amazon-web-services - aws 地形错误 CannotPullContainerError : Error response from daemon - but the image url is valid

Question

我使用 Terraform 通过 Fargate 部署容器。

我遇到了这个错误:

CannotPullContainerError: Error response from daemon: Get https://xxxxxxxxx.dkr.ecr.us-east-2.amazonaws.com/v2/: net/http: request canceled while waiting for connection (Client.Timeout exceeded while awaiting headers)

terraform 部署成功通过。

这个镜像只是 nginx (dockerfile):

FROM nginx:latest

WORKDIR /

COPY ./nginx.conf  /etc/nginx/nginx.conf

nginx.conf:

user  nginx;                                                                    

worker_processes 4;

events { worker_connections 1024; }

error_log  /var/log/nginx/error.log warn;                                       
pid        /var/run/nginx.pid;                                                  

http {                                                                          
    include       /etc/nginx/mime.types;                                        
    default_type  application/octet-stream;                                     
                                                                                
    log_format  main  '$remote_addr - $remote_user [$time_local] "$request" '   
                      '$status $body_bytes_sent "$http_referer" '               
                      '"$http_user_agent" "$http_x_forwarded_for"';             
                                                                                
    access_log  /var/log/nginx/access.log  main;                                
                                                                                
    sendfile        on;                                                         
    #tcp_nopush     on;                                                         
                                                                                
    keepalive_timeout  65;                                                      
  
    server {                                                                                                  
        listen       80;                                                                                      

        if ($host ~ ^(?!www\.)(?<domain>.+)$) {
            return  301 $scheme://www.$domain$request_uri;
        }

        location / {
            add_header Content-Type text/plain;
            
            return 200 "<H1>Nginx works!</H1>";
        }
    }                                                                                                         
}

我不明白为什么 aws 说它无法得到回应。网址没问题。我可以下载此镜像并在我的计算机上运行容器。

那为什么呢？问题出在哪里？

我的地形:

data "aws_iam_role" "ecs_task_execution_role" {
  name = "ecsTaskExecutionRole"
}

resource "aws_ecs_cluster" "cluster" {
  name = "${var.app}-ecs-cluster"
}

data "aws_iam_policy_document" "ecs_service_role" {
  statement {
    effect  = "Allow"
    actions = ["sts:AssumeRole"]
    principals {
      type        = "Service"
      identifiers = ["ecs.amazonaws.com"]
    }
  }
}

data "aws_iam_policy_document" "ecs_service_policy" {
  statement {
    effect = "Allow"
    resources = ["*"]
    actions = [
      "elasticloadbalancing:Describe*",
      "elasticloadbalancing:DeregisterInstancesFromLoadBalancer",
      "elasticloadbalancing:RegisterInstancesWithLoadBalancer",
      "ec2:Describe*",
      "ec2:AuthorizeSecurityGroupIngress"
    ]
  }
}


resource "aws_iam_role_policy" "ecs_service_role_policy" {
  name   = "ecs_service_role_policy"
  policy = "${data.aws_iam_policy_document.ecs_service_policy.json}"
  role   = "${aws_iam_role.ecs_role.id}"
}

resource "aws_iam_role" "ecs_role" {
  name               = "ecs_role"
  assume_role_policy = "${data.aws_iam_policy_document.ecs_service_role.json}"
}

resource "aws_ecs_task_definition" "nginx" {
  family = "nginx-${var.app}"

  network_mode             = "awsvpc"
  requires_compatibilities = ["FARGATE"]

  cpu    = "256"
  memory = "512"

  execution_role_arn = "${aws_iam_role.ecs_execution_role.arn}"
  task_role_arn      = "${aws_iam_role.ecs_execution_role.arn}"

  container_definitions = <<DEFINITION
  [
    {
      "image": "xxxxxx.dkr.ecr.us-east-2.amazonaws.com/org/prod/www-nginx:latest",
      "memory": 300,
      "name": "nginx-...-prod-www",
      "networkMode": "awsvpc",
      "essential": true,
      "portMappings": [
        {
          "containerPort": 80,
          "hostPort": 80
        }
      ],
      "logConfiguration": {
        "logDriver": "awslogs",
        "options": {
          "awslogs-group": "/xx-ecs-...-prod/nginx",
          "awslogs-region": "us-east-2",
          "awslogs-stream-prefix": "web"
        }
      }
    }    
  ]
  DEFINITION
}


resource "aws_cloudwatch_log_group" "nginx" {
  name = "/ecs-${var.app}/nginx"
}


resource "aws_ecs_service" "web" {
  name            = "nginx-${var.app}"

  task_definition = "${aws_ecs_task_definition.nginx.family}:${max("${aws_ecs_task_definition.nginx.revision}", "${aws_ecs_task_definition.nginx.revision}")}"
  
  desired_count   = 2
  launch_type     = "FARGATE"
  cluster =       "${aws_ecs_cluster.cluster.id}"

