towerops/k8s/deployment.yaml
Graham McIntire e7bca6174c feat(on_call): schedules list with gantt timeline (chunk 2)
Resolver
- Resolver.resolve_range/3: returns the contiguous on-call segments for a
  schedule across [start_at, end_at). Walks layer handoffs + override
  boundaries, drops gap segments, and merges adjacent same-user segments.

UserColor module
- New Towerops.OnCall.UserColor with deterministic id -> color mapping
  (Tailwind class + matching #RRGGBB hex). Refactored ScheduleLive.Show
  to use it instead of its own per-page index palette so the same person
  gets the same color across the schedules list and detail pages.

ScheduleLive.Index
- Date navigation: Today / prev / next + 1/2/4-week range selector.
- URL-driven: ?start=YYYY-MM-DD&range=N for shareable views; falls back
  to defaults on malformed values.
- Per-row card: schedule name link, on-call-now avatar swatch, day-of-week
  header strip, gantt strip rendered as a CSS grid with one column per day,
  Today marker overlay.

Tests: 5 new resolver tests, 9 new UserColor tests, 5 new ScheduleLive
integration tests. Full suite: 10,210 / 0 failures. Format/dialyzer clean.

Also: cleaned up two stale inline comments in k8s/deployment.yaml that
disagreed with the values they sat next to (replicas/maxSurge).
2026-04-28 12:48:52 -05:00

234 lines
7.4 KiB
YAML

apiVersion: apps/v1
kind: Deployment
metadata:
name: towerops
namespace: towerops
spec:
replicas: 2
strategy:
type: RollingUpdate
rollingUpdate:
maxSurge: 1 # Allow 3rd pod during rollout to avoid downtime
maxUnavailable: 0 # Keep all pods running during rollout
minReadySeconds: 10 # Wait 10s after pod is ready before considering it available
selector:
matchLabels:
app: towerops
template:
metadata:
labels:
app: towerops
spec:
# Use system-cluster-critical priority to ensure towerops starts after CNI is ready
priorityClassName: system-cluster-critical
terminationGracePeriodSeconds: 90 # Allow 90s for graceful shutdown and connection draining
imagePullSecrets:
- name: forgejo-registry
securityContext:
runAsNonRoot: true
runAsUser: 65534
fsGroup: 65534
seccompProfile:
type: RuntimeDefault
initContainers:
- name: migrate
image: git.mcintire.me/graham/towerops-web:main-1777396805-e822bc9 # {"$imagepolicy": "flux-system:towerops-web"}
imagePullPolicy: IfNotPresent
command: ["/app/bin/migrate"]
securityContext:
allowPrivilegeEscalation: false
runAsNonRoot: true
runAsUser: 65534
capabilities:
drop:
- ALL
seccompProfile:
type: RuntimeDefault
env:
- name: MIX_ENV
value: "prod"
- name: RELEASE_COOKIE
valueFrom:
secretKeyRef:
name: towerops-secrets
key: RELEASE_COOKIE
- name: SECRET_KEY_BASE
valueFrom:
secretKeyRef:
name: towerops-secrets
key: SECRET_KEY_BASE
- name: CLOAK_KEY
valueFrom:
secretKeyRef:
name: towerops-secrets
key: CLOAK_KEY
- name: STRIPE_SECRET_KEY
valueFrom:
secretKeyRef:
name: towerops-billing
key: STRIPE_SECRET_KEY
optional: true
- name: STRIPE_WEBHOOK_SECRET
valueFrom:
secretKeyRef:
name: towerops-billing
key: STRIPE_WEBHOOK_SECRET
optional: true
- name: STRIPE_PRICE_ID
valueFrom:
secretKeyRef:
name: towerops-billing
key: STRIPE_PRICE_ID
optional: true
- name: STRIPE_METER_ID
valueFrom:
secretKeyRef:
name: towerops-billing
key: STRIPE_METER_ID
optional: true
envFrom:
- secretRef:
name: towerops-db
- secretRef:
name: towerops-aws
resources:
requests:
memory: "512Mi"
cpu: "100m"
limits:
memory: "1Gi"
cpu: "500m"
containers:
- name: towerops
image: git.mcintire.me/graham/towerops-web:main-1777396805-e822bc9 # {"$imagepolicy": "flux-system:towerops-web"}
imagePullPolicy: IfNotPresent
securityContext:
allowPrivilegeEscalation: false
runAsNonRoot: true
runAsUser: 65534
capabilities:
drop:
- ALL
seccompProfile:
type: RuntimeDefault
ports:
- containerPort: 4000
name: http
- containerPort: 4369
name: epmd
- containerPort: 9000
name: dist
lifecycle:
preStop:
exec:
command:
- /bin/sh
- -c
- |
# Stop accepting new connections by failing readiness probe
# Give load balancer time to remove pod from rotation
# Allow existing connections to complete
sleep 20
env:
- name: POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: ETCD_ENABLED
value: "true"
- name: RELEASE_DISTRIBUTION
value: "name"
- name: RELEASE_NODE
value: "towerops@$(POD_IP)"
- name: PORT
value: "4000"
- name: PHX_HOST
value: "towerops.net"
- name: MIX_ENV
value: "prod"
- name: RELEASE_COOKIE
valueFrom:
secretKeyRef:
name: towerops-secrets
key: RELEASE_COOKIE
- name: SECRET_KEY_BASE
valueFrom:
secretKeyRef:
name: towerops-secrets
key: SECRET_KEY_BASE
- name: CLOAK_KEY
valueFrom:
secretKeyRef:
name: towerops-secrets
key: CLOAK_KEY
- name: STRIPE_SECRET_KEY
valueFrom:
secretKeyRef:
name: towerops-billing
key: STRIPE_SECRET_KEY
optional: true
- name: STRIPE_WEBHOOK_SECRET
valueFrom:
secretKeyRef:
name: towerops-billing
key: STRIPE_WEBHOOK_SECRET
optional: true
- name: STRIPE_PRICE_ID
valueFrom:
secretKeyRef:
name: towerops-billing
key: STRIPE_PRICE_ID
optional: true
- name: STRIPE_METER_ID
valueFrom:
secretKeyRef:
name: towerops-billing
key: STRIPE_METER_ID
optional: true
envFrom:
# Redis connection configured via towerops-redis secret
- secretRef:
name: towerops-redis
- secretRef:
name: towerops-db
- secretRef:
name: towerops-aws
resources:
requests:
memory: "1.5Gi"
cpu: "500m"
limits:
memory: "3Gi"
cpu: "2000m"
startupProbe:
httpGet:
path: /health
port: 4000
initialDelaySeconds: 10
periodSeconds: 5
timeoutSeconds: 3
failureThreshold: 24 # 10s + (24 * 5s) = 130s max startup time
livenessProbe:
httpGet:
path: /health
port: 4000
periodSeconds: 10
timeoutSeconds: 3
failureThreshold: 3
readinessProbe:
httpGet:
path: /health
port: 4000
initialDelaySeconds: 5
periodSeconds: 5
timeoutSeconds: 2
successThreshold: 1 # Mark ready after first successful check
failureThreshold: 2 # Allow 1 failure before marking not ready