Automatic site failover
First Claim
1. A storage controller, comprising:
- an input port to receive input/output data operations from a host computer;
an output port for transmitting input/output data operations to at least one destination controller;
a processor;
a memory module communicatively connected to the processor and comprising logic instructions which, when executed, configure the processor to;
detect a failure in normal heartbeat operations between the storage controller and at least one destination controller; and
in response to the failure;
take the storage controller offline to the host computer when communication connections fail between the storage controller and a first predetermined number of destination controllers; and
log write input/output operations directed to the one or more destination controllers into a data log when communication connections remain active between the storage controller and a second predetermined number of destination controllers.
2 Assignments
0 Petitions
Accused Products
Abstract
A data storage system adapted to maintain redundant data storage sets at a destination location(s) is disclosed. The data storage system establishes a copy set comprising a source volume and a destination volume. Data written to a source volume is automatically copied to the destination volume. The data storage system maintains a data log that may be activated when the destination volume is inaccessible due to, for example, a malfunction in the destination storage system or in the communication link between the source system and the destination system. I/O commands and the data associated with those commands are written to the data log, and after a destination system becomes available the information in the data log is merged into the destination volume to conform the data in the destination volume to the data in the source volume. The data log competes for disk capacity with other volumes on the system, and log memory is allocated as needed. In operation, the array controllers monitor connection status between array controllers in a DRM group. When a connection failure is detected the controllers determine which of the remaining controllers determine whether the source controller remains online, and if not then which destination controller should assume the role of the source controller.
-
Citations
9 Claims
-
1. A storage controller, comprising:
-
an input port to receive input/output data operations from a host computer; an output port for transmitting input/output data operations to at least one destination controller; a processor; a memory module communicatively connected to the processor and comprising logic instructions which, when executed, configure the processor to; detect a failure in normal heartbeat operations between the storage controller and at least one destination controller; and in response to the failure; take the storage controller offline to the host computer when communication connections fail between the storage controller and a first predetermined number of destination controllers; and log write input/output operations directed to the one or more destination controllers into a data log when communication connections remain active between the storage controller and a second predetermined number of destination controllers. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A storage controller, comprising:
-
an input port to receive input/output data operations for a data replication management group from a host computer; an output port for transmitting input/output data operations for a data replication management group to at least one destination controller; a processor; a memory module communicatively connected to the processor and comprising logic instructions which, when executed, configure the processor to; detect a failure in normal heartbeat operations between the storage controller and one or more peer storage controllers; determine whether the storage controller is a source controller for the data replication management group associated with the input/output data operations; implement a first failover technique when the storage controller is a source controller for the data replication management group associated with the input/output data operations; and implement a second failover technique when the storage controller is not a source controller for the data replication management group associated with the input/output data operations. - View Dependent Claims (7, 8, 9)
-
Specification