Hi, I heard from so many people saying we should using JBOD instead of RAID, that is we should format each local disk(used for data storage) into an individual file system and define the mount point in dfs.data.dir. In this kind of configuration, disk failure will cause the coresponding file system fail, can datanode continue running with file systems defined in dfs.data.dir not accessable? If the answer is no, does it mean single disk failure will cause the whole data node to fail?
Regards, Xiaobo Gu
