first claude draft

infra/aws/lambdas/aggregator/placeholder.txt

@@ -0,0 +1 @@
+placeholder

infra/aws/lambdas/compactor/placeholder.txt

@@ -0,0 +1 @@
+placeholder

infra/aws/terraform/ec2.tf

@@ -0,0 +1,148 @@
+# EC2 Instance for Docker Compose deployment
+
+resource "aws_security_group" "sysmonstm" {
+  name_prefix = "${var.project_name}-"
+  description = "Security group for System Monitor Platform"
+
+  # HTTP/HTTPS
+  ingress {
+    from_port   = 80
+    to_port     = 80
+    protocol    = "tcp"
+    cidr_blocks = ["0.0.0.0/0"]
+    description = "HTTP"
+  }
+
+  ingress {
+    from_port   = 443
+    to_port     = 443
+    protocol    = "tcp"
+    cidr_blocks = ["0.0.0.0/0"]
+    description = "HTTPS"
+  }
+
+  # gRPC for collectors
+  ingress {
+    from_port   = 50051
+    to_port     = 50051
+    protocol    = "tcp"
+    cidr_blocks = ["0.0.0.0/0"]
+    description = "gRPC Aggregator"
+  }
+
+  # SSH (restricted)
+  dynamic "ingress" {
+    for_each = length(var.allowed_ssh_cidrs) > 0 ? [1] : []
+    content {
+      from_port   = 22
+      to_port     = 22
+      protocol    = "tcp"
+      cidr_blocks = var.allowed_ssh_cidrs
+      description = "SSH"
+    }
+  }
+
+  egress {
+    from_port   = 0
+    to_port     = 0
+    protocol    = "-1"
+    cidr_blocks = ["0.0.0.0/0"]
+    description = "Allow all outbound"
+  }
+
+  tags = {
+    Name = "${var.project_name}-sg"
+  }
+}
+
+resource "aws_iam_role" "ec2" {
+  name_prefix = "${var.project_name}-ec2-"
+
+  assume_role_policy = jsonencode({
+    Version = "2012-10-17"
+    Statement = [
+      {
+        Action = "sts:AssumeRole"
+        Effect = "Allow"
+        Principal = {
+          Service = "ec2.amazonaws.com"
+        }
+      }
+    ]
+  })
+}
+
+resource "aws_iam_role_policy_attachment" "ec2_ssm" {
+  role       = aws_iam_role.ec2.name
+  policy_arn = "arn:aws:iam::aws:policy/AmazonSSMManagedInstanceCore"
+}
+
+resource "aws_iam_instance_profile" "ec2" {
+  name_prefix = "${var.project_name}-"
+  role        = aws_iam_role.ec2.name
+}
+
+resource "aws_instance" "sysmonstm" {
+  ami                    = data.aws_ami.amazon_linux_2023.id
+  instance_type          = var.ec2_instance_type
+  key_name               = var.ec2_key_name != "" ? var.ec2_key_name : null
+  vpc_security_group_ids = [aws_security_group.sysmonstm.id]
+  iam_instance_profile   = aws_iam_instance_profile.ec2.name
+
+  root_block_device {
+    volume_size = 20
+    volume_type = "gp3"
+    encrypted   = true
+  }
+
+  user_data = <<-EOF
+    #!/bin/bash
+    set -e
+
+    # Install Docker
+    dnf update -y
+    dnf install -y docker git
+    systemctl enable docker
+    systemctl start docker
+
+    # Install Docker Compose
+    curl -L "https://github.com/docker/compose/releases/latest/download/docker-compose-$(uname -s)-$(uname -m)" \
+      -o /usr/local/bin/docker-compose
+    chmod +x /usr/local/bin/docker-compose
+
+    # Add ec2-user to docker group
+    usermod -aG docker ec2-user
+
+    # Clone and start the application
+    cd /home/ec2-user
+    git clone https://github.com/yourusername/sysmonstm.git || true
+    cd sysmonstm
+
+    # Create .env file
+    cat > .env <<EOL
+    LOG_LEVEL=INFO
+    MACHINE_ID=aws-demo
+    EOL
+
+    # Start services
+    docker-compose up -d
+  EOF
+
+  tags = {
+    Name = "${var.project_name}-server"
+  }
+
+  lifecycle {
+    ignore_changes = [ami]
+  }
+}
+
+# Elastic IP for stable address
+resource "aws_eip" "sysmonstm" {
+  instance = aws_instance.sysmonstm.id
+  domain   = "vpc"
+
+  tags = {
+    Name = "${var.project_name}-eip"
+  }
+}

