Namespace performance acceleration by selective SSD caching
In one example, a method includes receiving metadata in the form of a modification to metadata represented by a file system namespace abstraction, wherein the file system namespace abstraction corresponds to less than an entire file system namespace, and the file system namespace abstraction includes one or more pages, and one of the pages corresponds to a particular cached block, updating the file system namespace abstraction based on the received metadata, determining if caching is enabled for the file system namespace abstraction, when caching is enabled for the file system namespace abstraction, caching the updated file system namespace abstraction in SSD storage that includes the cached block, and maintaining a status of the cached block in a Dtable of the SSD storage.
1. A method, comprising:
receiving metadata in the form of a modification to metadata represented by a file system namespace abstraction, wherein the file system namespace abstraction corresponds to less than an entire file system namespace, and the file system namespace abstraction includes one or more pages, and one of the pages corresponds to a particular cached block;
updating the file system namespace abstraction based on the received metadata;
determining if caching is enabled for the file system namespace abstraction;
when caching is enabled for the file system namespace abstraction, caching the updated file system namespace abstraction in SSD storage that includes the cached block; and
maintaining a status of the cached block in a Dtable of the SSD storage.
2. The method as recited in claim 1 , wherein the updated file system namespace abstraction is cached in the SSD storage in the form of a flattened Btree that comprises one or more pages, and each of the pages has a respective timestamp.
3. The method as recited in claim 2 , wherein the pages of the flattened Btree either are, or are not, all part of a common cached block of the SSD storage.
4. The method as recited in claim 1 , wherein the SSD storage comprises a header, and the cached block is positioned between the header and the Dtable in the SSD storage.
5. The method as recited in claim 1 , wherein the file system namespace abstraction comprises an Mtree.
6. The method as recited in claim 1 , wherein the Dtable includes an entry for the cached block, and the entry includes a size, and offset, of the cached block.
7. The method as recited in claim 1 , wherein another cached block of the SSD storage comprises a respective page of each of a plurality of flattened Btrees.
8. The method as recited in claim 7 , further comprising storing a copy of one of the flattened Btrees in a database.
9. The method as recited in claim 1 , further comprising allocating, based on one or more criteria, an amount of the SSD storage for namespace caching.
10. The method as recited in claim 1 , further comprising defragmenting the SSD storage.
11. A non-transitory storage medium having stored therein instructions that are executable by one or more hardware components to perform operations comprising:
receiving metadata in the form of a modification to metadata represented by a file system namespace abstraction, wherein the file system namespace abstraction corresponds to less than an entire file system namespace, and the file system namespace abstraction includes one or more pages, and one of the pages corresponds to a particular cached block;
updating the file system namespace abstraction based on the received metadata;
determining if caching is enabled for the file system namespace abstraction;
when caching is enabled for the file system namespace abstraction, caching the updated file system namespace abstraction in SSD storage that includes the cached block; and
maintaining a status of the cached block in a Dtable of the SSD storage.
12. The non-transitory storage medium as recited in claim 11 , wherein the updated file system namespace abstraction is cached in the SSD storage in the form of a flattened Btree that comprises one or more pages, and each of the pages has a respective timestamp.
13. The non-transitory storage medium as recited in claim 12 , wherein the pages of the flattened Btree either are, or are not, all part of a common cached block of the SSD storage.
14. The non-transitory storage medium as recited in claim 11 , wherein the SSD storage comprises a header, and the cached block is positioned between the header and the Dtable in the SSD storage.
15. The non-transitory storage medium as recited in claim 11 , wherein the file system namespace abstraction comprises an Mtree.
16. The non-transitory storage medium as recited in claim 11 , wherein the Dtable includes an entry for the cached block, and the entry includes a size, and offset, of the cached block.
17. The non-transitory storage medium as recited in claim 11 , wherein another cached block of the SSD storage comprises a respective page of each of a plurality of flattened Btrees.
18. The non-transitory storage medium as recited in claim 17 , wherein the operations further comprise storing a copy of one of the flattened Btrees in a database.
19. The non-transitory storage medium as recited in claim 11 , wherein the operations further comprise allocating, based on one or more criteria, an amount of the SSD storage for namespace caching.
20. The non-transitory storage medium as recited in claim 11 , wherein the operations further comprise defragmenting the SSD storage.