xpk/terraform.aws-baseline-infra
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

UPD: Added more monitoring modules and various enhancements

Browse Source
This commit is contained in:
KF 2022-10-26 11:13:56 +08:00
parent 2af0ff1b1a
commit b3ba6f2441
Signed by: xpk
GPG Key ID: CD4FF6793F09AB86
28 changed files with 443 additions and 167 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
modules/ManagementGovernance/Monitoring.ALB/main.tf
View File

@ -1,28 +1,28 @@
data external alb-targetgroups {
data "external" "alb-targetgroups" {
program = ["bash", "../../modules/ManagementGovernance/Monitoring.ALB/list-alb-targetgroups.sh"]
query = {
lb = var.load-balancer
}
}
resource aws_cloudwatch_metric_alarm alb-HealthyHostCount {
for_each = toset(split(" ", data.external.alb-targetgroups.result.result))
alarm_name = "ALBTG:HealthyHostCount:${split("/", each.value)[1]}/${split("/", each.value)[2]}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "1"
metric_name = "HealthyHostCount"
period = "300"
statistic = "Minimum"
threshold = var.threshold-HealthHostCountMin
alarm_description = "ALBTG:HealthyHostCount"
namespace = "AWS/ApplicationELB"
resource "aws_cloudwatch_metric_alarm" "alb-HealthyHostCount" {
for_each = toset(split(" ", data.external.alb-targetgroups.result.result))
alarm_name = "${var.cw-alarm-prefix}:ALBTG:HealthyHostCount:${split("/", each.value)[1]}/${split("/", each.value)[2]}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "1"
metric_name = "HealthyHostCount"
period = "300"
statistic = "Minimum"
threshold = var.threshold-HealthHostCountMin
alarm_description = "ALBTG:HealthyHostCount"
namespace = "AWS/ApplicationELB"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-emergency]
ok_actions = [var.alarm-actions-emergency]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-emergency]
ok_actions = [var.alarm-actions-emergency]
dimensions = {
TargetGroup = "targetgroup/${split("/", each.value)[1]}/${split("/", each.value)[2]}"
LoadBalancer = "app/${split("/",var.load-balancer)[2]}/${split("/",var.load-balancer)[3]}"
TargetGroup = "targetgroup/${split("/", each.value)[1]}/${split("/", each.value)[2]}"
LoadBalancer = "app/${split("/", var.load-balancer)[2]}/${split("/", var.load-balancer)[3]}"
}
tags = var.default-tags
lifecycle {

3
modules/ManagementGovernance/Monitoring.ALB/variables.tf
View File

@ -1,4 +1,5 @@
# variable target-group {}
variable cw-alarm-prefix {}
variable actions-enabled {}
variable load-balancer {}
variable threshold-HealthHostCountMin {}
variable alarm-actions-urgent {

5
modules/ManagementGovernance/Monitoring.ASG/README.md Normal file
View File

@ -0,0 +1,5 @@
# Monitoring module for BEA
This module deploys the default cloudwatch metric monitoring
## Notes
Terraform lifecycle ignores tags to speed up terraform subsequent update. Cloudwatch alarm tags cannot be read on aws console anyway.

22
modules/ManagementGovernance/Monitoring.ASG/main.tf Normal file
View File

@ -0,0 +1,22 @@
resource "aws_cloudwatch_metric_alarm" "asg-CPUUtilization" {
alarm_name = "${var.cw-alarm-prefix}:ASG:CPUUtilization:${var.asg-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "3"
metric_name = "CPUUtilization"
period = "1800"
statistic = "Average"
threshold = var.threshold-CPUUtilization
alarm_description = "ASG:CPUUtilization"
namespace = "AWS/EC2"
insufficient_data_actions = []
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
AutoScalingGroupName = var.asg-name
}
tags = var.default-tags
lifecycle {
ignore_changes = [tags]
}
}

9
modules/ManagementGovernance/Monitoring.ASG/provider.tf Normal file
View File

@ -0,0 +1,9 @@
terraform {
required_version = "~> 1.3.0"
required_providers {
aws = {
source = "hashicorp/aws"
version = "~> 4.36.1"
}
}
}

22
modules/ManagementGovernance/Monitoring.ASG/variables.tf Normal file
View File

@ -0,0 +1,22 @@
variable cw-alarm-prefix {}
variable actions-enabled {}
variable asg-name {}
variable alarm-actions-urgent {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-urgent"
}
variable alarm-actions-emergency {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-emergency"
}
variable alarm-actions-standard {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-standard"
}
variable alarm-actions-general {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support"
}
variable default-tags {}
variable threshold-CPUUtilization {}

