I have my 4-node HA cluster up and running, and it's been working great. Last night I had a power issue (malfunctioning UPS) which caused my cluster network to go down. All nodes lost quorum. After restoring the network, everything came back up just fine, except that now I can no longer access the cluster IP. Each node works fine, they all talk to each other, and show no visible errors. I can migrate machines and everything looks happy, so I'm not sure what to do. Just in case, I rebooted each node in the cluster one at a time and it's still not accessible. Where should I look from here?
Here's my cluster.conf (passwords changed):
Here's my cluster.conf (passwords changed):
Code:
root@pve1:~# cat /etc/pve/cluster.conf
<?xml version="1.0"?>
<cluster config_version="7" name="c6100-cluster-1">
<cman keyfile="/var/lib/pve-cluster/corosync.authkey"/>
<fencedevices>
<fencedevice agent="fence_ipmilan" ipaddr="10.99.99.21" lanplus="1" login="root" name="ipmi1" passwd="asdf" power_wait="5"/>
<fencedevice agent="fence_ipmilan" ipaddr="10.99.99.22" lanplus="1" login="root" name="ipmi2" passwd="asdf" power_wait="5"/>
<fencedevice agent="fence_ipmilan" ipaddr="10.99.99.23" lanplus="1" login="root" name="ipmi3" passwd="asdf" power_wait="5"/>
<fencedevice agent="fence_ipmilan" ipaddr="10.99.99.24" lanplus="1" login="root" name="ipmi4" passwd="asdf" power_wait="5"/>
</fencedevices>
<clusternodes>
<clusternode name="pve1" nodeid="1" votes="1">
<fence>
<method name="1">
<device name="ipmi1"/>
</method>
</fence>
</clusternode>
<clusternode name="pve2" nodeid="2" votes="1">
<fence>
<method name="1">
<device name="ipmi2"/>
</method>
</fence>
</clusternode>
<clusternode name="pve3" nodeid="3" votes="1">
<fence>
<method name="1">
<device name="ipmi3"/>
</method>
</fence>
</clusternode>
<clusternode name="pve4" nodeid="4" votes="1">
<fence>
<method name="1">
<device name="ipmi4"/>
</method>
</fence>
</clusternode>
</clusternodes>
<rm>
<service autostart="1" exclusive="0" name="HAClusterIP" recovery="relocate">
<ip address="192.168.1.25"/>
</service>
<pvevm autostart="1" vmid="105"/>
<pvevm autostart="1" vmid="103"/>
</rm>
</cluster>