feat: add golden signals pack

packs/golden-signals-web/alerts/cpu.yml

@@ -0,0 +1,37 @@
+---
+
+name: CPU Usage
+
+details: |+
+  This alert fires when a host's CPU usage goes above 90 percent for a period of 5 minutes.
+
+type: STATIC
+
+nrql:
+  query: "from SystemSample select average(cpuPercent) facet hostname"
+
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+- priority: CRITICAL
+  operator: ABOVE
+  # Value that triggers a violation
+  threshold: 90
+  # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions
+  thresholdDuration: 300
+  # How many data points must be in violation for the duration
+  thresholdOccurrences: ALL
+
+# Loss of Signal Settings
+expiration:
+  # Close open violations if signal is lost (Default: false)
+  closeViolationsOnExpiration: true
+  # Open "Loss of Signal" violation if signal is lost (Default: false)
+  openViolationOnExpiration: false
+  # Time in seconds; Max value: 172800 (48hrs), null if closeViolationsOnExpiration and openViolationOnExpiration are both 'false'
+  expirationDuration: 86400
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

packs/golden-signals-web/alerts/errors.yml

@@ -0,0 +1,37 @@
+---
+
+name: Errors
+
+details: |+
+  This alert fires when the 10 percent of the transactions against an application end with an error, over a period of 5 minutes.
+
+type: STATIC
+
+nrql:
+  query: "from Transaction select percentage(count(*), where error is not false) as 'Errors' where transactionType = 'Web' facet appName"
+
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+- priority: CRITICAL
+  operator: ABOVE
+  # Value that triggers a violation
+  threshold: 10
+  # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions
+  thresholdDuration: 300
+  # How many data points must be in violation for the duration
+  thresholdOccurrences: ALL
+
+# Loss of Signal Settings
+expiration:
+  # Close open violations if signal is lost (Default: false)
+  closeViolationsOnExpiration: true
+  # Open "Loss of Signal" violation if signal is lost (Default: false)
+  openViolationOnExpiration: false
+  # Time in seconds; Max value: 172800 (48hrs), null if closeViolationsOnExpiration and openViolationOnExpiration are both 'false'
+  expirationDuration: 86400
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

packs/golden-signals-web/alerts/memory.yml

@@ -0,0 +1,38 @@
+---
+
+name: Memory Usage
+
+details: |+
+  When memory limits are reached, applications can do weird and unpredicable things.
+  This alert fires when the percentage of memory used on a host exceeds 90 percent for 5 minutes.
+
+type: STATIC
+
+nrql:
+  query: "from SystemSample select average(memoryUsedPercent) facet hostname"
+
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+- priority: CRITICAL
+  operator: ABOVE
+  # Value that triggers a violation
+  threshold: 90
+  # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions
+  thresholdDuration: 300
+  # How many data points must be in violation for the duration
+  thresholdOccurrences: ALL
+
+# Loss of Signal Settings
+expiration:
+  # Close open violations if signal is lost (Default: false)
+  closeViolationsOnExpiration: true
+  # Open "Loss of Signal" violation if signal is lost (Default: false)
+  openViolationOnExpiration: false
+  # Time in seconds; Max value: 172800 (48hrs), null if closeViolationsOnExpiration and openViolationOnExpiration are both 'false'
+  expirationDuration: 86400
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

packs/golden-signals-web/alerts/response_time.yml

@@ -0,0 +1,37 @@
+---
+
+name: Response time
+
+details: |+
+  This alert fires when the average transaction duration is above 5 seconds for 5 mintues.
+
+type: STATIC
+
+nrql:
+  query: "FROM Transaction select average(duration) where transactionType = 'Web' facet appName"
+
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+- priority: CRITICAL
+  operator: ABOVE
+  # Value that triggers a violation
+  threshold: 5
+  # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions
+  thresholdDuration: 300
+  # How many data points must be in violation for the duration
+  thresholdOccurrences: ALL
+
+# Loss of Signal Settings
+expiration:
+  # Close open violations if signal is lost (Default: false)
+  closeViolationsOnExpiration: true
+  # Open "Loss of Signal" violation if signal is lost (Default: false)
+  openViolationOnExpiration: false
+  # Time in seconds; Max value: 172800 (48hrs), null if closeViolationsOnExpiration and openViolationOnExpiration are both 'false'
+  expirationDuration: 86400
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

packs/golden-signals-web/alerts/throughput.yml

@@ -0,0 +1,38 @@
+---
+
+name: Throughput
+
+details: |+
+  Throughput is a great way to measure the health of your applications.
+  This alert fires when the throughput of a web application drops below 5 transactions in a 5 minute period.
+
+type: STATIC
+
+nrql:
+  query: "FROM Transaction select count(*) where transactionType = 'Web' facet appName"
+
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+- priority: CRITICAL
+  operator: BELOW
+  # Value that triggers a violation
+  threshold: 5
+  # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions
+  thresholdDuration: 300
+  # How many data points must be in violation for the duration
+  thresholdOccurrences: ALL
+
+# Loss of Signal Settings
+expiration:
+  # Close open violations if signal is lost (Default: false)
+  closeViolationsOnExpiration: true
+  # Open "Loss of Signal" violation if signal is lost (Default: false)
+  openViolationOnExpiration: false
+  # Time in seconds; Max value: 172800 (48hrs), null if closeViolationsOnExpiration and openViolationOnExpiration are both 'false'
+  expirationDuration: 86400
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

packs/golden-signals-web/config.yml

@@ -0,0 +1,19 @@
+
+# Name of the pack
+name: Golden Signals for Web Servers
+
+# Description of the pack
+description: |+
+  Golden signals alerts for web servers. Includes alerts and a dashboard for throughput, errors, response time, CPU usage, and memory usage.
+
+# Support level: New Relic | Verified | Community
+level: New Relic
+
+# Design
+icon: icon.jpeg
+logo: logo.png
+
+# Authors of the pack
+authors:
+  - New Relic
+  - Alec Swanson

packs/golden-signals-web/dashboards/golden_signals.json

@@ -0,0 +1,163 @@
+{
+  "name": "Golden Signals Web",
+  "description": null,
+  "permissions": "PUBLIC_READ_WRITE",
+  "pages": [
+    {
+      "name": "Golden Signals Web",
+      "description": null,
+      "widgets": [
+        {
+          "visualization": {
+            "id": "viz.line"
+          },
+          "layout": {
+            "column": 1,
+            "row": 1,
+            "height": 3,
+            "width": 4
+          },
+          "title": "Response Time",
+          "rawConfiguration": {
+            "facet": {
+              "showOtherSeries": false
+            },
+            "legend": {
+              "enabled": true
+            },
+            "nrqlQueries": [
+              {
+                "accountId": 0,
+                "query": "FROM Transaction select average(duration) where transactionType = 'Web' TIMESERIES facet appName"
+              }
+            ],
+            "yAxisLeft": {
+              "zero": true
+            }
+          },
+          "linkedEntityGuids": null
+        },
+        {
+          "visualization": {
+            "id": "viz.line"
+          },
+          "layout": {
+            "column": 5,
+            "row": 1,
+            "height": 3,
+            "width": 4
+          },
+          "title": "Throughput",
+          "rawConfiguration": {
+            "facet": {
+              "showOtherSeries": false
+            },
+            "legend": {
+              "enabled": true
+            },
+            "nrqlQueries": [
+              {
+                "accountId": 0,
+                "query": "FROM Transaction select count(*) where transactionType = 'Web' TIMESERIES facet appName"
+              }
+            ],
+            "yAxisLeft": {
+              "zero": true
+            }
+          },
+          "linkedEntityGuids": null
+        },
+        {
+          "visualization": {
+            "id": "viz.line"
+          },
+          "layout": {
+            "column": 9,
+            "row": 1,
+            "height": 3,
+            "width": 4
+          },
+          "title": "Errors %",
+          "rawConfiguration": {
+            "facet": {
+              "showOtherSeries": false
+            },
+            "legend": {
+              "enabled": true
+            },
+            "nrqlQueries": [
+              {
+                "accountId": 0,
+                "query": "from Transaction select percentage(count(*), where error is not false) as 'Errors' where transactionType = 'Web' TIMESERIES facet appName"
+              }
+            ],
+            "yAxisLeft": {
+              "zero": true
+            }
+          },
+          "linkedEntityGuids": null
+        },
+        {
+          "visualization": {
+            "id": "viz.line"
+          },
+          "layout": {
+            "column": 1,
+            "row": 4,
+            "height": 3,
+            "width": 4
+          },
+          "title": "Average CPU Usage",
+          "rawConfiguration": {
+            "facet": {
+              "showOtherSeries": false
+            },
+            "legend": {
+              "enabled": true
+            },
+            "nrqlQueries": [
+              {
+                "accountId": 0,
+                "query": "from SystemSample select average(cpuPercent) TIMESERIES facet hostname"
+              }
+            ],
+            "yAxisLeft": {
+              "zero": true
+            }
+          },
+          "linkedEntityGuids": null
+        },
+        {
+          "visualization": {
+            "id": "viz.line"
+          },
+          "layout": {
+            "column": 5,
+            "row": 4,
+            "height": 3,
+            "width": 4
+          },
+          "title": "Memory Usage",
+          "rawConfiguration": {
+            "facet": {
+              "showOtherSeries": false
+            },
+            "legend": {
+              "enabled": true
+            },
+            "nrqlQueries": [
+              {
+                "accountId": 0,
+                "query": "from SystemSample select average(memoryUsedPercent) timeseries facet hostname"
+              }
+            ],
+            "yAxisLeft": {
+              "zero": true
+            }
+          },
+          "linkedEntityGuids": null
+        }
+      ]
+    }
+  ]
+}