Add new service cluster_has_scheduled_action

CHANGELOG.md

@@ -5,6 +5,7 @@
 ### Added
 
 * Add `sync_standby` as a valid replica type for `cluster_has_replica`. (contributed by @mattpoel)
+* Add a new service `cluster_has_scheduled_action` to warn of any scheduled switchover or restart.
 
 ### Fixed
 

check_patroni/cli.py

@@ -13,6 +13,7 @@
     ClusterHasLeader,
     ClusterHasLeaderSummary,
     ClusterHasReplica,
+    ClusterHasScheduledAction,
     ClusterIsInMaintenance,
     ClusterNodeCount,
 )
@@ -436,6 +437,33 @@ def cluster_is_in_maintenance(ctx: click.Context) -> None:
     check.main(verbose=ctx.obj.verbose, timeout=ctx.obj.timeout)
 
 
+@main.command(name="cluster_has_scheduled_action")
+@click.pass_context
+@nagiosplugin.guarded
+def cluster_has_scheduled_action(ctx: click.Context) -> None:
+    """Check if the cluster has a scheduled action (switchover or restart)
+
+    \b
+    Check:
+    * `OK`: If the cluster has no scheduled action
+    * `CRITICAL`: otherwise.
+
+    \b
+    Perfdata:
+    * `scheduled_actions` is 1 if the cluster has scheduled actions.
+    * `scheduled_switchover` is 1 if the cluster has a scheduled switchover.
+    * `scheduled_restart` counts the number of scheduled restart in the cluster.
+    """
+    check = nagiosplugin.Check()
+    check.add(
+        ClusterHasScheduledAction(ctx.obj.connection_info),
+        nagiosplugin.ScalarContext("has_scheduled_actions", None, "0:0"),
+        nagiosplugin.ScalarContext("scheduled_switchover"),
+        nagiosplugin.ScalarContext("scheduled_restart"),
+    )
+    check.main(verbose=ctx.obj.verbose, timeout=ctx.obj.timeout)
+
+
 @main.command(name="node_is_primary")
 @click.pass_context
 @nagiosplugin.guarded

check_patroni/cluster.py

@@ -191,3 +191,24 @@ def probe(self: "ClusterIsInMaintenance") -> Iterable[nagiosplugin.Metric]:
                 1 if "pause" in item_dict and item_dict["pause"] else 0,
             )
         ]
+
+
+class ClusterHasScheduledAction(PatroniResource):
+    def probe(self: "ClusterIsInMaintenance") -> Iterable[nagiosplugin.Metric]:
+        item_dict = self.rest_api("cluster")
+
+        scheduled_switchover = 0
+        scheduled_restart = 0
+        if "scheduled_switchover" in item_dict:
+            scheduled_switchover = 1
+
+        for member in item_dict["members"]:
+            if "scheduled_restart" in member:
+                scheduled_restart += 1
+
+        # The actual check
+        yield nagiosplugin.Metric("has_scheduled_actions", 1 if (scheduled_switchover + scheduled_restart) > 0 else 0)
+
+        # The performance data : scheduled_switchover, scheduled action count
+        yield nagiosplugin.Metric("scheduled_switchover", scheduled_switchover)
+        yield nagiosplugin.Metric("scheduled_restart", scheduled_restart)

tests/json/cluster_has_scheduled_action_ko_restart.json

@@ -0,0 +1,27 @@
+{
+  "members": [
+    {
+      "name": "p1",
+      "role": "sync_standby",
+      "state": "streaming",
+      "api_url": "http://10.20.30.51:8008/patroni",
+      "host": "10.20.30.51",
+      "port": 5432,
+      "timeline": 3,
+      "scheduled_restart": {
+        "schedule": "2023-10-08T11:30:00+00:00",
+        "postmaster_start_time": "2023-08-21 08:08:33.415237+00:00"
+      },
+      "lag": 0
+    },
+    {
+      "name": "p2",
+      "role": "leader",
+      "state": "running",
+      "api_url": "http://10.20.30.52:8008/patroni",
+      "host": "10.20.30.52",
+      "port": 5432,
+      "timeline": 3
+    }
+  ]
+}

