Merge pull request #2139 from harrykimpel/main

Adding MariaDB dashboard and alert conditions

.gitignore

@@ -15,4 +15,6 @@ snapshots/
 
 # yarn
 yarn.lock
-.yarn-integrity
+.yarn-integrity
+yarn-error.log
+utils/yarn-error.log

alert-policies/mariadb/innodb-pending-reads-and-writes.yml

@@ -0,0 +1,27 @@
+name: InnoDB Pending Reads and Writes
+
+description: |+
+  This alert is triggered when the aggregate number of pending reads and writes in the MySQL buffer pool is greater than 2 for 5 minutes, which indicates the database engine is backlogged and waiting on resources.
+
+type: STATIC
+nrql:
+  query: "FROM MysqlSample SELECT max(db.innodb.dataPendingReads) + max(db.innodb.dataPendingWrites) FACET displayName"
+
+# 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
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/mariadb/max-connection-errors-per-second.yml

@@ -0,0 +1,29 @@
+name: Max Connection Errors per Second
+
+description: |+
+  This alert is triggered when there is at least one error against the max_connections limit in a 5 minute window, which indicates you have requests to your MariaDB instance that are failing to connect.
+  This setting's default is 151, but can vary based on the underlying resources available to your instance. You can review your current max_connections limit with this query:
+  SHOW VARIABLES LIKE 'max_connections';
+
+type: STATIC
+nrql:
+  query: "FROM MysqlSample SELECT max(net.connectionErrorsMaxConnectionsPerSecond) FACET displayName"
+
+# 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: AT_LEAST_ONCE
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/mariadb/questions-per-second.yml

@@ -0,0 +1,59 @@
+name: Questions per Second
+
+description: |+
+  This alert is triggered when the current rate of Questions is greater than 2 standard deviations above the baseline for 60s, which could be an early indicator of a saturation problem for your instance.
+  It is important to note that this alert is disabled by default and you need to edit the configuration in New Relic One to add a targeted MySQL instance:
+  "WHERE displayName = 'MySql Instance Name'"
+  This allows the baseline to be calculated against a single instance instead of all running MySQL instances being monitored.
+
+type: BASELINE
+nrql:
+  # Cannot use FACET in Baseline alerts
+  query: "FROM MysqlSample SELECT average(query.questionsPerSecond)"
+
+# Direction in which baseline is set (Default: LOWER_ONLY)
+baselineDirection: UPPER_ONLY
+
+# 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, must be a multiple of 60 for Baseline conditions
+    thresholdDuration: 120
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+  # Adding a Warning threshold is optional
+  - priority: WARNING
+    operator: ABOVE
+    threshold: 1
+    thresholdDuration: 300
+    thresholdOccurrences: ALL
+
+# Loss of Signal Settings
+expiration:
+  # Close open violations if signal is lost (Default: false)
+  closeViolationsOnExpiration: false
+  # 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:
+
+# Advanced Signal Settings
+signal:
+  # Max Value for Baseline conditions = 20
+  evaluationOffset: 3
+  # Type of value that should be used to fill gaps
+  fillOption: NONE
+  # Integer; Used in conjunction with STATIC fillOption, otherwise null
+  fillValue:
+
+# 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/mariadb/slow-queries-per-second.yml

@@ -0,0 +1,29 @@
+name: Slow Queries per Second
+
+description: |+
+  This alert is triggered when the number of slow queries per second is greater than 5 for 5 minutes, which could indicate capacity issues or a query that has been changed and is experiencing performance issues.
+  The Slow_queries counter increments based on your settings applied to MySQL's long_query_time parameter (default 10s), which you can review with this query:
+  SHOW VARIABLES LIKE 'long_query_time';
+
+type: STATIC
+nrql:
+  query: "FROM MysqlSample SELECT average(query.slowQueriesPerSecond) FACET displayName"
+
+# 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: 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/redis/blocked-clients.yml

@@ -0,0 +1,27 @@
+name: Blocked clients alert
+
+description: |+
+  This alert is triggered when at least one blocked client occurs.
+
+type: STATIC
+nrql:
+  query: "SELECT sum(`net.blockedClients`) FROM RedisSample facet entityName"
+
+# 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: 0
+    # 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/redis/current-connections-anomaly.yml

@@ -0,0 +1,62 @@
+name: Anomalies in current connections
+
+# Description and details
+description: |
+  This alert is triggered when the number of current connections deviates from the norm either up or down.
+
+# Type of alert: BASELINE | STATIC
+type: BASELINE
+
+# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
+valueFunction: SINGLE_VALUE
+
+# NRQL query
+nrql:
+  query: "SELECT max(`net.connectedClients`) FROM RedisSample facet entityName"
+
+# Direction in which baseline is set (Default: LOWER_ONLY)
+baselineDirection: UPPER_AND_LOWER
+
+# 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: 30
+    # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions
+    thresholdDuration: 3600
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: AT_LEAST_ONCE
+
+  # Adding a Warning threshold is optional
+  - priority: WARNING
+    operator: ABOVE
+    threshold: 5
+    thresholdDuration: 300
+    thresholdOccurrences: AT_LEAST_ONCE
+
+# Loss of Signal Settings
+expiration:
+  # Close open violations if signal is lost (Default: false)
+  closeViolationsOnExpiration: false
+  # 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:
+
+# Advanced Signal Settings
+signal:
+  # Max Value for Baseline conditions = 20
+  evaluationOffset: 3
+  # Type of value that should be used to fill gaps
+  fillOption: NONE
+  # Integer; Used in conjunction with STATIC fillOption, otherwise null
+  fillValue:
+
+# 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