摘要:
A method, a system, and a computer-implemented method for performing multi-level deduplication of data are disclosed. A zone stamp is generated for each zone in a plurality of zones contained in at least one data stream. The zone stamp is compared to another zone stamp. The zone stamp and another zone stamp represent zones in the plurality of zones. The comparison is performed for zones at corresponding zone levels based on a determination that a zone stamp of a zone of a preceding zone level is not similar to another zone stamp of another preceding zone level. The zone at the preceding zone level includes at least one zone of a next zone level having a size smaller than or equal to a size of the zone of the preceding zone level. The zone and another zone are deduplicated based on a determination that the zone stamp is similar to another zone stamp.
摘要:
A method, a system, and a computer-implemented method for performing multi-level deduplication of data are disclosed. A zone stamp is generated for each zone in a plurality of zones contained in at least one data stream. The zone stamp is compared to another zone stamp. The zone stamp and another zone stamp represent zones in the plurality of zones. The comparison is performed for zones at corresponding zone levels based on a determination that a zone stamp of a zone of a preceding zone level is not similar to another zone stamp of another preceding zone level. The zone at the preceding zone level includes at least one zone of a next zone level having a size smaller than or equal to a size of the zone of the preceding zone level. The zone and another zone are deduplicated based on a determination that the zone stamp is similar to another zone stamp.
摘要:
A system, a method, and a computer program product for performing deduplication of data using a scalable deduplication grid are disclosed. A listing of a plurality of zone stamps is generated, where each zone stamp represents a zone in the plurality of zones in a data stream. The listing contains a logical arrangement of the plurality of zone stamps obtained from each storage location and being accessible by a plurality of servers. A first zone stamp in the listing is compared to a second zone stamp in the listing. The first and second zones are delta-compressed based on a determination that the first zone stamp is substantially similar to the second zone stamp. A server is selected to perform the comparison and delta-compression.
摘要:
A system, a method, and a computer program product for performing deduplication of data using a scalable deduplication grid are disclosed. A listing of a plurality of zone stamps is generated, where each zone stamp represents a zone in the plurality of zones in a data stream. The listing contains a logical arrangement of the plurality of zone stamps obtained from each storage location and being accessible by a plurality of servers. A first zone stamp in the listing is compared to a second zone stamp in the listing. The first and second zones are delta-compressed based on a determination that the first zone stamp is substantially similar to the second zone stamp. A server is selected to perform the comparison and delta-compression.
摘要:
A system, a method, and a computer program product for adaptive scheduled periodic caching are disclosed. A data stream is received. The data stream contains a plurality of versions of data arranged in a plurality of data clusters. Each data cluster includes an anchor version having a plurality of versions of data dependent on the anchor version. A size of each anchor version of each data cluster is determined. A number of versions of data dependent on each anchor version is also determined. For each anchor version, a ratio of the determined number of dependent versions of data to the determined size of each anchor is computed. At least one anchor version for storing in a memory location is selected based on the computed ratio.
摘要:
A system, a method, and a computer program product for adaptive scheduled periodic caching are disclosed. A data stream is received. The data stream contains a plurality of versions of data arranged in a plurality of data clusters. Each data cluster includes an anchor version having a plurality of versions of data dependent on the anchor version. A size of each anchor version of each data cluster is determined. A number of versions of data dependent on each anchor version is also determined. For each anchor version, a ratio of the determined number of dependent versions of data to the determined size of each anchor is computed. At least one anchor version for storing in a memory location is selected based on the computed ratio.
摘要:
Embodiments of this invention provide primary magnetic disk data storage capacity to clients while at the same time making sure that client data is replicated locally and at an offsite location to protect from all forms of data loss.
摘要:
The present invention provides systems and methods for transferring a set of files. Metadata and stub files associated with the set of files are received at a destination fileserver, a location component in the destination fileserver is updated to maintain a list of repository nodes associated with each file in the set of files, and each stub file is replaced with the full content of the file associated with the stub file. The replacing includes receiving a client request for a specified file in the set of files and replacing the stub file associated with the specified file with a full content of the specified file if the full content of the specified file has not yet been transferred. Replacing the stub file associated with a requested file is a higher priority task than replacing a stub file associated with a non-requested file.
摘要:
The present invention relates to a computer primary data storage system that integrates the functionality of file backup and remote replication to provide an integrated storage system.
摘要:
The present invention relates to a computer primary data storage system that integrates the functionality of file backup and remote replication to provide an integrated storage system that protects its data from loss related to system or network failures or the physical loss of a data center.