thermograph/infra/terraform/variables.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

185 lines
12 KiB
HCL

# ---------------------------------------------------------------------------------
# Hosts
# ---------------------------------------------------------------------------------
# Keyed by HOST (vps1, vps2), NOT by environment: vps2 alone runs TWO environments
# (prod AND beta) as separate Swarm stacks on the SAME box, so "one entry = one
# environment" broke the moment that became true — two entries that both defaulted
# `app_dir` to "/opt/thermograph" would let a prod apply and a beta apply stomp the
# identical checkout. Each host now carries its SSH identity ONCE (host IP,
# ssh_user, key) plus an `environments` map of everything that varies per
# environment running on it — checkout path, git branch, image tags, domain,
# sizing. `app_dir` is REQUIRED with no default for exactly this reason: two
# environments on one host must be given two explicitly DIFFERENT paths (see
# terraform.tfvars.example), so their checkouts — and a `git reset --hard` in one
# of them — can never collide.
#
# vps1 (75.119.132.91): Forgejo (git+CI+registry), Grafana/Loki/Alloy,
# emigriffith.dev, and the `dev` environment (its own Postgres, mesh-only, no
# public DNS/Caddy site). vps2 (169.58.46.181): `prod` (thermograph.org) and
# `beta` (beta.thermograph.org) — Centralis, Postfix and the backups also live
# here — sharing the ONE TimescaleDB instance both app environments use, on
# separate databases/roles (deploy/db/provision-env-db.sh); this variable's
# per-environment db_cpus/db_memory size only that environment's app-container
# caps, not a second database (see deploy/db/init/20-tuning.sh). The LAN dev
# branch (`make dev-up`, a laptop-local rehearsal) deploys nowhere via Terraform
# and is NOT managed here.
#
# An environment with `domain = ""` gets no Caddy/TLS: its app port is opened on
# the firewall and it's reached directly.
#
# Resource sizing (workers / app_cpus / db_cpus / db_memory), per environment,
# defaults to the historical 4 / 4 / 2 / 8g budget (right for beta). vps2 is 48 GB
# / 12 cores — raise these for prod (the example uses app_cpus 8, db_cpus 4,
# db_memory "16g", via the "large" size tier). 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.
#
# TODO(cutover): main.tf's `module.host` for_each (via `local.all_hosts`) still
# expects ONE flat entry per key, reading `each.value.host`/`.role`/`.app_dir`/…
# directly. It needs a flattening step ahead of that for_each — one derived entry
# per (host, environment) pair, keyed e.g. "<host>-<environment>" ("vps2-prod" and
# "vps2-beta" as two separate module instances sharing vps2's host/ssh_user/
# ssh_private_key_path but each with its own app_dir/role/image tags/sizing).
# This variable's new shape is not yet wired into main.tf's module block.
variable "hosts" {
description = "Map of VPS boxes to manage, keyed by a short host name (\"vps1\", \"vps2\") — NOT by environment. SSH identity is per-host; everything environment-specific lives in that host's `environments` map."
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
# One entry per environment running on this host, keyed by environment name
# ("prod" | "beta" | "dev"). A host normally carries one; vps2 carries two.
environments = map(object({
role = string # "prod" | "beta" | "dev" (informational + outputs; should match the map key above)
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
# environment 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 for this environment; "" => no Caddy/TLS
compose_files = optional(list(string), ["docker-compose.yml"])
# REQUIRED, no default — see the file header: two environments on one host
# must never be able to default to the same checkout path.
app_dir = string # 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 environment (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 `hosts` used to be — one entry per
# environment, since these are hypothetical single-purpose boxes (e.g. a future
# UAT VM), not vps1/vps2, so they don't need the host/environment split above.
# 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.
# TODO(cutover): main.tf's `local.all_hosts = merge(var.hosts, ...)` currently
# merges this flat shape with `var.hosts` into one map for `module.host`'s
# for_each. Once `var.hosts` is nested (above), that merge needs to target the
# same flattened (host, environment) shape this variable already has — e.g. by
# treating each `gcp_hosts` entry as its own single-environment host.
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.