×

Efficient system for predicting and processing storage subsystem failure

  • US 5,832,204 A
  • Filed: 06/23/1997
  • Issued: 11/03/1998
  • Est. Priority Date: 03/12/1996
  • Status: Expired due to Term
First Claim
Patent Images

1. A method for data recovery in a storage system including a host coupled to a supervising processor coupled to a parity-equipped RAID storage subsystem having multiple head disk assemblies ("HDA") each HDA including an HDA controller and at least one storage medium, said method comprising the steps of:

  • the supervising processor receiving from said host a Read request for reading target data;

    the supervising processor directing a first HDA to read the target data;

    the first HDA attempting to read the target data and detecting a data error during the attempt;

    the supervising processor executing a recovery process to reconstruct the target data by combining supplementary data and stored parity, said supplementary data comprising data corresponding to the target data and stored elsewhere in the RAID storage system than the first HDA, and said stored parity comprising parity corresponding to the target data and supplementary data and stored in the RAID storage subsystem;

    concurrently with the supervising processor executing the recovery process, the first HDA performing a selected predictive failure analysis ("PFA") to predict future failure of the at least one storage medium of the first HDA; and

    after completion of the recovery process, providing reconstructed target data from the supervising processor to the host.

View all claims
  • 0 Assignments
Timeline View
Assignment View
    ×
    ×