145 lines
8.8 KiB
HCL
145 lines
8.8 KiB
HCL
# ---------------------------------------------------------------------------------
|
|
# Hosts
|
|
# ---------------------------------------------------------------------------------
|
|
# One entry per VPS. The same module is instantiated for each (see main.tf's
|
|
# for_each). This config manages TWO hosts: prod (new 48 GB / 12-core VPS, branch
|
|
# `release`, thermograph.org) and beta (the old VPS 75.119.132.91, branch `main`,
|
|
# no public domain by default). The `dev` branch deploys to the LAN dev server via
|
|
# deploy/deploy-dev.sh (a self-hosted runner, in the app repo) and is NOT managed here.
|
|
#
|
|
# A host with `domain = ""` gets no Caddy/TLS: the app port is opened on the firewall
|
|
# and the app is reached directly (beta does this by default; set a domain to front
|
|
# it with Caddy TLS).
|
|
#
|
|
# Resource sizing (workers / app_cpus / db_cpus / db_memory) defaults to the historical
|
|
# 4 / 4 / 2 / 8g budget (right for beta). The prod box is 48 GB / 12 cores — raise these
|
|
# there (the example uses app_cpus 8, db_cpus 4, db_memory "16g"). The Postgres internal
|
|
# budget scales from db_memory automatically (deploy/db/init/20-tuning.sh), so no
|
|
# separate tuning edit is needed to exploit the RAM.
|
|
variable "hosts" {
|
|
description = "Map of hosts to manage, keyed by a short name (e.g. \"prod\", \"beta\")."
|
|
type = map(object({
|
|
host = string # IP or hostname to SSH to
|
|
ssh_user = optional(string, "deploy") # SSH login user
|
|
ssh_private_key_path = string # path to the private key for that user
|
|
role = string # "prod" | "beta" (informational + outputs)
|
|
git_branch = string # this INFRA repo's branch the checkout is reset to
|
|
# Which app images to run, e.g. "sha-<12 hex>" (each matching build-push.yml's tag
|
|
# for the commit that app repo built) or a semver tag on a release push. The app is
|
|
# TWO separately-published images now — emi/thermograph-backend/app and
|
|
# emi/thermograph-frontend/app — pinned independently. Required, no default: the
|
|
# host's checkout is this infra repo, not the app repos, so there's no "current
|
|
# commit" to derive a tag from; both must be explicit. Bump these (via a normal
|
|
# tfvars edit + apply) whenever an app repo ships a commit you want this host
|
|
# running; the infra repo's own git_branch is independent and rarely needs to change.
|
|
backend_image_tag = string
|
|
frontend_image_tag = string
|
|
domain = optional(string, "") # public domain; "" => no Caddy/TLS
|
|
compose_files = optional(list(string), ["docker-compose.yml"])
|
|
app_dir = optional(string, "/opt/thermograph") # checkout path on the host
|
|
workers = optional(number, 4) # uvicorn workers (WORKERS)
|
|
app_cpus = optional(number, 4) # app container CPU cap (APP_CPUS)
|
|
db_cpus = optional(number, 2) # db container CPU cap (DB_CPUS)
|
|
db_memory = optional(string, "8g") # db container memory cap (DB_MEMORY)
|
|
# A named size tier (see locals.sizes in main.tf: nano/small/medium/large) —
|
|
# when set, overrides the four fields above with the tier's preset. Leave
|
|
# null (default) to keep hand-picking workers/app_cpus/db_cpus/db_memory,
|
|
# as prod/beta already do below.
|
|
size = optional(string, null)
|
|
# The floating tag matches today's behavior everywhere until you pin it. Pin to
|
|
# an exact minor (SELECT extversion FROM pg_extension WHERE extname='timescaledb'
|
|
# on the live DB) before any host of this stack could ever replicate with
|
|
# another — a floating tag risks mismatched extension minors, which blocks a
|
|
# physical replica (hop-1 cutover runbook hazard #7). Use the SAME tag everywhere.
|
|
timescaledb_tag = optional(string, "latest-pg18")
|
|
# Self-host the ERA5 archive (docker-compose.openmeteo.yml + a host rclone mount
|
|
# of the object-storage bucket). Only the self-hosting host (prod) sets true.
|
|
openmeteo = optional(bool, false)
|
|
om_data_dir = optional(string, "/mnt/om-archive") # host rclone mount point (OM_DATA_DIR)
|
|
}))
|
|
}
|
|
|
|
# GCP-created hosts, keyed the same way as `hosts`. Default {} => zero GCP resources
|
|
# planned and the google provider is never actually invoked (see versions.tf and
|
|
# modules/gcp-host). Populate an entry to have Terraform create the VM itself; its
|
|
# output IP then feeds into the SAME thermograph-host module every SSH-managed host
|
|
# uses (main.tf), so provisioning logic is never duplicated between providers.
|
|
variable "gcp_hosts" {
|
|
description = "Map of hosts for Terraform to CREATE on GCP (Compute Engine), keyed the same way as `hosts`. Empty by default -- no live GCP resources exist yet; this is a scaffold for future use. See modules/gcp-host."
