further, if the serialization segment contains existing valid data prior to accumulating data objects and mapping information, the valid data is moved to the beginning of the serialization segment using either a remap or xcopy operation.

Abstract: An apparatus includes a data sequencing engine configured to receive first data and an identification of a first data container associated with the first data and to allocate the first data to a first data stream of multiple data streams based on the identification. The apparatus further includes at least one memory configured to store the first data container. The data sequencing engine is further configured to cause the at least one memory to send data in the first data stream to a flash memory in response to detecting a data size of the first data stream satisfies a threshold.

Abstract: A method includes accessing, in response to initiating an operation targeting data, auxiliary mapping data to determine whether the auxiliary mapping data includes an indication of a key associated with a node of a hierarchical data structure that is associated with the data. In response to the auxiliary mapping data including the indication of the key, the data is accessed from a memory using a node identification associated with the key. In response to the auxiliary mapping data not including the indication of the key, the data is accessed from the memory using a search operation.

Abstract: A memory controller detects a request, with a key to a data object and a value, to perform an operation. The memory controller locates the data object by mapping the key to a location of the data object in a tiered data structure and identifies a sequence number of the data object. When the sequence number of the data object is greater than a sequence number of a snapshot of the tiered data structure, the memory controller replaces the data object with a modified data object, including the key and the value, and assigns the modified object a unique sequence number. When the sequence number of the data object is less than the sequence number of the snapshot, the memory controller inserts a new data object, including the key and the value, into the tiered data structure and assigns the new data object the unique sequence number.

Abstract: Apparatuses, systems, methods, and computer program products are disclosed for key-value stores with partial data access. An interface module is configured to receive a data object for storage in a key-value store. The data object may include a key and a value. A block object module is configured to generate a plurality of block objects smaller than the data object. A block object may include a new key and a new value. The new key may be based on the key for the data object and on metadata for the new value. The new value may be based on at least a portion of the value for the data object. A storage module is configured to store the block objects in the key-value store.

Abstract: Systems, methods, and/or devices are used to store metadata in a storage system. In one aspect, a first user space module sends a logical memory request to a memory management module of a kernel space module. The logical memory request includes data and metadata. A second user space module obtains the metadata of the logical memory request. A storage engine of the second user space module determines, in accordance with the obtained metadata, a location in non-volatile memory for the data. A second user space module generates a physical memory request including an indication of the non-volatile memory for the data. The second user space module transmits the physical memory request to the kernel space memory management module.