Update cluster_has_replica to account for the quorum_standby state

check_patroni/cli.py

@@ -361,6 +361,13 @@ def cluster_has_leader(ctx: click.Context) -> None:
     type=str,
     help="Critical threshold for the number of sync replica.",
 )
+@click.option(
+    "--sync-type",
+    type=click.Choice(["any", "sync", "quorum"], case_sensitive=True),
+    default="any",
+    show_default=True,
+    help="Synchronous replication mode used to filter and count sync standbies.",
+)
 @click.option("--max-lag", "max_lag", type=str, help="maximum allowed lag")
 @click.pass_context
 @nagiosplugin.guarded
@@ -370,9 +377,10 @@ def cluster_has_replica(
     critical: str,
     sync_warning: str,
     sync_critical: str,
+    sync_type: str,
     max_lag: str,
 ) -> None:
-    """Check if the cluster has healthy replicas and/or if some are sync standbies
+    """Check if the cluster has healthy replicas and/or if some are sync or quorum standbies
 
     \b
     For patroni (and this check):
@@ -381,7 +389,7 @@ def cluster_has_replica(
 
     \b
     A healthy replica:
-    * has a `replica` or `sync_standby` role
+    * has a `replica`, `quorum_standby` or `sync_standby` role
     * has the same timeline as the leader and
       * is in `running` state (patroni < V3.0.4)
       * is in `streaming` or `in archive recovery` state (patroni >= V3.0.4)
@@ -398,16 +406,24 @@ def cluster_has_replica(
     switchover or failover and the standbies are in the process of catching up with
     the new leader. The alert shouldn't last long.
 
+    In PostgreSQL, synchronous replication has two modes: on and quorum and is
+    configured with the gucs `synchronous_standby_names` and `synchronous_commit`. Patroni
+    uses the parameter `synchronous_mode`, which can be set to `on`, `quorum` and `off`,
+    and has `synchronous_node_count` to configure the synchronous replication factor.
+    Please note that, in synchronous replication, the number of servers tagged as "{sync|quorum}_standby"
+    (what we measure) is not always equal tot `synchronous_node_count`.
+
     \b
     Check:
     * `OK`: if the healthy_replica count and their lag are compatible with the replica count threshold.
-            and if the sync_replica count is compatible with the sync replica count threshold.
+            and if the synchronous replica count is compatible with the sync replica count threshold.
     * `WARNING` / `CRITICAL`: otherwise
 
     \b
     Perfdata:
     * healthy_replica & unhealthy_replica count
-    * the number of sync_replica, they are included in the previous count
+    * the number of sync_replica (sync or quorum depending on `--sync-type`), they are included
+      in the previous count
     * the lag of each replica labelled with "member name"_lag
     * the timeline of each replica labelled with "member name"_timeline
     * a boolean to tell if the node is a sync stanbdy labelled with "member name"_sync
@@ -416,7 +432,7 @@ def cluster_has_replica(
     tmax_lag = size_to_byte(max_lag) if max_lag is not None else None
     check = nagiosplugin.Check()
     check.add(
-        ClusterHasReplica(ctx.obj.connection_info, tmax_lag),
+        ClusterHasReplica(ctx.obj.connection_info, tmax_lag, sync_type),
         nagiosplugin.ScalarContext(
             "healthy_replica",
             warning,

check_patroni/cluster.py

@@ -133,9 +133,12 @@ def problem(self, results: nagiosplugin.Result) -> str:
 
 
 class ClusterHasReplica(PatroniResource):
-    def __init__(self, connection_info: ConnectionInfo, max_lag: Union[int, None]):
+    def __init__(
+        self, connection_info: ConnectionInfo, max_lag: Union[int, None], sync_type: str
+    ):
         super().__init__(connection_info)
         self.max_lag = max_lag
+        self.sync_type = sync_type
 
     def probe(self) -> Iterable[nagiosplugin.Metric]:
         def debug_member(member: Any, health: str) -> None:
@@ -161,7 +164,7 @@ def debug_member(member: Any, health: str) -> None:
 
