Overlapping replication cycles for asynchronous replication
Peer storage systems share the workload of asynchronously replicating a shared logical storage unit (LSU) to a target system. Peer storage systems (S1 and S2) that synchronously replicate a shared LSU share the workload of asynchronously replicating the shared LSU to a target system (S3) by dividing ownership of the replication cycles in an alternating manner without a strict synchronization of cycles between the peer storage systems. Rather, a given cycle number (e.g., Cycle 1) on S1 may not start and end with a same write operation as a same cycle number (Cycle 1) on S2, such that cycles on S1 (e.g., Cycle 1 and Cycle 2) overlap with cycles having the same number (Cycle 1 and Cycle 2) on S2. S1 may asynchronously replicate to S3 only the cycles it owns, and S2 may asynchronously replicate to S3 only the cycles it owns to S3.
1. For a system including a first storage system, a second storage system, a third storage system and logical storage unit synchronously replicated between the first storage system and the second system, wherein the logical storage unit is asynchronously replicated from the first storage system to the third storage system and asynchronously replicated from the second storage system to the third storage system, a method comprising:
for a sequence of replication cycle numbers, designating a first series of alternating replication cycle numbers of the sequence to the first storage system and designating a second series of alternating replication cycle numbers of the sequence to the second storage system;
in response to receiving a first write operation on the first storage system, determining whether a current cycle number on the first storage system is a cycle number included in the first series designated to the first storage system; and
if the current cycle number on the first storage system is a cycle number included in the first series, recording the first write operation in a first cycle buffer on the first storage system.
2. The method of claim 1 , further comprising:
prior to receiving the first write operation, synchronizing the first storage system and the second storage system to an initial cycle number.
3. The method of claim 1 , further comprising:
the first storage system determining to transition from a first cycle to a second cycle; and
the first system transmitting an instruction to the second storage system to transition from the first cycle to the second cycle.
4. The method claim 3 , further comprising:
the first system receiving an acknowledgement from the second system that the second system has transitioned to the second cycle; and
in response to receiving the acknowledgement, transitioning the first cycle on the first storage system from a capture phase to a transfer phase during which the write operations are transmitted from the first cycle buffer to the third storage system.
5. The method of claim 3 , further comprising:
the second storage system receiving the instruction from the first storage system;
the second system storage incrementing a current cycle number on the second storage system to a next cycle number;
the second system storage acknowledging to a host system completion of any write operations being executed on the second system for the second cycle number; and
after the second system has acknowledged to the host system, the second storage system sending an acknowledgement to the instruction to the first system indicating that that second storage system has transitioned from the current cycle to a next cycle.
6. The method of claim 5 , further comprising:
prior to the first storage system receiving the acknowledgement, the first system receiving a second write request;
the second storage system, in response to receiving the second write request, recording the second write operation in a second cycle buffer on the first storage system; and
the second storage system, at a later point in time, transmitting the second write operation from the second cycle buffer to the third storage system.
7. The method of claim 1 , further comprising:
if the current cycle number on the first storage system is not a cycle number included in the first series, recording or not recording the first write operation in the first cycle buffer on the first storage system,
wherein the first storage system does not transmit the first write operation from the first cycle buffer to the third storage system, except if the first write operation is recorded in the first cycle buffer and the second storage system fails to transmit the first write operation to the third storage system.
8. The method of claim 1 , wherein the first storage system and the second storage system are in an active-active configuration.
9. A system comprising:
a first storage system;
a second storage system;
a third storage system;
a logical storage unit synchronously replicated between the first storage system and the second system, wherein the logical storage unit is asynchronously replicated from the first storage system to the third storage system and asynchronously replicated from the second storage system to the third storage system; and
executable logic that implements a method including:
for a sequence of replication cycle numbers, designating a first series of alternating replication cycle numbers of the sequence to the first storage system and designating a second series of alternating replication cycle numbers of the sequence to the second storage system;
in response to receiving a first write operation on the first storage system, determining whether a current cycle number on the first storage system is a cycle number included in the first series designated to the first storage system; and
if the current cycle number on the first storage system is a cycle number included in the first series, recording the first write operation in a first cycle buffer on the first storage system.
