Hi,
I have a question about mixing tcp and rdma transport protocols... I have
recently set up a infiniband gluster with two servers, replicated and using
rdma as transport-type. I'm now trying to hook the clients into this by
mounting the gigE ip from the main gluster server (server1)... how
ok, i can upgrade ofed (will be a PITA :-)). in the interim, if i move the
gluster volume over to tcp transport, is it cleanly transportable back to
rdma once my ofed issue is resolved?
--- michael
On Thu, Oct 28, 2010 at 3:05 PM, Craig Carl wrote:
> Michael -
>I would suggest OFED 1.5.1, w
Hi,
I solved this problem by downgrading glusterfs from 3.1 to 2.0.9, could not
find the source of the problem though. I am using same configuration files
and the same setup. I just downgraded the version. For your information, I
am using rpm builds.
I think it was a bug in the 3.1 build or missi
On 10/29/2010 12:23 PM, Horacio Sanson wrote:
The problem is that if I run any rails application when stored in the gluster
volume it take minutes to start and then each page load take 5~10 secs. If
instead I run the rails app from the local hard disk in the same machine it
goes fast as thunder.
On Oct 28, 2010, at 5:00 PM, Matt Sorin wrote:
> Can someone please tell me what I have done incorrectly?
Matt,
You have run into this bug:
http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2027
This has been fixed in the repository and will be available in the next
release. Until t
Hello,
I'm trying to set up an experimental gluster storage cluster using virtual
machines (VMs) on Xen. I want to be able to instruct the VMs to "forget"
any previous gluster configuration (i.e. the server to forget about all
previously configured peers, the peers to forget what storage volumes
I want to set up distribute/replicate and I want to know if I can set up a
dedicated subnet for replication?
Regards,
John
___
Gluster-users mailing list
Gluster-users@gluster.org
http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Hi Shehjar:
On Thu, Oct 28, 2010 at 12:34 AM, Shehjar Tikoo wrote:
> Thats not recommended but I can see why this is needed. The simplest way to
> run the nfs server for the two replicas is to simply copy over the nfs
> volume file from the current nfs server. It will work right away. The volume
Am 29.10.2010 18:23, schrieb Horacio Sanson:
[ ... rails via gluster mount ]
Hi Horacio,
The questions:
Am I doing something wrong or missing something or is this expected?
I don't think you are doing something wrong. We tried the same (serving
rails apps off of gluster mounts) and perfo
It would be better to have the rails application files on the local disk
and use the Gluster storage for images and other content that is uploaded.
The main reason for this is that a single access on a rails application
might result in the webserver having to read 20 small files. When you add
up t
Joe,
I believe that everything Gluster knows about is stored in /etc/glusterd by
default. I have just been removing this directory after shutting down services
whenever I want to test something from scratch.
Mike Robbert
On Oct 29, 2010, at 11:53 AM, Joe Whitney wrote:
> Hello,
>
> I'm trying
GlusterFS 3.1.0, distributed volumes, rdma transport, CentOS 5.4/5.5.
I was doing "tail -f" on a log file while the program generating it
was running and noticed some strange behavior. I wasn't able to
reproduce exactly the same strange behavior, but here is some which
did reproduce for me reliab
Thanks, that seems to work.
On Fri, Oct 29, 2010 at 4:33 PM, Michael Robbert wrote:
> Joe,
> I believe that everything Gluster knows about is stored in /etc/glusterd by
> default. I have just been removing this directory after shutting down
> services whenever I want to test something from scrat
13 matches
Mail list logo