Merge branch 'main' into main

alert-policies/amazon-cloudwatch-internet-monitor/LowerAvailabilityScore.yml

@@ -0,0 +1,40 @@
+# Name of the alert
+name: Lower Availability Score
+
+# Description and details
+description: |+
+  This alert occurs when availability score of traffic falls below 100 for 5 minutes
+
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+  query: "SELECT average(aws.internetmonitor.AvailabilityScore) 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: BELOW
+    # Value that triggers a violation; float value
+    threshold: 100
+    # 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: BELOW
+    threshold: 95
+    thresholdDuration: 300
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400
+

alert-policies/amazon-cloudwatch-internet-monitor/LowerPerformanceScore.yml

@@ -0,0 +1,39 @@
+# Name of the alert
+name: Lower Performance Score
+
+# Description and details
+description: |+
+  This alert occurs when performance score of traffic falls below 100 for 5 minutes
+
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+  query: "SELECT average(aws.internetmonitor.PerformanceScore) 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: BELOW
+    # Value that triggers a violation; float value
+    threshold: 100
+    # 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: BELOW
+    threshold: 95
+    thresholdDuration: 300
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/amazon-codebuild/BuildsFailed.yml

@@ -0,0 +1,26 @@
+name: Builds Failed
+
+description: |+
+  This alert is triggered when the Builds Failed Count is above 100 in 10 minutes.
+type: STATIC
+nrql:
+  query: "SELECT count(`aws.codebuild.FailedBuilds`) 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-codebuild/CPUUtilization.yml

@@ -0,0 +1,26 @@
+name: High CPU Utilization
+
+description: |+
+  This alert is triggered when the CPU Utilization is above 90%.
+type: STATIC
+nrql:
+  query: "SELECT rate(sum(aws.codebuild.CPUUtilized), 1 second) * 100 as cpuUsage 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-elastictranscoder/JobsErrored.yml

@@ -0,0 +1,27 @@
+name: Jobs Error
+
+description: |+
+  This alert is triggered when the Job Error Count is above 100 in 10 minutes.
+
+type: STATIC
+nrql:
+  query: "SELECT count(`aws.elastictranscoder.JobsErrored`) 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-inspector/HighAssessmentRunFindings.yml

@@ -0,0 +1,34 @@
+name: High Assessment Run Findings
+
+description: |+
+  This alert is triggered if the number of Assessment Run Findings exceeds 100 for 5 minutes.
+
+type: STATIC
+nrql:
+  query: "SELECT sum(`aws.inspector.TotalAssessmentRunFindings`) 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: 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: 50
+    thresholdDuration: 300
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/amazon-sagemaker/HighEndpointsCPUUtil.yml

@@ -0,0 +1,27 @@
+name: High CPU Utilization By Endpoints
+
+description: |+
+  This alert is triggered when the CPU Utilization by Endpoints is above 90%.
+
+type: STATIC
+nrql:
+  query: "SELECT average(`aws..aws.sagemaker.endpoints.CPUUtilization`) 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-sagemaker/HighEndpointsMemoryUtil.yml

@@ -0,0 +1,27 @@
+name: High Memory Utilization By Endpoints
+
+description: |+
+  This alert is triggered when the memory Utilization by Endpoints is above 90%.
+
+type: STATIC
+nrql:
+  query: "SELECT average(`aws..aws.sagemaker.endpoints.MemoryUtilization`) 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-sagemaker/HighModelInvocationErrors.yml

@@ -0,0 +1,27 @@
+name: High Model Invocation Errors
+
+description: |+
+  This alert is triggered when Model Invocation errors are above 100 in 10 minutes.
+
+type: STATIC
+nrql:
+  query: "SELECT count(`aws.sagemaker.InvocationModelErrors`) 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-sagemaker/HighTrainingJobsCPUUtil.yml

@@ -0,0 +1,27 @@
+name: High CPU Utilization By Training Jobs
+
+description: |+
+  This alert is triggered when the CPU Utilization by Training Jobs is above 90%.
+
+type: STATIC
+nrql:
+  query: "SELECT average(`aws..aws.sagemaker.trainingjobs.CPUUtilization`) 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-workspaces/ConnectionFailure.yml

@@ -0,0 +1,27 @@
+name: High Connection Failure
+
+description: |+
+  This alert is triggered if the number of failed connections exceeds 100 for 10 minutes.
+
+type: STATIC
+nrql:
+  query: "SELECT count(`aws.workspaces.ConnectionFailure`) 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/apache-hadoop/UsedDiskPercentage.yml

@@ -3,7 +3,7 @@ name: Used Disk Percent
 
 # Description and details
 description: |+
-  This alert is triggered when used disk space exceeds 90% for at least 5 minutes.
+  This alert is triggered when disk usage exceeds 90% for at least 5 minutes.
 # Type of alert
 type: STATIC
 
@@ -19,7 +19,7 @@ valueFunction: SINGLE_VALUE
 terms:
   - priority: CRITICAL
     # Operator used to compare against the threshold.
-    operator: BELOW
+    operator: ABOVE
     # Value that triggers a violation
     threshold: 90
     # Time in seconds; 120 - 3600
@@ -28,7 +28,7 @@ terms:
     thresholdOccurrences: ALL
   - priority: WARNING
     # Operator used to compare against the threshold.
-    operator: BELOW
+    operator: ABOVE
     # Value that triggers a violation
     threshold: 85
     # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions