[Gluster-users] Change transport type on volume from tcp to rdma

[Ivan Dimitrov]

What I did was:

gluster volume stop VOLUME
gluster volume delete VOLUME

On each peer on each brick I did:
setfattr -x trusted.glusterfs.volume-id /mnt/brick1
setfattr -x trusted.gfid /mnt/brick1
setfattr -x trusted.glusterfs.volume-id /mnt/brick2
setfattr -x trusted.gfid /mnt/brick2
rm -r /mnt/brick1/.glusterfs/
rm -r /mnt/brick2/.glusterfs/

gluster 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 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 setup and working with x2 bricks each. They have been
>>> working via tcp for the last 4-5 months.
>>> I just got two Infiniband cards and put the on the peers. I want to
>>> change the transport type to rdma instead of tcp but I don't see an 
>>> easy
>>> way to do this.
>>> Can you please help me with proper instructions.
>>>
>>
>> Hi Ivan,
>>
>> You are asking for a feature which just got merged upstream 
>> (http://review.gluster.org/4008). This will make it to 3.4.0 release, 
>> till then the functionality you are asking will not be available.
>>
>> Regards,
>> Amar
>>
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://supercolony.gluster.org/mailman/listinfo/gluster-users
>