infra/aws/terraform/lambda.tf

@@ -0,0 +1,203 @@
+# Lambda Functions for Data Processing Pipeline
+# These are optional and enabled via enable_lambda_pipeline variable
+
+# SQS Queue for buffering metrics
+resource "aws_sqs_queue" "metrics" {
+  count = var.enable_lambda_pipeline ? 1 : 0
+
+  name                       = "${var.project_name}-metrics"
+  visibility_timeout_seconds = var.lambda_timeout * 2
+  message_retention_seconds  = 86400  # 24 hours
+
+  redrive_policy = jsonencode({
+    deadLetterTargetArn = aws_sqs_queue.metrics_dlq[0].arn
+    maxReceiveCount     = 3
+  })
+}
+
+resource "aws_sqs_queue" "metrics_dlq" {
+  count = var.enable_lambda_pipeline ? 1 : 0
+
+  name                      = "${var.project_name}-metrics-dlq"
+  message_retention_seconds = 1209600  # 14 days
+}
+
+# S3 Bucket for metric backups
+resource "aws_s3_bucket" "metrics" {
+  count = var.enable_s3_backup ? 1 : 0
+
+  bucket_prefix = "${var.project_name}-metrics-"
+}
+
+resource "aws_s3_bucket_lifecycle_configuration" "metrics" {
+  count  = var.enable_s3_backup ? 1 : 0
+  bucket = aws_s3_bucket.metrics[0].id
+
+  rule {
+    id     = "archive-old-metrics"
+    status = "Enabled"
+
+    transition {
+      days          = 30
+      storage_class = "STANDARD_IA"
+    }
+
+    transition {
+      days          = 90
+      storage_class = "GLACIER"
+    }
+
+    expiration {
+      days = 365
+    }
+  }
+}
+
+# IAM Role for Lambda
+resource "aws_iam_role" "lambda" {
+  count       = var.enable_lambda_pipeline ? 1 : 0
+  name_prefix = "${var.project_name}-lambda-"
+
+  assume_role_policy = jsonencode({
+    Version = "2012-10-17"
+    Statement = [
+      {
+        Action = "sts:AssumeRole"
+        Effect = "Allow"
+        Principal = {
+          Service = "lambda.amazonaws.com"
+        }
+      }
+    ]
+  })
+}
+
+resource "aws_iam_role_policy" "lambda" {
+  count = var.enable_lambda_pipeline ? 1 : 0
+  name  = "lambda-policy"
+  role  = aws_iam_role.lambda[0].id
+
+  policy = jsonencode({
+    Version = "2012-10-17"
+    Statement = [
+      {
+        Effect = "Allow"
+        Action = [
+          "logs:CreateLogGroup",
+          "logs:CreateLogStream",
+          "logs:PutLogEvents"
+        ]
+        Resource = "arn:aws:logs:*:*:*"
+      },
+      {
+        Effect = "Allow"
+        Action = [
+          "sqs:ReceiveMessage",
+          "sqs:DeleteMessage",
+          "sqs:GetQueueAttributes"
+        ]
+        Resource = aws_sqs_queue.metrics[0].arn
+      },
+      {
+        Effect = "Allow"
+        Action = [
+          "s3:PutObject",
+          "s3:GetObject"
+        ]
+        Resource = var.enable_s3_backup ? "${aws_s3_bucket.metrics[0].arn}/*" : "*"
+      }
+    ]
+  })
+}
+
+# Lambda function for metric aggregation
+resource "aws_lambda_function" "aggregator" {
+  count = var.enable_lambda_pipeline ? 1 : 0
+
+  function_name = "${var.project_name}-aggregator"
+  role          = aws_iam_role.lambda[0].arn
+  handler       = "main.handler"
+  runtime       = "python3.11"
+  timeout       = var.lambda_timeout
+  memory_size   = var.lambda_memory_size
+
+  # Placeholder - will be deployed via CI/CD
+  filename         = "${path.module}/../lambdas/aggregator/placeholder.zip"
+  source_code_hash = filebase64sha256("${path.module}/../lambdas/aggregator/placeholder.zip")
+
+  environment {
+    variables = {
+      TIMESCALE_HOST = aws_instance.sysmonstm.private_ip
+      LOG_LEVEL      = "INFO"
+    }
+  }
+
+  lifecycle {
+    ignore_changes = [filename, source_code_hash]
+  }
+}
+
+resource "aws_lambda_event_source_mapping" "sqs_trigger" {
+  count = var.enable_lambda_pipeline ? 1 : 0
+
+  event_source_arn = aws_sqs_queue.metrics[0].arn
+  function_name    = aws_lambda_function.aggregator[0].arn
+  batch_size       = 100
+
+  scaling_config {
+    maximum_concurrency = 5
+  }
+}
+
+# CloudWatch Event for scheduled compaction
+resource "aws_cloudwatch_event_rule" "compactor" {
+  count = var.enable_lambda_pipeline ? 1 : 0
+
+  name                = "${var.project_name}-compactor-schedule"
+  description         = "Trigger metric compaction every hour"
+  schedule_expression = "rate(1 hour)"
+}
+
+resource "aws_lambda_function" "compactor" {
+  count = var.enable_lambda_pipeline ? 1 : 0
+
+  function_name = "${var.project_name}-compactor"
+  role          = aws_iam_role.lambda[0].arn
+  handler       = "main.handler"
+  runtime       = "python3.11"
+  timeout       = 300
+  memory_size   = 512
+
+  filename         = "${path.module}/../lambdas/compactor/placeholder.zip"
+  source_code_hash = filebase64sha256("${path.module}/../lambdas/compactor/placeholder.zip")
+
+  environment {
+    variables = {
+      TIMESCALE_HOST = aws_instance.sysmonstm.private_ip
+      S3_BUCKET      = var.enable_s3_backup ? aws_s3_bucket.metrics[0].bucket : ""
+      LOG_LEVEL      = "INFO"
+    }
+  }
+
+  lifecycle {
+    ignore_changes = [filename, source_code_hash]
+  }
+}
+
+resource "aws_cloudwatch_event_target" "compactor" {
+  count = var.enable_lambda_pipeline ? 1 : 0
+
+  rule      = aws_cloudwatch_event_rule.compactor[0].name
+  target_id = "compactor-lambda"
+  arn       = aws_lambda_function.compactor[0].arn
+}
+
+resource "aws_lambda_permission" "compactor_cloudwatch" {
+  count = var.enable_lambda_pipeline ? 1 : 0
+
+  statement_id  = "AllowCloudWatchInvoke"
+  action        = "lambda:InvokeFunction"
+  function_name = aws_lambda_function.compactor[0].function_name
+  principal     = "events.amazonaws.com"
+  source_arn    = aws_cloudwatch_event_rule.compactor[0].arn
+}

infra/aws/terraform/main.tf

@@ -0,0 +1,58 @@
+# System Monitor Platform - AWS Infrastructure
+#
+# This Terraform configuration sets up:
+# - EC2 instance for running Docker Compose (demo/staging)
+# - Lambda functions for data processing pipeline
+# - SQS queue for buffering metrics
+# - S3 bucket for metric backups
+# - Security groups and IAM roles
+
+terraform {
+  required_version = ">= 1.0"
+
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.0"
+    }
+  }
+
+  # Uncomment for remote state
+  # backend "s3" {
+  #   bucket = "your-terraform-state-bucket"
+  #   key    = "sysmonstm/terraform.tfstate"
+  #   region = "us-east-1"
+  # }
+}
+
+provider "aws" {
+  region = var.aws_region
+
+  default_tags {
+    tags = {
+      Project     = "sysmonstm"
+      Environment = var.environment
+      ManagedBy   = "terraform"
+    }
+  }
+}
+
+# Data sources
+data "aws_availability_zones" "available" {
+  state = "available"
+}
+
+data "aws_ami" "amazon_linux_2023" {
+  most_recent = true
+  owners      = ["amazon"]
+
+  filter {
+    name   = "name"
+    values = ["al2023-ami-*-x86_64"]
+  }
+
+  filter {
+    name   = "virtualization-type"
+    values = ["hvm"]
+  }
+}

