mirror of
https://gitea.com/gitea/act_runner.git
synced 2026-08-20 12:06:21 +00:00
silverwindandsilverwind
bc8161c673
Jobs occasionally go silent ([example](https://gitea.com/gitea/runner/actions/runs/805045/jobs/1055123)) mid-run and Gitea reaped them after `ZOMBIE_TASK_TIMEOUT`, with no error in the log. This contains a number of related fixes, all with full test coverage: 1. Bound every RPC to Gitea with a timeout, a stalled report otherwise parked logs and heartbeats for the whole job. 2. Cap `runner.fetch_timeout` at that ceiling. 3. Let only the daemon loop close its own channel, the race panicked the process. 4. Stop the job on any terminal server result, not just `RESULT_CANCELLED`. 5. Report that result instead of relabelling it as cancelled. 6. Log reporting failures once at each end of an outage instead of discarding them. 7. Clamp the acknowledged log index, a too-large ack panicked on a slice bound. 8. Stop reading server health from a `FetchTask` deadline, it marked the runner healthy and reset the error backoff on a timeout. 9. Return an error from the Docker version probe instead of a `logrus` panic. 10. Pass the context to go-git's fetch and pull. 11. Fail the clone when a refresh dies on a cancelled context. 12. Set `terminationGracePeriodSeconds` in the Kubernetes examples. Also contains a deprecation fix for goreleaser. Reviewed-on: https://gitea.com/gitea/runner/pulls/1174 Reviewed-by: bircni <bircni@icloud.com> Co-authored-by: silverwind <me@silverwind.io>
98 lines
2.9 KiB
YAML
98 lines
2.9 KiB
YAML
# StatefulSet variant of the dind example.
|
|
#
|
|
# Unlike the Deployment, a StatefulSet gives each replica a stable identity and,
|
|
# via volumeClaimTemplates, its own persistent volume. That means every runner
|
|
# pod keeps its own `.runner` registration file across restarts and reschedules,
|
|
# so it re-attaches to the server instead of trying to register again.
|
|
apiVersion: v1
|
|
data:
|
|
# The registration token can be obtained from the web UI, API or command-line.
|
|
# You can also set a pre-defined global runner registration token for the Gitea instance via
|
|
# `GITEA_RUNNER_REGISTRATION_TOKEN`/`GITEA_RUNNER_REGISTRATION_TOKEN_FILE` environment variable.
|
|
token: << base64 encoded registration token >>
|
|
kind: Secret
|
|
metadata:
|
|
name: runner-secret
|
|
type: Opaque
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: StatefulSet
|
|
metadata:
|
|
labels:
|
|
app: runner
|
|
name: runner
|
|
spec:
|
|
serviceName: runner
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: runner
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: runner
|
|
spec:
|
|
restartPolicy: Always
|
|
terminationGracePeriodSeconds: 10800 # keep above runner.shutdown_timeout, see README
|
|
volumes:
|
|
- name: docker-socket
|
|
emptyDir: {}
|
|
initContainers:
|
|
- name: docker
|
|
image: docker:28.2.2-dind
|
|
securityContext:
|
|
privileged: true
|
|
volumeMounts:
|
|
- name: docker-socket
|
|
mountPath: /var/run
|
|
# Keeps the images pulled for jobs across restarts. Without this, the
|
|
# daemon's data root is ephemeral and every job re-pulls its images.
|
|
- name: docker-data
|
|
mountPath: /var/lib/docker
|
|
startupProbe:
|
|
exec:
|
|
command: ["/usr/bin/test", "-S", "/var/run/docker.sock"]
|
|
livenessProbe:
|
|
exec:
|
|
command: ["/usr/bin/test", "-S", "/var/run/docker.sock"]
|
|
restartPolicy: Always
|
|
containers:
|
|
- name: runner
|
|
image: gitea/runner:nightly
|
|
env:
|
|
- name: GITEA_INSTANCE_URL
|
|
value: http://gitea-http.gitea.svc.cluster.local:3000
|
|
- name: GITEA_RUNNER_REGISTRATION_TOKEN
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: runner-secret
|
|
key: token
|
|
volumeMounts:
|
|
- name: runner-data
|
|
mountPath: /data
|
|
- name: docker-socket
|
|
mountPath: /var/run
|
|
volumeClaimTemplates:
|
|
# The runner's working directory: the .runner registration file and, optionally,
|
|
# the config file.
|
|
- metadata:
|
|
name: runner-data
|
|
spec:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
resources:
|
|
requests:
|
|
storage: 1Gi
|
|
storageClassName: standard
|
|
# The Docker daemon's data root: the images pulled for jobs. Size it for the
|
|
# images you expect to cache.
|
|
- metadata:
|
|
name: docker-data
|
|
spec:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
resources:
|
|
requests:
|
|
storage: 20Gi
|
|
storageClassName: standard
|