Efficient content meta-data collection and trace generation from deduplicated storage

• US 8,631,052 B1
• Filed: 12/22/2011
• Issued: 01/14/2014
• Est. Priority Date: 12/22/2011
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Douglis, Frederick, Shilane, Philip, Wallace, Grant
• Primary Examiner(s): MORRISON, JAY A
• Application Number:
  US13/335,746
• Time in Patent Office: 754 Days
• Field of Search: None
• US Class Current: 707/825
• CPC Class Codes: G06F 16/1748 De-duplication implemented within the file system, e.g. based on file segments de-duplication techniques in storage systems for the management of data blocks G06F3/0641

Abstract

The method and apparatus collect file recipes from deduplicated data storage systems, the file recipes consist of a list of fingerprints of data chunks of a file. Detailed meta-data for each unique data chunk is also collected. In an offline process, research and analysis can be performed on either the meta-data itself or on a reconstruction of a full trace of meta-data constructed by matching recipe fingerprints to the corresponding meta-data. The method and system can generate the full meta-data trace efficiently in an on-line or off-line process. Typical deduplicated storage systems achieve 10× or higher deduplication rates, and the meta-data collection is faster than processing all of the original files and produces compact meta-data that is smaller to store.

Claims

1. A computer-implemented method for generating a meta-data trace for a file in a deduplication data storage system, the method comprising:

selecting a file recipe for the file in the deduplication data storage system, the file recipe selected from a data collection storage unit that includes one or more file recipes;

retrieving data chunk meta-data for research and analysis, the data chunk meta-data corresponding to a unique data chunk identified by a fingerprint in the selected file recipe;

determining a number of file recipe bins corresponding to a memory unit for the selected file recipe based on a number of fingerprints in the selected file recipe;

mapping the selected file recipe to correspond to the determined number of file recipe bins;

reading the selected file recipe into the corresponding bins of the memory unit; and

merging retrieved data chunk meta-data into the meta-data trace corresponding to the file recipe, wherein the meta-data trace is a data structure used for research and analysis of the deduplication data storage system.

2. The method of claim 1, wherein the meta-data includes any one of data chunk type, local compression size, sub-chunk sizes, fingerprint, data chunk hashes, data chunk resemblance hashes for delta encoding and disk location.

3. The method of claim 1, further comprising:

appending logical file position data to each fingerprint in the selected file recipe to form an appended file recipe structure in the bins of the memory unit.

4. The method of claim 1, further comprising:

determining a number of bins for data chunk meta-data based on a number of records;

mapping data chunk meta-data into meta-data bins; and

determining a number of bins for merged data chunk meta-data and logical file position.

5. The method of claim 1, further comprising:

reading into the memory unit corresponding meta-data bins; and

sorting the file recipe bins and the meta-data bins based on a corresponding fingerprint.

6. The method of claim 5, further comprising:

appending matching data chunk meta-data with logical file position to form merged data structure; and

writing logical file position and data chunk meta-data merged data structure to merged bins based on mapping by logical file position.

7. The method of claim 6, further comprising:

reading in logical file position and data chunk meta-data merged data structure;

sorting the logical file position and data chunk meta-data merged data structure by logical file position; and

writing sorted data chunk meta-data to an output buffer to generate a meta-data trace.

8. A non-transitory computer-readable storage medium having instructions stored therein, which when executed by a computer, cause the computer to perform a method, the method for generating a meta-data trace for a file in a deduplication data storage system, the method comprising:

selecting a file recipe for the file in the deduplication data storage system, the file recipe selected from a data collection storage unit that includes one or more file recipes;

retrieving data chunk meta-data for research and analysis, the data chunk meta-data corresponding to a unique data chunk identified by a fingerprint in the selected file recipe;

determining a number of file recipe bins corresponding to a memory unit for the selected file recipe based on a number of fingerprints in the selected file recipe;

mapping the selected file recipe to correspond to the determined number of file recipe bins;

reading the selected file recipe into the corresponding bins of the memory unit; and

merging retrieved data chunk meta-data into the meta-data trace corresponding to the file recipe, wherein the meta-data trace is a data structure used for research and analysis of the deduplication data storage system.

9. The non-transitory computer-readable storage medium of claim 8, wherein the meta-data includes any one of data chunk type, local compression size, sub-chunk sizes, fingerprint, data chunk hashes, data chunk resemblance hashes for delta encoding and disk location.

10. The non-transitory computer-readable storage medium of claim 8, further comprising:

appending logical file position data to each fingerprint in the selected file recipe to form an appended file recipe structure.

11. The non-transitory computer-readable storage medium of claim 8, further comprising:

determining a number of bins for data chunk meta-data based on a number of records;

mapping data chunk meta-data into meta-data bins; and

determining a number of bins for merged data chunk meta-data and logical file position.

12. The non-transitory computer-readable storage medium of claim 8, further comprising:

reading into the memory unit corresponding meta-data bins; and

sorting the file recipe bins and the meta-data bins based on a corresponding fingerprint.

13. The non-transitory computer-readable storage medium of claim 12, further comprising:

appending matching data chunk meta-data with logical file position to form merged data structure; and

writing logical file position and chunk data meta-data merged data structure to merged bins based on mapping by logical file position.

14. The non-transitory computer-readable storage medium of claim 13, further comprising:

reading in logical file position and data chunk meta-data merged data structure;

sorting the logical file position and data chunk meta-data merged data structure by logical file position; and

writing sorted data chunk meta-data to an output buffer to generate a meta-data trace.

15. A deduplication data storage system, comprising:

a meta-data trace generation engine to select a file recipe for a file in the deduplication data storage system, the file recipe selected from a data collection storage unit that includes one or more file recipes, the meta-data trace generation engine to retrieve data chunk meta-data for research and analysis the data chunk meta-data of a unique data chunk identified by a fingerprint in the selected file recipe, determine a number of file recipe bins corresponding to a memory unit for the selected file recipe based on a number of fingerprints in the selected file recipe, map the selected file recipe to correspond to the determined number of file recipe bins, read the selected file recipe into the corresponding bins of the memory unit, and merge retrieved data chunk meta-data into a meta-data trace corresponding to the file recipe, wherein the meta-data trace is a data structure used for research and analysis of the deduplication data storage system; and

a data collection storage unit communicatively coupled to the meta-data trace generation engine, the data collection storage unit including the memory unit for storing the file recipe and meta-data for content data set research and analysis.

16. The deduplication data storage system of claim 15, wherein the meta-data trace generation engine reads into memory corresponding meta-data bins and sorts the file recipe bins and the meta-data bins based on a corresponding fingerprint.

17. The deduplication data storage system of claim 16, wherein the meta-data trace generation engine appends matching data chunk meta-data with logical file position to form a merged data structure and writes the logical file position and chunk data meta-data merged data structure to merged bins based on mapping by logical file position.

18. The deduplication data storage system of claim 17, wherein the meta-data trace generation engine reads in logical file position and data chunk meta-data merged data structure, sorts the logical file position and data chunk meta-data merged data structure by logical file positions, and writes sorted data chunk meta-data to an output buffer to generate the meta-data trace.