tests/json/cluster_has_scheduled_action_ko_switchover.json

@@ -0,0 +1,28 @@
+{
+  "members": [
+    {
+      "name": "p1",
+      "role": "sync_standby",
+      "state": "streaming",
+      "api_url": "http://10.20.30.51:8008/patroni",
+      "host": "10.20.30.51",
+      "port": 5432,
+      "timeline": 3,
+      "lag": 0
+    },
+    {
+      "name": "p2",
+      "role": "leader",
+      "state": "running",
+      "api_url": "http://10.20.30.52:8008/patroni",
+      "host": "10.20.30.52",
+      "port": 5432,
+      "timeline": 3
+    }
+  ],
+  "scheduled_switchover": {
+    "at": "2023-10-08T11:30:00+00:00",
+    "from": "p1",
+    "to": "p2"
+  }
+}

tests/json/cluster_has_scheduled_action_ok.json

@@ -0,0 +1,33 @@
+{
+  "members": [
+    {
+      "name": "srv1",
+      "role": "leader",
+      "state": "running",
+      "api_url": "https://10.20.199.3:8008/patroni",
+      "host": "10.20.199.3",
+      "port": 5432,
+      "timeline": 51
+    },
+    {
+      "name": "srv2",
+      "role": "replica",
+      "state": "streaming",
+      "api_url": "https://10.20.199.4:8008/patroni",
+      "host": "10.20.199.4",
+      "port": 5432,
+      "timeline": 51,
+      "lag": 0
+    },
+    {
+      "name": "srv3",
+      "role": "sync_standby",
+      "state": "streaming",
+      "api_url": "https://10.20.199.5:8008/patroni",
+      "host": "10.20.199.5",
+      "port": 5432,
+      "timeline": 51,
+      "lag": 0
+    }
+  ]
+}

tests/test_cluster_has_scheduled_action.py

@@ -0,0 +1,54 @@
+from click.testing import CliRunner
+from pytest_mock import MockerFixture
+
+from check_patroni.cli import main
+
+from .tools import my_mock
+
+
+def test_cluster_has_scheduled_action_ok(
+    mocker: MockerFixture, use_old_replica_state: bool
+) -> None:
+    runner = CliRunner()
+
+    my_mock(mocker, "cluster_has_scheduled_action_ok", 200)
+    result = runner.invoke(
+        main, ["-e", "https://10.20.199.3:8008", "cluster_has_scheduled_action"]
+    )
+    assert result.exit_code == 0
+    assert (
+        result.stdout
+        == "CLUSTERHASSCHEDULEDACTION OK - has_scheduled_actions is 0 | has_scheduled_actions=0;;0 scheduled_restart=0 scheduled_switchover=0\n"
+    )
+
+
+def test_cluster_has_scheduled_action_ko_switchover(
+    mocker: MockerFixture, use_old_replica_state: bool
+) -> None:
+    runner = CliRunner()
+
+    my_mock(mocker, "cluster_has_scheduled_action_ko_switchover", 200)
+    result = runner.invoke(
+        main, ["-e", "https://10.20.199.3:8008", "cluster_has_scheduled_action"]
+    )
+    assert result.exit_code == 2
+    assert (
+        result.stdout
+        == "CLUSTERHASSCHEDULEDACTION CRITICAL - has_scheduled_actions is 1 (outside range 0:0) | has_scheduled_actions=1;;0 scheduled_restart=0 scheduled_switchover=1\n"
+    )
+
+
+def test_cluster_has_scheduled_action_ko_restart(
+    mocker: MockerFixture, use_old_replica_state: bool
+) -> None:
+    runner = CliRunner()
+
+    my_mock(mocker, "cluster_has_scheduled_action_ko_restart", 200)
+    result = runner.invoke(
+        main, ["-e", "https://10.20.199.3:8008", "cluster_has_scheduled_action"]
+    )
+    assert result.exit_code == 2
+    assert (
+        result.stdout
+        == "CLUSTERHASSCHEDULEDACTION CRITICAL - has_scheduled_actions is 1 (outside range 0:0) | has_scheduled_actions=1;;0 scheduled_restart=1 scheduled_switchover=0\n"
+    )

vagrant/check_patroni.sh

@@ -12,6 +12,7 @@ check_patroni -e "$1" cluster_config_has_changed --state-file cluster.sate_file
 check_patroni -e "$1" cluster_has_leader
 check_patroni -e "$1" cluster_has_replica
 check_patroni -e "$1" cluster_is_in_maintenance
+check_patroni -e "$1" cluster_has_scheduled_action
 check_patroni -e "$1" cluster_node_count
 echo "-- Node checks"
 check_patroni -e "$1" node_is_alive