         # Look for replicas
         for member in cluster_item_dict["members"]:
-            if member["role"] in ["replica", "sync_standby"]:
+            if member["role"] in ["replica", "sync_standby", "quorum_standby"]:
                 if member["lag"] == "unknown":
                     # This could happen if the node is stopped
                     # nagiosplugin doesn't handle strings in perfstats
@@ -175,7 +178,11 @@ def debug_member(member: Any, health: str) -> None:
                             "name": member["name"],
                             "lag": member["lag"],
                             "timeline": member["timeline"],
-                            "sync": 1 if member["role"] == "sync_standby" else 0,
+                            "sync": (
+                                1
+                                if member["role"] in ["sync_standby", "quorum_standby"]
+                                else 0
+                            ),
                         }
                     )
 
@@ -214,7 +221,13 @@ def debug_member(member: Any, health: str) -> None:
                     unhealthy_replica += 1
                     continue
 
-                if member["role"] == "sync_standby":
+                if (
+                    self.sync_type in ["sync", "any"]
+                    and member["role"] == "sync_standby"
+                ) or (
+                    self.sync_type in ["quorum", "any"]
+                    and member["role"] == "quorum_standby"
+                ):
                     sync_replica += 1
 
                 if self.max_lag is None or self.max_lag >= int(member["lag"]):

tests/json/cluster_has_replica_ok_quorum.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": "quorum_standby",
+      "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": "quorum_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_replica.py

@@ -32,6 +32,59 @@ def test_cluster_has_relica_ok(runner: CliRunner, patroni_api: PatroniAPI) -> No
     assert result.exit_code == 0
 
 
+@pytest.fixture
+def cluster_has_replica_ok_sync(
+    patroni_api: PatroniAPI, old_replica_state: bool, datadir: Path, tmp_path: Path
+) -> Iterator[None]:
+    cluster_path: Union[str, Path] = "cluster_has_replica_ok.json"
+    patroni_path = "cluster_has_replica_patroni_verion_3.1.0.json"
+    if old_replica_state:
+        cluster_path = cluster_api_set_replica_running(datadir / cluster_path, tmp_path)
+        patroni_path = "cluster_has_replica_patroni_verion_3.0.0.json"
+    with patroni_api.routes({"cluster": cluster_path, "patroni": patroni_path}):
+        yield None
+
+
+@pytest.mark.usefixtures("cluster_has_replica_ok_sync")
+def test_cluster_has_relica_ok_sync(runner: CliRunner, patroni_api: PatroniAPI) -> None:
+    result = runner.invoke(
+        main, ["-e", patroni_api.endpoint, "cluster_has_replica", "--sync-type", "sync"]
+    )
+    assert (
+        result.stdout
+        == "CLUSTERHASREPLICA OK - healthy_replica is 2 | healthy_replica=2 srv2_lag=0 srv2_sync=0 srv2_timeline=51 srv3_lag=0 srv3_sync=1 srv3_timeline=51 sync_replica=1 unhealthy_replica=0\n"
+    )
+    assert result.exit_code == 0
+
+
+@pytest.fixture
+def cluster_has_replica_ok_quorum(
+    patroni_api: PatroniAPI, old_replica_state: bool, datadir: Path, tmp_path: Path
+) -> Iterator[None]:
+    cluster_path: Union[str, Path] = "cluster_has_replica_ok_quorum.json"
+    patroni_path = "cluster_has_replica_patroni_verion_3.1.0.json"
+    if old_replica_state:
+        cluster_path = cluster_api_set_replica_running(datadir / cluster_path, tmp_path)
+        patroni_path = "cluster_has_replica_patroni_verion_3.0.0.json"
+    with patroni_api.routes({"cluster": cluster_path, "patroni": patroni_path}):
+        yield None
+
+
+@pytest.mark.usefixtures("cluster_has_replica_ok_quorum")
+def test_cluster_has_relica_ok_qorum(
+    runner: CliRunner, patroni_api: PatroniAPI
+) -> None:
+    result = runner.invoke(
+        main,
+        ["-e", patroni_api.endpoint, "cluster_has_replica", "--sync-type", "quorum"],
+    )
+    assert (
+        result.stdout
+        == "CLUSTERHASREPLICA OK - healthy_replica is 2 | healthy_replica=2 srv2_lag=0 srv2_sync=1 srv2_timeline=51 srv3_lag=0 srv3_sync=1 srv3_timeline=51 sync_replica=2 unhealthy_replica=0\n"
+    )
+    assert result.exit_code == 0
+
+
 @pytest.mark.usefixtures("cluster_has_replica_ok")
 def test_cluster_has_replica_ok_with_count_thresholds(
     runner: CliRunner, patroni_api: PatroniAPI