[Gluster-users] glusterd crashed

Fri May 8 05:07:54 UTC 2015

Hi,

We've been using glusterfs for 1 years，It’s greadt except occasional glusterd crashed, and just need restart

But nowadays, Glusterd crashed more frequently, sometimes several glusterds crashed and cause split-brain and gfid different

Our environment: Centos 6.4  Gluster 3.4.2

[root at SVR4666HW2285 ~]# service glusterd status

glusterd dead but pid file exists

When glusterd crashed, We can see linux swap exhausted and then released

Then glustershd.log filled with “readv failed”

[2015-05-07 12:40:53.580605] W [socket.c:514:__socket_rwv] 0-glusterfs: readv failed (No data available)

[2015-05-07 12:40:53.609217] W [socket.c:1962:__socket_proto_state_machine] 0-glusterfs: reading from socket failed. Error (No data available), peer (127.0.0.1:24007)

[2015-05-07 12:41:03.837798] E [socket.c:2157:socket_connect_finish] 0-glusterfs: connection to 127.0.0.1:24007 failed (Connection refused)

[2015-05-07 12:41:03.837853] W [socket.c:514:__socket_rwv] 0-glusterfs: readv failed (No data available)

[2015-05-07 12:41:06.844262] W [socket.c:514:__socket_rwv] 0-glusterfs: readv failed (No data available)

[2015-05-07 12:41:09.847699] W [socket.c:514:__socket_rwv] 0-glusterfs: readv failed (No data available)

[2015-05-07 12:41:12.854243] W [socket.c:514:__socket_rwv] 0-glusterfs: readv failed (No data available)

Any help appreciated.

Best Regards
Young Yang
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.gluster.org/pipermail/gluster-users/attachments/20150508/6954a013/attachment.html>