Techniques for determining replication modes may include: issuing, while unsolicited data transfer mode is enabled for a first link, first write operations over the first link; issuing, while unsolicited data transfer mode is disabled for the first link, second write operations over the first link; determining a first performance metric for the first link in accordance with the first write operations; determining a second performance metric for the first link in accordance with the second write operations; and determining, in accordance with the first and second performance metrics whether to enable or disable unsolicited data transfer mode for the first link for a first time period. The first and second performance metrics may be response times. Unsolicited data transfer mode, when enabled, allows write data payload to be sent to a target without receiving an acknowledgement regarding receipt of a write command block for the write operation from the target.

The system, devices, and methods disclosed herein relate to a dynamic, robust method for choosing a winner in an active-active data storage network. In the systems and methods disclosed herein, two or more intelligent nodes within an active-active data storage network periodically exchange operational parameters in an ongoing negotiation regarding who should be the winner in the event of a communication failure within the network. The winner is chosen dynamically based on the operational parameters. A witness is kept apprised of the winner. In the event of a communication failure between the two nodes, the winner is chosen by the witness based on the most recently negotiated lock file reported by one or both of the nodes.

The system, devices, and methods disclosed herein relate to a dynamic, robust method for choosing a winner in an active-active data storage network. In the systems and methods disclosed herein, two or more intelligent nodes within an active-active data storage network periodically exchange operational parameters in an ongoing negotiation regarding who should be the winner in the event of a communication failure within the network. The winner is chosen dynamically based on the operational parameters. A witness is kept apprised of the winner. In the event of a communication failure between the two nodes, the winner is chosen by the witness based on the most recently negotiated lock file reported by one or both of the nodes.

A storage system includes a first storage control device including a first memory being a volatile memory and a first processor, and a second storage control device including a second memory being a non-volatile memory and a second processor, wherein the second processor is configured to receive a first write request to write first data into a first storage device, store the first data into the second memory, and transmit the first data to the first storage control device, the first processor is configured to store the first data into the first memory, and transmit a first notification to the second storage control device, and the second processor is configured to receive the first notification, transmit a first completion notification in response to the first write request, and execute processing to write the first data, stored in the second memory, into the first storage device.

A method, computer system, and computer program product area provided. A computer transmits a query command to a storage descriptor area of a first disk. The first disk belongs to a dual-site data replication system. The dual-site data replication system provides active-active access to a volume of data stored in an active disk and replicated in a backup disk. The computer receives a response to the query command. The response indicates the active disk and the backup disk for the dual-site data replication system. The computer controls an additional copy of the volume of data at a further remote site based on the active disk.

An example data storage system includes a first storage array having a first LUN and a second storage array having a second LUN. The first and second storage arrays may implement replication from the first LUN as a primary LUN to the second LUN as a secondary LUN. The first and second LUNs may both be an active target for host write I/O. The second storage array may, in response to receiving from a host a write that is directed to the second LUN, send write data of the write to the first storage for replication array while maintaining a copy of the write data in a fenced portion of a cache of the second storage array. The second storage array may wait to release the copy of the write data to the second LUN until a write acknowledgment is received from the first storage array.

An example data storage system includes a first storage array having a first LUN and a second storage array having a second LUN. The first and second storage arrays may implement replication from the first LUN as a primary LUN to the second LUN as a secondary LUN. The first and second LUNs may both be an active target for host write I/O. The second storage array may, in response to receiving from a host a write that is directed to the second LUN, send write data of the write to the first storage for replication array while maintaining a copy of the write data in a fenced portion of a cache of the second storage array. The second storage array may wait to release the copy of the write data to the second LUN until a write acknowledgment is received from the first storage array.

In a data backup method performed in a storage system having multiple storage devices, a first storage device having a first LUN queries data consistency points from a second storage device that has a second LUN which has an active-active relationship with the first LUN. The second storage device obtains the data consistency points based on the IO data status record of the first LUN and an IO data status record of the second LUN stored in the second storage device, and provides the data consistency points to the first storage device. The first storage device then creates a snapshot for the first LUN based on the data consistency points, provides differential data between the current snapshot and a previous snapshot, and stores the differential data in the backup storage device.

In one embodiment of the present description, mirroring is provided for a pair of storage units in bidirectional synchronous mirror relationships, and a tertiary storage unit. The mirroring includes multi-target mirroring to write updates written to the first storage unit to both the second storage unit and to a third storage unit. Similarly, for updates written to the second storage unit, multi-target mirroring is employed to write those to both the first storage unit and to the third storage unit. Other aspects are described.

A technique for providing active-active access to data over distance includes designating a first geographical site as a preferred site and designating a second geographical site as a non-preferred site. In response to a computing node at either site encountering a write request to write data to a storage object shared across both sites, the write request is handled by the preferred site, where the specified data is written to local storage at the preferred site and mirrored to local storage at the non-preferred site.