export function buildElasticSearchCWAlarms()

in source/patterns/@aws-solutions-constructs/core/lib/elasticsearch-helper.ts [90:221]
112 lines of code
1 McCabe index (conditional complexity)

export function buildElasticSearchCWAlarms(scope: Construct): cloudwatch.Alarm[] {
  // Setup CW Alarms for ES
  const alarms: cloudwatch.Alarm[] = new Array();

  // ClusterStatus.red maximum is >= 1 for 1 minute, 1 consecutive time
  alarms.push(new cloudwatch.Alarm(scope, 'StatusRedAlarm', {
    metric: new cloudwatch.Metric({
      namespace: 'AWS/ES',
      metricName: 'ClusterStatus.red',
      statistic: 'Maximum',
      period: cdk.Duration.seconds(60),
    }),
    threshold: 1,
    evaluationPeriods: 1,
    comparisonOperator: cloudwatch.ComparisonOperator.GREATER_THAN_OR_EQUAL_TO_THRESHOLD,
    alarmDescription: 'At least one primary shard and its replicas are not allocated to a node. '
  }));

  // ClusterStatus.yellow maximum is >= 1 for 1 minute, 1 consecutive time
  alarms.push(new cloudwatch.Alarm(scope, 'StatusYellowAlarm', {
    metric: new cloudwatch.Metric({
      namespace: 'AWS/ES',
      metricName: 'ClusterStatus.yellow',
      statistic: 'Maximum',
      period: cdk.Duration.seconds(60),
    }),
    threshold: 1,
    evaluationPeriods: 1,
    comparisonOperator: cloudwatch.ComparisonOperator.GREATER_THAN_OR_EQUAL_TO_THRESHOLD,
    alarmDescription: 'At least one replica shard is not allocated to a node.'
  }));

  // FreeStorageSpace minimum is <= 20480 for 1 minute, 1 consecutive time
  alarms.push(new cloudwatch.Alarm(scope, 'FreeStorageSpaceTooLowAlarm', {
    metric: new cloudwatch.Metric({
      namespace: 'AWS/ES',
      metricName: 'FreeStorageSpace',
      statistic: 'Minimum',
      period: cdk.Duration.seconds(60),
    }),
    threshold: 20000,
    evaluationPeriods: 1,
    comparisonOperator: cloudwatch.ComparisonOperator.LESS_THAN_OR_EQUAL_TO_THRESHOLD,
    alarmDescription: 'A node in your cluster is down to 20 GiB of free storage space.'
  }));

  // ClusterIndexWritesBlocked is >= 1 for 5 minutes, 1 consecutive time
  alarms.push(new cloudwatch.Alarm(scope, 'IndexWritesBlockedTooHighAlarm', {
    metric: new cloudwatch.Metric({
      namespace: 'AWS/ES',
      metricName: 'ClusterIndexWritesBlocked',
      statistic: 'Maximum',
      period: cdk.Duration.seconds(300),
    }),
    threshold: 1,
    evaluationPeriods: 1,
    comparisonOperator: cloudwatch.ComparisonOperator.GREATER_THAN_OR_EQUAL_TO_THRESHOLD,
    alarmDescription: 'Your cluster is blocking write requests.'
  }));

  // AutomatedSnapshotFailure maximum is >= 1 for 1 minute, 1 consecutive time
  alarms.push(new cloudwatch.Alarm(scope, 'AutomatedSnapshotFailureTooHighAlarm', {
    metric: new cloudwatch.Metric({
      namespace: 'AWS/ES',
      metricName: 'AutomatedSnapshotFailure',
      statistic: 'Maximum',
      period: cdk.Duration.seconds(60),
    }),
    threshold: 1,
    evaluationPeriods: 1,
    comparisonOperator: cloudwatch.ComparisonOperator.GREATER_THAN_OR_EQUAL_TO_THRESHOLD,
    alarmDescription: 'An automated snapshot failed. This failure is often the result of a red cluster health status.'
  }));

  // CPUUtilization maximum is >= 80% for 15 minutes, 3 consecutive times
  alarms.push(new cloudwatch.Alarm(scope, 'CPUUtilizationTooHighAlarm', {
    metric: new cloudwatch.Metric({
      namespace: 'AWS/ES',
      metricName: 'CPUUtilization',
      statistic: 'Average',
      period: cdk.Duration.seconds(900),
    }),
    threshold: 80,
    evaluationPeriods: 3,
    comparisonOperator: cloudwatch.ComparisonOperator.GREATER_THAN_OR_EQUAL_TO_THRESHOLD,
    alarmDescription: '100% CPU utilization is not uncommon, but sustained high usage is problematic. Consider using larger instance types or adding instances.'
  }));

  // JVMMemoryPressure maximum is >= 80% for 5 minutes, 3 consecutive times
  alarms.push(new cloudwatch.Alarm(scope, 'JVMMemoryPressureTooHighAlarm', {
    metric: new cloudwatch.Metric({
      namespace: 'AWS/ES',
      metricName: 'JVMMemoryPressure',
      statistic: 'Average',
      period: cdk.Duration.seconds(900),
    }),
    threshold: 80,
    evaluationPeriods: 1,
    comparisonOperator: cloudwatch.ComparisonOperator.GREATER_THAN_OR_EQUAL_TO_THRESHOLD,
    alarmDescription: 'Average JVM memory pressure over last 15 minutes too high. Consider scaling vertically.'
  }));

  // MasterCPUUtilization maximum is >= 50% for 15 minutes, 3 consecutive times
  alarms.push(new cloudwatch.Alarm(scope, 'MasterCPUUtilizationTooHighAlarm', {
    metric: new cloudwatch.Metric({
      namespace: 'AWS/ES',
      metricName: 'MasterCPUUtilization',
      statistic: 'Average',
      period: cdk.Duration.seconds(900),
    }),
    threshold: 50,
    evaluationPeriods: 3,
    comparisonOperator: cloudwatch.ComparisonOperator.GREATER_THAN_OR_EQUAL_TO_THRESHOLD,
    alarmDescription: 'Average CPU utilization over last 45 minutes too high. Consider using larger instance types for your dedicated master nodes.'
  }));

  // MasterJVMMemoryPressure maximum is >= 80% for 15 minutes, 1 consecutive time
  alarms.push(new cloudwatch.Alarm(scope, 'MasterJVMMemoryPressureTooHighAlarm', {
    metric: new cloudwatch.Metric({
      namespace: 'AWS/ES',
      metricName: 'MasterJVMMemoryPressure',
      statistic: 'Average',
      period: cdk.Duration.seconds(900),
    }),
    threshold: 50,
    evaluationPeriods: 1,
    comparisonOperator: cloudwatch.ComparisonOperator.GREATER_THAN_OR_EQUAL_TO_THRESHOLD,
    alarmDescription: 'Average JVM memory pressure over last 15 minutes too high. Consider scaling vertically.'
  }));

  return alarms;
}