Gluster users - Oct 2009 - Gluster 2-Node like DRBD - poor performance and not-redundant?

Hi guys

I've been playing around with GlusterFS because I was hoping to replace
DRBD with it. Maybe I'm getting something wrong, but it doesn't seem as
robust or dependable as DRBD.
I just want to setup 2 GlusterFS with striping (I believe the correct
term is really AFR with GlusterFS), for high availability.

So far I've found the performance very slow, with 3-7MB/s and that if
you shut down one GlusterFS server, you will get "Transport endpoint is
not connected" when trying to write data.

Here are my config files:


### Add client feature and attach to remote subvolume of server1
volume brick1
type protocol/client
option transport-type tcp/client
option remote-host 192.168.1.21 # IP address of the remote brick
option remote-subvolume brick # name of the remote volume
end-volume

### Add client feature and attach to remote subvolume of server2
volume brick2
type protocol/client
option transport-type tcp/client
option remote-host 192.168.1.22 # IP address of the remote brick
option remote-subvolume brick # name of the remote volume
end-volume

### The file index on server1
volume brick1-ns
type protocol/client
option transport-type tcp/client
option remote-host 192.168.1.21 # IP address of the remote brick
option remote-subvolume brick-ns # name of the remote volume
end-volume

### The file index on server2
volume brick2-ns
type protocol/client
option transport-type tcp/client
option remote-host 192.168.1.22 # IP address of the remote brick
option remote-subvolume brick-ns # name of the remote volume
end-volume

#The replicated volume with data
volume afr1
type cluster/afr
subvolumes brick1 brick2
end-volume

#The replicated volume with indexes
volume afr-ns
type cluster/afr
subvolumes brick1-ns brick2-ns
end-volume

#The unification of all afr volumes (used for > 2 servers)
volume unify
type cluster/unify
option scheduler rr # round robin
option namespace afr-ns
subvolumes afr1
end-volume

# file: /etc/glusterfs/glusterfs-server.vol

volume posix
type storage/posix
option directory /data/export
end-volume

volume locks
type features/locks
subvolumes posix
end-volume

volume brick
type performance/io-threads
option thread-count 8
subvolumes locks
end-volume

volume posix-ns
type storage/posix
option directory /data/export-ns
end-volume

volume locks-ns
type features/locks
subvolumes posix-ns
end-volume

volume brick-ns
type performance/io-threads
option thread-count 8
subvolumes locks-ns
end-volume

volume server
type protocol/server
option transport-type tcp
option auth.addr.brick.allow *
option auth.addr.brick-ns.allow *
subvolumes brick brick-ns
end-volume


Any comments/help would be appreciated.

Thank you.

Hello,
It 'seems" that you are using an old 1.x version (by your conf files).
The newer 2.x version has much better performance.
Also, config files are NOT directly compatible.
You could use client-side replication, avoiding SPOF.
Each client knows were are all servers and write to all of them, in this mode.
Read the docs and examples at site for 2.x.
Good luck!
Andre Felipe