Merge pull request #1857 from pkudikyala/NR-89144-Apache-Hadoop

NR-89144 Apache Hadoop quickstart

alert-policies/apache-hadoop/NameNodeDeadDataNodes.yml

@@ -0,0 +1,32 @@
+# Name of the alert
+name: Dead DataNodes
+
+# Description and details
+description: |+
+  This alert is triggered if the dead DataNodes exceeds 1 for 5 minutes.
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+
+  query: "SELECT latest(NumDeadDataNodes) AS 'Dead Data Nodes' FROM HadoopNameNodeSample"
+
+# 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

alert-policies/apache-hadoop/NameNodeMissingBlocks.yml

@@ -0,0 +1,41 @@
+# Name of the alert
+name: Missing Blocks in HDFS
+
+# Description and details
+description: |+
+  This alert is triggered if the missing blocks exceeds 3 for 5 minutes.
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+
+  query: "SELECT latest(NumberOfMissingBlocks) AS 'Missing Blocks' FROM HadoopNameNodeSample"
+
+# 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: 3
+    # 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: 1
+    # 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
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/apache-hadoop/NameNodeVolumeFailures.yml

@@ -0,0 +1,41 @@
+# Name of the alert
+name: NameNode Volume Failures
+
+# Description and details
+description: |+
+  This alert is triggered if the volume failures exceeds 2 for 5 minutes.
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+
+  query: "SELECT latest(VolumeFailuresTotal) AS 'Volume Failures' FROM HadoopNameNodeSample"
+
+# 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: 2
+    # 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: 1
+    # 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
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/apache-hadoop/UsedDiskPercentage.yml

@@ -0,0 +1,41 @@
+# Name of the alert
+name: Used Disk Percent
+
+# Description and details
+description: |+
+  This alert is triggered when used disk space exceeds 90% for at least 5 minutes.
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+
+  query: "SELECT latest(PercentUsed) FROM HadoopNameNodeSampleMetrics"
+
+# 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
+    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: BELOW
+    # Value that triggers a violation
+    threshold: 85
+    # 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
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400