browsertrix/chart/templates/operators.yaml
Ilya Kreymer fb3d88291f
Background Jobs Work (#1321)
Fixes #1252 

Supports a generic background job system, with two background jobs,
CreateReplicaJob and DeleteReplicaJob.
- CreateReplicaJob runs on new crawls, uploads, profiles and updates the
`replicas` array with the info about the replica after the job succeeds.
- DeleteReplicaJob deletes the replica.
- Both jobs are created from the new `replica_job.yaml` template. The
CreateReplicaJob sets secrets for primary storage + replica storage,
while DeleteReplicaJob only needs the replica storage.
- The job is processed in the operator when the job is finalized
(deleted), which should happen immediately when the job is done, either
because it succeeds or because the backoffLimit is reached (currently
set to 3).
- /jobs/ api lists all jobs using a paginated response, including filtering and sorting
- /jobs/<job id> returns details for a particular job
- tests: nightly tests updated to check create + delete replica jobs for crawls as well as uploads, job api endpoints
- tests: also fixes to timeouts in nightly tests to avoid crawls finishing too quickly.

---------
Co-authored-by: Tessa Walsh <tessa@bitarchivist.net>
2023-11-02 13:02:17 -07:00

138 lines
3.1 KiB
YAML

---
apiVersion: metacontroller.k8s.io/v1alpha1
kind: CompositeController
metadata:
name: crawljobs-operator
spec:
generateSelector: false
resyncPeriodSeconds: {{ .Values.operator_resync_seconds | default 10 }}
parentResource:
apiVersion: btrix.cloud/v1
resource: crawljobs
childResources:
- apiVersion: v1
resource: pods
updateStrategy:
method: OnDelete
- apiVersion: v1
resource: persistentvolumeclaims
updateStrategy:
method: InPlace
hooks:
sync:
webhook:
service:
namespace: {{ .Release.Namespace }}
name: {{ .Values.name }}-backend
port: {{ .Values.opPort }}
path: /op/crawls/sync
finalize:
webhook:
service:
namespace: {{ .Release.Namespace }}
name: {{ .Values.name }}-backend
port: {{ .Values.opPort }}
path: /op/crawls/finalize
customize:
webhook:
service:
namespace: {{ .Release.Namespace }}
name: {{ .Values.name }}-backend
port: {{ .Values.opPort }}
path: /op/crawls/customize
---
apiVersion: metacontroller.k8s.io/v1alpha1
kind: CompositeController
metadata:
name: profilejobs-operator
spec:
generateSelector: false
resyncPeriodSeconds: 30
parentResource:
apiVersion: btrix.cloud/v1
resource: profilejobs
childResources:
- apiVersion: v1
resource: pods
updateStrategy:
method: InPlace
hooks:
sync:
webhook:
service:
namespace: {{ .Release.Namespace }}
name: {{ .Values.name }}-backend
port: {{ .Values.opPort }}
path: /op/profilebrowsers/sync
---
apiVersion: metacontroller.k8s.io/v1alpha1
kind: DecoratorController
metadata:
name: cron-crawljobs-operator
spec:
resyncPeriodSeconds: 30
resources:
- apiVersion: batch/v1
resource: jobs
labelSelector:
matchLabels:
role: scheduled-crawljob
attachments:
- apiVersion: btrix.cloud/v1
resource: crawljobs
updateStrategy:
method: InPlace
hooks:
sync:
webhook:
service:
namespace: {{ .Release.Namespace }}
name: {{ .Values.name }}-backend
port: {{ .Values.opPort }}
path: /op/cronjob/sync
customize:
webhook:
service:
namespace: {{ .Release.Namespace }}
name: {{ .Values.name }}-backend
port: {{ .Values.opPort }}
path: /op/cronjob/customize
---
apiVersion: metacontroller.k8s.io/v1alpha1
kind: DecoratorController
metadata:
name: background-job-operator
spec:
resyncPeriodSeconds: 30
resources:
- apiVersion: batch/v1
resource: jobs
labelSelector:
matchLabels:
role: background-job
hooks:
sync:
webhook:
service:
namespace: {{ .Release.Namespace }}
name: {{ .Values.name }}-backend
port: {{ .Values.opPort }}
path: /op/backgroundjob/sync
finalize:
webhook:
service:
namespace: {{ .Release.Namespace }}
name: {{ .Values.name }}-backend
port: {{ .Values.opPort }}
path: /op/backgroundjob/finalize