Reducing failover time between data nodes
A storage node that maintains a replica of a logical volume for use in response to a failover trigger includes a data node with volatile memory in which a filesystem and its metadata and a VDM and its metadata associated with the replica are maintained prior to the failover trigger. The storage node also includes a SAN node in which data associated with the replica is maintained. The data is maintained in a RW (read-write) state by the SAN node prior to the failover trigger. However, the replica is presented in a RO (read-only) state by the storage node prior to the failover trigger. The storage node changes the in-memory state of the filesystem and VDM to RW responsive to the failover trigger. Because the filesystem and its metadata and VDM and its metadata are already in memory and the data is in a RW state in block storage the failover is completed relatively quickly.
1. An apparatus comprising:
a storage node that maintains a replica of a logical volume for use in response to a failover trigger, the storage node comprising:
a data node comprising a volatile memory in which a filesystem and its metadata associated with the replica is maintained prior to the failover trigger; and
a SAN (storage area network) node comprising a plurality of interconnected computing nodes configured to manage access to managed drives in which data associated with the replica is maintained.
2. The apparatus of claim 1 wherein the data node maintains a VDM (virtual data mover) and its metadata associated with the replica in the volatile memory prior to the failover trigger.
3. The apparatus of claim 2 wherein the data is maintained in a RW (read-write) state by the SAN node prior to the failover trigger.
4. The apparatus of claim 3 wherein the replica is presented in a RO (read-only) state by the storage node prior to the failover trigger.
5. The apparatus of claim 4 wherein the storage node changes in-memory state of the filesystem and VDM to RW responsive to the failover trigger.
6. The apparatus of claim 5 wherein SDNAS (software-defined network attached storage) applications synchronize the replica with a primary site replica prior to the failover trigger.
7. A method comprising:
in a storage node comprising a data node and a SAN (storage area network) node comprising a plurality of interconnected computing nodes configured to manage access to managed drives, maintaining a replica of a logical volume for use in response to a failover trigger, steps of the method comprising:
maintaining a filesystem and its metadata associated with the replica in volatile memory of the data node prior to the failover trigger; and
maintaining data associated with the replica in the managed drives of the SAN node prior to the failover trigger.
8. The method of claim 7 comprising the data node maintaining a VDM (virtual data mover) and its metadata associated with the replica in the volatile memory prior to the failover trigger.
9. The method of claim 8 comprising the SAN node maintaining the data in a RW (read-write) state prior to the failover trigger.
10. The method of claim 3 comprising the storage node presenting the replica in a RO (read-only) state prior to the failover trigger.
11. The method of claim 10 comprising the storage node changing in-memory state of the filesystem and VDM to RW responsive to the failover trigger.
12. The method of claim 11 comprising SDNAS (software-defined network attached storage) applications synchronizing the replica with a primary site replica prior to the failover trigger.
13. An apparatus comprising:
a first storage node that maintains a primary replica of a logical volume for use by at least one client computer prior to a failover trigger, the first storage node comprising:
a first data node comprising a volatile memory in which a filesystem associated with the primary replica is maintained; and
a first SAN (storage area network) node comprising a plurality of interconnected computing nodes configured to manage access to managed drives in which data associated with the primary replica is maintained; and
a second storage node that maintains a secondary replica of the logical volume for use in response to the failover trigger, the second storage node comprising:
a second data node comprising a volatile memory in which a filesystem associated with the second replica is maintained prior to the failover trigger; and
a second SAN (storage area network) node comprising a plurality of interconnected computing nodes configured to manage access to managed drives in which data associated with the second replica is maintained.
14. The apparatus of claim 13 wherein the second data node maintains a VDM (virtual data mover) associated with the second replica in the volatile memory prior to the failover trigger.
15. The apparatus of claim 14 wherein the data is maintained in a RW (read-write) state by the second SAN node prior to the failover trigger.
16. The apparatus of claim 15 wherein the second replica is presented in a RO (read-only) state by the second storage node prior to the failover trigger.
17. The apparatus of claim 16 wherein the second storage node changes in-memory state of the filesystem and VDM to RW responsive to the failover trigger.
18. The apparatus of claim 17 wherein SDNAS (software-defined network attached storage) applications synchronize the second replica with the first replica prior to the failover trigger.
19. The apparatus of claim 18 wherein the first data node comprises a volatile memory in which a filesystem associated with the first replica is maintained prior to the failover trigger.
20. The apparatus of claim 19 wherein a VDM associated with the first replica is maintained in the volatile memory of the first data node prior to the failover trigger.