Abstract: Techniques and mechanisms are provided to instantly clone active files including active optimized files. When a new instance of an active file is created, a new stub is generated in the user namespace and a block map file is cloned. The block map file includes the same offsets and location pointers that existed in the original block map file. No user file data needs to be copied. If the cloned file is later modified, the behavior can be same as what happens when a de-duplicated file is modified.

Abstract: Mechanisms are provided for performing network efficient deduplication. Segments are extracted from files received for deduplication at a host connected to a target over one or more networks and/or fabrics in a deduplication system. Segment identifiers (IDs) are determined and compared with segment IDs for segments already deduplicated. Segments already deduplicated need not be transmitted to a target system. References and reference counts are modified at a target system. Updating references and reference counts may involve modifying filemaps, dictionaries, and datastore suitcases for both already deduplicated and not already deduplicated segments.

Abstract: Mechanisms are provided for accelerated data deduplication. A data stream is received an input interface and maintained in memory. Chunk boundaries are detected and chunk fingerprints are calculated using a deduplication accelerator while a processor maintains a state machine. A deduplication dictionary is accessed using a chunk fingerprint to determine if the associated data chunk has previously been written to persistent memory. If the data chunk has previously been written, reference counts may be updated but the data chunk need not be stored again. Otherwise, datastore suitcases, filemaps, and the deduplication dictionary may be updated to reflect storage of the data chunk. Direct memory access (DMA) addresses are provided to directly transfer a chunk to an output interface as needed.

Abstract: Mechanisms are provided for efficiently determining commonality in a deduplicated data set in a scalable manner regardless of the number of deduplicated files or the number of stored segments. Information is generated and maintained during deduplication to allow scalable and efficient determination of data segments shared in a particular file, other files sharing data segments included in a particular file, the number of files sharing a data segment, etc. Data need not be expanded or uncompressed. Deduplication processing can be validated and verified during commonality detection.

Abstract: Techniques and mechanisms are provided to allow for selective optimization, including deduplication and/or compression, of portions of files and data blocks. Data access is monitored to generate a heat index for identifying sections of files and volumes that are frequently and infrequently accessed. These frequently used portions may be left non-optimized to reduce or eliminate optimization I/O overhead. Infrequently accessed portions can be more aggressively optimized.

Abstract: Techniques and mechanisms described herein facilitate the restoration temporal locality in global and local deduplication storage systems. According to various embodiments, when it is determined that cache memory in a storage system has reached a capacity threshold, each of a plurality of data dictionary entries stored in the cache memory may be associated with a respective merge identifier. Each data dictionary entry may correspond with a respective data chunk. Each data dictionary entry may indicate a storage location of the respective data chunk in the storage system. The respective merge identifier may indicate temporal locality information about the respective data chunk. The plurality of data dictionary entries may be stored to disk memory in the storage system. Each of the stored plurality of data dictionary entries may include the respective merge identifier.

Abstract: Mechanisms are provided for accelerated data deduplication. A data stream is received an input interface and maintained in memory. Chunk boundaries are detected and chunk fingerprints are calculated using a deduplication accelerator while a processor maintains a state machine. A deduplication dictionary is accessed using a chunk fingerprint to determine if the associated data chunk has previously been written to persistent memory. If the data chunk has previously been written, reference counts may be updated but the data chunk need not be stored again. Otherwise, datastore suitcases, filemaps, and the deduplication dictionary may be updated to reflect storage of the data chunk. Direct memory access (DMA) addresses are provided to directly transfer a chunk to an output interface as needed.

Abstract: Deduplication dictionaries are used to maintain data chunk identifier and location pairings in a deduplication system. When access to a particular data chunk is requested, a deduplication dictionary is accessed to determine the location of the data chunk and a datastore is accessed to retrieve the data chunk. However, deduplication dictionaries are large and typically maintained on disk, so dictionary access is expensive. Techniques and mechanisms of the present invention allow prefetches or read aheads of datastore (DS) headers. For example, if a dictionary hit results in datastore DS(X), then headers for DS (X+1), DS (X+2), DS(X+read-ahead-window) are prefetched ahead of time. These datastore headers are cached in memory, and indexed by datastore identifier. Before going to the dictionary, a lookup is first performed in the cached headers to reduce deduplication data access request latency.

Abstract: Mechanisms are provided for efficiently determining commonality in a deduplicated data set in a scalable manner regardless of the number of deduplicated files or the number of stored segments. Information is generated and maintained during deduplication to allow scalable and efficient determination of data segments shared in a particular file, other files sharing data segments included in a particular file, the number of files sharing a data segment, etc. Data need not be expanded or uncompressed. Deduplication processing can be validated and verified during commonality detection.

Abstract: Techniques and mechanisms are provided to allow for selective optimization, including deduplication and/or compression, of portions of files and data blocks. Data access is monitored to generate a heat index for identifying sections of files and volumes that are frequently and infrequently accessed. These frequently used portions may be left non-optimized to reduce or eliminate optimization I/O overhead. Infrequently accessed portions can be more aggressively optimized.

