rig major updates

This commit is contained in:
2026-09-22 05:15:49 -03:00
parent 9c963514f1
commit 2a0a793f19
64 changed files with 1762 additions and 645 deletions

View File

@@ -1,109 +0,0 @@
#!/usr/bin/env bash
# Apache Airflow — the cluster half of the airflow cabinet (one `standalone` pod).
# Requires the postgres addon; refuses to install without it.
# Notes: docs/notes/addons.md
set -euo pipefail
cd "$(dirname "$0")/.."
source ./lib/config.sh
load_config
K="kubectl --context ${KUBECONTEXT}"
NS="${DATA_NAMESPACE:-data}"
if ! $K get deployment -n "$NS" postgres >/dev/null 2>&1; then
echo " ! airflow needs the postgres addon, and it is not installed" >&2
echo " add it before airflow in the profile's ADDONS:" >&2
echo " ADDONS=\"... postgres airflow\"" >&2
exit 1
fi
# Reuse the credential postgres generated rather than storing a second copy.
db_user=$($K get secret -n "$NS" postgres -o jsonpath='{.data.POSTGRES_USER}' | base64 -d)
db_pass=$($K get secret -n "$NS" postgres -o jsonpath='{.data.POSTGRES_PASSWORD}' | base64 -d)
db_name=$($K get secret -n "$NS" postgres -o jsonpath='{.data.POSTGRES_DB}' | base64 -d)
if $K get secret -n "$NS" airflow >/dev/null 2>&1; then
echo " secret exists, keeping the current admin password and fernet key"
else
admin_password=$(head -c 18 /dev/urandom | base64 | tr -d '/+=' | head -c 24)
# Airflow requires a 32-byte urlsafe-base64 key; without a fixed one every
# restart invalidates every stored connection.
fernet_key=$(head -c 32 /dev/urandom | base64 | tr '+/' '-_')
$K create secret generic airflow -n "$NS" \
--from-literal=ADMIN_USER="${AIRFLOW_ADMIN_USER:-admin}" \
--from-literal=ADMIN_PASSWORD="$admin_password" \
--from-literal=FERNET_KEY="$fernet_key" \
--from-literal=SQL_ALCHEMY_CONN="postgresql+psycopg2://${db_user}:${db_pass}@postgres:5432/${db_name}" \
>/dev/null
echo " generated an admin password (read it back with the command below)"
fi
echo " applying manifests"
$K apply -n "$NS" -f - >/dev/null <<YAML
apiVersion: v1
kind: Service
metadata:
name: airflow
spec:
selector:
app: airflow
ports:
- port: 8080
targetPort: 8080
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: airflow
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app: airflow
template:
metadata:
labels:
app: airflow
spec:
containers:
- name: airflow
image: ${AIRFLOW_IMAGE}
args: ["standalone"]
env:
- name: AIRFLOW__CORE__EXECUTOR
value: LocalExecutor
- name: AIRFLOW__CORE__LOAD_EXAMPLES
value: "false"
- name: AIRFLOW__DATABASE__SQL_ALCHEMY_CONN
valueFrom:
secretKeyRef: {name: airflow, key: SQL_ALCHEMY_CONN}
- name: AIRFLOW__CORE__FERNET_KEY
valueFrom:
secretKeyRef: {name: airflow, key: FERNET_KEY}
- name: _AIRFLOW_WWW_USER_USERNAME
valueFrom:
secretKeyRef: {name: airflow, key: ADMIN_USER}
- name: _AIRFLOW_WWW_USER_PASSWORD
valueFrom:
secretKeyRef: {name: airflow, key: ADMIN_PASSWORD}
ports:
- containerPort: 8080
readinessProbe:
httpGet:
path: /health
port: 8080
# First boot runs the whole migration before it serves anything.
initialDelaySeconds: 60
periodSeconds: 15
failureThreshold: 20
YAML
echo " waiting for airflow (the first boot migrates the database, so this is slow)..."
$K rollout status deployment/airflow -n "$NS" --timeout=600s
echo " in-cluster: http://airflow.${NS}.svc.cluster.local:8080"
echo " reach it: kubectl --context ${KUBECONTEXT} -n ${NS} port-forward svc/airflow 8080:8080"
echo " password: kubectl --context ${KUBECONTEXT} -n ${NS} get secret airflow -o jsonpath='{.data.ADMIN_PASSWORD}' | base64 -d"

View File

@@ -2,7 +2,7 @@
# cert-manager plus a self-signed cluster issuer (offline local CA).
# Notes: docs/notes/addons.md
set -euo pipefail
cd "$(dirname "$0")/.."
cd "${RIG_CTRL:-$(dirname "$0")/..}"
source ./lib/config.sh
load_config
@@ -12,7 +12,9 @@ K="kubectl --context ${KUBECONTEXT}"
if $K get deployment -n cert-manager cert-manager >/dev/null 2>&1; then
echo " already installed"
else
$K apply -f "https://github.com/cert-manager/cert-manager/releases/download/${CERT_MANAGER_VERSION}/cert-manager.yaml"
# The pinned manifest, verified on disk — never a URL applied directly.
manifest=$(bash ./deps.sh manifest CERT_MANAGER)
$K apply -f "$manifest"
fi
echo " waiting for cert-manager..."

View File

@@ -3,7 +3,7 @@
# The pool is derived from the kind Docker network at install time.
# Notes: docs/notes/addons.md
set -euo pipefail
cd "$(dirname "$0")/.."
cd "${RIG_CTRL:-$(dirname "$0")/..}"
source ./lib/config.sh
load_config
@@ -46,7 +46,9 @@ echo " kind network $subnet → pool ${pool_start}-${pool_end}"
if $K get deployment -n metallb-system controller >/dev/null 2>&1; then
echo " already installed"
else
$K apply -f "https://raw.githubusercontent.com/metallb/metallb/${METALLB_VERSION}/config/manifests/metallb-native.yaml"
# The pinned manifest, verified on disk — never a URL applied directly.
manifest=$(bash ./deps.sh manifest METALLB)
$K apply -f "$manifest"
fi
# `rollout status`, not `kubectl wait`: wait errors out while the pod doesn't exist yet.

