Bump version to 0.9.32

This should be managed in ceph.conf with the `rbd default
features` configuration option instead, and thus can be tailored to the
underlying OS version.

.version

@@ -1 +1 @@
-0.9.26
+0.9.32

README.md

@@ -40,8 +40,51 @@ The core node and API daemons, as well as the CLI API client, are written in Pyt
 To get started with PVC, please see the [About](https://parallelvirtualcluster.readthedocs.io/en/latest/about/) page for general information about the project, and the [Getting Started](https://parallelvirtualcluster.readthedocs.io/en/latest/getting-started/) page for details on configuring your first cluster.
 
 
+## Screenshots
+
+While PVC's API and internals aren't very screenshot-worthy, here is some example output of the CLI tool.
+
+<p><img alt="Node listing" src="docs/images/pvc-nodes.png"/><br/><i>Listing the nodes in a cluster</i></p>
+
+<p><img alt="Network listing" src="docs/images/pvc-networks.png"/><br/><i>Listing the networks in a cluster, showing 3 bridged and 1 IPv4-only managed networks</i></p>
+
+<p><img alt="VM listing and migration" src="docs/images/pvc-migration.png"/><br/><i>Listing a limited set of VMs and migrating one with status updates</i></p>
+
+<p><img alt="Node logs" src="docs/images/pvc-nodelog.png"/><br/><i>Viewing the logs of a node (keepalives and VM [un]migration)</i></p>
+
+
 ## Changelog
 
+#### v0.9.32
+
+  * [CLI Client] Fixes some incorrect colours in network lists
+  * [Documentation] Adds documentation screenshots of CLI client
+  * [Node Daemon] Fixes a bug if VM stats gathering fails
+
+#### v0.9.31
+
+  * [Packages] Cleans up obsolete Suggests lines
+  * [Node Daemon] Adjusts log text of VM migrations to show the correct source node
+  * [API Daemon] Adjusts the OVA importer to support floppy RASD types for compatability
+  * [API Daemon] Ensures that volume resize commands without a suffix get B appended
+  * [API Daemon] Removes the explicit setting of image-features in PVC; defaulting to the limited set has been moved to the ceph.conf configuration on nodes via PVC Ansible
+
+#### v0.9.30
+
+  * [Node Daemon] Fixes bug with schema validation
+
+#### v0.9.29
+
+  * [Node Daemon] Corrects numerous bugs with node logging framework
+
+#### v0.9.28
+
+  * [CLI Client] Revamp confirmation options for "vm modify" command
+
+#### v0.9.27
+
+  * [CLI Client] Fixes a bug with vm modify command when passed a file
+
 #### v0.9.26
 
   * [Node Daemon] Corrects some bad assumptions about fencing results during hardware failures

api-daemon/pvcapid/Daemon.py

@@ -25,7 +25,7 @@ import yaml
 from distutils.util import strtobool as dustrtobool
 
 # Daemon version
-version = '0.9.26'
+version = '0.9.32'
 
 # API version
 API_VERSION = 1.0

api-daemon/pvcapid/ova.py

@@ -414,6 +414,7 @@ class OVFParser(object):
         "5": "ide-controller",
         "6": "scsi-controller",
         "10": "ethernet-adapter",
+        "14": "floppy",
         "15": "cdrom",
         "17": "disk",
         "20": "other-storage-device",

client-cli/pvc/cli_lib/network.py

@@ -491,14 +491,10 @@ def net_sriov_vf_info(config, node, vf):
 # Output display functions
 #
 def getColour(value):
-    if value in ['True', "start"]:
+    if value in ["False", "None"]:
-        return ansiprint.green()
-    elif value in ["restart", "shutdown"]:
-        return ansiprint.yellow()
-    elif value in ["stop", "fail"]:
-        return ansiprint.red()
-    else:
         return ansiprint.blue()
+    else:
+        return ansiprint.green()
 
 
 def getOutputColours(network_information):

