feat(spark-analytics): add 7 CronJobs, results webview, and LiChess staging demo

Adds CronJobs and headless driver Services for GameLengthJob, ColorAdvantageJob,
EloDistributionJob, TimeControlJob, DailyActivityJob, RatingMismatchJob, and
TerminationStatsJob. All suspended by default; scheduled Saturday mornings.

Adds spark-analytics-webview: a stdlib Python HTTP server (ConfigMap + Deployment
+ Service) that reads CSV output from the spark-analytics-output PVC and renders
13 datasets as browsable HTML tables. Disabled (replicas=0) in base.

Staging overlay enables the webview (replicas=1), exposes it via Ingress at
spark-results-st.nowchess.janis-eccarius.de, and sets NOWCHESS_PGN_PATH on all
CronJobs to the Lichess Jan-2013 rated standard PGN dump for demo runs without
a NowChess database.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Janis Eccarius
2026-06-21 15:01:25 +02:00
parent 2bc911ab81
commit a190d50a09
5 changed files with 1011 additions and 0 deletions
+713
View File
@@ -74,6 +74,139 @@ spec:
port: 44777
targetPort: 44777
---
apiVersion: v1
kind: Service
metadata:
name: spark-game-length-driver
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
clusterIP: None
selector:
app: spark-game-length
ports:
- name: driver
port: 44167
targetPort: 44167
- name: blockmanager
port: 44777
targetPort: 44777
---
apiVersion: v1
kind: Service
metadata:
name: spark-color-advantage-driver
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
clusterIP: None
selector:
app: spark-color-advantage
ports:
- name: driver
port: 44167
targetPort: 44167
- name: blockmanager
port: 44777
targetPort: 44777
---
apiVersion: v1
kind: Service
metadata:
name: spark-elo-distribution-driver
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
clusterIP: None
selector:
app: spark-elo-distribution
ports:
- name: driver
port: 44167
targetPort: 44167
- name: blockmanager
port: 44777
targetPort: 44777
---
apiVersion: v1
kind: Service
metadata:
name: spark-time-control-driver
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
clusterIP: None
selector:
app: spark-time-control
ports:
- name: driver
port: 44167
targetPort: 44167
- name: blockmanager
port: 44777
targetPort: 44777
---
apiVersion: v1
kind: Service
metadata:
name: spark-daily-activity-driver
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
clusterIP: None
selector:
app: spark-daily-activity
ports:
- name: driver
port: 44167
targetPort: 44167
- name: blockmanager
port: 44777
targetPort: 44777
---
apiVersion: v1
kind: Service
metadata:
name: spark-rating-mismatch-driver
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
clusterIP: None
selector:
app: spark-rating-mismatch
ports:
- name: driver
port: 44167
targetPort: 44167
- name: blockmanager
port: 44777
targetPort: 44777
---
apiVersion: v1
kind: Service
metadata:
name: spark-termination-stats-driver
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
clusterIP: None
selector:
app: spark-termination-stats
ports:
- name: driver
port: 44167
targetPort: 44167
- name: blockmanager
port: 44777
targetPort: 44777
---
apiVersion: batch/v1
kind: CronJob
metadata:
@@ -407,3 +540,583 @@ spec:
- name: spark-output
persistentVolumeClaim:
claimName: spark-analytics-output
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: spark-game-length
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
schedule: "0 2 * * 6"
suspend: true
concurrencyPolicy: Forbid
jobTemplate:
spec:
backoffLimit: 1
template:
metadata:
labels:
app: spark-game-length
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
serviceAccountName: spark-analytics
restartPolicy: OnFailure
securityContext:
fsGroup: 185
imagePullSecrets:
- name: ghcr-pull-secret
containers:
- name: spark-driver
image: ghcr.io/now-chess/now-chess-systems/analytics:latest
command:
- /opt/spark/bin/spark-submit
- --master
- spark://spark-master:7077
- --conf
- spark.executor.instances=1
- --conf
- spark.executor.cores=1
- --conf
- spark.executor.memory=512m
- --conf
- spark.driver.memory=512m
- --conf
- spark.driver.host=spark-game-length-driver
- --conf
- spark.driver.port=44167
- --conf
- spark.blockManager.port=44777
- --class
- de.nowchess.analytics.GameLengthJob
- file:///app/analytics.jar
- /spark-output/game-length
env:
- name: NOWCHESS_JDBC_URL
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_URL
- name: NOWCHESS_DB_USER
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_USER
- name: NOWCHESS_DB_PASS
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_PASSWORD
resources:
requests:
cpu: 50m
memory: 64Mi
limits:
cpu: "1"
memory: 1Gi
volumeMounts:
- name: spark-output
