gluster fsyncing/closing Input/output error

[syadnom]

Fresh install, get a 2 node gluster volume going on a dedicated network
cluster network (1G NICs to a switch):
p1 10.100.100.10
p2 10.100.100.11
p3 10.100.100.12 (quorum/management only)

gluster network (10G NICs direct between nodes)
p1g 10.100.101.10
p2g 10.100.101.11

create a volume 'vm' in gluster w/ replica 2 transport tcp p1g:/rpool/gluster/vm p2g:/rpool/gluster/vm and bring it online.

add it to the UI as 'vm' server1 is p1g server2 is p2g and select 'vm' for the volume

create a virtual machine on the 'vm' volume as qcow2 with virtio and boot it up. ubuntu 16.04 in this case.

When I get to partitioning, I get
"Error fsyncing/closing /dev/vda: Input/output error" "Warning!"

It sees the volume and the size I set during creation, but it seems write only.

On the CLI, I *CAN* write to /mnt/pve/vm/ which is the fuse mount prox made for it.

Any ideas?

 

[syadnom]

I should add that p1g and p2g are in /etc/hosts and do resolve out.

 

[syadnom]

All except type 'SATA' throws the error immediately. 'SATA' doesn't right away, but locks up for a few minutes and then throws the error. Have tried all disk systems with qcow backend as suggested in the wiki with the same results. Tried ubuntu 16.04 server amd64 installer, and debian 8.5 amd64 netinstaller, same results

 

[JTY]

What version of Gluster are you using? And, what file system are your bricks using?

 

[syadnom]

3.5.2 from the non-subscription prox repo, sitting on a zfs raid10

 

[JTY]

Probably best to upgrade to latest Gluster 3.7, or 3.8 from the Gluster repo. I recall some fixes recently related to issues with ZFS based bricks. That said, RedHat currently only recommends XFS for bricks.

 

[syadnom]

I couldn't get 3.8 to work with prox...