client-cli/pvc/pvc.py

@@ -764,9 +764,19 @@ def vm_meta(domain, node_limit, node_selector, node_autostart, migration_method,
     help='Immediately restart VM to apply new config.'
 )
 @click.option(
-    '-y', '--yes', 'confirm_flag',
+    '-d', '--confirm-diff', 'confirm_diff_flag',
     is_flag=True, default=False,
-    help='Confirm the restart'
+    help='Confirm the diff.'
+)
+@click.option(
+    '-c', '--confirm-restart', 'confirm_restart_flag',
+    is_flag=True, default=False,
+    help='Confirm the restart.'
+)
+@click.option(
+    '-y', '--yes', 'confirm_all_flag',
+    is_flag=True, default=False,
+    help='Confirm the diff and the restart.'
 )
 @click.argument(
     'domain'
@@ -774,7 +784,7 @@ def vm_meta(domain, node_limit, node_selector, node_autostart, migration_method,
 @click.argument(
     'cfgfile', type=click.File(), default=None, required=False
 )
-def vm_modify(domain, cfgfile, editor, restart, confirm_flag):
+def vm_modify(domain, cfgfile, editor, restart, confirm_diff_flag, confirm_restart_flag, confirm_all_flag):
     """
     Modify existing virtual machine DOMAIN, either in-editor or with replacement CONFIG. DOMAIN may be a UUID or name.
     """
@@ -788,12 +798,12 @@ def vm_modify(domain, cfgfile, editor, restart, confirm_flag):
 
     dom_name = vm_information.get('name')
 
-    if editor is True:
+    # Grab the current config
-        # Grab the current config
+    current_vm_cfg_raw = vm_information.get('xml')
-        current_vm_cfg_raw = vm_information.get('xml')
+    xml_data = etree.fromstring(current_vm_cfg_raw)
-        xml_data = etree.fromstring(current_vm_cfg_raw)
+    current_vm_cfgfile = etree.tostring(xml_data, pretty_print=True).decode('utf8').strip()
-        current_vm_cfgfile = etree.tostring(xml_data, pretty_print=True).decode('utf8').strip()
 
+    if editor is True:
         new_vm_cfgfile = click.edit(text=current_vm_cfgfile, require_save=True, extension='.xml')
         if new_vm_cfgfile is None:
             click.echo('Aborting with no modifications.')
@@ -831,9 +841,10 @@ def vm_modify(domain, cfgfile, editor, restart, confirm_flag):
     except Exception as e:
         cleanup(False, 'Error: XML is malformed or invalid: {}'.format(e))
 
-    click.confirm('Write modifications to cluster?', abort=True)
+    if not confirm_diff_flag and not confirm_all_flag and not config['unsafe']:
+        click.confirm('Write modifications to cluster?', abort=True)
 
-    if restart and not confirm_flag and not config['unsafe']:
+    if restart and not confirm_restart_flag and not confirm_all_flag and not config['unsafe']:
         try:
             click.confirm('Restart VM {}'.format(domain), prompt_suffix='? ', abort=True)
         except Exception:

client-cli/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
     name='pvc',
-    version='0.9.26',
+    version='0.9.32',
     packages=['pvc', 'pvc.cli_lib'],
     install_requires=[
         'Click',

daemon-common/ceph.py

@@ -491,7 +491,7 @@ def add_volume(zkhandler, pool, name, size):
         size = '{}B'.format(size)
 
     # 2. Create the volume
-    retcode, stdout, stderr = common.run_os_command('rbd create --size {} --image-feature layering,exclusive-lock {}/{}'.format(size, pool, name))
+    retcode, stdout, stderr = common.run_os_command('rbd create --size {} {}/{}'.format(size, pool, name))
     if retcode:
         return False, 'ERROR: Failed to create RBD volume "{}": {}'.format(name, stderr)
 
@@ -536,6 +536,10 @@ def resize_volume(zkhandler, pool, name, size):
     if not verifyVolume(zkhandler, pool, name):
         return False, 'ERROR: No volume with name "{}" is present in pool "{}".'.format(name, pool)
 
+    # Add 'B' if the volume is in bytes
+    if re.match(r'^[0-9]+$', size):
+        size = '{}B'.format(size)
+
     # 1. Resize the volume
     retcode, stdout, stderr = common.run_os_command('rbd resize --size {} {}/{}'.format(size, pool, name))
     if retcode:

daemon-common/log.py

@@ -23,6 +23,7 @@ from collections import deque
 from threading import Thread
 from queue import Queue
 from datetime import datetime
+from time import sleep
 
 from daemon_lib.zkhandler import ZKHandler
 
@@ -83,7 +84,8 @@ class Logger(object):
         self.last_prompt = ''
 
         if self.config['zookeeper_logging']:
-            self.zookeeper_logger = ZookeeperLogger(config)
+            self.zookeeper_queue = Queue()
+            self.zookeeper_logger = ZookeeperLogger(self.config, self.zookeeper_queue)
             self.zookeeper_logger.start()
 
     # Provide a hup function to close and reopen the writer
@@ -96,9 +98,15 @@ class Logger(object):
         if self.config['file_logging']:
             self.writer.close()
         if self.config['zookeeper_logging']:
-            self.out("Waiting for Zookeeper message queue to drain", state='s')
+            self.out("Waiting 15s for Zookeeper message queue to drain", state='s')
-            while not self.zookeeper_logger.queue.empty():
+
-                pass
+            tick_count = 0
+            while not self.zookeeper_queue.empty():
+                sleep(0.5)
+                tick_count += 1
+                if tick_count > 30:
+                    break
+
             self.zookeeper_logger.stop()
             self.zookeeper_logger.join()
 
@@ -145,7 +153,7 @@ class Logger(object):
 
         # Log to Zookeeper
         if self.config['zookeeper_logging']:
-            self.zookeeper_logger.queue.put(message)
+            self.zookeeper_queue.put(message)
 
         # Set last message variables
         self.last_colour = colour
@@ -157,19 +165,14 @@ class ZookeeperLogger(Thread):
     Defines a threaded writer for Zookeeper locks. Threading prevents the blocking of other
     daemon events while the records are written. They will be eventually-consistent
     """
-    def __init__(self, config):
+    def __init__(self, config, zookeeper_queue):
         self.config = config
         self.node = self.config['node']
         self.max_lines = self.config['node_log_lines']
-        self.queue = Queue()
+        self.zookeeper_queue = zookeeper_queue
-        self.zkhandler = None
+        self.connected = False
-        self.start_zkhandler()
-        # Ensure the root keys for this are instantiated
-        self.zkhandler.write([
-            ('base.logs', ''),
-            (('logs', self.node), '')
-        ])
         self.running = False
+        self.zkhandler = None
         Thread.__init__(self, args=(), kwargs=None)
 
     def start_zkhandler(self):
@@ -179,10 +182,29 @@ class ZookeeperLogger(Thread):
                 self.zkhandler.disconnect()
             except Exception:
                 pass
-        self.zkhandler = ZKHandler(self.config, logger=None)
+
-        self.zkhandler.connect(persistent=True)
+        while True:
+            try:
+                self.zkhandler = ZKHandler(self.config, logger=None)
+                self.zkhandler.connect(persistent=True)
+                break
+            except Exception:
+                sleep(0.5)
+                continue
+
+        self.connected = True
+
+        # Ensure the root keys for this are instantiated
+        self.zkhandler.write([
+            ('base.logs', ''),
+            (('logs', self.node), '')
+        ])
 
     def run(self):
+        while not self.connected:
+            self.start_zkhandler()
+            sleep(1)
+
         self.running = True
         # Get the logs that are currently in Zookeeper and populate our deque
         raw_logs = self.zkhandler.read(('logs.messages', self.node))
@@ -192,7 +214,7 @@ class ZookeeperLogger(Thread):
         while self.running:
             # Get a new message
             try:
-                message = self.queue.get(timeout=1)
+                message = self.zookeeper_queue.get(timeout=1)
                 if not message:
                     continue
             except Exception:
@@ -205,8 +227,21 @@ class ZookeeperLogger(Thread):
                 date = ''
             # Add the message to the deque
             logs.append(f'{date}{message}')
-            # Write the updated messages into Zookeeper
+
-            self.zkhandler.write([(('logs.messages', self.node), '\n'.join(logs))])
+            tick_count = 0
+            while True:
+                try:
+                    # Write the updated messages into Zookeeper
+                    self.zkhandler.write([(('logs.messages', self.node), '\n'.join(logs))])
+                    break
+                except Exception:
+                    # The write failed (connection loss, etc.) so retry for 15 seconds
+                    sleep(0.5)
+                    tick_count += 1
+                    if tick_count > 30:
+                        break
+                    else:
+                        continue
         return
 
     def stop(self):

daemon-common/zkhandler.py

@@ -777,7 +777,7 @@ class ZKSchema(object):
                         logger.out(f'Key not found: {self.path(kpath)}', state='w')
                     result = False
 
-        for elem in ['logs', 'node', 'domain', 'network', 'osd', 'pool']:
+        for elem in ['node', 'domain', 'network', 'osd', 'pool']:
             # First read all the subelements of the key class
             for child in zkhandler.zk_conn.get_children(self.path(f'base.{elem}')):
                 # For each key in the schema for that particular elem
@@ -856,7 +856,7 @@ class ZKSchema(object):
                         data = ''
                     zkhandler.zk_conn.create(self.path(kpath), data.encode(zkhandler.encoding))
 
-        for elem in ['logs', 'node', 'domain', 'network', 'osd', 'pool']:
+        for elem in ['node', 'domain', 'network', 'osd', 'pool']:
             # First read all the subelements of the key class
             for child in zkhandler.zk_conn.get_children(self.path(f'base.{elem}')):
                 # For each key in the schema for that particular elem

debian/changelog

@@ -1,3 +1,45 @@
+pvc (0.9.32-0) unstable; urgency=high
+
+  * [CLI Client] Fixes some incorrect colours in network lists
+  * [Documentation] Adds documentation screenshots of CLI client
+  * [Node Daemon] Fixes a bug if VM stats gathering fails
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Thu, 19 Aug 2021 12:37:58 -0400
+
+pvc (0.9.31-0) unstable; urgency=high
+
+  * [Packages] Cleans up obsolete Suggests lines
+  * [Node Daemon] Adjusts log text of VM migrations to show the correct source node
+  * [API Daemon] Adjusts the OVA importer to support floppy RASD types for compatability
+  * [API Daemon] Ensures that volume resize commands without a suffix get B appended
+  * [API Daemon] Removes the explicit setting of image-features in PVC; defaulting to the limited set has been moved to the ceph.conf configuration on nodes via PVC Ansible
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Fri, 30 Jul 2021 12:08:12 -0400
+
+pvc (0.9.30-0) unstable; urgency=high
+
+  * [Node Daemon] Fixes bug with schema validation
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Tue, 20 Jul 2021 00:01:45 -0400
+
+pvc (0.9.29-0) unstable; urgency=high
+
+  * [Node Daemon] Corrects numerous bugs with node logging framework
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Mon, 19 Jul 2021 16:55:41 -0400
+
+pvc (0.9.28-0) unstable; urgency=high
+
+  * [CLI Client] Revamp confirmation options for "vm modify" command
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Mon, 19 Jul 2021 09:29:34 -0400
+
+pvc (0.9.27-0) unstable; urgency=high
+
+  * [CLI Client] Fixes a bug with vm modify command when passed a file
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Mon, 19 Jul 2021 00:03:40 -0400
+
 pvc (0.9.26-0) unstable; urgency=high
 
   * [Node Daemon] Corrects some bad assumptions about fencing results during hardware failures

debian/control

@@ -9,7 +9,6 @@ X-Python3-Version: >= 3.2
 Package: pvc-daemon-node
 Architecture: all
 Depends: systemd, pvc-daemon-common, python3-kazoo, python3-psutil, python3-apscheduler, python3-libvirt, python3-psycopg2, python3-dnspython, python3-yaml, python3-distutils, python3-rados, python3-gevent, ipmitool, libvirt-daemon-system, arping, vlan, bridge-utils, dnsmasq, nftables, pdns-server, pdns-backend-pgsql
-Suggests: pvc-client-api, pvc-client-cli
 Description: Parallel Virtual Cluster node daemon (Python 3)
  A KVM/Zookeeper/Ceph-based VM and private cloud manager
  .

docs/index.md

@@ -40,8 +40,51 @@ The core node and API daemons, as well as the CLI API client, are written in Pyt
 To get started with PVC, please see the [About](https://parallelvirtualcluster.readthedocs.io/en/latest/about/) page for general information about the project, and the [Getting Started](https://parallelvirtualcluster.readthedocs.io/en/latest/getting-started/) page for details on configuring your first cluster.
 
 
+## Screenshots
+
+While PVC's API and internals aren't very screenshot-worthy, here is some example output of the CLI tool.
+
+<p><img alt="Node listing" src="images/pvc-nodes.png"/><br/><i>Listing the nodes in a cluster</i></p>
+
+<p><img alt="Network listing" src="images/pvc-networks.png"/><br/><i>Listing the networks in a cluster, showing 3 bridged and 1 IPv4-only managed networks</i></p>
+
+<p><img alt="VM listing and migration" src="images/pvc-migration.png"/><br/><i>Listing a limited set of VMs and migrating one with status updates</i></p>
+
+<p><img alt="Node logs" src="images/pvc-nodelog.png"/><br/><i>Viewing the logs of a node (keepalives and VM [un]migration)</i></p>
+
+
 ## Changelog
 
+#### v0.9.32
+
+  * [CLI Client] Fixes some incorrect colours in network lists
+  * [Documentation] Adds documentation screenshots of CLI client
+  * [Node Daemon] Fixes a bug if VM stats gathering fails
+
+#### v0.9.31
+
+  * [Packages] Cleans up obsolete Suggests lines
+  * [Node Daemon] Adjusts log text of VM migrations to show the correct source node
+  * [API Daemon] Adjusts the OVA importer to support floppy RASD types for compatability
+  * [API Daemon] Ensures that volume resize commands without a suffix get B appended
+  * [API Daemon] Removes the explicit setting of image-features in PVC; defaulting to the limited set has been moved to the ceph.conf configuration on nodes via PVC Ansible
+
+#### v0.9.30
+
+  * [Node Daemon] Fixes bug with schema validation
+
+#### v0.9.29
+
+  * [Node Daemon] Corrects numerous bugs with node logging framework
+
+#### v0.9.28
+
+  * [CLI Client] Revamp confirmation options for "vm modify" command
+
+#### v0.9.27
+
+  * [CLI Client] Fixes a bug with vm modify command when passed a file
+
 #### v0.9.26
 
   * [Node Daemon] Corrects some bad assumptions about fencing results during hardware failures

node-daemon/pvcnoded/Daemon.py

@@ -56,7 +56,7 @@ import pvcnoded.CephInstance as CephInstance
 import pvcnoded.MetadataAPIInstance as MetadataAPIInstance
 
 # Version string for startup output
-version = '0.9.26'
+version = '0.9.32'
 
 ###############################################################################
 # PVCD - node daemon startup program
@@ -76,8 +76,11 @@ version = '0.9.26'
 # Daemon functions
 ###############################################################################
 
-# Ensure the update_timer is None until it's set for real
+# Ensure update_timer, this_node, and d_domain are None until they're set for real
+# Ensures cleanup() doesn't fail due to these items not being created yet
 update_timer = None
+this_node = None
+d_domain = None
 
 
 # Create timer to update this node in Zookeeper
@@ -110,7 +113,7 @@ try:
     pvcnoded_config_file = os.environ['PVCD_CONFIG_FILE']
 except Exception:
     print('ERROR: The "PVCD_CONFIG_FILE" environment variable must be set before starting pvcnoded.')
-    exit(1)
+    os._exit(1)
 
 # Set local hostname and domain variables
 myfqdn = gethostname()
@@ -142,7 +145,7 @@ def readConfig(pvcnoded_config_file, myhostname):
             o_config = yaml.load(cfgfile, Loader=yaml.SafeLoader)
         except Exception as e:
             print('ERROR: Failed to parse configuration file: {}'.format(e))
-            exit(1)
+            os._exit(1)
 
     # Handle the basic config (hypervisor-only)
     try:
@@ -179,7 +182,7 @@ def readConfig(pvcnoded_config_file, myhostname):
         }
     except Exception as e:
         print('ERROR: Failed to load configuration: {}'.format(e))
-        exit(1)
+        cleanup(failure=True)
     config = config_general
 
     # Handle debugging config
@@ -236,7 +239,7 @@ def readConfig(pvcnoded_config_file, myhostname):
 
         except Exception as e:
             print('ERROR: Failed to load configuration: {}'.format(e))
-            exit(1)
+            cleanup(failure=True)
         config = {**config, **config_networking}
 
         # Create the by-id address entries
@@ -250,7 +253,7 @@ def readConfig(pvcnoded_config_file, myhostname):
                 network = ip_network(config[network_key])
             except Exception:
                 print('ERROR: Network address {} for {} is not valid!'.format(config[network_key], network_key))
-                exit(1)
+                cleanup(failure=True)
 
             # If we should be autoselected
             if config[address_key] == 'by-id':
@@ -270,7 +273,7 @@ def readConfig(pvcnoded_config_file, myhostname):
                     raise
             except Exception:
                 print('ERROR: Floating address {} for {} is not valid!'.format(config[floating_key], floating_key))
-                exit(1)
+                cleanup(failure=True)
 
