Systems and methods to reduce application input/output resumption time due to a failure of a storage site or a network partition within a cross-site storage system
A computer-implemented method includes establishing bi-directional synchronous replication between one or more members of a first consistency group (CG1) of a primary storage site and one or more members of a second consistency group (CG2) of a secondary storage site with each storage site having read/write access. The method includes detecting a disruption in a data replication session from one or more members of the CG1 to one or more members of the CG2 due to a disaster event, initiating a consensus establishment request to be sent to a mediator agent of the primary storage site, rejecting with the mediator agent the consensus establishment request, and initiating a role flip process for primary and secondary roles in serving I/O Operations in response to the rejection of the consensus establishment request to reduce an application input/output (I/O) resumption time due to the disaster event.
1 . A computer-implemented method comprising:
establishing bi-directional synchronous replication between one or more members of a first consistency group (CG1) of a primary storage site and one or more members of a second consistency group (CG2) of a secondary storage site with each storage site having read/write access while maintaining zero recovery point objective (RPO) and Zero recovery time objective (RTO);
detecting a disruption in a data replication session from one or more members of the CG1 to one or more members of the CG2 due to a disaster event that causes the one or more members of the CG1 to be non-operational having OOS state and initiates transition of CG2 from a secondary role to a primary role for serving input/output (I/O) operations;
initiating, based on the one or more members of CG1 becoming operational, a consensus establishment request to be sent to a mediator agent of the primary storage site;
rejecting with the mediator agent the consensus establishment request; and
initiating, with the primary storage site, an early trigger of a role flip process for primary and secondary roles in serving input/output (I/O) operations (Ops) in response to the rejection of the consensus establishment request to reduce an application I/O resumption time and for faster resumption of zero RPO.
2 . The computer-implemented method of claim 1 , further comprising:
generating and sending, with the primary storage site, a cross-cluster call for CG1 to the secondary storage site to initiate a resynchronization process between CG1 and CG2 for returning CG1 and CG2 to in sync state and for faster resumption of zero RPO.
3 . The computer-implemented method of claim 2 , wherein the resynchronization process ensures that the primary storage site does not independently transition from a primary role to a secondary role and proceeds with the role flip if the secondary storage site has transitioned to the primary role and this precaution prevents a scenario where both primary and secondary storage sites indicate a secondary role for serving I/O Ops.
4 . The computer-implemented method of claim 1 , further comprising:
sending a start resync call to a data plane of the secondary storage site.
5 . The computer-implemented method of claim 4 , further comprising:
sending with the data plane an upcall to a host of the secondary storage site to start the role flip process and resynchronization process.
6 . The computer-implemented method of claim 5 , further comprising:
sending a communication to a host of the primary storage site to flip replicated database (RDB) configuration information from source to destination for the primary storage site.
7 . The computer-implemented method of claim 6 , further comprising:
sending a communication to the data plane of the secondary storage site to seed a data plane cache with a flag to start resynchronization between CG1 and CG2; and
starting the resynchronization process.