Abstract the confd client creation

[ganeti-local] / daemons / ganeti-noded

diff --git a/daemons/ganeti-noded b/daemons/ganeti-noded
index fce0d29..97feb39 100755 (executable)
--- a/daemons/ganeti-noded
+++ b/daemons/ganeti-noded
@@ -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)
@@ -323,8 +345,9 @@ class NodeHttpServer(http.server.HttpServer):
     instance = objects.Instance.FromDict(params[2])
     cluster_name = params[3]
     dev_idx = params[4]
+    debug = params[5]
     return backend.ExportSnapshot(disk, dest_node, instance,
-                                  cluster_name, dev_idx)
+                                  cluster_name, dev_idx, debug)
 
   @staticmethod
   def perspective_finalize_export(params):
@@ -332,8 +355,14 @@ class NodeHttpServer(http.server.HttpServer):
 
     """
     instance = objects.Instance.FromDict(params[0])
-    snap_disks = [objects.Disk.FromDict(str_data)
-                  for str_data in params[1]]
+
+    snap_disks = []
+    for disk in params[1]:
+      if isinstance(disk, bool):
+        snap_disks.append(disk)
+      else:
+        snap_disks.append(objects.Disk.FromDict(disk))
+
     return backend.FinalizeExport(instance, snap_disks)
 
   @staticmethod
@@ -429,26 +458,27 @@ class NodeHttpServer(http.server.HttpServer):
     inst_s = params[0]
     inst = objects.Instance.FromDict(inst_s)
     reinstall = params[1]
-    return backend.InstanceOsAdd(inst, reinstall)
+    debug = params[2]
+    return backend.InstanceOsAdd(inst, reinstall, debug)
 
   @staticmethod
   def perspective_instance_run_rename(params):
     """Runs the OS rename script for an instance.
 
     """
-    inst_s, old_name = params
+    inst_s, old_name, debug = params
     inst = objects.Instance.FromDict(inst_s)
-    return backend.RunRenameInstance(inst, old_name)
+    return backend.RunRenameInstance(inst, old_name, debug)
 
   @staticmethod
   def perspective_instance_os_import(params):
     """Run the import function of an OS onto a given instance.
 
     """
-    inst_s, src_node, src_images, cluster_name = params
+    inst_s, src_node, src_images, cluster_name, debug = params
     inst = objects.Instance.FromDict(inst_s)
     return backend.ImportOSIntoInstance(inst, src_node, src_images,
-                                        cluster_name)
+                                        cluster_name, debug)
 
   @staticmethod
   def perspective_instance_shutdown(params):
@@ -803,8 +833,6 @@ 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 +840,12 @@ 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,