update_metadata: a datasource can support network re-config every boot

Very basic type definitions are now defined to distinguish 'boot'
events from 'new instance (first boot)'. Event types will now be handed
to a datasource.update_metadata method which can determine whether
to refresh its metadata and re-render configuration based on that
source event.

A datasource can 'subscribe' to an event by setting up the update_events
attribute on the datasource class which describe what config scope is
updated by a list of matching events. By default datasources will have
the following update_events: {'network': [EventType.BOOT_NEW_INSTANCE]}
This setting says the datasource will re-write network configuration only
on first boot of a new instance or when the instance id changes.

New methods are now present on the datasource:
  - clear_cached_attrs: Resets cached datasource attributes to values
    listed in datasource.cached_attr_defaults. This is performed prior to
    processing a fresh metadata process to avoid keeping old/invalid
    cached data around.
  - update_metadata: accepts source_event_types to determine if the
    metadata should be crawled again and processed

2 files changed, 159 insertions, 2 deletions

diff --git a/cloudinit/sources/__init__.py b/cloudinit/sources/__init__.py
index 90d74575..f424316a 100644
--- a/cloudinit/sources/__init__.py
+++ b/cloudinit/sources/__init__.py
@@ -19,6 +19,7 @@ from cloudinit.atomic_helper import write_json
 from cloudinit import importer
 from cloudinit import log as logging
 from cloudinit import net
+from cloudinit.event import EventType
 from cloudinit import type_utils
 from cloudinit import user_data as ud
 from cloudinit import util
@@ -102,6 +103,25 @@ class DataSource(object):
     url_timeout = 10    # timeout for each metadata url read attempt
     url_retries = 5     # number of times to retry url upon 404
 
+    # The datasource defines a list of supported EventTypes during which
+    # the datasource can react to changes in metadata and regenerate
+    # network configuration on metadata changes.
+    # A datasource which supports writing network config on each system boot
+    # would set update_events = {'network': [EventType.BOOT]}
+
+    # Default: generate network config on new instance id (first boot).
+    update_events = {'network': [EventType.BOOT_NEW_INSTANCE]}
+
+    # N-tuple listing default values for any metadata-related class
+    # attributes cached on an instance by a process_data runs. These attribute
+    # values are reset via clear_cached_attrs during any update_metadata call.
+    cached_attr_defaults = (
+        ('ec2_metadata', UNSET), ('network_json', UNSET),
+        ('metadata', {}), ('userdata', None), ('userdata_raw', None),
+        ('vendordata', None), ('vendordata_raw', None))
+
+    _dirty_cache = False
+
     def __init__(self, sys_cfg, distro, paths, ud_proc=None):
         self.sys_cfg = sys_cfg
         self.distro = distro
@@ -134,11 +154,31 @@ class DataSource(object):
             'region': self.region,
             'availability-zone': self.availability_zone}}
 
+    def clear_cached_attrs(self, attr_defaults=()):
+        """Reset any cached metadata attributes to datasource defaults.
+
+        @param attr_defaults: Optional tuple of (attr, value) pairs to
+           set instead of cached_attr_defaults.
+        """
+        if not self._dirty_cache:
+            return
+        if attr_defaults:
+            attr_values = attr_defaults
+        else:
+            attr_values = self.cached_attr_defaults
+
+        for attribute, value in attr_values:
+            if hasattr(self, attribute):
+                setattr(self, attribute, value)
+        if not attr_defaults:
+            self._dirty_cache = False
+
     def get_data(self):
         """Datasources implement _get_data to setup metadata and userdata_raw.
 
         Minimally, the datasource should return a boolean True on success.
         """
+        self._dirty_cache = True
         return_value = self._get_data()
         json_file = os.path.join(self.paths.run_dir, INSTANCE_JSON_FILE)
         if not return_value:
@@ -174,6 +214,7 @@ class DataSource(object):
         return return_value
 
     def _get_data(self):
+        """Walk metadata sources, process crawled data and save attributes."""
         raise NotImplementedError(
             'Subclasses of DataSource must implement _get_data which'
             ' sets self.metadata, vendordata_raw and userdata_raw.')
@@ -416,6 +457,41 @@ class DataSource(object):
     def get_package_mirror_info(self):
         return self.distro.get_package_mirror_info(data_source=self)
 
