feat(systemd): Warn user of unexpected run mode (#5209)

On systemd, services are started by PID 1. When this doesn't happen, cloud-init
is in an unknown run state and should warn the user.

Reorder pid log to be able to reuse Distro information.

Add docstring deprecating util.is_Linux().

cloudinit/cmd/main.py

@@ -79,17 +79,29 @@ def print_exc(msg=""):
     sys.stderr.write("\n")
 
 
-def log_ppid():
-    if util.is_Linux():
+def log_ppid(distro, bootstage_name):
+    if distro.is_linux:
         ppid = os.getppid()
-        LOG.info("PID [%s] started cloud-init.", ppid)
+        log = LOG.info
+        extra_message = ""
+        if 1 != ppid and distro.uses_systemd():
+            log = LOG.warning
+            extra_message = (
+                " Unsupported configuration: boot stage called "
+                "outside of systemd"
+            )
+        log(
+            "PID [%s] started cloud-init '%s'.%s",
+            ppid,
+            bootstage_name,
+            extra_message,
+        )
 
 
 def welcome(action, msg=None):
     if not msg:
         msg = welcome_format(action)
     util.multi_log("%s\n" % (msg), console=False, stderr=True, log=LOG)
-    log_ppid()
     return msg
 
 
@@ -333,10 +345,8 @@ def main_init(name, args):
     #    objects config as it may be different from init object
     # 10. Run the modules for the 'init' stage
     # 11. Done!
-    if not args.local:
-        w_msg = welcome_format(name)
-    else:
-        w_msg = welcome_format("%s-local" % (name))
+    bootstage_name = "init-local" if args.local else "init"
+    w_msg = welcome_format(bootstage_name)
     init = stages.Init(ds_deps=deps, reporter=args.reporter)
     # Stage 1
     init.read_cfg(extract_fns(args))
@@ -364,6 +374,7 @@ def main_init(name, args):
     # config applied.  We send the welcome message now, as stderr/out have
     # been redirected and log now configured.
     welcome(name, msg=w_msg)
+    log_ppid(init.distro, bootstage_name)
 
     # re-play early log messages before logging was setup
     for lvl, msg in early_logs:
@@ -591,7 +602,8 @@ def main_modules(action_name, args):
     #    the modules objects configuration
     # 5. Run the modules for the given stage name
     # 6. Done!
-    w_msg = welcome_format("%s:%s" % (action_name, name))
+    bootstage_name = "%s:%s" % (action_name, name)
+    w_msg = welcome_format(bootstage_name)
     init = stages.Init(ds_deps=[], reporter=args.reporter)
     # Stage 1
     init.read_cfg(extract_fns(args))
@@ -628,6 +640,7 @@ def main_modules(action_name, args):
 
     # now that logging is setup and stdout redirected, send welcome
     welcome(name, msg=w_msg)
+    log_ppid(init.distro, bootstage_name)
 
     if name == "init":
         util.deprecate(

cloudinit/distros/__init__.py

@@ -171,6 +171,7 @@ def __init__(self, name, cfg, paths):
         self.package_managers: List[PackageManager] = []
         self._dhcp_client = None
         self._fallback_interface = None
+        self.is_linux = True
 
     def _unpickle(self, ci_pkl_version: int) -> None:
         """Perform deserialization fixes for Distro."""
@@ -187,6 +188,8 @@ def _unpickle(self, ci_pkl_version: int) -> None:
             self._dhcp_client = None
         if not hasattr(self, "_fallback_interface"):
             self._fallback_interface = None
+        if not hasattr(self, "is_linux"):
+            self.is_linux = True
 
     def _validate_entry(self, entry):
         if isinstance(entry, str):

cloudinit/distros/bsd.py

@@ -40,6 +40,13 @@ def __init__(self, name, cfg, paths):
         cfg["rsyslog_svcname"] = "rsyslogd"
         self.osfamily = platform.system().lower()
         self.net_ops = bsd_netops.BsdNetOps
+        self.is_linux = False
+
+    def _unpickle(self, ci_pkl_version: int) -> None:
+        super()._unpickle(ci_pkl_version)
+
+        # this needs to be after the super class _unpickle to override it
+        self.is_linux = False
 
     def _read_system_hostname(self):
         sys_hostname = self._read_hostname(self.hostname_conf_fn)

cloudinit/util.py

@@ -499,6 +499,12 @@ def multi_log(
 
 @lru_cache()
 def is_Linux():
+    """deprecated: prefer Distro object's `is_linux` property
+
+    Multiple sources of truth is bad, and already know whether we are
+    working with Linux from the Distro class. Using Distro offers greater code
+    reusablity, cleaner code, and easier maintenance.
+    """
     return "Linux" in platform.system()