Resynchronization of mirrored logical data volumes subsequent to a failure in data processor storage systems with access to physical volume from multi-initiators at a plurality of nodes

Abstract

There is provided a system for dynamically resynchronizing, in the even of a system failure, a storage system made up of a plurality of nodes, each which has mirrored logical volumes respectively divided in to a plurality of mirrored logical data partitions. Each of these nodes has the means for accessing a common physical data volume, e.g. a disk drive in which data in corresponding logical volumes at respective nodes is represented by data stored in common in the physical volume. System recovery at the plurality of nodes after a failure at one of the nodes is carried out by commencing the sequential resynchronization of a logical data volume at a nonfailure node to thereby sequentially resynchronize the partitions of the physical data volume representative of the logical data volume, and indicating as resynchronized those portions of the logical data volume at the failure node represented by said resynchronized partitions of the physical data volume.