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
+15 -2
View File
@@ -345,6 +345,16 @@ func gitOptions(token string) (fetchOptions git.FetchOptions, pullOptions git.Pu
return fetchOptions, pullOptions
}
// staleRefreshErr reports why a failed refresh must abort: the resolve and
// checkout that follow are local and succeed on a cancelled context, which
// would hand back the cached revision as if it were fresh.
func staleRefreshErr(ctx context.Context, err error) error {
if err == nil || errors.Is(err, git.NoErrAlreadyUpToDate) {
return nil
}
return ctx.Err()
}
// NewGitCloneExecutor creates an executor to clone git repos
func NewGitCloneExecutor(input NewGitCloneExecutorInput) common.Executor {
return func(ctx context.Context) error {
@@ -385,7 +395,7 @@ func NewGitCloneExecutor(input NewGitCloneExecutorInput) common.Executor {
}
if !isOfflineMode {
err = r.Fetch(&fetchOptions)
err = r.FetchContext(ctx, &fetchOptions)
if err != nil && !errors.Is(err, git.NoErrAlreadyUpToDate) {
return err
}
@@ -454,9 +464,12 @@ func NewGitCloneExecutor(input NewGitCloneExecutorInput) common.Executor {
switch {
case !isOfflineMode && !shallow:
// In shallow mode the depth-limited fetch above already advanced the ref.
if err = w.Pull(&pullOptions); err != nil && err != git.NoErrAlreadyUpToDate {
if err = w.PullContext(ctx, &pullOptions); err != nil && !errors.Is(err, git.NoErrAlreadyUpToDate) {
logger.Debugf("Unable to pull %s: %v", refName, err)
}
if err := staleRefreshErr(ctx, err); err != nil {
return err
}
case isOfflineMode && reused:
reusedMsg = " (reused in offline mode)"
}