Graham McIntire
b80878056d
Extracts the memory-hostile HRRR fetch → decode → score pipeline for
forecast hours 1–18 into a separate Rust service (`prop-grid-rs`).
Elixir retains f00 with its native-duct + NEXRAD + commercial-link
enrichment; Rust handles the other 18 steps per hourly chain.
Hand-off via a new `grid_tasks` table (`FOR UPDATE SKIP LOCKED` claim
from Rust, Postgrex `NOTIFY propagation_ready` back to Elixir). Rust
writes the same on-disk score-grid format Elixir already uses, to the
same `/data/scores` NFS tree. Phase 1 ships in shadow mode with
PROP_SCORES_DIR=/data/scores_shadow.
Rust crate layout at `rust/prop_grid_rs/` (1:1 module parity with the
Elixir source it ports):
- grid, region, band_config, scores_file, sounding_params
- scorer: all 10 factors + composite. Matches the Elixir scorer
byte-for-byte across 115 golden-fixture samples (5 scenarios
× 23 bands).
- decoder: wgrib2 subprocess + Fortran-record lola-binary parser
- fetcher: HRRR URL derivation + idx cache (1h TTL) + 8-way
parallel byte-range downloads with 429/5xx retry
- pipeline: end-to-end chain step, f00 rejected at the boundary
- db: sqlx grid_tasks claim/complete + propagation_ready NOTIFY
- bin/worker: tokio main loop, JSON logs, SIGTERM-safe
91 Rust tests + clippy -D warnings clean. 2,158 Elixir tests green.
Elixir additions:
- `GridTaskEnqueuer` seeds fh=1..18 rows from
`PropagationGridWorker.seed_chain/0`
- `NotifyListener` LISTEN → warm `ScoreCache` → PubSub fan-out
- `ShadowComparator` diffs prod vs shadow `.ntms` bodies
- `mix rust.golden` task writes the Rust-side golden fixture
k8s: new `deployment-grid-rs.yaml` pinned to talos5 (32 GB NUC) via
`prop-grid-rs=primary` nodeSelector + `workload=grid-rs:NoSchedule`
toleration, 512 Mi limit, sharing the existing NFS `/data` mount.
The plan document is at `plans/vivid-hatching-quail.md` (local to my
workstation); phases 2 (cutover) and 3 (talos5 concurrency tuning)
follow after 72h of shadow-mode parity.
94 lines
3 KiB
YAML
94 lines
3 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: prop-grid-rs
|
|
namespace: prop
|
|
# Phase 1 (shadow) default: write to /data/scores_shadow so Elixir keeps
|
|
# owning the live /data/scores tree. Flip PROP_SCORES_DIR to /data/scores
|
|
# at cutover after ShadowComparator shows < 0.5 mean delta for 72h.
|
|
spec:
|
|
replicas: 1
|
|
minReadySeconds: 5
|
|
strategy:
|
|
type: RollingUpdate
|
|
rollingUpdate:
|
|
maxSurge: 0
|
|
maxUnavailable: 1
|
|
selector:
|
|
matchLabels:
|
|
app: prop-grid-rs
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: prop-grid-rs
|
|
tier: grid-rs
|
|
spec:
|
|
# Pin to talos5 — the 32 GB NUC with NVMe. The worker peaks at ~500 Mi
|
|
# steady-state but benefits from local NVMe for the NFS scores-dir
|
|
# writes (faster fsync) and from never sharing the node with a hot
|
|
# Elixir pod. Label talos5 with `prop-grid-rs=primary` and taint it
|
|
# `workload=grid-rs:NoSchedule` to enforce this.
|
|
nodeSelector:
|
|
prop-grid-rs: "primary"
|
|
tolerations:
|
|
- key: workload
|
|
operator: Equal
|
|
value: grid-rs
|
|
effect: NoSchedule
|
|
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
|
|
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"
|
|
- name: PROP_SCORES_DIR
|
|
value: "/data/scores_shadow"
|
|
- name: RUST_LOG
|
|
value: "info"
|
|
- name: PROP_GRID_RS_PG_CONNS
|
|
value: "4"
|
|
envFrom:
|
|
- secretRef:
|
|
name: prop-secrets
|
|
# No HTTP surface. 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).
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 128Mi
|
|
limits:
|
|
cpu: "4"
|
|
memory: 512Mi
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
runAsNonRoot: true
|
|
runAsUser: 65534
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
volumeMounts:
|
|
- name: data
|
|
mountPath: /data
|
|
volumes:
|
|
- name: data
|
|
nfs:
|
|
server: 10.0.15.103
|
|
path: /data
|