gitea/act_runner
1
0
Fork 0
mirror of https://gitea.com/gitea/act_runner.git synced 2026-07-27 09:57:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: clean service containers after failed job setup (#1066)

Browse Source 
Fixes https://gitea.com/gitea/runner/issues/659

Docker teardown was chained with `Then`, which stops on the previous step's error and on a cancelled context, so the first failure orphaned everything downstream. A volume that is still in use, or a flaky daemon, left the service containers and the job network behind — matching the reports in the issue, where the leaks show up after failed or overloaded jobs.

Cleanup is now straight-line and best-effort: every step runs regardless of what failed before it, and the errors are joined. Two things follow from that:

- Service containers are removed before the job volumes, since a service can hold one via `--volumes-from` in its options. The network stays last, once every container has detached.
- Only job container and volume errors are returned. Service and network errors are logged, as before, because `stopJobContainer()` also runs as the pre-flight step of job start, where a network cleanup error must not abort the job.

The nil check on `rc.JobContainer` is kept, but it is not the leak reporters are hitting: `container.NewContainer` never returns nil in the docker build, so cleanup with no job container is only reachable in the `WITHOUT_DOCKER` stub.

Addresses https://gitea.com/gitea/runner/pulls/1066#issuecomment-1239073.

Not covered here: the `buildx_buildkit_*` volumes reported in the issue are created by buildx inside the job, not by the runner, so no runner-side teardown removes them.

---------

Co-authored-by: silverwind <2021+silverwind@noreply.gitea.com>
Co-authored-by: silverwind <me@silverwind.io>
Reviewed-on: https://gitea.com/gitea/runner/pulls/1066
Reviewed-by: silverwind <2021+silverwind@noreply.gitea.com>
This commit is contained in:
bircni
2026-07-24 16:36:09 +00:00
parent c9c4957e38
commit 26f9fb12af
2 changed files with 77 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
act/runner/run_context.go
View File

@@ -454,37 +454,7 @@ func (rc *RunContext) startJobContainer() common.Executor {
rc.ServiceContainers = append(rc.ServiceContainers, c)
}
rc.cleanUpJobContainer = func(ctx context.Context) error {
reuseJobContainer := func(ctx context.Context) bool {
return rc.Config.ReuseContainers
}
if rc.JobContainer != nil {
return rc.JobContainer.Remove().IfNot(reuseJobContainer).
Then(container.NewDockerVolumeRemoveExecutor(rc.jobContainerName(), false)).IfNot(reuseJobContainer).
Then(container.NewDockerVolumeRemoveExecutor(rc.jobContainerName()+"-env", false)).IfNot(reuseJobContainer).
Then(func(ctx context.Context) error {
if len(rc.ServiceContainers) > 0 {
logger.Infof("Cleaning up services for job %s", rc.JobName)
if err := rc.stopServiceContainers()(ctx); err != nil {
logger.Errorf("Error while cleaning services: %v", err)
}
}
if createAndDeleteNetwork {
// clean network if it has been created by act
// if using service containers
// it means that the network to which containers are connecting is created by `runner`,
// so, we should remove the network at last.
logger.Infof("Cleaning up network for job %s, and network name is: %s", rc.JobName, networkName)
if err := container.NewDockerNetworkRemoveExecutor(networkName)(ctx); err != nil {
logger.Errorf("Error while cleaning network: %v", err)
}
}
return nil
})(ctx)
}
return nil
}
rc.cleanUpJobContainer = rc.cleanupJobResources(networkName, createAndDeleteNetwork)
// For Gitea, `jobContainerNetwork` should be the same as `networkName`
jobContainerNetwork := networkName
@@ -539,6 +509,41 @@ func (rc *RunContext) startJobContainer() common.Executor {
}
}
// cleanupJobResources removes everything the job created, continuing past failures.
// Only job container and volume errors are returned, the rest are logged.
func (rc *RunContext) cleanupJobResources(networkName string, createAndDeleteNetwork bool) common.Executor {
return func(ctx context.Context) error {
logger := common.Logger(ctx)
removeJobContainer := rc.JobContainer != nil && !rc.Config.ReuseContainers
var errs []error
if removeJobContainer {
errs = append(errs, rc.JobContainer.Remove()(ctx))
}
if len(rc.ServiceContainers) > 0 {
logger.Infof("Cleaning up services for job %s", rc.JobName)
if err := rc.stopServiceContainers()(ctx); err != nil {
logger.Errorf("Error while cleaning services: %v", err)
}
}
if removeJobContainer {
// after the containers using them, services can hold these via `--volumes-from`
name := rc.jobContainerName()
errs = append(errs,
container.NewDockerVolumeRemoveExecutor(name, false)(ctx),
container.NewDockerVolumeRemoveExecutor(name+"-env", false)(ctx))
}
if createAndDeleteNetwork {
// last, once every container has detached
logger.Infof("Cleaning up network for job %s, and network name is: %s", rc.JobName, networkName)
if err := container.NewDockerNetworkRemoveExecutor(networkName)(ctx); err != nil {
logger.Errorf("Error while cleaning network: %v", err)
}
}
return errors.Join(errs...)
}
}
func (rc *RunContext) execJobContainer(cmd []string, env map[string]string, user, workdir string) common.Executor { //nolint:unparam // pre-existing issue from nektos/act
return func(ctx context.Context) error {
return rc.JobContainer.Exec(cmd, env, user, workdir)(ctx)