unkin-agent
d48125d699
A g10k-code job wedged in ContainerCreating on a failed CephFS mount and never reached a terminal condition, so it stayed in the CronJob active list and `concurrencyPolicy: Forbid` skipped every following minute. No Puppet code reached the estate for 6 days, and the piled-up missed slots crossed the controller 100-slot cap into `TooManyMissedTimes`. The CronJob carried no deadlines at all. - Cap a job at `activeDeadlineSeconds: 300` on the Job spec, so a hang is failed as `DeadlineExceeded` and drops out of the active list (healthy runs take 16-18s). - Set `startingDeadlineSeconds: 200`, bounding missed-schedule look-back to ~3 slots so the count cannot reach 100. Reviewed-on: #490 Co-authored-by: unkin-agent <unkin-agent@unkin.net> Co-committed-by: unkin-agent <unkin-agent@unkin.net>
72 lines
2.2 KiB
YAML
72 lines
2.2 KiB
YAML
---
|
|
apiVersion: batch/v1
|
|
kind: CronJob
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/component: r10k-code
|
|
app.kubernetes.io/instance: puppetserver
|
|
app.kubernetes.io/name: puppetserver
|
|
app.kubernetes.io/version: 8.8.0
|
|
name: g10k-code
|
|
namespace: puppet
|
|
spec:
|
|
schedule: "*/1 * * * *"
|
|
startingDeadlineSeconds: 200
|
|
concurrencyPolicy: Forbid
|
|
successfulJobsHistoryLimit: 3
|
|
failedJobsHistoryLimit: 3
|
|
jobTemplate:
|
|
spec:
|
|
activeDeadlineSeconds: 300
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/component: g10k-code
|
|
app.kubernetes.io/instance: puppetserver
|
|
app.kubernetes.io/name: puppetserver
|
|
app.kubernetes.io/version: 8.8.0
|
|
spec:
|
|
hostname: g10k-code
|
|
imagePullSecrets: null
|
|
containers:
|
|
- name: g10k-code
|
|
image: git.unkin.net/unkin/almalinux9-g10k:20260606
|
|
imagePullPolicy: IfNotPresent
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 128Mi
|
|
limits:
|
|
cpu: 200m
|
|
memory: 256Mi
|
|
command:
|
|
- /bin/sh
|
|
- -c
|
|
args:
|
|
- |
|
|
set -e
|
|
echo "Cloning r10k config repository..."
|
|
git clone https://git.unkin.net/unkin/puppet-r10k.git /tmp/r10k-config
|
|
echo "Running g10k..."
|
|
/usr/bin/g10k -config /tmp/r10k-config/r10k.yaml
|
|
envFrom: null
|
|
env: []
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- all
|
|
runAsGroup: 999
|
|
runAsNonRoot: true
|
|
runAsUser: 999
|
|
volumeMounts:
|
|
- mountPath: /etc/puppetlabs/code/
|
|
name: puppet-code-volume
|
|
restartPolicy: OnFailure
|
|
securityContext:
|
|
fsGroup: 999
|
|
volumes:
|
|
- name: puppet-code-volume
|
|
persistentVolumeClaim:
|
|
claimName: puppetserver-code-shared
|