Dear All-
My etc-glusterfs-glusterd.vol.log files are flooded with warning
messages like the following.
bdan4: [2012-01-05 18:54:30.385095] W
[socket.c:1494:__socket_proto_state_machine] 0-socket.management:
reading from socket failed. Error (Transport endpoint is not connected),
peer (192.171.166.72:993)
Some of the "peers" mentioned are actually clients but others are
GlusterFS servers. The warnings seem to occur repeatedly for a period
of time on all the servers and then stop for a while before starting
again. I have a feeling it has something to do with NFS, because it
seems to occur more frequently on servers I use to export NFS (although
all are running the glusterfs NFS process). The warnings seem to
coincide with the NFS processes restarting, as they did on all the
servers in my cluster at 16:48 today, un-noticed by me, for no apparent
reason. The warnings stopped on most servers soon after this, but they
have carried on since then on the servers that are exporting NFS.
I have been ignoring these warnings for some time because there didn't
seem to be any adverse effects, but I am trying to solve a serious
performance problem affecting some applications and I want to look at
all possible causes for concern. I have seen these warnings in log
files posted to the list in the context of various problems which I
don't have, but I have never seen them mentioned specifically. Are
these spurious warnings that can be ignored or do they point to a
problem with my cluster? Any comments or suggestions would be much
appreciated.
Regards
Dan.
_______________________________________________
Gluster-users mailing list
[email protected]
http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
