<div dir="ltr"><div><div>Gluster 3.7.5, gluster repos, on proxmox (debian 8) <br><br>I have an issue with VM images (qcow2) being corrupted.<br><br></div>- gluster replica 3, shards on, shard size = 256MB<br></div><div>- Gluster nodes are all also VM host nodes<br></div><div>- VM image mounted from qemu via gfapi<br><br></div><div>To reproduce<br></div><div>- Start VM<br></div><div>- live migrate it to another node<br></div><div>- VM will rapidly become unresponsive and have to be stopped<br></div><div>- attempting to restart the vm results in a "qcow2: Image is corrupt; cannot be opened read/write" error.<br><br></div><div>I have never seen this before. 100% reproducible with shards on, never happens with shards off.<br><br></div><div>I don't think this happens when using NFS to access the shard volume, I suspect because with NFS it is still accessing the one node, whereas with gfapi it's handed off to the node the VM is running on.<br></div><div><br></div><br clear="all"><div><div><div><br>-- <br><div class="gmail_signature">Lindsay</div>
</div></div></div></div>