12
modules/ManagementGovernance/Monitoring.EC2/main.tf
View File

@ -1,5 +1,5 @@
resource "aws_cloudwatch_metric_alarm" "ec2-StatusCheckFailed_System" {
alarm_name = "EC2:StatusCheckFailed_System:${var.ec2-instance-id}"
alarm_name = "${var.cw-alarm-prefix}:EC2:StatusCheckFailed_System:${var.ec2-instance-id}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "StatusCheckFailed_System"
@ -9,7 +9,7 @@ resource "aws_cloudwatch_metric_alarm" "ec2-StatusCheckFailed_System" {
alarm_description = "EC2:StatusCheckFailed_System"
namespace = "AWS/EC2"
insufficient_data_actions = []
actions_enabled = "true"
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-emergency]
ok_actions = [var.alarm-actions-emergency]
dimensions = {
@ -22,7 +22,7 @@ resource "aws_cloudwatch_metric_alarm" "ec2-StatusCheckFailed_System" {
}
resource "aws_cloudwatch_metric_alarm" "ec2-StatusCheckFailed_Instance" {
alarm_name = "EC2:StatusCheckFailed_Instance:${var.ec2-instance-id}"
alarm_name = "${var.cw-alarm-prefix}:EC2:StatusCheckFailed_Instance:${var.ec2-instance-id}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "StatusCheckFailed_Instance"
@ -32,7 +32,7 @@ resource "aws_cloudwatch_metric_alarm" "ec2-StatusCheckFailed_Instance" {
alarm_description = "EC2:StatusCheckFailed_Instance"
namespace = "AWS/EC2"
insufficient_data_actions = []
actions_enabled = "true"
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-emergency]
ok_actions = [var.alarm-actions-emergency]
dimensions = {
@ -45,7 +45,7 @@ resource "aws_cloudwatch_metric_alarm" "ec2-StatusCheckFailed_Instance" {
}
resource "aws_cloudwatch_metric_alarm" "ec2-CPUUtilization" {
alarm_name = "EC2:CPUUtilization:${var.ec2-instance-id}"
alarm_name = "${var.cw-alarm-prefix}:EC2:CPUUtilization:${var.ec2-instance-id}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "6"
metric_name = "CPUUtilization"
@ -55,7 +55,7 @@ resource "aws_cloudwatch_metric_alarm" "ec2-CPUUtilization" {
alarm_description = "EC2:CPUUtilization"
namespace = "AWS/EC2"
insufficient_data_actions = []
actions_enabled = "true"
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
treat_missing_data = "notBreaching"

2
modules/ManagementGovernance/Monitoring.EC2/variables.tf
View File

@ -1,3 +1,5 @@
variable cw-alarm-prefix {}
variable actions-enabled {}
variable ec2-instance-id {}
variable alarm-actions-urgent {
type = string

8
modules/ManagementGovernance/Monitoring.EMR/main.tf
View File

@ -1,5 +1,5 @@
resource "aws_cloudwatch_metric_alarm" "emr-AppsPending" {
alarm_name = "EMR:AppsPending:${var.job-flow-id}"
alarm_name = "${var.cw-alarm-prefix}:EMR:AppsPending:${var.job-flow-id}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "AppsPending"
@ -9,7 +9,7 @@ resource "aws_cloudwatch_metric_alarm" "emr-AppsPending" {
alarm_description = "EMR:AppsPending"
namespace = "AWS/ElasticMapReduce"
insufficient_data_actions = []
actions_enabled = "true"
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-standard]
ok_actions = [var.alarm-actions-standard]
dimensions = {
@ -22,7 +22,7 @@ resource "aws_cloudwatch_metric_alarm" "emr-AppsPending" {
}
resource "aws_cloudwatch_metric_alarm" "emr-CapacityRemainingGB" {
alarm_name = "EMR:CapacityRemainingGB:${var.job-flow-id}"
alarm_name = "${var.cw-alarm-prefix}:EMR:CapacityRemainingGB:${var.job-flow-id}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "1"
metric_name = "CapacityRemainingGB"
@ -32,7 +32,7 @@ resource "aws_cloudwatch_metric_alarm" "emr-CapacityRemainingGB" {
alarm_description = "EMR:CapacityRemainingGB"
namespace = "AWS/ElasticMapReduce"
insufficient_data_actions = []
actions_enabled = "true"
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {

2
modules/ManagementGovernance/Monitoring.EMR/variables.tf
View File

@ -1,3 +1,5 @@
variable cw-alarm-prefix {}
variable actions-enabled {}
variable job-flow-id {}
variable threshold-AppsPending {}
variable threshold-CapacityRemainingGB {}

5
modules/ManagementGovernance/Monitoring.Kafka/README.md Normal file
View File

@ -0,0 +1,5 @@
# Monitoring module for BEA
This module deploys the default cloudwatch metric monitoring
## Notes
Terraform lifecycle ignores tags to speed up terraform subsequent update. Cloudwatch alarm tags cannot be read on aws console anyway.

