Quick question regarding the Glusterfs FUSE client black magic. I currently have a gluster 3 node doing a single replica volume. On my gluster fuse client i am pointing to one of the glusterfs nodes as a mount point. I noticed after I shutdown the specific glusterfs node in question, i was still able to do reads and writes to the volume and also noticed that the changes are being made to the other replicas.
So my question is what type of black magic does the Glusterfs FUSE client have that is cluster aware?
Has glusterfs sold its soul to the devil?
I noticed that
The FUSE client allows the mount to happen with a GlusterFS “round robin” style connection. In /etc/fstab, the name of one node is used; however, internal mechanisms allow that node to fail, and the clients will roll over to other connected nodes in the trusted storage pool. The performance is slightly slower than the NFS method based on tests, but not drastically so. The gain is automatic HA client failover, which is typically worth the effect on performance.
To clarify does this mean that the FUSE client is cluster aware? If a node dies, it is able to route traffic to other nodes automatically?
Is there any other depth documentation I can read up on that?