公开(公告)号：US20130339784A1

公开(公告)日：2013-12-19

申请号：US13524719

申请日：2012-06-15

申请人： Craig A. Bickelman ,  Brian Bowles ,  David D. Cadigan ,  Edward W. Chencinski ,  Robert E. Galbraith ,  Adam J. McPadden ,  Kenneth J. Oakes ,  Peter K. Szwed

发明人： Craig A. Bickelman ,  Brian Bowles ,  David D. Cadigan ,  Edward W. Chencinski ,  Robert E. Galbraith ,  Adam J. McPadden ,  Kenneth J. Oakes ,  Peter K. Szwed

IPC分类号： G06F11/14

CPC分类号： G06F11/1092 ,  G06F11/2082

摘要： Embodiments relate to providing error recovery in a storage system that utilizes data redundancy. An aspect of the invention includes monitoring plurality of storage devices of the storage system and determining that one of the plurality of storage devices has failed based on the monitoring. Another aspect of includes suspending data reads and writes to the failed storage device and determining that the failed storage device is recoverable. Based on determining that the failed storage device is recoverable, initiating a rebuilding recovery process of the failed storage device based on determining that the failed storage device is recoverable and restoring data reads and writes to the failed storage device upon completion of the rebuilding recovery process.

摘要翻译： 实施例涉及在利用数据冗余的存储系统中提供错误恢复。 本发明的一个方面包括监视存储系统的多个存储设备，并且基于监视来确定多个存储设备中的一个存储设备已经发生故障。 另一方面包括暂停对故障存储设备的数据读写，并确定故障存储设备是可恢复的。 基于确定故障存储设备是可恢复的，基于确定故障存储设备是可恢复的，启动故障存储设备的重建恢复过程，并且在重建恢复过程完成时恢复对故障存储设备的数据读取和写入。