Patent application number | Description | Published |
20110273982 | DEDUPLICATED DATA PROCESSING CONGESTION CONTROL - Various embodiments for deduplicated data processing congestion control in a computing environment are provided. In one such embodiment, a single congestion metric is determined from a sampling of a plurality of combined deduplicated data processing congestion statistics in a number of active deduplicated data processes. The congestion limit is calculated from a comparison of the single congestion metric to a congestion target setpoint, the congestion target setpoint being a virtual dimension setpoint and the congestion limit being a manipulated variable. The number of active deduplicated data processes is compared to the congestion limit. If the number of active deduplicated data processes is less than the congestion limit, a new deduplicated data process is spawned. | 11-10-2011 |
20120131038 | FACILITATION OF SEARCH, LIST, AND RETRIEVAL OPERATIONS ON PERSISTENT DATA SET USING DISTRIBUTED SHARED MEMORY - Various embodiments for facilitating search, list and retrieval operations on a persistent data set using a distributed shared memory (DSM) by a processor device are provided. In one exemplary embodiment, a DSM is used to store the data structures in a cluster shared memory, such that updates, deletions and insertions are applied to both the persistent data set and the DSM, and search, list and retrieval operations are processed directly from the DSM. A data structure in the persistent data set is stored in two separate DSM pages: a first page includes an identifying search key of the data structure, the search key also pointing to a location of the data structure in the storage. A second page includes the updatable properties of the data structure. A DSM storing the data structures' pages is organized as a two-row matrix. | 05-24-2012 |
20120143832 | DYNAMIC REWRITE OF FILES WITHIN DEDUPLICATION SYSTEM - Various embodiments for rewriting data in a deduplication storage environment by a processor device are provided. A dynamic layer above a sequential deduplication file system (denoted as DFS) implements the rewrite functionality. A user file is composed of one or more DFS files. As incoming data is written into a user file, the data is written by the dynamic layer sequentially into DFS files, created one by one. For each user file this dynamic layer creates and maintains a dynamic metadata file, in a regular, non deduplicated file system. This metadata file contains entries pointing to sections of DFS files. | 06-07-2012 |
20120144135 | REDUCTION OF COMMUNICATION AND EFFICIENT FAILOVER PROCESSING IN DISTRIBUTED SHARED MEMORY-BASED APPLICATION - Various embodiments for reducing communication between cluster nodes and optimizing failover processing in a distributed shared memory (DSM)-based application by at least one processor device are provided. In one embodiment, for a data structure operable on a DSM, a read-mostly portion is maintained in a single copy sharable between the cluster nodes while an updatable portion is maintained in multiple copies, each of the multiple copies dedicated to a single cluster node. | 06-07-2012 |
20120144149 | CAPACITY MANAGEMENT IN DEDUPLICATION STORAGE SYSTEMS - Various embodiments for capacity management in a deduplication computing storage environment by a processor device are provided. A deduplication storage capacity is estimated as a function of an expected deduplication ratio, the expected deduplication ratio being a combined average of a current deduplication ratio and a configured deduplication ratio, the current deduplication ratio depending on the data currently stored in the deduplication storage, and the configured deduplication ratio being an estimate made at a configuration stage of the deduplication computing storage environment. | 06-07-2012 |
20120239633 | DYNAMIC REWRITE OF FILES WITHIN DEDUPLICATION SYSTEM - A dynamic layer above a sequential deduplication file system (denoted as DFS) implements the rewrite functionality. A user file is composed of one or more DFS files. As incoming data is written into a user file, the data is written by the dynamic layer sequentially into DFS files, created one by one. For each user file this dynamic layer creates and maintains a dynamic metadata file, in a regular, non deduplicated file system. This metadata file contains entries pointing to sections of DFS files. | 09-20-2012 |
20120239687 | FACILITATION OF SEARCH, LIST, AND RETRIEVAL OPERATIONS ON PERSISTENT DATA SET USING DISTRIBUTED SHARED MEMORY - In one exemplary embodiment, a DSM is used to store the data structures in a cluster shared memory, such that updates, deletions and insertions are applied to both the persistent data set and the DSM, and search, list and retrieval operations are processed directly from the DSM. A data structure in the persistent data set is stored in two separate DSM pages: a first page includes an identifying search key of the data structure, the search key also pointing to a location of the data structure in the storage. A second page includes the updatable properties of the data structure. A DSM storing the data structures' pages is organized as a two-row matrix. | 09-20-2012 |
20120246428 | REDUCTION OF COMMUNICATION AND EFFICIENT FAILOVER PROCESSING IN DISTRIBUTED SHARED MEMORY-BASED APPLICATION - Various embodiments for reducing communication between cluster nodes and optimizing failover processing in a distributed shared memory (DSM)-based application by at least one processor device are provided. In one embodiment, for a data structure operable on a DSM, a read-mostly portion is maintained in a single copy sharable between the cluster nodes while an updatable portion is maintained in multiple copies, each of the multiple copies dedicated to a single cluster node. | 09-27-2012 |
