There has been discussion in the past about improvement in the way glusterfs
handles unequal components in a distribute, for instance unequal size brick
pairs in a distribute/replicate cluster. Has this happened and I missed it?
I don't see this listed as a feature in any of the new glusterfs
Thank you. This is the main new feature I care about in glusterfs (except, of
course, stability).
--- Bill Sebok
On Thu, Jan 16, 2014 at 05:41:28PM -0500, Jeffrey Darcy wrote:
- Original Message -
There has been discussion in the past about improvement in the way glusterfs
I have a cluster whose members are connected with a private network. I want to
export a glusterfs volume and also root directories to run some diskless
computers. I don't quite trust gluster nfs enough to do diskless booting off of
a gluster volume so I want to use kernel nfs for them. The
This is another reason why it there *really* should be a way with the CLI to
have an option that GlusterNFS be enabled on only one machine in a cluster
(I've asked for that before). Our cluster has a private network. Inside the
cluster private network I use native glusterfs mounts. Outside the
Is there any reason why this bug is Access Denied to us mortals? I was also
denied after I logged in to Redhat bugzilla.
Bill Sebok Computer Software Manager, Univ. of Maryland, Astronomy
Internet: w...@astro.umd.eduURL: http://furo.astro.umd.edu/
On Wed, Dec 14, 2011 at
This looks like the messages that were worrying me. I'm still getting timeouts
on nfs mounts.
Bill Sebok Computer Software Manager, Univ. of Maryland, Astronomy
Internet: w...@astro.umd.eduURL: http://furo.astro.umd.edu/
On Wed, Dec 07, 2011 at 10:33:58AM -0600, Matt Weil
On Wed, Dec 07, 2011 at 11:16:54PM +0530, Pranith Kumar K wrote:
William,
In which log do you see the messages?.
Pranith
/var/log/etc-glusterfs-glusterd.vol.log on any of the servers.
I now have determined that I need to add a nfsvers=3 on mount on the client I
was using as a test.
I remember seeing instructions given recently on how to revert a glusterfs
setup from 3.2.* back to 3.1.*. Does anyone remember those instructions?
Today I I upgraded a cluster from glusterfs 3.1.5 to 3.2.5 and have ended up
with many log errors of this sort:
[2011-12-06 19:19:56.300768] W
It also won't work well when the bricks are under use and might be changing.
Bill Sebok Computer Software Manager, Univ. of Maryland, Astronomy
Internet: w...@astro.umd.eduURL: http://furo.astro.umd.edu/
On Thu, Mar 10, 2011 at 09:39:44AM -0800, Mohit Anchlia wrote:
It doesn't
For me these are top critical items:
1) Stability
2) A way of deleting nodes without losing files (adequate space in remaining
nodes permitting)
3) Performance
4) Documentation
Bill Sebok Computer Software Manager, Univ. of Maryland, Astronomy
Internet: w...@astro.umd.eduURL:
On Tue, Feb 15, 2011 at 11:49:06PM -0600, Rahul C S wrote:
For the last question,
remove-brick command does not migrate data, the data in that brick cannot
be accessed from the client unlike replace-brick which actually migrates
data from one brick to the another.
I strongly suggest for an
Adding an option to disable the Gluster NFS server is in the works
(http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2094).
Previous versions of Gluster just re-exported the native client to a
uNFS or kNFS service. I think the closer integration may have resolved a
lot of these
/2010 10:30 AM, William L. Sebok wrote:
Many of the computers in our cluster are diskless and those computers
need to
have disk space exported to them. The space for diskless booting is
supplied
by a server within the cluster that does have disks and that also
supplies a
couple of bricks
Many of the computers in our cluster are diskless and those computers need to
have disk space exported to them. The space for diskless booting is supplied
by a server within the cluster that does have disks and that also supplies a
couple of bricks to a glusterfs file system. The space for
14 matches
Mail list logo