Abstract: Techniques and mechanisms are provided to support live file optimization. Active I/O access to an optimization target is monitored during optimization. Active files need not be taken offline or made unavailable to an application during optimization and retain the ability to support file operations such as read, write, unlink, and truncate while an optimization engine performs deduplication and/or compression on active file ranges.

Abstract: Techniques and mechanisms are provided for storing data in a backup storage system. According to various embodiments, a first blockmap in a backup storage system may be identified. The first blockmap may correspond with a first restore point. The first blockmap may identify a first plurality of data segments. Each of the first plurality of data segments may have associated therewith a respective storage location in the backup storage system. The first blockmap may be compared with a designated storage system state to identify a subset of the first plurality of data segments that each correspond with a respective matching data segment in the designated storage system state. A second blockmap may be stored in the backup storage system. The second blockmap may correspond with a second restore point. The second blockmap may include the identified subset of the first plurality of data segments.

Abstract: Mechanisms are provided for adjusting a configuration of data stored in a storage system. According to various embodiments, a storage module may be configured to store a configuration of data. A processor may be configured to identify an estimated performance level for the storage system based on a configuration of data stored on the storage system.

Abstract: Mechanisms are provided for optimizing random access in a storage system. According to various embodiments, an access pattern may be identified for a plurality of data segments stored in a first arrangement on a storage medium. Each of the plurality of data segments may be stored at a respective first storage location on the storage medium in the first arrangement. The access pattern may indicate an order in which the data segments are likely to be retrieved from the storage medium. The plurality of data segments may be stored in a second arrangement on the storage medium based on the identified access pattern. Each of the plurality of data segments may be stored at a respective second storage location on the storage medium in the updated arrangement.

Abstract: Mechanisms are provided for data transfer reduction in scale out architectures. When a compute node receives a write input/output (I/O) request for a data stream, the compute node separates the data stream into chunks and generates fingerprints for the individual chunks. Fingerprints are then sent to a scale out node and compared to fingerprints of chunks already maintained at the scale out node. Write data transfers are only made for chunks not already maintained at the scale out node. For a read I/O request for a data stream, fingerprints for chunks of the data stream are requested by the compute node from a scale out node. Fingerprints received are compared to fingerprints of chunks already maintained at the compute node and read data transfers are only made for chunks not already maintained at the compute node.

Abstract: Deduplication dictionaries are used to maintain data chunk identifier and location pairings in a deduplication system. When access to a particular data chunk is requested, a deduplication dictionary is accessed to determine the location of the data chunk and a datastore is accessed to retrieve the data chunk. However, deduplication dictionaries are large and typically maintained on disk, so dictionary access is expensive. Techniques and mechanisms of the present invention allow prefetches or read aheads of datastore (DS) headers. For example, if a dictionary hit results in datastore DS(X), then headers for DS (X+1), DS (X+2), DS(X+read-ahead-window) are prefetched ahead of time. These datastore headers are cached in memory, and indexed by datastore identifier. Before going to the dictionary, a lookup is first performed in the cached headers to reduce deduplication data access request latency.

Abstract: Techniques and mechanisms are provided to allow for selective optimization, including deduplication and/or compression, of portions of files and data blocks. Data access is monitored to generate a heat index for identifying sections of files and volumes that are frequently and infrequently accessed. These frequently used portions may be left non-optimized to reduce or eliminate optimization I/O overhead. Infrequently accessed portions can be more aggressively optimized.

Abstract: Mechanisms are provided for efficiently detecting segments for deduplication. Data is analyzed to determine file types and file components. File types such as images may have optimal data segment boundaries set at the file boundaries. Other file types such as container files are delayered to extract objects to set optimal data segment boundaries based on file type or based on the boundaries of the individual objects. Storage of unnecessary information is minimized in a deduplication dictionary while allowing for effective deduplication.

Abstract: Mechanisms are provided for accelerated data deduplication. A data stream is received an input interface and maintained in memory. Chunk boundaries are detected and chunk fingerprints are calculated using a deduplication accelerator while a processor maintains a state machine. A deduplication dictionary is accessed using a chunk fingerprint to determine if the associated data chunk has previously been written to persistent memory. If the data chunk has previously been written, reference counts may be updated but the data chunk need not be stored again. Otherwise, datastore suitcases, filemaps, and the deduplication dictionary may be updated to reflect storage of the data chunk. Direct memory access (DMA) addresses are provided to directly transfer a chunk to an output interface as needed.

Abstract: Mechanisms are provided for improving the efficiency of garbage collection in a deduplication system by intelligently managing storage of deduplication segments. When a duplicate segment is identified, a reference count for an already maintained segment is incremented only if the already maintained segment has the same lifecycle as the identified duplicate segment. In some instances, an already maintained segment is assumed to have the same lifecycle if it is not stale or the age is not significantly different from the age of the newly identified duplicate. If the already maintained segment is has a different lifecycle, the new segment is stored again even though duplicates are already maintained.