[mongo] add mongo recommended cluster monitors (#18858)

* add mongo recommended monitors * fix typo
DataDog · Oct 17, 2024 · 9772e77 · 9772e77
1 parent 2eb2e02
commit 9772e77
Show file tree

Hide file tree

Showing 6 changed files with 147 additions and 4 deletions.
diff --git a/mongo/assets/monitors/high_connections.json b/mongo/assets/monitors/high_connections.json
@@ -1,14 +1,14 @@
 {
   "version": 2,
   "created_at": "2020-08-05",
-  "last_updated_at": "2021-01-11",
+  "last_updated_at": "2024-10-16",
   "title": "Connection pool is reaching saturation",
   "tags": [
     "integration:mongodb"
   ],
   "description": "A connection pool helps reduce application latency and the number of times new connections are created. This monitor tracks the number of incoming connections to alert when the connection pool is near the saturation point.",
   "definition": {
-    "message": "The number of incoming connections is reaching the maximum. {{value}} % of the available connections have been used on {{replset_name.name}}",
+    "message": "The number of incoming connections is reaching the maximum. {{value}} % of the available connections have been used on MongoDB Cluster {{clustername.name}} Replica Set {{replset_name.name}}",
     "name": "[MongoDB] High incoming connections",
     "options": {
       "escalation_message": "",
@@ -26,7 +26,7 @@
       },
       "timeout_h": 0
     },
-    "query": "avg(last_5m):100 * sum:mongodb.connections.current{*} by {replset_name} / ( sum:mongodb.connections.current{*} by {replset_name} + sum:mongodb.connections.available{*} by {replset_name} ) > 90",
+    "query": "avg(last_5m):100 * sum:mongodb.connections.current{*} by {clustername,replset_name} / ( sum:mongodb.connections.current{*} by {clustername,replset_name} + sum:mongodb.connections.available{*} by {clustername,replset_name} ) > 90",
     "tags": [
       "integration:mongodb"
     ],

