Hi there,   We are doing some testing on a very small cluster and we were experiencing some extra load by du command. It is affecting our testing results significantly and we are bypassing it by creating a symbolic link of du to a df command.    Our testing steps: 1. on all nodes: echo 1 > /proc/sys/vm/drop_caches 2. run scripts   Can anyone has a detailed explaination of how the du command gets triggered by impala( we assume it's something related with vfs caching). Is there a config or a better way to make it not doing du?   Thanks a lot! Let me know if you need more information. 🙂   ... View more