[Gluster-users] mountpoint hangs and blocks all other mounts - V. 2.0.6

[Christian Marnitz]

Hi,

I got hanging mountpoints and so the entire system hangs... on the
storage-nodes there is nothing in the log-file. On the clients (4x) I
get:


[2009-08-14 21:57:02] E [ib-verbs.c:1969:tcp_connect_finish] remote2:
tcp connect to 10.10.10.11:6997 failed (Connection refused)
[2009-08-16 23:25:29] E [ib-verbs.c:2020:ib_verbs_event_handler]
transport/ib-verbs: remote2: pollin received on tcp socket (peer:
10.10.10.11:6997) after handshake is complete
[2009-08-16 23:25:29] E [ib-verbs.c:2020:ib_verbs_event_handler]
transport/ib-verbs: remote2: pollin received on tcp socket (peer:
10.10.10.11:6997) after handshake is complete
[2009-08-16 23:25:29] E [ib-verbs.c:1969:tcp_connect_finish] remote2:
tcp connect to 10.10.10.11:6997 failed (Connection refused)


[2009-08-16 23:25:29] E [ib-verbs.c:2020:ib_verbs_event_handler]
transport/ib-verbs: remote2: pollin received on tcp socket (peer:
10.10.10.11:6997) after handshake is complete
[2009-08-16 23:25:29] E [ib-verbs.c:2020:ib_verbs_event_handler]
transport/ib-verbs: remote2: pollin received on tcp socket (peer:
10.10.10.11:6997) after handshake is complete
[2009-08-16 23:25:29] E [ib-verbs.c:1969:tcp_connect_finish] remote2:
tcp connect to 10.10.10.11:6997 failed (Connection refused)


I could kill the glusterfs-process and then restart it. All would be
fine then. Restarting the exporting-node (10.10.10.11:6997) doenst have
any effect on the mountpoint. Just the lines above are written toi the
clients logfile.

Any ideas? Many thanks in advance.

Christian Marnitz