摘要:
In traditional journal based replication environments, the journal is lost on failover. However, example embodiments of the present invention overcome this and other deficiencies by preserving a journal in a symmetric continuous data protection environment. Therefore, example embodiments of the present invention provide a method, an apparatus, and a computer program production for preserving a journal in a symmetric continuous data protection environment. The method comprises maintaining a journal in a journal-based replication environment comprising a production volume at a production site and a replication volume at a replication site and, after detecting a failover event, symmetrically preserving the journal after failover.
摘要:
In one aspect, a method includes performing a failover in a journal-based replication system and performing a failback in the journal-based replication system without loss to journaling. In another aspect, an article includes a non-transitory machine-readable medium that stores executable instructions. The instructions cause a machine to perform a failover in a journal-based replication system and perform a failback in the journal-based replication system without loss to journaling. In a further aspect, an apparatus includes circuitry configured to perform a failover in a journal-based replication system and perform a failback in the journal-based replication system without loss to journaling.
摘要:
In one aspect, a method includes determining that a first quorum of servers is available at a production site and a target site and generating a group-set bookmark if the first quorum of servers is available. In another aspect, an article includes a non-transitory machine-readable medium that stores executable instructions. The instructions cause a machine to determine that a first quorum of servers is available at a production site and a target site and generate a group-set bookmark if the first quorum of servers is available. In a further aspect, an apparatus includes circuitry configured to determine that a first quorum of servers is available at a production site and a target site; and generate a group -set bookmark if the first quorum of servers available.
摘要:
In one aspect, a method includes receiving a request to access a virtual volume snapshot, preparing to bind the virtual volume snapshot, intercepting a command to prepare bind of the virtual volume snapshot, rolling back to a point in time corresponding to the requested virtual volume snapshot and generating a virtual volume snapshot in a storage array.
摘要:
In one aspect, a method includes performing replication of a first volume using a snapshot shipping mode, performing replication of a second volume using a continuous replication mode and generating a consistent point in time for the first and second volumes to enable retrieval of replicated data from the first and second volumes at the consistent point in time.
摘要:
The SCSI WRITE command is a two round trip protocol, which introduces significant latency in synchronous replication environments. Example embodiments of the present invention overcome these and other deficiencies by using SCSI READ commands from the replication site to the production site instead of using SCSI WRITE commands from the production site to the replication site to decrease latency in a synchronous replication environment. SCSI READ commands are single round trip commands. Thus, the number of round trips required to complete each I/O is reduced from two round trips to one round trip by maintaining at least one SCSI READ command from a SCSI initiator to a SCSI target and then responding to at least one of the at least one SCSI READ command at the SCSI target according to the SCSI READ command.
摘要:
In a first embodiment, computer implemented method and computer program product for executing an action selected from the group consisting of removing a LUN from a consistency group on a production site and adding a LUN to a consistency group on a production site; wherein the action is performed without loss of a journal tracking the changes to the consistency group at a replication site, the replication site replicating the consistency group on the production site.
摘要:
In one aspect, a method includes providing data protection to data in a first volume at a first data protection appliance by storing a copy of the data in a second volume using a second data protection appliance, tracking changes between data locations in the first volume and the second volume using a delta marking stream (DMS) and receiving, at the first data protection appliance, metadata. The metadata is intended to be committed to the DMS. The method further includes mirroring the metadata at a third data protection appliance.
摘要:
A system, program product, and computer implemented method for data replication, comprising enabling a virtual service layer to consume a storage medium of a site and map the storage medium of the site as one or more virtual storage volumes, enabling the virtual service layer to present the one or more virtual storage volumes for consumption by a host, enabling a splitter of the site to intercept I/O written to the one or more virtual storage volumes, splitting intercepted I/O to a journal based replication appliance, and enabling the journal based replication appliance to create a continuous data protection image of the data written to one or more virtual storage volumes.
摘要:
A method, system and computer program product for enabling a virtual service layer to consume a storage medium at a first site and map the storage medium as one or more virtual storage volumes, enabling the virtual service layer to present the one or more virtual storage volumes for consumption at the first site, enabling a splitter of the virtual service layer to intercept I/O written to the one or more virtual storage volumes, splitting intercepted I/O to a journal based replication appliance, enabling the virtual storage volumes to be accessible at a second site, wherein the one or more the virtual storage volume are mirrored at the second site by the virtual service layer; and replicating IO from either the first site or the second site to a third site.