Host-based RAID-5 and NV-RAM integration and method therefor

摘要

In a computing system utilizing redundant storage devices arranged in the RAID disk array (44), data is stored in the computing system using a memory cache (42) created from system memory and the disk array. A checkpoint module (90) detects a fault in the computing system and generates a fault indication, and a cache manager (92) writes data and parity to the memory cache (42) in a first mode, and writes data and parity to the storage device (44) in a second mode. In response to the fault indication (100, 102, 104) , the checkpoint module copies the data contained in the cache to the disk array, and switches the cache manager from the first mode to the second mode.