View File

@@ -2,7 +2,7 @@
# metrics-server — makes `kubectl top` work (patched with --kubelet-insecure-tls for kind).
# Notes: docs/notes/addons.md
set -euo pipefail
cd "$(dirname "$0")/.."
cd "${RIG_CTRL:-$(dirname "$0")/..}"
source ./lib/config.sh
load_config
@@ -10,7 +10,9 @@ load_config
K="kubectl --context ${KUBECONTEXT}"
if ! $K get deployment -n kube-system metrics-server >/dev/null 2>&1; then
$K apply -f "https://github.com/kubernetes-sigs/metrics-server/releases/download/${METRICS_SERVER_VERSION}/components.yaml"
# The pinned manifest, verified on disk — never a URL applied directly.
manifest=$(bash ./deps.sh manifest METRICS_SERVER)
$K apply -f "$manifest"
fi
$K patch deployment metrics-server -n kube-system --type=json \

View File

@@ -1,105 +0,0 @@
#!/usr/bin/env bash
# PostgreSQL — the cluster half of the postgres cabinet: plain manifests, one replica on a PVC.
# Notes: docs/notes/addons.md
set -euo pipefail
cd "$(dirname "$0")/.."
source ./lib/config.sh
load_config
K="kubectl --context ${KUBECONTEXT}"
NS="${DATA_NAMESPACE:-data}"
$K get namespace "$NS" >/dev/null 2>&1 || $K create namespace "$NS"
# The password is generated once and then left alone, so re-running this does
# not rotate the credential out from under whatever is already connected.
if $K get secret -n "$NS" postgres >/dev/null 2>&1; then
echo " secret exists, keeping the current password"
else
password=$(head -c 18 /dev/urandom | base64 | tr -d '/+=' | head -c 24)
$K create secret generic postgres -n "$NS" \
--from-literal=POSTGRES_DB="${POSTGRES_DB:-postgres}" \
--from-literal=POSTGRES_USER="${POSTGRES_USER:-postgres}" \
--from-literal=POSTGRES_PASSWORD="$password" >/dev/null
echo " generated a password (read it back with the command printed below)"
fi
echo " applying manifests"
$K apply -n "$NS" -f - >/dev/null <<YAML
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: postgres-data
spec:
accessModes: [ReadWriteOnce]
resources:
requests:
storage: ${POSTGRES_STORAGE:-2Gi}
---
apiVersion: v1
kind: Service
metadata:
name: postgres
spec:
selector:
app: postgres
ports:
- port: 5432
targetPort: 5432
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: postgres
spec:
replicas: 1
# One volume, one writer. Rolling would start a second pod against the same
# PVC before the first exits, and Postgres refuses to share a data directory.
strategy:
type: Recreate
selector:
matchLabels:
app: postgres
template:
metadata:
labels:
app: postgres
spec:
containers:
- name: postgres
image: ${POSTGRES_IMAGE}
envFrom:
- secretRef:
name: postgres
env:
# The image initialises into the volume root otherwise, and a
# lost+found from the PVC makes it refuse to initdb.
- name: PGDATA
value: /var/lib/postgresql/data/pgdata
ports:
- containerPort: 5432
volumeMounts:
- name: data
mountPath: /var/lib/postgresql/data
readinessProbe:
exec:
command: ["sh", "-c", "pg_isready -U \$POSTGRES_USER -d \$POSTGRES_DB"]
initialDelaySeconds: 5
periodSeconds: 5
livenessProbe:
exec:
command: ["sh", "-c", "pg_isready -U \$POSTGRES_USER -d \$POSTGRES_DB"]
initialDelaySeconds: 30
periodSeconds: 15
volumes:
- name: data
persistentVolumeClaim:
claimName: postgres-data
YAML
echo " waiting for postgres..."
$K rollout status deployment/postgres -n "$NS" --timeout=240s
echo " in-cluster: postgres.${NS}.svc.cluster.local:5432"
echo " password: kubectl --context ${KUBECONTEXT} -n ${NS} get secret postgres -o jsonpath='{.data.POSTGRES_PASSWORD}' | base64 -d"

View File

@@ -1,57 +0,0 @@
#!/usr/bin/env bash
# Redis — the cluster half of the redis cabinet: cache/broker, no persistence.
# Notes: docs/notes/addons.md
set -euo pipefail
cd "$(dirname "$0")/.."
source ./lib/config.sh
load_config
K="kubectl --context ${KUBECONTEXT}"
NS="${DATA_NAMESPACE:-data}"
$K get namespace "$NS" >/dev/null 2>&1 || $K create namespace "$NS"
echo " applying manifests"
$K apply -n "$NS" -f - >/dev/null <<YAML
apiVersion: v1
kind: Service
metadata:
name: redis
spec:
selector:
app: redis
ports:
- port: 6379
targetPort: 6379
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: redis
spec:
replicas: 1
selector:
matchLabels:
app: redis
template:
metadata:
labels:
app: redis
spec:
containers:
- name: redis
image: ${REDIS_IMAGE}
ports:
- containerPort: 6379
readinessProbe:
exec:
command: ["redis-cli", "ping"]
initialDelaySeconds: 3
periodSeconds: 5
YAML
echo " waiting for redis..."
$K rollout status deployment/redis -n "$NS" --timeout=180s
echo " in-cluster: redis://redis.${NS}.svc.cluster.local:6379/0"