mountPath: /spark-output
volumes:
- name: spark-output
persistentVolumeClaim:
claimName: spark-analytics-output
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: spark-color-advantage
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
schedule: "0 3 * * 6"
suspend: true
concurrencyPolicy: Forbid
jobTemplate:
spec:
backoffLimit: 1
template:
metadata:
labels:
app: spark-color-advantage
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
serviceAccountName: spark-analytics
restartPolicy: OnFailure
securityContext:
fsGroup: 185
imagePullSecrets:
- name: ghcr-pull-secret
containers:
- name: spark-driver
image: ghcr.io/now-chess/now-chess-systems/analytics:latest
command:
- /opt/spark/bin/spark-submit
- --master
- spark://spark-master:7077
- --conf
- spark.executor.instances=1
- --conf
- spark.executor.cores=1
- --conf
- spark.executor.memory=512m
- --conf
- spark.driver.memory=512m
- --conf
- spark.driver.host=spark-color-advantage-driver
- --conf
- spark.driver.port=44167
- --conf
- spark.blockManager.port=44777
- --class
- de.nowchess.analytics.ColorAdvantageJob
- file:///app/analytics.jar
- /spark-output/color-advantage
env:
- name: NOWCHESS_JDBC_URL
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_URL
- name: NOWCHESS_DB_USER
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_USER
- name: NOWCHESS_DB_PASS
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_PASSWORD
resources:
requests:
cpu: 50m
memory: 64Mi
limits:
cpu: "1"
memory: 1Gi
volumeMounts:
- name: spark-output
mountPath: /spark-output
volumes:
- name: spark-output
persistentVolumeClaim:
claimName: spark-analytics-output
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: spark-elo-distribution
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
schedule: "0 4 * * 6"
suspend: true
concurrencyPolicy: Forbid
jobTemplate:
spec:
backoffLimit: 1
template:
metadata:
labels:
app: spark-elo-distribution
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
serviceAccountName: spark-analytics
restartPolicy: OnFailure
securityContext:
fsGroup: 185
imagePullSecrets:
- name: ghcr-pull-secret
containers:
- name: spark-driver
image: ghcr.io/now-chess/now-chess-systems/analytics:latest
command:
- /opt/spark/bin/spark-submit
- --master
- spark://spark-master:7077
- --conf
- spark.executor.instances=1
- --conf
- spark.executor.cores=1
- --conf
- spark.executor.memory=512m
- --conf
- spark.driver.memory=512m
- --conf
- spark.driver.host=spark-elo-distribution-driver
- --conf
- spark.driver.port=44167
- --conf
- spark.blockManager.port=44777
- --class
- de.nowchess.analytics.EloDistributionJob
- file:///app/analytics.jar
- /spark-output/elo-distribution
env:
- name: NOWCHESS_JDBC_URL
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_URL
- name: NOWCHESS_DB_USER
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_USER
- name: NOWCHESS_DB_PASS
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_PASSWORD
resources:
requests:
cpu: 50m
memory: 64Mi
limits:
cpu: "1"
memory: 1Gi
volumeMounts:
- name: spark-output
mountPath: /spark-output
volumes:
- name: spark-output
persistentVolumeClaim:
claimName: spark-analytics-output
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: spark-time-control
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
schedule: "0 5 * * 6"
suspend: true
concurrencyPolicy: Forbid
jobTemplate:
spec:
backoffLimit: 1
template:
metadata:
labels:
app: spark-time-control
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
serviceAccountName: spark-analytics
restartPolicy: OnFailure
securityContext:
fsGroup: 185
imagePullSecrets:
- name: ghcr-pull-secret
containers:
- name: spark-driver
image: ghcr.io/now-chess/now-chess-systems/analytics:latest
command:
- /opt/spark/bin/spark-submit
- --master
- spark://spark-master:7077
- --conf
- spark.executor.instances=1
- --conf
- spark.executor.cores=1
- --conf
- spark.executor.memory=512m
- --conf
- spark.driver.memory=512m
- --conf
- spark.driver.host=spark-time-control-driver
- --conf
- spark.driver.port=44167
- --conf
- spark.blockManager.port=44777
- --class
- de.nowchess.analytics.TimeControlJob
- file:///app/analytics.jar
- /spark-output/time-control
env:
- name: NOWCHESS_JDBC_URL
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_URL
- name: NOWCHESS_DB_USER
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_USER
- name: NOWCHESS_DB_PASS
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_PASSWORD
resources:
requests:
cpu: 50m
memory: 64Mi
limits:
cpu: "1"
memory: 1Gi
volumeMounts:
- name: spark-output
mountPath: /spark-output
volumes:
- name: spark-output
persistentVolumeClaim:
