Method to improve the I/O performance in a deduplicated storage system
View Patent ↗A method, article of manufacture, and apparatus for performing backup operations using a deduplicated storage system is presented. A data segment can be received at a deduplicated storage system. A fingerprint can be calculated for the data segment. The fingerprint and the offset can be stored in a reference cache on the deduplicated storage system. A metadata segment can be loaded from the deduplicated storage system. The metadata segment can be updated to include the fingerprint. Backup operations may include storage and management using a tree structure.
1. A method for optimizing backups, the method comprising:
receiving a data segment at a deduplicated storage system, wherein the data segment comprises data overwriting previous data at an offset on a primary storage system;
calculating a fingerprint for the data segment;
storing the fingerprint and the offset in a reference cache on the deduplicated storage system;
loading a metadata segment from the deduplicated storage system, wherein the metadata segment is associated with the offset;
updating the metadata segment to include the fingerprint;
receiving a read request for the data segment at the deduplicated storage system, wherein the read request comprises the fingerprint for the data segment;
loading the data segment on the deduplicated storage system using the fingerprint; and
returning the data segment to the primary storage system.
2. The method of claim 1 , wherein the metadata segment comprises a node in a tree structure.
3. The method of claim 1 , further comprising storing the data segment as a leaf in a tree structure.
4. The method of claim 1 , further comprising transmitting a write complete notification to the primary storage system after storing the fingerprint and the offset in the reference cache.
5. The method of claim 1 , wherein loading and updating the metadata segment occurs asynchronously with storing the fingerprint and the offset in the reference cache.
6. The method of claim 1 , wherein the data segment is loaded from a data cache on the deduplicated storage system.
7. The method of claim 1 , wherein the data segment is loaded from persistent storage on the deduplicated storage system.
8. A computer program product for optimizing backups, the computer program product comprising a non-transitory computer readable medium encoded with computer executable program, the code enabling:
receiving a data segment at a deduplicated storage system, wherein the data segment comprises data overwriting previous data at an offset on a primary storage system;
calculating a fingerprint for the data segment;
storing the fingerprint and the offset in a reference cache on the deduplicated storage system;
loading a metadata segment from the deduplicated storage system, wherein the metadata segment is associated with the offset;
updating the metadata segment to include the fingerprint;
receiving a read request for the data segment at the deduplicated storage system, wherein the read request comprises the fingerprint for the data segment;
loading the data segment on the deduplicated storage system using the fingerprint; and
returning the data segment to the primary storage system.
9. The computer program product of claim 8 , wherein the metadata segment comprises a node in a tree structure.
10. The computer program product of claim 8 , further comprising storing the data segment as a leaf in a tree structure.
11. The computer program product of claim 8 , further comprising transmitting a write complete notification to the primary storage system after storing the fingerprint and the offset in the reference cache.
12. The computer program product of claim 8 , wherein loading and updating the metadata segment occurs asynchronously with storing the fingerprint and the offset in the reference cache.
13. The computer program product of claim 8 , wherein the data segment is loaded from a data cache on the deduplicated storage system.
14. A system for optimizing backups, the system comprising a computer processor configured to execute instructions comprising:
receiving a data segment at a deduplicated storage system, wherein the data segment comprises data overwriting previous data at an offset on a primary storage system;
calculating a fingerprint for the data segment;
storing the fingerprint and the offset in a reference cache on the deduplicated storage system;
loading a metadata segment from the deduplicated storage system, wherein the metadata segment is associated with the offset;
updating the metadata segment to include the fingerprint;
receiving a read request for the data segment at the deduplicated storage system, wherein the read request comprises the fingerprint for the data segment;
loading the data segment on the deduplicated storage system using the fingerprint; and
returning the data segment to the primary storage system.
15. The system of claim 14 , wherein the metadata segment comprises a node in a tree structure.
16. The system of claim 14 , further comprising storing the data segment as a leaf in a tree structure.
17. The system of claim 14 , further comprising transmitting a write complete notification to the primary storage system after storing the fingerprint and the offset in the reference cache.
18. The system of claim 14 , wherein loading and updating the metadata segment occurs asynchronously with storing the fingerprint and the offset in the reference cache.
19. The system of claim 14 , wherein the data segment is loaded from a data cache on the deduplicated storage system.
20. The system of claim 14 , wherein the data segment is loaded from persistent storage on the deduplicated storage system.