Skip to content

bringing down the API #183

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

bringing down the API #183

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5859253
bringing down the API
irvingpop Aug 31, 2025
dec0ddc
Try to reduce spot availability issues
irvingpop Aug 31, 2025
a05b488
Switch to arm due to amd64 spot unreliability
irvingpop Sep 1, 2025
6719605
Update back-end image to the latest one in ECR if needed
irvingpop Sep 1, 2025
db0899b
API still up for now
irvingpop Sep 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions terraform/alb.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,11 @@ resource "aws_security_group" "lb_security_group" {
resource "aws_lb" "ecs" {
name_prefix = "oc"
security_groups = [aws_security_group.lb_security_group.id]
access_logs {
bucket = "oc-alb-logs"
enabled = true
prefix = "2025"
}

load_balancer_type = "application"
internal = false
Expand Down
49 changes: 24 additions & 25 deletions terraform/apps.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ module "python_backend_prod" {
logs_group = aws_cloudwatch_log_group.ecslogs.name
ecs_cluster_id = module.ecs.cluster_id
task_execution_role = data.aws_iam_role.ecs_task_execution_role.arn
image_tag = "master"
image_tag = "latest"
}

resource "aws_lb_listener_rule" "python_backend_prod" {
Expand All @@ -46,31 +46,31 @@ resource "aws_lb_listener_rule" "python_backend_prod" {
}

# Backend Staging
module "python_backend_staging" {
source = "./python_backend"
# module "python_backend_staging" {
# source = "./python_backend"

env = "staging"
vpc_id = data.aws_vpc.use2.id
logs_group = aws_cloudwatch_log_group.ecslogs.name
ecs_cluster_id = module.ecs.cluster_id
task_execution_role = data.aws_iam_role.ecs_task_execution_role.arn
image_tag = "staging"
}
# env = "staging"
# vpc_id = data.aws_vpc.use2.id
# logs_group = aws_cloudwatch_log_group.ecslogs.name
# ecs_cluster_id = module.ecs.cluster_id
# task_execution_role = data.aws_iam_role.ecs_task_execution_role.arn
# image_tag = "latest"
# }

resource "aws_lb_listener_rule" "python_backend_staging" {
listener_arn = aws_lb_listener.default_https.arn
# resource "aws_lb_listener_rule" "python_backend_staging" {
# listener_arn = aws_lb_listener.default_https.arn

action {
type = "forward"
target_group_arn = module.python_backend_staging.lb_tg_arn
}
# action {
# type = "forward"
# target_group_arn = module.python_backend_staging.lb_tg_arn
# }

condition {
host_header {
values = ["backend-staging.operationcode.org", "api.staging.operationcode.org"]
}
}
}
# condition {
# host_header {
# values = ["backend-staging.operationcode.org", "api.staging.operationcode.org"]
# }
# }
# }

# Redirector for shut down sites
resource "aws_lb_listener_rule" "shutdown_sites_redirector" {
Expand All @@ -91,9 +91,8 @@ resource "aws_lb_listener_rule" "shutdown_sites_redirector" {
host_header {
values = [
"resources.operationcode.org",
"resources.staging.operationcode.org",
"resources-staging.operationcode.org",
"pybot.staging.operationcode.org",
"api.staging.operationcode.org",
]
}
}
Expand Down Expand Up @@ -199,7 +198,7 @@ module "pybot_prod" {
logs_group = aws_cloudwatch_log_group.ecslogs.name
ecs_cluster_id = module.ecs.cluster_id
task_execution_role = data.aws_iam_role.ecs_task_execution_role.arn
image_tag = "master"
image_tag = "latest"
}

resource "aws_lb_listener_rule" "pybot_prod" {
Expand Down
71 changes: 63 additions & 8 deletions terraform/asg.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@

