Granted Patent B2

US 8,719,235 · App. 13/373,984 · Granted May 6, 2014

Abstract

Claims (39)

1. A non-transitory computer-readable medium storing computer-executable instructions that when executed by a computer control the computer to perform a method, the method comprising:

accessing a de-duplication data set, where the de-duplication data set includes a set of sub-blocks produced by a de-duplication process, an index produced by the de-duplication process, where the index stores index entries related to members of the set of sub-blocks, and re-creation information produced by the de-duplication process, where the re-creation information stores data for re-creating a larger data block from two or more sub-blocks in the set of sub-blocks;

identifying a de-duplication attribute associated with the de-duplication data set; determining a tape-specific layout for at least a portion of the de-duplication data set based, at least in part, on the de-duplication attribute and on a buffer scheme associated with a de-duplication apparatus that will access the de-duplication data set; and

controlling a tape drive to write at least a portion of the de-duplication data set to a first tape according to the tape-specific layout.

2. The computer-readable medium of claim 1 , where the set of sub-blocks has been parsed into sub-blocks by the de-duplication process but has not had duplicate sub-blocks removed.

3. The computer-readable medium of claim 1 , where the set of sub-blocks has had at least one duplicate removed by the de-duplication process.

4. The computer-readable medium of claim 1 , where accessing the de-duplication data set comprises controlling a tape drive to read the de-duplication data set from a second tape.

5. The computer-readable medium of claim 1 , where the de-duplication attribute is related to one or more of, a sub-block reference count, a sub-block access order, a sub-block access frequency, a sub-block access group relationship, a sub-block basis/delta relationship, a sub-block accessing entity identity, an indexing parameter, and a re-creation information parameter.

6. The computer-readable medium of claim 1 , where accessing the de-duplication data set comprises ingesting the set of sub-blocks into a temporary de-duplication work area, where the temporary de-duplication work area is located in random access memory associated with the computer executing the method, and where the size of the temporary de-duplication work area is less than the size of the first tape.

7. The computer-readable medium of claim 6 , where identifying the de-duplication attribute is performed by analyzing the set of sub-blocks in the temporary de-duplication work area.

8. The computer-readable medium of claim 7 , where the set of sub-blocks are analyzed in the temporary de-duplication work area before sub-blocks are written to the first tape according to the tape-specific layout.

9. The computer-readable medium of claim 1 , where identifying the de-duplication attribute is performed as part of one or more of, a pre-de-duplication of the set of sub-blocks, a partial de-duplication of the set of sub-blocks, a re-de-duplication of the set of sub-blocks, and a complete de-duplication of the set of sub-blocks.

10. The computer-readable medium of claim 9 , where one or more of, the pre-de-duplication of the set of sub-blocks, the partial de-duplication of the set of sub-blocks, the re-de-duplication of the set of sub-blocks, and the complete de-duplication of the set of sub-blocks is performed on replicated data.

11. The computer-readable medium of claim 1 , where the tape-specific layout identifies one or more of, a sub-block order on the tape, a number of sub-block partitions on the tape, a location for a sub-block partition on the tape, a number of index partitions on the tape, a location for an index partition on the tape, a number of re-creation information partitions on the tape, and a location for an information partition on the tape.

12. The computer-readable medium of claim 1 , where the tape-specific layout includes at least one logical partition sized as a function of the amount of random access memory available to the de-duplication apparatus and as a function of a buffering scheme employed by the de-duplication apparatus.

13. The computer-readable medium of claim 1 , where the tape-specific layout includes at least one logical partition sized as a function of the amount of disk space available to the de-duplication apparatus and as a function of a buffering scheme employed by the de-duplication apparatus.

14. The computer-readable medium of claim 1 , where determining the tape-specific layout comprises partitioning a portion of the index into at least two indexes and determining different locations on the tape for the at least two indexes.

15. The computer-readable medium of claim 1 , where determining the tape-specific layout comprises partitioning a portion of the re-creation information into at least two portions of re-creation information and determining different locations on the tape for the at least two portions of re-creation information.

16. The computer-readable medium of claim 1 , where determining the tape-specific layout comprises partitioning the set of sub-blocks into at least two subsets of sub-blocks and determining different locations on the tape for the at least two subsets of sub-blocks.

17. The computer-readable medium of claim 1 , where determining the tape-specific layout comprises partitioning a portion of the index into at least two indexes and determining different locations on the tape for the at least two indexes, partitioning a portion of the re-creation information into at least two portions of re-creation information and determining different locations on the tape for the at least two portions of re-creation information, and partitioning the set of sub-blocks into at least two subsets of sub-blocks and determining different locations on the tape for the at least two subsets of sub-blocks.

18. The computer-readable medium of claim of claim 14 , comprising re-indexing sub-blocks in the set of sub-blocks as a function of the at least two indexes.

19. The computer-readable medium of claim 18 , where an index entry in one of the at least two indexes is smaller than an index entry in the index.

20. The computer-readable medium of claim 1 ,

where the de-duplication data set comprises a portion of a first logical partition of a previous de-duplication data set previously written to a previous tape according to a previous tape-specific layout and a portion of a second logical partition of the previous de-duplication data set written to the previous tape according to the previous tape-specific layout.

21. The computer-readable medium of claim 1 , the method comprising writing information about the tape-specific layout to the tape.

22. An apparatus, comprising:

a processor;

a memory;

a set of logics; and

an interface to connect the processor, the memory, and the set of logics, the set of logics comprising:

a tape layout logic configured to determine a tape-specific layout for a de-duplication data set based on forensic data acquired for the de-duplication data set, where the de-duplication data set includes a set of sub-blocks produced by a de-duplication process, an index produced by the de-duplication process, where the index stores index entries related to members of the set of sub-blocks, and re-creation information produced by the de-duplication process, and where the re-creation information stores data for re-creating a larger data block from two or more sub-blocks in the set of sub-blocks, and

where determining the tape specific layout includes identifying a de-duplication attribute associated with the de-duplication data set and determining the tape-specific layout for at least a portion of the de-duplication data set based, at least in part, on the de-duplication attribute and on a buffer scheme associated with a de-duplication apparatus that will access the de-duplication data set; and

a write logic configured to write the de-duplication data set to a tape according to the tape-specific layout.

23. The apparatus of claim 22 , where the tape layout logic is configured to determine the tape-specific layout based on one or more of, observed de-duplication operation data, tape capacity, tape configuration, tape drive operating parameters, and observed de-duplication processing parameters.

24. The apparatus of claim 23 , where the observed de-duplication operation data identifies one or more of, a sub-block reference count, a sub-block access order, a sub-block access frequency, a sub-block access group relationship, a sub-block basis/delta relationship, a sub-block accessing entity identity, an indexing parameter, and a re-creation information parameter.

25. The apparatus of claim 23 , where the observed de-duplication processing parameters include one or more of, a de-duplication pre-fetch scheme, a de-duplication buffering scheme, and a de-duplication apparatus buffering capacity.

26. The apparatus of claim 22 , where the tape-specific layout controls one or more of, a number of index partitions on the tape, a location of an index partition on the tape, a number of re-creation information partitions on the tape, a location of a re-creation information partition on the tape, a number of sub-block groups on the tape, a location of a sub-block group on the tape, and an order of sub-blocks on the tape.

27. The apparatus of claim 22 , where the write logic is configured to write information about the tape-specific layout to the tape.

28. The apparatus of claim 22 , where the tape layout logic is configured to position portions of the de-duplication data set in the memory and to control the processor to generate the forensic data in response to analyzing the de-duplication data set in the memory as the de-duplication data set is at least partially de-duplicated in place.

Assignments (13)