Abstract: Aspects of the present disclosure provide for operations of a key-value store (KVS) that uses journaling with storage of data (e.g., key data or value data of a key-value pair) in different types of data storage objects (e.g., data storage formats) selected based on one or more criteria.

Abstract: Aspects of the present disclosure provide for operations of a key-value store (KVS) that uses journaling with storage of data (e.g., key data or value data of a key-value pair) in different types of data storage objects (e.g., data storage formats) selected based on one or more criteria.

Abstract: Aspects of the present disclosure provide for operations of a key-value store (KVS) that uses journaling with storage of data (e.g., key data or value data of a key-value pair) in different types of data storage objects (e.g., data storage formats) selected based on one or more criteria.

Abstract: Techniques for enabling communication between a virtual machine and the host of the virtual machine are disclosed. An example computing device includes a host operating system and a virtual machine running on the host operating system. The storage device also includes a split driver. The split driver includes a frontend driver residing on the virtual machine and a backend driver residing on the host. The split driver processes messages received from the virtual machine and passes the messages from the frontend driver to the backend driver.

Abstract: The present subject matter relates to file creation. In one example a user request for creating a new file is received. An inode corresponding to a pre-created file is retrieved from a pre-created pool of files in response to receiving the user request. Further, the inode is associated with an in-memory dentry corresponding to the new file. Further, a log entry is created in an intent log to indicate intent of lazy linking of the pre-created file with a target directory in which the new file is to be created. Further, lazy linking of the pre-created file with the target directory is performed using a file system link operation upon occurrence of a predefined event.

Abstract: Aspects of the present disclosure provide for operations of a key-value store (KVS) that uses journaling with storage of data (e.g., key data or value data of a key-value pair) in different types of data storage objects (e.g., data storage formats) selected based on one or more criteria.

Abstract: Techniques for enabling communication between a virtual machine and the host of the virtual machine are disclosed. An example computing device includes a host operating system and a virtual machine running on the host operating system. The storage device also includes a split driver. The split driver includes a frontend driver residing on the virtual machine and a backend driver residing on the host. The split driver processes messages received from the virtual machine and passes the messages from the frontend driver to the backend driver.

Abstract: The present subject matter relates to file creation. In one example a user request for creating a new file is received. An inode corresponding to a pre-created file is retrieved from a pre-created pool of files in response to receiving the user request. Further, the inode is associated with an in-memory dentry corresponding to the new file. Further, a log entry is created in an intent log to indicate intent of lazy linking of the pre-created file with a target directory in which the new file is to be created. Further, lazy linking of the pre-created file with the target directory is performed using a file system link operation upon occurrence of a predefined event.

Abstract: Presented is a method of operating a server to enable a client to access data stored by a file system. The method comprises: receiving from the client a request to perform an operation on the data; instructing the file system to perform a preliminary metadata operation and, before the metadata-operation has completed, instructing the file system to perform the operation on the data; waiting for the file system to complete both the metadata-operation and the operation on the data; and responding to the client.

Abstract: A method for processing concurrent write operations in a computer system, the method comprising a first step of copying data residing in one or more source buffers to a contiguous intermediate buffer, prior to acquiring a lock for a write operation. In a second step, on acquiring the lock performing a translation operation between the intermediate buffer and a destination buffer, to process the write operation.

Abstract: A stacked file system and method for managing a stack are disclosed. In one embodiment, a stacked file system includes a stack and a stack manager. The stack has at least a file system stacked on top of an underlying file system. Further, the stack manager has a logic for managing the stack, where the logic includes an eject operation for ejecting a first file system from the stack.

Abstract: A plurality of bits are added to virtual and physical memory addresses to specify the level at which data is stored in a multi-level cache hierarchy. When data is to be written to cache, each cache level determines whether it is permitted to store the data. Storing data at the appropriate cache level addresses the problem of cache thrashing.

Abstract: Presented is a method of operating a server to enable a client to access data stored by a file system. The method comprises: receiving from the client a request to perform an operation on the data; instructing the file system to perform a preliminary metadata operation and, before the metadata-operation has completed, instructing the file system to perform the operation on the data; waiting for the file system to complete both the metadata-operation and the operation on the data; and responding to the client.

Abstract: An efficient stacked file system and method are disclosed herein. The stacked file system is capable of inserting a layer into a stack and ejecting the same from the stack in accordance with the requirement of the functionalities provided by the layer; thereby minimises adverse affect on the overall file system performance.

Abstract: An apparatus and a method for managing a memory are presented. In one example embodiment, the method and the apparatus includes a memory that has one or more partitions. Each of the partitions includes one or more zones. Each of the zones includes one or more memory ranges. In this example embodiment, the method begins by determining occurrence of memory shortage in a first partition of the memory during runtime of the apparatus. Based on the outcome of the determination, during runtime of the apparatus, the memory from the one or more zones of the one or more partitions of the memory is claimed by instantiating invocation of memory claiming process.

Abstract: A method for processing concurrent write operations in a computer system, the method comprising a first step of copying data residing in one or more source buffers to a contiguous intermediate buffer, prior to acquiring a lock for a write operation. In a second step, on acquiring the lock performing a translation operation between the intermediate buffer and a destination buffer, to process the write operation.

Abstract: A plurality of bits are added to virtual and physical memory addresses to specify the level at which data is stored in a multi-level cache hierarchy. When data is to be written to cache, each cache level determines whether it is permitted to store the data. Storing data at the appropriate cache level addresses the problem of cache thrashing.