Granted Patent B2

US 12,321,627 · App. 18/424,244 · Granted Jun 3, 2025

Inventors: Krishna Murthy Chandraiah Setty Narasingarayanapeta (Bangalore, IN); Akhil Kaushik (Bangalore Karnataka, IN)

Assignee: NetApp, Inc.

G06F3/0647G06F3/0604G06F3/0679

Abstract

Claims (56)

1. A computer implemented method performed by one or more processing resources of a storage node, the method comprising:

temporarily disallowing input/output (I/O) operations for a storage object of the storage node of a primary storage cluster when the storage object of the primary storage cluster has a connection loss or failure;

initiating a resynchronization between the storage object and a replicated storage object of a secondary storage cluster based on the connection loss or failure with the resynchronization including initiating asynchronous inflight tracking and replay for reconciliation of any missing I/O operations that are missing from one of a first Op log of the primary storage cluster and a second Op log of the secondary storage cluster and performing a dependency check to determine any dependencies between Ops for any I/O operations being replayed from the primary storage cluster; and

allowing new I/O operations to be handled with the storage object of the primary storage cluster just after asynchronous inflight tracking and replay processes pendings Ops at the primary storage cluster without waiting for completion of the asynchronous inflight tracking and replay including receiving responses from the secondary storage cluster.

2. The computer implemented method of claim 1 , further comprising:

performing the dependency check with a dependent graph manager at a volume level barrier for any missing I/O operations that are issued during the asynchronous inflight tracking and replay; and

populating a tracking data structure of the dependent graph manager during the dependency check.

3. The computer implemented method of claim 1 , further comprising:

performing the dependency check with a dependent graph manager at a file system object barrier level for any missing I/O operations that are issued during the asynchronous inflight tracking and replay; and

populating a tracking data structure of the dependent graph manager during the dependency check.

4. The computer implemented method of claim 3 , wherein the tracking data structure of the dependent graph manager is configured to track in flight Ops, Ops completed at the secondary storage cluster, and Ops waiting for dependencies to be satisfied.

5. The computer implemented method of claim 1 , further comprising:

performing an overlap conflict check of any storage object to be modified by any missing I/O operations and also be modified by an inflight Op with an overlap write manager; and

populating a tracking data structure of the overlap write manager during the overlap conflict check.

6. The computer implemented method of claim 5 , wherein the tracking data structure of the overlap write manager is configured to track in flight Ops, Ops completed at the secondary storage cluster, and Ops waiting for dependencies to be satisfied.

7. The computer implemented method of claim 1 , wherein the new I/O operations are allowed to be handled with the storage object of the primary storage cluster without waiting for replay Ops to complete at the secondary storage cluster.

8. A non-transitory computer-readable storage medium embodying a set of instructions, which when executed by a processing resource of a storage node cause the processing resource to:

temporarily disallow input/output (I/O) operations for a storage object of the storage node of a primary storage cluster when the storage object of the primary storage cluster has a connection loss or failure;

initiating a resynchronization between the storage object and a replicated storage object of a secondary storage cluster based on the connection loss or failure with the resynchronization including initiating asynchronous inflight tracking and replay for reconciliation of any missing I/O operations that are missing from one of a first Op log of the primary storage cluster and a second Op log of the secondary storage cluster and performing a dependency check to determine any dependencies between Ops for any I/O operations being replayed from the primary storage cluster; and

allowing new I/O operations to be handled with the storage object of the primary storage cluster just after asynchronous inflight tracking and replay processes pendings Ops at the primary storage cluster without waiting for completion of the asynchronous inflight tracking and replay including receiving responses from the secondary storage cluster.

9. The non-transitory computer-readable storage medium of claim 8 , wherein the instructions when executed by the processing resource cause the processing resource to:

perform the dependency check with a dependent graph manager at a volume level barrier for any missing I/O operations that are issued during the asynchronous inflight tracking and replay; and

populate a tracking data structure of the dependent graph manager during the dependency check.

10. The non-transitory computer-readable storage medium of claim 8 , wherein the instructions when executed by the processing resource cause the processing resource to:

perform the dependency check with a dependent graph manager at a file system object barrier level for any missing I/O operations that are issued during the asynchronous inflight tracking and replay; and

populate a tracking data structure of the dependent graph manager during the dependency check.

