Hi,
I am trying to ceph-deploy with Hammer on rhel7. While trying to activate
the OSD using ceph-deploy on admin-node, the below step hangs. I tried to
run it manually on the osd-node and tried tracing using "python -m trace
--trace" . It looks like it is stuck in some threading.py code. Can someone
please help?
[*ceph-vm-osd1*][*WARNIN*] INFO:ceph-disk:Running command: /usr/bin/ceph
--cluster ceph --name client.bootstrap-osd --keyring
/var/lib/ceph/bootstrap-osd/ceph.keyring osd create --concise
c2d19639-f3ec-447d-9a7c-a180a226dded
[*ceph-vm-osd1*][*WARNIN*] No data was received after 300 seconds,
disconnecting...
*Manual run with --verbose option:*
[cloud-user@ceph-vm-osd1 ~]$ sudo /usr/bin/ceph --verbose --cluster ceph
--name client.bootstrap-osd --keyring
/var/lib/ceph/bootstrap-osd/ceph.keyring osd create
c2d19639-f3ec-447d-9a7c-a180a226dded
parsed_args: Namespace(admin_socket=None, admin_socket_nope=None,
cephconf=None, client_id=None, client_name='client.bootstrap-osd',
cluster='ceph', cluster_timeout=None, completion=False, help=False,
input_file=None, output_file=None, output_format=None, status=False,
verbose=True, version=False, watch=False, watch_debug=False,
watch_error=False, watch_info=False, watch_sec=False, watch_warn=False),
childargs: ['--keyring', '/var/lib/ceph/bootstrap-osd/ceph.keyring', 'osd',
'create', 'c2d19639-f3ec-447d-9a7c-a180a226dded']
^CError connecting to cluster: InterruptedOrTimeoutError
*Manual run with python -m trace --trace :*
<<truncated>>
--- modulename: threading, funcname: _note
threading.py(64): if self.__verbose:
threading.py(946): self.__block.acquire()
threading.py(947): try:
threading.py(948): if timeout is None:
threading.py(954): deadline = _time() + timeout
threading.py(955): while not self.__stopped:
threading.py(956): delay = deadline - _time()
threading.py(957): if delay <= 0:
threading.py(961): self.__block.wait(delay, balancing)
--- modulename: threading, funcname: wait
threading.py(331): if not self._is_owned():
--- modulename: threading, funcname: _is_owned
threading.py(302): if self.__lock.acquire(0):
threading.py(306): return True
threading.py(333): waiter = _allocate_lock()
threading.py(334): waiter.acquire()
threading.py(335): self.__waiters.append(waiter)
threading.py(336): saved_state = self._release_save()
--- modulename: threading, funcname: _release_save
threading.py(294): self.__lock.release() # No state to
save
threading.py(337): try: # restore state no matter what (e.g.,
KeyboardInterrupt)
threading.py(338): if timeout is None:
threading.py(348): endtime = _time() + timeout
threading.py(349): delay = 0.0005 # 500 us -> initial delay
of 1 ms
threading.py(350): while True:
threading.py(351): gotit = waiter.acquire(0)
threading.py(352): if gotit:
threading.py(354): remaining = endtime - _time()
threading.py(355): if remaining <= 0:
threading.py(357): if balancing:
threading.py(358): delay = min(delay * 2,
remaining, 0.05)
threading.py(361): _sleep(delay)
--- modulename: threading, funcname: _note
threading.py(64): if self.__verbose:
--- modulename: threading, funcname: __stop
threading.py(870): if not hasattr(self, '_Thread__block'):
threading.py(872): self.__block.acquire()
threading.py(873): self.__stopped = True
threading.py(874): self.__block.notify_all()
--- modulename: threading, funcname: notifyAll
threading.py(409): self.notify(len(self.__waiters))
--- modulename: threading, funcname: notify
threading.py(385): if not self._is_owned():
--- modulename: threading, funcname: _is_owned
threading.py(302): if self.__lock.acquire(0):
threading.py(306): return True
threading.py(387): __waiters = self.__waiters
threading.py(388): waiters = __waiters[:n]
threading.py(389): if not waiters:
threading.py(393): self._note("%s.notify(): notifying %d waiter%s",
self, n,
threading.py(394): n!=1 and "s" or "")
--- modulename: threading, funcname: _note
threading.py(64): if self.__verbose:
threading.py(395): for waiter in waiters:
threading.py(396): waiter.release()
threading.py(397): try:
threading.py(398): __waiters.remove(waiter)
threading.py(395): for waiter in waiters:
threading.py(875): self.__block.release()
threading.py(350): while True:
threading.py(351): gotit = waiter.acquire(0)
threading.py(352): if gotit:
threading.py(353): break
threading.py(362): if not gotit:
threading.py(371): self._note("%s.wait(%s): got
it", self, timeout)
--- modulename: threading, funcname: _note
threading.py(64): if self.__verbose:
threading.py(373): self._acquire_restore(saved_state)
--- modulename: threading, funcname: _acquire_restore
threading.py(297): self.__lock.acquire() # Ignore saved
state
threading.py(955): while not self.__stopped:
threading.py(964): self._note("%s.join(): thread
stopped", self)
--- modulename: threading, funcname: _note
threading.py(64): if self.__verbose:
threading.py(966): self.__block.release()
rados.py(178): if timeout and t.is_alive():
rados.py(176): while t.is_alive():
--- modulename: threading, funcname: isAlive
threading.py(1004): assert self.__initialized, "Thread.__init__()
not called"
threading.py(1005): return self.__started.is_set() and not
self.__stopped
--- modulename: threading, funcname: isSet
threading.py(572): return self.__flag
rados.py(183): t.join() # in case t exits before reaching
the join() above
--- modulename: threading, funcname: join
threading.py(936): if not self.__initialized:
threading.py(938): if not self.__started.is_set():
--- modulename: threading, funcname: isSet
threading.py(572): return self.__flag
threading.py(940): if self is current_thread():
--- modulename: threading, funcname: currentThread
threading.py(1160): try:
threading.py(1161): return _active[_get_ident()]
threading.py(944): if not self.__stopped:
threading.py(946): self.__block.acquire()
threading.py(947): try:
threading.py(948): if timeout is None:
threading.py(949): while not self.__stopped:
threading.py(952): self._note("%s.join(): thread
stopped", self)
--- modulename: threading, funcname: _note
threading.py(64): if self.__verbose:
threading.py(966): self.__block.release()
rados.py(193): if interrupt:
rados.py(195): return t.retval
rados.py(265): self.state = "shutdown"
ceph(916): sys.exit(retval)
--- modulename: trace, funcname: _unsettrace
Thanks,
Pavana
_______________________________________________
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
