Description of problem: I created a distributed-replicate volume & created 2 mounts. Removed all performance translators. On 1 client started, untarring ltp-testsuite in a loop & on another client started rm -rf of the ltp directory in a loop. Got directory not empty error during rm which was fine. Stopped all operations & then reset the volume. Next i tried removing the ltp directory. I got these errors: rm: cannot remove `ltp-full-20091031/testcases/ballista/': Directory not empty rm: cannot remove `ltp-full-20091031/testcases/kernel/syscalls': Directory not empty rm: cannot remove `ltp-full-20091031/testcases/open_posix_testsuite/conformance': Directory not empty rm: cannot remove `ltp-full-20091031/testcases/network/stress': Directory not empty Checked the backend: The first dht subvolume did not have any entries under ltp-full-20091031/testcases/ballista/ but the second subvolume had directories under it. echo 3 > /proc/sys/vm/drop_caches on the mountpoint & `stat`d from the mountpoint. Found nothing. Therefore it keeps telling. directory not empty. Version-Release number of selected component (if applicable): How reproducible: Steps to Reproduce: 1. 2. 3. Actual results: Expected results: Additional info:
CHANGE: http://review.gluster.com/3202 (cluster/dht: rmdir should succeed last on the hashed subvol) merged in master by Anand Avati (avati)