# https://docs.aws.amazon.com/AmazonECS/latest/developerguide/ecs-optimized_AMI.html#ecs-optimized-ami-linux
data "aws_ssm_parameter" "ecs_optimized_ami" {
name = "/aws/service/ecs/optimized-ami/amazon-linux-2023/recommended"
# name = "/aws/service/ecs/optimized-ami/amazon-linux-2023/recommended"
name = "/aws/service/ecs/optimized-ami/amazon-linux-2023/arm64/recommended"
}

# https://registry.terraform.io/modules/terraform-aws-modules/autoscaling/aws/latest
Expand All @@ -10,12 +11,51 @@ module "autoscaling" {
version = "~> 6.5"

name = "${local.name}-spot"
instance_type = "t3.small"
min_size = 1
max_size = 2
desired_capacity = 1
instance_market_options = {
market_type = "spot"
min_size = 2
max_size = 4
desired_capacity = 2

# Enable mixed instances policy
use_mixed_instances_policy = true

# Mixed Instances Policy for better availability
mixed_instances_policy = {
instances_distribution = {
on_demand_base_capacity = 0
on_demand_percentage_above_base_capacity = 0
spot_allocation_strategy = "capacity-optimized"
}

override = [
{
instance_type = "t4g.small"
weighted_capacity = "1"
},
{
instance_type = "t4g.micro"
weighted_capacity = "1"
}
]

#amd64 options
# override = [
# {
# instance_type = "t3.small"
# weighted_capacity = "2"
# },
# {
# instance_type = "t3a.small"
# weighted_capacity = "2"
# },
# {
# instance_type = "t3.micro"
# weighted_capacity = "1"
# },
# {
# instance_type = "t3a.micro"
# weighted_capacity = "1"
# }
# ]
}

image_id = jsondecode(data.aws_ssm_parameter.ecs_optimized_ami.value)["image_id"]
Expand All @@ -37,7 +77,7 @@ module "autoscaling" {
{
delete_on_termination = true
device_index = 0
associate_public_ip_address = false
associate_public_ip_address = true
security_groups = [module.autoscaling_sg.security_group_id]
}
]
Expand Down Expand Up @@ -67,6 +107,21 @@ module "autoscaling" {
# reduce cloudwatch costs
enable_monitoring = false

# Enable essential autoscaling metrics
enabled_metrics = [
"GroupDesiredCapacity",
"GroupInServiceCapacity",
"GroupInServiceInstances",
"GroupMaxSize",
"GroupMinSize",
"GroupPendingCapacity",
"GroupPendingInstances",
"GroupTerminatingCapacity",
"GroupTerminatingInstances",
"GroupTotalCapacity",
"GroupTotalInstances"
]

tags = local.tags
}

Expand Down
10 changes: 9 additions & 1 deletion terraform/pybot/main.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ locals {

# CHANGEME once infra scales up
cpu = var.env == "prod" ? 256 : 256
memory = var.env == "prod" ? 512 : 256
memory = var.env == "prod" ? 256 : 128
count = var.env == "prod" ? 1 : 1


Expand Down Expand Up @@ -52,6 +52,14 @@ resource "aws_ecs_task_definition" "pybot" {
}
}

healthCheck = {
command = ["CMD-SHELL", "wget -q -O /dev/null http://localhost:5000/health"]
interval = 30
timeout = 5
retries = 3
startPeriod = 60
}

secrets = local.secrets_env

mountPoints = []
Expand Down
9 changes: 8 additions & 1 deletion terraform/python_backend/main.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ resource "aws_ecs_task_definition" "python_backend" {
container_definitions = jsonencode([
{
name = "python_backend_${var.env}"
image = "operationcode/back-end:${var.image_tag}"
image = "633607774026.dkr.ecr.us-east-2.amazonaws.com/back-end:${var.image_tag}"
essential = true

portMappings = [
Expand All @@ -53,6 +53,13 @@ resource "aws_ecs_task_definition" "python_backend" {
}
}

healthCheck = {
command = ["CMD-SHELL", "wget -q -O /dev/null http://localhost:8000/healthz"]
interval = 30
timeout = 5
retries = 3
startPeriod = 60
}

environment = [
{
Expand Down