Zero-copy volume move within a distributed storage system
Systems and methods for performing a zero-copy volume move between nodes of a distributed storage system are provided. In one example, an approach for performing a zero-copy volume move is proposed in which volume data may be maintained in place within a storage pod and need not be copied to move a given volume between the source node and the destination node. In one embodiment, metadata (e.g., a top-most physical volume block number (PVBN) of a node tree representing the volume at issue) of a write-anywhere file system is copied from the source node to the destination node. Since the storage pod is associated with a global PVBN space that is visible and accessible to all nodes of the distributed storage system, as a result of copying the top-mode PVBN of the volume to the destination node, anything below the top-most PVBN will automatically be visible to the destination node.
1. A method comprising:
providing a storage pod having a group of disks containing a plurality of Redundant Array of Independent Disks (RAID) groups, wherein an entirety of a global physical volume block number (PVBN) space associated with the storage pod is visible and accessible to all nodes of a plurality of nodes of a cluster representing a distributed storage system via their respective dynamically extensible file systems (DEFSs) and wherein storage space associated with the group of disks is partitioned into a plurality of allocation areas (AAs), in which a given AA of the plurality of AAs is owned by a given DEFS of a plurality of DEFSs of the cluster; and
relocating a source volume from a first DEFS of the plurality of DEFSs of a source node of the plurality of nodes of the cluster to a second DEFS of the plurality of DEFSs of a destination node of the plurality of nodes of the cluster as part of a constant-time operation that is independent of a size of the source volume by copying an index node (inode) of a first container file representing the source volume to a new inode of a second container file representing a destination volume within the second DEFS.
2. The method of claim 1 , wherein content of the inode includes metadata maintained by the file system that is associated the first container file.
3. The method of claim 2 , wherein the metadata comprises a PVBN at a top of a node tree representing the source volume.
4. The method of claim 1 , wherein the file system comprises a write-anywhere file system in which writes are performed to free blocks rather than overwriting existing blocks.
5. A non-transitory machine readable medium storing instructions, which when executed by one or more processing resources of a distributed storage system, cause the distributed storage system to:
provide a storage pod having a group of disks containing a plurality of Redundant Array of Independent Disks (RAID) groups, wherein an entirety of a global physical volume block number (PVBN) space associated with the storage pod is visible and accessible to all nodes of a plurality of nodes of a cluster representing a distributed storage system; and
move a source volume from a source node of the plurality of nodes of the cluster to a destination node of the plurality of nodes of the cluster as part of a constant-time operation that is independent of a size of the source volume by copying metadata maintained by the file system that is associated with a first container file representing the source volume to the destination node.
6. The non-transitory machine readable medium of claim 5 , wherein moving the source volume includes creating, by the destination node, a destination volume associated with the destination node.
7. The non-transitory machine readable medium of claim 6 , wherein the metadata comprises content an index node (inode) of a first container file representing the source volume and wherein moving the source volume comprises copying the content of the inode to a second inode of a second container file representing the destination volume.
8. The non-transitory machine readable medium of claim 5 , wherein the file system comprises a write-anywhere file system in which writes are performed to free blocks rather than overwriting existing blocks.
9. The non-transitory machine readable medium of claim 5 , wherein the metadata comprises a PVBN at a top of a node tree representing the source volume and wherein moving the source volume is accomplished by copying the PVBN to the destination node.
10. The non-transitory machine readable medium of claim 5 , wherein moving the source volume includes sending a message identifying a set of one or more PVBNs of the first container file from the source node to the destination node.
11. The non-transitory machine readable medium of claim 10 , wherein the message is sent via a persistent message queue.
12. The non-transitory machine readable medium of claim 10 , wherein the message is sent via an on-wire internode communication mechanism.
13. The non-transitory machine readable medium of claim 5 , wherein the entirety of the global PVBN space associated with the storage pod is visible and accessible to all nodes of the plurality of nodes of the cluster via their respective dynamically extensible file systems (DEFSs) and wherein storage space associated with the group of disks is partitioned into a plurality of allocation areas (AAs), in which a given AA of the plurality of AAs is owned by a given DEFS of a plurality of DEFSs of the cluster.
14. The non-transitory machine readable medium of claim 13 , wherein moving the source volume comprises moving the source volume from a first DEFS of the plurality of DEFSs of the source node of the plurality of nodes of the cluster to a second DEFS of the plurality of DEFSs of the destination node of the plurality of nodes of the cluster by copying an inode of a first container file representing the source volume to a new inode of a second container file representing a destination volume within the second DEFS.
15. A distributed storage system comprising:
one or more processing resources; and
instructions that when executed by the one or more processing resources cause the distributed storage system to:
provide a storage pod having a group of disks containing a plurality of Redundant Array of Independent Disks (RAID) groups, wherein an entirety of a global physical volume block number (PVBN) space associated with the storage pod is visible and accessible to all nodes of a plurality of nodes of a cluster representing a distributed storage system; and
move a source volume from a source node of the plurality of nodes of the cluster to a destination node of the plurality of nodes of the cluster as part of a constant-time operation that is independent of a size of the source volume by copying metadata maintained by the file system that is associated with a first container file representing the source volume to the destination node.
16. The distributed storage system of claim 15 , wherein moving the source volume includes creating, by the destination node, a destination volume associated with the destination node.
17. The distributed storage system of claim 16 , wherein the metadata comprises content an index node (inode) of a first container file representing the source volume and wherein moving the source volume comprises copying the content of the inode to a second inode of a second container file representing the destination volume.
18. The distributed storage system of claim 15 , wherein the file system comprises a write-anywhere file system in which writes are performed to free blocks rather than overwriting existing blocks.
19. The distributed storage system of claim 15 , wherein the metadata comprises a PVBN at a top of a node tree representing the source volume and wherein moving the source volume is accomplished by copying the PVBN to the destination node.
20. The distributed storage system of claim 15 , wherein moving the source volume includes sending a message identifying a set of one or more PVBNs of the first container file from the source node to the destination node.
21. The distributed storage system of claim 20 , wherein the message is sent via a persistent message queue.
22. The distributed storage system of claim 20 , wherein the message is sent via an on-wire internode communication mechanism.
23. The distributed storage system of claim 15 , wherein the entirety of the global PVBN space associated with the storage pod is visible and accessible to all nodes of the plurality of nodes of the cluster via their respective dynamically extensible file systems (DEFSs) and wherein storage space associated with the group of disks is partitioned into a plurality of allocation areas (AAs), in which a given AA of the plurality of AAs is owned by a given DEFS of a plurality of DEFSs of the cluster.
24. The distributed storage system of claim 23 , wherein moving the source volume comprises moving the source volume from a first DEFS of the plurality of DEFSs of the source node of the plurality of nodes of the cluster to a second DEFS of the plurality of DEFSs of the destination node of the plurality of nodes of the cluster by copying an inode of a first container file representing the source volume to a new inode of a second container file representing a destination volume within the second DEFS.