Abstract: Method and system for moving an object from a source partition server to a target partition server in a distributed file system having multiple partition servers. Each object has at least one associated and linked parent object, and each partition server owns a subset of objects of the file system. The object migration is accomplished by creating a copy in a target partition server of a selected object from a source partition server. At the source partition server, a forwarding link is created that references the copy in the target partition server. The copy is linked to the parent object of the selected object, and requests for access to the selected object are responded to with the forwarding link.

Abstract: In a method of mapping peers in a peer-to-peer network to an overlay network, network coordinates are determined for a selected peer. The logical coordinates in the overlay network are determined based on the network coordinates. A zone is determined based on the logical coordinates. The network coordinates, a network address of the selected peer and the zone is stored as an object at a peer owning the zone, where associated information is stored in the peer that has the network coordinate and using the network coordinate as a key.

Abstract: In a method for creating expressway for overlay routing, an existing peer-to-peer network is organized into a plurality of zones. A neighboring zone to a destination peer is selected. A plurality of residents of the neighboring zone are retrieved. A candidate peer is selected from the plurality of residents based a physical distance value and an estimated distance value.

Abstract: In a method of generating a routing table for a selected peer, a zone of the selected peer is compared to a target zone. A current entry associated with the zone of the selected peer is created in a routing table of said selected peer in response to the zone of the selected peer being one of smaller and equal to the target zone.

Abstract: A peer-to-peer system includes a plurality of nodes functioning as a distributed, shared, file system. A node of the plurality of nodes is operable to randomly place an object within a logical space relative to a parent node hosting a parent object in the peer-to-peer system.

Abstract: A peer-to-peer system includes a plurality of nodes. The plurality of nodes includes at least an initial node and a neighboring node. The initial node is operable to determine whether to place an object at either the initial node or another node in the system based on a comparison of storage utilizations for the initial node and the neighboring node.

Abstract: A peer-to-peer system is divided into a plurality of zones for placing an object. A parent zone having a parent node is identified. The parent zone is divided into the plurality of zones, i.e., subzones, and one of subzones is selected. A node in the subzone is selected for placing the object.

Abstract: In a method for creating expressway for overlay routing, an existing peer-to-peer network is organized into a plurality of zones. The plurality of zones is organized into a plurality of levels. Neighboring zones are identified for each zone of the plurality of zones. One or more representatives are identified for each neighboring zone. A routing table is created based the plurality of zones, the neighboring zones, the one or more representatives, and the plurality of levels.

Abstract: In a method for expressway routing among peers, a request is received to forward data. The destination is determined from said request. A routing table is searched for an expressway route based on zones to the destination. The data is transmitted across the expressway route to the destination.

Abstract: Method and system for performing a namespace operation in a distributed file system. The file system is disposed on a plurality of partition servers, and each partition server controls access to a subset of hierarchically-related, shared storage objects. Each namespace operation involves a namespace object and a target object that are part of the shared storage objects. Namespace operations received at each partition server are serialized. In response to an unlink namespace operation, a reference in the namespace object to the target object is removed, and after removal the target object is modified in accordance with the unlink operation. In response to a link operation, the target object is modified consistent with the link operation. After modification of the target object, a reference to the target object is inserted in the namespace object.

Abstract: A method for operating a shared memory computer system to reduce the latency times associated with lock/unlock code sequences. The computer system includes a shared memory and a plurality of processors. When one of the processors wishes to modify a shared variable stored in the shared memory, the processor must first request and receive a lock from the shared memory. The lock prevents any other processor in the computer system from modifying data in the shared memory during the locked period. In the present invention, a list of variables in the shared memory that are shared by two or more of the processors is generated. When one of the processors is granted a lock, a prefetch instruction is executed for each variable in the list. Each prefetch instruction specifies the processor receiving the lock as the destination of the data specified in that prefetch instruction. The list may be generated by a compiler during the compilation of a program that is to run on one of the processors.

