Commit 81198f6e authored by Iustin Pop's avatar Iustin Pop
Browse files

node daemon: allow working with broken queue dir



In case the queue dir cannot be create/initialized, currently
ganeti-noded exits. This means that a read-only filesystem or a
permission error breaks all node daemon functionality, including
powercycle. This is not good for the usual failure case for nodes.

To workaround this, we don't require successful initialization at node
daemon startup; if we can't init the queue dir/lock, we retry at every
RPC call requiring a job queue lock, and if we still can't acquire the
lock, we raise an exception (which is catched in HandleRequest and
transformed into an RPC failure).

This allows the node daemon to start in face of queue issues, and the
master node to power-cycle it.
Signed-off-by: default avatarIustin Pop <iustin@google.com>
Reviewed-by: default avatarMichael Hanselmann <hansmi@google.com>
parent aac3fbf0
......@@ -52,6 +52,25 @@ import ganeti.http.server # pylint: disable-msg=W0611
queue_lock = None
def _PrepareQueueLock():
"""Try to prepare the queue lock.
@return: None for success, otherwise an exception object
"""
global queue_lock # pylint: disable-msg=W0603
if queue_lock is not None:
return None
# Prepare job queue
try:
queue_lock = jstore.InitAndVerifyQueue(must_lock=False)
return None
except EnvironmentError, err:
return err
def _RequireJobQueueLock(fn):
"""Decorator for job queue manipulating functions.
......@@ -61,6 +80,9 @@ def _RequireJobQueueLock(fn):
def wrapper(*args, **kwargs):
# Locking in exclusive, blocking mode because there could be several
# children running at the same time. Waiting up to 10 seconds.
if _PrepareQueueLock() is not None:
raise errors.JobQueueError("Job queue failed initialization,"
" cannot update jobs")
queue_lock.Exclusive(blocking=True, timeout=QUEUE_LOCK_TIMEOUT)
try:
return fn(*args, **kwargs)
......@@ -803,8 +825,6 @@ def ExecNoded(options, _):
"""Main node daemon function, executed with the PID file held.
"""
global queue_lock # pylint: disable-msg=W0603
# Read SSL certificate
if options.ssl:
ssl_params = http.HttpSslParams(ssl_key_path=options.ssl_key,
......@@ -812,8 +832,12 @@ def ExecNoded(options, _):
else:
ssl_params = None
# Prepare job queue
queue_lock = jstore.InitAndVerifyQueue(must_lock=False)
err = _PrepareQueueLock()
if err is not None:
# this might be some kind of file-system/permission error; while
# this breaks the job queue functionality, we shouldn't prevent
# startup of the whole node daemon because of this
logging.critical("Can't init/verify the queue, proceeding anyway: %s", err)
mainloop = daemon.Mainloop()
server = NodeHttpServer(mainloop, options.bind_address, options.port,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment