def test_archive03(self):
"""
All archives should be purged, both with the new naming (with incarnation number) and with the old naming.
"""
start = datetime.now()
timestamp1 = start + timedelta(seconds=5)
timestamp2 = start + timedelta(seconds=10)
dir_old = timestamp1.isoformat()
dir_new = "{0}_incarnation_1".format(timestamp2.isoformat())
archive_old = "{0}.zip".format(timestamp1.isoformat())
archive_new = "{0}_incarnation_1.zip".format(timestamp2.isoformat())
self._write_file(
os.path.join("history", dir_old, "Prod.0.manifest.xml"))
self._write_file(
os.path.join("history", dir_new, "Prod.1.manifest.xml"))
self._write_file(os.path.join("history", archive_old))
self._write_file(os.path.join("history", archive_new))
self.assertEqual(4, len(os.listdir(self.history_dir)),
"Not all entries were archived!")
test_subject = StateArchiver(self.tmp_dir)
with patch("azurelinuxagent.common.utils.archive._MAX_ARCHIVED_STATES",
0):
test_subject.purge()
archived_entries = os.listdir(self.history_dir)
self.assertEqual(0, len(archived_entries),
"Not all entries were purged!")
def test_archive04(self):
"""
The archive directory is created if it does not exist.
This failure was caught when .purge() was called before .archive().
"""
test_subject = StateArchiver(os.path.join(self.tmp_dir, 'does-not-exist'))
test_subject.purge()
class CleanupGoalStateHistory(PeriodicOperation):
def __init__(self):
super(CleanupGoalStateHistory,
self).__init__(conf.get_goal_state_history_cleanup_period())
self.archiver = StateArchiver(conf.get_lib_dir())
def _operation(self):
"""
Purge history and create a .zip of the history that has been preserved.
"""
self.archiver.purge()
self.archiver.archive()
def test_archive02(self):
"""
StateArchiver should purge the MAX_ARCHIVED_STATES oldest files
or directories. The oldest timestamps are purged first.
This test case creates a mixture of archive files and directories.
It creates 5 more values than MAX_ARCHIVED_STATES to ensure that
5 archives are cleaned up. It asserts that the files and
directories are properly deleted from the disk.
"""
count = 6
total = _MAX_ARCHIVED_STATES + count
start = datetime.now()
timestamps = []
for i in range(0, total):
timestamp = start + timedelta(seconds=i)
timestamps.append(timestamp)
if i % 2 == 0:
filename = os.path.join(
'history',
"{0}_incarnation_0".format(timestamp.isoformat()),
'Prod.0.manifest.xml')
else:
filename = os.path.join(
'history',
"{0}_incarnation_0.zip".format(timestamp.isoformat()))
self._write_file(filename)
self.assertEqual(total, len(os.listdir(self.history_dir)))
test_subject = StateArchiver(self.tmp_dir)
test_subject.purge()
archived_entries = os.listdir(self.history_dir)
self.assertEqual(_MAX_ARCHIVED_STATES, len(archived_entries))
archived_entries.sort()
for i in range(0, _MAX_ARCHIVED_STATES):
timestamp = timestamps[i + count].isoformat()
if i % 2 == 0:
filename = "{0}_incarnation_0".format(timestamp)
else:
filename = "{0}_incarnation_0.zip".format(timestamp)
self.assertTrue(
filename in archived_entries,
"'{0}' is not in the list of unpurged entires".format(
filename))
class EnvHandler(object):
"""
Monitor changes to dhcp and hostname.
If dhcp client process re-start has occurred, reset routes, dhcp with fabric.
Monitor scsi disk.
If new scsi disk found, set timeout
"""
def __init__(self):
self.osutil = get_osutil()
self.dhcp_handler = get_dhcp_handler()
self.protocol_util = get_protocol_util()
self.stopped = True
self.hostname = None
self.dhcp_id_list = []
self.server_thread = None
self.dhcp_warning_enabled = True
self.last_archive = None
self.archiver = StateArchiver(conf.get_lib_dir())
def run(self):
if not self.stopped:
logger.info("Stop existing env monitor service.")
self.stop()
self.stopped = False
logger.info("Start env monitor service.")
self.dhcp_handler.conf_routes()
self.hostname = self.osutil.get_hostname_record()
self.dhcp_id_list = self.get_dhcp_client_pid()
self.start()
def is_alive(self):
return self.server_thread.is_alive()
def start(self):
self.server_thread = threading.Thread(target=self.monitor)
self.server_thread.setDaemon(True)
self.server_thread.setName("EnvHandler")
self.server_thread.start()
def monitor(self):
"""
Monitor firewall rules
Monitor dhcp client pid and hostname.
If dhcp client process re-start has occurred, reset routes.
Purge unnecessary files from disk cache.
"""
protocol = self.protocol_util.get_protocol()
reset_firewall_fules = False
while not self.stopped:
self.osutil.remove_rules_files()
if conf.enable_firewall():
# If the rules ever change we must reset all rules and start over again.
#
# There was a rule change at 2.2.26, which started dropping non-root traffic
# to WireServer. The previous rules allowed traffic. Having both rules in
# place negated the fix in 2.2.26.
if not reset_firewall_fules:
self.osutil.remove_firewall(dst_ip=protocol.endpoint,
uid=os.getuid())
reset_firewall_fules = True
success = self.osutil.enable_firewall(dst_ip=protocol.endpoint,
uid=os.getuid())
add_periodic(logger.EVERY_HOUR,
AGENT_NAME,
version=CURRENT_VERSION,
op=WALAEventOperation.Firewall,
is_success=success,
log_event=False)
timeout = conf.get_root_device_scsi_timeout()
if timeout is not None:
self.osutil.set_scsi_disks_timeout(timeout)
if conf.get_monitor_hostname():
self.handle_hostname_update()
self.handle_dhclient_restart()
self.archive_history()
time.sleep(5)
def handle_hostname_update(self):
curr_hostname = socket.gethostname()
if curr_hostname != self.hostname:
logger.info("EnvMonitor: Detected hostname change: {0} -> {1}",
self.hostname, curr_hostname)
self.osutil.set_hostname(curr_hostname)
self.osutil.publish_hostname(curr_hostname)
self.hostname = curr_hostname
def get_dhcp_client_pid(self):
pid = []
try:
# return a sorted list since handle_dhclient_restart needs to compare the previous value with
# the new value and the comparison should not be affected by the order of the items in the list
pid = sorted(self.osutil.get_dhcp_pid())
if len(pid) == 0 and self.dhcp_warning_enabled:
logger.warn("Dhcp client is not running.")
except Exception as exception:
if self.dhcp_warning_enabled:
logger.error("Failed to get the PID of the DHCP client: {0}",
ustr(exception))
self.dhcp_warning_enabled = len(pid) != 0
return pid
def handle_dhclient_restart(self):
if len(self.dhcp_id_list) == 0:
self.dhcp_id_list = self.get_dhcp_client_pid()
return
if all(self.osutil.check_pid_alive(pid) for pid in self.dhcp_id_list):
return
new_pid = self.get_dhcp_client_pid()
if len(new_pid) != 0 and new_pid != self.dhcp_id_list:
logger.info(
"EnvMonitor: Detected dhcp client restart. Restoring routing table."
)
self.dhcp_handler.conf_routes()
self.dhcp_id_list = new_pid
def archive_history(self):
"""
Purge history if we have exceed the maximum count.
Create a .zip of the history that has been preserved.
"""
if self.last_archive is not None \
and datetime.datetime.utcnow() < \
self.last_archive + ARCHIVE_INTERVAL:
return
self.archiver.purge()
self.archiver.archive()
def stop(self):
"""
Stop server communication and join the thread to main thread.
"""
self.stopped = True
if self.server_thread is not None:
self.server_thread.join()
class EnvHandler(object):
"""
Monitor changes to dhcp and hostname.
If dhcp client process re-start has occurred, reset routes, dhcp with fabric.
Monitor scsi disk.
If new scsi disk found, set timeout
"""
def __init__(self):
self.osutil = get_osutil()
self.dhcp_handler = get_dhcp_handler()
self.protocol_util = get_protocol_util()
self.stopped = True
self.hostname = None
self.dhcp_id = None
self.server_thread = None
self.dhcp_warning_enabled = True
self.last_archive = None
self.archiver = StateArchiver(conf.get_lib_dir())
def run(self):
if not self.stopped:
logger.info("Stop existing env monitor service.")
self.stop()
self.stopped = False
logger.info("Start env monitor service.")
self.dhcp_handler.conf_routes()
self.hostname = self.osutil.get_hostname_record()
self.dhcp_id = self.osutil.get_dhcp_pid()
self.start()
def is_alive(self):
return self.server_thread.is_alive()
def start(self):
self.server_thread = threading.Thread(target=self.monitor)
self.server_thread.setDaemon(True)
self.server_thread.start()
def monitor(self):
"""
Monitor firewall rules
Monitor dhcp client pid and hostname.
If dhcp client process re-start has occurred, reset routes.
Purge unnecessary files from disk cache.
"""
protocol = self.protocol_util.get_protocol()
reset_firewall_fules = False
while not self.stopped:
self.osutil.remove_rules_files()
if conf.enable_firewall():
# If the rules ever change we must reset all rules and start over again.
#
# There was a rule change at 2.2.26, which started dropping non-root traffic
# to WireServer. The previous rules allowed traffic. Having both rules in
# place negated the fix in 2.2.26.
if not reset_firewall_fules:
self.osutil.remove_firewall(dst_ip=protocol.endpoint, uid=os.getuid())
reset_firewall_fules = True
success = self.osutil.enable_firewall(
dst_ip=protocol.endpoint,
uid=os.getuid())
add_periodic(
logger.EVERY_HOUR,
AGENT_NAME,
version=CURRENT_VERSION,
op=WALAEventOperation.Firewall,
is_success=success,
log_event=False)
timeout = conf.get_root_device_scsi_timeout()
if timeout is not None:
self.osutil.set_scsi_disks_timeout(timeout)
if conf.get_monitor_hostname():
self.handle_hostname_update()
self.handle_dhclient_restart()
self.archive_history()
time.sleep(5)
def handle_hostname_update(self):
curr_hostname = socket.gethostname()
if curr_hostname != self.hostname:
logger.info("EnvMonitor: Detected hostname change: {0} -> {1}",
self.hostname,
curr_hostname)
self.osutil.set_hostname(curr_hostname)
self.osutil.publish_hostname(curr_hostname)
self.hostname = curr_hostname
def handle_dhclient_restart(self):
if self.dhcp_id is None:
if self.dhcp_warning_enabled:
logger.warn("Dhcp client is not running. ")
self.dhcp_id = self.osutil.get_dhcp_pid()
# disable subsequent error logging
self.dhcp_warning_enabled = self.dhcp_id is not None
return
# the dhcp process has not changed since the last check
if self.osutil.check_pid_alive(self.dhcp_id.strip()):
return
new_pid = self.osutil.get_dhcp_pid()
if new_pid is not None and new_pid != self.dhcp_id:
logger.info("EnvMonitor: Detected dhcp client restart. "
"Restoring routing table.")
self.dhcp_handler.conf_routes()
self.dhcp_id = new_pid
def archive_history(self):
"""
Purge history if we have exceed the maximum count.
Create a .zip of the history that has been preserved.
"""
if self.last_archive is not None \
and datetime.datetime.utcnow() < \
self.last_archive + ARCHIVE_INTERVAL:
return
self.archiver.purge()
self.archiver.archive()
def stop(self):
"""
Stop server communication and join the thread to main thread.
"""
self.stopped = True
if self.server_thread is not None:
self.server_thread.join()
class EnvHandler(object):
"""
Monitor changes to dhcp and hostname.
If dhcp client process re-start has occurred, reset routes, dhcp with fabric.
Monitor scsi disk.
If new scsi disk found, set timeout
"""
def __init__(self):
self.osutil = get_osutil()
self.dhcp_handler = get_dhcp_handler()
self.protocol_util = get_protocol_util()
self.stopped = True
self.hostname = None
self.dhcp_id = None
self.server_thread = None
self.dhcp_warning_enabled = True
self.last_archive = None
self.archiver = StateArchiver(conf.get_lib_dir())
def run(self):
if not self.stopped:
logger.info("Stop existing env monitor service.")
self.stop()
self.stopped = False
logger.info("Start env monitor service.")
self.dhcp_handler.conf_routes()
self.hostname = self.osutil.get_hostname_record()
self.dhcp_id = self.osutil.get_dhcp_pid()
self.start()
def is_alive(self):
return self.server_thread.is_alive()
def start(self):
self.server_thread = threading.Thread(target=self.monitor)
self.server_thread.setDaemon(True)
self.server_thread.start()
def monitor(self):
"""
Monitor firewall rules
Monitor dhcp client pid and hostname.
If dhcp client process re-start has occurred, reset routes.
Purge unnecessary files from disk cache.
"""
protocol = self.protocol_util.get_protocol()
while not self.stopped:
self.osutil.remove_rules_files()
if conf.enable_firewall():
success = self.osutil.enable_firewall(
dst_ip=protocol.endpoint,
uid=os.getuid())
add_periodic(
logger.EVERY_HOUR,
AGENT_NAME,
version=CURRENT_VERSION,
op=WALAEventOperation.Firewall,
is_success=success,
log_event=False)
timeout = conf.get_root_device_scsi_timeout()
if timeout is not None:
self.osutil.set_scsi_disks_timeout(timeout)
if conf.get_monitor_hostname():
self.handle_hostname_update()
self.handle_dhclient_restart()
self.archive_history()
time.sleep(5)
def handle_hostname_update(self):
curr_hostname = socket.gethostname()
if curr_hostname != self.hostname:
logger.info("EnvMonitor: Detected hostname change: {0} -> {1}",
self.hostname,
curr_hostname)
self.osutil.set_hostname(curr_hostname)
self.osutil.publish_hostname(curr_hostname)
self.hostname = curr_hostname
def handle_dhclient_restart(self):
if self.dhcp_id is None:
if self.dhcp_warning_enabled:
logger.warn("Dhcp client is not running. ")
self.dhcp_id = self.osutil.get_dhcp_pid()
# disable subsequent error logging
self.dhcp_warning_enabled = self.dhcp_id is not None
return
# the dhcp process has not changed since the last check
if self.osutil.check_pid_alive(self.dhcp_id.strip()):
return
new_pid = self.osutil.get_dhcp_pid()
if new_pid is not None and new_pid != self.dhcp_id:
logger.info("EnvMonitor: Detected dhcp client restart. "
"Restoring routing table.")
self.dhcp_handler.conf_routes()
self.dhcp_id = new_pid
def archive_history(self):
"""
Purge history if we have exceed the maximum count.
Create a .zip of the history that has been preserved.
"""
if self.last_archive is not None \
and datetime.datetime.utcnow() < \
self.last_archive + ARCHIVE_INTERVAL:
return
self.archiver.purge()
self.archiver.archive()
def stop(self):
"""
Stop server communication and join the thread to main thread.
"""
self.stopped = True
if self.server_thread is not None:
self.server_thread.join()
class EnvHandler(object):
"""
Monitor changes to dhcp and hostname.
If dhcp client process re-start has occurred, reset routes, dhcp with fabric.
Monitor scsi disk.
If new scsi disk found, set timeout
"""
def __init__(self):
self.osutil = get_osutil()
self.dhcp_handler = get_dhcp_handler()
self.protocol_util = None
self._protocol = None
self.stopped = True
self.hostname = None
self.dhcp_id_list = []
self.server_thread = None
self.dhcp_warning_enabled = True
self.archiver = StateArchiver(conf.get_lib_dir())
self._reset_firewall_rules = False
self._periodic_operations = [
PeriodicOperation("_remove_persistent_net_rules", self._remove_persistent_net_rules_period, conf.get_remove_persistent_net_rules_period()),
PeriodicOperation("_monitor_dhcp_client_restart", self._monitor_dhcp_client_restart, conf.get_monitor_dhcp_client_restart_period()),
PeriodicOperation("_cleanup_goal_state_history", self._cleanup_goal_state_history, conf.get_goal_state_history_cleanup_period())
]
if conf.enable_firewall():
self._periodic_operations.append(PeriodicOperation("_enable_firewall", self._enable_firewall, conf.get_enable_firewall_period()))
if conf.get_root_device_scsi_timeout() is not None:
self._periodic_operations.append(PeriodicOperation("_set_root_device_scsi_timeout", self._set_root_device_scsi_timeout, conf.get_root_device_scsi_timeout_period()))
if conf.get_monitor_hostname():
self._periodic_operations.append(PeriodicOperation("_monitor_hostname", self._monitor_hostname_changes, conf.get_monitor_hostname_period()))
def run(self):
if not self.stopped:
logger.info("Stop existing env monitor service.")
self.stop()
self.stopped = False
logger.info("Start env monitor service.")
self.dhcp_handler.conf_routes()
self.hostname = self.osutil.get_hostname_record()
self.dhcp_id_list = self.get_dhcp_client_pid()
self.start()
def is_alive(self):
return self.server_thread.is_alive()
def start(self):
self.server_thread = threading.Thread(target=self.monitor)
self.server_thread.setDaemon(True)
self.server_thread.setName("EnvHandler")
self.server_thread.start()
def monitor(self):
try:
# The initialization of ProtocolUtil for the Environment thread should be done within the thread itself rather
# than initializing it in the ExtHandler thread. This is done to avoid any concurrency issues as each
# thread would now have its own ProtocolUtil object as per the SingletonPerThread model.
self.protocol_util = get_protocol_util()
self._protocol = self.protocol_util.get_protocol()
while not self.stopped:
try:
for op in self._periodic_operations:
op.run()
except Exception as e:
logger.error("An error occurred in the environment thread main loop; will skip the current iteration.\n{0}", ustr(e))
finally:
PeriodicOperation.sleep_until_next_operation(self._periodic_operations)
except Exception as e:
logger.error("An error occurred in the environment thread; will exit the thread.\n{0}", ustr(e))
def _remove_persistent_net_rules_period(self):
self.osutil.remove_rules_files()
def _enable_firewall(self):
# If the rules ever change we must reset all rules and start over again.
#
# There was a rule change at 2.2.26, which started dropping non-root traffic
# to WireServer. The previous rules allowed traffic. Having both rules in
# place negated the fix in 2.2.26.
if not self._reset_firewall_rules:
self.osutil.remove_firewall(dst_ip=self._protocol.get_endpoint(), uid=os.getuid())
self._reset_firewall_rules = True
success = self.osutil.enable_firewall(dst_ip=self._protocol.get_endpoint(), uid=os.getuid())
add_periodic(
logger.EVERY_HOUR,
AGENT_NAME,
version=CURRENT_VERSION,
op=WALAEventOperation.Firewall,
is_success=success,
log_event=False)
def _set_root_device_scsi_timeout(self):
self.osutil.set_scsi_disks_timeout(conf.get_root_device_scsi_timeout())
def _monitor_hostname_changes(self):
curr_hostname = socket.gethostname()
if curr_hostname != self.hostname:
logger.info("EnvMonitor: Detected hostname change: {0} -> {1}",
self.hostname,
curr_hostname)
self.osutil.set_hostname(curr_hostname)
self.osutil.publish_hostname(curr_hostname)
self.hostname = curr_hostname
def get_dhcp_client_pid(self):
pid = []
try:
# return a sorted list since handle_dhclient_restart needs to compare the previous value with
# the new value and the comparison should not be affected by the order of the items in the list
pid = sorted(self.osutil.get_dhcp_pid())
if len(pid) == 0 and self.dhcp_warning_enabled:
logger.warn("Dhcp client is not running.")
except Exception as exception:
if self.dhcp_warning_enabled:
logger.error("Failed to get the PID of the DHCP client: {0}", ustr(exception))
self.dhcp_warning_enabled = len(pid) != 0
return pid
def _monitor_dhcp_client_restart(self):
self.handle_dhclient_restart()
def handle_dhclient_restart(self):
if len(self.dhcp_id_list) == 0:
self.dhcp_id_list = self.get_dhcp_client_pid()
return
if all(self.osutil.check_pid_alive(pid) for pid in self.dhcp_id_list):
return
new_pid = self.get_dhcp_client_pid()
if len(new_pid) != 0 and new_pid != self.dhcp_id_list:
logger.info("EnvMonitor: Detected dhcp client restart. Restoring routing table.")
self.dhcp_handler.conf_routes()
self.dhcp_id_list = new_pid
def _cleanup_goal_state_history(self):
"""
Purge history and create a .zip of the history that has been preserved.
"""
self.archiver.purge()
self.archiver.archive()
def stop(self):
"""
Stop server communication and join the thread to main thread.
"""
self.stopped = True
if self.server_thread is not None:
self.server_thread.join()