Inventors:
William Alexander Brant - Boulder CO
Michael Edward Nielson - Broomfield CO
Gary Ward Howard - Boulder CO
Assignee:
EMC Corporation - Hopkinton MA
International Classification:
G06F 1200
Abstract:
Data is recovered despite a single point of failure in a data exchanging system while accommodating scaleable data transfer rate performance. In the environment of at least two disk array controllers, a serial dumping scheme assists in recovery of data from a fast memory. It is imperative to avoid loss of write data from a host computer which is received and acknowledged but not yet stored in a disk medium. The configuration ensures that at least one of the controllers will handle the data so as to correct single failure point errors and properly store that data on one of the disks of an array. A fast memory providing a buffer between a remote host computer and arrays of data storage media is managed so that data received for writing is duplicated for reliability of storage while data for reading to the host computer is manipulated with an enhanced bandwidth of fast memory operation.