infra/aws/terraform/outputs.tf

@@ -0,0 +1,36 @@
+# Outputs
+
+output "ec2_public_ip" {
+  description = "Public IP of the EC2 instance"
+  value       = aws_eip.sysmonstm.public_ip
+}
+
+output "ec2_instance_id" {
+  description = "EC2 instance ID"
+  value       = aws_instance.sysmonstm.id
+}
+
+output "dashboard_url" {
+  description = "URL for the monitoring dashboard"
+  value       = "http://${aws_eip.sysmonstm.public_ip}:8000"
+}
+
+output "grpc_endpoint" {
+  description = "gRPC endpoint for collectors"
+  value       = "${aws_eip.sysmonstm.public_ip}:50051"
+}
+
+output "sqs_queue_url" {
+  description = "SQS queue URL for metrics"
+  value       = var.enable_lambda_pipeline ? aws_sqs_queue.metrics[0].url : null
+}
+
+output "s3_bucket" {
+  description = "S3 bucket for metric backups"
+  value       = var.enable_s3_backup ? aws_s3_bucket.metrics[0].bucket : null
+}
+
+output "ssh_command" {
+  description = "SSH command to connect to the instance"
+  value       = var.ec2_key_name != "" ? "ssh -i ${var.ec2_key_name}.pem ec2-user@${aws_eip.sysmonstm.public_ip}" : "Use SSM Session Manager"
+}

infra/aws/terraform/terraform.tfvars.example

@@ -0,0 +1,16 @@
+# Example Terraform variables
+# Copy to terraform.tfvars and fill in your values
+
+aws_region    = "us-east-1"
+environment   = "staging"
+project_name  = "sysmonstm"
+domain_name   = "sysmonstm.mcrn.ar"
+
+# EC2
+ec2_instance_type = "t2.small"
+ec2_key_name      = "your-key-pair-name"
+allowed_ssh_cidrs = ["YOUR.IP.ADDRESS/32"]
+
+# Feature flags
+enable_lambda_pipeline = false
+enable_s3_backup       = false

infra/aws/terraform/variables.tf

@@ -0,0 +1,70 @@
+# Variables for System Monitor Platform
+
+variable "aws_region" {
+  description = "AWS region to deploy to"
+  type        = string
+  default     = "us-east-1"
+}
+
+variable "environment" {
+  description = "Environment name (dev, staging, prod)"
+  type        = string
+  default     = "staging"
+}
+
+variable "project_name" {
+  description = "Project name for resource naming"
+  type        = string
+  default     = "sysmonstm"
+}
+
+variable "domain_name" {
+  description = "Domain name for the service"
+  type        = string
+  default     = "sysmonstm.mcrn.ar"
+}
+
+# EC2 Configuration
+variable "ec2_instance_type" {
+  description = "EC2 instance type"
+  type        = string
+  default     = "t2.small"
+}
+
+variable "ec2_key_name" {
+  description = "SSH key pair name"
+  type        = string
+  default     = ""
+}
+
+variable "allowed_ssh_cidrs" {
+  description = "CIDR blocks allowed to SSH"
+  type        = list(string)
+  default     = []  # Set to your IP for security
+}
+
+# Lambda Configuration
+variable "lambda_memory_size" {
+  description = "Lambda function memory in MB"
+  type        = number
+  default     = 256
+}
+
+variable "lambda_timeout" {
+  description = "Lambda function timeout in seconds"
+  type        = number
+  default     = 60
+}
+
+# Feature flags
+variable "enable_lambda_pipeline" {
+  description = "Enable Lambda data processing pipeline"
+  type        = bool
+  default     = false
+}
+
+variable "enable_s3_backup" {
+  description = "Enable S3 backup for metrics"
+  type        = bool
+  default     = false
+}