@PJ The balancer does not balance between individual disks on a single data node. Assuming Data nodes are fairly balanced across the cluster, why do you care? If you have multiple nodes and this one disk is reaching capacity, that shouldn't affect how Hadoop works. As new data comes in, Hadoop will be smart enough to place blocks on other nodes. Now, a question that comes to mind is, do you have other things on this disk (I mean other than HDFS data)? Can you do a cat /proc/mount to check what is mounted on your /dev/sdi? There might be other things that are taking space.
... View more
