Skip to content

Instantly share code, notes, and snippets.

@tommeramber

tommeramber/EDA-CronJobs.yaml

Created June 11, 2025 08:16
Show Gist options
  • Save tommeramber/08ad6ac3af85face1982aa9a3526bbc9 to your computer and use it in GitHub Desktop.
Save tommeramber/08ad6ac3af85face1982aa9a3526bbc9 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
EDA-CronJobs.yaml
# detect-nfs-stale
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: detect-nfs-stale
namespace: openshift-monitoring
spec:
concurrencyPolicy: Allow
failedJobsHistoryLimit: 1
schedule: ’45 * * * *’
successfulJobsHistoryLimit: 3
suspend: false
jobTemplate:
spec:
template:
spec:
containers:
- command:
- /bin/sh
args:
- /opt/scripts/detect-nfs-stale.sh
image: {{ .Values.image }} # https://medium.com/@tamber/mini-howto-the-ultimate-container-tool-image-for-openshift-8e338094822e
imagePullPolicy: IfNotPresent
name: detect-nfs-stale
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /opt/scripts
name: detect-nfs-stale-scripts
env:
- name: CONTAINER_TOOLS_IMAGE
value: {{ .Values.image }} # https://medium.com/@tamber/mini-howto-the-ultimate-container-tool-image-for-openshift-8e338094822e
volumes:
- configMap:
name: detect-nfs-stale-scripts
name: detect-nfs-stale-scripts
dnsPolicy: ClusterFirst
restartPolicy: OnFailure
schedulerName: default-scheduler
securityContext: {}
serviceAccount: detect-nfs-stale
serviceAccountName: detect-nfs-stale
terminationGracePeriodSeconds: 30
---
apiVersion: v1
kind: ConfigMap
metadata:
name: detect-nfs-stale-scripts
namespace: openshift-monitoring
data:
detect-nfs-stale.sh: |
NODES=$(oc get nodes|grep -v master|grep -v infra|awk ’{print $1}’|grep -v NAME)
for i in $NODES; do
echo "" > /tmp/job.yaml
echo "apiVersion: batch/v1" >> /tmp/job.yaml
echo "kind: CronJob" >> /tmp/job.yaml
echo "metadata:" >> /tmp/job.yaml
echo " name: detect-stale-nfs-$i" >> /tmp/job.yaml
echo " namespace: openshift-monitoring" >> /tmp/job.yaml
echo "spec:" >> /tmp/job.yaml
echo " concurrencyPolicy: Allow" >> /tmp/job.yaml
echo " failedJobsHistoryLimit: 3" >> /tmp/job.yaml
echo " schedule: ’50 * * * *’" >> /tmp/job.yaml
echo " successfulJobsHistoryLimit: 3" >> /tmp/job.yaml
echo " suspend: false" >> /tmp/job.yaml
echo " jobTemplate:" >> /tmp/job.yaml
echo " spec:" >> /tmp/job.yaml
echo " template:" >> /tmp/job.yaml
echo " spec:" >> /tmp/job.yaml
echo " containers:" >> /tmp/job.yaml
echo " - command: " >> /tmp/job.yaml
echo " - /bin/bash" >> /tmp/job.yaml
echo " args:" >> /tmp/job.yaml
echo " - /opt/scripts/detect-nfs-delete-job-script.sh" >> /tmp/job.yaml
echo " image: ${CONTAINER_TOOLS_IMAGE}" >> /tmp/job.yaml
echo " imagePullPolicy: IfNotPresent" >> /tmp/job.yaml
echo " name: detect-stale-nfs" >> /tmp/job.yaml
echo " volumeMounts:" >> /tmp/job.yaml
echo " - mountPath: /opt/scripts" >> /tmp/job.yaml
echo " name: detect-nfs-delete-job-script" >> /tmp/job.yaml
echo " env:" >> /tmp/job.yaml
echo " - name: NODE" >> /tmp/job.yaml
echo " value: $i" >> /tmp/job.yaml
echo " volumes:" >> /tmp/job.yaml
echo " - configMap:" >> /tmp/job.yaml
echo " name: detect-nfs-delete-job-script" >> /tmp/job.yaml
echo " name: detect-nfs-delete-job-script" >> /tmp/job.yaml
echo " serviceAccount: detect-nfs-stale" >> /tmp/job.yaml
echo " serviceAccountName: detect-nfs-stale" >> /tmp/job.yaml
