Merge branch 'main' into Java-RMI-Installation-upgrade

Author: nr-mlosier

alert-policies/adobe-commerce-business-insights/5xxErrors.yml

@@ -0,0 +1,35 @@
+name: 5xx Server Errors
+
+description: |+
+  This alert is triggered if the customer faces 5xx server errors more than 5 times in 5 minutes.
+type: STATIC
+nrql:
+  query: "SELECT count(*) as '5xx Server Errors' from Transaction WHERE httpResponseCode LIKE '5%'"
+
+# 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
+    threshold: 10
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+  - priority: WARNING
+    # Operator used to compare against the threshold.
+    operator: ABOVE
+    # Value that triggers a violation
+    threshold: 5
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/adobe-commerce-business-insights/cpuUsage.yml

@@ -0,0 +1,35 @@
+name: CPU Usage (%)
+
+description: |+
+  This alert is triggered if CPU usage exceeds 90% for 5 minutes.
+type: STATIC
+nrql:
+  query: "SELECT latest(host.cpuPercent) AS 'CPU Used %' 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
+    threshold: 90
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+  - priority: WARNING
+    # Operator used to compare against the threshold.
+    operator: ABOVE
+    # Value that triggers a violation
+    threshold: 80
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/adobe-commerce-business-insights/downtime.yml

@@ -0,0 +1,35 @@
+name: Downtime (%)
+
+description: |+
+  This alert is triggered if Downtime is more than 1% for 2 minutes.
+type: STATIC
+nrql:
+  query: "SELECT percentage(count(result), where result = 'FAILED') as 'Downtime (%)' from SyntheticCheck"
+
+# 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
+    threshold: 1
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 120
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+  - priority: WARNING
+    # Operator used to compare against the threshold.
+    operator: ABOVE
+    # Value that triggers a violation
+    threshold: 0.5
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 120
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/adobe-commerce-business-insights/memoryUsage.yml

@@ -0,0 +1,35 @@
+name: Memory Usage (%)
+
+description: |+
+  This alert is triggered if Memory usage exceeds 90% for 5 minutes.
+type: STATIC
+nrql:
+  query: "SELECT latest(host.memoryUsedPercent) as 'Memory Used %' 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
+    threshold: 90
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+  - priority: WARNING
+    # Operator used to compare against the threshold.
+    operator: ABOVE
+    # Value that triggers a violation
+    threshold: 80
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/amazon-appstream/HighCapacityUtilization.yml

@@ -0,0 +1,27 @@
+name: High Capacity Utilization
+
+description: |+
+  This alert is triggered when the Capacity Utilization is above 90%.
+
+type: STATIC
+nrql:
+  query: "SELECT average(`aws.appstream.CapacityUtilization`) as 'Query' 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
+    threshold: 90
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/amazon-appstream/HighInsufficientCapacityErrors.yml

@@ -0,0 +1,27 @@
+name: High Insufficient Capacity Errors
+
+description: |+
+  This alert is triggered when Insufficient Capacity Errors are above 10 in 10 minutes.
+
+type: STATIC
+nrql:
+  query: "SELECT count(`aws.appstream.InsufficientCapacityError`) as 'Query' 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
+    threshold: 100
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 600
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/amazon-cloudsearch/HighIndexUtilization.yml

@@ -0,0 +1,27 @@
+name: High Index Utilization
+
+description: |+
+  This alert is triggered when the Index Utilization is above 90%.
+
+type: STATIC
+nrql:
+  query: "SELECT average(`aws.cloudsearch.IndexUtilization`) as 'Query' 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
+    threshold: 90
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/azure-machine-learning/ModelDeployFailed.yml

@@ -0,0 +1,33 @@
+name: Model Deployment Failed
+
+description: |+
+  This alert is triggered if the number of Failure exceeds 20 within 10 minutes.
+type: STATIC
+nrql:
+  query: "FROM Metric SELECT sum(azure.machinelearningservices.workspaces.ModelDeployFailed) AS 'ModelDeployFailed'"
+
+# 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
+    threshold: 20
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 600
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+  # Adding a Warning threshold is optional
+  - priority: WARNING
+    operator: ABOVE
+    threshold: 10
+    thresholdDuration: 600
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/f5/f5-node-offline.yml

