Efficient resilience in a metadata paging array for in-flight user data
Protection and recovery is provided for an allocation unit of data that is in-flight between a source device and a target device of a storage system during a systemic failure by selecting between corresponding source device and target device metadata based on consistency and reciprocal linkage. If logical volume metadata for the allocation unit of the data in volatile memory is not consistent with logical volume metadata for the allocation unit in non-volatile storage, then the allocation unit is recovered from the source device. If target device metadata for the data in volatile memory is not consistent with target device metadata for the data in non-volatile storage, then the allocation unit is recovered from the source device. If linkage between logical volume metadata for the allocation unit and target device metadata for the data is not reciprocal, then the allocation unit is recovered from the source device. If none of those conditions are satisfied, then the allocation unit is recovered from the target device.
1. A method comprising:
in a storage system in which an allocation unit of data of a logical volume is being moved from a source device to a target device when a failure occurs, recovering the data by:
determining that logical volume metadata for the allocation unit in volatile memory is consistent with logical volume metadata for the allocation unit in non-volatile storage;
determining that target device metadata for the data in volatile memory is consistent with target device metadata for the data in non-volatile storage;
determining that linkage between logical volume metadata for the allocation unit and target device metadata for the data is reciprocal; and
recovering the data from the target device.
2. The method of claim 1 comprising recovering the data from the source device in response to determining that logical volume metadata for the allocation unit in volatile memory is inconsistent with logical volume metadata for the allocation unit in non-volatile storage.
3. The method of claim 1 comprising recovering the data from the source device in response to determining that target device metadata for the data in volatile memory is inconsistent with target device metadata for the data in non-volatile storage.
4. The method of claim 1 comprising recovering the data from the source device in response to determining that reciprocal linkage between logical volume metadata for the allocation unit and target device metadata for the data is lacking.
5. The method of claim 1 comprising updating the logical volume metadata for the allocation unit in volatile memory to indicate that the allocation unit is being moved from the source device to the target device.
6. The method of claim 5 comprising lazily updating the logical volume metadata for the allocation unit in non-volatile storage to indicate that the allocation unit is being moved from the source device to the target device.
7. The method of claim 1 comprising updating the target device metadata for the data in volatile memory to indicate that corresponding target device data is associated with the allocation unit of the logical volume.
8. The method of claim 7 comprising lazily updating the target device metadata for the data in non-volatile storage to indicate that corresponding target device data is associated with the allocation unit of the logical volume.
9. An apparatus comprising:
a plurality of managed drives;
a plurality of interconnected computing nodes that manage access to the managed drives and present a logical volume to a host; and
a relocator, responsive to a failure occurring during movement of an allocation unit of data of the logical volume from a source device to a target device, to: determine that logical volume metadata for the allocation unit in volatile memory is consistent with logical volume metadata for the allocation unit in non-volatile storage, determine that target device metadata for the data in volatile memory is consistent with target device metadata for the data in non-volatile storage, determine that linkage between logical volume metadata for the allocation unit and target device metadata for the data is reciprocal, and recover the data from the target device.
10. The apparatus of claim 9 wherein the relocator recovers the data from the source device responsive to a determination that logical volume metadata for the allocation unit in volatile memory is inconsistent with logical volume metadata for the allocation unit in non-volatile storage.
11. The apparatus of claim 9 wherein the relocator recovers the data from the source device responsive to a determination that target device metadata for the data in volatile memory is inconsistent with target device metadata for the data in non-volatile storage.
12. The apparatus of claim 9 wherein the relocator recovers the data from the source device responsive to a determination that reciprocal linkage between logical volume metadata for the allocation unit and target device metadata for the data is lacking.
13. The apparatus of claim 9 wherein the relocator updates the logical volume metadata for the allocation unit in volatile memory to indicate that the allocation unit is being moved from the source device to the target device.
14. The apparatus of claim 13 wherein the relocator lazily updates the logical volume metadata for the allocation unit in non-volatile storage to indicate that the allocation unit is being moved from the source device to the target device.
15. The apparatus of claim 9 wherein the relocator updates the target device metadata for the data in volatile memory to indicate that corresponding target device data is associated with the allocation unit of the logical volume.
16. The apparatus of claim 15 wherein the relocator lazily updates the target device metadata for the data in non-volatile storage to indicate that corresponding target device data is associated with the allocation unit of the logical volume.
17. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for using a computer system to recover data that is in-flight during a failure, the method comprising:
in a storage system in which an allocation unit of data of a logical volume is being moved from a source device to a target device when a failure occurs, recovering the data by:
determining that logical volume metadata for the allocation unit in volatile memory is consistent with logical volume metadata for the allocation unit in non-volatile storage;
determining that target device metadata for the data in volatile memory is consistent with target device metadata for the data in non-volatile storage;
determining that linkage between logical volume metadata for the allocation unit and target device metadata for the data is reciprocal; and
recovering the data from the target device.
18. The non-transitory computer-readable storage medium of claim 17 wherein the method further comprises recovering the data from the source device in response to determining that logical volume metadata for the allocation unit in volatile memory is inconsistent with logical volume metadata for the allocation unit in non-volatile storage.
19. The non-transitory computer-readable storage medium of claim 18 wherein the method further comprises recovering the data from the source device in response to determining that target device metadata for the data in volatile memory is inconsistent with target device metadata for the data in non-volatile storage.
20. The non-transitory computer-readable storage medium of claim 19 wherein the method further comprises recovering the data from the source device in response to determining that reciprocal linkage between logical volume metadata for the allocation unit and target device metadata for the data is lacking.