terraform.aws-baseline-infra/modules/ManagementGovernance/Monitoring.OpenSearch/main.tf

data "aws_caller_identity" "this" {}

resource "aws_cloudwatch_metric_alarm" "ES-CPUUtilization" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:CPUUtilization:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "3"
  metric_name               = "CPUUtilization"
  period                    = "1800"
  statistic                 = "Average"
  threshold                 = var.threshold-CPUUtilization
  alarm_description         = "ES:CPUUtilization"
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-SearchLatency" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:SearchLatency:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "3"
  metric_name               = "SearchLatency"
  period                    = "1800"
  statistic                 = "Average"
  threshold                 = var.threshold-SearchLatency
  alarm_description         = "ES:SearchLatency"
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-IndexingLatency" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:IndexingLatency:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "3"
  metric_name               = "IndexingLatency"
  period                    = "1800"
  statistic                 = "Average"
  threshold                 = var.threshold-IndexingLatency
  alarm_description         = "ES:IndexingLatency"
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-ClusterStatusRed" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:ClusterStatusRed:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "ClusterStatus.red"
  period                    = "900"
  statistic                 = "Maximum"
  threshold                 = 0
  alarm_description         = "At least one primary shard and its replicas aren't allocated to a node."
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-ThreadpoolWriteQueue" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:ThreadpoolWriteQueue:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "ThreadpoolWriteQueue"
  period                    = "60"
  statistic                 = "Average"
  threshold                 = var.threshold-ThreadpoolWriteQueue
  alarm_description         = "The cluster is experiencing high indexing concurrency. Review and control indexing requests, or increase cluster resources."
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-standard]
  ok_actions                = [var.sns-targets.alarm-actions-standard]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-ThreadpoolSearchQueue" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:ThreadpoolSearchQueue:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "ThreadpoolSearchQueue"
  period                    = "60"
  statistic                 = "Average"
  threshold                 = var.threshold-ThreadpoolSearchQueue
  alarm_description         = "The cluster is experiencing high search concurrency. Consider scaling your cluster. You can also increase the search queue size, but increasing it excessively can cause out of memory errors."
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-standard]
  ok_actions                = [var.sns-targets.alarm-actions-standard]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-ThreadpoolSearchRejected" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:ThreadpoolSearchRejected:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "ThreadpoolSearchRejected"
  period                    = "60"
  statistic                 = "Average"
  threshold                 = var.threshold-ThreadpoolSearchRejected
  alarm_description         = "These alarms notify you of domain issues that might impact performance and stability."
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-ThreadpoolWriteRejected" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:ThreadpoolWriteRejected:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "ThreadpoolWriteRejected"
  period                    = "60"
  statistic                 = "Average"
  threshold                 = var.threshold-ThreadpoolWriteRejected
  alarm_description         = "These alarms notify you of domain issues that might impact performance and stability."
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-MasterCPUUtilization" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:MasterCPUUtilization:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "MasterCPUUtilization"
  period                    = "300"
  statistic                 = "Average"
  threshold                 = var.threshold-MasterCPUUtilization
  alarm_description         = "MasterCPUUtilization"
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-MasterJVMMemoryPressure" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:MasterJVMMemoryPressure:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "MasterJVMMemoryPressure"
  period                    = "60"
  statistic                 = "Average"
  threshold                 = var.threshold-MasterJVMMemoryPressure
  alarm_description         = "MasterJVMMemoryPressure"
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-JVMMemoryPressure" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:JVMMemoryPressure:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "JVMMemoryPressure"
  period                    = "60"
  statistic                 = "Average"
  threshold                 = var.threshold-JVMMemoryPressure
  alarm_description         = "The cluster could encounter out of memory errors if usage increases. Consider scaling vertically. OpenSearch Service uses half of an instance's RAM for the Java heap, up to a heap size of 32 GiB. You can scale instances vertically up to 64 GiB of RAM, at which point you can scale horizontally by adding instances."
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-ClusterIndexWritesBlocked" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:ClusterIndexWritesBlocked:${var.domain-name}"
  comparison_operator       = "GreaterThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "ClusterIndexWritesBlocked"
  period                    = "60"
  statistic                 = "Average"
  threshold                 = var.threshold-ClusterIndexWritesBlocked
  alarm_description         = "Your cluster is blocking write requests. See ClusterBlockException."
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}

resource "aws_cloudwatch_metric_alarm" "ES-FreeStorageSpace" {
  alarm_name                = "${var.cw-alarm-prefix}:ES:FreeStorageSpace:${var.domain-name}"
  comparison_operator       = "LessThanThreshold"
  evaluation_periods        = "2"
  metric_name               = "FreeStorageSpace"
  period                    = "300"
  statistic                 = "Average"
  threshold                 = var.threshold-FreeStorageSpace
  alarm_description         = "A node in your cluster is low on free storage space."
  namespace                 = "AWS/ES"
  insufficient_data_actions = []
  actions_enabled           = var.actions-enabled
  alarm_actions             = [var.sns-targets.alarm-actions-urgent]
  ok_actions                = [var.sns-targets.alarm-actions-urgent]
  dimensions = {
    DomainName = var.domain-name
    ClientId   = data.aws_caller_identity.this.id
  }
  tags = var.default-tags
  lifecycle {
    ignore_changes = [tags]
  }
}