|
|
type = map(object({
|
|
project = string # GCP project ID
|
|
zone = string # e.g. "us-west1-a"
|
|
machine_type = optional(string, "e2-medium")
|
|
ssh_user = optional(string, "deploy")
|
|
ssh_public_key_path = string # path to the PUBLIC key installed on the instance
|
|
ssh_private_key_path = string # path to the matching PRIVATE key (for the module's provisioner)
|
|
role = string
|
|
git_branch = string
|
|
backend_image_tag = string
|
|
frontend_image_tag = string
|
|
domain = optional(string, "")
|
|
compose_files = optional(list(string), ["docker-compose.yml"])
|
|
app_dir = optional(string, "/opt/thermograph")
|
|
size = optional(string, "small")
|
|
timescaledb_tag = optional(string, "latest-pg18")
|
|
}))
|
|
default = {}
|
|
}
|
|
|
|
variable "repo_url" {
|
|
description = "Git remote to clone from when a host has no checkout yet. Points at THIS repo (thermograph-infra) now, not the app repo -- the app's own source is never checked out on a host; only its published registry images are pulled (see var.hosts[*].backend_image_tag / frontend_image_tag). thermograph-infra is a private repo, so this typically needs embedded read credentials, e.g. a Forgejo deploy token: \"https://<token-name>:<token>@git.thermograph.org/emi/thermograph-infra.git\"."
|
|
type = string
|
|
default = "https://git.thermograph.org/emi/thermograph-infra.git"
|
|
sensitive = true
|
|
}
|
|
|
|
variable "app_port" {
|
|
description = "Port the app binds inside the container / is health-checked on."
|
|
type = number
|
|
default = 8137
|
|
}
|
|
|
|
# ---------------------------------------------------------------------------------
|
|
# Self-hosted Open-Meteo (object storage) — consumed only by hosts with openmeteo=true
|
|
# ---------------------------------------------------------------------------------
|
|
# The ERA5 .om archive lives in an object-storage bucket, surfaced on the host by an
|
|
# rclone FUSE mount at each host's om_data_dir. These describe that bucket + mount.
|
|
# om_rclone_conf holds credentials, so it's sensitive and lands in state — keep the
|
|
# real value in terraform.tfvars (gitignored), never committed.
|
|
variable "om_bucket_remote" {
|
|
description = "rclone remote:path for the archive bucket, e.g. \"om-archive:thermograph-era5\" (matches a [remote] in om_rclone_conf)."
|
|
type = string
|
|
default = ""
|
|
}
|
|
|
|
variable "om_rclone_conf" {
|
|
description = "Full rclone.conf contents defining the archive remote (installed to /etc/rclone/rclone.conf, 0600). Sensitive."
|
|
type = string
|
|
default = ""
|
|
sensitive = true
|
|
}
|
|
|
|
variable "om_vfs_cache_max" {
|
|
description = "rclone --vfs-cache-max-size: bounds the on-disk hot cache for the mount (keep within the disk budget)."
|
|
type = string
|
|
default = "80G"
|
|
}
|
|
|
|
# ---------------------------------------------------------------------------------
|
|
# Secrets: owned by the SOPS+age vault now, NOT Terraform
|
|
# ---------------------------------------------------------------------------------
|
|
# POSTGRES_PASSWORD, THERMOGRAPH_AUTH_SECRET, THERMOGRAPH_METRICS_TOKEN,
|
|
# THERMOGRAPH_INDEXNOW_KEY, THERMOGRAPH_VAPID_*, REGISTRY_TOKEN, Discord/SMTP
|
|
# credentials, and every other app secret are no longer Terraform variables --
|
|
# they're rendered at deploy time from deploy/secrets/*.yaml (SOPS-encrypted,
|
|
# committed) by deploy/render-secrets.sh, which deploy.sh calls before `docker
|
|
# compose up`. Terraform's job here shrank to topology/sizing only (see
|
|
# modules/thermograph-host/templates/thermograph-topology.env.tftpl) plus
|
|
# triggering the deploy. See deploy/secrets/README.md to rotate or add a secret.
|
|
#
|
|
# The four secrets Terraform used to generate itself (postgres_password,
|
|
# auth_secret, metrics_token, indexnow_key) still exist as values -- they just
|
|
# live in the vault now, seeded once from Terraform's own generated values via
|
|
# deploy/secrets/seed-from-live.sh so the handoff changed nothing in use. Rotate
|
|
# them the same way as any other vault secret from here on (sops edit + commit +
|
|
# deploy), not via a Terraform keeper change.
|