claimName: spark-analytics-output
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: spark-daily-activity
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
schedule: "0 6 * * 6"
suspend: true
concurrencyPolicy: Forbid
jobTemplate:
spec:
backoffLimit: 1
template:
metadata:
labels:
app: spark-daily-activity
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
serviceAccountName: spark-analytics
restartPolicy: OnFailure
securityContext:
fsGroup: 185
imagePullSecrets:
- name: ghcr-pull-secret
containers:
- name: spark-driver
image: ghcr.io/now-chess/now-chess-systems/analytics:latest
command:
- /opt/spark/bin/spark-submit
- --master
- spark://spark-master:7077
- --conf
- spark.executor.instances=1
- --conf
- spark.executor.cores=1
- --conf
- spark.executor.memory=512m
- --conf
- spark.driver.memory=512m
- --conf
- spark.driver.host=spark-daily-activity-driver
- --conf
- spark.driver.port=44167
- --conf
- spark.blockManager.port=44777
- --class
- de.nowchess.analytics.DailyActivityJob
- file:///app/analytics.jar
env:
- name: NOWCHESS_JDBC_URL
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_URL
- name: NOWCHESS_DB_USER
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_USER
- name: NOWCHESS_DB_PASS
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_PASSWORD
resources:
requests:
cpu: 50m
memory: 64Mi
limits:
cpu: "1"
memory: 1Gi
volumeMounts:
- name: spark-output
mountPath: /spark-output
volumes:
- name: spark-output
persistentVolumeClaim:
claimName: spark-analytics-output
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: spark-rating-mismatch
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
schedule: "0 7 * * 6"
suspend: true
concurrencyPolicy: Forbid
jobTemplate:
spec:
backoffLimit: 1
template:
metadata:
labels:
app: spark-rating-mismatch
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
serviceAccountName: spark-analytics
restartPolicy: OnFailure
securityContext:
fsGroup: 185
imagePullSecrets:
- name: ghcr-pull-secret
containers:
- name: spark-driver
image: ghcr.io/now-chess/now-chess-systems/analytics:latest
command:
- /opt/spark/bin/spark-submit
- --master
- spark://spark-master:7077
- --conf
- spark.executor.instances=1
- --conf
- spark.executor.cores=1
- --conf
- spark.executor.memory=512m
- --conf
- spark.driver.memory=512m
- --conf
- spark.driver.host=spark-rating-mismatch-driver
- --conf
- spark.driver.port=44167
- --conf
- spark.blockManager.port=44777
- --class
- de.nowchess.analytics.RatingMismatchJob
- file:///app/analytics.jar
- /spark-output/rating-mismatch
env:
- name: NOWCHESS_JDBC_URL
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_URL
- name: NOWCHESS_DB_USER
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_USER
- name: NOWCHESS_DB_PASS
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_PASSWORD
resources:
requests:
cpu: 50m
memory: 64Mi
limits:
cpu: "1"
memory: 1Gi
volumeMounts:
- name: spark-output
mountPath: /spark-output
volumes:
- name: spark-output
persistentVolumeClaim:
claimName: spark-analytics-output
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: spark-termination-stats
labels:
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
schedule: "0 8 * * 6"
suspend: true
concurrencyPolicy: Forbid
jobTemplate:
spec:
backoffLimit: 1
template:
metadata:
labels:
app: spark-termination-stats
app.kubernetes.io/name: spark-analytics
app.kubernetes.io/part-of: nowchess
spec:
serviceAccountName: spark-analytics
restartPolicy: OnFailure
securityContext:
fsGroup: 185
imagePullSecrets:
- name: ghcr-pull-secret
containers:
- name: spark-driver
image: ghcr.io/now-chess/now-chess-systems/analytics:latest
command:
- /opt/spark/bin/spark-submit
- --master
- spark://spark-master:7077
- --conf
- spark.executor.instances=1
- --conf
- spark.executor.cores=1
- --conf
- spark.executor.memory=512m
- --conf
- spark.driver.memory=512m
- --conf
- spark.driver.host=spark-termination-stats-driver
- --conf
- spark.driver.port=44167
- --conf
- spark.blockManager.port=44777
- --class
- de.nowchess.analytics.TerminationStatsJob
- file:///app/analytics.jar
- /spark-output/termination-stats
env:
- name: NOWCHESS_JDBC_URL
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_URL
- name: NOWCHESS_DB_USER
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_USER
- name: NOWCHESS_DB_PASS
valueFrom:
secretKeyRef:
name: ncs-db-secrets
key: STORE_DB_PASSWORD
resources:
requests:
cpu: 50m
memory: 64Mi
limits:
cpu: "1"
memory: 1Gi
volumeMounts:
- name: spark-output
mountPath: /spark-output
volumes:
- name: spark-output
persistentVolumeClaim:
claimName: spark-analytics-output