System and method for bulk data movement between storage tiers

• US 8,949,208 B1
• Filed: 09/30/2011
• Issued: 02/03/2015
• Est. Priority Date: 09/30/2011
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Xu, Teng, Hsu, Windsor W., Chin, Lan
• Primary Examiner(s): Chen, Susan
• Application Number:
  US13/250,670
• Time in Patent Office: 1,222 Days
• Field of Search: 707/626, 707/704, 707/712, 707/769, 706/47, 713/190, 709/220, 711/117, 705/35
• US Class Current: 707/698
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0641 De-duplication techniques
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

Techniques for data migration of a storage system are described herein. According to one embodiment, a candidate index is generated to store information identifying a plurality of segments associated with one or more candidate files of a source storage tier to be migrated to a target storage tier of a storage system. Segments of the one or more candidate files are then migrated from the source storage tier to the target storage tier according to a sequential order, and based on the candidate index.

Claims

1. A computer-implemented method, comprising:

in response to a request for data migration from a source storage tier to a target storage tier, identifying, by a processor, one or more candidate files to be migrated from the source storage tier to the target storage tier;

generating, by the processor, a candidate index having information stored therein for identifying a plurality of segments associated with each of the candidate files;

after the segments associated with the one or more candidate files have been indicated in the candidate index, retrieving by the processor the segments from one or more storage units of the source storage tier based on the information stored in the candidate index; and

migrating, by the processor, the segments of the one or more candidate files from the source storage tier to the target storage tier, including transmitting segments of the source storage tier that are identified based on the candidate index to the target storage tier over a network, wherein the source storage tier and the target storage tier are separate storage systems coupled to the network, wherein migrating segments of the one or more candidate files comprises;

scanning storage containers containing segments in the source storage tier,

identifying candidate segments in the scanned storage containers based on the candidate index,

generating a fingerprint for each candidate segment by performing a hash operation on the candidate segment,

transmitting the fingerprint to the target storage tier to allow the target storage tier to determine based on the fingerprint whether the candidate segment has been stored in the target storage tier, and

transmitting to the target storage tier the candidate segments that have not been stored in the target storage.

2. The method of claim 1, further comprising identifying the one or more candidate files based on a predetermined policy governing files stored in the source storage tier.

3. The method of claim 2, wherein a file is designated as a candidate file when the file has not been accessed for a predetermined period of time which is set forth in the predetermined policy.

4. The method of claim 2, wherein all candidate files are identified from the source storage tier and indicated in the candidate index before starting migration of segments of the candidate files in a bulk manner.

5. The method of claim 1, wherein generating a candidate index comprises:

for each candidate file, identifying a plurality of segments associated with the candidate file;

for each of the segments of each candidate file, generating a fingerprint of the segment by performing a hash operation on the segment using a predetermined hash function; and

populating a field of the candidate index based on the fingerprint, wherein a value of the field indicates that the segment is to be migrated.

6. The method of claim 5, wherein the candidate index comprises a bloom filter.

7. The method of claim 5, wherein the candidate index is a bit array, and wherein the fingerprint determines an offset to an entry of the bit array that stores a value indicating migration of the segment.

8. A non-transitory computer-readable storage medium having instructions stored therein, which when executed by a computer, cause the computer to perform operations of data migration of a storage system, the operations comprising:

in response to a request for data migration from a source storage tier to a target storage tier, identifying, by a processor, one or more candidate files to be migrated from the source storage tier to the target storage tier;

generating a candidate index having information stored therein for identifying a plurality of segments associated with each of the candidate files;

after the segments associated with the one or more candidate files have been indicated in the candidate index, retrieving by the processor the segments from one or more storage units of the source storage tier based on the information stored in the candidate index; and

migrating the segments of the one or more candidate files from the source storage tier to the target storage tier, including transmitting segments of the source storage tier that are identified based on the candidate index to the target storage tier over a network, wherein the source storage tier and the target storage tier are separate storage systems coupled to the network, wherein migrating segments of the one or more candidate files comprises;

scanning storage containers containing segments in the source storage tier,

identifying candidate segments in the scanned storage containers based on the candidate index,

generating a fingerprint for each candidate segment by performing a hash operation on the candidate segment,

transmitting the fingerprint to the target storage tier to allow the target storage tier to determine based on the fingerprint whether the candidate segment has been stored in the target storage tier, and

transmitting to the target storage tier the candidate segments that have not been stored in the target storage.

