Detect missing 'user' process

'user' process can be unrecoverably crashed with good timing. As a
result some rabbitmqctl commands will stop working, e.g. add_user:

    rabbitmqctl -n rabbit@localhost add_user ley ley
    Creating user "ley" ...
    Error: {badarg,
           [{erlang,group_leader,[undefined,<5428.28745.44>],[]},
            {rabbit_log,with_local_io,1,
                [{file,"src/rabbit_log.erl"},{line,99}]},
            {rabbit_auth_backend_internal,add_user,2,
                [{file,"src/rabbit_auth_backend_internal.erl"},{line,149}]},
            {rpc,'-handle_call_call/6-fun-0-',5,
                [{file,"rpc.erl"},{line,206}]}]}

Exact sequence events that will crash 'user' is the following:
- Move startup_log file to a separate partition
- Start server
- Fill partition to the fullest
- Do stop_app/start_app several times, so all the remaning slack will be
  used by log records.
- At some point 'user' will crash.
- Free some space on partition with startup_log
- Observe that any rabbit action that requires logging is now broken

0 files changed, 0 insertions, 0 deletions