thermograph/infra/terraform/main.tf
emi d138f00a20
Some checks failed
Sync infra to hosts / sync-beta (push) Has been skipped
Sync infra to hosts / sync-prod (push) Has been skipped
Sync infra to hosts / sync-dev (push) Failing after 6s
secrets-guard / encrypted (push) Successful in 6s
shell-lint / shellcheck (push) Successful in 13s
Validate observability stack / validate (push) Successful in 17s
PR build (required check) / changes (pull_request) Successful in 6s
secrets-guard / encrypted (pull_request) Successful in 5s
PR build (required check) / build-backend (pull_request) Has been skipped
shell-lint / shellcheck (pull_request) Successful in 6s
PR build (required check) / build-frontend (pull_request) Has been skipped
PR build (required check) / validate-observability (pull_request) Successful in 18s
PR build (required check) / gate (pull_request) Successful in 2s
infra: split the estate into vps1/vps2 — beta joins prod, dev gets a home (#103)
2026-07-26 06:56:38 +00:00

143 lines
6.1 KiB
HCL

# No project/region default here on purpose: each var.gcp_hosts entry carries its
# own project + zone (a fleet could span projects), and with var.gcp_hosts empty
# this provider is never invoked, so there's nothing to default. When you do
# populate var.gcp_hosts, authenticate via Application Default Credentials
# (`gcloud auth application-default login`) or GOOGLE_APPLICATION_CREDENTIALS --
# no credentials are configured in this repo.
provider "google" {}
locals {
# Repo root (one level above this terraform/ dir). The module hashes the compose
# files here so a compose change re-triggers the remote deploy, and this is the
# tree the host's checkout mirrors over git.
repo_root = abspath("${path.root}/..")
# Reusable size presets — a host can reference one by name (hosts.<name>.size)
# instead of hand-picking workers/app_cpus/db_cpus/db_memory separately. Mirrors
# the target Proxmox sizing-tier model (architecture doc §6: nano/small/medium/
# large -> {cores, mem}) ahead of actually provisioning VMs — Proxmox itself is
# deferred; today these tiers just size the container caps on the existing
# SSH-managed VPS hosts. "large" matches the current 48 GB prod box's numbers.
sizes = {
nano = { workers = 1, app_cpus = 1, db_cpus = 1, db_memory = "1g" }
small = { workers = 4, app_cpus = 4, db_cpus = 2, db_memory = "8g" }
medium = { workers = 6, app_cpus = 6, db_cpus = 3, db_memory = "12g" }
large = { workers = 8, app_cpus = 8, db_cpus = 4, db_memory = "16g" }
}
}
# GCP-created hosts (empty by default — see variables.tf and modules/gcp-host).
# Creates only the VM + minimal networking; every provisioning behavior comes from
# the SAME thermograph-host module every SSH-managed host below uses, via
# local.all_hosts merging its output IP in below. No live resources exist until
# var.gcp_hosts is populated.
module "gcp_vm" {
source = "./modules/gcp-host"
for_each = var.gcp_hosts
name = each.key
project = each.value.project
zone = each.value.zone
machine_type = each.value.machine_type
ssh_user = each.value.ssh_user
ssh_public_key_path = each.value.ssh_public_key_path
}
locals {
# ONE MODULE INSTANCE PER (HOST, ENVIRONMENT) PAIR, not per host.
#
# var.hosts is keyed by machine (vps1, vps2) and each machine carries an
# `environments` map, because vps2 runs prod AND beta. The module below
# provisions an ENVIRONMENT — a checkout, a branch, image tags, a Caddy site,
# container sizing — so it needs one instance per environment, with the two
# instances on vps2 sharing that machine's SSH identity.
#
# Flattened to keys like "vps2-prod" and "vps2-beta". Keeping them distinct
# module instances is what makes `app_dir` (required, no default in
# variables.tf) do its job: two environments on one box get two explicitly
# different checkouts, so neither apply can `git reset --hard` the other's
# tree.
ssh_environments = merge([
for hname, h in var.hosts : {
for ename, e in h.environments :
"${hname}-${ename}" => merge(e, {
host = h.host
ssh_user = h.ssh_user
ssh_private_key_path = h.ssh_private_key_path
})
}
]...)
# Every environment this config manages, SSH-only (flattened above) plus
# GCP-created (whose `host` is filled in from the VM Terraform just created) —
# one unified map so a single `module.host` for_each below handles both without
# duplicating any provisioning logic. GCP hosts stay one-entry-per-machine:
# nothing creates two environments on a created VM today, and the variable
# keeps its flat shape. They always use a named size tier (simpler than
# exposing the four raw sizing fields on that variable too).
all_hosts = merge(
local.ssh_environments,
{
for name, h in var.gcp_hosts : name => merge(h, {
host = module.gcp_vm[name].external_ip
workers = null
app_cpus = null
db_cpus = null
db_memory = null
openmeteo = false
om_data_dir = "/mnt/om-archive"
})
}
)
# Per-host resolved sizing: a named tier (host.size) wins when set; otherwise the
# host's own workers/app_cpus/db_cpus/db_memory fields (each individually
# defaulted in variables.tf) — so existing tfvars with explicit numbers are
# unaffected, and a tier is purely an opt-in shortcut.
host_sizing = {
for name, h in local.all_hosts : name => h.size != null ? local.sizes[h.size] : {
workers = h.workers
app_cpus = h.app_cpus
db_cpus = h.db_cpus
db_memory = h.db_memory
}
}
}
# One module instance per host (SSH-managed or GCP-created — see local.all_hosts).
# The module is entirely SSH-provisioner driven: it configures an already-running
# VM (however it came to exist) and hands the app off to docker compose.
module "host" {
source = "./modules/thermograph-host"
for_each = local.all_hosts
# Per-host config
name = each.key
host = each.value.host
ssh_user = each.value.ssh_user
ssh_private_key_path = each.value.ssh_private_key_path
role = each.value.role
git_branch = each.value.git_branch
backend_image_tag = each.value.backend_image_tag
frontend_image_tag = each.value.frontend_image_tag
domain = each.value.domain
compose_files = each.value.compose_files
app_dir = each.value.app_dir
workers = local.host_sizing[each.key].workers
app_cpus = local.host_sizing[each.key].app_cpus
db_cpus = local.host_sizing[each.key].db_cpus
db_memory = local.host_sizing[each.key].db_memory
timescaledb_tag = each.value.timescaledb_tag
openmeteo = each.value.openmeteo
om_data_dir = each.value.om_data_dir
# Shared infra config
repo_root = local.repo_root
repo_url = var.repo_url
app_port = var.app_port
# Shared object-storage config (only used where openmeteo = true)
om_bucket_remote = var.om_bucket_remote
om_rclone_conf = var.om_rclone_conf
om_vfs_cache_max = var.om_vfs_cache_max
}