mirror of
https://github.com/alexandrev/xslt-lab.git
synced 2026-09-13 08:43:16 +00:00
claude-code
4e1f3ffdac
The backend container runs three JVMs — Saxon 12, Saxon 9.6 and Xalan — whose -Xmx values add up to 512 MB, inside a container limited to 256Mi. The limit was half the heap the JVMs believed they had, so the kernel was killing the container: OOMKilled twice a day on the 16th and 17th of August, five times a day on the 18th and 19th, and 81 users in 24 hours got "transform service unavailable" instead of a result. Before each kill the serial collector spends hours in continuous full GC, which is why three of the five pods sat pinned at exactly 0.5 CPU — their limit — around the clock, and why XSLT 2.0's p95 was 5.5s against 0.7s for the other two engines. Those limits were never in the chart to begin with: the backend deployment has never rendered a resources block, values.resources.backend was declared and unused, and the live numbers came from a manual kubectl patch that an ArgoCD sync would have silently dropped. So the chart now owns them, with room for what actually runs in there. The CPU request moves 10m -> 250m as well: against real usage of 500m the HPA read utilisation in the thousands of percent and the deployment sat permanently at maxReplicas, unable to signal anything. And the backend gets minReplicas 2, for the reason the frontend already learnt. The other half is the mid-keystroke problem again, one level down. Gating the automatic run on well-formedness took the error rate from 54% to 24%, but a stylesheet whose XPath is half-typed is perfectly good XML, so it still went to the backend and still came back as a compile error. A day of logs is mostly that, keystroke by keystroke: 'current()/..[@N' then '[@Na' then '[@Name', and "Required attribute 'select' is missing" 65 times on a single line. So the gate now also declines to send an expression that is provably unfinished — a required attribute that is absent, an empty value, a quote or bracket still open, a trailing token that cannot end an expression. Facts about the text, not guesses at intent: there are twice as many tests for what it must leave alone as for what it catches, including every template the app itself ships. It is skipped above 64KB, where a document was pasted rather than typed, and as before it only holds back the automatic run — "Run it anyway" is always there. Finally, the error classifier learns the rest of what was sitting in "other": Xalan's "Syntax error in '<expr>'" is the stylesheet's XPath, not the input. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018HnUwBeXv6PCTEzRpFoMSU
119 lines
3.2 KiB
YAML
119 lines
3.2 KiB
YAML
replicaCount:
|
|
frontend: 1
|
|
backend: 1
|
|
|
|
image:
|
|
frontend:
|
|
repository: xslt-playground-frontend
|
|
tag: "latest"
|
|
pullPolicy: IfNotPresent
|
|
backend:
|
|
repository: xslt-playground-backend
|
|
tag: "latest"
|
|
pullPolicy: IfNotPresent
|
|
|
|
service:
|
|
frontend:
|
|
type: ClusterIP
|
|
port: 80
|
|
backend:
|
|
type: ClusterIP
|
|
port: 8000
|
|
|
|
ingress:
|
|
enabled: true
|
|
className: ""
|
|
annotations: {}
|
|
hosts:
|
|
- host: xslt.local
|
|
paths:
|
|
- path: /
|
|
pathType: Prefix
|
|
tls: []
|
|
|
|
resources:
|
|
frontend: {}
|
|
# The backend container runs three JVMs side by side (Saxon 12, Saxon 9.6 and
|
|
# Xalan — see backend/start.sh), whose -Xmx values alone add up to 512 MB,
|
|
# before metaspace, thread stacks and the Go server. The limit has to leave
|
|
# room for all of it or the kernel kills the container mid-transform.
|
|
backend:
|
|
requests:
|
|
# Sized so the HPA reads something meaningful: with a 10m request the
|
|
# utilisation ratio is permanently in the thousands of percent and the
|
|
# deployment sits pinned at maxReplicas.
|
|
cpu: 250m
|
|
memory: 384Mi
|
|
limits:
|
|
cpu: "1"
|
|
memory: 1Gi
|
|
|
|
hpa:
|
|
frontend:
|
|
enabled: true
|
|
minReplicas: 1
|
|
maxReplicas: 5
|
|
targetCPUUtilizationPercentage: 80
|
|
backend:
|
|
enabled: true
|
|
# Two, so a single evicted or restarting pod never leaves the app with no
|
|
# backend at all — the frontend learnt this the hard way.
|
|
minReplicas: 2
|
|
maxReplicas: 5
|
|
targetCPUUtilizationPercentage: 80
|
|
|
|
firebase:
|
|
enabled: true
|
|
secretName: firebase-config
|
|
credentialsKey: service-account.json
|
|
configKey: firebase-config.json
|
|
credentialsMountPath: /var/secrets/firebase
|
|
|
|
storage:
|
|
enabled: true
|
|
databaseUrl: postgres://postgres:postgres@db/xslt?sslmode=disable
|
|
|
|
frontend:
|
|
# URL used by the frontend to reach the backend. Defaults to the
|
|
# internal service URL when empty.
|
|
backendUrl: ""
|
|
# Optional Google Analytics measurement ID
|
|
googleAnalyticsId: ""
|
|
# Optional Microsoft Clarity project ID
|
|
clarityId: ""
|
|
# Optional n8n webhook URL for in-app feedback form
|
|
feedbackWebhookUrl: ""
|
|
|
|
# Content for the optional ads.txt file served by the frontend
|
|
adsTxt: ""
|
|
|
|
# Prometheus metrics + Grafana dashboard
|
|
metrics:
|
|
enabled: true
|
|
# Dedicated internal port where the Go backend exposes /metrics.
|
|
# Not routed through the public ingress.
|
|
backendPort: 9100
|
|
# nginx-prometheus-exporter sidecar for the frontend.
|
|
frontend:
|
|
exporter:
|
|
image: nginx/nginx-prometheus-exporter:1.3.0
|
|
port: 9113
|
|
# Internal-only nginx stub_status endpoint scraped by the exporter.
|
|
stubStatusPort: 8081
|
|
serviceMonitor:
|
|
enabled: true
|
|
interval: 30s
|
|
scrapeTimeout: 10s
|
|
# Label the kube-prometheus-stack Prometheus selects ServiceMonitors by.
|
|
releaseLabel: kube-prom-stack
|
|
dashboard:
|
|
enabled: true
|
|
# Namespace the dashboard ConfigMap is created in. The kube-prometheus-stack
|
|
# Grafana dashboard sidecar only watches its own namespace (observability),
|
|
# so the ConfigMap must live there to be auto-loaded. Empty = release namespace.
|
|
namespace: observability
|
|
# Label the Grafana dashboard sidecar selects ConfigMaps by.
|
|
label: grafana_dashboard
|
|
labelValue: "1"
|
|
|