browsertrix/chart/app-templates/crawl_cron_job.yaml
Ilya Kreymer 3cd52342a7
Remove Crawl Workflow Configmaps (#1894)
Fixes #1893 

- Removes crawl workflow-scoped configmaps, and replaces with operator-controlled
per-crawl configmaps that only contain the json config passed to Browsertrix
Crawler (as a volume).
- Other configmap settings replaced are replaced the custom CrawlJob options
(mostly already were, just added profile_filename and storage_filename)
- Cron jobs also updated to create CrawlJob without relying on configmaps,
querying the db for additional settings.
- The `userid` associated with cron jobs is set to the user that last modified
 the schedule of the crawl, rather than whomever last modified the workflow
- Various functions that deal with updating configmaps have been removed,
including in migrations.
- New migration 0029 added to remove all crawl workflow configmaps
2024-06-28 15:25:23 -07:00

35 lines
689 B
YAML

apiVersion: batch/v1
kind: CronJob
metadata:
name: "{{ id }}"
labels:
btrix.crawlconfig: "{{ cid }}"
btrix.org: "{{ oid }}"
{% if userid %}
btrix.userid: "{{ userid }}"
{% endif %}
role: "cron-job"
spec:
concurrencyPolicy: Forbid
successfulJobsHistoryLimit: 0
failedJobsHistoryLimit: 2
schedule: "{{ schedule }}"
jobTemplate:
metadata:
labels:
btrix.crawlconfig: "{{ cid }}"
role: "scheduled-crawljob"
spec:
suspend: true
template:
spec:
restartPolicy: Never
containers:
- name: noop
image: "docker.io/tianon/true"
imagePullPolicy: IfNotPresent