+    def update_metadata(self, source_event_types):
+        """Refresh cached metadata if the datasource supports this event.
+
+        The datasource has a list of update_events which
+        trigger refreshing all cached metadata as well as refreshing the
+        network configuration.
+
+        @param source_event_types: List of EventTypes which may trigger a
+            metadata update.
+
+        @return True if the datasource did successfully update cached metadata
+            due to source_event_type.
+        """
+        supported_events = {}
+        for event in source_event_types:
+            for update_scope, update_events in self.update_events.items():
+                if event in update_events:
+                    if not supported_events.get(update_scope):
+                        supported_events[update_scope] = []
+                    supported_events[update_scope].append(event)
+        for scope, matched_events in supported_events.items():
+            LOG.debug(
+                "Update datasource metadata and %s config due to events: %s",
+                scope, ', '.join(matched_events))
+            # Each datasource has a cached config property which needs clearing
+            # Once cleared that config property will be regenerated from
+            # current metadata.
+            self.clear_cached_attrs((('_%s_config' % scope, UNSET),))
+        if supported_events:
+            self.clear_cached_attrs()
+            result = self.get_data()
+            if result:
+                return True
+        return False
+
     def check_instance_id(self, sys_cfg):
         # quickly (local check only) if self.instance_id is still
         return False
@@ -520,7 +596,7 @@ def find_source(sys_cfg, distro, paths, ds_deps, cfg_list, pkg_list, reporter):
             with myrep:
                 LOG.debug("Seeing if we can get any data from %s", cls)
                 s = cls(sys_cfg, distro, paths)
-                if s.get_data():
+                if s.update_metadata([EventType.BOOT_NEW_INSTANCE]):
                     myrep.message = "found %s data from %s" % (mode, name)
                     return (s, type_utils.obj_name(cls))
         except Exception:
diff --git a/cloudinit/sources/tests/test_init.py b/cloudinit/sources/tests/test_init.py
index d5bc98a4..dcd221be 100644
--- a/cloudinit/sources/tests/test_init.py
+++ b/cloudinit/sources/tests/test_init.py
@@ -5,10 +5,11 @@ import os
 import six
 import stat
 
+from cloudinit.event import EventType
 from cloudinit.helpers import Paths
 from cloudinit import importer
 from cloudinit.sources import (
-    INSTANCE_JSON_FILE, DataSource)
+    INSTANCE_JSON_FILE, DataSource, UNSET)
 from cloudinit.tests.helpers import CiTestCase, skipIf, mock
 from cloudinit.user_data import UserDataProcessor
 from cloudinit import util
@@ -381,3 +382,83 @@ class TestDataSource(CiTestCase):
                     get_args(grandchild.get_hostname),  # pylint: disable=W1505
                     '%s does not implement DataSource.get_hostname params'
                     % grandchild)
+
+    def test_clear_cached_attrs_resets_cached_attr_class_attributes(self):
+        """Class attributes listed in cached_attr_defaults are reset."""
+        count = 0
+        # Setup values for all cached class attributes
+        for attr, value in self.datasource.cached_attr_defaults:
+            setattr(self.datasource, attr, count)
+            count += 1
+        self.datasource._dirty_cache = True
+        self.datasource.clear_cached_attrs()
+        for attr, value in self.datasource.cached_attr_defaults:
+            self.assertEqual(value, getattr(self.datasource, attr))
+
+    def test_clear_cached_attrs_noops_on_clean_cache(self):
+        """Class attributes listed in cached_attr_defaults are reset."""
+        count = 0
+        # Setup values for all cached class attributes
+        for attr, _ in self.datasource.cached_attr_defaults:
+            setattr(self.datasource, attr, count)
+            count += 1
+        self.datasource._dirty_cache = False   # Fake clean cache
+        self.datasource.clear_cached_attrs()
+        count = 0
+        for attr, _ in self.datasource.cached_attr_defaults:
+            self.assertEqual(count, getattr(self.datasource, attr))
+            count += 1
+
+    def test_clear_cached_attrs_skips_non_attr_class_attributes(self):
+        """Skip any cached_attr_defaults which aren't class attributes."""
+        self.datasource._dirty_cache = True
+        self.datasource.clear_cached_attrs()
+        for attr in ('ec2_metadata', 'network_json'):
+            self.assertFalse(hasattr(self.datasource, attr))
+
+    def test_clear_cached_attrs_of_custom_attrs(self):
+        """Custom attr_values can be passed to clear_cached_attrs."""
+        self.datasource._dirty_cache = True
+        cached_attr_name = self.datasource.cached_attr_defaults[0][0]
+        setattr(self.datasource, cached_attr_name, 'himom')
+        self.datasource.myattr = 'orig'
+        self.datasource.clear_cached_attrs(
+            attr_defaults=(('myattr', 'updated'),))
+        self.assertEqual('himom', getattr(self.datasource, cached_attr_name))
+        self.assertEqual('updated', self.datasource.myattr)
+
+    def test_update_metadata_only_acts_on_supported_update_events(self):
+        """update_metadata won't get_data on unsupported update events."""
+        self.assertEqual(
+            {'network': [EventType.BOOT_NEW_INSTANCE]},
+            self.datasource.update_events)
+
+        def fake_get_data():
+            raise Exception('get_data should not be called')
+
+        self.datasource.get_data = fake_get_data
+        self.assertFalse(
+            self.datasource.update_metadata(
+                source_event_types=[EventType.BOOT]))
+
+    def test_update_metadata_returns_true_on_supported_update_event(self):
+        """update_metadata returns get_data response on supported events."""
+
+        def fake_get_data():
+            return True
+
+        self.datasource.get_data = fake_get_data
+        self.datasource._network_config = 'something'
+        self.datasource._dirty_cache = True
+        self.assertTrue(
+            self.datasource.update_metadata(
+                source_event_types=[
+                    EventType.BOOT, EventType.BOOT_NEW_INSTANCE]))
+        self.assertEqual(UNSET, self.datasource._network_config)
+        self.assertIn(
+            "DEBUG: Update datasource metadata and network config due to"
+            " events: New instance first boot",
+            self.logs.getvalue())
+
+
+# vi: ts=4 expandtab