  network_configuration {
    subnets         = [aws_subnet.demo-private-1.id, aws_subnet.demo-private-2.id, aws_subnet.demo-private-3.id]
    security_groups = [aws_security_group.lb_sg.id]
  }


  load_balancer {
    target_group_arn = aws_alb_target_group.nginx.id
    container_name   = "nginx-${var.app}"
    container_port   = "80"
  }
  
  depends_on = ["aws_alb_target_group.nginx", "aws_iam_role_policy.ecs_service_role_policy"]
}

resource "aws_alb_target_group" "nginx" {
  name       = "nginx-${var.app}"
  port       = 80
  protocol   = "HTTP"
  vpc_id     = aws_vpc.demo-tf.id
  depends_on = [aws_alb.demo_eu_alb]
  target_type = "ip"

  stickiness {
    type            = "lb_cookie"
    cookie_duration = 86400
  }

  health_check {
    # path                = "/health"
    path                = "/"

    healthy_threshold   = 2
    unhealthy_threshold = 10 # 2 # 10
    timeout             = 60 # 5 # 60
    interval            = 300 # 8 # 300
    matcher             = "200,301,302"
  }
}


resource "aws_alb" "demo_eu_alb" {
  name            = "eu-alb-${var.app}"
  subnets         = [aws_subnet.demo-private-1.id, aws_subnet.demo-private-2.id, aws_subnet.demo-private-3.id]
  security_groups = [aws_security_group.lb_sg.id]
  enable_http2    = "true"
  idle_timeout    = 600
}



output "alb_output" {
  value = aws_alb.demo_eu_alb.dns_name
}


resource "aws_security_group" "lb_sg" {
  description = "controls access to the application ELB"

  vpc_id = aws_vpc.demo-tf.id
  name   = "ELB-${var.app}"

  ingress {
    protocol    = "tcp"
    from_port   = 80
    to_port     = 80
    cidr_blocks = ["0.0.0.0/0"]
  }

  ingress {
    protocol    = "tcp"
    from_port   = 443
    to_port     = 443
    cidr_blocks = ["0.0.0.0/0"]
  }

  egress {
    from_port = 0
    to_port   = 0
    protocol  = "-1"

    cidr_blocks = [
      "0.0.0.0/0",
    ]
  }
}



resource "aws_alb_listener" "front_end" {
  load_balancer_arn = aws_alb.demo_eu_alb.id
  port              = "80"
  protocol          = "HTTP"

  default_action {
    type = "redirect"

    redirect {
      port        = "443"
      protocol    = "HTTPS"
      status_code = "HTTP_301"
    }
  }
}


resource "aws_alb_listener" "alb_front_https" {
    load_balancer_arn   =   "${aws_alb.demo_eu_alb.arn}"
    port            =   "443"
    protocol        =   "HTTPS"
    ssl_policy      =   "ELBSecurityPolicy-TLS-1-2-Ext-2018-06"
    certificate_arn     =   "${aws_iam_server_certificate.lb_cert.arn}"
    default_action {
        target_group_arn    =   "${aws_alb_target_group.nginx.arn}"
        type            =   "forward"
    }
}


resource "aws_iam_server_certificate" "lb_cert" {
  name              = "lb_cert-${var.app}"
  certificate_body  = "${file("./www.____.com/cert.pem")}"
  private_key       = "${file("./www.____.com/privkey.pem")}"
  certificate_chain = "${file("./www.____.com/chain.pem")}"
}

resource "aws_iam_role" "ecs_execution_role" {
  name = "ecs_task_execution_role"
 
  assume_role_policy = <<EOF
{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Sid": "",
        "Effect": "Allow",
        "Principal": {
         "Service": "ecs-tasks.amazonaws.com"
        },
        "Action": "sts:AssumeRole"
    }    
  ]
}
EOF
}

resource "aws_iam_policy" "ecs_permissions" {
  name        = "my_ecs_permissions"
  description = "Permissions to enable CT"

  policy = <<EOF
{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Sid": "",
      "Effect": "Allow",
      "Action": [
        "ecs:CreateCluster",
        "ecs:DeregisterContainerInstance",
        "ecs:DiscoverPollEndpoint",
        "ecs:Poll",
        "ecs:RegisterContainerInstance",
        "ecs:StartTelemetrySession",
        "ecs:Submit*",
        "ecs:StartTask",
        "ecr:GetAuthorizationToken",
        "ecr:BatchCheckLayerAvailability",
        "ecr:GetDownloadUrlForLayer",
        "ecr:BatchGetImage",
        "logs:CreateLogStream",
        "logs:PutLogEvents"
      ],
      "Resource": "*"
    }    
  ]
}
EOF
}

resource "aws_iam_role_policy_attachment" "ecs_attachment" {
  role       = aws_iam_role.ecs_execution_role.name
  policy_arn = aws_iam_policy.ecs_permissions.arn
}









