prop/k8s/deployment-grid-rs.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: prop-grid-rs
  namespace: prop
  # Phase 2 cutover: Rust writes directly to /data/scores. Elixir only
  # runs the f00 analysis-hour step (which carries enrichment Rust
  # doesn't own yet — native-level duct merge, NEXRAD composite,
  # commercial-link degradation, ProfilesFile write). f01..f18 land
  # here from the Rust worker.
spec:
  # Replicas claim from grid_tasks via FOR UPDATE SKIP LOCKED with no
  # coordination; anti-affinity spreads them across distinct hosts so
  # any single node going down leaves the hourly chain with other
  # workers still draining.
  # Replica count is HPA-managed (hpa.yaml, min 1 / max 4).
  minReadySeconds: 5
  # Zero-downtime rollout for the propagation chain. With HPA min=1
  # and the previous maxSurge:0/maxUnavailable:1 config, every deploy
  # tore the single replica down before bringing the new one up,
  # leaving a multi-minute window where the :05 hourly cron had no
  # worker to claim tasks. Surge-first means the new pod is ready
  # before the old one drains; the two briefly overlap and race for
  # `grid_tasks` rows via FOR UPDATE SKIP LOCKED, which is safe.
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 1
      maxUnavailable: 0
  selector:
    matchLabels:
      app: prop-grid-rs
  template:
    metadata:
      labels:
        app: prop-grid-rs
        tier: grid-rs
      annotations:
        # Scraped by the Prometheus at 10.0.15.31 via the
        # `kubernetes-pods` job in prometheus.yml.j2 (apiserver proxy).
        # Metrics endpoint is on container port 9100 (see METRICS_ADDR
        # env below). `prometheus.io/job` makes the dashboard's
        # `up{job="prop-grid-rs"}` selector work without per-pod
        # relabel.
        prometheus.io/scrape: "true"
        prometheus.io/port: "9100"
        prometheus.io/path: "/metrics"
        prometheus.io/job: "prop-grid-rs"
    spec:
      # No node pinning — scheduler picks any host. Anti-affinity was
      # removed so HPA can stack multiple replicas on the same node if
      # that's where the scheduler wants them; grid-rs is CPU-bound but
      # not memory-bound so colocating a couple of replicas is fine.
      # Wide window for an in-flight chain step (typically 1–3 min) to
      # finish before SIGKILL. The worker handles SIGTERM by stopping
      # task pickup; releasing the current claim is the cron's job
      # (visibility timeout reclaims abandoned `grid_tasks` rows).
      terminationGracePeriodSeconds: 300
      imagePullSecrets:
        - name: forgejo-registry
      securityContext:
        runAsUser: 65534
        runAsNonRoot: true
        fsGroup: 65534
        seccompProfile:
          type: RuntimeDefault
      containers:
        - name: prop-grid-rs
          # Image built by a new CI pipeline from rust/prop_grid_rs/.
          # Multi-arch (amd64 + arm64) — reuses the repo's existing
          # buildx wiring.
          image: git.mcintire.me/graham/prop-grid-rs:main-1781279001-e879f29
          imagePullPolicy: IfNotPresent
          env:
            # Elixir secrets bundle carries DATABASE_URL already. Rust
            # reads it directly (sqlx connects with the same URL).
            - name: HRRR_BASE_URL
              value: "http://skippy.w5isp.com:8080"
            # When the LAN caching proxy at skippy is unreachable, fetches
            # retry once against the NOAA S3 public bucket so a proxy
            # outage degrades to direct S3 reads instead of stalling the
            # hourly pipeline.
            - name: HRRR_FALLBACK_BASE_URL
              value: "https://noaa-hrrr-bdp-pds.s3.amazonaws.com"
            - name: PROP_SCORES_DIR
              value: "/data/scores"
            # Shared idx-file cache on NFS. All grid-rs replicas read/write
            # through the same directory; idx bodies are immutable per HRRR
            # run, so cross-replica hits eliminate redundant NOAA S3 calls.
            - name: HRRR_IDX_CACHE_DIR
              value: "/data/hrrr_idx"
            - name: RUST_LOG
              value: "info"
            # Single concurrent task per pod. 2 replicas → 2 concurrent
            # cluster-wide. Raised from 2 after the new 3 Gi limit still
            # OOMed under 2-parallel forecast load — the NFS-backed
            # score-file writes (23 files × ~2 MB each) keep cgroup page
            # cache high enough that two concurrent tasks plus the
            # wgrib2 working set regularly crosses 3 Gi. Single-lane
            # parallelism stays comfortably under 2 Gi and lets the
            # analysis step (native duct + NEXRAD + commercial merges)
            # run safely within the same budget.
            - name: PROP_GRID_RS_PARALLELISM
              value: "1"
            # Pool size = parallelism + 2 (NOTIFY + retry slack). Kept in
            # sync with PROP_GRID_RS_PARALLELISM when either changes.
            - name: PROP_GRID_RS_PG_CONNS
              value: "3"
            - name: METRICS_ADDR
              value: "0.0.0.0:9100"
          envFrom:
            - secretRef:
                name: prop-secrets
          ports:
            - name: metrics
              containerPort: 9100
              protocol: TCP
          # Liveness is "the process is still running"; let the kubelet
          # restart us if we crash. Claiming work from grid_tasks is the
          # implicit readiness signal — an idle pod is still healthy
          # (the queue is simply empty). A minimal readiness check on
          # /health confirms the metrics listener is up, which doubles
          # as evidence the tokio runtime is alive.
          readinessProbe:
            httpGet:
              path: /health
              port: 9100
            # Generous initialDelaySeconds so a slow DB connect during
            # startup (Postgres acquire_timeout is 10s) can't race the
            # first probe. failureThreshold=6 keeps the pod from
            # flapping if a single scrape times out during a long
            # chain step.
            initialDelaySeconds: 15
            periodSeconds: 10
            timeoutSeconds: 3
            failureThreshold: 6
          resources:
            requests:
              cpu: 100m
              memory: 768Mi
            limits:
              cpu: "4"
              # Analysis tasks (f00) run the native-level HRRR decode
              # (~530 MB GRIB2 + wgrib2 working set) on top of 2 concurrent
              # forecast tasks. 2 Gi OOM'd reliably in the 13 h after
              # Stream A cutover. 3 Gi leaves room for the analysis
              # wgrib2 peak without eliminating the forecast-lane
              # parallelism headroom.
              memory: 3Gi
          securityContext:
            allowPrivilegeEscalation: false
            runAsNonRoot: true
            runAsUser: 65534
            capabilities:
              drop:
                - ALL
            seccompProfile:
              type: RuntimeDefault
          volumeMounts:
            - name: data
              mountPath: /data
      volumes:
        - name: data
          nfs:
            server: 10.0.19.103
            path: /data