[Gluster-users] Unable to peer probe between new servers and old servers

Michael Bushey michael at realtymogul.com
Wed Jan 7 21:44:48 UTC 2015


I have two production machines (web1, web2) that are currently using
Glusterfs. I added two new machines, web3 and web4. Web1 and web2 are
peered and are running great. Web3 and web4 will peer with each other but
web1 and web2 will not peer with web3 or web4 and vice versa.

All machines are running Gluster 3.6.1:
ii  glusterfs-client               3.6.1-1
amd64        clustered file-system (client package)
ii  glusterfs-common               3.6.1-1
amd64        GlusterFS common libraries and translator modules
ii  glusterfs-server               3.6.1-1
amd64        clustered file-system (server package)

I ran "gluster volume set all cluster.op-version 30600" on web2, now all
four machines have "operating-version=30600" in /var/lib/glusterd/
glusterd.info

All machines have the same kernel:
Linux web1 3.16.0-4-amd64 #1 SMP Debian 3.16.7-ckt2-1 (2014-12-08) x86_64
GNU/Linux

/etc/hosts is managed with Ansible, all machines resolve by their names
(web1, web2, web3, web4) to their internal IP.

"hping3 -8 111,2049,24007,49152-49162 -S [web1-web4]" shows all Gluster
ports open from all servers.

root at web1:~# gluster peer probe web2
peer probe: success. Host web2 port 24007 already in peer list
root at web1:~# gluster peer probe web3
peer probe: failed: Probe returned with unknown errno 107
root at web1:~# gluster peer probe web4
peer probe: failed: Probe returned with unknown errno 107


root at web3:~# gluster peer probe web1
peer probe: failed: Probe returned with unknown errno 107
root at web3:~# gluster peer probe web2
peer probe: failed: Probe returned with unknown errno 107
root at web3:~# gluster peer probe web4
peer probe: success. Host web4 port 24007 already in peer list


from /var/log/glusterfs/cli.log:

[2015-01-07 20:38:33.978304] T [cli.c:264:cli_rpc_notify] 0-glusterfs: got
RPC_CLNT_CONNECT
[2015-01-07 20:38:33.978322] T [cli-quotad-client.c:94:cli_quotad_notify]
0-glusterfs: got RPC_CLNT_CONNECT
[2015-01-07 20:38:33.978333] I [socket.c:2344:socket_event_handler]
0-transport: disconnecting now
[2015-01-07 20:38:33.978354] T [cli-quotad-client.c:100:cli_quotad_notify]
0-glusterfs: got RPC_CLNT_DISCONNECT
[2015-01-07 20:38:33.978622] T [rpc-clnt.c:1381:rpc_clnt_record]
0-glusterfs: Auth Info: pid: 0, uid: 0, gid: 0, owner:
[2015-01-07 20:38:33.978681] T
[rpc-clnt.c:1238:rpc_clnt_record_build_header] 0-rpc-clnt: Request fraglen
144, payload: 80, rpc hdr: 64
[2015-01-07 20:38:33.979037] T [socket.c:2863:socket_connect] (-->
/usr/lib/x86_64-linux-gnu/libglusterfs.so.0(_gf_log_callingfn+0x1cd)[0x7f9e8ef0ac1d]
(-->
/usr/lib/x86_64-linux-gnu/glusterfs/3.6.1/rpc-transport/socket.so(+0x637c)[0x7f9e8bcc637c]
(-->
/usr/lib/x86_64-linux-gnu/libgfrpc.so.0(rpc_clnt_submit+0x3a4)[0x7f9e8e40fad4]
(--> gluster(cli_submit_request+0x15f)[0x7f9e8f3c52df] (-->
gluster(cli_cmd_submit+0x8b)[0x7f9e8f3c6eeb] ))))) 0-glusterfs: connect ()
called on transport already connected
[2015-01-07 20:38:33.979100] T [rpc-clnt.c:1573:rpc_clnt_submit]
0-rpc-clnt: submitted request (XID: 0x1 Program: Gluster CLI, ProgVers: 2,
Proc: 1) to rpc-transport (glusterfs)
[2015-01-07 20:38:33.979111] D [rpc-clnt-ping.c:231:rpc_clnt_start_ping]
0-glusterfs: ping timeout is 0, returning
[2015-01-07 20:38:33.986269] T [rpc-clnt.c:660:rpc_clnt_reply_init]
0-glusterfs: received rpc message (RPC XID: 0x1 Program: Gluster CLI,
ProgVers: 2, Proc: 1) from rpc-transport (glusterfs)
[2015-01-07 20:38:33.986311] I [cli-rpc-ops.c:131:gf_cli_probe_cbk] 0-cli:
Received resp to probe
[2015-01-07 20:38:33.986321] E [cli-rpc-ops.c:136:gf_cli_probe_cbk] 0-cli:
Probe returned with unknown errno 107
[2015-01-07 20:38:33.986620] D [cli-cmd.c:384:cli_cmd_submit] 0-cli:
Returning -1
[2015-01-07 20:38:33.986638] D [cli-rpc-ops.c:3021:gf_cli_probe] 0-cli:
Returning -1
[2015-01-07 20:38:33.986650] D [cli-cmd-peer.c:96:cli_cmd_peer_probe_cbk]
0-cli: frame->local is not NULL (0x7f9e7c000980)
[2015-01-07 20:38:33.986667] I [input.c:36:cli_batch] 0-: Exiting with: -1



Thanks in advance for any help.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.gluster.org/pipermail/gluster-users/attachments/20150107/6945f75b/attachment.html>


More information about the Gluster-users mailing list