22
modules/ManagementGovernance/Monitoring.Kafka/main.tf Normal file
View File

@ -0,0 +1,22 @@
resource "aws_cloudwatch_metric_alarm" "Kafka-ZooKeeperRequestLatencyMsMean" {
alarm_name = "${var.cw-alarm-prefix}:Kafka:ZooKeeperRequestLatencyMsMean:${var.cluster-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "3"
metric_name = "ZooKeeperRequestLatencyMsMean"
period = "1800"
statistic = "Average"
threshold = var.threshold-ZooKeeperRequestLatencyMsMean
alarm_description = "Kafka:ZooKeeperRequestLatencyMsMean"
namespace = "AWS/Kafka"
insufficient_data_actions = []
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
"Cluster Name" = var.cluster-name
}
tags = var.default-tags
lifecycle {
ignore_changes = [tags]
}
}

9
modules/ManagementGovernance/Monitoring.Kafka/provider.tf Normal file
View File

@ -0,0 +1,9 @@
terraform {
required_version = "~> 1.3.0"
required_providers {
aws = {
source = "hashicorp/aws"
version = "~> 4.36.1"
}
}
}

22
modules/ManagementGovernance/Monitoring.Kafka/variables.tf Normal file
View File

@ -0,0 +1,22 @@
variable cw-alarm-prefix {}
variable actions-enabled {}
variable cluster-name {}
variable alarm-actions-urgent {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-urgent"
}
variable alarm-actions-emergency {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-emergency"
}
variable alarm-actions-standard {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-standard"
}
variable alarm-actions-general {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support"
}
variable default-tags {}
variable threshold-ZooKeeperRequestLatencyMsMean {}

4
modules/ManagementGovernance/Monitoring.NLB/main.tf
View File

@ -16,7 +16,7 @@ module "nlb-targetgroups" {
resource "aws_cloudwatch_metric_alarm" "nlb-HealthyHostCount" {
for_each = module.nlb-targetgroups.result-set
alarm_name = "NLBTG:HealthyHostCount:${split(":", each.value)[5]}"
alarm_name = "${var.cw-alarm-prefix}:NLBTG:HealthyHostCount:${split(":", each.value)[5]}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "1"
metric_name = "HealthyHostCount"
@ -26,7 +26,7 @@ resource "aws_cloudwatch_metric_alarm" "nlb-HealthyHostCount" {
alarm_description = "NLBTG:HealthyHostCount"
namespace = "AWS/NetworkELB"
insufficient_data_actions = []
actions_enabled = "true"
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-emergency]
ok_actions = [var.alarm-actions-emergency]
dimensions = {

3
modules/ManagementGovernance/Monitoring.NLB/variables.tf
View File

@ -1,4 +1,5 @@
# variable target-group {}
variable cw-alarm-prefix {}
variable actions-enabled {}
variable load-balancer {}
variable threshold-HealthHostCountMin {}
variable alarm-actions-urgent {

5
modules/ManagementGovernance/Monitoring.OpenSearch/README.md Normal file
View File

@ -0,0 +1,5 @@
# Monitoring module for BEA
This module deploys the default cloudwatch metric monitoring
## Notes
Terraform lifecycle ignores tags to speed up terraform subsequent update. Cloudwatch alarm tags cannot be read on aws console anyway.