### VPC

### Network

# Internet VPC

resource "aws_vpc" "demo-tf" {
  cidr_block           = "172.21.0.0/16"
  instance_tenancy     = "default"
  enable_dns_support   = "true"
  enable_dns_hostnames = "true"
  enable_classiclink   = "false"

  tags = {
    Name = "vpc-${var.app}"
  }
}

# Subnets
resource "aws_subnet" "demo-public-1" {
  vpc_id                  = aws_vpc.demo-tf.id
  cidr_block              = "172.21.10.0/24"
  map_public_ip_on_launch = "true"
  availability_zone       = "us-east-2a"

  tags = {
    Name = "public-1-${var.app}"
  }
}

resource "aws_subnet" "demo-public-2" {
  vpc_id                  = aws_vpc.demo-tf.id
  cidr_block              = "172.21.20.0/24"
  map_public_ip_on_launch = "true"
  availability_zone       = "us-east-2b"

  tags = {
    Name = "public-2-${var.app}"
  }
}

resource "aws_subnet" "demo-public-3" {
  vpc_id                  = aws_vpc.demo-tf.id
  cidr_block              = "172.21.30.0/24"
  map_public_ip_on_launch = "true"
  availability_zone       = "us-east-2c"

  tags = {
    Name = "public-3-${var.app}"
  }
}

resource "aws_subnet" "demo-private-1" {
  vpc_id                  = aws_vpc.demo-tf.id
  cidr_block              = "172.21.40.0/24"
  map_public_ip_on_launch = "false"
  availability_zone       = "us-east-2a"

  tags = {
    Name = "private-1-${var.app}"
  }
}

resource "aws_subnet" "demo-private-2" {
  vpc_id                  = aws_vpc.demo-tf.id
  cidr_block              = "172.21.50.0/24"
  map_public_ip_on_launch = "false"
  availability_zone       = "us-east-2b"

  tags = {
    Name = "private-2-${var.app}"
  }
}

resource "aws_subnet" "demo-private-3" {
  vpc_id                  = aws_vpc.demo-tf.id
  cidr_block              = "172.21.60.0/24"
  map_public_ip_on_launch = "false"
  availability_zone       = "us-east-2c"

  tags = {
    Name = "private-3-${var.app}"
  }
}

# Internet GW
resource "aws_internet_gateway" "demo-gw" {
  vpc_id = aws_vpc.demo-tf.id

  tags = {
    Name = "IG-${var.app}"
  }
}

# route tables
resource "aws_route_table" "demo-private" {
  vpc_id = aws_vpc.demo-tf.id

  route {
    cidr_block = "0.0.0.0/0"
    gateway_id = aws_internet_gateway.demo-gw.id
  }

  tags = {
    Name = "private-1-${var.app}"
  }
}

# route tables
resource "aws_route_table" "demo-public" {
  vpc_id = aws_vpc.demo-tf.id

  route {
    cidr_block = "0.0.0.0/0"
    gateway_id = aws_internet_gateway.demo-gw.id
  }

  tags = {
    Name = "public-1-${var.app}"
  }
}


# route associations public
resource "aws_route_table_association" "demo-public-1-a" {
  subnet_id      = aws_subnet.demo-public-1.id
  route_table_id = aws_route_table.demo-public.id
}

resource "aws_route_table_association" "demo-public-2-a" {
  subnet_id      = aws_subnet.demo-public-2.id
  route_table_id = aws_route_table.demo-public.id
}

resource "aws_route_table_association" "demo-public-3-a" {
  subnet_id      = aws_subnet.demo-public-3.id
  route_table_id = aws_route_table.demo-public.id
}


# route associations private
resource "aws_route_table_association" "demo-private-1-a" {
  subnet_id      = aws_subnet.demo-private-1.id
  route_table_id = aws_route_table.demo-private.id
}

resource "aws_route_table_association" "demo-private-2-a" {
  subnet_id      = aws_subnet.demo-private-2.id
  route_table_id = aws_route_table.demo-private.id
}

resource "aws_route_table_association" "demo-private-3-a" {
  subnet_id      = aws_subnet.demo-private-3.id
  route_table_id = aws_route_table.demo-private.id
}

Answer 1

可能的原因是无法访问互联网以执行您在 Fargate 中的任务。

具体来说，您在 aws_ecs_service 中使用:

  network_configuration {
    subnets         = [aws_subnet.demo-private-1.id, aws_subnet.demo-private-2.id, aws_subnet.demo-private-3.id]
    security_groups = [aws_security_group.lb_sg.id]
  }

但是，它没有指定 assign_public_ip ，默认情况下为 false。随后，您在 Fargate 上的任务没有公共(public) ip 并且无法访问 ECR 服务，导致观察到超时。

请注意，即使您添加了公共(public) ip，也可能有其他原因与您的 vpc 或其他设置相关，我尚未验证。