Abstract: Multiple computers in a cluster maintain respective sets of identifiers of neighbor computers in the cluster for each of multiple named resource. A combination of the respective sets of identifiers define a respective tree formed by the respective sets of identifiers for a respective named resource in the set of named resources. Upon origination and detection of a request at a given computer in the cluster, a given computer forwards the request from the given computer over a network to successive computers in the hierarchical tree leading to the computers relevant in handling the request based on use of identifiers of neighbor computers. Thus, a combination of identifiers of neighbor computers identify potential paths to related computers in the tree.

Abstract: Multiple computers in a cluster maintain respective sets of identifiers of neighbor computers in the cluster for each of multiple named resource. A combination of the respective sets of identifiers define a respective tree formed by the respective sets of identifiers for a respective named resource in the set of named resources. Upon origination and detection of a request at a given computer in the cluster, a given computer forwards the request from the given computer over a network to successive computers in the hierarchical tree leading to the computers relevant in handling the request based on use of identifiers of neighbor computers. Thus, a combination of identifiers of neighbor computers identify potential paths to related computers in the tree.

Abstract: A file storage system can include a file manager that adaptively partitions memory to accommodate the storage of fragmented data information. The fragments, potentially of varying size, can be stored in a volume of memory that is partitioned to include a group of storage segments. In the event that a particular fragment is not sized to efficiently fit in a free storage segment, the segment can be further subdivided to accommodate a fragment. In this way, a segment allotted for storage of data information can be adaptively subdivided into a smaller group of storage sub-segments. These sub-segments and yet potentially smaller storage partitions of the sub-segments can then be used to store additional fragments of a related stream of data. Based on this technique, portions of a logical stream of data information can be stored in the segments that vary in size. Meta data associated with the stored fragments can be used to facilitate reconstruction of a file or data stream.

Abstract: Each of multiple computers in a cluster of computers negotiates access to locations in a common storage system. Each of the computers (coupled together via a network) in the cluster includes a transaction manager application to coordinate access to shared storage locations (such as a volume or portions thereof) in the storage system. The transaction managers at each of the multiple computers utilize a unified address space that maps locations in the storage system to corresponding access properties maintained by respective transaction managers in the computers. The access properties derived from use of the unified address space indicate an access status of the regions or locations in the shared storage system. If necessary, the computers in a cluster communicate with each other to negotiate access to the shared storage. Also, the computers in a cluster communicate so that current access properties maintained in each computer are consistent.

Abstract: Multiple computers in a cluster maintain respective sets of identifiers of neighbor computers in the cluster for each of multiple named resource. A combination of the respective sets of identifiers define a respective tree formed by the respective sets of identifiers for a respective named resource in the set of named resources. Upon origination and detection of a request at a given computer in the cluster, a given computer forwards the request from the given computer over a network to successive computers in the hierarchical tree leading to the computers relevant in handling the request based on use of identifiers of neighbor computers. Thus, a combination of identifiers of neighbor computers identify potential paths to related computers in the tree.

Abstract: A given computer in a cluster communicates with multiple computers in the cluster i) via use of a network supporting communications from the multiple computers amongst each other, and ii) through accesses to the shared storage system to which each of the computers in the cluster have access. Each computer in the cluster i) supports communications over a network connection to the other computers and ii) includes a link (e.g., a fiber channel) directly to the shared storage system. Thus, if one communication path fails such as the network path, the other communication path such as the independent link to the shared storage supporting the ability to read/write to storage provides a backup means of communicating. Attributes associated with a cluster can therefore be properly maintained via the members even during a failure.

Abstract: Multiple computers have access to a shared storage system. The computers negotiate with each other for access rights (e.g., READ or WRITE) to regions of the storage system. After negotiating for permission to modify a location (e.g., a range of addresses) of the shared storage system, a given computer copies data from the shared storage system into its own corresponding cache. The given computer granted the permission then modifies the data in its cache while maintaining a separate journal of corresponding changes to metadata. The given computer writes the journal to a dedicated region of the storage system. Thereafter, the given computer attempts to flush contents of the modified cache to the storage system. If the given computer crashes while attempting to flush the modified cache to the shared storage system, a healthy one of the multiple computers utilizes the journal information in the storage system to recover metadata.

Abstract: Methods facilitating management of shared volumes of logical storage, residing on one or more disks in a shared storage system, are accessible by multiple computers. A coherent view of the shared storage is provided by assigning unique identifiers to each managed disk, physical partition, partition set, and volume; and by describing a volume as a logical tree of partitions; when computer needs to modify a volume configuration it temporarily disables all computers' access to the modified shared disks and performs the changes. Efficient shared volume input/output handling is provided by minimizing number of requests directed toward each storage unit using page aligned buffers and transfer offsets. Per computer and per user access control is provided by storing a security descriptor for each shared volume, when user or computer access has to be enforced the security identifier of the user or machine is checked against the security descriptor for needed rights.