@@ -0,0 +1,19 @@
+name: F5 Node Offline
+description: |+
+  This alert fires when an F5 Node has an availability state = 'offline' for at least 10 minutes.
+type: STATIC
+nrql:
+  query: "FROM F5BigIpNodeSample SELECT count(*) FACET reportingEndpoint, displayName WHERE node.availabilityState = 0"
+valueFunction: SINGLE_VALUE 
+terms:
+  - priority: CRITICAL
+    operator: ABOVE
+    threshold: 0
+    thresholdDuration: 600
+    thresholdOccurrences: ALL
+signal:
+  aggregationDelay: 120
+  aggregationMethod: EVENT_FLOW
+  aggregationWindow: 60
+
+violationTimeLimitSeconds: 259200

alert-policies/f5/f5-pool-member-offline.yml

@@ -0,0 +1,19 @@
+name: F5 Pool Member Offline
+description: |+
+  This alert fires when an F5 Pool Member has an availability state = 'offline' for at least 10 minutes.
+type: STATIC
+nrql:
+  query: "FROM F5BigIpPoolMemberSample SELECT count(*) FACET aparse(url, '%//*'), poolName, displayName WHERE member.availabilityState = 0"
+valueFunction: SINGLE_VALUE 
+terms:
+  - priority: CRITICAL
+    operator: ABOVE
+    threshold: 0
+    thresholdDuration: 600
+    thresholdOccurrences: ALL
+signal:
+  aggregationDelay: 120
+  aggregationMethod: EVENT_FLOW
+  aggregationWindow: 60
+
+violationTimeLimitSeconds: 259200

alert-policies/f5/f5-pool-offline.yml

@@ -0,0 +1,19 @@
+name: F5 Pool Offline
+description: |+
+  This alert fires when an F5 Pool has an availability state = 'offline' for at least 10 minutes.
+type: STATIC
+nrql:
+  query: "FROM F5BigIpPoolSample SELECT count(*) FACET reportingEndpoint, displayName WHERE pool.availabilityState = 0"
+valueFunction: SINGLE_VALUE 
+terms:
+  - priority: CRITICAL
+    operator: ABOVE
+    threshold: 0
+    thresholdDuration: 600
+    thresholdOccurrences: ALL
+signal:
+  aggregationDelay: 120
+  aggregationMethod: EVENT_FLOW
+  aggregationWindow: 60
+
+violationTimeLimitSeconds: 259200

alert-policies/f5/f5-virtual-server-offline.yml

@@ -0,0 +1,19 @@
+name: F5 Virtual Server Offline
+description: |+
+  This alert fires when an F5 Virtual Server has an availability state = 'offline' for at least 10 minutes.
+type: STATIC
+nrql:
+  query: "FROM F5BigIpVirtualServerSample SELECT count(*) FACET reportingEndpoint, displayName WHERE virtualserver.availabilityState = 0"
+valueFunction: SINGLE_VALUE 
+terms:
+  - priority: CRITICAL
+    operator: ABOVE
+    threshold: 0
+    thresholdDuration: 600
+    thresholdOccurrences: ALL
+signal:
+  aggregationDelay: 120
+  aggregationMethod: EVENT_FLOW
+  aggregationWindow: 60
+
+violationTimeLimitSeconds: 259200

alert-policies/openstack-controller/ImageStatus.yml

@@ -0,0 +1,32 @@
+# Name of the alert
+name: Image Status
+
+# Description and details
+description: |+
+  This alert is triggered when the image status is inactive for 5 minutes.
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+
+  query: "SELECT count(*)FROM OSImageSample where openstack.glance.image.status != 'active'"
+
+# 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
+    threshold: 1
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400