Hi Nic, I suspect it to be an issue with /dev/md3 itself. check /var/log/messages for any irregularities. Regards, Amar > > > Here is the df output on one of our Gluster hosts, notice that the exported > volume is a dedicated filesystem. > > root at gluster01.jnb1:/export/glusterfs# df -h > Filesystem Size Used Avail Use% Mounted on > /dev/md2 50G 1.6G 46G 4% / > none 997M 200K 997M 1% /dev > none 1004M 0 1004M 0% /dev/shm > none 1004M 72K 1004M 1% /var/run > none 1004M 0 1004M 0% /var/lock > /dev/md3 1.7T 1.7T 0 100% /export/glusterfs > /dev/md0 230M 26M 193M 12% /boot > > > du only finds about 23GB of data on the filesystem. After rebooting the > Gluster server disk usage is reported accurately by df. > > nic at gluster01:~$ df -h > Filesystem Size Used Avail Use% Mounted on > /dev/md2 50G 1.6G 46G 4% / > none 997M 200K 997M 1% /dev > none 1004M 0 1004M 0% /dev/shm > none 1004M 68K 1004M 1% /var/run > none 1004M 0 1004M 0% /var/lock > none 50G 1.6G 46G 4% /var/lib/ureadahead/debugfs > /dev/md0 230M 26M 193M 12% /boot > /dev/md3 1.7T 23G 1.6T 2% /export/glusterfs > > Do you have any idea what would cause this to occur? > >
