On 10/24/2011 02:16 PM, Robert Krig wrote:> I've been reading the documentation, but I'm a bit stumped as to
how to
> setup geo-replication with glusterfs.
>
> The documentation mentions that you use an existing glusterfs volume to
> start geo replication. But what kind of volume? Do you just create a
> standard replicated volume with a replica count of 1?
Geo-rep only needs the volume name. You can create volume of any type
(plain distribute, replicate, distribute-replicate etc...) and use it as
the master volume for geo-replication. Suppose you have a
distribute-replicate volume called 'vol-dr' then you start geo-rep by:
# gluster volume geo-replication vol-dr <slave> start
Geo-rep internally mounts this volume (FUSE mount), hence it does not
care about the volume layout, it just *looks* at the unified namespace
you get by mounting the volume.
> Could somebody outline the steps for geo-replication?
>
>
> Also, does geo-replication perform better than replication?
Geo-rep is a continuous mirroring of data from master to slave. The
slave can be a file system path or a gluster mount (both of them can be
local or remote). While replicate mirrors data cross clusters, geo-rep
mirrors data across geographically distributes clusters.
Check this out for the differences:
http://www.gluster.com/community/documentation/index.php/Gluster_3.2:_Replicated_Volumes_vs_Geo-replication
> In our setup we need redundancy, but more as a fail-safe backup option,
> rather than a load balancing setup. We just want to be able to quickly
> switch to our backup server, if our primary server should go down for
> any reason.
> Would a geo-replication setup with GlusterFS have better read and write
> performance, since the slave can lag behind a bit?
>
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://gluster.org/cgi-bin/mailman/listinfo/gluster-users