98
modules/ManagementGovernance/Monitoring.OpenSearch/main.tf Normal file
View File

@ -0,0 +1,98 @@
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.alarm-actions-urgent]
ok_actions = [var.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.alarm-actions-urgent]
ok_actions = [var.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.alarm-actions-urgent]
ok_actions = [var.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.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
DomainName = var.domain-name
ClientId = data.aws_caller_identity.this.id
}
tags = var.default-tags
lifecycle {
ignore_changes = [tags]
}
}

9
modules/ManagementGovernance/Monitoring.OpenSearch/provider.tf Normal file
View File

@ -0,0 +1,9 @@
terraform {
required_version = "~> 1.3.0"
required_providers {
aws = {
source = "hashicorp/aws"
version = "~> 4.36.1"
}
}
}

25
modules/ManagementGovernance/Monitoring.OpenSearch/variables.tf Normal file
View File

@ -0,0 +1,25 @@
variable cw-alarm-prefix {}
variable actions-enabled {}
variable domain-name {}
variable alarm-actions-urgent {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-urgent"
}
variable alarm-actions-emergency {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-emergency"
}
variable alarm-actions-standard {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-standard"
}
variable alarm-actions-general {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support"
}
variable default-tags {}
variable threshold-CPUUtilization {}
variable threshold-SearchLatency {}
variable threshold-IndexingLatency {}
# variable threshold-KibanaHealthyNodes {}

156
modules/ManagementGovernance/Monitoring.RDS/main.tf
View File

@ -1,17 +1,17 @@
resource aws_cloudwatch_metric_alarm rds-cpu {
alarm_name = "RDS:CpuUtilization:${var.rds-instance-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "CPUUtilization"
period = "3600"
statistic = "Average"
threshold = var.threshold-CpuUtilization
alarm_description = "RDS:CpuUtilization"
namespace = "AWS/RDS"
resource "aws_cloudwatch_metric_alarm" "rds-cpu" {
alarm_name = "${var.cw-alarm-prefix}:RDS:CpuUtilization:${var.rds-instance-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "CPUUtilization"
period = "3600"
statistic = "Average"
threshold = var.threshold-CpuUtilization
alarm_description = "RDS:CpuUtilization"
namespace = "AWS/RDS"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
DBInstanceIdentifier = var.rds-instance-name
}
@ -21,20 +21,20 @@ resource aws_cloudwatch_metric_alarm rds-cpu {
}
}
resource aws_cloudwatch_metric_alarm rds-storage {
alarm_name = "RDS:FreeStorageSpace:${var.rds-instance-name}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "1"
metric_name = "FreeStorageSpace"
period = "3600"
statistic = "Average"
threshold = var.threshold-FreeStorageSpace
alarm_description = "RDS:FreeStorageSpace"
namespace = "AWS/RDS"
resource "aws_cloudwatch_metric_alarm" "rds-storage" {
alarm_name = "${var.cw-alarm-prefix}:RDS:FreeStorageSpace:${var.rds-instance-name}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "1"
metric_name = "FreeStorageSpace"
period = "3600"
statistic = "Average"
threshold = var.threshold-FreeStorageSpace
alarm_description = "RDS:FreeStorageSpace"
namespace = "AWS/RDS"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
DBInstanceIdentifier = var.rds-instance-name
}
@ -44,20 +44,20 @@ resource aws_cloudwatch_metric_alarm rds-storage {
}
}
resource aws_cloudwatch_metric_alarm rds-memory {
alarm_name = "RDS:FreeableMemory:${var.rds-instance-name}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "1"
metric_name = "FreeableMemory"
period = "3600"
statistic = "Average"
threshold = var.threshold-FreeableMemory
alarm_description = "RDS:FreeableMemory"
namespace = "AWS/RDS"
resource "aws_cloudwatch_metric_alarm" "rds-memory" {
alarm_name = "${var.cw-alarm-prefix}:RDS:FreeableMemory:${var.rds-instance-name}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "1"
metric_name = "FreeableMemory"
period = "3600"
statistic = "Average"
threshold = var.threshold-FreeableMemory
alarm_description = "RDS:FreeableMemory"
namespace = "AWS/RDS"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
DBInstanceIdentifier = var.rds-instance-name
}
@ -67,20 +67,20 @@ resource aws_cloudwatch_metric_alarm rds-memory {
}
}
resource aws_cloudwatch_metric_alarm rds-DiskQueueDepth {
alarm_name = "RDS:DiskQueueDepth:${var.rds-instance-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "DiskQueueDepth"
period = "300"
statistic = "Average"
threshold = var.threshold-DiskQueueDepth
alarm_description = "RDS:DiskQueueDepth"
namespace = "AWS/RDS"
resource "aws_cloudwatch_metric_alarm" "rds-DiskQueueDepth" {
alarm_name = "${var.cw-alarm-prefix}:RDS:DiskQueueDepth:${var.rds-instance-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "DiskQueueDepth"
period = "300"
statistic = "Average"
threshold = var.threshold-DiskQueueDepth
alarm_description = "RDS:DiskQueueDepth"
namespace = "AWS/RDS"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
DBInstanceIdentifier = var.rds-instance-name
}
@ -90,20 +90,20 @@ resource aws_cloudwatch_metric_alarm rds-DiskQueueDepth {
}
}
resource aws_cloudwatch_metric_alarm rds-ReadLatency {
alarm_name = "RDS:ReadLatency:${var.rds-instance-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "2"
metric_name = "ReadLatency"
period = "900"
statistic = "Average"
threshold = var.threshold-ReadLatency
alarm_description = "RDS:ReadLatency"
namespace = "AWS/RDS"
resource "aws_cloudwatch_metric_alarm" "rds-ReadLatency" {
alarm_name = "${var.cw-alarm-prefix}:RDS:ReadLatency:${var.rds-instance-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "2"
metric_name = "ReadLatency"
period = "900"
statistic = "Average"
threshold = var.threshold-ReadLatency
alarm_description = "RDS:ReadLatency"
namespace = "AWS/RDS"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
DBInstanceIdentifier = var.rds-instance-name
}
@ -113,20 +113,20 @@ resource aws_cloudwatch_metric_alarm rds-ReadLatency {
}
}
resource aws_cloudwatch_metric_alarm rds-WriteLatency {
alarm_name = "RDS:WriteLatency:${var.rds-instance-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "2"
metric_name = "WriteLatency"
period = "900"
statistic = "Average"
threshold = var.threshold-WriteLatency
alarm_description = "RDS:WriteLatency"
namespace = "AWS/RDS"
resource "aws_cloudwatch_metric_alarm" "rds-WriteLatency" {
alarm_name = "${var.cw-alarm-prefix}:RDS:WriteLatency:${var.rds-instance-name}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "2"
metric_name = "WriteLatency"
period = "900"
statistic = "Average"
threshold = var.threshold-WriteLatency
alarm_description = "RDS:WriteLatency"
namespace = "AWS/RDS"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
DBInstanceIdentifier = var.rds-instance-name
}

2
modules/ManagementGovernance/Monitoring.RDS/variables.tf
View File

@ -1,3 +1,5 @@
variable cw-alarm-prefix {}
variable actions-enabled {}
variable rds-instance-name {}
variable alarm-actions-urgent {
type = string

84
modules/ManagementGovernance/Monitoring.Redis/main.tf
View File

@ -1,17 +1,17 @@
resource aws_cloudwatch_metric_alarm redis-EngineCPUUtilization {
alarm_name = "Redis:EngineCPUUtilization:${var.redis-cluster-id}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "EngineCPUUtilization"
period = "3600"
statistic = "Average"
threshold = var.threshold-EngineCPUUtilization
alarm_description = "Redis:EngineCPUUtilization"
namespace = "AWS/ElastiCache"
resource "aws_cloudwatch_metric_alarm" "redis-EngineCPUUtilization" {
alarm_name = "${var.cw-alarm-prefix}:Redis:EngineCPUUtilization:${var.redis-cluster-id}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "EngineCPUUtilization"
period = "3600"
statistic = "Average"
threshold = var.threshold-EngineCPUUtilization
alarm_description = "Redis:EngineCPUUtilization"
namespace = "AWS/ElastiCache"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
CacheClusterId = var.redis-cluster-id
}
@ -21,20 +21,20 @@ resource aws_cloudwatch_metric_alarm redis-EngineCPUUtilization {
}
}
resource aws_cloudwatch_metric_alarm redis-DatabaseMemoryUsagePercentage {
alarm_name = "Redis:DatabaseMemoryUsagePercentage:${var.redis-cluster-id}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "DatabaseMemoryUsagePercentage"
period = "3600"
statistic = "Average"
threshold = var.threshold-DatabaseMemoryUsagePercentage
alarm_description = "Redis:DatabaseMemoryUsagePercentage"
namespace = "AWS/ElastiCache"
resource "aws_cloudwatch_metric_alarm" "redis-DatabaseMemoryUsagePercentage" {
alarm_name = "${var.cw-alarm-prefix}:Redis:DatabaseMemoryUsagePercentage:${var.redis-cluster-id}"
comparison_operator = "GreaterThanThreshold"
evaluation_periods = "1"
metric_name = "DatabaseMemoryUsagePercentage"
period = "3600"
statistic = "Average"
threshold = var.threshold-DatabaseMemoryUsagePercentage
alarm_description = "Redis:DatabaseMemoryUsagePercentage"
namespace = "AWS/ElastiCache"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-urgent]
ok_actions = [var.alarm-actions-urgent]
dimensions = {
CacheClusterId = var.redis-cluster-id
}
@ -44,26 +44,20 @@ resource aws_cloudwatch_metric_alarm redis-DatabaseMemoryUsagePercentage {
}
}
/*
data aws_elasticache_cluster redis-cluster {
cluster_id = var.redis-cluster-id
}
*/
resource aws_cloudwatch_metric_alarm redis-CacheHitRate {
# for_each = toset(data.aws_elasticache_cluster.redis-cluster.cache_nodes.*.id)
alarm_name = "Redis:CacheHitRate:${var.redis-cluster-id}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "4"
metric_name = "CacheHitRate"
period = "900"
statistic = "Average"
threshold = var.threshold-CacheHitRate
alarm_description = "Redis:CacheHitRate"
namespace = "AWS/ElastiCache"
resource "aws_cloudwatch_metric_alarm" "redis-CacheHitRate" {
alarm_name = "${var.cw-alarm-prefix}:Redis:CacheHitRate:${var.redis-cluster-id}"
comparison_operator = "LessThanThreshold"
evaluation_periods = "4"
metric_name = "CacheHitRate"
period = "900"
statistic = "Average"
threshold = var.threshold-CacheHitRate
alarm_description = "Redis:CacheHitRate"
namespace = "AWS/ElastiCache"
insufficient_data_actions = []
actions_enabled = "true"
alarm_actions = [var.alarm-actions-standard]
ok_actions = [var.alarm-actions-standard]
actions_enabled = var.actions-enabled
alarm_actions = [var.alarm-actions-standard]
ok_actions = [var.alarm-actions-standard]
dimensions = {
CacheClusterId = var.redis-cluster-id
# CacheNodeId = each.value

