Graham McIntire
db57b3a1c7
Item 1 — .sgrid dense binary scalar format replacing chunked gzip+msgpack - New rust/prop_grid_rs/src/sgrid.rs: magic SGRD, same header layout as .pgrid, 20-field cell-major f32 body, write_atomic (tmp+rename, NFS-safe) - New lib/microwaveprop/weather/sgrid.ex: Elixir reader modeled on pgrid.ex (pread single-cell reads, bounds-filtered viewport reads, NaN→nil sentinel) - ScalarFile updated to prefer .sgrid reads, chunked .mp.gz as fallback - Pipeline writes .sgrid alongside existing chunked format (all three paths) Item 2 — HRDPS decode-once + rotated-pole index, restore 0.125° resolution - New rust/prop_grid_rs/src/rotated_pole.rs: CF-convention geographic→rotated transform, OnceLock-cached GDS params parsed from wgrib2 -grid, precomputed Vec<u32> lookup table mapping target cells to native grid indices - Native decode path in decoder.rs: wgrib2 -no_header -order we:sn -bin (raw f32 dump, ~0.32 s/message) + indexing via lookup table - HRDPS_STEP: 0.5° → 0.125° (4× finer, ~57k Canadian cells vs ~3.5k) Item 3 — k8s memory limits: 3Gi → 1.5Gi (per-task grid footprint: ~200-400 MB HashMap → ~18 MB dense planes) Item 4 — CLAUDE.md and profiles_file.ex documentation drift fixed: .pgrid primary, .mp.gz legacy, .sgrid added, write_atomic protocol doc, cleanup gaps reorganized, 'Only f00 is persisted' corrected to f00..f48
163 lines
6.9 KiB
YAML
163 lines
6.9 KiB
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_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"
|
||
# Was "1": a decoded grid used to be ~95 k nested HashMaps
|
||
# (~200-400 MB per in-flight task), so two concurrent tasks
|
||
# plus the wgrib2 working set crossed the 3 Gi limit. The
|
||
# dense `FieldGrid` representation stores the same data as
|
||
# ~48 f32 planes (~18 MB), and the profile artifact is now a
|
||
# flat f32 write instead of an rmpv tree + gzip -9, so the
|
||
# per-task footprint is roughly an order of magnitude lower.
|
||
#
|
||
# Raising to 3 first and holding the memory limit; drop the
|
||
# limit only after observing steady-state RSS at this
|
||
# parallelism (one knob per deploy).
|
||
- name: PROP_GRID_RS_PARALLELISM
|
||
value: "3"
|
||
# 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: "5"
|
||
- 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"
|
||
# After the dense-grid rewrite (commit 63f25a96) the
|
||
# per-task grid footprint dropped from ~200-400 MB of
|
||
# nested HashMaps to ~18 MB of dense f32 planes.
|
||
# PARALLELISM went 1 → 3 in the same commit. The remaining
|
||
# large term is the f00 native-level decode (~530 MB GRIB2
|
||
# + wgrib2 working set). 1.5Gi leaves headroom for three
|
||
# concurrent chain steps plus one analysis step.
|
||
memory: 1.5Gi
|
||
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
|