That's a very good point. I've been evaluating glusterfs from version
1.0 and refused to use it for one and only reason: the split-brain
problem. With version 3.3 I have finally switched to glusterfs, but
after a few months of production usage, I'm thinking of going back to
separate servers wit
I have the same experiance. All comunication goes through ethernet. I
think the documentation should be changed to "NOT SUPPORTED AT ALL!",
because with my broken english I figured that there was no commercial
support for rdma, but the code is there.
On 10/19/12 9:00 PM, Bartek Krawczyk wrote:
I have an existing volume configured to use GbE and just got two
Infiniband cards. How can I reconfigure the peers to use the IPoIB?
On 10/19/12 2:48 PM, Bartek Krawczyk wrote:
Due to the lack of rdma support in 3.3.x we decided to stick with plain IPoIB.
On 10/18/12 10:48 AM, Bartek Krawczyk wrote:
On 18 October 2012 08:44, Ling Ho wrote:
If your volume is created with both tcp and rdma, my experience is rdma does
not work under 3.3.0 and it will always fall back to tcp.
I just converted from gbe to infiniband and I was cursing the entire
las
volume create VOLUME replica 2 transport rdma,tcp
peer1:brick1
peer2:brick1 peer1:brick2 peer2:brick2
Now I was able to mount with -o transport=rdma where I have
Infiniband
cards and -o transport=tcp where I have only ethernet
Best Regards
Ivan Dimitrov
On 10/10/12 4:59 PM, Ivan Dimitrov wrote:
So
Regards
Ivan Dimitrov
On 10/10/12 4:59 PM, Ivan Dimitrov wrote:
So there is no manual way to change the transport right now?
I need the transport between peers to be rdma and the transport
between clients/peers to be tcp.
Regards
Ivan Dimitrov
On 10/10/12 3:57 PM, Amar Tumballi wrote:
On 10/10
So there is no manual way to change the transport right now?
I need the transport between peers to be rdma and the transport between
clients/peers to be tcp.
Regards
Ivan Dimitrov
On 10/10/12 3:57 PM, Amar Tumballi wrote:
On 10/10/2012 04:47 PM, Ivan Dimitrov wrote:
Hello
I have two peers
lease help me with proper instructions.
Best Regards
Ivan Dimitrov
___
Gluster-users mailing list
Gluster-users@gluster.org
http://supercolony.gluster.org/mailman/listinfo/gluster-users
I agree on the fewer bricks. Also see if you can use Infiniband.
Best Regards
Ivan
On 10/2/12 11:29 PM, Robert Hajime Lanning wrote:
On 10/02/12 13:01, ja...@combatyoga.net wrote:
Basically, I'm trying to figure out if Gluster will perform better with
more storage nodes in the storage block or
y to convert my payed hosting users, but I can't
find any system suitable for the job.
Fernando, what gluster structure are you talking about?
Best Regards
Ivan Dimitrov
Fernando, what
On 8/13/12 2:16 PM, Fernando Frediani (Qube) wrote:
I heard from a Large ISP talking to someone that w
to it's architecture.
On all stat() calls (which rsync is doing plenty of), all replicas are
being checked for integrity.
regards,
Philip
2012/8/10 Ivan Dimitrov mailto:dob...@amln.net>>:
> So I stopped a node to check the BIOS and after it went up, the
rebal
Dimitrov
On 8/10/12 1:23 PM, Ivan Dimitrov wrote:
Hello
What am I doing wrong?!?
I have a test setup with 4 identical servers with 2 disks each in
distribute-replicate 2. All servers are connected to a GB switch.
I am experiencing really slow speeds at anything I do. Slow write,
slow read, not
Hello
What am I doing wrong?!?
I have a test setup with 4 identical servers with 2 disks each in
distribute-replicate 2. All servers are connected to a GB switch.
I am experiencing really slow speeds at anything I do. Slow write, slow
read, not to mention random write/reads.
Here is an exam
Hi group,
I'm in production with gluster for the last 2 weeks. No problems until
today.
As of today I've got the "Transport endpoint is not connected" problem
on the client, maybe once every hour.
df: `/services/users/6': Transport endpoint is not connected
Here is my setup:
I have 1 Client an
14 matches
Mail list logo