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

[Linux-cluster] waiting for glock: pid does not exists



Hello,

we are trying to run OpenVZ on a GFS2. We copied a virtual machine to
the GFS2 storage (on node1) and added the service to cluster.conf. After
reloading the configuration on all nodes, rgmanager was trying to start
the virtual machine on node3. That is not working and now the machine is
hanging with a lock.

This is the result of the gfs2 hang analyzer:

There are 4 glocks with waiters.
node1, pid 2674 is waiting for glock 3/8389396, which is held by pid 6821
node3, pid 7024 is waiting for glock 3/8389396, which is held by pid 6821


node1, pid 10188 is waiting for glock 2/1857345, which is held by pid 6821
node3, pid 6772 is waiting for glock 2/1857345, which is held by pid 6821
node3, pid 7251 is waiting for glock 2/1857345, which is held by pid 6821
node3, pid 7289 is waiting for glock 2/1857345, which is held by pid 6821


carl, pid 23817 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 4243 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7055 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7090 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7129 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7176 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7230 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7270 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7306 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7345 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7369 is waiting for glock 2/394135, which is held by pid 7024
node3, pid 7402 is waiting for glock 2/394135, which is held by pid 7024


node3, pid 6821 is waiting for glock 5/8425127, which is held by pid 7258



The pid 6821 is still running on node3:

root      6821  0.0  0.0  12216   696 ?        D<   08:29   0:00 /bin/cp
-fp /etc/hosts /etc/hosts.12

The problem pid is 7258 - but I can not find this process running on any
node. Any idea what is the problem here?

Mario


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