[Gluster-users] no luck making read local ONLY local work

[Vlad Kopylov]

Standard fuse mount - mount and brick are on the save server. 3.13 branch.
Volume created and fstab mounted via server-name from the hosts file
vm1 vm2 vm3 ... pointing to interface IP

trying:
cluster.nufa on
cluster.choose-local on
cluster.read-hash-mode: 0
cluster.choose-local on (by default)
trying to mount with xlator-option=cluster.read-subvolume-index=X

When read happens - network tops out whatever I try, making everything dead slow
Copy from the brick takes 2 sec, through mount minutes

Maybe I can use the brick directly for read? and maybe for write?
Can I just block fuse mount ports so there will be no fuse client
communication with other nodes from each server?

only non ancient doc on this I was able to find
http://lists.gluster.org/pipermail/gluster-users/2015-June/022321.html