--- Anton Khalikov <anton@xxxxxxxxxxx> wrote: > In fact it works different. When failed node comes > up, it starts to resync. From client's point it looks > like file becomes 0 bytes length and then start > growing up to the length it had before. I do not think that this is normal behavior, it sounds like a bug. Subvolumes which are being healed should see this behavior, but not the mounted client glusterfs filesystem. -Martin