     # Handle the storage config
     if config['enable_storage']:
@@ -281,7 +284,7 @@ def readConfig(pvcnoded_config_file, myhostname):
             }
         except Exception as e:
             print('ERROR: Failed to load configuration: {}'.format(e))
-            exit(1)
+            cleanup(failure=True)
         config = {**config, **config_storage}
 
     # Handle an empty ipmi_hostname
@@ -488,6 +491,9 @@ if enable_networking:
         else:
             common.run_os_command('ip route add default via {} dev {}'.format(upstream_gateway, 'brupstream'))
 
+    logger.out('Waiting 3s for networking to come up', state='s')
+    time.sleep(3)
+
 ###############################################################################
 # PHASE 2c - Prepare sysctl for pvcnoded
 ###############################################################################
@@ -559,8 +565,8 @@ if enable_storage:
         logger.out('Starting Ceph manager daemon', state='i')
         common.run_os_command('systemctl start ceph-mgr@{}'.format(myhostname))
 
-logger.out('Waiting 5s for daemons to start', state='s')
+logger.out('Waiting 3s for daemons to start', state='s')
-time.sleep(5)
+time.sleep(3)
 
 ###############################################################################
 # PHASE 4 - Attempt to connect to the coordinators and start zookeeper client
@@ -575,7 +581,7 @@ try:
     zkhandler.connect(persistent=True)
 except Exception as e:
     logger.out('ERROR: Failed to connect to Zookeeper cluster: {}'.format(e), state='e')
-    exit(1)
+    os._exit(1)
 
 logger.out('Validating Zookeeper schema', state='i')
 
@@ -696,7 +702,7 @@ else:
 
 
 # Cleanup function
-def cleanup():
+def cleanup(failure=False):
     global logger, zkhandler, update_timer, d_domain
 
     logger.out('Terminating pvcnoded and cleaning up', state='s')
@@ -708,19 +714,19 @@ def cleanup():
 
     # Waiting for any flushes to complete
     logger.out('Waiting for any active flushes', state='s')
-    while this_node.flush_thread is not None:
+    if this_node is not None:
-        time.sleep(0.5)
+        while this_node.flush_thread is not None:
+            time.sleep(0.5)
 
     # Stop console logging on all VMs
     logger.out('Stopping domain console watchers', state='s')
-    for domain in d_domain:
+    if d_domain is not None:
-        if d_domain[domain].getnode() == myhostname:
+        for domain in d_domain:
-            try:
+            if d_domain[domain].getnode() == myhostname:
-                d_domain[domain].console_log_instance.stop()
+                try:
-            except NameError:
+                    d_domain[domain].console_log_instance.stop()
-                pass
+                except Exception:
-            except AttributeError:
+                    pass
-                pass
 
     # Force into secondary coordinator state if needed
     try:
@@ -737,13 +743,11 @@ def cleanup():
     # Stop keepalive thread
     try:
         stopKeepaliveTimer()
-    except NameError:
-        pass
-    except AttributeError:
-        pass
 
-    logger.out('Performing final keepalive update', state='s')
+        logger.out('Performing final keepalive update', state='s')
-    node_keepalive()
+        node_keepalive()
+    except Exception:
+        pass
 
     # Set stop state in Zookeeper
     zkhandler.write([
@@ -763,12 +767,17 @@ def cleanup():
     logger.out('Terminated pvc daemon', state='s')
     logger.terminate()
 
-    os._exit(0)
+    if failure:
+        retcode = 1
+    else:
+        retcode = 0
+
+    os._exit(retcode)
 
 
 # Termination function
 def term(signum='', frame=''):
-    cleanup()
+    cleanup(failure=False)
 
 
 # Hangup (logrotate) function
@@ -868,7 +877,7 @@ if enable_hypervisor:
         lv_conn.close()
     except Exception as e:
         logger.out('ERROR: Failed to connect to Libvirt daemon: {}'.format(e), state='e')
-        exit(1)
+        cleanup(failure=True)
 
