Updated alert and dashboard

alert-policies/stripe/cpuUsage.yml → alert-policies/stripe/clientErrors.yml

@@ -1,10 +1,10 @@
-name: CPU usage (%)
+name: 4xx client errors
 
 description: |+
-  This alert is triggered if CPU usage exceeds 90% for 5 minutes.
+  This alert is triggered if customer faces 4xx errors more than 5 times for 5 minutes.
 type: STATIC
 nrql:
-  query: "SELECT latest(host.cpuPercent) AS 'CPU Used %' FROM Metric"
+  query: "SELECT count(*) from Transaction WHERE httpResponseCode LIKE '4%'"
 
 # Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
 valueFunction: SINGLE_VALUE
@@ -15,7 +15,7 @@ terms:
     # Operator used to compare against the threshold.
     operator: ABOVE
     # Value that triggers a violation
-    threshold: 90
+    threshold: 5
     # Time in seconds; 120 - 3600
     thresholdDuration: 300
     # How many data points must be in violation for the duration
@@ -24,7 +24,7 @@ terms:
     # Operator used to compare against the threshold.
     operator: ABOVE
     # Value that triggers a violation
-    threshold: 80
+    threshold: 3
     # Time in seconds; 120 - 3600
     thresholdDuration: 300
     # How many data points must be in violation for the duration

dashboards/stripe/stripe.json

@@ -279,33 +279,69 @@
           }
         },
         {
-          "title": "Transaction volume",
+          "title": "4xx client errors",
           "layout": {
             "column": 9,
             "row": 3,
-            "width": 4,
+            "width": 2,
             "height": 2
           },
           "linkedEntityGuids": null,
           "visualization": {
-            "id": "viz.area"
+            "id": "viz.billboard"
           },
           "rawConfiguration": {
             "facet": {
               "showOtherSeries": false
             },
-            "legend": {
-              "enabled": true
+            "nrqlQueries": [
+              {
+                "accountIds": [],
+                "query": "SELECT count(*) from Transaction  FACET concat(httpResponseCode, ' client errors') WHERE httpResponseCode LIKE '4%' "
+              }
+            ],
+            "platformOptions": {
+              "ignoreTimeRange": false
+            },
+            "thresholds": [
+              {
+                "alertSeverity": "CRITICAL",
+                "value": 1
+              }
+            ]
+          }
+        },
+        {
+          "title": "5xx server errors",
+          "layout": {
+            "column": 11,
+            "row": 3,
+            "width": 2,
+            "height": 2
+          },
+          "linkedEntityGuids": null,
+          "visualization": {
+            "id": "viz.billboard"
+          },
+          "rawConfiguration": {
+            "facet": {
+              "showOtherSeries": false
             },
             "nrqlQueries": [
               {
                 "accountIds": [],
-                "query": "SELECT uniqueCount(stripe.session_id)as'Transaction volume' from Metric TIMESERIES "
+                "query": "SELECT count(*) from Transaction FACET concat(httpResponseCode, ' server errors') WHERE httpResponseCode LIKE '5%'"
               }
             ],
             "platformOptions": {
               "ignoreTimeRange": false
-            }
+            },
+            "thresholds": [
+              {
+                "alertSeverity": "CRITICAL",
+                "value": 1
+              }
+            ]
           }
         },
         {