| 摘要 |
A system for managing input/output (I/O) errors in a storage system employing asymmetric distributed block virtualization includes a volume server, a plurality of volume clients, and one or more physical block devices. The volume server aggregates storage in the physical block devices into a logical volume and makes the logical volume accessible to the volume client. A designated route may be used to send I/O requests from the volume client to a physical block device during normal operation. If the volume client loses connectivity on the designated route, the volume client may route an I/O request to the physical block device via an alternate route. In one specific embodiment, the volume client may route an I/O request to the physical block device via the volume server.
|