diff --git a/mongo/assets/monitors/high_fsstorage_usage.json b/mongo/assets/monitors/high_fsstorage_usage.json
@@ -0,0 +1,35 @@
+{
+    "version": 2,
+    "created_at": "2024-10-16",
+    "last_updated_at": "2024-10-16",
+    "title": "Used file system storage is reaching capacity",
+    "tags": [
+      "integration:mongodb"
+    ],
+    "description": "This monitor tracks the used file system storage on a MongoDB server to alert when it is reaching capacity.",
+    "definition": {
+      "message": "The used file system storage is reaching capacity for database host {{database_instance.name}} on MongoDB Cluster {{clustername.name}}. {{value}} % of the total storage has been used.",
+      "name": "[MongoDB] High file system storage usage",
+      "options": {
+        "escalation_message": "",
+        "include_tags": true,
+        "locked": false,
+        "new_host_delay": 300,
+        "no_data_timeframe": null,
+        "notify_audit": false,
+        "notify_no_data": false,
+        "renotify_interval": "0",
+        "require_full_window": true,
+        "thresholds": {
+          "critical": 80,
+          "warning": 70
+        },
+        "timeout_h": 0
+      },
+      "query": "avg(last_60m):100 * avg:mongodb.stats.fsusedsize{*} by {clustername,database_instance} / avg:mongodb.stats.fstotalsize{*} by {clustername,database_instance} > 80",
+      "tags": [
+        "integration:mongodb"
+      ],
+      "type": "query alert"
+    }
+  }
diff --git a/mongo/assets/monitors/high_replication_lag.json b/mongo/assets/monitors/high_replication_lag.json
@@ -0,0 +1,35 @@
+{
+    "version": 2,
+    "created_at": "2024-10-16",
+    "last_updated_at": "2024-10-16",
+    "title": "High replication lag",
+    "tags": [
+      "integration:mongodb"
+    ],
+    "description": "This monitor tracks the replication lag on a MongoDB replica set to alert when it is high.",
+    "definition": {
+      "message": "MongoDB Cluster {{clustername.name}} member {{member.name}} replication lag is high. The replication lag is {{value}} seconds.",
+      "name": "[MongoDB] High replication lag",
+      "options": {
+        "escalation_message": "",
+        "include_tags": true,
+        "locked": false,
+        "new_host_delay": 300,
+        "no_data_timeframe": null,
+        "notify_audit": false,
+        "notify_no_data": false,
+        "renotify_interval": "0",
+        "require_full_window": true,
+        "thresholds": {
+          "critical": 120,
+          "warning": 60
+        },
+        "timeout_h": 0
+      },
+      "query": "avg(last_5m):100 * avg:mongodb.replset.optime_lag{*} by {clustername,member} > 120",
+      "tags": [
+        "integration:mongodb"
+      ],
+      "type": "query alert"
+    }
+  }
diff --git a/mongo/assets/monitors/low_oplog_window.json b/mongo/assets/monitors/low_oplog_window.json
@@ -0,0 +1,35 @@
+{
+    "version": 2,
+    "created_at": "2024-10-16",
+    "last_updated_at": "2024-10-16",
+    "title": "Low oplog window",
+    "tags": [
+      "integration:mongodb"
+    ],
+    "description": "This monitor tracks the oplog window on a MongoDB replica set to alert when it is insufficient.",
+    "definition": {
+      "message": "Oplog window for database host {{database_instance.name}} on MongoDB Cluster {{clustername.name}} is below the threshold. The oplog window is {{value}} seconds.",
+      "name": "[MongoDB] Low oplog window",
+      "options": {
+        "escalation_message": "",
+        "include_tags": true,
+        "locked": false,
+        "new_host_delay": 300,
+        "no_data_timeframe": null,
+        "notify_audit": false,
+        "notify_no_data": false,
+        "renotify_interval": "0",
+        "require_full_window": true,
+        "thresholds": {
+          "critical": 3600,
+          "warning": 7200
+        },
+        "timeout_h": 0
+      },
+      "query": "avg(last_60m):100 * avg:mongodb.oplog.timediff{*} by {clustername,database_instance} < 3600",
+      "tags": [
+        "integration:mongodb"
+      ],
+      "type": "query alert"
+    }
+  }
diff --git a/mongo/assets/monitors/unhealthy_repliset_member.json b/mongo/assets/monitors/unhealthy_repliset_member.json
@@ -0,0 +1,34 @@
+{
+    "version": 2,
+    "created_at": "2024-10-16",
+    "last_updated_at": "2024-10-16",
+    "title": "Unhealthy replica set member",
+    "tags": [
+      "integration:mongodb"
+    ],
+    "description": "This monitor tracks the health of a MongoDB replica set member to alert when it is unhealthy.",
+    "definition": {
+      "message": "MongoDB Cluster {{clustername.name}} replica set member {{database_instance.name}} is unhealthy.",
+      "name": "[MongoDB] Unhealthy replica set member",
+      "options": {
+        "escalation_message": "",
+        "include_tags": true,
+        "locked": false,
+        "new_host_delay": 300,
+        "no_data_timeframe": null,
+        "notify_audit": false,
+        "notify_no_data": false,
+        "renotify_interval": "0",
+        "require_full_window": true,
+        "thresholds": {
+          "critical": 1
+        },
+        "timeout_h": 0
+      },
+      "query": "max(last_5m):avg:mongodb.replset.health{*} by {clustername,database_instance} != 1",
+      "tags": [
+        "integration:mongodb"
+      ],
+      "type": "query alert"
+    }
+  }
diff --git a/mongo/manifest.json b/mongo/manifest.json
@@ -63,7 +63,11 @@
       "mongodb": "assets/dashboards/overview.json"
     },
     "monitors": {
-      "Connection pool is reaching saturation": "assets/monitors/high_connections.json"
+      "Connection pool is reaching saturation": "assets/monitors/high_connections.json",
+      "High replication lag": "assets/monitors/high_replication_lag.json",
+      "Low oplog window": "assets/monitors/low_oplog_window.json",
+      "Unhealthy replica set member": "assets/monitors/unhealthy_repliset_member.json",
+      "Used file system storage is reaching capacity": "assets/monitors/high_fsstorage_usage.json"
     },
     "saved_views": {
       "operations_by_type_overview": "assets/saved_views/operations_by_type_overview.json",