The 'Better peer identification' part is completed. GlusterD can now
correctly identify the mentioned peer, regardless of the type of name
used (IP, FQDN, short name). It also laid down a framework on which we
can build a nice multi-interface support in the future, as we can now
associate multiple
On 2014-11-13 20:15, Jeff Darcy wrote:
AFAIK multiple network scenario only works if you are not using Gluster via
FUSE mounts or gfapi from remote hosts. It will work for NFS access or when
you set up something like Samba with CTDB. Just not with native Gluster as
the server always tells the
Heartbeats, quorums, etc.
should also be aware of multi-homed hosts.
Definitely for that feature.
I have spent the last six years managing an SGI Clustered XFS setup.
The heartbeat for CXFS tends to run on a completely private network - a set of
dumb switches, and interfaces which carry no
What if the gluster servers are also clients? I locally plan to use
a number of servers acting as gluster and VM servers, so that gluster serves
both the VM's and other clients.
I think that fits fairly well into this paradigm. Note that the routing of
traffic is by *type* (e.g. user I/O,
On 2014-11-14 16:03, Jeff Darcy wrote:
What if the gluster servers are also clients? I locally plan to use
a number of servers acting as gluster and VM servers, so that gluster serves
both the VM's and other clients.
I think that fits fairly well into this paradigm. Note that the routing of
On Thu, 13 Nov 2014 14:15:24 -0500 (EST)
Jeff Darcy jda...@redhat.com wrote:
AFAIK multiple network scenario only works if you are not using
Gluster via FUSE mounts or gfapi from remote hosts. It will work
for NFS access or when you set up something like Samba with CTDB.
Just not with
Forgive me for a stupid question, I hav looked at the Wiki page on multiple
networks.
If I have a set of Gluster storage servers which have both a gigabit network
connection and a 10Gig network connection
(or an Infiniband network connection) how do I make sure the Gluster traffic
goes over
AFAIK multiple network scenario only works if you are not using Gluster
via FUSE mounts or gfapi from remote hosts. It will work for NFS access
or when you set up something like Samba with CTDB. Just not with native
Gluster as the server always tells the clients which addresses to
connect to:
AFAIK multiple network scenario only works if you are not using Gluster via
FUSE mounts or gfapi from remote hosts. It will work for NFS access or when
you set up something like Samba with CTDB. Just not with native Gluster as
the server always tells the clients which addresses to connect to:
Hi all
may I just add a question to the topic?
In a scenario with (say) two or three servers, one distributed volume,
native (fuse) clients, and stable filesystems with more read than write
operations, what is the typical amount of traffic between the servers,
compared to the client-server
On Thu, 13 Nov 2014 06:06:28 PM Alex Crow wrote:
AFAIK multiple network scenario only works if you are not using Gluster via
FUSE mounts or gfapi from remote hosts. It will work for NFS access or when
you set up something like Samba with CTDB. Just not with native Gluster as
the server always
11 matches
Mail list logo