echo " restartPolicy: Never">>/tmp/job.yaml
echo " nodeSelector:" >> /tmp/job.yaml
echo " kubernetes.io/hostname: $i" >> /tmp/job.yaml
echo "" >> /tmp/job.yaml
cat /tmp/job.yaml
oc apply -f /tmp/job.yaml
done
---
# node-health-check
apiVersion: batch/v1
kind: CronJob
metadata:
name: node-health-check
namespace: openshift-monitoring
spec:
concurrencyPolicy: Allow
failedJobsHistoryLimit: 1
schedule: ’25 * * * *’
successfulJobsHistoryLimit: 3
suspend: false
jobTemplate:
spec:
template:
spec:
containers:
- command:
- /bin/sh
args:
- /opt/scripts/node-health.sh
image: {{ .Values.image }} # https://medium.com/@tamber/mini-howto-the-ultimate-container-tool-image-for-openshift-8e338094822e
imagePullPolicy: IfNotPresent
name: node-health-check
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /opt/scripts
name: node-health-scripts
env:
- name: CONTAINER_TOOLS_IMAGE
value: {{ .Values.image }} # https://medium.com/@tamber/mini-howto-the-ultimate-container-tool-image-for-openshift-8e338094822e
volumes:
- configMap:
name: node-health-scripts
name: node-health-scripts
dnsPolicy: ClusterFirst
restartPolicy: OnFailure
schedulerName: default-scheduler
securityContext: {}
serviceAccount: node-health-check
serviceAccountName: node-health-check
terminationGracePeriodSeconds: 30
---
apiVersion: v1
kind: ConfigMap
metadata:
name: node-health-scripts
namespace: openshift-monitoring
data:
node-health.sh: |
NODES=$(oc get nodes|grep -v master|grep -v infra|awk ’{print $1}’|grep -v NAME)
for i in $NODES; do
echo "" > /tmp/job.yaml
echo "apiVersion: batch/v1" >> /tmp/job.yaml
echo "kind: CronJob" >> /tmp/job.yaml
echo "metadata:" >> /tmp/job.yaml
echo " name: node-health-check-$i" >> /tmp/job.yaml
echo " namespace: openshift-monitoring" >> /tmp/job.yaml
echo "spec:" >> /tmp/job.yaml
echo " concurrencyPolicy: Allow" >> /tmp/job.yaml
echo " failedJobsHistoryLimit: 3" >> /tmp/job.yaml
echo " schedule: ’30 * * * *’" >> /tmp/job.yaml
echo " successfulJobsHistoryLimit: 3" >> /tmp/job.yaml
echo " suspend: false" >> /tmp/job.yaml
echo " jobTemplate:" >> /tmp/job.yaml
echo " spec:" >> /tmp/job.yaml
echo " template:" >> /tmp/job.yaml
echo " spec:" >> /tmp/job.yaml
echo " containers:" >> /tmp/job.yaml
echo " - command: " >> /tmp/job.yaml
echo " - /bin/bash" >> /tmp/job.yaml
echo " args:" >> /tmp/job.yaml
echo " - /opt/scripts/delete-job-script.sh" >> /tmp/job.yaml
echo " image: ${CONTAINER_TOOLS_IMAGE}" >> /tmp/job.yaml
echo " imagePullPolicy: IfNotPresent" >> /tmp/job.yaml
echo " name: node-health-check" >> /tmp/job.yaml
echo " volumeMounts:" >> /tmp/job.yaml
echo " - mountPath: /opt/scripts" >> /tmp/job.yaml
echo " name: delete-job-script" >> /tmp/job.yaml
echo " env:" >> /tmp/job.yaml
echo " - name: NODE" >> /tmp/job.yaml
echo " value: $i" >> /tmp/job.yaml
echo " volumes:" >> /tmp/job.yaml
echo " - configMap:" >> /tmp/job.yaml
echo " name: delete-job-script" >> /tmp/job.yaml
echo " name: delete-job-script" >> /tmp/job.yaml
echo " serviceAccount: node-health-check" >> /tmp/job.yaml
echo " serviceAccountName: node-health-check" >> /tmp/job.yaml
echo " restartPolicy: Never">>/tmp/job.yaml
echo " nodeSelector:" >> /tmp/job.yaml
echo " kubernetes.io/hostname: $i" >> /tmp/job.yaml
echo "" >> /tmp/job.yaml
cat /tmp/job.yaml
oc apply -f /tmp/job.yaml
done
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment