Saved copies of DataDog objects.

tools/Datadog/Monitor-CPU-load.json

@@ -9,7 +9,6 @@
     "notify_audit": false,
     "locked": false,
     "timeout_h": 0,
-    "silenced": {},
     "include_tags": false,
     "no_data_timeframe": null,
     "require_full_window": true,
@@ -21,8 +20,11 @@
     "thresholds": {
       "critical": 80,
       "warning": 60,
-      "critical_recovery": 70,
-      "warning_recovery": 50
-    }
-  }
-}
+      "warning_recovery": 50,
+      "critical_recovery": 70
+    },
+    "silenced": {}
+  },
+  "priority": null,
+  "restricted_roles": null
+}

tools/Datadog/Monitor-DataSource-health-check.json

@@ -2,14 +2,13 @@
   "id": 17305330,
   "name": "DataSource health check failed",
   "type": "log alert",
-  "query": "logs(\"env:prod status:warn message:\"DataSource health check failed\"\").index(\"main\").rollup(\"count\").by(\"service\").last(\"10m\") > 5",
+  "query": "logs(\"env:prod status:warn message:\\\"DataSource health check failed\\\"\").index(\"main\").rollup(\"count\").by(\"service\").last(\"10m\") > 5",
   "message": "@slack-codekvast-alarms @[email protected]",
   "tags": [],
   "options": {
     "notify_audit": true,
     "locked": false,
     "timeout_h": 0,
-    "silenced": {},
     "include_tags": true,
     "thresholds": {
       "critical": 5,
@@ -18,15 +17,15 @@
     "queryConfig": {
       "logset": {
         "name": "main",
-        "type": "logs",
+        "readDataAccess": true,
         "dailyLimit": null,
         "rateLimited": false,
         "scopeId": "8939",
         "query": "",
-        "retention": 15,
-        "readDataAccess": true,
+        "dailyQuotaDisabled": true,
+        "type": "logs",
         "id": "8939",
-        "dailyQuotaDisabled": true
+        "retention": 15
       },
       "track": "logs",
       "timeRange": {
@@ -48,6 +47,9 @@
       "metric": "count",
       "type": "count",
       "groupBy": "core_service"
-    }
-  }
-}
+    },
+    "silenced": {}
+  },
+  "priority": null,
+  "restricted_roles": null
+}

tools/Datadog/Monitor-OutOfMemory.json

@@ -6,54 +6,50 @@
   "message": "@[email protected] @slack-codekvast-alarms",
   "tags": [],
   "options": {
+    "notify_audit": false,
+    "locked": false,
+    "timeout_h": 0,
+    "include_tags": true,
+    "thresholds": {
+      "critical": 1
+    },
     "queryConfig": {
-      "timeRange": {
-        "from": 1591758013421,
-        "to": 1591773013421,
-        "live": true
-      },
-      "queryString": "message:*java.lang.OutOfMemoryError*",
-      "queryIsFailed": false,
       "logset": {
         "name": "main",
-        "type": "logs",
+        "readDataAccess": true,
         "dailyLimit": null,
         "rateLimited": null,
         "scopeId": "8939",
         "query": "",
-        "retention": 15,
-        "readDataAccess": true,
+        "dailyQuotaDisabled": true,
+        "type": "logs",
         "id": "8939",
-        "dailyQuotaDisabled": true
+        "retention": 15
       },
       "track": "logs",
+      "timeRange": {
+        "to": 1591773013421,
+        "live": true,
+        "from": 1591758013421
+      },
+      "queryString": "message:*java.lang.OutOfMemoryError*",
       "indexes": [
         "main"
-      ]
+      ],
+      "queryIsFailed": false
     },
+    "new_host_delay": 300,
+    "notify_no_data": false,
+    "renotify_interval": 0,
+    "groupby_simple_monitor": false,
+    "enable_logs_sample": true,
     "aggregation": {
       "metric": "count",
       "type": "count",
       "groupBy": "core_service"
     },
-    "thresholds": {
-      "comparison": ">=",
-      "period": {
-        "value": "last_5m",
-        "seconds": 300
-      },
-      "critical": "1",
-      "timeAggregator": "avg"
-    },
-    "enable_logs_sample": true,
-    "notify_audit": false,
-    "locked": false,
-    "timeout_h": 0,
-    "include_tags": true,
-    "new_host_delay": 300,
-    "notify_no_data": false,
-    "renotify_interval": 0,
-    "groupby_simple_monitor": false,
-    "no_data_timeframe": 2
-  }
+    "silenced": {}
+  },
+  "priority": null,
+  "restricted_roles": null
 }

