Abstract: A method of reading data from a partitioned directory incident to a serialized process. A first read and an offset value are received. A first data block in a modeled fully partitioned directory is identified based on the offset value and a predetermined number of entries associated with a buffer. It is determined whether the first data block in the fully partitioned directory is present in the actual partitioned directory. Zeros are written in the buffer if the first data block in the fully partitioned directory is not present in the actual partitioned directory otherwise the first data block associated with the actual partitioned directory is written to the buffer. A second data block is similarly read by a second read operation and written. The second data block is associated with a second subdirectory, selected based on a horizontal node traversal at a node level of said first subdirectory.

Abstract: A method, in one embodiment, can include determining whether an administrative task for a file system is to be performed within a thin storage memory array. Furthermore, if the administrative task for the file system is to be performed, a determination is made as to whether memory space is freed up while performing the administrative task. If memory space is freed up while performing the administrative task, a determination is made as to whether the freed up memory space satisfies a predefined contiguous memory space threshold. If the predefined contiguous memory space threshold is satisfied by the freed up memory space, a determination is made as to whether a memory space reclamation process is to be performed. If the memory space reclamation process is to be performed, the freed up memory space is reclaimed from the file system.

Abstract: A method of maintaining and providing information relating to file deduplication. A first portion of a first file and a second portion of a second file that contain a first content are identified. A first header associated with the first portion is created. The first header identifies the first portion and the second portion containing the first content. The first header is appended to a storage location of the first content of the first portion to form a first data structure for the first file. The first data structure is stored. The first data structure is provided to an application requesting the first file so that duplicate data processing can be avoided by the application. The first data structure is updated when the first file or the second file are altered. A similar process may occur to generate a data structure for the second file.

Abstract: A method for identifying data for relocation in a multivolume file system. The method includes generating a file location map, the file location map containing a list of the locations of files that occupy space on each of a plurality of volumes of the file system, wherein The file system comprising least a first volume and a second volume. The method further includes updating the file location map in accordance with changes in a file change log for the file system, and identifying data residing on the first volume of the file system by scanning the file location map. Using the identified data, a ratio of per-file activity during a first time period relative to overall file system activity over a second time period is calculated to derive a file activity ratio for each of the files of the identified data. Files are then selected for relocation based on the file activity ratio.

Abstract: A plurality of data objects may be replicated across a plurality of computing nodes coupled to a network. The network may include a first node operable to initiate an update operation to update a plurality of replicas of a first object. If one or more of the replicas are not reachable then the update operation may update a subset (e.g., a quorum) but not all of the replicas. For each node on which one of the replicas was updated in the update operation, the node may add the object to a list of incoherent objects. The list of incoherent objects may subsequently be used to bring the lagging replicas in sync with the replicas that were updated. In another embodiment, a plurality of replicas of an object may be stored on a plurality of nodes, similarly as described above. A first node that stores a replica of the object may store a first timestamp associated with the replica on the first node.

Abstract: A system for fault tolerant multi-stage data replication with relaxed coherency comprises one or more processors and memory coupled to the processors, where the memory stores program instructions executable by the processors to implement a data replication service. In response to an update request directed at a data object, in a first stage of replication, the data replication service is configured to update respective primary replicas at a plurality of primary replica sites for the data object, and to store metadata descriptors at each of the plurality of primary replica sites. The data replication service is configured to determine whether a notification of the update is to be sent to any other replica sites. In response to identifying such other replica sites, an update notification including contents of a metadata descriptor may be sent to the other replica sites in one or more additional replication stages.

Abstract: A method for information flow tracking is provided using, for example, a functional programming language based on lambda calculus, ?I. The method provides a unified information-tracking framework that supports multiple, interdependent dimensions of information. An expressive policy-specification system is separated from the underlying information-flow tracking mechanism. Arbitrary domain-specific policies are supported that can be developed and enforced independent of information flow tracking. Information-flow metadata is treated as a first-class entity, and information flow is correctly tracked on the metadata itself. Classes of information flow polices are defined using multiple dimensions that are application to both information flow data and to the information flows themselves. These classes of polices accurately model more realistic security policies, based on partial trust relations.

Abstract: A plurality of data objects may be replicated across a plurality of computing nodes coupled to a network. The network may include a first node operable to initiate an update operation to update a plurality of replicas of a first object. If one or more of the replicas are not reachable then the update operation may update a subset (e.g., a quorum) but not all of the replicas. For each node on which one of the replicas was updated in the update operation, the node may add the object to a list of incoherent objects. The list of incoherent objects may subsequently be used to bring the lagging replicas in sync with the replicas that were updated. In another embodiment, a plurality of replicas of an object may be stored on a plurality of nodes, similarly as described above. A first node that stores a replica of the object may store a first timestamp associated with the replica on the first node.

Abstract: An efficient distributed transaction protocol for a distributed file sharing system is described. One embodiment of the protocol involves a transaction coordinator node sending three messages to participant nodes, where the participant nodes reply to only two of those messages. In one embodiment, the transaction coordinator node may return success to the client application after receiving replies to the second message from the participant nodes. The protocol may provide benefits associated with traditional three-phase commit (3PC) protocols while also decreasing response time latencies experienced by client applications and decreasing network traffic.

Abstract: A system and method for pre-allocating replicas for a distributed file sharing system. Creating a new file may involve creating a plurality of replicas for the file on a plurality of nodes. In one embodiment nodes in the system may pre-allocate sets of file replicas, where the pre-allocated replicas can be used to satisfy requests to create new files. Pre-allocating the file replicas may decrease the latency of file creation requests by enabling the requests to be satisfied without performing replica allocation in response to the requests.

Abstract: A system and method is disclosed for optimization of master planning problems. The system provides for accessing supply chain data describing the flow of one or more items through the supply chain network and accessing constraints and a planning problem associated with one or more entities associated with the supply chain network. The system further provides for modeling a planning problem for a planning horizon based on at least a portion of the accessed supply chain data and the constraints. The system still further provides for decomposing the planning horizon into multiple sub-horizons and optimizing the planning problem for each of the multiple sub-horizons. The system yet further provides for generating an optimal supply chain plan for the planning problem, based on the optimization of the multiple sub-horizons.

Abstract: A system and method is disclosed for optimizing supply chain planning problems associated with a supply chain network. The system includes a supply chain planner coupled with one or more supply chain entities. The supply chain planner determines a supply chain plan for managing the flow of one or more items through the supply chain network.