Point in time copy technique using a block level of granularity
First Claim
Patent Images
1. A method, comprising:
- identifying, utilizing a processor, an index node for a file, the index node including a data structure that stores a plurality of data block addresses that are numbered relative to each other, where the data block addresses indicate data blocks within a storage medium that contain data comprising the file;
translating, utilizing the processor, the data block addresses identified by the index node to locations of one or more physical tracks on which the data blocks are located, where each of the one or more physical tracks includes an entire physical band of data located on the storage medium that includes one or more of the data blocks that contain the data comprising the file, where the translating includes;
determining the data block addresses identified by the index node for the file,converting the data block addresses to the locations of the one or more physical tracks, utilizing a modulus operation that includes evaluating B mod A for each of the data block addresses B for the file, where each of the one or more physical tracks includes a fixed number of data blocks A,storing the locations of the one or more physical tracks in a track map for the file that maps the data block addresses for the file to the locations of the one or more physical tracks, andremoving locations of duplicate physical tracks from the track map for the file, such that only a single instance of a duplicated physical track is stored within the track map for the file; and
performing, utilizing the processor, a point in time copy of the file utilizing the locations of the physical tracks stored within the track map for the file.
1 Assignment
0 Petitions
Accused Products
Abstract
A method is provided for performing a point in time copy using a block level of granularity. The method includes identifying an index node for a file, and translating data block locations identified by the index node to physical track locations. Further, the method includes performing a point in time copy utilizing the physical track locations.
-
Citations
17 Claims
-
1. A method, comprising:
-
identifying, utilizing a processor, an index node for a file, the index node including a data structure that stores a plurality of data block addresses that are numbered relative to each other, where the data block addresses indicate data blocks within a storage medium that contain data comprising the file; translating, utilizing the processor, the data block addresses identified by the index node to locations of one or more physical tracks on which the data blocks are located, where each of the one or more physical tracks includes an entire physical band of data located on the storage medium that includes one or more of the data blocks that contain the data comprising the file, where the translating includes; determining the data block addresses identified by the index node for the file, converting the data block addresses to the locations of the one or more physical tracks, utilizing a modulus operation that includes evaluating B mod A for each of the data block addresses B for the file, where each of the one or more physical tracks includes a fixed number of data blocks A, storing the locations of the one or more physical tracks in a track map for the file that maps the data block addresses for the file to the locations of the one or more physical tracks, and removing locations of duplicate physical tracks from the track map for the file, such that only a single instance of a duplicated physical track is stored within the track map for the file; and performing, utilizing the processor, a point in time copy of the file utilizing the locations of the physical tracks stored within the track map for the file. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A computer program product for performing a point in time copy using a block level of granularity, the computer program product comprising a computer readable storage medium that is not a transitory signal per se, the computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
-
identify an index node for a file, the index node including a data structure that stores a plurality of data block addresses that are numbered relative to each other, where the data block addresses indicate data blocks within a storage medium that contain data comprising the file; translate the data block addresses identified by the index node to locations of one or more physical tracks on which the data blocks are located, where each of the one or more physical tracks includes an entire physical band of data located on the storage medium that includes one or more of the data blocks that contain the data comprising the file, where the translating includes; determining the data block addresses identified by the index node for the file, converting the data block addresses to the locations of the one or more physical tracks, utilizing a modulus operation that includes evaluating B mod A for each of the data block addresses B for the file, where each of the one or more physical tracks includes a fixed number of data blocks A, storing the locations of the one or more physical tracks in a track map for the file that maps the data block addresses for the file to the locations of the one or more physical tracks, and removing locations of duplicate physical tracks from the track map for the file, such that only a single instance of a duplicated physical track is stored within the track map for the file; and perform a point in time copy of the file utilizing the locations of the physical tracks stored within the track map for the file. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A system, comprising:
-
a processor; and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to cause the processor to; identify an index node for a file, the index node including a data structure that stores a plurality of data block addresses that are numbered relative to each other, where the data block addresses indicate data blocks within a storage medium that contain data comprising the file; translate the data block addresses identified by the index node to locations of one or more physical tracks on which the data blocks are located, where each of the one or more physical tracks includes an entire physical band of data located on the storage medium that includes one or more of the data blocks that contain the data comprising the file, where the translating includes; determining the data block addresses identified by the index node for the file, converting the data block addresses to the locations of the one or more physical tracks, utilizing a modulus operation that includes evaluating B mod A for each of the data block addresses B for the file, where each of the one or more physical tracks includes a fixed number of data blocks A, storing the locations of the one or more physical tracks in a track map for the file that maps the data block addresses for the file to the locations of the one or more physical tracks, and removing locations of duplicate physical tracks from the track map for the file, such that only a single instance of a duplicated physical track is stored within the track map for the file; and perform a point in time copy of the file utilizing the locations of the physical tracks stored within the track map for the file. - View Dependent Claims (16, 17)
-
Specification