infrastructure/
├── terragrunt.hcl
├── modules/
│   ├── networking/
│   ├── database/
│   ├── kubernetes/
│   ├── monitoring/
│   ├── security/
│   ├── storage/
│   ├── compute/
│   ├── iam/
│   ├── logging/
│   └── dns/
└── environments/
    ├── dev/
    │   ├── terragrunt.hcl
    │   ├── networking/
    │   │   └── terragrunt.hcl
    │   ├── database/
    │   │   └── terragrunt.hcl
    │   ├── kubernetes/
    │   │   └── terragrunt.hcl
    │   └── ...
    ├── staging/
    │   ├── terragrunt.hcl
    │   ├── networking/
    │   │   └── terragrunt.hcl
    │   ├── database/
    │   │   └── terragrunt.hcl
    │   └── ...
    └── prod/
        ├── terragrunt.hcl 
        ├── networking/
        │   └── terragrunt.hcl
        ├── database/
        │   └── terragrunt.hcl
        └── ...

export TF_PLUGIN_CACHE_DIR="$HOME/.terraform.d/plugin-cache"
mkdir -p $HOME/.terraform.d/plugin-cache

>cat ~/.bashrc |grep -i terra
export TF_PLUGIN_CACHE_DIR="$HOME/.terraform.d/plugin-cache"

environments/dev/networking/
├── terragrunt.hcl
└── .terragrunt-cache/
    └── AbCdEfGh12345/
        └── XyZaBcDe67890/          # хеш-директория
            ├── main.tf             # копия нашего модуля терраформа
            ├── variables.tf
            ├── outputs.tf
            ├── .terraform/
            │   └── providers/
            │       └── registry.terraform.io/
            │           └── hashicorp/
            │               └── aws/
            │                   └── 4.67.0/
            │                       └── linux_amd64 -> ~/.terraform.d/plugin-cache/registry.terraform.io/hashicorp/aws/4.67.0/linux_amd64    # симлинк на провайдер в директории с кешем
            └── ...

>cat .gitignore |grep -i terra
.terragrunt-cache/

kubectl run telegram-test --image=curlimages/curl --restart=Never --rm -i --tty -- \
  curl --max-time 10 --connect-timeout 10 https://api.telegram.org

curl -s "https://api.telegram.org/bot<ваш_токен>/getMe"

curl -X POST https://*********/api/v1/alerts \
-H "Content-Type: application/json" \
-d '[
  {
    "labels": {
...
    },
    "annotations": {
...
    },
    "startsAt": "'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'",
    "endsAt": "'"$(date -u -d "+3 minutes" +"%Y-%m-%dT%H:%M:%SZ")"'"
  }
]'

kubectl get VMAlertmanagerConfig -A |wc -l

>k port-forward svc/vmagent-tratata-prod-aks-us-1 8429

curl -X POST http://localhost:8429/api/v1/import/prometheus \
-d 'kube_pod_status_phase{phase="Pending",exported_namespace="test-namespace",pod="logical-backup-pgsql-test-pod",cluster="test-prod-cluster"} 1'

curl -X POST http://localhost:8429/api/v1/import/prometheus \
-d 'kube_pod_status_phase{phase="Pending",exported_namespace="test-namespace",pod="logical-backup-pgsql-test-pod",cluster="test-prod-cluster"} 0'

curl -X POST https://alertmanager.domain.com/api/v1/alerts \
-H "Content-Type: application/json" \
-d '[
 {
   "labels": {
     "alertname": "KubernetesPodNotHealthy",
     "cluster": "test-prod-cluster",
     "exported_namespace": "test-namespace",
     "pod": "logical-backup-pgsql-test-pod",
     "phase": "Pending",
     "emoji": "🔥",
     "incident_type": "outage"
   },
   "annotations": {
     "summary": "POD'"'"'s state is `Pending` for `test-prod-cluster`/`test-namespace`/`logical-backup-pgsql-test-pod`",
     "description": "Pod test-namespace/logical-backup-pgsql-test-pod has been in a non-running state for longer than 15 minutes.\n  VALUE = 1\n  LABELS = map[cluster:test-prod-cluster exported_namespace:test-namespace phase:Pending pod:logical-backup-pgsql-test-pod]"
   },
   "startsAt": "'$(date -u +"%Y-%m-%dT%H:%M:%SZ")'",
   "endsAt": "'$(date -u -d "+3 minutes" +"%Y-%m-%dT%H:%M:%SZ")'"
 }
]'

The node had condition: [DiskPressure].
The node was low on resource: ephemeral-storage. Threshold quantity: 4281126156, available: 3438556Ki

resource "aws_launch_template" "node-launch-template" {
...
  block_device_mappings {
    device_name = "/dev/xvda"
    ebs {
      volume_size = 200
      volume_type = "gp3"
    }
  }
...

  lifecycle {
    ignore_changes 

kubectl get nodes -o yaml | grep -i -A6 ephemeral-storage

resource "aws_launch_template" "node-launch-template" {
...
# !!! вот тут много не надо, это для самой ноды, операционка, можно хоть 10
  block_device_mappings {
    device_name = "/dev/xvda"
    ebs {
      volume_size = 20
      volume_type = "gp3"
    }
  }
# !!! вот это добавляем, для POD-ов
  block_device_mappings {
    device_name = "/dev/xvdb"
    ebs {
      volume_size = 200
      volume_type = "gp3"
    }
  }

kubectl get nodes -o yaml | grep -i -A6 ephemeral-storage

---
apiVersion: keda.sh/v1alpha1
kind: ScaledObject
...
spec:
  cooldownPeriod: 300
  maxReplicaCount: 50
  minReplicaCount: 2
  pollingInterval: 30
  scaleTargetRef:
    name: application
  triggers:
  - authenticationRef:
      name: keda-aws-credentials
    metadata:
      awsRegion: us-east-1
      identityOwner: operator
      queueLength: "500"
      queueURL: https://sqs.us-east-1.amazonaws.com/123456789/sqsname
    type: aws-sqs-queue

---
apiVersion: keda.sh/v1alpha1
kind: ScaledObject
...
spec:
...
    metricType: Value

---
apiVersion: keda.sh/v1alpha1
kind: ScaledObject
...
spec:
  advanced:
    horizontalPodAutoscalerConfig:
      behavior:
        scaleDown:
          policies:
          - periodSeconds: 15
            type: Pods
            value: 1
          stabilizationWindowSeconds: 300
        scaleUp:
          policies:
          - periodSeconds: 15
            type: Pods
            value: 1
          selectPolicy: Max
          stabilizationWindowSeconds: 60
... (остальное так же)

---
apiVersion: keda.sh/v1alpha1
kind: ScaledObject
...
spec:
  advanced:
...(тут тоже самое)
    metadata:
...
      scaleOnInFlight: "false"   << - - вот это вот важное нам
...