Avoid overwriting AWS cloud_metadata (DataDog#20774)

* Avoid overwriting AWS cloud_metadata

* Changelog

* Fix

* Retry wal stats more times

Author: sethsamuel

postgres/changelog.d/20774.fixed

@@ -0,0 +1 @@
+Fixed a bug where the AWS configuration was overwritten for the Postgres integration

postgres/datadog_checks/postgres/postgres.py

@@ -203,9 +203,8 @@ def set_resource_tags(self):
             # allow for detecting if the host is an RDS host, and emit
             # the resource properly even if the `aws` config is unset
             self.tags.append("dd.internal.resource:aws_rds_instance:{}".format(self.resolved_hostname))
-            self.cloud_metadata["aws"] = {
-                "instance_endpoint": self.resolved_hostname,
-            }
+            self.cloud_metadata["aws"] = self.cloud_metadata.get("aws", {})
+            self.cloud_metadata["aws"]["instance_endpoint"] = self.resolved_hostname
         if self.cloud_metadata.get("azure") is not None:
             deployment_type = self.cloud_metadata.get("azure")["deployment_type"]
             # some `deployment_type`s map to multiple `resource_type`s

postgres/tests/test_pg_integration.py

@@ -619,7 +619,7 @@ def test_wal_stats(aggregator, integration_check, pg_instance, is_aurora):
         cur.execute("insert into persons (lastname) values ('test');")
 
     # Wait for pg_stat_wal to be updated
-    for _ in range(10):
+    for _ in range(50):
         with conn.cursor() as cur:
             cur.execute("select wal_records, wal_bytes from pg_stat_wal;")
             new_wal_records = cur.fetchall()[0][0]