On Fri, Sep 8, 2017 at 12:43 PM, Diego Remolina <dijur...@gmail.com> wrote: > This is exactly the problem, > > Systemctl stop glusterd does *not* kill the brick processes.
Yes, I now. > On CentOS with gluster 3.10.x there is also a service, meant to only stop > glusterfsd (brick processes). I think the reboot process may not be properly > stopping glusterfsd or network or firewall may be stopped before glusterfsd > and so the nodes go into the long timeout. I think reboot should switch init to level 1 and processes are gracefully terminated - same as killall... > Once again , in my case a simple reboot hangs my VMs, whereas stopping > glusterd *and* glusterfsd processes, then reboot works perfectly. Testing it now... _______________________________________________ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