9. The non-transitory computer-readable storage medium of claim 8, wherein the method further comprises identifying the one or more candidate files based on a predetermined policy governing files stored in the source storage tier.

10. The non-transitory computer-readable storage medium of claim 9, wherein a file is designated as a candidate file when the file has not been accessed for a predetermined period of time which is set forth in the predetermined policy.

11. The non-transitory computer-readable storage medium of claim 9, wherein all candidate files are identified from the source storage tier and indicated in the candidate index before starting migration of segments of the candidate files in a bulk manner.

12. The non-transitory computer-readable storage medium of claim 8, wherein generating a candidate index comprises:

for each candidate file, identifying a plurality of segments associated with the candidate file;

for each of the segments of each candidate file, generating a fingerprint of the segment by performing a hash operation on the segment using a predetermined hash function; and

populating a field of the candidate index based on the fingerprint, wherein a value of the field indicates that the segment is to be migrated.

13. The non-transitory computer-readable storage medium of claim 12, wherein the candidate index comprises a bloom filter.

14. The non-transitory computer-readable storage medium of claim 12, wherein the candidate index is a bit array, and wherein the fingerprint determines an offset to an entry of the bit array that stores a value indicating migration of the segment.

15. A storage system operating as a source storage tier, the system comprising:

a candidate builder executed by a processor, in response to a request for data migration from the source storage tier to a target storage tier, to identify one or more candidate files to be migrated from the source storage tier to the target storage tier and to generate a candidate index having information stored therein for identifying a plurality of segments associated with each of the candidate files; and

a migration module executed by the processor and coupled to the candidate builder, after the segments associated with the one or more candidate files have been indicated in the candidate index, to retrieve the segments from one or more storage units of the source storage tier based on the information stored in the candidate index and to migrate the segments of the one or more candidate files from the source storage tier to the target storage tier, including transmitting segments of the source storage tier that are identified based on the candidate index to the target storage tier over a network, wherein the source storage tier and the target storage tier are separate storage systems coupled to the network, wherein migrating segments of the one or more candidate files comprises;

scanning storage containers containing segments in the source storage tier,

identifying candidate segments in the scanned storage containers based on the candidate index,

generating a fingerprint for each candidate segment by performing a hash operation on the candidate segment,

transmitting the fingerprint to the target storage tier to allow the target storage tier to determine based on the fingerprint whether the candidate segment has been stored in the target storage tier, and

transmitting to the target storage tier the candidate segments that have not been stored in the target storage.

16. The system of claim 15, wherein the candidate builder is configured to identify the one or more candidate files based on a predetermined policy governing files stored in the source storage tier.

17. The system of claim 16, wherein a file is designated as a candidate file when the file has not been accessed for a predetermined period of time which is set forth in the predetermined policy.

18. The system of claim 16, wherein all candidate files are identified from the source storage tier and indicated in the candidate index before starting migration of segments of the candidate files in a bulk manner.

19. The system of claim 15, wherein generating a candidate index comprises:

for each candidate file, identifying a plurality of segments associated with the candidate file;

for each of the segments of each candidate file, generating a fingerprint of the segment by performing a hash operation on the segment using a predetermined hash function; and

populating a field of the candidate index based on the fingerprint, wherein a value of the field indicates that the segment is to be migrated.

20. The system of claim 19, wherein the candidate index comprises a bloom filter.

21. The system of claim 19, wherein the candidate index is a bit array, and wherein the fingerprint determines an offset to an entry of the bit array that stores a value indicating migration of the segment.