Merge pull request #2256 from newrelic/release

1/25/2024 Release

alert-policies/amazon-cloudwatch-network-monitor/HighPacketLoss.yml

@@ -0,0 +1,43 @@
+# Name of the alert
+name: High Packet Loss
+
+# Description and details
+description: |+
+  The latency for successful requests between the time that the request was made and the response was passed back
+
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+  query: "SELECT max(`aws.networkmonitor.PacketLoss`) FROM Metric"
+
+# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+  - priority: CRITICAL
+    # Operator used to compare against the threshold.
+    operator: ABOVE
+    # Value that triggers a violation; float value
+    threshold: 30
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+  # Adding a Warning threshold is optional
+  - priority: WARNING
+    operator: ABOVE
+    threshold: 20
+    thresholdDuration: 300
+    thresholdOccurrences: ALL
+
+
+# OPTIONAL: URL of runbook to be sent with notification
+runbookUrl:
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/amazon-cloudwatch-network-monitor/Network Unhealthy.yml

@@ -0,0 +1,38 @@
+# Name of the alert
+name: Network Unhealthy
+
+# Description and details
+description: |+
+  The Network Health Indicator supports two values – 0 (AWS Network is health) or 1(AWS Network is
+  Degraded)
+
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+  query: "SELECT sum(aws.networkmonitor.PacketLoss) from Metric"
+
+# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+  - priority: CRITICAL
+    # Operator used to compare against the threshold.
+    operator: EQUALS
+    # Value that triggers a violation; float value
+    threshold: 1
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+
+
+# OPTIONAL: URL of runbook to be sent with notification
+runbookUrl:
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

dashboards/amazon-cloudwatch-network-monitor/amazon-cloudwatch-network-monitor.json

@@ -0,0 +1,175 @@
+{
+  "name": "Amazon CloudWatch Network Monitor",
+  "description": null,
+  "pages": [
+    {
+      "name": "Amazon CloudWatch Network Monitor",
+      "description": null,
+      "widgets": [
+        {
+          "title": "",
+          "layout": {
+            "column": 1,
+            "row": 1,
+            "width": 3,
+            "height": 2
+          },
+          "linkedEntityGuids": null,
+          "visualization": {
+            "id": "viz.markdown"
+          },
+          "rawConfiguration": {
+            "text": "# Amazon CloudWatch Network Monitor\nIt is an active network monitoring service to troubleshoot issues in hybrid network connectivity from on-premise to AWS via AWS Direct Connect. Using this real-time data, customers can mitigate the issue quickly by routing the traffic to a redundant healthy path."
+          }
+        },
+        {
+          "title": "Network Health",
+          "layout": {
+            "column": 4,
+            "row": 1,
+            "width": 3,
+            "height": 2
+          },
+          "linkedEntityGuids": null,
+          "visualization": {
+            "id": "viz.billboard"
+          },
+          "rawConfiguration": {
+            "facet": {
+              "showOtherSeries": false
+            },
+            "nrqlQueries": [
+              {
+                "accountIds": [],
+                "query": "FROM Metric select if(sum(aws.networkmonitor.HealthIndicator) = 1, 'Unhealthy', 'Healthy') as 'Status'"
+              }
+            ],
+            "platformOptions": {
+              "ignoreTimeRange": false
+            }
+          }
+        },
+        {
+          "title": "Overlay Network Performance",
+          "layout": {
+            "column": 7,
+            "row": 1,
+            "width": 6,
+            "height": 2
+          },
+          "linkedEntityGuids": null,
+          "visualization": {
+            "id": "viz.line"
+          },
+          "rawConfiguration": {
+            "colors": {
+              "seriesOverrides": [
+                {
+                  "color": "#2bf410",
+                  "seriesName": "Health Indicator"
+                }
+              ]
+            },
+            "facet": {
+              "showOtherSeries": false
+            },
+            "legend": {
+              "enabled": true
+            },
+            "nrqlQueries": [
+              {
+                "accountIds": [],
+                "query": "FROM Metric select sum(aws.networkmonitor.HealthIndicator) as 'Health Indicator' TIMESERIES AUTO"
+              }
+            ],
+            "platformOptions": {
+              "ignoreTimeRange": false
+            },
+            "yAxisLeft": {
+              "zero": true
+            },
+            "yAxisRight": {
+              "zero": true
+            }
+          }
+        },
+        {
+          "title": "Round Trip Latency",
+          "layout": {
+            "column": 1,
+            "row": 3,
+            "width": 12,
+            "height": 2
+          },
+          "linkedEntityGuids": null,
+          "visualization": {
+            "id": "viz.line"
+          },
+          "rawConfiguration": {
+            "facet": {
+              "showOtherSeries": false
+            },
+            "legend": {
+              "enabled": true
+            },
+            "nrqlQueries": [
+              {
+                "accountIds": [],
+                "query": "select min(aws.networkmonitor.RTT) as 'Minimum Latency',max(aws.networkmonitor.RTT) as 'Maximum Latency',average(aws.networkmonitor.RTT) as 'Average Latency' from Metric where metricName = 'aws.networkmonitor.RTT' TIMESERIES AUTO facet aws.networkmonitor.Monitor"
+              }
+            ],
+            "platformOptions": {
+              "ignoreTimeRange": false
+            },
+            "units": {
+              "unit": "MS"
+            },
+            "yAxisLeft": {
+              "zero": true
+            },
+            "yAxisRight": {
+              "zero": true
+            }
+          }
+        },
+        {
+          "title": "Packet Loss (%)",
+          "layout": {
+            "column": 1,
+            "row": 5,
+            "width": 12,
+            "height": 2
+          },
+          "linkedEntityGuids": null,
+          "visualization": {
+            "id": "viz.line"
+          },
+          "rawConfiguration": {
+            "facet": {
+              "showOtherSeries": false
+            },
+            "legend": {
+              "enabled": true
+            },
+            "nrqlQueries": [
+              {
+                "accountIds": [],
+                "query": "SELECT max(`aws.networkmonitor.PacketLoss`) FROM Metric FACET aws.networkmonitor.Monitor TIMESERIES AUTO"
+              }
+            ],
+            "platformOptions": {
+              "ignoreTimeRange": false
+            },
+            "yAxisLeft": {
+              "zero": true
+            },
+            "yAxisRight": {
+              "zero": true
+            }
+          }
+        }
+      ]
+    }
+  ],
+  "variables": []
+}