tools/Datadog/Monitor-Publication-queue-buildup.json

@@ -9,7 +9,6 @@
     "notify_audit": false,
     "locked": false,
     "timeout_h": 0,
-    "silenced": {},
     "include_tags": true,
     "no_data_timeframe": null,
     "require_full_window": true,
@@ -20,8 +19,11 @@
     "thresholds": {
       "critical": 200,
       "warning": 150,
-      "warning_recovery": 50,
-      "critical_recovery": 25
-    }
-  }
+      "critical_recovery": 25,
+      "warning_recovery": 50
+    },
+    "silenced": {}
+  },
+  "priority": null,
+  "restricted_roles": null
 }

tools/Datadog/Monitor-RabbitMQ-queue-buildup.json

@@ -9,7 +9,6 @@
     "notify_audit": false,
     "locked": false,
     "timeout_h": 0,
-    "silenced": {},
     "include_tags": true,
     "no_data_timeframe": null,
     "require_full_window": true,
@@ -20,8 +19,11 @@
     "thresholds": {
       "critical": 1000,
       "warning": 500,
-      "warning_recovery": 100,
-      "critical_recovery": 50
-    }
-  }
-}
+      "critical_recovery": 50,
+      "warning_recovery": 100
+    },
+    "silenced": {}
+  },
+  "priority": null,
+  "restricted_roles": null
+}

tools/Datadog/Monitor-database-deadlock.json

@@ -9,7 +9,6 @@
     "notify_audit": false,
     "locked": false,
     "timeout_h": 0,
-    "silenced": {},
     "include_tags": true,
     "thresholds": {
       "critical": 2,
@@ -18,15 +17,15 @@
     "queryConfig": {
       "logset": {
         "name": "main",
-        "type": "logs",
+        "readDataAccess": true,
         "dailyLimit": null,
         "rateLimited": null,
         "scopeId": "8939",
         "query": "",
-        "retention": 15,
-        "readDataAccess": true,
+        "dailyQuotaDisabled": true,
+        "type": "logs",
         "id": "8939",
-        "dailyQuotaDisabled": true
+        "retention": 15
       },
       "track": "logs",
       "timeRange": {
@@ -48,6 +47,9 @@
       "metric": "count",
       "type": "count",
       "groupBy": "core_service"
-    }
-  }
-}
+    },
+    "silenced": {}
+  },
+  "priority": null,
+  "restricted_roles": null
+}

tools/Datadog/Monitor-high-number-of-logged-errors.json

@@ -9,7 +9,6 @@
     "notify_audit": false,
     "locked": false,
     "timeout_h": 0,
-    "silenced": {},
     "include_tags": true,
     "thresholds": {
       "critical": 5,
@@ -18,15 +17,15 @@
     "queryConfig": {
       "logset": {
         "name": "main",
-        "type": "logs",
+        "readDataAccess": true,
         "dailyLimit": null,
         "rateLimited": false,
         "scopeId": "8939",
         "query": "",
-        "retention": 15,
-        "readDataAccess": true,
+        "dailyQuotaDisabled": true,
+        "type": "logs",
         "id": "8939",
-        "dailyQuotaDisabled": true
+        "retention": 15
       },
       "track": "logs",
       "timeRange": {
@@ -48,6 +47,9 @@
       "metric": "count",
       "type": "count",
       "groupBy": "core_service"
-    }
-  }
-}
+    },
+    "silenced": {}
+  },
+  "priority": null,
+  "restricted_roles": null
+}

tools/Datadog/Monitor-unhealthy-targets.json

@@ -0,0 +1,27 @@
+{
+  "id": 28609928,
+  "name": "Unhealthy targets for more than 1 hour",
+  "type": "metric alert",
+  "query": "avg(last_1h):max:aws.applicationelb.un_healthy_host_count.maximum{env:prod} > 1",
+  "message": "@[email protected] @slack-codekvast-alarms",
+  "tags": [],
+  "options": {
+    "notify_audit": false,
+    "locked": false,
+    "timeout_h": 0,
+    "include_tags": true,
+    "no_data_timeframe": null,
+    "require_full_window": true,
+    "new_host_delay": 300,
+    "notify_no_data": false,
+    "renotify_interval": 120,
+    "evaluation_delay": 900,
+    "escalation_message": "",
+    "thresholds": {
+      "critical": 1
+    },
+    "silenced": {}
+  },
+  "priority": null,
+  "restricted_roles": null
+}

tools/ship-services.sh

@@ -9,6 +9,7 @@ tools/clean-workspace.sh
 tools/build-it.sh --no-daemon --no-build-cache --max-workers=1 build
 
 deploy/deploy-backoffice.sh
+deploy/deploy-intake.sh
 deploy/deploy-login.sh
 deploy/deploy-dashboard.sh