28
modules/ManagementGovernance/Monitoring.Redis/variables.tf
View File

@ -1,22 +1,24 @@
variable redis-cluster-id {}
variable alarm-actions-urgent {
type = string
variable cw-alarm-prefix {}
variable "actions-enabled" {}
variable "redis-cluster-id" {}
variable "alarm-actions-urgent" {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-urgent"
}
variable alarm-actions-emergency {
type = string
variable "alarm-actions-emergency" {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-emergency"
}
variable alarm-actions-standard {
type = string
variable "alarm-actions-standard" {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support-standard"
}
variable alarm-actions-general {
type = string
variable "alarm-actions-general" {
type = string
default = "arn:aws:sns:ap-east-1:843733946244:rackspace-support"
}
variable default-tags {}
variable "default-tags" {}
variable threshold-EngineCPUUtilization {}
variable threshold-DatabaseMemoryUsagePercentage {}
variable threshold-CacheHitRate {}
variable "threshold-EngineCPUUtilization" {}
variable "threshold-DatabaseMemoryUsagePercentage" {}
variable "threshold-CacheHitRate" {}

1
modules/util/resource-list/list-alb.sh
View File

@ -1,3 +1,4 @@
#!/bin/bash
RESULTS=$(aws elbv2 describe-load-balancers --query 'LoadBalancers[?Type==`application`].LoadBalancerArn' --output text --no-cli-pager | sed 's/\t/\n/g' | sort | xargs)
jq -n --arg result "$RESULTS" '{"result":$result}'

6
modules/util/resource-list/list-asg.sh Executable file
View File

@ -0,0 +1,6 @@
#!/bin/bash
# exclude ASG instances
RESULTS=$(aws autoscaling describe-auto-scaling-groups --query 'AutoScalingGroups[*].AutoScalingGroupName' --output text --no-cli-pager | sed 's/\t/\n/g' | sort | xargs)
jq -n --arg result "$RESULTS" '{"result":$result}'

6
modules/util/resource-list/list-kafka.sh Executable file
View File

@ -0,0 +1,6 @@
#!/bin/bash
# exclude ASG instances
RESULTS=$(aws kafka list-clusters --query ClusterInfoList[*].ClusterName --output text --no-cli-pager | sed 's/\t/\n/g' | sort | xargs)
jq -n --arg result "$RESULTS" '{"result":$result}'

6
modules/util/resource-list/list-opensearch.sh Executable file
View File

@ -0,0 +1,6 @@
#!/bin/bash
# exclude ASG instances
RESULTS=$(aws opensearch list-domain-names --query DomainNames[*].DomainName --output text --no-cli-pager | sed 's/\t/\n/g' | sort | xargs)
jq -n --arg result "$RESULTS" '{"result":$result}'