Re: non-blocking connect() returned: 111 (Connection refused)

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Jordi,
  Do you have any firewall running on machines?

--
gowda

On Thu, Dec 18, 2008 at 1:47 PM, Jordi Moles Blanco <jordi@xxxxxxxxx> wrote:
En/na Raghavendra G ha escrit:
Hi Jordi,

Have you started glusterfsd on each of the newly added nodes? If not, please start them.

some comments have been inlined.

On Wed, Dec 17, 2008 at 3:28 PM, Jordi Moles Blanco <jordi@xxxxxxxxx <mailto:jordi@xxxxxxxxx>> wrote:

   Hi,

   i've got 6 nodes providing a storage unit with gluster 2.5 patch
   800. They are set in 2 groups of 3 nodes each.

   On top of that, i've got a Xen 3.2 machine storing its virtual
   machines in gluster mount point.

   The thing is that i used to have only 2 nodes for group, that's 4
   nodes in total, and today I'm trying to add 1 extra node for each
   group.

   This is the final setting on Xen's Side:


   **************

   volume espai1
         type protocol/client
         option transport-type tcp/client
         option remote-host 10.0.0.3
         option remote-subvolume espai
   end-volume

   volume espai2
         type protocol/client
         option transport-type tcp/client
         option remote-host 10.0.0.4
         option remote-subvolume espai
   end-volume

   volume espai3
         type protocol/client
         option transport-type tcp/client
         option remote-host 10.0.0.5
         option remote-subvolume espai
   end-volume

   volume espai4
     type protocol/client
     option transport-type tcp/client
     option remote-host 10.0.0.6
     option remote-subvolume espai
   end-volume

   volume espai5
     type protocol/client
     option transport-type tcp/client
     option remote-host 10.0.0.7
     option remote-subvolume espai
   end-volume

   volume espai6
     type protocol/client
     option transport-type tcp/client
     option remote-host 10.0.0.8
     option remote-subvolume espai
   end-volume

   volume namespace1
         type protocol/client
         option transport-type tcp/client
         option remote-host 10.0.0.4
         option remote-subvolume nm
   end-volume

   volume namespace2
         type protocol/client
         option transport-type tcp/client
         option remote-host 10.0.0.5
         option remote-subvolume nm
   end-volume

   volume grup1
         type cluster/afr
         subvolumes espai1 espai3 espai5
   end-volume

   volume grup2
         type cluster/afr
         subvolumes espai2 espai4 espai6
   end-volume

   volume nm
         type cluster/afr
         subvolumes namespace1 namespace2
   end-volume

   volume g01
         type cluster/unify
         subvolumes grup1 grup2
         option scheduler rr
         option namespace nm
   end-volume

   volume io-cache
         type performance/io-cache
         option cache-size 512MB
         option page-size 1MB
         option force-revalidate-timeout 2
         subvolumes g01
   end-volume  
   **************

   so... i stopped all virtual machines, unmounted gluster on Xen,
   updated the spec file (the one above) and ran gluster again in Xen.

   I've set different gluster environments but i had never tried
   this, and now i'm facing some problems.

   For what i had read before this... i used to think that when
   adding and extra node to a group and "remounting" on client's
   side, the Healing feature would copy all the content of the other
   nodes already present in the group to the "new one". That hasn't
   happened, even when I've tried to force the file system, by
   listing the files or doing what you suggest in you documentation:

   **********

   find /mnt/glusterfs -type f -print0 | xargs -0 head -c1 >/dev/null

   **********

   so... my first question would be... does "self-healing" work this
   way? If it doesn't.... which is the best way to add a node to a
   group? Do i have to run a "copy" command manually to get the new
   node ready?
   I've also noticed that i have necessarily to umount gluster from
   Xen. Is there a way to avoid stopping all the virtual machines,
   umounting and mounting again? Is there a feature like "refresh
   config file"?


Hot add ("refresh config file") is in the roadmap.
 


   And finally... i looked into the logs to see why self-healing
   wasn't working, and i found this on Xen's Side:

   **********
   2008-12-17 12:08:30 E [tcp-client.c:190:tcp_connect] espai6:
   non-blocking connect() returned: 111 (Connection refused)
   **********

   and it keeps saying this when i want to access  files which were
   created in the "old nodes".

   is this a bug? how can i work around this?

   If i create new stuff, though, it replicates to the 3 nodes, no
   problem with that.... the only problem is with the old files that
   were already present before i added the new node.

   Thanks for your help in advance, and let me know if you need any
   further information.




   _______________________________________________
   Gluster-devel mailing list
   Gluster-devel@xxxxxxxxxx <mailto:Gluster-devel@xxxxxxxxxx>

hi, yes.

when gluster behaves like this, all nodes are running. As i said, when you create new data, it replicates to all the nodes of each group, so it's working fine.
However, it keeps logging "connection refused", which i though was reported only when a node wasn't available, but they are all available and replicating data fine.

The thing, though, is that old data is not beeing replicated into the new nodes?

Is there any way to "force" replication to the new nodes? Could i be getting somehow the "connection refused" because new nodes won't accept previous data?

Thanks for your help.



_______________________________________________
Gluster-devel mailing list
Gluster-devel@xxxxxxxxxx
http://lists.nongnu.org/mailman/listinfo/gluster-devel



--
hard work often pays off after time, but laziness always pays off now

[Index of Archives]     [Gluster Users]     [Ceph Users]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Security]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux