7d44c38c90
This commit introduces dccertmon, a new managed service for DC certificate auditing and management. Currently, platform cert management, DC cert management, and subcloud cert auditing are coupled into a single platform service (certmon). To meet the requirements of DC scalability and portability, DC specific functionality must be decoupled. These changes lay the groundwork for the new service, by: - Creating the necessary service files. - Introducing configs for the service. - Declaring high level methods (Skeleton - lifecycle and manager) DC-specific functionality will be migrated to this dccertmon service and optimized in subsequent changes. Non-DC cert management will continue to be handled by certmon. Overall, this commit introduces: - The OCF file necessary for high availability management of the dccertmon service by SM. - Package configurations to build the service (Package: distributedcloud-dccertmon). - Lifecycle manager for a running DC cert monitor service. - Skeleton/base service application logic - CertificateMonitorManager. - RPC notification handlers for subcloud online/managed. - Configuration for the log folders and log rotation. The logs will be available in /var/log/dccertmon/dccertmon.log. These changes are part of a set of commits to introduce the dccertmon service: [1] https://review.opendev.org/c/starlingx/ha/+/941205 [2] https://review.opendev.org/c/starlingx/stx-puppet/+/941208 Test Plan: - PASS: Build dccertmon package - PASS: Install and bootstrap system with custom ISO containing the newly created dccertmon package - PASS: Verify that the dccertmon.service is loaded - PASS: Verify dccertmon is being properly logged to the correct folder. - PASS: Check logged messages and verify execution of - Cert Watcher thread - Task Executor (Audit thread) - Periodic tasks running at expected intervals - PASS: Configure and provision the service using SM and verify it has correctly started and can be restarted with 'sm-restart'. - PASS: Tox checks running on dccertmon Note: This commit has been tested alongside the related changes and their respective test plans. [1][2] Story: 2011311 Task: 51663 Change-Id: Ic23d8d13e4b292cf0508d23eaae99b8e07f36d31 Signed-off-by: Salman Rana <salman.rana@windriver.com>
96 lines
2.8 KiB
Python
96 lines
2.8 KiB
Python
#
|
|
# Copyright (c) 2025 Wind River Systems, Inc.
|
|
#
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
#
|
|
|
|
import time
|
|
|
|
import eventlet
|
|
import greenlet
|
|
from oslo_config import cfg
|
|
from oslo_log import log
|
|
from oslo_service import periodic_task
|
|
|
|
from dccertmon.common import watcher
|
|
|
|
|
|
LOG = log.getLogger(__name__)
|
|
CONF = cfg.CONF
|
|
|
|
|
|
class CertificateMonitorManager(periodic_task.PeriodicTasks):
|
|
def __init__(self):
|
|
super(CertificateMonitorManager, self).__init__(CONF)
|
|
self.mon_thread = None
|
|
self.worker_thread = None
|
|
|
|
def on_start(self):
|
|
LOG.info("Service Start - prepare for initial audit")
|
|
|
|
def start_task_executor(self):
|
|
self.worker_thread = eventlet.greenthread.spawn(self.worker_task_loop)
|
|
self.on_start()
|
|
|
|
def start_cert_watcher(self):
|
|
dc_monitor = None
|
|
while True:
|
|
try:
|
|
dc_monitor = watcher.DC_CertWatcher()
|
|
dc_monitor.initialize()
|
|
except Exception as e:
|
|
LOG.exception(e)
|
|
time.sleep(5)
|
|
else:
|
|
break
|
|
|
|
# spawn monitor thread
|
|
self.mon_thread = eventlet.greenthread.spawn(self.monitor_cert_loop, dc_monitor)
|
|
|
|
def stop_cert_watcher(self):
|
|
if self.mon_thread:
|
|
self.mon_thread.kill()
|
|
self.mon_thread.wait()
|
|
self.mon_thread = None
|
|
|
|
def stop_task_executor(self):
|
|
if self.worker_thread:
|
|
self.worker_thread.kill()
|
|
self.worker_thread.wait()
|
|
self.worker_thread = None
|
|
|
|
def worker_task_loop(self):
|
|
while True:
|
|
try:
|
|
self.run_periodic_tasks(context=None)
|
|
# TODO(srana): Reset sleep after proper implementation
|
|
time.sleep(60)
|
|
except greenlet.GreenletExit:
|
|
break
|
|
except Exception as e:
|
|
LOG.exception(e)
|
|
|
|
def monitor_cert_loop(self, monitor):
|
|
while True:
|
|
# never exit until exit signal received
|
|
try:
|
|
monitor.start_watch(on_success=None, on_error=None)
|
|
except greenlet.GreenletExit:
|
|
break
|
|
except Exception:
|
|
# It shouldn't fall to here, but log and restart if it did
|
|
LOG.exception("Unexpected exception from start_watch")
|
|
time.sleep(1)
|
|
|
|
@periodic_task.periodic_task(spacing=CONF.dccertmon.audit_interval)
|
|
def audit_sc_cert_start(self, context):
|
|
LOG.info("periodic_task: audit_sc_cert_start")
|
|
|
|
@periodic_task.periodic_task(spacing=5)
|
|
def audit_sc_cert_task(self, context):
|
|
LOG.info("periodic_task: audit_sc_cert_task")
|
|
|
|
@periodic_task.periodic_task(spacing=CONF.dccertmon.retry_interval)
|
|
def retry_monitor_task(self, context):
|
|
LOG.info("periodic_task: retry_monitor_task")
|