Storing a point in time coherently for a distributed storage system
A plurality of computing devices are communicatively coupled to each other via a network, and each of the plurality of computing devices is operably coupled to one or more of a plurality of storage devices. The computing devices may take snapshots to store points in time coherently for a distributed storage system.
1. A method for a distributed storage system, comprising:
taking a snapshot of a file system distributed across multiple storage nodes, wherein the snapshot is taken on the whole file system, and wherein the snapshot is not taken on a subset of the file system;
maintaining the snapshot for the file system using a snapshot table and a file system views table; and
providing a snapshot index for accessing the snapshot,
wherein:
a constant snapshot index is provided for a current view of the file system,
the file system comprises a plurality of buckets,
each of the plurality of buckets is operable to write to a unique stripe, and
each of the plurality of buckets is independent of each other of the plurality of buckets.
2. The method of claim 1 , wherein the file system is distributed across five nodes.
3. The method of claim 1 , wherein the snapshot table comprises one or more entries, and each of the one or more entries has a snapshot index field, a pointer to its parent, a pointer to a left child, and a pointer to a right child.
4. The method of claim 3 , wherein the snapshot table comprises a file system identification.
5. The method of claim 1 , wherein the file system views table comprises one or more entries, and each of the one or more entries has a name field and a pointer to a corresponding snapshot.
6. The method of claim 1 , wherein the snapshot is writeable.
7. The method of claim 1 , comprising enumerating file system objects that belong to the snapshot.
8. The method of claim 7 , wherein the enumeration is done via an on-disk hash.
9. The method of claim 7 , wherein the enumeration is done with double-linked lists for the file system objects.
10. A distributed storage system comprising:
a file system distributed across multiple storage nodes; and
a processor, wherein the processor is configured to:
take a snapshot of the file system, wherein the snapshot is taken on the whole file system, and wherein the snapshot is not taken on a subset of the file system;
maintain the snapshot for the file system using a snapshot table and a file system views table; and
provide a snapshot index for accessing the snapshot, wherein:
a constant snapshot index is provided for a current view of the file system,
the file system comprises a plurality of buckets,
each of the plurality of buckets is operable to write to a unique stripe, and
each of the plurality of buckets is independent of each other of the plurality of buckets.
11. The system of claim 10 , wherein the file system is distributed across five storage nodes.
12. The system of claim 10 , wherein the processor is configured to populate one or more entries for the snapshot table, wherein each of the one or more entries has an identification (ID) field, a pointer to its parent, a pointer to a left child, and a pointer to a right child.
13. The system of claim 12 , wherein the processor is configured to populate a file system identification field in the snapshot table.
14. The system of claim 10 , wherein the processor is configured to populate one or more entries for the file system views table, wherein each of the one or more entries has a name field and a pointer to a corresponding snapshot.
15. A non-transitory machine-readable storage medium having stored thereon, a computer program having at least one code section for taking snapshots in a storage system, the at least one code section comprising machine executable instructions for causing the machine to perform steps comprising:
taking a snapshot of a file system distributed across multiple storage nodes, wherein the snapshot is taken on the whole file system, and wherein the snapshot is not taken on a subset of the file system;
maintaining the snapshot for the file system using a snapshot table and a file system views table; and
providing a snapshot index for accessing the snapshot, wherein:
a constant snapshot index is provided for a current view of the file system,
the file system comprises a plurality of buckets,
each of the plurality of buckets is operable to write to a unique stripe, and
each of the plurality of buckets is independent of each other of the plurality of buckets.
16. The non-transitory machine-readable storage medium of claim 15 , wherein the file system is distributed across five nodes.
17. The non-transitory machine-readable storage medium of claim 15 , wherein the snapshot table comprises one or more entries, and each of the one or more entries has a snapshot index field, a pointer to its parent, a pointer to a left child, and a pointer to a right child.
18. The non-transitory machine-readable storage medium of claim 17 , wherein the snapshot table comprises a file system identification.
19. The non-transitory machine-readable storage medium of claim 15 , wherein the file system views table comprises one or more entries, and each of the one or more entries has a name field and a pointer to a corresponding snapshot.
20. The non-transitory machine-readable storage medium of claim 15 , wherein the snapshot is writeable.