fix: bound blocking calls and stop failing silently (#1174)

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>
This commit is contained in:
silverwind
2026-08-19 11:13:21 +00:00
committed by silverwind
parent 3f70822458
commit bc8161c673
21 changed files with 422 additions and 63 deletions
+13 -7
View File
@@ -88,14 +88,14 @@ func (cr *containerReference) connectToNetwork(name string, aliases []string) co
}
}
// supportsContainerImagePlatform returns true if the underlying Docker server
// API version is 1.41 and beyond
func supportsContainerImagePlatform(ctx context.Context, cli client.APIClient) bool {
// supportsContainerImagePlatform reports whether the Docker server API version
// is 1.41 and beyond
func supportsContainerImagePlatform(ctx context.Context, cli client.APIClient) (bool, error) {
ver, err := cli.ServerVersion(ctx, client.ServerVersionOptions{})
if err != nil {
common.Logger(ctx).Panicf("Failed to get Docker API Version: %s", err)
return false, fmt.Errorf("get docker API version: %w", err)
}
return versions.GreaterThanOrEqualTo(ver.APIVersion, "1.41")
return versions.GreaterThanOrEqualTo(ver.APIVersion, "1.41"), nil
}
func (cr *containerReference) Create(capAdd, capDrop []string) common.Executor {
@@ -682,11 +682,17 @@ func (cr *containerReference) create(capAdd, capDrop []string) common.Executor {
}
var platSpecs *specs.Platform
if cr.input.Platform != "" && supportsContainerImagePlatform(ctx, cr.cli) {
platSpecs, err = parsePlatform(cr.input.Platform)
if cr.input.Platform != "" {
// Dropping the platform silently would build for the host arch.
supported, err := supportsContainerImagePlatform(ctx, cr.cli)
if err != nil {
return err
}
if supported {
if platSpecs, err = parsePlatform(cr.input.Platform); err != nil {
return err
}
}
}
hostConfig := &container.HostConfig{