feat: Eliminate redundant configuration reads (#5536)

When instance id hasn't changed and datasource hasn't changed, don't
forcibly reload the configuration.

cloudinit/stages.py

@@ -11,6 +11,7 @@
 import sys
 from collections import namedtuple
 from contextlib import suppress
+from pathlib import Path
 from typing import Dict, Iterable, List, Optional, Set, Tuple, Union
 
 from cloudinit import (
@@ -459,8 +460,13 @@ def _reflect_cur_instance(self):
         # Remove the old symlink and attach a new one so
         # that further reads/writes connect into the right location
         idir = self._get_ipath()
-        util.del_file(self.paths.instance_link)
-        util.sym_link(idir, self.paths.instance_link)
+        destination = Path(self.paths.instance_link).resolve().absolute()
+        already_instancified = destination == Path(idir).absolute()
+        if already_instancified:
+            LOG.info("Instance link already exists, not recreating it.")
+        else:
+            util.del_file(self.paths.instance_link)
+            util.sym_link(idir, self.paths.instance_link)
 
         # Ensures these dirs exist
         dir_list = []
@@ -499,10 +505,16 @@ def _reflect_cur_instance(self):
         )
 
         self._write_to_cache()
-        # Ensure needed components are regenerated
-        # after change of instance which may cause
-        # change of configuration
-        self._reset()
+        if already_instancified and previous_ds == ds:
+            LOG.info(
+                "Not re-loading configuration, instance "
+                "id and datasource have not changed."
+            )
+            # Ensure needed components are regenerated
+            # after change of instance which may cause
+            # change of configuration
+        else:
+            self._reset()
         return iid
 
     def previous_iid(self):

tests/integration_tests/test_instance_id.py

@@ -0,0 +1,97 @@
+from typing import cast
+
+import pytest
+from pycloudlib.lxd.instance import LXDInstance
+
+from cloudinit import subp
+from tests.integration_tests.instances import IntegrationInstance
+from tests.integration_tests.integration_settings import PLATFORM
+
+_INSTANCE_ID = 0
+
+
+def setup_meta_data(instance: LXDInstance):
+    """Increment the instance id and apply it to the instance."""
+    global _INSTANCE_ID
+    _INSTANCE_ID += 1
+    command = [
+        "lxc",
+        "config",
+        "set",
+        instance.name,
+        f"user.meta-data=instance-id: test_{_INSTANCE_ID}",
+    ]
+    subp.subp(command)
+
+
+# class TestInstanceID:
+@pytest.mark.skipif(
+    PLATFORM not in ["lxd_container", "lxd_vm"],
+    reason="Uses lxd-specific behavior.",
+)
+@pytest.mark.lxd_setup.with_args(setup_meta_data)
+@pytest.mark.lxd_use_exec
+def test_instance_id_changes(client: IntegrationInstance):
+    """Verify instance id change behavior
+
+    If the id from the datasource changes, cloud-init should update the
+    instance id link.
+    """
+    client.execute("cloud-init status --wait")
+    # check that instance id is the one we set
+    assert (
+        "test_1"
+        == client.execute("cloud-init query instance-id").stdout.rstrip()
+    )
+    assert (
+        "/var/lib/cloud/instances/test_1"
+        == client.execute(
+            "readlink -f /var/lib/cloud/instance"
+        ).stdout.rstrip()
+    )
+
+    instance = cast(LXDInstance, client.instance)
+    setup_meta_data(instance)
+    client.restart()
+    client.execute("cloud-init status --wait")
+    # check that instance id is the one we reset
+    assert (
+        "test_2"
+        == client.execute("cloud-init query instance-id").stdout.rstrip()
+    )
+    assert (
+        "/var/lib/cloud/instances/test_2"
+        == client.execute(
+            "readlink -f /var/lib/cloud/instance"
+        ).stdout.rstrip()
+    )
+
+
+@pytest.mark.lxd_use_exec
+def test_instance_id_no_changes(client: IntegrationInstance):
+    """Verify instance id no change behavior
+
+    If the id from the datasource does not change, cloud-init should not
+    update the instance id link.
+    """
+    instance_id = client.execute(
+        "cloud-init query instance-id"
+    ).stdout.rstrip()
+    assert (
+        f"/var/lib/cloud/instances/{instance_id}"
+        == client.execute(
+            "readlink -f /var/lib/cloud/instance"
+        ).stdout.rstrip()
+    )
+    client.restart()
+    client.execute("cloud-init status --wait")
+    assert (
+        instance_id
+        == client.execute("cloud-init query instance-id").stdout.rstrip()
+    )
+    assert (
+        f"/var/lib/cloud/instances/{instance_id}"
+        == client.execute(
+            "readlink -f /var/lib/cloud/instance"
+        ).stdout.rstrip()
+    )