Hi, I will soon have to deploy a glusterFS across several servers. Here are my goals : - Every server can access the all filesystem - Every file must be replicated I used a combination of Replicate and Distribute to be able to add new servers. Each server storage is divided in two bricks (primary and secondary). First server's primary storage is replicated on second server's secondary. Second server's primary is replicated on third servers secondary and so on. And then, I use Distribute across these replicated volumes. I think this should work, but could you please review the attached configuration file for errors ? Regards, -------------- next part -------------- volume posixprimary type storage/posix option directory /mnt/primary end-volume volume locksprimary type features/locks subvolumes posix end-volume volume primary type performance/io-threads subvolumes locks end-volume volume posixsecondary type storage/posix option directory /mnt/secondary end-volume volume lockssecondary type features/locks subvolumes posix end-volume volume secondary type performance/io-threads subvolumes locks end-volume volume server type protocol/server option transport-type tcp option auth.addr.brick.allow * subvolumes primary secondary end-volume volume node01p type protocol/client option transport-type tcp option remote-host node01 option remote-subvolume primary end-volume volume node01s type protocol/client option transport-type tcp option remote-host node01 option remote-subvolume secondary end-volume volume node02p type protocol/client option transport-type tcp option remote-host node02 option remote-subvolume primary end-volume volume node02s type protocol/client option transport-type tcp option remote-host node02 option remote-subvolume secondary end-volume volume node03p type protocol/client option transport-type tcp option remote-host node03 option remote-subvolume primary end-volume volume node03s type protocol/client option transport-type tcp option remote-host node03 option remote-subvolume secondary end-volume volume node01 type cluster/replicate subvolumes node01p node02s end-volume volume node02 type cluster/replicate subvolumes node02p node03s end-volume volume node03 type cluster/replicate subvolumes node03p node01s end-volume volume distribute type cluster/distribute subvolumes node01 node02 node03 end-volume volume writebehind type performance/write-behind option cache-size 1MB subvolumes distribute end-volume volume cache type performance/io-cache option cache-size 512MB subvolumes writebehind end-volume