Abstract: A server computer system receives a file access request for accessing a file in a file system. The file access request includes a file handle for the file. The server computer system assigns a value as a file descriptor for the file. The assignment is performed without issuing a file open request to open the file. The server computer system associates the file descriptor with the file handle in a data store accessible to a storage subsystem and provides the file descriptor for accessing the file to the storage subsystem according to the file access request.

Abstract: File link migration is described. A method may include identifying a first file link referencing a file residing at a first computer system, and identifying, at the first computer system, a first inode data structure referenced by the first file link, the first inode data structure comprising a first link count. The method may also include creating a second inode data structure at a second computer system, wherein the second data structure comprises a second link count, and creating a second file link to reference the second inode data structure at the second computer system. The method may also include, responsive to determining that the first link count matches the second link count, migrating file data referenced by the first data structure to the second computer system.

Abstract: A distributed file system includes a plurality of computing devices that are coupled to a plurality of storage devices. A first computing device transfers objects to an additional computing device. The first computing device determines times when multiple computing devices, including the first computing device, transferred objects to the additional computing device. The first computing device identifies the earliest of the times and may store this information on the additional computing devices. A second computing device resumes transferring data to the additional computing device when the first computing device becomes unavailable or inoperable. The second computing device may use the earliest of the times to determine which objects should be transferred to the additional computing device.

Abstract: A first server hosted on a computer system identifies a set of file links in the first server that is associated with one or more hard links that point to file data for a file in the first server. The computer system migrates the set of files links for the file to a second server prior to migrating the file data for the file in the first server to the second server. The second server is hosted by a second computer system. The first computer system migrates the file data for the file in the first server to the second server when the migration of the set of file links for the file to the second server is complete.

Abstract: Systems and methods implementing a path resolver facilitating client access to a distributed file system. An example method may comprise: receiving, by a processing device, file identifier comprising a symbolic link; producing, by a user space process being executed by the processing device, a modified file identifier, by replacing a pre-defined sequence of characters within the file identifier by a path to a mount point of a distributed file system; and identifying, in view of the modified file identifier, a data structure comprising information about a file identified by the file identifier.

Abstract: An outcast index in a distributed file system is described. A first server can receive an indication that a first replica stored on the first server is to be modified in view of a second replica stored on a second server. The first replica and the second replica are replicas of a same file. The first server updates metadata associated with the first replica to indicate an outcast state of the first replica. The first server receives an indication that the modification of the first replica is complete. The first server updates the metadata associated with the first replica to remove the outcast state of the first replica.

Abstract: A server processing device acquires a lock on a region of a file which has stale data. The server processing device self-heals the stale data in the locked region using current data and receives a write request to modify another region of the file during the self-healing of the locked region of the file. The server processing device provides write access to the requested region during the self-healing of the locked region of the file.

Abstract: A server computer system performs a first set of operations for a first transaction. The first transaction pertaining to data stored in a file system. The server computer system delays a second set of operations for the first transaction and identifies a second transaction pertaining to the data. In response to identifying the second transaction, the server computer system cancels the second set of operations for the first transaction, and cancels a first set of operations for the second transaction.

Abstract: A server computer system identifies change operations for an object in a file system. The object can be a file or a directory. The change operations can include a change to a local copy of the object and one or more remote copies of the object. The server computer system determines that one of the change operations is unsuccessful and creates tracking data that identifies the object that is associated with at least one change operation that is unsuccessful.

Abstract: A first server hosted on a computer system identifies a set of file links in the first server that is associated with one or more hard links that point to file data for a file in the first server. The computer system migrates the set of files links for the file to a second server prior to migrating the file data for the file in the first server to the second server. The second server is hosted by a second computer system. The first computer system migrates the file data for the file in the first server to the second server when the migration of the set of file links for the file to the second server is complete.

Abstract: A server computer system identifies change operations for an object in a file system. The object can be a file or a directory. The change operations can include a change to a local copy of the object and one or more remote copies of the object. The server computer system determines that one of the change operations is unsuccessful and creates tracking data that identifies the object that is associated with at least one change operation that is unsuccessful.

Abstract: A server computer system receives a file access request for accessing a file in a file system. The file access request includes a file handle for the file. The server computer system assigns a value as a file descriptor for the file. The assignment is performed without issuing a file open request to open the file. The server computer system associates the file descriptor with the file handle in a data store accessible to a storage subsystem and provides the file descriptor for accessing the file to the storage subsystem according to the file access request.

Abstract: A server computer system receives a request for access to an object in a file system. The object is a file or a directory. The server computer system identifies an object handle in the request. The object handle is an identifier of the object. The server computer system identifies an object link that is associated with the object handle. The object link is a hard link to the file or a relative symbolic link to the directory. The server computer system accesses the object using the object link that is associated with the object handle.

Abstract: A first storage server identifies a second storage server connecting to a cluster of storage servers in a file system. The first storage server locates a file in a replication directory hierarchy in the second storage server. The file has not been accessed by a client application. The first storage server determines, prior to the file being accessed by the client application, that the file on the second storage server has stale data and overwrites the stale data in the file on the second storage server with current data.

Abstract: A first server identifies a second server connecting to a cluster of servers in a file system. The first server examines a file in a replication directory hierarchy in the second server. The file has not been accessed by a client application. The first server determines, prior to the file being accessed by the client application that the file on the second server has stale data and overwrites the stale data in the file on the second server with current data.

Abstract: A processing device receives a request for access to a source file that is stored in an initial location in a file system. The processing device determines that the source file is associated with a migration to a new location. The processing device reads the source file from the initial location if the request is a read request and writes to the source file at the initial location and writes to a destination file at the new location if the request is a write request.

Abstract: A server processing device acquires a lock on a region of a file which has stale data. The server processing device self-heals the stale data in the locked region using current data and receives a write request to modify another region of the file during the self-healing of the locked region of the file. The server processing device provides write access to the requested region during the self-healing of the locked region of the file.

Abstract: A server computing device receives, from a client computing device, a hypertext transfer protocol (HTTP) request to perform an operation on an object. The server computing device identifies a file, that corresponds to the object, in a network attached storage file system in a local area network. The server computing device mounts, via the local area network, the network attached storage file system to perform the operation using the file that corresponds to the object. The computer device sends a HTTP response indicating performance of the operation to the client computing device.

Abstract: A server computing device receives, from a client computing device, a request to perform an operation on an object. The server computing device identifies a file, that corresponds to the object, in a network attached storage file system in a local area network. The server computing device mounts, via the local area network, the network attached storage file system to perform the operation using the file that corresponds to the object. The computer device sends a response indicating performance of the operation to the client computing device.