20120246438 | CAPACITY MANAGEMENT IN DEDUPLICATION STORAGE SYSTEMS - A deduplication storage capacity is estimated as a function of an expected deduplication ratio, the expected deduplication ratio being a combined average of a current deduplication ratio and a configured deduplication ratio, the current deduplication ratio depending on the data currently stored in the deduplication storage, and the configured deduplication ratio being an estimate made at a configuration stage of the deduplication computing storage environment. | 09-27-2012 |
20130080409 | DEDUPLICATED DATA PROCESSING CONGESTION CONTROL - Various embodiments for deduplicated data processing congestion control in a computing environment are provided. In one such embodiment, a congestion target setpoint is calculated using one of a proportional constant, an integral constant, and a derivative constant, wherein the congestion target setpoint is a virtual dimension setpoint. A single congestion metric is determined from a sampling of a plurality of combined deduplicated data processing congestion statistics in a number of active deduplicated data processes. A congestion limit is calculated from a comparison of the single congestion metric to the congestion target setpoint, the congestion limit being a manipulated variable. The congestion limit is compared to the number of active deduplicated data processes. If the number of active deduplicated data processes are less than the congestion limit, a new deduplicated data process of the number of active deduplicated data processes is spawned. | 03-28-2013 |
20130218850 | DYNAMIC REWRITE OF FILES WITHIN DEDUPLICATION SYSTEM - An original deduplication file system (DFS) file is partitioned into a first set of sections being sections including data affected by rewrite operations and a second set of sections being sections including data unaffected by rewrite operations. A new DFS file to be stored as part of a plurality of user files is created, the plurality of user files including the original DFS file and being accessible by a sequential DFS and a dynamic non-DFS, the dynamic non-DFS including a plurality of dynamic metadata files having entries pointing to corresponding sections of the original DFS files. The first set of sections of the original DFS file including data affected by rewrite operations is directly written into the new DFS file. The second set of sections from the original DFS file including data unaffected by rewrite operations is quoted into the new DFS file. The original DFS file is deleted. | 08-22-2013 |
20130232379 | RESTORING DISTRIBUTED SHARED MEMORY DATA CONSISTENCY WITHIN A RECOVERY PROCESS FROM A CLUSTER NODE FAILURE - A set of data structures are stored in a distributed shared memory (DSM) component and in persistent storage. The DSM component is organized as a matrix of page. The data structure of the set of data structures occupies a column in the matrix of pages. A recovery file is maintained in the persistent storage. The recovery file consists of entries and each one of the entries corresponds to a column in the matrix of pages by a location of each one of the entries. | 09-05-2013 |
20130325902 | PERSISTENT ITERATION OVER A DATABASE TREE STRUCTURE - Persistent iteration is performed in stages on nodes arranged according to a node identification (ID) that is increasing in order under a parent node in database tree structure. While performing the persistent iteration, storing a start node ID of the node where the persistent iteration commenced, a current node ID of the node that is undergoing the persistent iteration, a parent node ID of the node that is undergoing the persistent iteration, and a numerical value representing the current level and all levels greater than the current level of nodes that are undergoing the persistent iteration. Upon completion of the persistent iteration on the nodes that are the children of the node with the parent node ID, returning to the first node among the children of the node with the parent node ID, as ordered by increasing node ID, and performing the persistent iteration for children nodes of each node. | 12-05-2013 |
20130326176 | MANAGEMENT OF MULTIPLE CAPACITY TYPES IN STORAGE SYSTEMS - A management of capacity types with different consumption policies for an object in a computing storage system is performed by updating a reference type bitmap in a segment-fragment table containing segments that reference fragments upon the creation of a segment for an object. A reference is created in an object-segment reference table, between the object and the segment, in compliance with a consumption policy upon the creation of one of the segments for the object. The reference types that reference the segment are removed upon deletion of the segment. | 12-05-2013 |
20140006735 | SPACE RESERVATION IN A DEDUPLICATION SYSTEM | 01-02-2014 |
20140304476 | MAINTAINING CACHE CONSISTENCY IN A CACHE FOR CACHE EVICTION POLICIES SUPPORTING DEPENDENCIES - For maintaining consistency for a cache that contains dependent objects in a computing environment, object dependencies for cached objects are managed by defining and maintaining object dependency lists for each one of the cached objects for identifying objects upon which the cached objects are dependent. Maintaining cache consistency for 2 types of cache eviction policies is supported by maintaining an object dependency lists for each one of the cached objects for identifying objects dependent upon the cached object. Each of the objects in an object dependency list is updated when the object is updated. | 10-09-2014 |