On Tue, Jul 31, 2012 at 02:04:25PM +0200, Christian Wittwer wrote: > b) Can I just restart glusterd on that node to trigger the self > healing? I would double-check that the underlying filesystem on unic-prd-os-compute4:/data/brick0 is OK first. Look for errors in dmesg; look at your RAID status (e.g. if it's mdraid then cat /proc/mdstat); check RAID logs, SMART logs etc.