Abstract: A method and system of enforcing file authorization access. The method may include generating an authorization combination at a metadata server and encrypting the authorization combination. The authorization combination may include a block combination including a block list for accessing user requested data from a storage server system and an authorization prefix. The authorization prefix may indicate at least one operation which the user requesting data access is authorized to perform. The method may further include receiving the encrypted authorization combination at the storage server, and decrypting the encrypted authorization combination to recover the block list for retrieving the user requested data.

Abstract: Namespace service in a distributed file system using a database management system. A namespace database is configured on a namespace server with namespace identifiers and associated file location information. The namespace server is separate from the data servers in the distributed file system. A client proxy arrangement interfaces with client applications and with the namespace server to obtain from the namespace server location information associated with files referenced in file access requests and submit storage access requests to the appropriate data servers. The separate namespace server and data servers enhances scalability of the distributed file system.

Abstract: Data coherency and lock services for distributed physical file systems. Client applications are coupled to a virtual file system, which is coupled to one or more physical file systems. A lock agent is coupled to one or more lock servers and to the virtual file system. The virtual file system, in response to a file access request from a client application, submits a data validation request to the lock agent. The lock agent, in turn, submits a lease request to the lock server. When the lock server grants the lease, the lease and a validation code are returned to the lock agent. The validation code indicates whether the data in the buffer cache of the virtual file system are valid. The lock agent then returns the lease to the virtual file system, which then submits the file access request to a selected one of the physical file systems.

Abstract: Method and system for performing a namespace operation in a distributed file system. The file system is disposed on a plurality of partition servers, and each partition server controls access to a subset of hierarchically-related, shared storage objects. Each namespace operation involves a namespace object and a target object that are part of the shared storage objects. Namespace operations received at each partition server are serialized. In response to an unlink namespace operation, a reference in the namespace object to the target object is removed, and after removal the target object is modified in accordance with the unlink operation. In response to a link operation, the target object is modified consistent with the link operation. After modification of the target object, a reference to the target object is inserted in the namespace object.

Abstract: Method and system for performing a namespace operation in a distributed file system. The file system is disposed on a plurality of partition servers, and each partition server controls access to a subset of hierarchically-related, shared storage objects. Each namespace operation involves a namespace object and a target object that are part of the shared storage objects. Namespace operations received at each partition server are serialized. In response to an unlink namespace operation, a reference in the namespace object to the target object is removed, and after removal the target object is modified in accordance with the unlink operation. In response to a link operation, the target object is modified consistent with the link operation. After modification of the target object, a reference to the target object is inserted in the namespace object.

Abstract: Method and arrangement for updating references to a migrated object in a distributed file system. A migrated object is an object has moved from a source partition server to a target partition server. Each object has an associated parent object and each partition server owns a subset of objects of the file system. A set of forward pointers that reference one or more child objects of the parent object is maintained in each parent object. In the migrated object a set of back pointers is maintained that reference one or more parent objects having forward pointers to the migrated object. To each partition server that owns a parent object of the migrated object, an update request is transmitted. The forward pointers in each parent object are updated in response to the update request.

Abstract: Method and system for moving an object from a source partition server to a target partition server in a distributed file system having multiple partition servers. Each object has at least one associated and linked parent object, and each partition server owns a subset of objects of the file system. The object migration is accomplished by creating a copy in a target partition server of a selected object from a source partition server. At the source partition server, a forwarding link is created that references the copy in the target partition server. The copy is linked to the parent object of the selected object, and requests for access to the selected object are responded to with the forwarding link.

Abstract: Method and system for migrating a logical volumes in a distributed file system having multiple partitions servers. Each partition server owns one or more volumes, and each volume including a subset of logically related objects of the file system. In response to a migration request that requests migration of a selected logical volume from a source partition server to the target partition server, an ownership map is updated to indicate the selected logical volume is owned by the target partition server. At the source partition server, forwarding information is stored to reference the target partition server. When the source partition server receives a request for access to the object, the forwarding information is transmitted to the requester.

Abstract: The present invention provides methods and systems for performing improved implementations of the BLAST algorithm for high-speed sequence database searching, e.g., on commodity Beowulf-class parallel computing hardware. The present invention also provides methods and systems for query packing, dynamic database division, and improved hit extension.