ink/act_runner
1
1
Fork 0
mirror of https://gitea.com/gitea/act_runner.git synced 2026-06-10 02:54:23 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: clean up job network and container when container start fails (#986)

Browse Source 
The teardown that removes a job's per-job network and container runs as a `Finally` on the step pipeline in `newJobExecutor`, which only executes after a successful start. When the start itself fails (e.g. a `docker cp` error from a buggy daemon), that `Finally` is skipped, so the network and container leak until Docker's address pool is exhausted and later jobs can no longer create networks.

This tears them down in `startContainer` when the start returns an error, reusing the existing `cleanUpJobContainer` teardown.

Exposed by the daemon regression in https://gitea.com/gitea/runner/issues/981, where every failed `docker cp` leaked a per-job network.

---
This PR was written with the help of Claude Opus 4.7

Reviewed-on: https://gitea.com/gitea/runner/pulls/986
Reviewed-by: Nicolas <bircni@icloud.com>
Co-authored-by: silverwind <me@silverwind.io>
Co-committed-by: silverwind <me@silverwind.io>
This commit is contained in:
silverwind
2026-05-21 15:19:01 +00:00
committed by Nicolas
parent 7b5ebe9618
commit b30204aa94
2 changed files with 77 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
act/runner/run_context.go
View File

@@ -601,10 +601,34 @@ func (rc *RunContext) interpolateOutputs() common.Executor {
func (rc *RunContext) startContainer() common.Executor {
return func(ctx context.Context) error {
var err error
if rc.IsHostEnv(ctx) {
return rc.startHostEnvironment()(ctx)
err = rc.startHostEnvironment()(ctx)
} else {
err = rc.startJobContainer()(ctx)
}
return rc.startJobContainer()(ctx)
if err != nil {
// The job executor's teardown only runs after a successful start, so a failed
// start would otherwise leak the per-job network and container.
rc.cleanupFailedStart(ctx)
}
return err
}
}
func (rc *RunContext) cleanupFailedStart(ctx context.Context) {
if rc.cleanUpJobContainer == nil {
return
}
cleanCtx := ctx
if ctx.Err() != nil {
// the start likely failed because ctx was cancelled, detach so teardown still runs
var cancel context.CancelFunc
cleanCtx, cancel = context.WithTimeout(common.WithLogger(context.Background(), common.Logger(ctx)), time.Minute)
defer cancel()
}
if err := rc.cleanUpJobContainer(cleanCtx); err != nil {
common.Logger(ctx).Errorf("Error while cleaning up after failed container start for job %s: %v", rc.JobName, err)
}
}