10. The system of claim 9 , wherein the method further includes:
prior to receiving the first write operation, synchronizing the first storage system and the second storage system to an initial cycle number.
11. The system of claim 9 , wherein the method further includes:
the first storage system determining to transition from a first cycle to a second cycle; and
the first system transmitting an instruction to the second storage system to transition from the first cycle to the second cycle.
12. The system claim 11 , wherein the method further includes:
the first system receiving an acknowledgement from the second system that the second system has transitioned to the second cycle; and
in response to receiving the acknowledgement, transitioning the first cycle on the first storage system from a capture phase to a transfer phase during which the write operations are transmitted from the first cycle buffer to the third storage system.
13. The system of claim 11 , wherein the method further includes:
the second storage system receiving the instruction from the first storage system;
the second system storage incrementing a current cycle number on the second storage system to a next cycle number;
the second system storage acknowledging to a host system completion of any write operations being executed on the second system for the second cycle number; and
after the second system has acknowledged to the host system, the second storage system sending an acknowledgement to the instruction to the first system indicating that that second storage system has transitioned from the current cycle to a next cycle.
14. The system of claim 13 , wherein the method further includes:
prior to the first storage system receiving the acknowledgement, the first system receiving a second write request;
the second storage system, in response to receiving the second write request, recording the second write operation in a second cycle buffer on the first storage system; and
the second storage system, at a later point in time, transmitting the second write operation from the second cycle buffer to the third storage system.
15. The system of claim 9 , wherein the method further includes:
if the current cycle number on the first storage system is not a cycle number included in the first series, recording or not recording the first write operation in the first cycle buffer on the first storage system,
wherein the first storage system does not transmit the first write operation from the first cycle buffer to the third storage system, except if the first write operation is recorded in the first cycle buffer and the second storage system fails to transmit the first write operation to the third storage system.
16. For a system including a first storage system, a second storage system, a third storage system and logical storage unit synchronously replicated between the first storage system and the second system, wherein the logical storage unit is asynchronously replicated from the first storage system to the third storage system and asynchronously replicated from the second storage system to the third storage system, computer-readable media having software stored thereon, the software comprising:
executable code that for a sequence of replication cycle numbers, designates a first series of alternating replication cycle numbers of the sequence to the first storage system and designates a second series of alternating replication cycle numbers of the sequence to the second storage system;
executable code that, in response to receiving a first write operation on the first storage system, determines whether a current cycle number on the first storage system is a cycle number included in the first series designated to the first storage system; and
executable code that, if the current cycle number on the first storage system is a cycle number included in the first series, records the first write operation in a first cycle buffer on the first storage system.
17. The computer-readable media of claim 16 , further comprising:
executable code that, prior to receiving the first write operation, synchronizes the first storage system and the second storage system to an initial cycle number.
18. The computer-readable media of claim 16 , wherein the software further comprises:
executable code that controls the first storage system to determine to transition from a first cycle to a second cycle; and
executable code that controls the first system to transmit an instruction to the second storage system to transition from the first cycle to the second cycle.
19. The computer-readable media claim 18 , wherein the software further comprises:
executable code that controls the first system to receive an acknowledgement from the second system that the second system has transitioned to the second cycle; and
executable code that, in response to receiving the acknowledgement, transitions the first cycle on the first storage system from a capture phase to a transfer phase during which the write operations are transmitted from the first cycle buffer to the third storage system.
20. The computer-readable media of claim 18 , wherein the software further comprises:
executable code that controls the second storage system to receive the instruction from the first storage system;
executable code that controls the second system storage to increment a current cycle number on the second storage system to a next cycle number;
executable code that controls the second system storage to acknowledge to a host system completion of any write operations being executed on the second system for the second cycle number; and
executable code that controls the second storage system to send, after the second system has acknowledged to the host system, an acknowledgement to the instruction to the first system indicating that that second storage system has transitioned from the current cycle to a next cycle.