11. The non-transitory computer-readable storage medium of claim 10 , wherein the tracking data structure of the dependent graph manager is configured to track in flight Ops, Ops completed at the secondary storage cluster, and Ops waiting for dependencies to be satisfied.

12. The non-transitory computer-readable storage medium of claim 8 , wherein the instructions when executed by the processing resource cause the processing resource to:

perform an overlap conflict check of any storage object to be modified by any missing I/O operations and also to be modified by an inflight Op with an overlap write manager; and

populate a tracking data structure of the overlap write manager during the overlap conflict check.

13. The non-transitory computer-readable storage medium of claim 12 , wherein the tracking data structure of the overlap write manager is configured to track in flight Ops, Ops completed at the secondary storage cluster, and Ops waiting for dependencies to be satisfied.

14. The non-transitory computer-readable storage medium of claim 8 , wherein the new I/O operations are allowed to be handled with the storage object of the primary storage cluster without waiting for replay Ops to complete at the secondary storage cluster.

15. A storage node of a primary storage cluster, comprising:

a processing resource; and

a non-transitory computer-readable medium coupled to the processing resource, having stored therein instructions, which when executed by the processing resource cause the processing resource to:

temporarily disallow input/output (I/O) operations for a storage object of the storage node of a primary storage cluster when the storage object of the primary storage cluster has a connection loss or failure;

initiate a resynchronization between the storage object and a replicated storage object of a secondary storage cluster based on the connection loss or failure with the resynchronization including initiating asynchronous inflight tracking and replay for reconciliation of any missing I/O operations that are missing from one of a first Op log of the primary storage cluster and a second Op log of the secondary storage cluster;

perform a dependency check to determine any dependencies between Ops for any I/O operations being replayed from the primary storage cluster; and

allow new I/O operations to be handled with the storage object of the primary storage cluster just after asynchronous inflight tracking and replay processes pendings Ops at the primary storage cluster without waiting for completion of the asynchronous inflight tracking and replay including receiving responses from the secondary storage cluster.

16. The storage node of claim 15 , wherein the instructions when executed by the processing resource cause the processing resource to:

perform the dependency check with a dependent graph manager at a volume level barrier for any missing I/O operations that are issued during the persistent inflight tracking replay; and

populate a tracking data structure of the dependent graph manager during the dependency check.

17. The storage node of claim 15 , wherein the instructions when executed by the processing resource cause the processing resource to:

perform the dependency check with a dependent graph manager at a file system object barrier level for any missing I/O operations that are issued during the asynchronous inflight tracking and replay; and

populate a tracking data structure of the dependent graph manager during the dependency check, wherein the tracking data structure of the dependent graph manager is configured to track in flight Ops, Ops completed at the secondary storage cluster, and Ops waiting for dependencies to be satisfied.

18. The storage node of claim 15 , wherein the instructions when executed by the processing resource cause the processing resource to:

perform an overlap conflict check of any storage object to be modified by any missing I/O operations and inflight Ops with an overlap write manager for any missing I/O operations that are issued during the asynchronous inflight tracking and replay; and

populate a tracking data structure of the overlap write manager during the overlap conflict check, wherein the tracking data structure of the overlap write manager is configured to track in flight Ops, Ops completed at the secondary storage cluster, and Ops waiting for dependencies to be satisfied.

19. The storage node of claim 15 , wherein the new I/O operations are allowed to be handled with the storage object of the primary storage cluster without waiting for replay Ops to complete at the secondary storage cluster.

20. The storage node of claim 15 , wherein the instructions when executed by the processing resource cause the processing resource to:

maintain a count of a number of Ops in the asynchronous inflight tracking replay;

create an identifier for each Op being replayed;

increment a count for each Op being replayed;

decrement the count for each Op that completes the asynchronous inflight tracking and replay;

until the count becomes zero, subject read Ops to overlap range manager and dependent graph manager checks; and

determine if an incoming read Op is conflicting with Ops pending in the asynchronous inflight tracking and replay.

Continuity (2)

References Cited (133)

Cited By (1)

US 12,436,707