 ###############################################################################
 # PHASE 7c - Ensure NFT is running on the local host
@@ -1666,11 +1675,7 @@ def collect_vm_stats(queue):
             domain_memory_stats = domain.memoryStats()
             domain_cpu_stats = domain.getCPUStats(True)[0]
         except Exception as e:
-            if debug:
+            logger.out("Failed getting VM information for {}: {}".format(domain.name(), e), state='w', prefix='vm-thread')
-                try:
-                    logger.out("Failed getting VM information for {}: {}".format(domain.name(), e), state='d', prefix='vm-thread')
-                except Exception:
-                    pass
             continue
 
         # Ensure VM is present in the domain_list
@@ -1680,42 +1685,50 @@ def collect_vm_stats(queue):
         if debug:
             logger.out("Getting disk statistics for VM {}".format(domain_name), state='d', prefix='vm-thread')
         domain_disk_stats = []
-        for disk in tree.findall('devices/disk'):
+        try:
-            disk_name = disk.find('source').get('name')
+            for disk in tree.findall('devices/disk'):
-            if not disk_name:
+                disk_name = disk.find('source').get('name')
-                disk_name = disk.find('source').get('file')
+                if not disk_name:
-            disk_stats = domain.blockStats(disk.find('target').get('dev'))
+                    disk_name = disk.find('source').get('file')
-            domain_disk_stats.append({
+                disk_stats = domain.blockStats(disk.find('target').get('dev'))
-                "name": disk_name,
+                domain_disk_stats.append({
-                "rd_req": disk_stats[0],
+                    "name": disk_name,
-                "rd_bytes": disk_stats[1],
+                    "rd_req": disk_stats[0],
-                "wr_req": disk_stats[2],
+                    "rd_bytes": disk_stats[1],
-                "wr_bytes": disk_stats[3],
+                    "wr_req": disk_stats[2],
-                "err": disk_stats[4]
+                    "wr_bytes": disk_stats[3],
-            })
+                    "err": disk_stats[4]
+                })
+        except Exception as e:
+            logger.out("Failed to get disk stats for VM {}: {}".format(domain_name, e), state='w', prefix='vm-thread')
+            continue
 
         if debug:
             logger.out("Getting network statistics for VM {}".format(domain_name), state='d', prefix='vm-thread')
         domain_network_stats = []
-        for interface in tree.findall('devices/interface'):
+        try:
-            interface_type = interface.get('type')
+            for interface in tree.findall('devices/interface'):
-            if interface_type not in ['bridge']:
+                interface_type = interface.get('type')
-                continue
+                if interface_type not in ['bridge']:
-            interface_name = interface.find('target').get('dev')
+                    continue
-            interface_bridge = interface.find('source').get('bridge')
+                interface_name = interface.find('target').get('dev')
-            interface_stats = domain.interfaceStats(interface_name)
+                interface_bridge = interface.find('source').get('bridge')
-            domain_network_stats.append({
+                interface_stats = domain.interfaceStats(interface_name)
-                "name": interface_name,
+                domain_network_stats.append({
-                "bridge": interface_bridge,
+                    "name": interface_name,
-                "rd_bytes": interface_stats[0],
+                    "bridge": interface_bridge,
-                "rd_packets": interface_stats[1],
+                    "rd_bytes": interface_stats[0],
-                "rd_errors": interface_stats[2],
+                    "rd_packets": interface_stats[1],
-                "rd_drops": interface_stats[3],
+                    "rd_errors": interface_stats[2],
-                "wr_bytes": interface_stats[4],
+                    "rd_drops": interface_stats[3],
-                "wr_packets": interface_stats[5],
+                    "wr_bytes": interface_stats[4],
-                "wr_errors": interface_stats[6],
+                    "wr_packets": interface_stats[5],
-                "wr_drops": interface_stats[7]
+                    "wr_errors": interface_stats[6],
-            })
+                    "wr_drops": interface_stats[7]
+                })
+        except Exception as e:
+            logger.out("Failed to get network stats for VM {}: {}".format(domain_name, e), state='w', prefix='vm-thread')
+            continue
 
         # Create the final dictionary
         domain_stats = {

node-daemon/pvcnoded/VMInstance.py

@@ -635,7 +635,7 @@ class VMInstance(object):
 
         self.inreceive = True
 
-        self.logger.out('Receiving VM migration from node "{}"'.format(self.node), state='i', prefix='Domain {}'.format(self.domuuid))
+        self.logger.out('Receiving VM migration from node "{}"'.format(self.last_currentnode), state='i', prefix='Domain {}'.format(self.domuuid))
 
         # Short delay to ensure sender is in sync
         time.sleep(0.5)